diff --git a/.gitattributes b/.gitattributes index d5f5214f67810bec738bbb27fe8398ce6b91e8a1..962ad648a7fa1bdee55a78e9fc176023cf51bda7 100644 --- a/.gitattributes +++ b/.gitattributes @@ -37,3 +37,4 @@ tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoint-231/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoint-462/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoint-693/tokenizer.json filter=lfs diff=lfs merge=lfs -text +checkpoint-924/tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/checkpoint-924/1_AdvancedWeightedPooling/config.json b/checkpoint-924/1_AdvancedWeightedPooling/config.json new file mode 100644 index 0000000000000000000000000000000000000000..25ff91031ae4753e5f5692b851e62a5f1183d31f --- /dev/null +++ b/checkpoint-924/1_AdvancedWeightedPooling/config.json @@ -0,0 +1,16 @@ +{ + "embed_dim": 1024, + "num_heads": 4, + "dropout": 0.1, + "bias": true, + "use_layernorm": true, + "use_MLP": true, + "MLP_h_size": 2048, + "MLP_output_size": 2048, + "use_residual_MLP": "no", + "MLP_type": "swiglu_h+swiglu_d", + "h2_size": 2048, + "ignore_cls_as_kv": true, + "expand_emb_dim_to": 0, + "compress_output_dim_to": 0 +} \ No newline at end of file diff --git a/checkpoint-924/1_AdvancedWeightedPooling/pytorch_model.bin b/checkpoint-924/1_AdvancedWeightedPooling/pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..cc02d659ce2eb9dc750a079f3b7aecbcee2ce191 --- /dev/null +++ b/checkpoint-924/1_AdvancedWeightedPooling/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7c7804224f238e0703165303043ec0dc5972aacff73b383d8a35fed881cdf2b +size 83965726 diff --git a/checkpoint-924/README.md b/checkpoint-924/README.md new file mode 100644 index 0000000000000000000000000000000000000000..e54c4763135f94899704e1e3ddc85a9251ff87c5 --- /dev/null +++ b/checkpoint-924/README.md @@ -0,0 +1,1881 @@ +--- +tags: +- sentence-transformers +- sentence-similarity +- feature-extraction +- generated_from_trainer +- dataset_size:147810 +- loss:MatryoshkaLoss +- loss:CachedGISTEmbedLoss +base_model: BAAI/bge-m3 +widget: +- source_sentence: if we could vibrate at the natural frequency of air could we "phase" + through objects? + sentences: + - No. There is literally nothing about that question that makes any scientific sense. + Even if air had a "natural frequency", it does not pass through solid objects, + so there would be no reason to think a person would either. + - 'The industry is worth about £80m a year to the economy, employs about 4,000 + workers, with 105 million journeys taken in Wales each year. + + Economy Secretary Ken Skates said 2016 had been a "mixed year" with the "demise" + of some service providers. + + He told Wales'' first bus summit some communities had been left "vulnerable" and + longer-term solutions are needed. + + Mr Skates added more young people should be encouraged to travel by bus, and services + must work for both rural and urban areas. + + Between 2011 and 2014, nearly 100 subsidised bus routes were scrapped by local + councils in Wales. + + Passengers and transport providers attended Monday''s summit, which was one of + five steps the Welsh Government recommended to strengthen the industry. + + Bus coordinators have also been appointed in north and south Wales to develop + good practice. + + Mr Skates said: "It''s a tough task but I''m positive we have the expertise and + the will in Wales to deliver it. + + "I''m keen, amongst other things, to explore with others whether new legislation + can play a role in this. + + "In the meantime, of course, we will continue to support local authorities and + communities wherever possible, whether it be through taking on new services like + the T1C between Aberystwyth and Cardiff or providing further financial support + to areas affected by loss of service providers."' + - It's called [ASMR](_URL_0_) and it is not entirely understood. It can be triggered + by a varsity of stimuli and each person is different, but it is a pretty good + sensation, isn't it? +- source_sentence: Why do we get shakey? + sentences: + - 'It was the first time Prince Charles and his son Prince William have attended + the event at Edinburgh Castle. + + The annual Tattoo is currently in its 68th season. + + This year''s event recognises 2017 as being the Year of the Royal Navy and comes + ahead of the official naming of the aircraft carrier HMS Prince of Wales later + this year. + + It is also marking Scotland''s Year of History, Heritage and Archaeology with + a second "Splash of Tartan" theme. + + As well as attending the Tattoo, the royals viewed a short performance beforehand + on the forecourt at the Palace of Holyroodhouse. + + Charles, known as the Duke of Rothesay in Scotland, and William, who takes the + title the Earl of Strathearn when north of the border, attended the Tattoo around + halfway through its August run. + + This year''s performance involves a cast of more than 1,200 people from across + the globe. + + The line-up includes more than 250 pipers and drummers, five UK military bands + and the event''s first Japanese act, as well as major contingents from France, + India and the United States. + + The first Edinburgh Tattoo took place in 1950, with the first overseas regiment + taking part in 1952. + + Since then, 48 countries from across six continents have been represented at the + Tattoo. + + It attracts an annual audience of around 220,000, meaning that more than 14m people + have attended the Tattoo since it began.' + - Any particular triggers? I get something like that occasionally, but usually in + a situation like being in a very quiet house and trying not to wake people up. + - Electrolytes. Salt, magnesium, and the such... Like an engine will shudder on + Empty with no fuel. +- source_sentence: How did man discover smoking things like tobacco and marijuana? + What made those plants special to give them the idea? + sentences: + - They probably just started out by throwing random things in the fire as fuel or + to create smoke (which is great for keeping bugs away). One day someone threw + on the leaves of one particular plant and it was **awesome** so they did it again. + - Tenth Doctor This incarnation's companions include working class shop assistant + Rose Tyler (Billie Piper), medical student Martha Jones (Freema Agyeman), and + fiery temp worker Donna Noble (Catherine Tate). He eventually parts ways with + them all by the end of the 2008 series finale, "Journey's End", after which he + attempts to travel alone for the duration of the 2008–2010 specials before being + accompanied by Donna Noble's grandfather Wilfred Mott on his final adventure in + The End of Time. + - The compound was patented by Dr. Patrick Page and his team , and was invented + in 2007 by Genkyotex . +- source_sentence: when did hurricane maria occur in puerto rico + sentences: + - As of 21 March , more than 275,000 cases of COVID-19 have been reported in over + 185 countries and territories , resulting in more than 11,300 deaths and 91,000 + recoveries . + - Hurricane Maria Originating from a tropical wave, Maria became a tropical storm + on September 16, east of the Lesser Antilles. Highly favorable environmental conditions + allowed the storm to undergo explosive intensification as it approached the island + arc. The hurricane reached Category 5 strength on September 18 just before making + landfall on Dominica, becoming the first Category 5 hurricane on record to strike + the island. After weakening slightly due to crossing Dominica, Maria achieved + its peak intensity over the eastern Caribbean with maximum sustained winds of + 175 mph (280 km/h) and a pressure of 908 mbar (hPa; 26.81 inHg), making it the + tenth-most intense Atlantic hurricane on record. On September 20, an eyewall replacement + cycle took place, weakening Maria to a high-end Category 4 hurricane by the time + it struck Puerto Rico. Interaction with land further weakened the hurricane, though + it regained some strength as it moved northeast of The Bahamas. Moving slowly + to the north, Maria gradually degraded and weakened to a tropical storm on September + 28. Embedded in the westerlies, Maria accelerated toward the east and later east-northeast + over the open Atlantic, becoming extratropical on September 30 and dissipating + by October 3. + - NPR's Ari Shapiro talks with reporter Jacqueline Charles of The Miami Herald + about the end of temporary protection for Haitians. The Trump administration decided + that Haitians must go back to their home country next year, adding that the conditions + after the 2010 earthquake no longer exist. +- source_sentence: The Elder Scrolls series up until "Skyrim". + sentences: + - 'The government-appointed trust was set up after the services at Sandwell Council + were ranked "inadequate". + + Mrs Smith will head the new Sandwell Children''s Social Care Trust which is being + asked to bring "rapid improvements". + + She said she relished the opportunity of improving the lives of vulnerable children + and families in Sandwell. + + Mrs Smith added: "My job is to help build that team by challenging us all to find + the best ways to improve and innovate - and by making the trust a great place + to work." + + For more on this and other West Midlands news + + Sandwell''s children services was rated inadequate in June 2015 after another + poor rating in 2013. + + Ofsted inspectors in 2015 said the department did "not fully understand the scale + and prevalence of child sexual exploitation". + + "There are widespread and serious failures that create or leave children being + harmed or at risk of harm," the report found:. + + An Ofsted inspection last year found "positive progress" had been made. + + The council said since the announcement in October 2016 that an independent trust + would run the services, it had worked with commissioner Malcolm Newsam and the + Department for Education. + + Council Leader Steve Eling welcomed Mrs Smith''s appointment and her "wealth of + experience". + + "With the setting up of the trust, we want to build on recent improvements with + a board that will focus on providing a clear vision, be innovative and strive + to deliver rapid and sustained improvements," he said.' + - 'The Unofficial Elder Scrolls Pages had some great stuff but it''s not really + for five year olds. [Here](_URL_2_) is the main lore page and [here](_URL_0_) + is the beginning of the history. Based on previous Elder Scrolls games you will + not need to have played the previous game to enjoy them and understand the story. + You might miss out on some small references or easter eggs put in for fans though. + EDIT: _URL_1_ will most likely put together a [historical references](_URL_3_) + page for Skyrim like it did for Oblivion.' + - Game of Thrones (season 7) The seventh season of the fantasy drama television + series Game of Thrones premiered on HBO on July 16, 2017, and concluded on August + 27, 2017.[1][2][3] Unlike previous seasons that consisted of ten episodes each, + the seventh season consisted of only seven.[4] Like the previous season, it largely + consisted of original content not found in George R. R. Martin's A Song of Ice + and Fire series, while also adapting material Martin revealed to showrunners about + the upcoming novels in the series.[5] The series was adapted for television by + David Benioff and D. B. Weiss. +pipeline_tag: sentence-similarity +library_name: sentence-transformers +metrics: +- pearson_cosine +- spearman_cosine +- cosine_accuracy +model-index: +- name: SentenceTransformer based on BAAI/bge-m3 + results: + - task: + type: semantic-similarity + name: Semantic Similarity + dataset: + name: sts test + type: sts-test + metrics: + - type: pearson_cosine + value: 0.8878947010894737 + name: Pearson Cosine + - type: spearman_cosine + value: 0.9258002047273748 + name: Spearman Cosine + - task: + type: semantic-similarity + name: Semantic Similarity + dataset: + name: sts test 1024 + type: sts-test-1024 + metrics: + - type: pearson_cosine + value: 0.885149365257635 + name: Pearson Cosine + - type: spearman_cosine + value: 0.9258567760577375 + name: Spearman Cosine + - task: + type: semantic-similarity + name: Semantic Similarity + dataset: + name: sts test 512 + type: sts-test-512 + metrics: + - type: pearson_cosine + value: 0.88725994150817 + name: Pearson Cosine + - type: spearman_cosine + value: 0.9272581696465901 + name: Spearman Cosine + - task: + type: semantic-similarity + name: Semantic Similarity + dataset: + name: sts test 256 + type: sts-test-256 + metrics: + - type: pearson_cosine + value: 0.8861095686328364 + name: Pearson Cosine + - type: spearman_cosine + value: 0.9268503548030278 + name: Spearman Cosine + - task: + type: semantic-similarity + name: Semantic Similarity + dataset: + name: sts test 128 + type: sts-test-128 + metrics: + - type: pearson_cosine + value: 0.880812025351224 + name: Pearson Cosine + - type: spearman_cosine + value: 0.9247529190228797 + name: Spearman Cosine + - task: + type: semantic-similarity + name: Semantic Similarity + dataset: + name: sts test 64 + type: sts-test-64 + metrics: + - type: pearson_cosine + value: 0.8741180224496476 + name: Pearson Cosine + - type: spearman_cosine + value: 0.922292066152112 + name: Spearman Cosine + - task: + type: semantic-similarity + name: Semantic Similarity + dataset: + name: sts test 32 + type: sts-test-32 + metrics: + - type: pearson_cosine + value: 0.8553627166015102 + name: Pearson Cosine + - type: spearman_cosine + value: 0.9153789063632594 + name: Spearman Cosine + - task: + type: triplet + name: Triplet + dataset: + name: allNLI triplets + type: allNLI-triplets + metrics: + - type: cosine_accuracy + value: 0.9296875 + name: Cosine Accuracy + - task: + type: triplet + name: Triplet + dataset: + name: allNLI triplets 1024 + type: allNLI--triplets-1024 + metrics: + - type: cosine_accuracy + value: 0.9296875 + name: Cosine Accuracy + - task: + type: triplet + name: Triplet + dataset: + name: allNLI triplets 512 + type: allNLI--triplets-512 + metrics: + - type: cosine_accuracy + value: 0.9296875 + name: Cosine Accuracy + - task: + type: triplet + name: Triplet + dataset: + name: allNLI triplets 256 + type: allNLI--triplets-256 + metrics: + - type: cosine_accuracy + value: 0.9296875 + name: Cosine Accuracy + - task: + type: triplet + name: Triplet + dataset: + name: allNLI triplets 128 + type: allNLI--triplets-128 + metrics: + - type: cosine_accuracy + value: 0.9296875 + name: Cosine Accuracy + - type: cosine_accuracy + value: 0.9296875 + name: Cosine Accuracy + - task: + type: triplet + name: Triplet + dataset: + name: allNLI triplets 32 + type: allNLI--triplets-32 + metrics: + - type: cosine_accuracy + value: 0.921875 + name: Cosine Accuracy +--- + +# SentenceTransformer based on BAAI/bge-m3 + +This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) on the global_dataset dataset. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more. + +## Model Details + +### Model Description +- **Model Type:** Sentence Transformer +- **Base model:** [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) +- **Maximum Sequence Length:** 512 tokens +- **Output Dimensionality:** 1024 dimensions +- **Similarity Function:** Cosine Similarity +- **Training Dataset:** + - global_dataset + + + +### Model Sources + +- **Documentation:** [Sentence Transformers Documentation](https://sbert.net) +- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers) +- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers) + +### Full Model Architecture + +``` +SentenceTransformer( + (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: XLMRobertaModel + (1): AdvancedWeightedPooling( + (mha): MultiheadAttention( + (out_proj): NonDynamicallyQuantizableLinear(in_features=1024, out_features=1024, bias=True) + ) + (MLP): Sequential( + (0): SwiGLUBlock( + (in_proj_w): Linear(in_features=1024, out_features=2048, bias=True) + (in_proj_v): Linear(in_features=1024, out_features=2048, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + (1): SwiGLUBlock( + (in_proj_w): Linear(in_features=2048, out_features=2048, bias=True) + (in_proj_v): Linear(in_features=2048, out_features=2048, bias=True) + (dropout): Dropout(p=0.05, inplace=False) + ) + (2): Linear(in_features=2048, out_features=2048, bias=True) + ) + (layernorm): LayerNorm((2048,), eps=1e-05, elementwise_affine=True) + ) +) +``` + +## Usage + +### Direct Usage (Sentence Transformers) + +First install the Sentence Transformers library: + +```bash +pip install -U sentence-transformers +``` + +Then you can load this model and run inference. +```python +from sentence_transformers import SentenceTransformer + +# Download from the 🤗 Hub +model = SentenceTransformer("bobox/XLMRoBERTaM3-CustomPoolinMRL-v1.07-2048MLP-step1-checkpoints-tmp") +# Run inference +sentences = [ + 'The Elder Scrolls series up until "Skyrim".', + "The Unofficial Elder Scrolls Pages had some great stuff but it's not really for five year olds. [Here](_URL_2_) is the main lore page and [here](_URL_0_) is the beginning of the history. Based on previous Elder Scrolls games you will not need to have played the previous game to enjoy them and understand the story. You might miss out on some small references or easter eggs put in for fans though. EDIT: _URL_1_ will most likely put together a [historical references](_URL_3_) page for Skyrim like it did for Oblivion.", + "Game of Thrones (season 7) The seventh season of the fantasy drama television series Game of Thrones premiered on HBO on July 16, 2017, and concluded on August 27, 2017.[1][2][3] Unlike previous seasons that consisted of ten episodes each, the seventh season consisted of only seven.[4] Like the previous season, it largely consisted of original content not found in George R. R. Martin's A Song of Ice and Fire series, while also adapting material Martin revealed to showrunners about the upcoming novels in the series.[5] The series was adapted for television by David Benioff and D. B. Weiss.", +] +embeddings = model.encode(sentences) +print(embeddings.shape) +# [3, 1024] + +# Get the similarity scores for the embeddings +similarities = model.similarity(embeddings, embeddings) +print(similarities.shape) +# [3, 3] +``` + + + + + + + +## Evaluation + +### Metrics + +#### Semantic Similarity + +* Dataset: `sts-test` +* Evaluated with [EmbeddingSimilarityEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) + +| Metric | Value | +|:--------------------|:-----------| +| pearson_cosine | 0.8879 | +| **spearman_cosine** | **0.9258** | + +#### Semantic Similarity + +* Dataset: `sts-test-1024` +* Evaluated with [EmbeddingSimilarityEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) with these parameters: + ```json + { + "truncate_dim": 1024 + } + ``` + +| Metric | Value | +|:--------------------|:-----------| +| pearson_cosine | 0.8851 | +| **spearman_cosine** | **0.9259** | + +#### Semantic Similarity + +* Dataset: `sts-test-512` +* Evaluated with [EmbeddingSimilarityEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) with these parameters: + ```json + { + "truncate_dim": 512 + } + ``` + +| Metric | Value | +|:--------------------|:-----------| +| pearson_cosine | 0.8873 | +| **spearman_cosine** | **0.9273** | + +#### Semantic Similarity + +* Dataset: `sts-test-256` +* Evaluated with [EmbeddingSimilarityEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) with these parameters: + ```json + { + "truncate_dim": 256 + } + ``` + +| Metric | Value | +|:--------------------|:-----------| +| pearson_cosine | 0.8861 | +| **spearman_cosine** | **0.9269** | + +#### Semantic Similarity + +* Dataset: `sts-test-128` +* Evaluated with [EmbeddingSimilarityEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) with these parameters: + ```json + { + "truncate_dim": 128 + } + ``` + +| Metric | Value | +|:--------------------|:-----------| +| pearson_cosine | 0.8808 | +| **spearman_cosine** | **0.9248** | + +#### Semantic Similarity + +* Dataset: `sts-test-64` +* Evaluated with [EmbeddingSimilarityEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) with these parameters: + ```json + { + "truncate_dim": 64 + } + ``` + +| Metric | Value | +|:--------------------|:-----------| +| pearson_cosine | 0.8741 | +| **spearman_cosine** | **0.9223** | + +#### Semantic Similarity + +* Dataset: `sts-test-32` +* Evaluated with [EmbeddingSimilarityEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) with these parameters: + ```json + { + "truncate_dim": 32 + } + ``` + +| Metric | Value | +|:--------------------|:-----------| +| pearson_cosine | 0.8554 | +| **spearman_cosine** | **0.9154** | + +#### Triplet + +* Dataset: `allNLI-triplets` +* Evaluated with [TripletEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator) + +| Metric | Value | +|:--------------------|:-----------| +| **cosine_accuracy** | **0.9297** | + +#### Triplet + +* Dataset: `allNLI--triplets-1024` +* Evaluated with [TripletEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator) with these parameters: + ```json + { + "truncate_dim": 1024 + } + ``` + +| Metric | Value | +|:--------------------|:-----------| +| **cosine_accuracy** | **0.9297** | + +#### Triplet + +* Dataset: `allNLI--triplets-512` +* Evaluated with [TripletEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator) with these parameters: + ```json + { + "truncate_dim": 512 + } + ``` + +| Metric | Value | +|:--------------------|:-----------| +| **cosine_accuracy** | **0.9297** | + +#### Triplet + +* Dataset: `allNLI--triplets-256` +* Evaluated with [TripletEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator) with these parameters: + ```json + { + "truncate_dim": 256 + } + ``` + +| Metric | Value | +|:--------------------|:-----------| +| **cosine_accuracy** | **0.9297** | + +#### Triplet + +* Dataset: `allNLI--triplets-128` +* Evaluated with [TripletEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator) with these parameters: + ```json + { + "truncate_dim": 128 + } + ``` + +| Metric | Value | +|:--------------------|:-----------| +| **cosine_accuracy** | **0.9297** | + +#### Triplet + +* Dataset: `allNLI--triplets-128` +* Evaluated with [TripletEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator) with these parameters: + ```json + { + "truncate_dim": 64 + } + ``` + +| Metric | Value | +|:--------------------|:-----------| +| **cosine_accuracy** | **0.9297** | + +#### Triplet + +* Dataset: `allNLI--triplets-32` +* Evaluated with [TripletEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator) with these parameters: + ```json + { + "truncate_dim": 32 + } + ``` + +| Metric | Value | +|:--------------------|:-----------| +| **cosine_accuracy** | **0.9219** | + + + + + +## Training Details + +### Training Dataset + +#### global_dataset + +* Dataset: global_dataset +* Size: 147,810 training samples +* Columns: sentence1, sentence2, and negative_1 +* Approximate statistics based on the first 1000 samples: + | | sentence1 | sentence2 | negative_1 | + |:--------|:----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------| + | type | string | string | string | + | details | | | | +* Samples: + | sentence1 | sentence2 | negative_1 | + |:----------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| + | why is my earliest memory not from birth or a little after birth? | Your brain is not finished developing until further age. By the time of your birth your brain still lack the cognitive ability to store memories. It is not until further age you get some of the brain abilities that might seem obvious to you now. You should watch this video about [cognitive development among children](_URL_0_) - Its quite interesting. | It's not that children have no memory at all - it's that, as we age, our brains overwrite unnecessary information with new information. *As adults,* we often can't remember things from when we were very young - but this doesn't say anything about a child's memory when they are still that age. Some suggest there's a link between language ability and memory - such that your memory becomes clearer and stronger the more your language ability develops. Maybe that plays a role as well. | + | Why does the throat become so dry when laying in bed/sleeping? | Generally because you are sleeping with your mouth open which dries out the mucous membrane. If you don't believe me, try keeping your mouth wide open and breath in and out for an hour and tell me how your throat feels. | Your throat is sensitive. It is trying to keep out chemicals and cocks. | + | The last British survivor of the Dambusters raid has been presented with the Bristol Lord Mayor's Medal. | George "Johnny" Johnson, who is in his 90s, was just 22 when he took part in the 1943 air raid on German dams using experimental "bouncing" bombs.
The 1955 film - The Dam Busters - cemented its place as one of the most famous episodes of World War Two.
Mr Johnson, who lives in Westbury on Trym, received the honour from Lord Mayor Councillor Clare Campion-Smith.
A bomb aimer, he joined the newly formed 617 Squadron in March 1943.
On 16 May of that year he was one of the 133-strong squadron who dodged anti-aircraft fire, power cables and mountainous terrain to drop the four-tonne skipping bomb on dams in the Ruhr Valley.
Codenamed Operation Chastise, eight of the 19 planes were lost, 53 men died and three were captured.
But the young sergeant survived the mission and has now been presented with a special Lord Mayor's Medal in recognition of his "work for his country".
"We had no idea of what the target was going to be until the day of the raid, when we did the briefing," he said.
"But it... | The Cardiff-born player scored 478 tries in 487 games for Wigan, becoming the greatest try-scorer in the history of the British game.
A pioneer among black players, Boston signed for the club in 1953 and also played for Blackpool.
He attended the ceremony in Wigan's Believe Square, where the bronze statue created by sculptor Steve Winterburn is located.
Source: Rugby League Hall of Fame
The 82-year-old recently revealed he was suffering from dementia.
Wigan Warriors head coach Shaun Wane said the statue was a "fitting" tribute, adding: "Doing this for Billy is just reward for what he's done for the town of Wigan.
"Whenever anyone speaks about Wigan rugby league, they tend to mention Billy Boston."
Club director Kris Radlinski added: "His charity work over the years is unwavering, as is his support of Wigan rugby league and his love for the club and town."
More than £90,000 was raised for the statue, which included a large donation from former Wigan Athletic chairman Dave Whelan and £... | +* Loss: [MatryoshkaLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters: + ```json + { + "loss": "CachedGISTEmbedLoss", + "matryoshka_dims": [ + 2048, + 1024, + 512, + 256, + 128, + 64, + 32 + ], + "matryoshka_weights": [ + 1, + 0.35, + 0.15, + 0.05, + 0.05, + 0.033, + 0.025 + ], + "n_dims_per_step": -1 + } + ``` + +### Evaluation Dataset + +#### global_dataset + +* Dataset: global_dataset +* Size: 1,071 evaluation samples +* Columns: sentence1, sentence2, and negative_1 +* Approximate statistics based on the first 1000 samples: + | | sentence1 | sentence2 | negative_1 | + |:--------|:----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------| + | type | string | string | string | + | details | | | | +* Samples: + | sentence1 | sentence2 | negative_1 | + |:----------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| + | He was born in Carter County , Tennessee and was later moved to Arkansas . | He was born in Carter County , Tennessee and later moved to Arkansas . | He was born on December 21 , 1965 in Oxon Hill , Maryland , and attended High School in New Haven , Connecticut . | + | who sings the theme song for kath and kim | Kath & Kim The title sequence shows the main five regular characters over a white background. In Series 3, it was amended to include Epponnee-Rae and Cujo. The five regular cast members are then credited over aerial shots of suburban houses. Szubanski is credited as "Special Guest Star," despite appearing in every episode. The theme song is "The Joker," performed by Gina Riley. A re-recording of it debuted in the telemovie opening sequence and has continued into Series 4. | Portland composer and vocalist Natasha Kmeto recently dropped by KEXP's Audioasis to perform a magnificent feat of multitasking. Surreal and symphonic, Kmeto's songs stretch the boundaries of contemporary pop and EDM with percussive, intriguing compositions that sound pleasing but aren't easily forgotten. As Kmeto croons over a background of delicate digital noise in the sleek single "Inevitable," it's hard not to be moved by this intricate, confessional, visceral, meticulously produced music. SET LIST "Inevitable" Watch Natasha Kmeto's full performance on KEXP's YouTube channel. | + | who plays the yellow power ranger in the 2017 movie | Power Rangers (film) Saban's Power Rangers[4] (or simply Power Rangers) is a 2017 American superhero film based on the franchise of the same name, directed by Dean Israelite and written by John Gatins. It is the third Power Rangers film, and is a reboot. The film features the main characters of the Mighty Morphin Power Rangers television series with a new cast, starring Dacre Montgomery, Naomi Scott, RJ Cyler, Becky G, Ludi Lin, Bill Hader, Bryan Cranston, and Elizabeth Banks. | Most reviewers have awarded the action-packed epic four or five stars, with The Daily Telegraph describing it as a "Krakatoan eruption of craziness".
The film sees British actor Tom Hardy take on Mel Gibson's role as "Road Warrior" Max Rockatansky.
Charlize Theron also appears in the futuristic drama, which is set for release in the UK and US on Friday.
Also awarding it five stars, Time Out's David Ehrlich said watching director George Miller's film was like "a tornado tearing through a tea party".
He added: "Fury Road steers this macho franchise in a brilliant new direction, forging a mythical portrait about the need for female rule in a world where men need to be saved from themselves."
Jamie Graham from Total Film said the blockbuster had "some of the greatest action ever put on screen".
He wrote: "In the battle of the 2015 behemoths, the maxed-out madness of Mad Max: Fury Road sets an extraordinarily high bar - then pole-vaults clean over it and smashes the entire rig to smithereen... | +* Loss: [MatryoshkaLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters: + ```json + { + "loss": "CachedGISTEmbedLoss", + "matryoshka_dims": [ + 2048, + 1024, + 512, + 256, + 128, + 64, + 32 + ], + "matryoshka_weights": [ + 1, + 0.35, + 0.15, + 0.05, + 0.05, + 0.033, + 0.025 + ], + "n_dims_per_step": -1 + } + ``` + +### Training Hyperparameters +#### Non-Default Hyperparameters + +- `eval_strategy`: steps +- `per_device_train_batch_size`: 192 +- `per_device_eval_batch_size`: 128 +- `learning_rate`: 0.0001 +- `weight_decay`: 0.005 +- `lr_scheduler_type`: cosine_with_min_lr +- `lr_scheduler_kwargs`: {'num_cycles': 0.5, 'min_lr': 1e-05} +- `warmup_ratio`: 0.2 +- `save_safetensors`: False +- `fp16`: True +- `remove_unused_columns`: False +- `push_to_hub`: True +- `hub_model_id`: bobox/XLMRoBERTaM3-CustomPoolinMRL-v1.07-2048MLP-step1-checkpoints-tmp +- `hub_strategy`: all_checkpoints +- `hub_private_repo`: False +- `batch_sampler`: no_duplicates + +#### All Hyperparameters +
Click to expand + +- `overwrite_output_dir`: False +- `do_predict`: False +- `eval_strategy`: steps +- `prediction_loss_only`: True +- `per_device_train_batch_size`: 192 +- `per_device_eval_batch_size`: 128 +- `per_gpu_train_batch_size`: None +- `per_gpu_eval_batch_size`: None +- `gradient_accumulation_steps`: 1 +- `eval_accumulation_steps`: None +- `torch_empty_cache_steps`: None +- `learning_rate`: 0.0001 +- `weight_decay`: 0.005 +- `adam_beta1`: 0.9 +- `adam_beta2`: 0.999 +- `adam_epsilon`: 1e-08 +- `max_grad_norm`: 1.0 +- `num_train_epochs`: 3 +- `max_steps`: -1 +- `lr_scheduler_type`: cosine_with_min_lr +- `lr_scheduler_kwargs`: {'num_cycles': 0.5, 'min_lr': 1e-05} +- `warmup_ratio`: 0.2 +- `warmup_steps`: 0 +- `log_level`: passive +- `log_level_replica`: warning +- `log_on_each_node`: True +- `logging_nan_inf_filter`: True +- `save_safetensors`: False +- `save_on_each_node`: False +- `save_only_model`: False +- `restore_callback_states_from_checkpoint`: False +- `no_cuda`: False +- `use_cpu`: False +- `use_mps_device`: False +- `seed`: 42 +- `data_seed`: None +- `jit_mode_eval`: False +- `use_ipex`: False +- `bf16`: False +- `fp16`: True +- `fp16_opt_level`: O1 +- `half_precision_backend`: auto +- `bf16_full_eval`: False +- `fp16_full_eval`: False +- `tf32`: None +- `local_rank`: 0 +- `ddp_backend`: None +- `tpu_num_cores`: None +- `tpu_metrics_debug`: False +- `debug`: [] +- `dataloader_drop_last`: False +- `dataloader_num_workers`: 0 +- `dataloader_prefetch_factor`: None +- `past_index`: -1 +- `disable_tqdm`: False +- `remove_unused_columns`: False +- `label_names`: None +- `load_best_model_at_end`: False +- `ignore_data_skip`: False +- `fsdp`: [] +- `fsdp_min_num_params`: 0 +- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False} +- `tp_size`: 0 +- `fsdp_transformer_layer_cls_to_wrap`: None +- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None} +- `deepspeed`: None +- `label_smoothing_factor`: 0.0 +- `optim`: adamw_torch +- `optim_args`: None +- `adafactor`: False +- `group_by_length`: False +- `length_column_name`: length +- `ddp_find_unused_parameters`: None +- `ddp_bucket_cap_mb`: None +- `ddp_broadcast_buffers`: False +- `dataloader_pin_memory`: True +- `dataloader_persistent_workers`: False +- `skip_memory_metrics`: True +- `use_legacy_prediction_loop`: False +- `push_to_hub`: True +- `resume_from_checkpoint`: None +- `hub_model_id`: bobox/XLMRoBERTaM3-CustomPoolinMRL-v1.07-2048MLP-step1-checkpoints-tmp +- `hub_strategy`: all_checkpoints +- `hub_private_repo`: False +- `hub_always_push`: False +- `gradient_checkpointing`: False +- `gradient_checkpointing_kwargs`: None +- `include_inputs_for_metrics`: False +- `include_for_metrics`: [] +- `eval_do_concat_batches`: True +- `fp16_backend`: auto +- `push_to_hub_model_id`: None +- `push_to_hub_organization`: None +- `mp_parameters`: +- `auto_find_batch_size`: False +- `full_determinism`: False +- `torchdynamo`: None +- `ray_scope`: last +- `ddp_timeout`: 1800 +- `torch_compile`: False +- `torch_compile_backend`: None +- `torch_compile_mode`: None +- `include_tokens_per_second`: False +- `include_num_input_tokens_seen`: False +- `neftune_noise_alpha`: None +- `optim_target_modules`: None +- `batch_eval_metrics`: False +- `eval_on_start`: False +- `use_liger_kernel`: False +- `eval_use_gather_object`: False +- `average_tokens_across_devices`: False +- `prompts`: None +- `batch_sampler`: no_duplicates +- `multi_dataset_batch_sampler`: proportional + +
+ +### Training Logs +
Click to expand + +| Epoch | Step | Training Loss | global dataset loss | sts-test_spearman_cosine | sts-test-1024_spearman_cosine | sts-test-512_spearman_cosine | sts-test-256_spearman_cosine | sts-test-128_spearman_cosine | sts-test-64_spearman_cosine | sts-test-32_spearman_cosine | allNLI-triplets_cosine_accuracy | allNLI--triplets-1024_cosine_accuracy | allNLI--triplets-512_cosine_accuracy | allNLI--triplets-256_cosine_accuracy | allNLI--triplets-128_cosine_accuracy | allNLI--triplets-32_cosine_accuracy | +|:------:|:----:|:-------------:|:-------------------:|:------------------------:|:-----------------------------:|:----------------------------:|:----------------------------:|:----------------------------:|:---------------------------:|:---------------------------:|:-------------------------------:|:-------------------------------------:|:------------------------------------:|:------------------------------------:|:------------------------------------:|:-----------------------------------:| +| 0.0013 | 1 | 11.01 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0026 | 2 | 11.01 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0039 | 3 | 11.0099 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0052 | 4 | 11.0097 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0065 | 5 | 11.0099 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0078 | 6 | 11.0099 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0091 | 7 | 11.0099 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0104 | 8 | 11.0099 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0117 | 9 | 11.0099 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0130 | 10 | 11.0099 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0143 | 11 | 11.0097 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0156 | 12 | 11.0097 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0169 | 13 | 11.0097 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0182 | 14 | 11.0097 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0195 | 15 | 11.0096 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0208 | 16 | 11.0095 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0221 | 17 | 11.0096 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0234 | 18 | 11.0094 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0247 | 19 | 11.0095 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0260 | 20 | 11.0093 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0273 | 21 | 11.0091 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0286 | 22 | 11.0091 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0299 | 23 | 11.0089 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0312 | 24 | 11.0088 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0325 | 25 | 11.0087 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0338 | 26 | 11.0083 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0351 | 27 | 11.0083 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0364 | 28 | 11.0077 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0377 | 29 | 11.0075 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0390 | 30 | 11.0053 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0403 | 31 | 11.007 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0416 | 32 | 11.006 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0429 | 33 | 11.0056 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0442 | 34 | 11.0045 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0455 | 35 | 11.0035 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0468 | 36 | 11.0017 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0481 | 37 | 11.0001 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0494 | 38 | 10.9974 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0506 | 39 | 10.9955 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0519 | 40 | 10.9926 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0532 | 41 | 10.9886 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0545 | 42 | 10.983 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0558 | 43 | 10.977 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0571 | 44 | 10.9703 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0584 | 45 | 10.9547 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0597 | 46 | 10.9435 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0610 | 47 | 10.9263 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0623 | 48 | 10.9014 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0636 | 49 | 10.8546 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0649 | 50 | 10.8134 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0662 | 51 | 10.7805 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0675 | 52 | 10.7495 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0688 | 53 | 10.6997 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0701 | 54 | 10.5774 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0714 | 55 | 10.5443 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0727 | 56 | 10.4336 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0740 | 57 | 10.3595 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0753 | 58 | 10.2175 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0766 | 59 | 10.667 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0779 | 60 | 10.0476 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0792 | 61 | 10.0367 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0805 | 62 | 10.0531 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0818 | 63 | 9.7963 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0831 | 64 | 9.4349 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0844 | 65 | 9.5733 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0857 | 66 | 9.0604 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0870 | 67 | 8.7291 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0883 | 68 | 8.38 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0896 | 69 | 8.2196 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0909 | 70 | 7.8955 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0922 | 71 | 7.2905 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0935 | 72 | 7.3614 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0948 | 73 | 6.6031 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0961 | 74 | 5.9224 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0974 | 75 | 5.7627 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.0987 | 76 | 5.2194 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1 | 77 | 5.3339 | 1.7795 | 0.9061 | 0.9033 | 0.9014 | 0.8961 | 0.8942 | 0.8899 | 0.8781 | 0.9375 | 0.9453 | 0.9375 | 0.9297 | 0.9062 | 0.9141 | +| 0.1013 | 78 | 5.0749 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1026 | 79 | 4.7881 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1039 | 80 | 4.2653 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1052 | 81 | 4.0863 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1065 | 82 | 4.2845 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1078 | 83 | 3.8356 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1091 | 84 | 3.5652 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1104 | 85 | 4.1484 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1117 | 86 | 3.4415 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1130 | 87 | 3.129 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1143 | 88 | 3.5604 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1156 | 89 | 3.6036 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1169 | 90 | 2.8276 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1182 | 91 | 3.4752 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1195 | 92 | 3.3796 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1208 | 93 | 2.7567 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1221 | 94 | 3.2728 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1234 | 95 | 2.8496 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1247 | 96 | 2.6072 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1260 | 97 | 2.5959 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1273 | 98 | 2.4787 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1286 | 99 | 2.1368 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1299 | 100 | 2.233 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1312 | 101 | 2.4691 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1325 | 102 | 2.3472 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1338 | 103 | 2.0578 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1351 | 104 | 2.3437 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1364 | 105 | 2.4822 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1377 | 106 | 2.2261 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1390 | 107 | 2.3113 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1403 | 108 | 2.2162 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1416 | 109 | 2.0638 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1429 | 110 | 1.9822 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1442 | 111 | 1.9165 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1455 | 112 | 2.0633 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1468 | 113 | 1.9012 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1481 | 114 | 1.8559 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1494 | 115 | 2.1804 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1506 | 116 | 1.9728 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1519 | 117 | 1.795 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1532 | 118 | 1.5135 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1545 | 119 | 1.8776 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1558 | 120 | 1.9858 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1571 | 121 | 1.6143 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1584 | 122 | 1.7321 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1597 | 123 | 1.7272 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1610 | 124 | 1.5508 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1623 | 125 | 1.2961 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1636 | 126 | 1.6425 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1649 | 127 | 1.5193 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1662 | 128 | 1.6626 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1675 | 129 | 2.0871 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1688 | 130 | 1.5114 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1701 | 131 | 1.4414 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1714 | 132 | 1.5323 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1727 | 133 | 1.2476 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1740 | 134 | 1.4671 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1753 | 135 | 1.5581 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1766 | 136 | 1.5237 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1779 | 137 | 1.2613 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1792 | 138 | 1.2949 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1805 | 139 | 1.3592 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1818 | 140 | 1.3918 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1831 | 141 | 1.0371 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1844 | 142 | 1.5028 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1857 | 143 | 1.2347 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1870 | 144 | 1.2731 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1883 | 145 | 1.2688 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1896 | 146 | 1.3688 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1909 | 147 | 1.8782 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1922 | 148 | 1.0597 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1935 | 149 | 1.229 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1948 | 150 | 1.1233 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1961 | 151 | 1.2579 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1974 | 152 | 1.1547 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.1987 | 153 | 1.3986 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2 | 154 | 1.3071 | 0.8410 | 0.9182 | 0.9158 | 0.9152 | 0.9113 | 0.9080 | 0.9005 | 0.8867 | 0.9453 | 0.9375 | 0.9219 | 0.9062 | 0.9062 | 0.9141 | +| 0.2013 | 155 | 1.5306 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2026 | 156 | 1.0775 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2039 | 157 | 1.2954 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2052 | 158 | 1.1233 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2065 | 159 | 1.2492 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2078 | 160 | 1.2897 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2091 | 161 | 1.0752 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2104 | 162 | 1.269 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2117 | 163 | 1.1273 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2130 | 164 | 1.2208 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2143 | 165 | 1.2356 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2156 | 166 | 1.1039 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2169 | 167 | 1.0146 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2182 | 168 | 1.3097 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2195 | 169 | 1.2947 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2208 | 170 | 1.291 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2221 | 171 | 1.0295 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2234 | 172 | 1.0948 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2247 | 173 | 1.1393 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2260 | 174 | 1.0063 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2273 | 175 | 1.1769 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2286 | 176 | 1.1731 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2299 | 177 | 0.7476 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2312 | 178 | 1.022 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2325 | 179 | 0.9579 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2338 | 180 | 1.0753 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2351 | 181 | 1.2243 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2364 | 182 | 1.2154 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2377 | 183 | 0.8147 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2390 | 184 | 1.1086 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2403 | 185 | 1.0155 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2416 | 186 | 1.1898 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2429 | 187 | 1.11 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2442 | 188 | 1.3128 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2455 | 189 | 1.0642 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2468 | 190 | 0.8932 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2481 | 191 | 1.1683 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2494 | 192 | 1.0554 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2506 | 193 | 1.2186 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2519 | 194 | 1.027 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2532 | 195 | 0.799 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2545 | 196 | 1.099 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2558 | 197 | 0.7717 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2571 | 198 | 1.1011 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2584 | 199 | 1.0083 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2597 | 200 | 1.1488 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2610 | 201 | 1.0453 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2623 | 202 | 1.2942 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2636 | 203 | 1.0279 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2649 | 204 | 0.9493 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2662 | 205 | 1.2698 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2675 | 206 | 1.066 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2688 | 207 | 1.0352 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2701 | 208 | 0.8514 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2714 | 209 | 1.094 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2727 | 210 | 1.0087 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2740 | 211 | 0.9035 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2753 | 212 | 0.9475 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2766 | 213 | 0.9838 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2779 | 214 | 1.1285 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2792 | 215 | 0.7406 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2805 | 216 | 0.9309 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2818 | 217 | 0.8669 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2831 | 218 | 1.0496 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2844 | 219 | 0.9547 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2857 | 220 | 0.7442 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2870 | 221 | 0.6949 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2883 | 222 | 0.958 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2896 | 223 | 0.7528 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2909 | 224 | 0.8338 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2922 | 225 | 1.108 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2935 | 226 | 1.1113 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2948 | 227 | 0.8191 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2961 | 228 | 0.8167 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2974 | 229 | 0.8165 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.2987 | 230 | 0.8569 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3 | 231 | 0.943 | 0.6770 | 0.9229 | 0.9210 | 0.9212 | 0.9174 | 0.9159 | 0.9075 | 0.8928 | 0.9453 | 0.9531 | 0.9375 | 0.9219 | 0.8984 | 0.9141 | +| 0.3013 | 232 | 0.8316 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3026 | 233 | 0.6811 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3039 | 234 | 0.7579 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3052 | 235 | 0.8088 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3065 | 236 | 0.8242 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3078 | 237 | 0.9401 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3091 | 238 | 0.9815 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3104 | 239 | 0.6338 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3117 | 240 | 1.1544 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3130 | 241 | 0.7693 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3143 | 242 | 0.745 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3156 | 243 | 0.722 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3169 | 244 | 0.7834 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3182 | 245 | 0.8727 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3195 | 246 | 0.657 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3208 | 247 | 0.9334 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3221 | 248 | 0.9641 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3234 | 249 | 0.9539 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3247 | 250 | 0.916 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3260 | 251 | 0.7535 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3273 | 252 | 1.0744 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3286 | 253 | 0.7207 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3299 | 254 | 0.9337 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3312 | 255 | 0.7114 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3325 | 256 | 0.6995 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3338 | 257 | 0.8138 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3351 | 258 | 1.0225 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3364 | 259 | 0.9528 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3377 | 260 | 0.9607 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3390 | 261 | 0.971 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3403 | 262 | 0.7819 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3416 | 263 | 0.6537 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3429 | 264 | 1.0185 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3442 | 265 | 1.0832 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3455 | 266 | 0.533 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3468 | 267 | 0.9556 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3481 | 268 | 0.8863 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3494 | 269 | 1.0875 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3506 | 270 | 0.9424 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3519 | 271 | 0.7181 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3532 | 272 | 0.9829 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3545 | 273 | 0.8581 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3558 | 274 | 0.669 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3571 | 275 | 1.0623 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3584 | 276 | 0.8738 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3597 | 277 | 1.0384 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3610 | 278 | 0.9253 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3623 | 279 | 0.6211 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3636 | 280 | 0.7466 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3649 | 281 | 0.8584 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3662 | 282 | 0.8048 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3675 | 283 | 0.7548 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3688 | 284 | 0.7822 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3701 | 285 | 1.0389 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3714 | 286 | 0.7156 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3727 | 287 | 0.7989 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3740 | 288 | 1.0917 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3753 | 289 | 0.9575 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3766 | 290 | 0.9086 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3779 | 291 | 1.0582 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3792 | 292 | 0.879 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3805 | 293 | 0.6524 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3818 | 294 | 0.767 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3831 | 295 | 0.8842 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3844 | 296 | 0.9167 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3857 | 297 | 1.0106 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3870 | 298 | 0.8014 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3883 | 299 | 0.7783 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3896 | 300 | 0.8608 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3909 | 301 | 0.6383 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3922 | 302 | 0.9668 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3935 | 303 | 0.9447 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3948 | 304 | 0.6609 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3961 | 305 | 0.8104 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3974 | 306 | 0.7231 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.3987 | 307 | 0.853 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4 | 308 | 0.8893 | 0.6459 | 0.9304 | 0.9281 | 0.9266 | 0.9250 | 0.9175 | 0.9150 | 0.9039 | 0.9453 | 0.9453 | 0.9375 | 0.9297 | 0.9141 | 0.9141 | +| 0.4013 | 309 | 0.6674 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4026 | 310 | 0.7047 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4039 | 311 | 0.778 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4052 | 312 | 0.6232 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4065 | 313 | 0.8989 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4078 | 314 | 0.9614 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4091 | 315 | 0.9365 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4104 | 316 | 0.8101 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4117 | 317 | 0.8199 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4130 | 318 | 0.8435 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4143 | 319 | 0.9404 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4156 | 320 | 0.6967 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4169 | 321 | 0.8238 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4182 | 322 | 0.9732 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4195 | 323 | 0.6953 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4208 | 324 | 0.6633 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4221 | 325 | 0.9486 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4234 | 326 | 0.9642 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4247 | 327 | 0.7443 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4260 | 328 | 1.0133 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4273 | 329 | 1.0489 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4286 | 330 | 0.5865 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4299 | 331 | 0.7757 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4312 | 332 | 0.9716 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4325 | 333 | 0.7289 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4338 | 334 | 0.864 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4351 | 335 | 0.706 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4364 | 336 | 0.7336 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4377 | 337 | 0.6631 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4390 | 338 | 0.8824 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4403 | 339 | 0.7209 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4416 | 340 | 0.6866 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4429 | 341 | 0.8544 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4442 | 342 | 0.7208 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4455 | 343 | 0.9237 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4468 | 344 | 0.8569 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4481 | 345 | 0.9145 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4494 | 346 | 0.8172 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4506 | 347 | 0.8755 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4519 | 348 | 0.7049 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4532 | 349 | 0.8571 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4545 | 350 | 0.71 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4558 | 351 | 0.7568 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4571 | 352 | 0.5732 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4584 | 353 | 0.7801 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4597 | 354 | 0.6895 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4610 | 355 | 0.8078 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4623 | 356 | 0.9609 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4636 | 357 | 0.9131 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4649 | 358 | 0.8842 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4662 | 359 | 0.7314 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4675 | 360 | 0.7894 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4688 | 361 | 0.7982 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4701 | 362 | 0.8729 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4714 | 363 | 0.9753 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4727 | 364 | 0.6694 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4740 | 365 | 0.7563 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4753 | 366 | 0.7814 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4766 | 367 | 0.5552 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4779 | 368 | 1.0459 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4792 | 369 | 0.9098 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4805 | 370 | 0.7817 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4818 | 371 | 0.6203 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4831 | 372 | 0.7885 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4844 | 373 | 0.7767 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4857 | 374 | 0.8126 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4870 | 375 | 0.7252 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4883 | 376 | 0.8657 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4896 | 377 | 0.8491 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4909 | 378 | 0.784 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4922 | 379 | 0.6108 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4935 | 380 | 1.0215 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4948 | 381 | 0.8208 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4961 | 382 | 0.7456 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4974 | 383 | 1.0181 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.4987 | 384 | 0.8263 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5 | 385 | 0.7218 | 0.6584 | 0.9217 | 0.9193 | 0.9186 | 0.9130 | 0.9097 | 0.9105 | 0.8955 | 0.9609 | 0.9531 | 0.9375 | 0.9375 | 0.9219 | 0.9062 | +| 0.5013 | 386 | 0.6829 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5026 | 387 | 0.8304 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5039 | 388 | 0.6935 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5052 | 389 | 0.9569 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5065 | 390 | 0.7174 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5078 | 391 | 0.8543 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5091 | 392 | 0.8769 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5104 | 393 | 0.5945 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5117 | 394 | 0.7787 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5130 | 395 | 0.9674 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5143 | 396 | 0.7011 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5156 | 397 | 0.9993 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5169 | 398 | 0.6368 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5182 | 399 | 0.6236 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5195 | 400 | 0.6543 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5208 | 401 | 0.6927 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5221 | 402 | 1.1117 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5234 | 403 | 0.8847 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5247 | 404 | 0.9657 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5260 | 405 | 0.8722 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5273 | 406 | 0.7465 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5286 | 407 | 0.5488 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5299 | 408 | 0.6888 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5312 | 409 | 0.7561 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5325 | 410 | 0.5411 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5338 | 411 | 0.7663 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5351 | 412 | 1.0137 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5364 | 413 | 0.667 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5377 | 414 | 0.7111 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5390 | 415 | 0.8531 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5403 | 416 | 0.8561 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5416 | 417 | 0.612 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5429 | 418 | 0.7229 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5442 | 419 | 0.8387 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5455 | 420 | 0.7439 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5468 | 421 | 0.5846 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5481 | 422 | 0.5976 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5494 | 423 | 0.7378 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5506 | 424 | 0.8756 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5519 | 425 | 0.6755 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5532 | 426 | 0.6566 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5545 | 427 | 0.5624 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5558 | 428 | 0.5887 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5571 | 429 | 0.9906 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5584 | 430 | 0.735 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5597 | 431 | 0.8759 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5610 | 432 | 0.8514 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5623 | 433 | 0.7531 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5636 | 434 | 0.6816 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5649 | 435 | 0.8911 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5662 | 436 | 0.7555 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5675 | 437 | 0.8079 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5688 | 438 | 0.6203 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5701 | 439 | 0.6348 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5714 | 440 | 0.5986 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5727 | 441 | 0.8259 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5740 | 442 | 0.7051 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5753 | 443 | 0.591 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5766 | 444 | 0.7197 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5779 | 445 | 0.6624 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5792 | 446 | 0.9108 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5805 | 447 | 0.7401 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5818 | 448 | 0.7475 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5831 | 449 | 1.0367 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5844 | 450 | 0.819 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5857 | 451 | 0.9914 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5870 | 452 | 0.5852 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5883 | 453 | 0.8283 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5896 | 454 | 0.9477 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5909 | 455 | 0.7091 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5922 | 456 | 0.958 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5935 | 457 | 0.6203 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5948 | 458 | 0.6183 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5961 | 459 | 0.7303 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5974 | 460 | 0.9273 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.5987 | 461 | 0.7091 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6 | 462 | 0.9906 | 0.6540 | 0.9273 | 0.9263 | 0.9279 | 0.9217 | 0.9135 | 0.9083 | 0.8991 | 0.9453 | 0.9453 | 0.9453 | 0.9375 | 0.9297 | 0.9219 | +| 0.6013 | 463 | 0.9442 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6026 | 464 | 0.7803 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6039 | 465 | 0.6228 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6052 | 466 | 0.7387 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6065 | 467 | 0.9448 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6078 | 468 | 0.7838 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6091 | 469 | 0.9093 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6104 | 470 | 0.6647 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6117 | 471 | 0.5482 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6130 | 472 | 0.6356 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6143 | 473 | 0.8282 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6156 | 474 | 0.8235 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6169 | 475 | 0.6899 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6182 | 476 | 0.6827 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6195 | 477 | 0.7347 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6208 | 478 | 0.8705 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6221 | 479 | 0.8298 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6234 | 480 | 0.7419 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6247 | 481 | 1.1283 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6260 | 482 | 0.7298 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6273 | 483 | 0.8972 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6286 | 484 | 0.7502 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6299 | 485 | 0.6169 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6312 | 486 | 0.7648 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6325 | 487 | 0.8191 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6338 | 488 | 0.8094 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6351 | 489 | 0.9006 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6364 | 490 | 0.8384 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6377 | 491 | 0.6431 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6390 | 492 | 0.7507 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6403 | 493 | 1.0524 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6416 | 494 | 0.9618 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6429 | 495 | 0.8119 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6442 | 496 | 0.6538 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6455 | 497 | 0.8877 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6468 | 498 | 1.0556 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6481 | 499 | 0.6788 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6494 | 500 | 0.9637 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6506 | 501 | 0.8143 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6519 | 502 | 0.6673 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6532 | 503 | 0.8358 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6545 | 504 | 0.7588 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6558 | 505 | 0.8241 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6571 | 506 | 0.925 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6584 | 507 | 0.6336 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6597 | 508 | 0.6907 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6610 | 509 | 0.8237 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6623 | 510 | 0.828 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6636 | 511 | 0.6624 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6649 | 512 | 0.8069 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6662 | 513 | 0.566 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6675 | 514 | 1.0294 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6688 | 515 | 0.8889 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6701 | 516 | 0.6539 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6714 | 517 | 0.7279 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6727 | 518 | 0.7805 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6740 | 519 | 0.6657 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6753 | 520 | 0.5069 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6766 | 521 | 0.9967 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6779 | 522 | 0.719 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6792 | 523 | 0.4709 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6805 | 524 | 0.7421 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6818 | 525 | 0.7005 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6831 | 526 | 0.9615 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6844 | 527 | 0.7011 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6857 | 528 | 0.7021 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6870 | 529 | 0.7954 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6883 | 530 | 1.0179 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6896 | 531 | 0.6674 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6909 | 532 | 0.7634 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6922 | 533 | 0.5306 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6935 | 534 | 0.6792 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6948 | 535 | 0.8223 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6961 | 536 | 0.9346 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6974 | 537 | 0.7369 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.6987 | 538 | 0.7636 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7 | 539 | 0.632 | 0.6428 | 0.9242 | 0.9253 | 0.9243 | 0.9223 | 0.9169 | 0.9143 | 0.9123 | 0.9297 | 0.9297 | 0.9219 | 0.9141 | 0.8984 | 0.8984 | +| 0.7013 | 540 | 0.672 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7026 | 541 | 0.8924 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7039 | 542 | 0.822 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7052 | 543 | 0.4934 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7065 | 544 | 0.5939 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7078 | 545 | 0.5593 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7091 | 546 | 0.737 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7104 | 547 | 0.6734 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7117 | 548 | 0.949 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7130 | 549 | 0.9343 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7143 | 550 | 0.4662 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7156 | 551 | 0.6602 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7169 | 552 | 0.6273 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7182 | 553 | 0.665 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7195 | 554 | 0.7826 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7208 | 555 | 1.0379 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7221 | 556 | 0.5787 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7234 | 557 | 0.6639 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7247 | 558 | 0.5511 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7260 | 559 | 0.6313 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7273 | 560 | 0.7771 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7286 | 561 | 0.4077 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7299 | 562 | 0.6628 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7312 | 563 | 0.5646 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7325 | 564 | 0.5972 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7338 | 565 | 1.0101 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7351 | 566 | 0.9496 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7364 | 567 | 0.6219 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7377 | 568 | 0.7275 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7390 | 569 | 0.905 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7403 | 570 | 0.7303 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7416 | 571 | 0.6518 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7429 | 572 | 0.6725 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7442 | 573 | 0.8026 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7455 | 574 | 0.6042 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7468 | 575 | 0.7192 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7481 | 576 | 0.6089 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7494 | 577 | 0.92 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7506 | 578 | 0.81 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7519 | 579 | 0.7004 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7532 | 580 | 0.636 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7545 | 581 | 0.6059 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7558 | 582 | 0.5995 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7571 | 583 | 0.8563 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7584 | 584 | 0.6008 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7597 | 585 | 0.6576 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7610 | 586 | 0.5438 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7623 | 587 | 0.6347 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7636 | 588 | 0.6002 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7649 | 589 | 0.726 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7662 | 590 | 0.8955 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7675 | 591 | 0.5638 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7688 | 592 | 0.6315 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7701 | 593 | 0.7253 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7714 | 594 | 0.6148 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7727 | 595 | 0.4651 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7740 | 596 | 0.5097 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7753 | 597 | 0.7487 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7766 | 598 | 0.7269 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7779 | 599 | 0.8212 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7792 | 600 | 0.822 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7805 | 601 | 0.6172 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7818 | 602 | 0.6488 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7831 | 603 | 0.8928 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7844 | 604 | 0.7068 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7857 | 605 | 0.6558 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7870 | 606 | 0.6012 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7883 | 607 | 0.7806 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7896 | 608 | 0.5802 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7909 | 609 | 0.7414 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7922 | 610 | 0.6715 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7935 | 611 | 0.6947 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7948 | 612 | 0.6908 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7961 | 613 | 0.587 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7974 | 614 | 0.642 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.7987 | 615 | 0.5082 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8 | 616 | 0.6574 | 0.6188 | 0.9289 | 0.9274 | 0.9280 | 0.9270 | 0.9238 | 0.9215 | 0.9138 | 0.9453 | 0.9453 | 0.9453 | 0.9453 | 0.9297 | 0.9297 | +| 0.8013 | 617 | 0.5828 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8026 | 618 | 0.8306 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8039 | 619 | 0.6332 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8052 | 620 | 0.6006 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8065 | 621 | 0.5365 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8078 | 622 | 0.6386 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8091 | 623 | 0.684 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8104 | 624 | 0.9585 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8117 | 625 | 0.6687 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8130 | 626 | 0.7117 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8143 | 627 | 0.7052 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8156 | 628 | 0.7474 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8169 | 629 | 0.7309 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8182 | 630 | 0.6185 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8195 | 631 | 0.7055 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8208 | 632 | 0.8739 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8221 | 633 | 0.7134 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8234 | 634 | 0.7014 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8247 | 635 | 0.6907 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8260 | 636 | 0.6316 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8273 | 637 | 1.013 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8286 | 638 | 0.7022 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8299 | 639 | 0.5908 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8312 | 640 | 0.6008 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8325 | 641 | 0.6932 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8338 | 642 | 0.5935 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8351 | 643 | 0.7817 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8364 | 644 | 0.5923 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8377 | 645 | 0.5689 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8390 | 646 | 0.5501 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8403 | 647 | 0.7422 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8416 | 648 | 0.9285 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8429 | 649 | 0.6054 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8442 | 650 | 0.6312 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8455 | 651 | 0.9075 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8468 | 652 | 0.5705 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8481 | 653 | 0.9817 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8494 | 654 | 0.6819 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8506 | 655 | 0.9261 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8519 | 656 | 0.3939 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8532 | 657 | 0.7817 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8545 | 658 | 0.5585 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8558 | 659 | 0.4809 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8571 | 660 | 0.9696 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8584 | 661 | 0.5146 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8597 | 662 | 0.8808 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8610 | 663 | 0.5708 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8623 | 664 | 0.4975 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8636 | 665 | 0.5205 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8649 | 666 | 0.9157 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8662 | 667 | 0.7465 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8675 | 668 | 0.8935 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8688 | 669 | 0.7008 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8701 | 670 | 0.4422 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8714 | 671 | 0.4216 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8727 | 672 | 0.739 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8740 | 673 | 0.5473 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8753 | 674 | 0.6101 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8766 | 675 | 0.6453 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8779 | 676 | 0.6317 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8792 | 677 | 0.6964 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8805 | 678 | 0.617 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8818 | 679 | 0.4839 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8831 | 680 | 0.6383 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8844 | 681 | 0.595 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8857 | 682 | 0.5053 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8870 | 683 | 0.8086 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8883 | 684 | 0.7465 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8896 | 685 | 0.9109 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8909 | 686 | 0.8457 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8922 | 687 | 0.7412 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8935 | 688 | 0.6259 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8948 | 689 | 0.8406 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8961 | 690 | 0.5437 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8974 | 691 | 0.7564 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.8987 | 692 | 0.7379 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9 | 693 | 0.6142 | 0.6449 | 0.9256 | 0.9256 | 0.9270 | 0.9244 | 0.9201 | 0.9186 | 0.9080 | 0.9375 | 0.9453 | 0.9375 | 0.9375 | 0.9062 | 0.9062 | +| 0.9013 | 694 | 0.5799 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9026 | 695 | 0.5429 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9039 | 696 | 0.6803 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9052 | 697 | 0.5692 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9065 | 698 | 0.665 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9078 | 699 | 0.7442 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9091 | 700 | 0.5755 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9104 | 701 | 0.9233 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9117 | 702 | 0.8297 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9130 | 703 | 0.7288 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9143 | 704 | 0.8476 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9156 | 705 | 0.6464 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9169 | 706 | 0.8881 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9182 | 707 | 0.7609 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9195 | 708 | 0.6834 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9208 | 709 | 0.8218 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9221 | 710 | 0.7413 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9234 | 711 | 0.6379 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9247 | 712 | 0.8378 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9260 | 713 | 0.5754 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9273 | 714 | 0.7367 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9286 | 715 | 0.6389 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9299 | 716 | 0.4474 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9312 | 717 | 0.6341 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9325 | 718 | 0.4793 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9338 | 719 | 0.7057 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9351 | 720 | 0.9687 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9364 | 721 | 0.7017 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9377 | 722 | 0.7511 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9390 | 723 | 0.7509 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9403 | 724 | 0.5742 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9416 | 725 | 0.4425 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9429 | 726 | 0.5795 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9442 | 727 | 0.5996 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9455 | 728 | 0.6483 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9468 | 729 | 0.6893 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9481 | 730 | 0.5996 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9494 | 731 | 0.7856 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9506 | 732 | 0.7376 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9519 | 733 | 0.4758 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9532 | 734 | 0.52 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9545 | 735 | 0.6945 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9558 | 736 | 0.5963 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9571 | 737 | 0.5071 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9584 | 738 | 0.7511 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9597 | 739 | 0.4206 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9610 | 740 | 0.4838 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9623 | 741 | 0.6777 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9636 | 742 | 0.7201 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9649 | 743 | 0.5443 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9662 | 744 | 0.7611 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9675 | 745 | 0.7433 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9688 | 746 | 0.8613 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9701 | 747 | 0.4005 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9714 | 748 | 0.5841 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9727 | 749 | 0.7196 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9740 | 750 | 0.5471 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9753 | 751 | 0.7167 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9766 | 752 | 0.7802 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9779 | 753 | 0.4997 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9792 | 754 | 0.6485 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9805 | 755 | 0.7916 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9818 | 756 | 0.6993 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9831 | 757 | 0.7207 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9844 | 758 | 0.6119 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9857 | 759 | 0.7745 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9870 | 760 | 0.5289 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9883 | 761 | 0.5566 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9896 | 762 | 0.8124 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9909 | 763 | 0.632 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9922 | 764 | 0.5499 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9935 | 765 | 0.7703 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9948 | 766 | 0.5896 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9961 | 767 | 0.8109 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9974 | 768 | 0.6031 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 0.9987 | 769 | 0.5933 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0 | 770 | 0.5364 | 0.6764 | 0.9294 | 0.9289 | 0.9303 | 0.9310 | 0.9267 | 0.9216 | 0.9142 | 0.9453 | 0.9453 | 0.9453 | 0.9453 | 0.9375 | 0.9219 | +| 1.0013 | 771 | 0.5231 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0026 | 772 | 0.5183 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0039 | 773 | 0.5389 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0052 | 774 | 0.6834 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0065 | 775 | 0.5017 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0078 | 776 | 0.6083 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0091 | 777 | 0.5966 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0104 | 778 | 0.6968 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0117 | 779 | 0.6885 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0130 | 780 | 0.4656 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0143 | 781 | 0.5064 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0156 | 782 | 0.5485 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0169 | 783 | 0.6034 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0182 | 784 | 0.5317 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0195 | 785 | 0.6418 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0208 | 786 | 0.5612 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0221 | 787 | 0.6258 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0234 | 788 | 0.44 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0247 | 789 | 0.5192 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0260 | 790 | 0.7895 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0273 | 791 | 0.5412 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0286 | 792 | 0.5783 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0299 | 793 | 0.7388 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0312 | 794 | 0.5155 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0325 | 795 | 0.5151 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0338 | 796 | 0.6496 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0351 | 797 | 0.5297 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0364 | 798 | 0.7569 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0377 | 799 | 0.5531 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0390 | 800 | 0.6787 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0403 | 801 | 0.6457 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0416 | 802 | 0.5036 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0429 | 803 | 0.6496 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0442 | 804 | 0.5846 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0455 | 805 | 0.6225 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0468 | 806 | 0.4491 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0481 | 807 | 0.5019 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0494 | 808 | 0.6818 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0506 | 809 | 0.6625 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0519 | 810 | 0.3794 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0532 | 811 | 0.573 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0545 | 812 | 0.4855 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0558 | 813 | 0.5567 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0571 | 814 | 0.5972 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0584 | 815 | 0.493 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0597 | 816 | 0.4468 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0610 | 817 | 0.6582 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0623 | 818 | 0.6123 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0636 | 819 | 0.49 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0649 | 820 | 0.5702 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0662 | 821 | 0.6142 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0675 | 822 | 0.4589 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0688 | 823 | 0.6596 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0701 | 824 | 0.6645 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0714 | 825 | 0.5507 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0727 | 826 | 0.5414 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0740 | 827 | 0.4573 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0753 | 828 | 0.4044 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0766 | 829 | 0.5288 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0779 | 830 | 0.473 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0792 | 831 | 0.4046 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0805 | 832 | 0.5648 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0818 | 833 | 0.7126 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0831 | 834 | 0.5931 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0844 | 835 | 0.5465 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0857 | 836 | 0.4738 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0870 | 837 | 0.5459 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0883 | 838 | 0.4774 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0896 | 839 | 0.3781 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0909 | 840 | 0.4029 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0922 | 841 | 0.516 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0935 | 842 | 0.558 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0948 | 843 | 0.6146 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0961 | 844 | 0.6729 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0974 | 845 | 0.4631 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.0987 | 846 | 0.5166 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1 | 847 | 0.6677 | 0.7927 | 0.9202 | 0.9212 | 0.9221 | 0.9214 | 0.9179 | 0.9132 | 0.9062 | 0.9297 | 0.9297 | 0.9219 | 0.9219 | 0.9219 | 0.9141 | +| 1.1013 | 848 | 0.4758 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1026 | 849 | 0.6897 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1039 | 850 | 0.5571 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1052 | 851 | 0.7302 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1065 | 852 | 0.5423 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1078 | 853 | 0.6124 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1091 | 854 | 0.5472 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1104 | 855 | 0.6467 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1117 | 856 | 0.5758 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1130 | 857 | 0.5486 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1143 | 858 | 0.7601 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1156 | 859 | 0.48 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1169 | 860 | 0.3987 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1182 | 861 | 0.5175 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1195 | 862 | 0.546 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1208 | 863 | 0.4782 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1221 | 864 | 0.5394 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1234 | 865 | 0.5649 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1247 | 866 | 0.6247 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1260 | 867 | 0.5004 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1273 | 868 | 0.4551 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1286 | 869 | 0.4896 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1299 | 870 | 0.5858 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1312 | 871 | 0.6222 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1325 | 872 | 0.6812 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1338 | 873 | 0.6444 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1351 | 874 | 0.4732 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1364 | 875 | 0.4766 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1377 | 876 | 0.5361 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1390 | 877 | 0.6461 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1403 | 878 | 0.6055 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1416 | 879 | 0.5212 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1429 | 880 | 0.5049 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1442 | 881 | 0.6102 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1455 | 882 | 0.5279 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1468 | 883 | 0.6135 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1481 | 884 | 0.4196 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1494 | 885 | 0.634 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1506 | 886 | 0.5867 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1519 | 887 | 0.5583 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1532 | 888 | 0.4851 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1545 | 889 | 0.5288 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1558 | 890 | 0.8795 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1571 | 891 | 0.4514 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1584 | 892 | 0.5311 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1597 | 893 | 0.2328 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1610 | 894 | 0.4935 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1623 | 895 | 0.605 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1636 | 896 | 0.5583 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1649 | 897 | 0.7555 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1662 | 898 | 0.3022 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1675 | 899 | 0.4693 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1688 | 900 | 0.6197 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1701 | 901 | 0.5576 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1714 | 902 | 0.6272 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1727 | 903 | 0.6684 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1740 | 904 | 0.6356 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1753 | 905 | 0.729 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1766 | 906 | 0.5553 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1779 | 907 | 0.466 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1792 | 908 | 0.4107 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1805 | 909 | 0.8187 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1818 | 910 | 0.5597 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1831 | 911 | 0.6618 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1844 | 912 | 0.5037 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1857 | 913 | 0.6033 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1870 | 914 | 0.3695 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1883 | 915 | 0.5632 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1896 | 916 | 0.6387 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1909 | 917 | 0.4989 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1922 | 918 | 0.7159 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1935 | 919 | 0.4639 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1948 | 920 | 0.52 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1961 | 921 | 0.431 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1974 | 922 | 0.5008 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.1987 | 923 | 0.5209 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | +| 1.2 | 924 | 0.4301 | 0.6651 | 0.9258 | 0.9259 | 0.9273 | 0.9269 | 0.9248 | 0.9223 | 0.9154 | 0.9297 | 0.9297 | 0.9297 | 0.9297 | 0.9297 | 0.9219 | + +
+ +### Framework Versions +- Python: 3.11.11 +- Sentence Transformers: 4.1.0 +- Transformers: 4.51.1 +- PyTorch: 2.5.1+cu124 +- Accelerate: 1.3.0 +- Datasets: 3.5.0 +- Tokenizers: 0.21.0 + +## Citation + +### BibTeX + +#### Sentence Transformers +```bibtex +@inproceedings{reimers-2019-sentence-bert, + title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks", + author = "Reimers, Nils and Gurevych, Iryna", + booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing", + month = "11", + year = "2019", + publisher = "Association for Computational Linguistics", + url = "https://arxiv.org/abs/1908.10084", +} +``` + +#### MatryoshkaLoss +```bibtex +@misc{kusupati2024matryoshka, + title={Matryoshka Representation Learning}, + author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi}, + year={2024}, + eprint={2205.13147}, + archivePrefix={arXiv}, + primaryClass={cs.LG} +} +``` + + + + + + \ No newline at end of file diff --git a/checkpoint-924/config.json b/checkpoint-924/config.json new file mode 100644 index 0000000000000000000000000000000000000000..2d7e808503f6dfe049e22510820b28dda2b2eee2 --- /dev/null +++ b/checkpoint-924/config.json @@ -0,0 +1,27 @@ +{ + "architectures": [ + "XLMRobertaModel" + ], + "attention_probs_dropout_prob": 0.1, + "bos_token_id": 0, + "classifier_dropout": null, + "eos_token_id": 2, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 4096, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 8194, + "model_type": "xlm-roberta", + "num_attention_heads": 16, + "num_hidden_layers": 24, + "output_past": true, + "pad_token_id": 1, + "position_embedding_type": "absolute", + "torch_dtype": "float32", + "transformers_version": "4.51.1", + "type_vocab_size": 1, + "use_cache": true, + "vocab_size": 250002 +} diff --git a/checkpoint-924/config_sentence_transformers.json b/checkpoint-924/config_sentence_transformers.json new file mode 100644 index 0000000000000000000000000000000000000000..62e46a37396f1211d0647fc417c0f6f7a664cf41 --- /dev/null +++ b/checkpoint-924/config_sentence_transformers.json @@ -0,0 +1,10 @@ +{ + "__version__": { + "sentence_transformers": "4.1.0", + "transformers": "4.51.1", + "pytorch": "2.5.1+cu124" + }, + "prompts": {}, + "default_prompt_name": null, + "similarity_fn_name": "cosine" +} \ No newline at end of file diff --git a/checkpoint-924/modules.json b/checkpoint-924/modules.json new file mode 100644 index 0000000000000000000000000000000000000000..4d28f1d12104554608cffe035493213a32207dd1 --- /dev/null +++ b/checkpoint-924/modules.json @@ -0,0 +1,14 @@ +[ + { + "idx": 0, + "name": "0", + "path": "", + "type": "sentence_transformers.models.Transformer" + }, + { + "idx": 1, + "name": "1", + "path": "1_AdvancedWeightedPooling", + "type": "__main__.AdvancedWeightedPooling" + } +] \ No newline at end of file diff --git a/checkpoint-924/optimizer.pt b/checkpoint-924/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..1129b50dc9202862a7bea1bec89fdca4f930b364 --- /dev/null +++ b/checkpoint-924/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc51977a91aab9b66d630a22a70c170a8a9e9a63d5316cad9f2e95d7556c3d0a +size 167933422 diff --git a/checkpoint-924/pytorch_model.bin b/checkpoint-924/pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..3ca31fa89c1fe43177cde98ca92cf417eea1bf86 --- /dev/null +++ b/checkpoint-924/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e969b03be79a3f792216f1febef058e86c2b7f27374fb1e044d87938ceea1ba +size 2271151270 diff --git a/checkpoint-924/rng_state.pth b/checkpoint-924/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..ed264349e4c8bc32931a99dffccf31b3431b8080 --- /dev/null +++ b/checkpoint-924/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cb77afc6c0e9c344104d80b837584feecb643b940b1faedb57e5740a4548567 +size 14244 diff --git a/checkpoint-924/scaler.pt b/checkpoint-924/scaler.pt new file mode 100644 index 0000000000000000000000000000000000000000..7c5bde2ee10c0de968705ae5057810a6a8f989e4 --- /dev/null +++ b/checkpoint-924/scaler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ed2b6134a84c253f297eb2e87e16a7970a6377fcbd0badb276a91233005d68d +size 988 diff --git a/checkpoint-924/scheduler.pt b/checkpoint-924/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..3e99a04e1ab0c666e2dd79b0ae34c73ddac56d86 --- /dev/null +++ b/checkpoint-924/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6d1cc3d0c54c50790a6fb4bb5e5bb9c831e9e7b8b6521b9c99d007da017e8fa +size 1000 diff --git a/checkpoint-924/sentence_bert_config.json b/checkpoint-924/sentence_bert_config.json new file mode 100644 index 0000000000000000000000000000000000000000..f789d99277496b282d19020415c5ba9ca79ac875 --- /dev/null +++ b/checkpoint-924/sentence_bert_config.json @@ -0,0 +1,4 @@ +{ + "max_seq_length": 512, + "do_lower_case": false +} \ No newline at end of file diff --git a/checkpoint-924/sentencepiece.bpe.model b/checkpoint-924/sentencepiece.bpe.model new file mode 100644 index 0000000000000000000000000000000000000000..7a3f40a75f870bc1f21700cd414dc2acc431583c --- /dev/null +++ b/checkpoint-924/sentencepiece.bpe.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865 +size 5069051 diff --git a/checkpoint-924/special_tokens_map.json b/checkpoint-924/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..b1879d702821e753ffe4245048eee415d54a9385 --- /dev/null +++ b/checkpoint-924/special_tokens_map.json @@ -0,0 +1,51 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "cls_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "mask_token": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "sep_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-924/tokenizer.json b/checkpoint-924/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..225ca0f803c45cce8b17cafe2dde2c7682e91938 --- /dev/null +++ b/checkpoint-924/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9a6af42442a3e3e9f05f618eae0bb2d98ca4f6a6406cb80ef7a4fa865204d61 +size 17083052 diff --git a/checkpoint-924/tokenizer_config.json b/checkpoint-924/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..95bd7c849ee6a47d5c92805af18d187239c1ba4a --- /dev/null +++ b/checkpoint-924/tokenizer_config.json @@ -0,0 +1,56 @@ +{ + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250001": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "", + "clean_up_tokenization_spaces": true, + "cls_token": "", + "eos_token": "", + "extra_special_tokens": {}, + "mask_token": "", + "model_max_length": 8192, + "pad_token": "", + "sep_token": "", + "sp_model_kwargs": {}, + "tokenizer_class": "XLMRobertaTokenizer", + "unk_token": "" +} diff --git a/checkpoint-924/trainer_state.json b/checkpoint-924/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..cfa0ffce9cbabf3a58d65be437c90d464241a49f --- /dev/null +++ b/checkpoint-924/trainer_state.json @@ -0,0 +1,6850 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.2, + "eval_steps": 77, + "global_step": 924, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0012987012987012987, + "grad_norm": 0.011165409348905087, + "learning_rate": 0.0, + "loss": 11.01, + "step": 1 + }, + { + "epoch": 0.0025974025974025974, + "grad_norm": 0.011394021101295948, + "learning_rate": 2.1645021645021646e-07, + "loss": 11.01, + "step": 2 + }, + { + "epoch": 0.003896103896103896, + "grad_norm": 0.012114278972148895, + "learning_rate": 4.329004329004329e-07, + "loss": 11.0099, + "step": 3 + }, + { + "epoch": 0.005194805194805195, + "grad_norm": 0.011571550741791725, + "learning_rate": 6.493506493506494e-07, + "loss": 11.0097, + "step": 4 + }, + { + "epoch": 0.006493506493506494, + "grad_norm": 0.012371700257062912, + "learning_rate": 8.658008658008658e-07, + "loss": 11.0099, + "step": 5 + }, + { + "epoch": 0.007792207792207792, + "grad_norm": 0.012187338434159756, + "learning_rate": 1.0822510822510822e-06, + "loss": 11.0099, + "step": 6 + }, + { + "epoch": 0.00909090909090909, + "grad_norm": 0.012087634764611721, + "learning_rate": 1.2987012987012988e-06, + "loss": 11.0099, + "step": 7 + }, + { + "epoch": 0.01038961038961039, + "grad_norm": 0.011910870671272278, + "learning_rate": 1.5151515151515152e-06, + "loss": 11.0099, + "step": 8 + }, + { + "epoch": 0.011688311688311689, + "grad_norm": 0.01282087154686451, + "learning_rate": 1.7316017316017317e-06, + "loss": 11.0099, + "step": 9 + }, + { + "epoch": 0.012987012987012988, + "grad_norm": 0.01281706988811493, + "learning_rate": 1.948051948051948e-06, + "loss": 11.0099, + "step": 10 + }, + { + "epoch": 0.014285714285714285, + "grad_norm": 0.013667456805706024, + "learning_rate": 2.1645021645021643e-06, + "loss": 11.0097, + "step": 11 + }, + { + "epoch": 0.015584415584415584, + "grad_norm": 0.01482036616653204, + "learning_rate": 2.3809523809523808e-06, + "loss": 11.0097, + "step": 12 + }, + { + "epoch": 0.016883116883116882, + "grad_norm": 0.014698008075356483, + "learning_rate": 2.5974025974025976e-06, + "loss": 11.0097, + "step": 13 + }, + { + "epoch": 0.01818181818181818, + "grad_norm": 0.014225203543901443, + "learning_rate": 2.813852813852814e-06, + "loss": 11.0097, + "step": 14 + }, + { + "epoch": 0.01948051948051948, + "grad_norm": 0.016268573701381683, + "learning_rate": 3.0303030303030305e-06, + "loss": 11.0096, + "step": 15 + }, + { + "epoch": 0.02077922077922078, + "grad_norm": 0.017191331833600998, + "learning_rate": 3.2467532467532465e-06, + "loss": 11.0095, + "step": 16 + }, + { + "epoch": 0.02207792207792208, + "grad_norm": 0.016200311481952667, + "learning_rate": 3.4632034632034634e-06, + "loss": 11.0096, + "step": 17 + }, + { + "epoch": 0.023376623376623377, + "grad_norm": 0.019106043502688408, + "learning_rate": 3.67965367965368e-06, + "loss": 11.0094, + "step": 18 + }, + { + "epoch": 0.024675324675324677, + "grad_norm": 0.017216097563505173, + "learning_rate": 3.896103896103896e-06, + "loss": 11.0095, + "step": 19 + }, + { + "epoch": 0.025974025974025976, + "grad_norm": 0.020744245499372482, + "learning_rate": 4.112554112554113e-06, + "loss": 11.0093, + "step": 20 + }, + { + "epoch": 0.02727272727272727, + "grad_norm": 0.02340623177587986, + "learning_rate": 4.329004329004329e-06, + "loss": 11.0091, + "step": 21 + }, + { + "epoch": 0.02857142857142857, + "grad_norm": 0.023833388462662697, + "learning_rate": 4.5454545454545455e-06, + "loss": 11.0091, + "step": 22 + }, + { + "epoch": 0.02987012987012987, + "grad_norm": 0.027158446609973907, + "learning_rate": 4.7619047619047615e-06, + "loss": 11.0089, + "step": 23 + }, + { + "epoch": 0.03116883116883117, + "grad_norm": 0.029171699658036232, + "learning_rate": 4.978354978354978e-06, + "loss": 11.0088, + "step": 24 + }, + { + "epoch": 0.032467532467532464, + "grad_norm": 0.03013516403734684, + "learning_rate": 5.194805194805195e-06, + "loss": 11.0087, + "step": 25 + }, + { + "epoch": 0.033766233766233764, + "grad_norm": 0.035284992307424545, + "learning_rate": 5.411255411255411e-06, + "loss": 11.0083, + "step": 26 + }, + { + "epoch": 0.03506493506493506, + "grad_norm": 0.03512846305966377, + "learning_rate": 5.627705627705628e-06, + "loss": 11.0083, + "step": 27 + }, + { + "epoch": 0.03636363636363636, + "grad_norm": 0.044411927461624146, + "learning_rate": 5.844155844155844e-06, + "loss": 11.0077, + "step": 28 + }, + { + "epoch": 0.03766233766233766, + "grad_norm": 0.04630338028073311, + "learning_rate": 6.060606060606061e-06, + "loss": 11.0075, + "step": 29 + }, + { + "epoch": 0.03896103896103896, + "grad_norm": 0.05681515112519264, + "learning_rate": 6.277056277056277e-06, + "loss": 11.0053, + "step": 30 + }, + { + "epoch": 0.04025974025974026, + "grad_norm": 0.05574386194348335, + "learning_rate": 6.493506493506493e-06, + "loss": 11.007, + "step": 31 + }, + { + "epoch": 0.04155844155844156, + "grad_norm": 0.07001659274101257, + "learning_rate": 6.709956709956711e-06, + "loss": 11.006, + "step": 32 + }, + { + "epoch": 0.04285714285714286, + "grad_norm": 0.07613399624824524, + "learning_rate": 6.926406926406927e-06, + "loss": 11.0056, + "step": 33 + }, + { + "epoch": 0.04415584415584416, + "grad_norm": 0.0930153876543045, + "learning_rate": 7.142857142857143e-06, + "loss": 11.0045, + "step": 34 + }, + { + "epoch": 0.045454545454545456, + "grad_norm": 0.11075685918331146, + "learning_rate": 7.35930735930736e-06, + "loss": 11.0035, + "step": 35 + }, + { + "epoch": 0.046753246753246755, + "grad_norm": 0.1421954482793808, + "learning_rate": 7.5757575757575764e-06, + "loss": 11.0017, + "step": 36 + }, + { + "epoch": 0.048051948051948054, + "grad_norm": 0.165273517370224, + "learning_rate": 7.792207792207792e-06, + "loss": 11.0001, + "step": 37 + }, + { + "epoch": 0.04935064935064935, + "grad_norm": 0.2073814570903778, + "learning_rate": 8.008658008658008e-06, + "loss": 10.9974, + "step": 38 + }, + { + "epoch": 0.05064935064935065, + "grad_norm": 0.240090012550354, + "learning_rate": 8.225108225108225e-06, + "loss": 10.9955, + "step": 39 + }, + { + "epoch": 0.05194805194805195, + "grad_norm": 0.2896934747695923, + "learning_rate": 8.441558441558442e-06, + "loss": 10.9926, + "step": 40 + }, + { + "epoch": 0.053246753246753244, + "grad_norm": 0.3400895595550537, + "learning_rate": 8.658008658008657e-06, + "loss": 10.9886, + "step": 41 + }, + { + "epoch": 0.05454545454545454, + "grad_norm": 0.4271922707557678, + "learning_rate": 8.874458874458876e-06, + "loss": 10.983, + "step": 42 + }, + { + "epoch": 0.05584415584415584, + "grad_norm": 0.5322330594062805, + "learning_rate": 9.090909090909091e-06, + "loss": 10.977, + "step": 43 + }, + { + "epoch": 0.05714285714285714, + "grad_norm": 0.6354700922966003, + "learning_rate": 9.307359307359308e-06, + "loss": 10.9703, + "step": 44 + }, + { + "epoch": 0.05844155844155844, + "grad_norm": 0.8793215155601501, + "learning_rate": 9.523809523809523e-06, + "loss": 10.9547, + "step": 45 + }, + { + "epoch": 0.05974025974025974, + "grad_norm": 1.008970856666565, + "learning_rate": 9.740259740259742e-06, + "loss": 10.9435, + "step": 46 + }, + { + "epoch": 0.06103896103896104, + "grad_norm": 1.2915687561035156, + "learning_rate": 9.956709956709957e-06, + "loss": 10.9263, + "step": 47 + }, + { + "epoch": 0.06233766233766234, + "grad_norm": 1.5786389112472534, + "learning_rate": 1.0173160173160174e-05, + "loss": 10.9014, + "step": 48 + }, + { + "epoch": 0.06363636363636363, + "grad_norm": 2.4445056915283203, + "learning_rate": 1.038961038961039e-05, + "loss": 10.8546, + "step": 49 + }, + { + "epoch": 0.06493506493506493, + "grad_norm": 2.5852527618408203, + "learning_rate": 1.0606060606060607e-05, + "loss": 10.8134, + "step": 50 + }, + { + "epoch": 0.06623376623376623, + "grad_norm": 2.70867919921875, + "learning_rate": 1.0822510822510823e-05, + "loss": 10.7805, + "step": 51 + }, + { + "epoch": 0.06753246753246753, + "grad_norm": 2.796766757965088, + "learning_rate": 1.103896103896104e-05, + "loss": 10.7495, + "step": 52 + }, + { + "epoch": 0.06883116883116883, + "grad_norm": 2.8984150886535645, + "learning_rate": 1.1255411255411256e-05, + "loss": 10.6997, + "step": 53 + }, + { + "epoch": 0.07012987012987013, + "grad_norm": 3.7665364742279053, + "learning_rate": 1.1471861471861473e-05, + "loss": 10.5774, + "step": 54 + }, + { + "epoch": 0.07142857142857142, + "grad_norm": 4.654474258422852, + "learning_rate": 1.1688311688311688e-05, + "loss": 10.5443, + "step": 55 + }, + { + "epoch": 0.07272727272727272, + "grad_norm": 5.21140718460083, + "learning_rate": 1.1904761904761905e-05, + "loss": 10.4336, + "step": 56 + }, + { + "epoch": 0.07402597402597402, + "grad_norm": 5.744906425476074, + "learning_rate": 1.2121212121212122e-05, + "loss": 10.3595, + "step": 57 + }, + { + "epoch": 0.07532467532467532, + "grad_norm": 7.051860332489014, + "learning_rate": 1.2337662337662339e-05, + "loss": 10.2175, + "step": 58 + }, + { + "epoch": 0.07662337662337662, + "grad_norm": 11.466012954711914, + "learning_rate": 1.2554112554112554e-05, + "loss": 10.667, + "step": 59 + }, + { + "epoch": 0.07792207792207792, + "grad_norm": 7.726934432983398, + "learning_rate": 1.2770562770562773e-05, + "loss": 10.0476, + "step": 60 + }, + { + "epoch": 0.07922077922077922, + "grad_norm": 8.461792945861816, + "learning_rate": 1.2987012987012986e-05, + "loss": 10.0367, + "step": 61 + }, + { + "epoch": 0.08051948051948052, + "grad_norm": 9.503273010253906, + "learning_rate": 1.3203463203463205e-05, + "loss": 10.0531, + "step": 62 + }, + { + "epoch": 0.08181818181818182, + "grad_norm": 9.650754928588867, + "learning_rate": 1.3419913419913421e-05, + "loss": 9.7963, + "step": 63 + }, + { + "epoch": 0.08311688311688312, + "grad_norm": 11.210810661315918, + "learning_rate": 1.3636363636363637e-05, + "loss": 9.4349, + "step": 64 + }, + { + "epoch": 0.08441558441558442, + "grad_norm": 11.565103530883789, + "learning_rate": 1.3852813852813853e-05, + "loss": 9.5733, + "step": 65 + }, + { + "epoch": 0.08571428571428572, + "grad_norm": 13.807746887207031, + "learning_rate": 1.406926406926407e-05, + "loss": 9.0604, + "step": 66 + }, + { + "epoch": 0.08701298701298701, + "grad_norm": 14.853765487670898, + "learning_rate": 1.4285714285714285e-05, + "loss": 8.7291, + "step": 67 + }, + { + "epoch": 0.08831168831168831, + "grad_norm": 15.971939086914062, + "learning_rate": 1.4502164502164502e-05, + "loss": 8.38, + "step": 68 + }, + { + "epoch": 0.08961038961038961, + "grad_norm": 16.851449966430664, + "learning_rate": 1.471861471861472e-05, + "loss": 8.2196, + "step": 69 + }, + { + "epoch": 0.09090909090909091, + "grad_norm": 18.741369247436523, + "learning_rate": 1.4935064935064936e-05, + "loss": 7.8955, + "step": 70 + }, + { + "epoch": 0.09220779220779221, + "grad_norm": 18.92623519897461, + "learning_rate": 1.5151515151515153e-05, + "loss": 7.2905, + "step": 71 + }, + { + "epoch": 0.09350649350649351, + "grad_norm": 20.634117126464844, + "learning_rate": 1.5367965367965366e-05, + "loss": 7.3614, + "step": 72 + }, + { + "epoch": 0.09480519480519481, + "grad_norm": 20.857202529907227, + "learning_rate": 1.5584415584415583e-05, + "loss": 6.6031, + "step": 73 + }, + { + "epoch": 0.09610389610389611, + "grad_norm": 22.039953231811523, + "learning_rate": 1.5800865800865803e-05, + "loss": 5.9224, + "step": 74 + }, + { + "epoch": 0.09740259740259741, + "grad_norm": 22.81475257873535, + "learning_rate": 1.6017316017316017e-05, + "loss": 5.7627, + "step": 75 + }, + { + "epoch": 0.0987012987012987, + "grad_norm": 22.588449478149414, + "learning_rate": 1.6233766233766234e-05, + "loss": 5.2194, + "step": 76 + }, + { + "epoch": 0.1, + "grad_norm": 24.180652618408203, + "learning_rate": 1.645021645021645e-05, + "loss": 5.3339, + "step": 77 + }, + { + "epoch": 0.1, + "eval_allNLI--triplets-1024_cosine_accuracy": 0.9453125, + "eval_allNLI--triplets-128_cosine_accuracy": 0.90625, + "eval_allNLI--triplets-256_cosine_accuracy": 0.9296875, + "eval_allNLI--triplets-32_cosine_accuracy": 0.9140625, + "eval_allNLI--triplets-512_cosine_accuracy": 0.9375, + "eval_allNLI-triplets_cosine_accuracy": 0.9375, + "eval_global_dataset_loss": 1.779486060142517, + "eval_global_dataset_runtime": 113.4191, + "eval_global_dataset_samples_per_second": 9.443, + "eval_global_dataset_steps_per_second": 0.079, + "eval_sequential_score": 0.9140625, + "eval_sts-test-1024_pearson_cosine": 0.8570094674494524, + "eval_sts-test-1024_spearman_cosine": 0.9032869635214775, + "eval_sts-test-128_pearson_cosine": 0.8454774972598778, + "eval_sts-test-128_spearman_cosine": 0.8941657316165149, + "eval_sts-test-256_pearson_cosine": 0.846547357013354, + "eval_sts-test-256_spearman_cosine": 0.8961152942356522, + "eval_sts-test-32_pearson_cosine": 0.8158296423835969, + "eval_sts-test-32_spearman_cosine": 0.8781449456856982, + "eval_sts-test-512_pearson_cosine": 0.8548761563192739, + "eval_sts-test-512_spearman_cosine": 0.9013753538201782, + "eval_sts-test-64_pearson_cosine": 0.8326302932611978, + "eval_sts-test-64_spearman_cosine": 0.8899336232311702, + "eval_sts-test_pearson_cosine": 0.8635863698279433, + "eval_sts-test_spearman_cosine": 0.906139519148046, + "step": 77 + }, + { + "epoch": 0.1012987012987013, + "grad_norm": 25.592409133911133, + "learning_rate": 1.6666666666666667e-05, + "loss": 5.0749, + "step": 78 + }, + { + "epoch": 0.1025974025974026, + "grad_norm": 25.978023529052734, + "learning_rate": 1.6883116883116884e-05, + "loss": 4.7881, + "step": 79 + }, + { + "epoch": 0.1038961038961039, + "grad_norm": 29.861833572387695, + "learning_rate": 1.70995670995671e-05, + "loss": 4.2653, + "step": 80 + }, + { + "epoch": 0.10519480519480519, + "grad_norm": 28.283815383911133, + "learning_rate": 1.7316017316017315e-05, + "loss": 4.0863, + "step": 81 + }, + { + "epoch": 0.10649350649350649, + "grad_norm": 29.428701400756836, + "learning_rate": 1.7532467532467535e-05, + "loss": 4.2845, + "step": 82 + }, + { + "epoch": 0.10779220779220779, + "grad_norm": 27.637096405029297, + "learning_rate": 1.7748917748917752e-05, + "loss": 3.8356, + "step": 83 + }, + { + "epoch": 0.10909090909090909, + "grad_norm": 28.08953857421875, + "learning_rate": 1.7965367965367965e-05, + "loss": 3.5652, + "step": 84 + }, + { + "epoch": 0.11038961038961038, + "grad_norm": 28.57408332824707, + "learning_rate": 1.8181818181818182e-05, + "loss": 4.1484, + "step": 85 + }, + { + "epoch": 0.11168831168831168, + "grad_norm": 26.506061553955078, + "learning_rate": 1.83982683982684e-05, + "loss": 3.4415, + "step": 86 + }, + { + "epoch": 0.11298701298701298, + "grad_norm": 26.066709518432617, + "learning_rate": 1.8614718614718616e-05, + "loss": 3.129, + "step": 87 + }, + { + "epoch": 0.11428571428571428, + "grad_norm": 27.7386531829834, + "learning_rate": 1.8831168831168833e-05, + "loss": 3.5604, + "step": 88 + }, + { + "epoch": 0.11558441558441558, + "grad_norm": 26.726911544799805, + "learning_rate": 1.9047619047619046e-05, + "loss": 3.6036, + "step": 89 + }, + { + "epoch": 0.11688311688311688, + "grad_norm": 22.78415870666504, + "learning_rate": 1.9264069264069266e-05, + "loss": 2.8276, + "step": 90 + }, + { + "epoch": 0.11818181818181818, + "grad_norm": 23.38465118408203, + "learning_rate": 1.9480519480519483e-05, + "loss": 3.4752, + "step": 91 + }, + { + "epoch": 0.11948051948051948, + "grad_norm": 24.04189109802246, + "learning_rate": 1.9696969696969697e-05, + "loss": 3.3796, + "step": 92 + }, + { + "epoch": 0.12077922077922078, + "grad_norm": 20.70046043395996, + "learning_rate": 1.9913419913419914e-05, + "loss": 2.7567, + "step": 93 + }, + { + "epoch": 0.12207792207792208, + "grad_norm": 22.61043930053711, + "learning_rate": 2.012987012987013e-05, + "loss": 3.2728, + "step": 94 + }, + { + "epoch": 0.12337662337662338, + "grad_norm": 21.59564208984375, + "learning_rate": 2.0346320346320347e-05, + "loss": 2.8496, + "step": 95 + }, + { + "epoch": 0.12467532467532468, + "grad_norm": 19.719247817993164, + "learning_rate": 2.0562770562770564e-05, + "loss": 2.6072, + "step": 96 + }, + { + "epoch": 0.12597402597402596, + "grad_norm": 19.73863410949707, + "learning_rate": 2.077922077922078e-05, + "loss": 2.5959, + "step": 97 + }, + { + "epoch": 0.12727272727272726, + "grad_norm": 20.621767044067383, + "learning_rate": 2.0995670995670998e-05, + "loss": 2.4787, + "step": 98 + }, + { + "epoch": 0.12857142857142856, + "grad_norm": 18.53163719177246, + "learning_rate": 2.1212121212121215e-05, + "loss": 2.1368, + "step": 99 + }, + { + "epoch": 0.12987012987012986, + "grad_norm": 19.333633422851562, + "learning_rate": 2.1428571428571428e-05, + "loss": 2.233, + "step": 100 + }, + { + "epoch": 0.13116883116883116, + "grad_norm": 20.839101791381836, + "learning_rate": 2.1645021645021645e-05, + "loss": 2.4691, + "step": 101 + }, + { + "epoch": 0.13246753246753246, + "grad_norm": 20.799968719482422, + "learning_rate": 2.1861471861471862e-05, + "loss": 2.3472, + "step": 102 + }, + { + "epoch": 0.13376623376623376, + "grad_norm": 18.40387725830078, + "learning_rate": 2.207792207792208e-05, + "loss": 2.0578, + "step": 103 + }, + { + "epoch": 0.13506493506493505, + "grad_norm": 19.460140228271484, + "learning_rate": 2.2294372294372296e-05, + "loss": 2.3437, + "step": 104 + }, + { + "epoch": 0.13636363636363635, + "grad_norm": 20.304363250732422, + "learning_rate": 2.2510822510822512e-05, + "loss": 2.4822, + "step": 105 + }, + { + "epoch": 0.13766233766233765, + "grad_norm": 19.452438354492188, + "learning_rate": 2.272727272727273e-05, + "loss": 2.2261, + "step": 106 + }, + { + "epoch": 0.13896103896103895, + "grad_norm": 18.387685775756836, + "learning_rate": 2.2943722943722946e-05, + "loss": 2.3113, + "step": 107 + }, + { + "epoch": 0.14025974025974025, + "grad_norm": 19.084980010986328, + "learning_rate": 2.3160173160173163e-05, + "loss": 2.2162, + "step": 108 + }, + { + "epoch": 0.14155844155844155, + "grad_norm": 18.559663772583008, + "learning_rate": 2.3376623376623376e-05, + "loss": 2.0638, + "step": 109 + }, + { + "epoch": 0.14285714285714285, + "grad_norm": 17.65582847595215, + "learning_rate": 2.3593073593073593e-05, + "loss": 1.9822, + "step": 110 + }, + { + "epoch": 0.14415584415584415, + "grad_norm": 17.26728057861328, + "learning_rate": 2.380952380952381e-05, + "loss": 1.9165, + "step": 111 + }, + { + "epoch": 0.14545454545454545, + "grad_norm": 17.52690887451172, + "learning_rate": 2.4025974025974027e-05, + "loss": 2.0633, + "step": 112 + }, + { + "epoch": 0.14675324675324675, + "grad_norm": 17.66120147705078, + "learning_rate": 2.4242424242424244e-05, + "loss": 1.9012, + "step": 113 + }, + { + "epoch": 0.14805194805194805, + "grad_norm": 17.794565200805664, + "learning_rate": 2.4458874458874457e-05, + "loss": 1.8559, + "step": 114 + }, + { + "epoch": 0.14935064935064934, + "grad_norm": 18.78278923034668, + "learning_rate": 2.4675324675324678e-05, + "loss": 2.1804, + "step": 115 + }, + { + "epoch": 0.15064935064935064, + "grad_norm": 17.93096351623535, + "learning_rate": 2.4891774891774894e-05, + "loss": 1.9728, + "step": 116 + }, + { + "epoch": 0.15194805194805194, + "grad_norm": 16.865169525146484, + "learning_rate": 2.5108225108225108e-05, + "loss": 1.795, + "step": 117 + }, + { + "epoch": 0.15324675324675324, + "grad_norm": 16.265134811401367, + "learning_rate": 2.5324675324675325e-05, + "loss": 1.5135, + "step": 118 + }, + { + "epoch": 0.15454545454545454, + "grad_norm": 18.573184967041016, + "learning_rate": 2.5541125541125545e-05, + "loss": 1.8776, + "step": 119 + }, + { + "epoch": 0.15584415584415584, + "grad_norm": 18.620136260986328, + "learning_rate": 2.575757575757576e-05, + "loss": 1.9858, + "step": 120 + }, + { + "epoch": 0.15714285714285714, + "grad_norm": 17.044523239135742, + "learning_rate": 2.5974025974025972e-05, + "loss": 1.6143, + "step": 121 + }, + { + "epoch": 0.15844155844155844, + "grad_norm": 17.63654136657715, + "learning_rate": 2.6190476190476192e-05, + "loss": 1.7321, + "step": 122 + }, + { + "epoch": 0.15974025974025974, + "grad_norm": 17.7145938873291, + "learning_rate": 2.640692640692641e-05, + "loss": 1.7272, + "step": 123 + }, + { + "epoch": 0.16103896103896104, + "grad_norm": 16.036033630371094, + "learning_rate": 2.6623376623376623e-05, + "loss": 1.5508, + "step": 124 + }, + { + "epoch": 0.16233766233766234, + "grad_norm": 16.252811431884766, + "learning_rate": 2.6839826839826843e-05, + "loss": 1.2961, + "step": 125 + }, + { + "epoch": 0.16363636363636364, + "grad_norm": 17.2477970123291, + "learning_rate": 2.7056277056277056e-05, + "loss": 1.6425, + "step": 126 + }, + { + "epoch": 0.16493506493506493, + "grad_norm": 16.966596603393555, + "learning_rate": 2.7272727272727273e-05, + "loss": 1.5193, + "step": 127 + }, + { + "epoch": 0.16623376623376623, + "grad_norm": 16.886764526367188, + "learning_rate": 2.7489177489177493e-05, + "loss": 1.6626, + "step": 128 + }, + { + "epoch": 0.16753246753246753, + "grad_norm": 18.556442260742188, + "learning_rate": 2.7705627705627707e-05, + "loss": 2.0871, + "step": 129 + }, + { + "epoch": 0.16883116883116883, + "grad_norm": 15.574275970458984, + "learning_rate": 2.792207792207792e-05, + "loss": 1.5114, + "step": 130 + }, + { + "epoch": 0.17012987012987013, + "grad_norm": 16.09569549560547, + "learning_rate": 2.813852813852814e-05, + "loss": 1.4414, + "step": 131 + }, + { + "epoch": 0.17142857142857143, + "grad_norm": 16.894790649414062, + "learning_rate": 2.8354978354978357e-05, + "loss": 1.5323, + "step": 132 + }, + { + "epoch": 0.17272727272727273, + "grad_norm": 14.77379035949707, + "learning_rate": 2.857142857142857e-05, + "loss": 1.2476, + "step": 133 + }, + { + "epoch": 0.17402597402597403, + "grad_norm": 16.156719207763672, + "learning_rate": 2.878787878787879e-05, + "loss": 1.4671, + "step": 134 + }, + { + "epoch": 0.17532467532467533, + "grad_norm": 16.27682113647461, + "learning_rate": 2.9004329004329005e-05, + "loss": 1.5581, + "step": 135 + }, + { + "epoch": 0.17662337662337663, + "grad_norm": 16.400676727294922, + "learning_rate": 2.922077922077922e-05, + "loss": 1.5237, + "step": 136 + }, + { + "epoch": 0.17792207792207793, + "grad_norm": 15.038251876831055, + "learning_rate": 2.943722943722944e-05, + "loss": 1.2613, + "step": 137 + }, + { + "epoch": 0.17922077922077922, + "grad_norm": 15.061074256896973, + "learning_rate": 2.9653679653679655e-05, + "loss": 1.2949, + "step": 138 + }, + { + "epoch": 0.18051948051948052, + "grad_norm": 15.902937889099121, + "learning_rate": 2.9870129870129872e-05, + "loss": 1.3592, + "step": 139 + }, + { + "epoch": 0.18181818181818182, + "grad_norm": 15.730782508850098, + "learning_rate": 3.0086580086580092e-05, + "loss": 1.3918, + "step": 140 + }, + { + "epoch": 0.18311688311688312, + "grad_norm": 13.916067123413086, + "learning_rate": 3.0303030303030306e-05, + "loss": 1.0371, + "step": 141 + }, + { + "epoch": 0.18441558441558442, + "grad_norm": 16.503026962280273, + "learning_rate": 3.051948051948052e-05, + "loss": 1.5028, + "step": 142 + }, + { + "epoch": 0.18571428571428572, + "grad_norm": 14.891773223876953, + "learning_rate": 3.073593073593073e-05, + "loss": 1.2347, + "step": 143 + }, + { + "epoch": 0.18701298701298702, + "grad_norm": 14.444226264953613, + "learning_rate": 3.095238095238095e-05, + "loss": 1.2731, + "step": 144 + }, + { + "epoch": 0.18831168831168832, + "grad_norm": 14.655235290527344, + "learning_rate": 3.1168831168831166e-05, + "loss": 1.2688, + "step": 145 + }, + { + "epoch": 0.18961038961038962, + "grad_norm": 15.224197387695312, + "learning_rate": 3.1385281385281387e-05, + "loss": 1.3688, + "step": 146 + }, + { + "epoch": 0.19090909090909092, + "grad_norm": 17.209598541259766, + "learning_rate": 3.160173160173161e-05, + "loss": 1.8782, + "step": 147 + }, + { + "epoch": 0.19220779220779222, + "grad_norm": 12.981212615966797, + "learning_rate": 3.181818181818182e-05, + "loss": 1.0597, + "step": 148 + }, + { + "epoch": 0.19350649350649352, + "grad_norm": 14.368124961853027, + "learning_rate": 3.2034632034632034e-05, + "loss": 1.229, + "step": 149 + }, + { + "epoch": 0.19480519480519481, + "grad_norm": 13.885086059570312, + "learning_rate": 3.2251082251082254e-05, + "loss": 1.1233, + "step": 150 + }, + { + "epoch": 0.1961038961038961, + "grad_norm": 14.75069522857666, + "learning_rate": 3.246753246753247e-05, + "loss": 1.2579, + "step": 151 + }, + { + "epoch": 0.1974025974025974, + "grad_norm": 14.663084030151367, + "learning_rate": 3.268398268398268e-05, + "loss": 1.1547, + "step": 152 + }, + { + "epoch": 0.1987012987012987, + "grad_norm": 16.447593688964844, + "learning_rate": 3.29004329004329e-05, + "loss": 1.3986, + "step": 153 + }, + { + "epoch": 0.2, + "grad_norm": 16.009765625, + "learning_rate": 3.311688311688312e-05, + "loss": 1.3071, + "step": 154 + }, + { + "epoch": 0.2, + "eval_allNLI--triplets-1024_cosine_accuracy": 0.9375, + "eval_allNLI--triplets-128_cosine_accuracy": 0.90625, + "eval_allNLI--triplets-256_cosine_accuracy": 0.90625, + "eval_allNLI--triplets-32_cosine_accuracy": 0.9140625, + "eval_allNLI--triplets-512_cosine_accuracy": 0.921875, + "eval_allNLI-triplets_cosine_accuracy": 0.9453125, + "eval_global_dataset_loss": 0.8410314917564392, + "eval_global_dataset_runtime": 113.466, + "eval_global_dataset_samples_per_second": 9.439, + "eval_global_dataset_steps_per_second": 0.079, + "eval_sequential_score": 0.9140625, + "eval_sts-test-1024_pearson_cosine": 0.8637686212043777, + "eval_sts-test-1024_spearman_cosine": 0.9158389959804479, + "eval_sts-test-128_pearson_cosine": 0.8587735042324499, + "eval_sts-test-128_spearman_cosine": 0.9079734327816954, + "eval_sts-test-256_pearson_cosine": 0.8614854438059253, + "eval_sts-test-256_spearman_cosine": 0.9113397849846575, + "eval_sts-test-32_pearson_cosine": 0.8204607604412608, + "eval_sts-test-32_spearman_cosine": 0.8866968838230891, + "eval_sts-test-512_pearson_cosine": 0.8636960327159487, + "eval_sts-test-512_spearman_cosine": 0.9151565595521514, + "eval_sts-test-64_pearson_cosine": 0.8415761749347184, + "eval_sts-test-64_spearman_cosine": 0.9004612613745113, + "eval_sts-test_pearson_cosine": 0.8701225080029533, + "eval_sts-test_spearman_cosine": 0.9182271654330917, + "step": 154 + }, + { + "epoch": 0.2012987012987013, + "grad_norm": 16.777559280395508, + "learning_rate": 3.3333333333333335e-05, + "loss": 1.5306, + "step": 155 + }, + { + "epoch": 0.2025974025974026, + "grad_norm": 14.096006393432617, + "learning_rate": 3.3549783549783555e-05, + "loss": 1.0775, + "step": 156 + }, + { + "epoch": 0.2038961038961039, + "grad_norm": 15.965473175048828, + "learning_rate": 3.376623376623377e-05, + "loss": 1.2954, + "step": 157 + }, + { + "epoch": 0.2051948051948052, + "grad_norm": 13.835360527038574, + "learning_rate": 3.398268398268398e-05, + "loss": 1.1233, + "step": 158 + }, + { + "epoch": 0.2064935064935065, + "grad_norm": 14.972121238708496, + "learning_rate": 3.41991341991342e-05, + "loss": 1.2492, + "step": 159 + }, + { + "epoch": 0.2077922077922078, + "grad_norm": 14.487752914428711, + "learning_rate": 3.4415584415584416e-05, + "loss": 1.2897, + "step": 160 + }, + { + "epoch": 0.20909090909090908, + "grad_norm": 13.836915016174316, + "learning_rate": 3.463203463203463e-05, + "loss": 1.0752, + "step": 161 + }, + { + "epoch": 0.21038961038961038, + "grad_norm": 15.030878067016602, + "learning_rate": 3.484848484848485e-05, + "loss": 1.269, + "step": 162 + }, + { + "epoch": 0.21168831168831168, + "grad_norm": 14.309725761413574, + "learning_rate": 3.506493506493507e-05, + "loss": 1.1273, + "step": 163 + }, + { + "epoch": 0.21298701298701297, + "grad_norm": 14.790210723876953, + "learning_rate": 3.528138528138528e-05, + "loss": 1.2208, + "step": 164 + }, + { + "epoch": 0.21428571428571427, + "grad_norm": 14.586909294128418, + "learning_rate": 3.5497835497835503e-05, + "loss": 1.2356, + "step": 165 + }, + { + "epoch": 0.21558441558441557, + "grad_norm": 13.816767692565918, + "learning_rate": 3.571428571428572e-05, + "loss": 1.1039, + "step": 166 + }, + { + "epoch": 0.21688311688311687, + "grad_norm": 13.635117530822754, + "learning_rate": 3.593073593073593e-05, + "loss": 1.0146, + "step": 167 + }, + { + "epoch": 0.21818181818181817, + "grad_norm": 14.119977951049805, + "learning_rate": 3.6147186147186144e-05, + "loss": 1.3097, + "step": 168 + }, + { + "epoch": 0.21948051948051947, + "grad_norm": 14.68720531463623, + "learning_rate": 3.6363636363636364e-05, + "loss": 1.2947, + "step": 169 + }, + { + "epoch": 0.22077922077922077, + "grad_norm": 14.55096435546875, + "learning_rate": 3.6580086580086584e-05, + "loss": 1.291, + "step": 170 + }, + { + "epoch": 0.22207792207792207, + "grad_norm": 13.37848949432373, + "learning_rate": 3.67965367965368e-05, + "loss": 1.0295, + "step": 171 + }, + { + "epoch": 0.22337662337662337, + "grad_norm": 12.699470520019531, + "learning_rate": 3.701298701298702e-05, + "loss": 1.0948, + "step": 172 + }, + { + "epoch": 0.22467532467532467, + "grad_norm": 13.583250999450684, + "learning_rate": 3.722943722943723e-05, + "loss": 1.1393, + "step": 173 + }, + { + "epoch": 0.22597402597402597, + "grad_norm": 12.980260848999023, + "learning_rate": 3.7445887445887445e-05, + "loss": 1.0063, + "step": 174 + }, + { + "epoch": 0.22727272727272727, + "grad_norm": 14.338798522949219, + "learning_rate": 3.7662337662337665e-05, + "loss": 1.1769, + "step": 175 + }, + { + "epoch": 0.22857142857142856, + "grad_norm": 14.311129570007324, + "learning_rate": 3.787878787878788e-05, + "loss": 1.1731, + "step": 176 + }, + { + "epoch": 0.22987012987012986, + "grad_norm": 12.44087028503418, + "learning_rate": 3.809523809523809e-05, + "loss": 0.7476, + "step": 177 + }, + { + "epoch": 0.23116883116883116, + "grad_norm": 14.917692184448242, + "learning_rate": 3.831168831168831e-05, + "loss": 1.022, + "step": 178 + }, + { + "epoch": 0.23246753246753246, + "grad_norm": 13.485183715820312, + "learning_rate": 3.852813852813853e-05, + "loss": 0.9579, + "step": 179 + }, + { + "epoch": 0.23376623376623376, + "grad_norm": 13.994976997375488, + "learning_rate": 3.8744588744588746e-05, + "loss": 1.0753, + "step": 180 + }, + { + "epoch": 0.23506493506493506, + "grad_norm": 15.207565307617188, + "learning_rate": 3.8961038961038966e-05, + "loss": 1.2243, + "step": 181 + }, + { + "epoch": 0.23636363636363636, + "grad_norm": 15.602945327758789, + "learning_rate": 3.917748917748918e-05, + "loss": 1.2154, + "step": 182 + }, + { + "epoch": 0.23766233766233766, + "grad_norm": 12.87066650390625, + "learning_rate": 3.939393939393939e-05, + "loss": 0.8147, + "step": 183 + }, + { + "epoch": 0.23896103896103896, + "grad_norm": 14.42218017578125, + "learning_rate": 3.9610389610389614e-05, + "loss": 1.1086, + "step": 184 + }, + { + "epoch": 0.24025974025974026, + "grad_norm": 14.212447166442871, + "learning_rate": 3.982683982683983e-05, + "loss": 1.0155, + "step": 185 + }, + { + "epoch": 0.24155844155844156, + "grad_norm": 15.133934020996094, + "learning_rate": 4.004329004329004e-05, + "loss": 1.1898, + "step": 186 + }, + { + "epoch": 0.24285714285714285, + "grad_norm": 13.727578163146973, + "learning_rate": 4.025974025974026e-05, + "loss": 1.11, + "step": 187 + }, + { + "epoch": 0.24415584415584415, + "grad_norm": 15.756597518920898, + "learning_rate": 4.047619047619048e-05, + "loss": 1.3128, + "step": 188 + }, + { + "epoch": 0.24545454545454545, + "grad_norm": 13.591508865356445, + "learning_rate": 4.0692640692640695e-05, + "loss": 1.0642, + "step": 189 + }, + { + "epoch": 0.24675324675324675, + "grad_norm": 13.608804702758789, + "learning_rate": 4.0909090909090915e-05, + "loss": 0.8932, + "step": 190 + }, + { + "epoch": 0.24805194805194805, + "grad_norm": 13.768484115600586, + "learning_rate": 4.112554112554113e-05, + "loss": 1.1683, + "step": 191 + }, + { + "epoch": 0.24935064935064935, + "grad_norm": 13.267477989196777, + "learning_rate": 4.134199134199134e-05, + "loss": 1.0554, + "step": 192 + }, + { + "epoch": 0.2506493506493506, + "grad_norm": 14.142014503479004, + "learning_rate": 4.155844155844156e-05, + "loss": 1.2186, + "step": 193 + }, + { + "epoch": 0.2519480519480519, + "grad_norm": 13.442983627319336, + "learning_rate": 4.1774891774891775e-05, + "loss": 1.027, + "step": 194 + }, + { + "epoch": 0.2532467532467532, + "grad_norm": 12.284928321838379, + "learning_rate": 4.1991341991341996e-05, + "loss": 0.799, + "step": 195 + }, + { + "epoch": 0.2545454545454545, + "grad_norm": 14.540982246398926, + "learning_rate": 4.220779220779221e-05, + "loss": 1.099, + "step": 196 + }, + { + "epoch": 0.2558441558441558, + "grad_norm": 12.08164119720459, + "learning_rate": 4.242424242424243e-05, + "loss": 0.7717, + "step": 197 + }, + { + "epoch": 0.2571428571428571, + "grad_norm": 14.687990188598633, + "learning_rate": 4.264069264069264e-05, + "loss": 1.1011, + "step": 198 + }, + { + "epoch": 0.2584415584415584, + "grad_norm": 13.88438606262207, + "learning_rate": 4.2857142857142856e-05, + "loss": 1.0083, + "step": 199 + }, + { + "epoch": 0.2597402597402597, + "grad_norm": 13.972654342651367, + "learning_rate": 4.3073593073593077e-05, + "loss": 1.1488, + "step": 200 + }, + { + "epoch": 0.261038961038961, + "grad_norm": 14.187093734741211, + "learning_rate": 4.329004329004329e-05, + "loss": 1.0453, + "step": 201 + }, + { + "epoch": 0.2623376623376623, + "grad_norm": 14.916047096252441, + "learning_rate": 4.3506493506493503e-05, + "loss": 1.2942, + "step": 202 + }, + { + "epoch": 0.2636363636363636, + "grad_norm": 13.239340782165527, + "learning_rate": 4.3722943722943724e-05, + "loss": 1.0279, + "step": 203 + }, + { + "epoch": 0.2649350649350649, + "grad_norm": 12.49507999420166, + "learning_rate": 4.3939393939393944e-05, + "loss": 0.9493, + "step": 204 + }, + { + "epoch": 0.2662337662337662, + "grad_norm": 14.923321723937988, + "learning_rate": 4.415584415584416e-05, + "loss": 1.2698, + "step": 205 + }, + { + "epoch": 0.2675324675324675, + "grad_norm": 13.260164260864258, + "learning_rate": 4.437229437229438e-05, + "loss": 1.066, + "step": 206 + }, + { + "epoch": 0.2688311688311688, + "grad_norm": 13.298815727233887, + "learning_rate": 4.458874458874459e-05, + "loss": 1.0352, + "step": 207 + }, + { + "epoch": 0.2701298701298701, + "grad_norm": 12.438820838928223, + "learning_rate": 4.4805194805194805e-05, + "loss": 0.8514, + "step": 208 + }, + { + "epoch": 0.2714285714285714, + "grad_norm": 13.921923637390137, + "learning_rate": 4.5021645021645025e-05, + "loss": 1.094, + "step": 209 + }, + { + "epoch": 0.2727272727272727, + "grad_norm": 13.15014934539795, + "learning_rate": 4.523809523809524e-05, + "loss": 1.0087, + "step": 210 + }, + { + "epoch": 0.274025974025974, + "grad_norm": 12.404814720153809, + "learning_rate": 4.545454545454546e-05, + "loss": 0.9035, + "step": 211 + }, + { + "epoch": 0.2753246753246753, + "grad_norm": 13.696551322937012, + "learning_rate": 4.567099567099568e-05, + "loss": 0.9475, + "step": 212 + }, + { + "epoch": 0.2766233766233766, + "grad_norm": 13.52684211730957, + "learning_rate": 4.588744588744589e-05, + "loss": 0.9838, + "step": 213 + }, + { + "epoch": 0.2779220779220779, + "grad_norm": 14.523106575012207, + "learning_rate": 4.6103896103896106e-05, + "loss": 1.1285, + "step": 214 + }, + { + "epoch": 0.2792207792207792, + "grad_norm": 12.710862159729004, + "learning_rate": 4.6320346320346326e-05, + "loss": 0.7406, + "step": 215 + }, + { + "epoch": 0.2805194805194805, + "grad_norm": 13.21323299407959, + "learning_rate": 4.653679653679654e-05, + "loss": 0.9309, + "step": 216 + }, + { + "epoch": 0.2818181818181818, + "grad_norm": 13.333338737487793, + "learning_rate": 4.675324675324675e-05, + "loss": 0.8669, + "step": 217 + }, + { + "epoch": 0.2831168831168831, + "grad_norm": 14.696738243103027, + "learning_rate": 4.696969696969697e-05, + "loss": 1.0496, + "step": 218 + }, + { + "epoch": 0.2844155844155844, + "grad_norm": 14.372692108154297, + "learning_rate": 4.718614718614719e-05, + "loss": 0.9547, + "step": 219 + }, + { + "epoch": 0.2857142857142857, + "grad_norm": 11.897599220275879, + "learning_rate": 4.740259740259741e-05, + "loss": 0.7442, + "step": 220 + }, + { + "epoch": 0.287012987012987, + "grad_norm": 12.831521034240723, + "learning_rate": 4.761904761904762e-05, + "loss": 0.6949, + "step": 221 + }, + { + "epoch": 0.2883116883116883, + "grad_norm": 12.80624008178711, + "learning_rate": 4.783549783549784e-05, + "loss": 0.958, + "step": 222 + }, + { + "epoch": 0.2896103896103896, + "grad_norm": 11.822639465332031, + "learning_rate": 4.8051948051948054e-05, + "loss": 0.7528, + "step": 223 + }, + { + "epoch": 0.2909090909090909, + "grad_norm": 12.583551406860352, + "learning_rate": 4.826839826839827e-05, + "loss": 0.8338, + "step": 224 + }, + { + "epoch": 0.2922077922077922, + "grad_norm": 14.761630058288574, + "learning_rate": 4.848484848484849e-05, + "loss": 1.108, + "step": 225 + }, + { + "epoch": 0.2935064935064935, + "grad_norm": 14.278302192687988, + "learning_rate": 4.87012987012987e-05, + "loss": 1.1113, + "step": 226 + }, + { + "epoch": 0.2948051948051948, + "grad_norm": 12.455058097839355, + "learning_rate": 4.8917748917748915e-05, + "loss": 0.8191, + "step": 227 + }, + { + "epoch": 0.2961038961038961, + "grad_norm": 12.987092018127441, + "learning_rate": 4.9134199134199135e-05, + "loss": 0.8167, + "step": 228 + }, + { + "epoch": 0.2974025974025974, + "grad_norm": 11.661968231201172, + "learning_rate": 4.9350649350649355e-05, + "loss": 0.8165, + "step": 229 + }, + { + "epoch": 0.2987012987012987, + "grad_norm": 12.673922538757324, + "learning_rate": 4.956709956709957e-05, + "loss": 0.8569, + "step": 230 + }, + { + "epoch": 0.3, + "grad_norm": 13.494362831115723, + "learning_rate": 4.978354978354979e-05, + "loss": 0.943, + "step": 231 + }, + { + "epoch": 0.3, + "eval_allNLI--triplets-1024_cosine_accuracy": 0.953125, + "eval_allNLI--triplets-128_cosine_accuracy": 0.8984375, + "eval_allNLI--triplets-256_cosine_accuracy": 0.921875, + "eval_allNLI--triplets-32_cosine_accuracy": 0.9140625, + "eval_allNLI--triplets-512_cosine_accuracy": 0.9375, + "eval_allNLI-triplets_cosine_accuracy": 0.9453125, + "eval_global_dataset_loss": 0.677043080329895, + "eval_global_dataset_runtime": 113.6829, + "eval_global_dataset_samples_per_second": 9.421, + "eval_global_dataset_steps_per_second": 0.079, + "eval_sequential_score": 0.9140625, + "eval_sts-test-1024_pearson_cosine": 0.8787763074934598, + "eval_sts-test-1024_spearman_cosine": 0.9210331750283494, + "eval_sts-test-128_pearson_cosine": 0.8722131705651872, + "eval_sts-test-128_spearman_cosine": 0.9158898385684954, + "eval_sts-test-256_pearson_cosine": 0.8732650189534636, + "eval_sts-test-256_spearman_cosine": 0.9174469823390422, + "eval_sts-test-32_pearson_cosine": 0.8348374873613509, + "eval_sts-test-32_spearman_cosine": 0.8928345151210231, + "eval_sts-test-512_pearson_cosine": 0.8784119512407846, + "eval_sts-test-512_spearman_cosine": 0.9211549108025473, + "eval_sts-test-64_pearson_cosine": 0.8606305478646585, + "eval_sts-test-64_spearman_cosine": 0.9075380483657413, + "eval_sts-test_pearson_cosine": 0.8837500780432396, + "eval_sts-test_spearman_cosine": 0.9228735334971034, + "step": 231 + }, + { + "epoch": 0.3012987012987013, + "grad_norm": 12.865336418151855, + "learning_rate": 5e-05, + "loss": 0.8316, + "step": 232 + }, + { + "epoch": 0.3025974025974026, + "grad_norm": 11.271172523498535, + "learning_rate": 5.0216450216450216e-05, + "loss": 0.6811, + "step": 233 + }, + { + "epoch": 0.3038961038961039, + "grad_norm": 11.870718955993652, + "learning_rate": 5.043290043290043e-05, + "loss": 0.7579, + "step": 234 + }, + { + "epoch": 0.3051948051948052, + "grad_norm": 12.892427444458008, + "learning_rate": 5.064935064935065e-05, + "loss": 0.8088, + "step": 235 + }, + { + "epoch": 0.3064935064935065, + "grad_norm": 13.148665428161621, + "learning_rate": 5.086580086580087e-05, + "loss": 0.8242, + "step": 236 + }, + { + "epoch": 0.3077922077922078, + "grad_norm": 13.16065788269043, + "learning_rate": 5.108225108225109e-05, + "loss": 0.9401, + "step": 237 + }, + { + "epoch": 0.3090909090909091, + "grad_norm": 13.374222755432129, + "learning_rate": 5.1298701298701304e-05, + "loss": 0.9815, + "step": 238 + }, + { + "epoch": 0.3103896103896104, + "grad_norm": 11.324379920959473, + "learning_rate": 5.151515151515152e-05, + "loss": 0.6338, + "step": 239 + }, + { + "epoch": 0.3116883116883117, + "grad_norm": 14.477818489074707, + "learning_rate": 5.173160173160173e-05, + "loss": 1.1544, + "step": 240 + }, + { + "epoch": 0.312987012987013, + "grad_norm": 13.306774139404297, + "learning_rate": 5.1948051948051944e-05, + "loss": 0.7693, + "step": 241 + }, + { + "epoch": 0.3142857142857143, + "grad_norm": 12.13784408569336, + "learning_rate": 5.216450216450217e-05, + "loss": 0.745, + "step": 242 + }, + { + "epoch": 0.3155844155844156, + "grad_norm": 12.215293884277344, + "learning_rate": 5.2380952380952384e-05, + "loss": 0.722, + "step": 243 + }, + { + "epoch": 0.3168831168831169, + "grad_norm": 13.042692184448242, + "learning_rate": 5.25974025974026e-05, + "loss": 0.7834, + "step": 244 + }, + { + "epoch": 0.3181818181818182, + "grad_norm": 12.925629615783691, + "learning_rate": 5.281385281385282e-05, + "loss": 0.8727, + "step": 245 + }, + { + "epoch": 0.3194805194805195, + "grad_norm": 11.345806121826172, + "learning_rate": 5.303030303030303e-05, + "loss": 0.657, + "step": 246 + }, + { + "epoch": 0.3207792207792208, + "grad_norm": 14.048829078674316, + "learning_rate": 5.3246753246753245e-05, + "loss": 0.9334, + "step": 247 + }, + { + "epoch": 0.3220779220779221, + "grad_norm": 14.103421211242676, + "learning_rate": 5.346320346320347e-05, + "loss": 0.9641, + "step": 248 + }, + { + "epoch": 0.3233766233766234, + "grad_norm": 13.120491027832031, + "learning_rate": 5.3679653679653686e-05, + "loss": 0.9539, + "step": 249 + }, + { + "epoch": 0.3246753246753247, + "grad_norm": 12.34601879119873, + "learning_rate": 5.38961038961039e-05, + "loss": 0.916, + "step": 250 + }, + { + "epoch": 0.32597402597402597, + "grad_norm": 11.876169204711914, + "learning_rate": 5.411255411255411e-05, + "loss": 0.7535, + "step": 251 + }, + { + "epoch": 0.32727272727272727, + "grad_norm": 13.08942985534668, + "learning_rate": 5.4329004329004326e-05, + "loss": 1.0744, + "step": 252 + }, + { + "epoch": 0.32857142857142857, + "grad_norm": 11.773645401000977, + "learning_rate": 5.4545454545454546e-05, + "loss": 0.7207, + "step": 253 + }, + { + "epoch": 0.32987012987012987, + "grad_norm": 13.143170356750488, + "learning_rate": 5.4761904761904766e-05, + "loss": 0.9337, + "step": 254 + }, + { + "epoch": 0.33116883116883117, + "grad_norm": 11.403676986694336, + "learning_rate": 5.497835497835499e-05, + "loss": 0.7114, + "step": 255 + }, + { + "epoch": 0.33246753246753247, + "grad_norm": 12.294326782226562, + "learning_rate": 5.51948051948052e-05, + "loss": 0.6995, + "step": 256 + }, + { + "epoch": 0.33376623376623377, + "grad_norm": 13.27484130859375, + "learning_rate": 5.5411255411255414e-05, + "loss": 0.8138, + "step": 257 + }, + { + "epoch": 0.33506493506493507, + "grad_norm": 13.444418907165527, + "learning_rate": 5.562770562770563e-05, + "loss": 1.0225, + "step": 258 + }, + { + "epoch": 0.33636363636363636, + "grad_norm": 13.552763938903809, + "learning_rate": 5.584415584415584e-05, + "loss": 0.9528, + "step": 259 + }, + { + "epoch": 0.33766233766233766, + "grad_norm": 13.628582954406738, + "learning_rate": 5.606060606060606e-05, + "loss": 0.9607, + "step": 260 + }, + { + "epoch": 0.33896103896103896, + "grad_norm": 13.577703475952148, + "learning_rate": 5.627705627705628e-05, + "loss": 0.971, + "step": 261 + }, + { + "epoch": 0.34025974025974026, + "grad_norm": 11.462188720703125, + "learning_rate": 5.64935064935065e-05, + "loss": 0.7819, + "step": 262 + }, + { + "epoch": 0.34155844155844156, + "grad_norm": 10.696789741516113, + "learning_rate": 5.6709956709956715e-05, + "loss": 0.6537, + "step": 263 + }, + { + "epoch": 0.34285714285714286, + "grad_norm": 12.647172927856445, + "learning_rate": 5.692640692640693e-05, + "loss": 1.0185, + "step": 264 + }, + { + "epoch": 0.34415584415584416, + "grad_norm": 13.042900085449219, + "learning_rate": 5.714285714285714e-05, + "loss": 1.0832, + "step": 265 + }, + { + "epoch": 0.34545454545454546, + "grad_norm": 9.650392532348633, + "learning_rate": 5.7359307359307355e-05, + "loss": 0.533, + "step": 266 + }, + { + "epoch": 0.34675324675324676, + "grad_norm": 12.420098304748535, + "learning_rate": 5.757575757575758e-05, + "loss": 0.9556, + "step": 267 + }, + { + "epoch": 0.34805194805194806, + "grad_norm": 11.905637741088867, + "learning_rate": 5.7792207792207796e-05, + "loss": 0.8863, + "step": 268 + }, + { + "epoch": 0.34935064935064936, + "grad_norm": 13.118106842041016, + "learning_rate": 5.800865800865801e-05, + "loss": 1.0875, + "step": 269 + }, + { + "epoch": 0.35064935064935066, + "grad_norm": 12.499323844909668, + "learning_rate": 5.822510822510823e-05, + "loss": 0.9424, + "step": 270 + }, + { + "epoch": 0.35194805194805195, + "grad_norm": 11.671981811523438, + "learning_rate": 5.844155844155844e-05, + "loss": 0.7181, + "step": 271 + }, + { + "epoch": 0.35324675324675325, + "grad_norm": 12.202942848205566, + "learning_rate": 5.8658008658008656e-05, + "loss": 0.9829, + "step": 272 + }, + { + "epoch": 0.35454545454545455, + "grad_norm": 12.920580863952637, + "learning_rate": 5.887445887445888e-05, + "loss": 0.8581, + "step": 273 + }, + { + "epoch": 0.35584415584415585, + "grad_norm": 10.84870433807373, + "learning_rate": 5.90909090909091e-05, + "loss": 0.669, + "step": 274 + }, + { + "epoch": 0.35714285714285715, + "grad_norm": 13.038583755493164, + "learning_rate": 5.930735930735931e-05, + "loss": 1.0623, + "step": 275 + }, + { + "epoch": 0.35844155844155845, + "grad_norm": 11.414346694946289, + "learning_rate": 5.9523809523809524e-05, + "loss": 0.8738, + "step": 276 + }, + { + "epoch": 0.35974025974025975, + "grad_norm": 12.988877296447754, + "learning_rate": 5.9740259740259744e-05, + "loss": 1.0384, + "step": 277 + }, + { + "epoch": 0.36103896103896105, + "grad_norm": 12.147465705871582, + "learning_rate": 5.995670995670996e-05, + "loss": 0.9253, + "step": 278 + }, + { + "epoch": 0.36233766233766235, + "grad_norm": 9.99681568145752, + "learning_rate": 6.0173160173160184e-05, + "loss": 0.6211, + "step": 279 + }, + { + "epoch": 0.36363636363636365, + "grad_norm": 10.887341499328613, + "learning_rate": 6.03896103896104e-05, + "loss": 0.7466, + "step": 280 + }, + { + "epoch": 0.36493506493506495, + "grad_norm": 11.995635032653809, + "learning_rate": 6.060606060606061e-05, + "loss": 0.8584, + "step": 281 + }, + { + "epoch": 0.36623376623376624, + "grad_norm": 11.818434715270996, + "learning_rate": 6.0822510822510825e-05, + "loss": 0.8048, + "step": 282 + }, + { + "epoch": 0.36753246753246754, + "grad_norm": 11.93957805633545, + "learning_rate": 6.103896103896104e-05, + "loss": 0.7548, + "step": 283 + }, + { + "epoch": 0.36883116883116884, + "grad_norm": 12.328822135925293, + "learning_rate": 6.125541125541126e-05, + "loss": 0.7822, + "step": 284 + }, + { + "epoch": 0.37012987012987014, + "grad_norm": 13.202193260192871, + "learning_rate": 6.147186147186147e-05, + "loss": 1.0389, + "step": 285 + }, + { + "epoch": 0.37142857142857144, + "grad_norm": 10.988061904907227, + "learning_rate": 6.16883116883117e-05, + "loss": 0.7156, + "step": 286 + }, + { + "epoch": 0.37272727272727274, + "grad_norm": 11.593925476074219, + "learning_rate": 6.19047619047619e-05, + "loss": 0.7989, + "step": 287 + }, + { + "epoch": 0.37402597402597404, + "grad_norm": 14.6128568649292, + "learning_rate": 6.212121212121213e-05, + "loss": 1.0917, + "step": 288 + }, + { + "epoch": 0.37532467532467534, + "grad_norm": 12.564693450927734, + "learning_rate": 6.233766233766233e-05, + "loss": 0.9575, + "step": 289 + }, + { + "epoch": 0.37662337662337664, + "grad_norm": 12.380928039550781, + "learning_rate": 6.255411255411255e-05, + "loss": 0.9086, + "step": 290 + }, + { + "epoch": 0.37792207792207794, + "grad_norm": 13.53039836883545, + "learning_rate": 6.277056277056277e-05, + "loss": 1.0582, + "step": 291 + }, + { + "epoch": 0.37922077922077924, + "grad_norm": 12.092082023620605, + "learning_rate": 6.2987012987013e-05, + "loss": 0.879, + "step": 292 + }, + { + "epoch": 0.38051948051948054, + "grad_norm": 10.496182441711426, + "learning_rate": 6.320346320346321e-05, + "loss": 0.6524, + "step": 293 + }, + { + "epoch": 0.38181818181818183, + "grad_norm": 11.645306587219238, + "learning_rate": 6.341991341991342e-05, + "loss": 0.767, + "step": 294 + }, + { + "epoch": 0.38311688311688313, + "grad_norm": 12.280860900878906, + "learning_rate": 6.363636363636364e-05, + "loss": 0.8842, + "step": 295 + }, + { + "epoch": 0.38441558441558443, + "grad_norm": 12.687444686889648, + "learning_rate": 6.385281385281385e-05, + "loss": 0.9167, + "step": 296 + }, + { + "epoch": 0.38571428571428573, + "grad_norm": 12.968870162963867, + "learning_rate": 6.406926406926407e-05, + "loss": 1.0106, + "step": 297 + }, + { + "epoch": 0.38701298701298703, + "grad_norm": 10.828211784362793, + "learning_rate": 6.428571428571429e-05, + "loss": 0.8014, + "step": 298 + }, + { + "epoch": 0.38831168831168833, + "grad_norm": 10.606407165527344, + "learning_rate": 6.450216450216451e-05, + "loss": 0.7783, + "step": 299 + }, + { + "epoch": 0.38961038961038963, + "grad_norm": 11.974769592285156, + "learning_rate": 6.471861471861473e-05, + "loss": 0.8608, + "step": 300 + }, + { + "epoch": 0.39090909090909093, + "grad_norm": 10.047250747680664, + "learning_rate": 6.493506493506494e-05, + "loss": 0.6383, + "step": 301 + }, + { + "epoch": 0.3922077922077922, + "grad_norm": 12.191349983215332, + "learning_rate": 6.515151515151516e-05, + "loss": 0.9668, + "step": 302 + }, + { + "epoch": 0.3935064935064935, + "grad_norm": 13.38426685333252, + "learning_rate": 6.536796536796536e-05, + "loss": 0.9447, + "step": 303 + }, + { + "epoch": 0.3948051948051948, + "grad_norm": 10.779813766479492, + "learning_rate": 6.55844155844156e-05, + "loss": 0.6609, + "step": 304 + }, + { + "epoch": 0.3961038961038961, + "grad_norm": 11.49394702911377, + "learning_rate": 6.58008658008658e-05, + "loss": 0.8104, + "step": 305 + }, + { + "epoch": 0.3974025974025974, + "grad_norm": 10.99763298034668, + "learning_rate": 6.601731601731602e-05, + "loss": 0.7231, + "step": 306 + }, + { + "epoch": 0.3987012987012987, + "grad_norm": 12.296140670776367, + "learning_rate": 6.623376623376624e-05, + "loss": 0.853, + "step": 307 + }, + { + "epoch": 0.4, + "grad_norm": 12.42627239227295, + "learning_rate": 6.645021645021645e-05, + "loss": 0.8893, + "step": 308 + }, + { + "epoch": 0.4, + "eval_allNLI--triplets-1024_cosine_accuracy": 0.9453125, + "eval_allNLI--triplets-128_cosine_accuracy": 0.9140625, + "eval_allNLI--triplets-256_cosine_accuracy": 0.9296875, + "eval_allNLI--triplets-32_cosine_accuracy": 0.9140625, + "eval_allNLI--triplets-512_cosine_accuracy": 0.9375, + "eval_allNLI-triplets_cosine_accuracy": 0.9453125, + "eval_global_dataset_loss": 0.6458740234375, + "eval_global_dataset_runtime": 113.11, + "eval_global_dataset_samples_per_second": 9.469, + "eval_global_dataset_steps_per_second": 0.08, + "eval_sequential_score": 0.9140625, + "eval_sts-test-1024_pearson_cosine": 0.8917026424281715, + "eval_sts-test-1024_spearman_cosine": 0.9280852568183454, + "eval_sts-test-128_pearson_cosine": 0.8799111388722691, + "eval_sts-test-128_spearman_cosine": 0.9174530691277519, + "eval_sts-test-256_pearson_cosine": 0.8869619950989827, + "eval_sts-test-256_spearman_cosine": 0.924964524442147, + "eval_sts-test-32_pearson_cosine": 0.8506411556887592, + "eval_sts-test-32_spearman_cosine": 0.9038834688150462, + "eval_sts-test-512_pearson_cosine": 0.8886416592593962, + "eval_sts-test-512_spearman_cosine": 0.9265875487493185, + "eval_sts-test-64_pearson_cosine": 0.8675142483501502, + "eval_sts-test-64_spearman_cosine": 0.9149750300300387, + "eval_sts-test_pearson_cosine": 0.8953751075507514, + "eval_sts-test_spearman_cosine": 0.9303824824867356, + "step": 308 + }, + { + "epoch": 0.4012987012987013, + "grad_norm": 10.81874942779541, + "learning_rate": 6.666666666666667e-05, + "loss": 0.6674, + "step": 309 + }, + { + "epoch": 0.4025974025974026, + "grad_norm": 10.319266319274902, + "learning_rate": 6.688311688311688e-05, + "loss": 0.7047, + "step": 310 + }, + { + "epoch": 0.4038961038961039, + "grad_norm": 11.703706741333008, + "learning_rate": 6.709956709956711e-05, + "loss": 0.778, + "step": 311 + }, + { + "epoch": 0.4051948051948052, + "grad_norm": 9.888168334960938, + "learning_rate": 6.731601731601732e-05, + "loss": 0.6232, + "step": 312 + }, + { + "epoch": 0.4064935064935065, + "grad_norm": 11.571825981140137, + "learning_rate": 6.753246753246754e-05, + "loss": 0.8989, + "step": 313 + }, + { + "epoch": 0.4077922077922078, + "grad_norm": 12.945980072021484, + "learning_rate": 6.774891774891774e-05, + "loss": 0.9614, + "step": 314 + }, + { + "epoch": 0.4090909090909091, + "grad_norm": 12.342436790466309, + "learning_rate": 6.796536796536796e-05, + "loss": 0.9365, + "step": 315 + }, + { + "epoch": 0.4103896103896104, + "grad_norm": 11.575722694396973, + "learning_rate": 6.818181818181818e-05, + "loss": 0.8101, + "step": 316 + }, + { + "epoch": 0.4116883116883117, + "grad_norm": 11.095999717712402, + "learning_rate": 6.83982683982684e-05, + "loss": 0.8199, + "step": 317 + }, + { + "epoch": 0.412987012987013, + "grad_norm": 11.149064064025879, + "learning_rate": 6.861471861471862e-05, + "loss": 0.8435, + "step": 318 + }, + { + "epoch": 0.4142857142857143, + "grad_norm": 11.510180473327637, + "learning_rate": 6.883116883116883e-05, + "loss": 0.9404, + "step": 319 + }, + { + "epoch": 0.4155844155844156, + "grad_norm": 10.658203125, + "learning_rate": 6.904761904761905e-05, + "loss": 0.6967, + "step": 320 + }, + { + "epoch": 0.41688311688311686, + "grad_norm": 11.118837356567383, + "learning_rate": 6.926406926406926e-05, + "loss": 0.8238, + "step": 321 + }, + { + "epoch": 0.41818181818181815, + "grad_norm": 11.655184745788574, + "learning_rate": 6.948051948051948e-05, + "loss": 0.9732, + "step": 322 + }, + { + "epoch": 0.41948051948051945, + "grad_norm": 10.72670841217041, + "learning_rate": 6.96969696969697e-05, + "loss": 0.6953, + "step": 323 + }, + { + "epoch": 0.42077922077922075, + "grad_norm": 10.018539428710938, + "learning_rate": 6.991341991341992e-05, + "loss": 0.6633, + "step": 324 + }, + { + "epoch": 0.42207792207792205, + "grad_norm": 11.938111305236816, + "learning_rate": 7.012987012987014e-05, + "loss": 0.9486, + "step": 325 + }, + { + "epoch": 0.42337662337662335, + "grad_norm": 12.473401069641113, + "learning_rate": 7.034632034632035e-05, + "loss": 0.9642, + "step": 326 + }, + { + "epoch": 0.42467532467532465, + "grad_norm": 11.210603713989258, + "learning_rate": 7.056277056277057e-05, + "loss": 0.7443, + "step": 327 + }, + { + "epoch": 0.42597402597402595, + "grad_norm": 12.498502731323242, + "learning_rate": 7.077922077922077e-05, + "loss": 1.0133, + "step": 328 + }, + { + "epoch": 0.42727272727272725, + "grad_norm": 13.254681587219238, + "learning_rate": 7.099567099567101e-05, + "loss": 1.0489, + "step": 329 + }, + { + "epoch": 0.42857142857142855, + "grad_norm": 9.72973918914795, + "learning_rate": 7.121212121212121e-05, + "loss": 0.5865, + "step": 330 + }, + { + "epoch": 0.42987012987012985, + "grad_norm": 10.99699592590332, + "learning_rate": 7.142857142857143e-05, + "loss": 0.7757, + "step": 331 + }, + { + "epoch": 0.43116883116883115, + "grad_norm": 12.112956047058105, + "learning_rate": 7.164502164502165e-05, + "loss": 0.9716, + "step": 332 + }, + { + "epoch": 0.43246753246753245, + "grad_norm": 10.795978546142578, + "learning_rate": 7.186147186147186e-05, + "loss": 0.7289, + "step": 333 + }, + { + "epoch": 0.43376623376623374, + "grad_norm": 11.796692848205566, + "learning_rate": 7.207792207792208e-05, + "loss": 0.864, + "step": 334 + }, + { + "epoch": 0.43506493506493504, + "grad_norm": 10.812421798706055, + "learning_rate": 7.229437229437229e-05, + "loss": 0.706, + "step": 335 + }, + { + "epoch": 0.43636363636363634, + "grad_norm": 10.89258098602295, + "learning_rate": 7.251082251082252e-05, + "loss": 0.7336, + "step": 336 + }, + { + "epoch": 0.43766233766233764, + "grad_norm": 10.730430603027344, + "learning_rate": 7.272727272727273e-05, + "loss": 0.6631, + "step": 337 + }, + { + "epoch": 0.43896103896103894, + "grad_norm": 11.678521156311035, + "learning_rate": 7.294372294372295e-05, + "loss": 0.8824, + "step": 338 + }, + { + "epoch": 0.44025974025974024, + "grad_norm": 10.951140403747559, + "learning_rate": 7.316017316017317e-05, + "loss": 0.7209, + "step": 339 + }, + { + "epoch": 0.44155844155844154, + "grad_norm": 10.380850791931152, + "learning_rate": 7.337662337662338e-05, + "loss": 0.6866, + "step": 340 + }, + { + "epoch": 0.44285714285714284, + "grad_norm": 10.9320707321167, + "learning_rate": 7.35930735930736e-05, + "loss": 0.8544, + "step": 341 + }, + { + "epoch": 0.44415584415584414, + "grad_norm": 11.206174850463867, + "learning_rate": 7.380952380952382e-05, + "loss": 0.7208, + "step": 342 + }, + { + "epoch": 0.44545454545454544, + "grad_norm": 12.502874374389648, + "learning_rate": 7.402597402597404e-05, + "loss": 0.9237, + "step": 343 + }, + { + "epoch": 0.44675324675324674, + "grad_norm": 10.985047340393066, + "learning_rate": 7.424242424242424e-05, + "loss": 0.8569, + "step": 344 + }, + { + "epoch": 0.44805194805194803, + "grad_norm": 11.576885223388672, + "learning_rate": 7.445887445887446e-05, + "loss": 0.9145, + "step": 345 + }, + { + "epoch": 0.44935064935064933, + "grad_norm": 10.66639518737793, + "learning_rate": 7.467532467532467e-05, + "loss": 0.8172, + "step": 346 + }, + { + "epoch": 0.45064935064935063, + "grad_norm": 10.709420204162598, + "learning_rate": 7.489177489177489e-05, + "loss": 0.8755, + "step": 347 + }, + { + "epoch": 0.45194805194805193, + "grad_norm": 9.81844425201416, + "learning_rate": 7.510822510822511e-05, + "loss": 0.7049, + "step": 348 + }, + { + "epoch": 0.45324675324675323, + "grad_norm": 10.78894329071045, + "learning_rate": 7.532467532467533e-05, + "loss": 0.8571, + "step": 349 + }, + { + "epoch": 0.45454545454545453, + "grad_norm": 10.1858549118042, + "learning_rate": 7.554112554112555e-05, + "loss": 0.71, + "step": 350 + }, + { + "epoch": 0.45584415584415583, + "grad_norm": 10.635689735412598, + "learning_rate": 7.575757575757576e-05, + "loss": 0.7568, + "step": 351 + }, + { + "epoch": 0.45714285714285713, + "grad_norm": 9.103358268737793, + "learning_rate": 7.597402597402598e-05, + "loss": 0.5732, + "step": 352 + }, + { + "epoch": 0.4584415584415584, + "grad_norm": 11.04738712310791, + "learning_rate": 7.619047619047618e-05, + "loss": 0.7801, + "step": 353 + }, + { + "epoch": 0.4597402597402597, + "grad_norm": 10.552362442016602, + "learning_rate": 7.640692640692642e-05, + "loss": 0.6895, + "step": 354 + }, + { + "epoch": 0.461038961038961, + "grad_norm": 11.45176887512207, + "learning_rate": 7.662337662337662e-05, + "loss": 0.8078, + "step": 355 + }, + { + "epoch": 0.4623376623376623, + "grad_norm": 12.02926254272461, + "learning_rate": 7.683982683982685e-05, + "loss": 0.9609, + "step": 356 + }, + { + "epoch": 0.4636363636363636, + "grad_norm": 12.51374626159668, + "learning_rate": 7.705627705627707e-05, + "loss": 0.9131, + "step": 357 + }, + { + "epoch": 0.4649350649350649, + "grad_norm": 11.659627914428711, + "learning_rate": 7.727272727272727e-05, + "loss": 0.8842, + "step": 358 + }, + { + "epoch": 0.4662337662337662, + "grad_norm": 10.37750244140625, + "learning_rate": 7.748917748917749e-05, + "loss": 0.7314, + "step": 359 + }, + { + "epoch": 0.4675324675324675, + "grad_norm": 10.31059455871582, + "learning_rate": 7.770562770562771e-05, + "loss": 0.7894, + "step": 360 + }, + { + "epoch": 0.4688311688311688, + "grad_norm": 10.418132781982422, + "learning_rate": 7.792207792207793e-05, + "loss": 0.7982, + "step": 361 + }, + { + "epoch": 0.4701298701298701, + "grad_norm": 10.784585952758789, + "learning_rate": 7.813852813852814e-05, + "loss": 0.8729, + "step": 362 + }, + { + "epoch": 0.4714285714285714, + "grad_norm": 11.513368606567383, + "learning_rate": 7.835497835497836e-05, + "loss": 0.9753, + "step": 363 + }, + { + "epoch": 0.4727272727272727, + "grad_norm": 9.88028335571289, + "learning_rate": 7.857142857142858e-05, + "loss": 0.6694, + "step": 364 + }, + { + "epoch": 0.474025974025974, + "grad_norm": 10.181724548339844, + "learning_rate": 7.878787878787879e-05, + "loss": 0.7563, + "step": 365 + }, + { + "epoch": 0.4753246753246753, + "grad_norm": 10.725600242614746, + "learning_rate": 7.900432900432901e-05, + "loss": 0.7814, + "step": 366 + }, + { + "epoch": 0.4766233766233766, + "grad_norm": 9.441679000854492, + "learning_rate": 7.922077922077923e-05, + "loss": 0.5552, + "step": 367 + }, + { + "epoch": 0.4779220779220779, + "grad_norm": 12.737554550170898, + "learning_rate": 7.943722943722945e-05, + "loss": 1.0459, + "step": 368 + }, + { + "epoch": 0.4792207792207792, + "grad_norm": 10.601099014282227, + "learning_rate": 7.965367965367965e-05, + "loss": 0.9098, + "step": 369 + }, + { + "epoch": 0.4805194805194805, + "grad_norm": 10.562568664550781, + "learning_rate": 7.987012987012987e-05, + "loss": 0.7817, + "step": 370 + }, + { + "epoch": 0.4818181818181818, + "grad_norm": 9.046710968017578, + "learning_rate": 8.008658008658008e-05, + "loss": 0.6203, + "step": 371 + }, + { + "epoch": 0.4831168831168831, + "grad_norm": 10.283613204956055, + "learning_rate": 8.03030303030303e-05, + "loss": 0.7885, + "step": 372 + }, + { + "epoch": 0.4844155844155844, + "grad_norm": 10.934900283813477, + "learning_rate": 8.051948051948052e-05, + "loss": 0.7767, + "step": 373 + }, + { + "epoch": 0.4857142857142857, + "grad_norm": 10.616456985473633, + "learning_rate": 8.073593073593074e-05, + "loss": 0.8126, + "step": 374 + }, + { + "epoch": 0.487012987012987, + "grad_norm": 10.01803970336914, + "learning_rate": 8.095238095238096e-05, + "loss": 0.7252, + "step": 375 + }, + { + "epoch": 0.4883116883116883, + "grad_norm": 10.306028366088867, + "learning_rate": 8.116883116883117e-05, + "loss": 0.8657, + "step": 376 + }, + { + "epoch": 0.4896103896103896, + "grad_norm": 10.669329643249512, + "learning_rate": 8.138528138528139e-05, + "loss": 0.8491, + "step": 377 + }, + { + "epoch": 0.4909090909090909, + "grad_norm": 10.165072441101074, + "learning_rate": 8.16017316017316e-05, + "loss": 0.784, + "step": 378 + }, + { + "epoch": 0.4922077922077922, + "grad_norm": 8.929415702819824, + "learning_rate": 8.181818181818183e-05, + "loss": 0.6108, + "step": 379 + }, + { + "epoch": 0.4935064935064935, + "grad_norm": 11.677674293518066, + "learning_rate": 8.203463203463204e-05, + "loss": 1.0215, + "step": 380 + }, + { + "epoch": 0.4948051948051948, + "grad_norm": 10.382437705993652, + "learning_rate": 8.225108225108226e-05, + "loss": 0.8208, + "step": 381 + }, + { + "epoch": 0.4961038961038961, + "grad_norm": 10.082671165466309, + "learning_rate": 8.246753246753248e-05, + "loss": 0.7456, + "step": 382 + }, + { + "epoch": 0.4974025974025974, + "grad_norm": 10.928060531616211, + "learning_rate": 8.268398268398268e-05, + "loss": 1.0181, + "step": 383 + }, + { + "epoch": 0.4987012987012987, + "grad_norm": 10.922670364379883, + "learning_rate": 8.29004329004329e-05, + "loss": 0.8263, + "step": 384 + }, + { + "epoch": 0.5, + "grad_norm": 10.033293724060059, + "learning_rate": 8.311688311688312e-05, + "loss": 0.7218, + "step": 385 + }, + { + "epoch": 0.5, + "eval_allNLI--triplets-1024_cosine_accuracy": 0.953125, + "eval_allNLI--triplets-128_cosine_accuracy": 0.921875, + "eval_allNLI--triplets-256_cosine_accuracy": 0.9375, + "eval_allNLI--triplets-32_cosine_accuracy": 0.90625, + "eval_allNLI--triplets-512_cosine_accuracy": 0.9375, + "eval_allNLI-triplets_cosine_accuracy": 0.9609375, + "eval_global_dataset_loss": 0.6583967208862305, + "eval_global_dataset_runtime": 112.7848, + "eval_global_dataset_samples_per_second": 9.496, + "eval_global_dataset_steps_per_second": 0.08, + "eval_sequential_score": 0.90625, + "eval_sts-test-1024_pearson_cosine": 0.8804763387747968, + "eval_sts-test-1024_spearman_cosine": 0.9192536844466944, + "eval_sts-test-128_pearson_cosine": 0.867682985932934, + "eval_sts-test-128_spearman_cosine": 0.9096662761358334, + "eval_sts-test-256_pearson_cosine": 0.8723111264791312, + "eval_sts-test-256_spearman_cosine": 0.9130394312202947, + "eval_sts-test-32_pearson_cosine": 0.8338645489107269, + "eval_sts-test-32_spearman_cosine": 0.8955438521897122, + "eval_sts-test-512_pearson_cosine": 0.8794209596972049, + "eval_sts-test-512_spearman_cosine": 0.9186070526578676, + "eval_sts-test-64_pearson_cosine": 0.8606438099441043, + "eval_sts-test-64_spearman_cosine": 0.9104955115859569, + "eval_sts-test_pearson_cosine": 0.8855632236901727, + "eval_sts-test_spearman_cosine": 0.9217009315544635, + "step": 385 + }, + { + "epoch": 0.5012987012987012, + "grad_norm": 9.382086753845215, + "learning_rate": 8.333333333333334e-05, + "loss": 0.6829, + "step": 386 + }, + { + "epoch": 0.5025974025974026, + "grad_norm": 10.253658294677734, + "learning_rate": 8.354978354978355e-05, + "loss": 0.8304, + "step": 387 + }, + { + "epoch": 0.5038961038961038, + "grad_norm": 9.05147647857666, + "learning_rate": 8.376623376623377e-05, + "loss": 0.6935, + "step": 388 + }, + { + "epoch": 0.5051948051948052, + "grad_norm": 10.728251457214355, + "learning_rate": 8.398268398268399e-05, + "loss": 0.9569, + "step": 389 + }, + { + "epoch": 0.5064935064935064, + "grad_norm": 9.828920364379883, + "learning_rate": 8.41991341991342e-05, + "loss": 0.7174, + "step": 390 + }, + { + "epoch": 0.5077922077922078, + "grad_norm": 10.326533317565918, + "learning_rate": 8.441558441558442e-05, + "loss": 0.8543, + "step": 391 + }, + { + "epoch": 0.509090909090909, + "grad_norm": 10.311280250549316, + "learning_rate": 8.463203463203464e-05, + "loss": 0.8769, + "step": 392 + }, + { + "epoch": 0.5103896103896104, + "grad_norm": 8.989762306213379, + "learning_rate": 8.484848484848486e-05, + "loss": 0.5945, + "step": 393 + }, + { + "epoch": 0.5116883116883116, + "grad_norm": 9.76150894165039, + "learning_rate": 8.506493506493507e-05, + "loss": 0.7787, + "step": 394 + }, + { + "epoch": 0.512987012987013, + "grad_norm": 11.173674583435059, + "learning_rate": 8.528138528138529e-05, + "loss": 0.9674, + "step": 395 + }, + { + "epoch": 0.5142857142857142, + "grad_norm": 8.645306587219238, + "learning_rate": 8.549783549783549e-05, + "loss": 0.7011, + "step": 396 + }, + { + "epoch": 0.5155844155844156, + "grad_norm": 11.850281715393066, + "learning_rate": 8.571428571428571e-05, + "loss": 0.9993, + "step": 397 + }, + { + "epoch": 0.5168831168831168, + "grad_norm": 8.96986198425293, + "learning_rate": 8.593073593073593e-05, + "loss": 0.6368, + "step": 398 + }, + { + "epoch": 0.5181818181818182, + "grad_norm": 9.281974792480469, + "learning_rate": 8.614718614718615e-05, + "loss": 0.6236, + "step": 399 + }, + { + "epoch": 0.5194805194805194, + "grad_norm": 9.10240650177002, + "learning_rate": 8.636363636363637e-05, + "loss": 0.6543, + "step": 400 + }, + { + "epoch": 0.5207792207792208, + "grad_norm": 9.484097480773926, + "learning_rate": 8.658008658008658e-05, + "loss": 0.6927, + "step": 401 + }, + { + "epoch": 0.522077922077922, + "grad_norm": 12.794879913330078, + "learning_rate": 8.67965367965368e-05, + "loss": 1.1117, + "step": 402 + }, + { + "epoch": 0.5233766233766234, + "grad_norm": 10.31647777557373, + "learning_rate": 8.701298701298701e-05, + "loss": 0.8847, + "step": 403 + }, + { + "epoch": 0.5246753246753246, + "grad_norm": 11.432804107666016, + "learning_rate": 8.722943722943724e-05, + "loss": 0.9657, + "step": 404 + }, + { + "epoch": 0.525974025974026, + "grad_norm": 11.18320369720459, + "learning_rate": 8.744588744588745e-05, + "loss": 0.8722, + "step": 405 + }, + { + "epoch": 0.5272727272727272, + "grad_norm": 9.664923667907715, + "learning_rate": 8.766233766233767e-05, + "loss": 0.7465, + "step": 406 + }, + { + "epoch": 0.5285714285714286, + "grad_norm": 8.084552764892578, + "learning_rate": 8.787878787878789e-05, + "loss": 0.5488, + "step": 407 + }, + { + "epoch": 0.5298701298701298, + "grad_norm": 9.583297729492188, + "learning_rate": 8.80952380952381e-05, + "loss": 0.6888, + "step": 408 + }, + { + "epoch": 0.5311688311688312, + "grad_norm": 10.47243595123291, + "learning_rate": 8.831168831168831e-05, + "loss": 0.7561, + "step": 409 + }, + { + "epoch": 0.5324675324675324, + "grad_norm": 9.173786163330078, + "learning_rate": 8.852813852813854e-05, + "loss": 0.5411, + "step": 410 + }, + { + "epoch": 0.5337662337662338, + "grad_norm": 10.696986198425293, + "learning_rate": 8.874458874458876e-05, + "loss": 0.7663, + "step": 411 + }, + { + "epoch": 0.535064935064935, + "grad_norm": 12.49531078338623, + "learning_rate": 8.896103896103896e-05, + "loss": 1.0137, + "step": 412 + }, + { + "epoch": 0.5363636363636364, + "grad_norm": 9.877222061157227, + "learning_rate": 8.917748917748918e-05, + "loss": 0.667, + "step": 413 + }, + { + "epoch": 0.5376623376623376, + "grad_norm": 9.855676651000977, + "learning_rate": 8.93939393939394e-05, + "loss": 0.7111, + "step": 414 + }, + { + "epoch": 0.538961038961039, + "grad_norm": 11.593993186950684, + "learning_rate": 8.961038961038961e-05, + "loss": 0.8531, + "step": 415 + }, + { + "epoch": 0.5402597402597402, + "grad_norm": 10.321015357971191, + "learning_rate": 8.982683982683983e-05, + "loss": 0.8561, + "step": 416 + }, + { + "epoch": 0.5415584415584416, + "grad_norm": 8.318321228027344, + "learning_rate": 9.004329004329005e-05, + "loss": 0.612, + "step": 417 + }, + { + "epoch": 0.5428571428571428, + "grad_norm": 10.25160026550293, + "learning_rate": 9.025974025974027e-05, + "loss": 0.7229, + "step": 418 + }, + { + "epoch": 0.5441558441558442, + "grad_norm": 9.849309921264648, + "learning_rate": 9.047619047619048e-05, + "loss": 0.8387, + "step": 419 + }, + { + "epoch": 0.5454545454545454, + "grad_norm": 9.49033260345459, + "learning_rate": 9.06926406926407e-05, + "loss": 0.7439, + "step": 420 + }, + { + "epoch": 0.5467532467532468, + "grad_norm": 8.027220726013184, + "learning_rate": 9.090909090909092e-05, + "loss": 0.5846, + "step": 421 + }, + { + "epoch": 0.548051948051948, + "grad_norm": 8.108675003051758, + "learning_rate": 9.112554112554112e-05, + "loss": 0.5976, + "step": 422 + }, + { + "epoch": 0.5493506493506494, + "grad_norm": 9.802972793579102, + "learning_rate": 9.134199134199136e-05, + "loss": 0.7378, + "step": 423 + }, + { + "epoch": 0.5506493506493506, + "grad_norm": 10.613837242126465, + "learning_rate": 9.155844155844156e-05, + "loss": 0.8756, + "step": 424 + }, + { + "epoch": 0.551948051948052, + "grad_norm": 10.099786758422852, + "learning_rate": 9.177489177489178e-05, + "loss": 0.6755, + "step": 425 + }, + { + "epoch": 0.5532467532467532, + "grad_norm": 9.524248123168945, + "learning_rate": 9.199134199134199e-05, + "loss": 0.6566, + "step": 426 + }, + { + "epoch": 0.5545454545454546, + "grad_norm": 9.682258605957031, + "learning_rate": 9.220779220779221e-05, + "loss": 0.5624, + "step": 427 + }, + { + "epoch": 0.5558441558441558, + "grad_norm": 9.256147384643555, + "learning_rate": 9.242424242424242e-05, + "loss": 0.5887, + "step": 428 + }, + { + "epoch": 0.5571428571428572, + "grad_norm": 11.301840782165527, + "learning_rate": 9.264069264069265e-05, + "loss": 0.9906, + "step": 429 + }, + { + "epoch": 0.5584415584415584, + "grad_norm": 10.433177947998047, + "learning_rate": 9.285714285714286e-05, + "loss": 0.735, + "step": 430 + }, + { + "epoch": 0.5597402597402598, + "grad_norm": 11.203728675842285, + "learning_rate": 9.307359307359308e-05, + "loss": 0.8759, + "step": 431 + }, + { + "epoch": 0.561038961038961, + "grad_norm": 10.540921211242676, + "learning_rate": 9.32900432900433e-05, + "loss": 0.8514, + "step": 432 + }, + { + "epoch": 0.5623376623376624, + "grad_norm": 9.670626640319824, + "learning_rate": 9.35064935064935e-05, + "loss": 0.7531, + "step": 433 + }, + { + "epoch": 0.5636363636363636, + "grad_norm": 9.004586219787598, + "learning_rate": 9.372294372294373e-05, + "loss": 0.6816, + "step": 434 + }, + { + "epoch": 0.564935064935065, + "grad_norm": 9.889915466308594, + "learning_rate": 9.393939393939395e-05, + "loss": 0.8911, + "step": 435 + }, + { + "epoch": 0.5662337662337662, + "grad_norm": 9.216524124145508, + "learning_rate": 9.415584415584417e-05, + "loss": 0.7555, + "step": 436 + }, + { + "epoch": 0.5675324675324676, + "grad_norm": 9.710390090942383, + "learning_rate": 9.437229437229437e-05, + "loss": 0.8079, + "step": 437 + }, + { + "epoch": 0.5688311688311688, + "grad_norm": 8.755694389343262, + "learning_rate": 9.45887445887446e-05, + "loss": 0.6203, + "step": 438 + }, + { + "epoch": 0.5701298701298702, + "grad_norm": 9.18278694152832, + "learning_rate": 9.480519480519481e-05, + "loss": 0.6348, + "step": 439 + }, + { + "epoch": 0.5714285714285714, + "grad_norm": 8.409049987792969, + "learning_rate": 9.502164502164502e-05, + "loss": 0.5986, + "step": 440 + }, + { + "epoch": 0.5727272727272728, + "grad_norm": 10.397635459899902, + "learning_rate": 9.523809523809524e-05, + "loss": 0.8259, + "step": 441 + }, + { + "epoch": 0.574025974025974, + "grad_norm": 9.205062866210938, + "learning_rate": 9.545454545454546e-05, + "loss": 0.7051, + "step": 442 + }, + { + "epoch": 0.5753246753246753, + "grad_norm": 9.241551399230957, + "learning_rate": 9.567099567099568e-05, + "loss": 0.591, + "step": 443 + }, + { + "epoch": 0.5766233766233766, + "grad_norm": 9.01000690460205, + "learning_rate": 9.588744588744589e-05, + "loss": 0.7197, + "step": 444 + }, + { + "epoch": 0.577922077922078, + "grad_norm": 8.933067321777344, + "learning_rate": 9.610389610389611e-05, + "loss": 0.6624, + "step": 445 + }, + { + "epoch": 0.5792207792207792, + "grad_norm": 10.92744255065918, + "learning_rate": 9.632034632034633e-05, + "loss": 0.9108, + "step": 446 + }, + { + "epoch": 0.5805194805194805, + "grad_norm": 9.574989318847656, + "learning_rate": 9.653679653679654e-05, + "loss": 0.7401, + "step": 447 + }, + { + "epoch": 0.5818181818181818, + "grad_norm": 9.929916381835938, + "learning_rate": 9.675324675324677e-05, + "loss": 0.7475, + "step": 448 + }, + { + "epoch": 0.5831168831168831, + "grad_norm": 10.541657447814941, + "learning_rate": 9.696969696969698e-05, + "loss": 1.0367, + "step": 449 + }, + { + "epoch": 0.5844155844155844, + "grad_norm": 9.241097450256348, + "learning_rate": 9.71861471861472e-05, + "loss": 0.819, + "step": 450 + }, + { + "epoch": 0.5857142857142857, + "grad_norm": 10.230196952819824, + "learning_rate": 9.74025974025974e-05, + "loss": 0.9914, + "step": 451 + }, + { + "epoch": 0.587012987012987, + "grad_norm": 7.502562999725342, + "learning_rate": 9.761904761904762e-05, + "loss": 0.5852, + "step": 452 + }, + { + "epoch": 0.5883116883116883, + "grad_norm": 9.432659149169922, + "learning_rate": 9.783549783549783e-05, + "loss": 0.8283, + "step": 453 + }, + { + "epoch": 0.5896103896103896, + "grad_norm": 8.886880874633789, + "learning_rate": 9.805194805194806e-05, + "loss": 0.9477, + "step": 454 + }, + { + "epoch": 0.5909090909090909, + "grad_norm": 8.474105834960938, + "learning_rate": 9.826839826839827e-05, + "loss": 0.7091, + "step": 455 + }, + { + "epoch": 0.5922077922077922, + "grad_norm": 9.925548553466797, + "learning_rate": 9.848484848484849e-05, + "loss": 0.958, + "step": 456 + }, + { + "epoch": 0.5935064935064935, + "grad_norm": 7.961300849914551, + "learning_rate": 9.870129870129871e-05, + "loss": 0.6203, + "step": 457 + }, + { + "epoch": 0.5948051948051948, + "grad_norm": 8.644482612609863, + "learning_rate": 9.891774891774892e-05, + "loss": 0.6183, + "step": 458 + }, + { + "epoch": 0.5961038961038961, + "grad_norm": 8.991077423095703, + "learning_rate": 9.913419913419914e-05, + "loss": 0.7303, + "step": 459 + }, + { + "epoch": 0.5974025974025974, + "grad_norm": 10.966276168823242, + "learning_rate": 9.935064935064936e-05, + "loss": 0.9273, + "step": 460 + }, + { + "epoch": 0.5987012987012987, + "grad_norm": 10.023669242858887, + "learning_rate": 9.956709956709958e-05, + "loss": 0.7091, + "step": 461 + }, + { + "epoch": 0.6, + "grad_norm": 11.322511672973633, + "learning_rate": 9.978354978354978e-05, + "loss": 0.9906, + "step": 462 + }, + { + "epoch": 0.6, + "eval_allNLI--triplets-1024_cosine_accuracy": 0.9453125, + "eval_allNLI--triplets-128_cosine_accuracy": 0.9296875, + "eval_allNLI--triplets-256_cosine_accuracy": 0.9375, + "eval_allNLI--triplets-32_cosine_accuracy": 0.921875, + "eval_allNLI--triplets-512_cosine_accuracy": 0.9453125, + "eval_allNLI-triplets_cosine_accuracy": 0.9453125, + "eval_global_dataset_loss": 0.6539728045463562, + "eval_global_dataset_runtime": 113.7266, + "eval_global_dataset_samples_per_second": 9.417, + "eval_global_dataset_steps_per_second": 0.079, + "eval_sequential_score": 0.921875, + "eval_sts-test-1024_pearson_cosine": 0.8797687244140173, + "eval_sts-test-1024_spearman_cosine": 0.9263218783244517, + "eval_sts-test-128_pearson_cosine": 0.865709098903634, + "eval_sts-test-128_spearman_cosine": 0.9134647903371974, + "eval_sts-test-256_pearson_cosine": 0.873391317761029, + "eval_sts-test-256_spearman_cosine": 0.9216776585388081, + "eval_sts-test-32_pearson_cosine": 0.835229116152323, + "eval_sts-test-32_spearman_cosine": 0.8990595097392636, + "eval_sts-test-512_pearson_cosine": 0.8784096835085939, + "eval_sts-test-512_spearman_cosine": 0.9279259261727042, + "eval_sts-test-64_pearson_cosine": 0.8518886914166497, + "eval_sts-test-64_spearman_cosine": 0.9082587957582707, + "eval_sts-test_pearson_cosine": 0.8813813147500178, + "eval_sts-test_spearman_cosine": 0.9273104444202163, + "step": 462 + }, + { + "epoch": 0.6012987012987013, + "grad_norm": 10.7688627243042, + "learning_rate": 0.0001, + "loss": 0.9442, + "step": 463 + }, + { + "epoch": 0.6025974025974026, + "grad_norm": 9.374990463256836, + "learning_rate": 9.999993497531978e-05, + "loss": 0.7803, + "step": 464 + }, + { + "epoch": 0.6038961038961039, + "grad_norm": 7.978273868560791, + "learning_rate": 9.999973990146702e-05, + "loss": 0.6228, + "step": 465 + }, + { + "epoch": 0.6051948051948052, + "grad_norm": 8.63952350616455, + "learning_rate": 9.999941477900548e-05, + "loss": 0.7387, + "step": 466 + }, + { + "epoch": 0.6064935064935065, + "grad_norm": 9.687905311584473, + "learning_rate": 9.999895960887477e-05, + "loss": 0.9448, + "step": 467 + }, + { + "epoch": 0.6077922077922078, + "grad_norm": 8.742199897766113, + "learning_rate": 9.999837439239033e-05, + "loss": 0.7838, + "step": 468 + }, + { + "epoch": 0.6090909090909091, + "grad_norm": 9.454602241516113, + "learning_rate": 9.99976591312434e-05, + "loss": 0.9093, + "step": 469 + }, + { + "epoch": 0.6103896103896104, + "grad_norm": 7.550654411315918, + "learning_rate": 9.999681382750109e-05, + "loss": 0.6647, + "step": 470 + }, + { + "epoch": 0.6116883116883117, + "grad_norm": 7.778524398803711, + "learning_rate": 9.999583848360633e-05, + "loss": 0.5482, + "step": 471 + }, + { + "epoch": 0.612987012987013, + "grad_norm": 8.33474063873291, + "learning_rate": 9.999473310237784e-05, + "loss": 0.6356, + "step": 472 + }, + { + "epoch": 0.6142857142857143, + "grad_norm": 10.372974395751953, + "learning_rate": 9.999349768701014e-05, + "loss": 0.8282, + "step": 473 + }, + { + "epoch": 0.6155844155844156, + "grad_norm": 9.575736045837402, + "learning_rate": 9.999213224107359e-05, + "loss": 0.8235, + "step": 474 + }, + { + "epoch": 0.6168831168831169, + "grad_norm": 8.910548210144043, + "learning_rate": 9.99906367685143e-05, + "loss": 0.6899, + "step": 475 + }, + { + "epoch": 0.6181818181818182, + "grad_norm": 8.8406400680542, + "learning_rate": 9.998901127365415e-05, + "loss": 0.6827, + "step": 476 + }, + { + "epoch": 0.6194805194805195, + "grad_norm": 9.354793548583984, + "learning_rate": 9.998725576119081e-05, + "loss": 0.7347, + "step": 477 + }, + { + "epoch": 0.6207792207792208, + "grad_norm": 9.497842788696289, + "learning_rate": 9.998537023619768e-05, + "loss": 0.8705, + "step": 478 + }, + { + "epoch": 0.6220779220779221, + "grad_norm": 9.095974922180176, + "learning_rate": 9.998335470412392e-05, + "loss": 0.8298, + "step": 479 + }, + { + "epoch": 0.6233766233766234, + "grad_norm": 8.34008502960205, + "learning_rate": 9.998120917079436e-05, + "loss": 0.7419, + "step": 480 + }, + { + "epoch": 0.6246753246753247, + "grad_norm": 9.542933464050293, + "learning_rate": 9.997893364240958e-05, + "loss": 1.1283, + "step": 481 + }, + { + "epoch": 0.625974025974026, + "grad_norm": 7.765565395355225, + "learning_rate": 9.997652812554582e-05, + "loss": 0.7298, + "step": 482 + }, + { + "epoch": 0.6272727272727273, + "grad_norm": 8.254328727722168, + "learning_rate": 9.997399262715498e-05, + "loss": 0.8972, + "step": 483 + }, + { + "epoch": 0.6285714285714286, + "grad_norm": 7.9485883712768555, + "learning_rate": 9.997132715456464e-05, + "loss": 0.7502, + "step": 484 + }, + { + "epoch": 0.6298701298701299, + "grad_norm": 7.377613544464111, + "learning_rate": 9.996853171547794e-05, + "loss": 0.6169, + "step": 485 + }, + { + "epoch": 0.6311688311688312, + "grad_norm": 8.520637512207031, + "learning_rate": 9.996560631797367e-05, + "loss": 0.7648, + "step": 486 + }, + { + "epoch": 0.6324675324675325, + "grad_norm": 8.45702075958252, + "learning_rate": 9.996255097050623e-05, + "loss": 0.8191, + "step": 487 + }, + { + "epoch": 0.6337662337662338, + "grad_norm": 9.343992233276367, + "learning_rate": 9.995936568190549e-05, + "loss": 0.8094, + "step": 488 + }, + { + "epoch": 0.6350649350649351, + "grad_norm": 9.630705833435059, + "learning_rate": 9.995605046137689e-05, + "loss": 0.9006, + "step": 489 + }, + { + "epoch": 0.6363636363636364, + "grad_norm": 9.293671607971191, + "learning_rate": 9.995260531850137e-05, + "loss": 0.8384, + "step": 490 + }, + { + "epoch": 0.6376623376623377, + "grad_norm": 8.072113990783691, + "learning_rate": 9.994903026323536e-05, + "loss": 0.6431, + "step": 491 + }, + { + "epoch": 0.638961038961039, + "grad_norm": 7.910200595855713, + "learning_rate": 9.994532530591071e-05, + "loss": 0.7507, + "step": 492 + }, + { + "epoch": 0.6402597402597403, + "grad_norm": 9.722458839416504, + "learning_rate": 9.994149045723469e-05, + "loss": 1.0524, + "step": 493 + }, + { + "epoch": 0.6415584415584416, + "grad_norm": 9.438432693481445, + "learning_rate": 9.993752572828996e-05, + "loss": 0.9618, + "step": 494 + }, + { + "epoch": 0.6428571428571429, + "grad_norm": 8.785840034484863, + "learning_rate": 9.993343113053453e-05, + "loss": 0.8119, + "step": 495 + }, + { + "epoch": 0.6441558441558441, + "grad_norm": 8.101314544677734, + "learning_rate": 9.992920667580176e-05, + "loss": 0.6538, + "step": 496 + }, + { + "epoch": 0.6454545454545455, + "grad_norm": 8.958012580871582, + "learning_rate": 9.99248523763002e-05, + "loss": 0.8877, + "step": 497 + }, + { + "epoch": 0.6467532467532467, + "grad_norm": 11.046570777893066, + "learning_rate": 9.992036824461376e-05, + "loss": 1.0556, + "step": 498 + }, + { + "epoch": 0.6480519480519481, + "grad_norm": 8.324684143066406, + "learning_rate": 9.991575429370151e-05, + "loss": 0.6788, + "step": 499 + }, + { + "epoch": 0.6493506493506493, + "grad_norm": 9.95218276977539, + "learning_rate": 9.99110105368977e-05, + "loss": 0.9637, + "step": 500 + }, + { + "epoch": 0.6506493506493507, + "grad_norm": 9.085275650024414, + "learning_rate": 9.990613698791173e-05, + "loss": 0.8143, + "step": 501 + }, + { + "epoch": 0.6519480519480519, + "grad_norm": 8.417174339294434, + "learning_rate": 9.990113366082806e-05, + "loss": 0.6673, + "step": 502 + }, + { + "epoch": 0.6532467532467533, + "grad_norm": 8.649909019470215, + "learning_rate": 9.989600057010624e-05, + "loss": 0.8358, + "step": 503 + }, + { + "epoch": 0.6545454545454545, + "grad_norm": 8.382777214050293, + "learning_rate": 9.989073773058086e-05, + "loss": 0.7588, + "step": 504 + }, + { + "epoch": 0.6558441558441559, + "grad_norm": 8.671955108642578, + "learning_rate": 9.98853451574614e-05, + "loss": 0.8241, + "step": 505 + }, + { + "epoch": 0.6571428571428571, + "grad_norm": 8.806478500366211, + "learning_rate": 9.987982286633239e-05, + "loss": 0.925, + "step": 506 + }, + { + "epoch": 0.6584415584415585, + "grad_norm": 7.872350215911865, + "learning_rate": 9.987417087315311e-05, + "loss": 0.6336, + "step": 507 + }, + { + "epoch": 0.6597402597402597, + "grad_norm": 8.123810768127441, + "learning_rate": 9.986838919425777e-05, + "loss": 0.6907, + "step": 508 + }, + { + "epoch": 0.6610389610389611, + "grad_norm": 9.4236421585083, + "learning_rate": 9.986247784635533e-05, + "loss": 0.8237, + "step": 509 + }, + { + "epoch": 0.6623376623376623, + "grad_norm": 9.10471248626709, + "learning_rate": 9.98564368465295e-05, + "loss": 0.828, + "step": 510 + }, + { + "epoch": 0.6636363636363637, + "grad_norm": 8.953938484191895, + "learning_rate": 9.98502662122387e-05, + "loss": 0.6624, + "step": 511 + }, + { + "epoch": 0.6649350649350649, + "grad_norm": 9.512434959411621, + "learning_rate": 9.984396596131595e-05, + "loss": 0.8069, + "step": 512 + }, + { + "epoch": 0.6662337662337663, + "grad_norm": 7.959551811218262, + "learning_rate": 9.98375361119689e-05, + "loss": 0.566, + "step": 513 + }, + { + "epoch": 0.6675324675324675, + "grad_norm": 10.5604887008667, + "learning_rate": 9.983097668277975e-05, + "loss": 1.0294, + "step": 514 + }, + { + "epoch": 0.6688311688311688, + "grad_norm": 9.543386459350586, + "learning_rate": 9.98242876927051e-05, + "loss": 0.8889, + "step": 515 + }, + { + "epoch": 0.6701298701298701, + "grad_norm": 7.930560111999512, + "learning_rate": 9.981746916107607e-05, + "loss": 0.6539, + "step": 516 + }, + { + "epoch": 0.6714285714285714, + "grad_norm": 8.005714416503906, + "learning_rate": 9.981052110759813e-05, + "loss": 0.7279, + "step": 517 + }, + { + "epoch": 0.6727272727272727, + "grad_norm": 8.585083961486816, + "learning_rate": 9.980344355235102e-05, + "loss": 0.7805, + "step": 518 + }, + { + "epoch": 0.674025974025974, + "grad_norm": 7.590928077697754, + "learning_rate": 9.979623651578881e-05, + "loss": 0.6657, + "step": 519 + }, + { + "epoch": 0.6753246753246753, + "grad_norm": 6.786378860473633, + "learning_rate": 9.978890001873971e-05, + "loss": 0.5069, + "step": 520 + }, + { + "epoch": 0.6766233766233766, + "grad_norm": 9.419742584228516, + "learning_rate": 9.978143408240611e-05, + "loss": 0.9967, + "step": 521 + }, + { + "epoch": 0.6779220779220779, + "grad_norm": 8.207934379577637, + "learning_rate": 9.977383872836444e-05, + "loss": 0.719, + "step": 522 + }, + { + "epoch": 0.6792207792207792, + "grad_norm": 7.318924427032471, + "learning_rate": 9.976611397856519e-05, + "loss": 0.4709, + "step": 523 + }, + { + "epoch": 0.6805194805194805, + "grad_norm": 8.9629545211792, + "learning_rate": 9.975825985533274e-05, + "loss": 0.7421, + "step": 524 + }, + { + "epoch": 0.6818181818181818, + "grad_norm": 8.531639099121094, + "learning_rate": 9.975027638136544e-05, + "loss": 0.7005, + "step": 525 + }, + { + "epoch": 0.6831168831168831, + "grad_norm": 10.551216125488281, + "learning_rate": 9.974216357973539e-05, + "loss": 0.9615, + "step": 526 + }, + { + "epoch": 0.6844155844155844, + "grad_norm": 9.172273635864258, + "learning_rate": 9.973392147388847e-05, + "loss": 0.7011, + "step": 527 + }, + { + "epoch": 0.6857142857142857, + "grad_norm": 8.73135757446289, + "learning_rate": 9.972555008764424e-05, + "loss": 0.7021, + "step": 528 + }, + { + "epoch": 0.687012987012987, + "grad_norm": 9.322381019592285, + "learning_rate": 9.971704944519594e-05, + "loss": 0.7954, + "step": 529 + }, + { + "epoch": 0.6883116883116883, + "grad_norm": 10.328460693359375, + "learning_rate": 9.970841957111022e-05, + "loss": 1.0179, + "step": 530 + }, + { + "epoch": 0.6896103896103896, + "grad_norm": 7.732416152954102, + "learning_rate": 9.969966049032736e-05, + "loss": 0.6674, + "step": 531 + }, + { + "epoch": 0.6909090909090909, + "grad_norm": 8.953222274780273, + "learning_rate": 9.969077222816096e-05, + "loss": 0.7634, + "step": 532 + }, + { + "epoch": 0.6922077922077922, + "grad_norm": 6.733580589294434, + "learning_rate": 9.968175481029797e-05, + "loss": 0.5306, + "step": 533 + }, + { + "epoch": 0.6935064935064935, + "grad_norm": 7.927433013916016, + "learning_rate": 9.96726082627986e-05, + "loss": 0.6792, + "step": 534 + }, + { + "epoch": 0.6948051948051948, + "grad_norm": 8.450961112976074, + "learning_rate": 9.966333261209626e-05, + "loss": 0.8223, + "step": 535 + }, + { + "epoch": 0.6961038961038961, + "grad_norm": 8.986429214477539, + "learning_rate": 9.965392788499741e-05, + "loss": 0.9346, + "step": 536 + }, + { + "epoch": 0.6974025974025974, + "grad_norm": 7.740746021270752, + "learning_rate": 9.96443941086816e-05, + "loss": 0.7369, + "step": 537 + }, + { + "epoch": 0.6987012987012987, + "grad_norm": 8.5305757522583, + "learning_rate": 9.963473131070133e-05, + "loss": 0.7636, + "step": 538 + }, + { + "epoch": 0.7, + "grad_norm": 7.068668842315674, + "learning_rate": 9.96249395189819e-05, + "loss": 0.632, + "step": 539 + }, + { + "epoch": 0.7, + "eval_allNLI--triplets-1024_cosine_accuracy": 0.9296875, + "eval_allNLI--triplets-128_cosine_accuracy": 0.8984375, + "eval_allNLI--triplets-256_cosine_accuracy": 0.9140625, + "eval_allNLI--triplets-32_cosine_accuracy": 0.8984375, + "eval_allNLI--triplets-512_cosine_accuracy": 0.921875, + "eval_allNLI-triplets_cosine_accuracy": 0.9296875, + "eval_global_dataset_loss": 0.6427525877952576, + "eval_global_dataset_runtime": 113.506, + "eval_global_dataset_samples_per_second": 9.436, + "eval_global_dataset_steps_per_second": 0.079, + "eval_sequential_score": 0.8984375, + "eval_sts-test-1024_pearson_cosine": 0.8873943324412861, + "eval_sts-test-1024_spearman_cosine": 0.9253282995791614, + "eval_sts-test-128_pearson_cosine": 0.8722931553862875, + "eval_sts-test-128_spearman_cosine": 0.9168565638341831, + "eval_sts-test-256_pearson_cosine": 0.8785673618962662, + "eval_sts-test-256_spearman_cosine": 0.9222670029044829, + "eval_sts-test-32_pearson_cosine": 0.8547551484487256, + "eval_sts-test-32_spearman_cosine": 0.9122828791882953, + "eval_sts-test-512_pearson_cosine": 0.8852620294819122, + "eval_sts-test-512_spearman_cosine": 0.9242760012251404, + "eval_sts-test-64_pearson_cosine": 0.8669129026803459, + "eval_sts-test-64_spearman_cosine": 0.9143251758236597, + "eval_sts-test_pearson_cosine": 0.8900120725090723, + "eval_sts-test_spearman_cosine": 0.9241635746572048, + "step": 539 + }, + { + "epoch": 0.7012987012987013, + "grad_norm": 8.080013275146484, + "learning_rate": 9.961501876182148e-05, + "loss": 0.672, + "step": 540 + }, + { + "epoch": 0.7025974025974026, + "grad_norm": 8.661029815673828, + "learning_rate": 9.960496906789089e-05, + "loss": 0.8924, + "step": 541 + }, + { + "epoch": 0.7038961038961039, + "grad_norm": 8.918992042541504, + "learning_rate": 9.959479046623367e-05, + "loss": 0.822, + "step": 542 + }, + { + "epoch": 0.7051948051948052, + "grad_norm": 7.410845756530762, + "learning_rate": 9.958448298626576e-05, + "loss": 0.4934, + "step": 543 + }, + { + "epoch": 0.7064935064935065, + "grad_norm": 7.634463310241699, + "learning_rate": 9.957404665777567e-05, + "loss": 0.5939, + "step": 544 + }, + { + "epoch": 0.7077922077922078, + "grad_norm": 7.014540195465088, + "learning_rate": 9.956348151092421e-05, + "loss": 0.5593, + "step": 545 + }, + { + "epoch": 0.7090909090909091, + "grad_norm": 8.57436466217041, + "learning_rate": 9.955278757624455e-05, + "loss": 0.737, + "step": 546 + }, + { + "epoch": 0.7103896103896103, + "grad_norm": 8.323346138000488, + "learning_rate": 9.954196488464198e-05, + "loss": 0.6734, + "step": 547 + }, + { + "epoch": 0.7116883116883117, + "grad_norm": 9.893049240112305, + "learning_rate": 9.953101346739391e-05, + "loss": 0.949, + "step": 548 + }, + { + "epoch": 0.712987012987013, + "grad_norm": 9.634085655212402, + "learning_rate": 9.951993335614982e-05, + "loss": 0.9343, + "step": 549 + }, + { + "epoch": 0.7142857142857143, + "grad_norm": 6.592012882232666, + "learning_rate": 9.950872458293105e-05, + "loss": 0.4662, + "step": 550 + }, + { + "epoch": 0.7155844155844155, + "grad_norm": 7.7272186279296875, + "learning_rate": 9.949738718013078e-05, + "loss": 0.6602, + "step": 551 + }, + { + "epoch": 0.7168831168831169, + "grad_norm": 7.066654682159424, + "learning_rate": 9.948592118051398e-05, + "loss": 0.6273, + "step": 552 + }, + { + "epoch": 0.7181818181818181, + "grad_norm": 7.870489120483398, + "learning_rate": 9.94743266172172e-05, + "loss": 0.665, + "step": 553 + }, + { + "epoch": 0.7194805194805195, + "grad_norm": 8.590832710266113, + "learning_rate": 9.946260352374857e-05, + "loss": 0.7826, + "step": 554 + }, + { + "epoch": 0.7207792207792207, + "grad_norm": 9.697837829589844, + "learning_rate": 9.945075193398767e-05, + "loss": 1.0379, + "step": 555 + }, + { + "epoch": 0.7220779220779221, + "grad_norm": 7.371159076690674, + "learning_rate": 9.943877188218541e-05, + "loss": 0.5787, + "step": 556 + }, + { + "epoch": 0.7233766233766233, + "grad_norm": 7.7747907638549805, + "learning_rate": 9.942666340296398e-05, + "loss": 0.6639, + "step": 557 + }, + { + "epoch": 0.7246753246753247, + "grad_norm": 6.700680732727051, + "learning_rate": 9.941442653131673e-05, + "loss": 0.5511, + "step": 558 + }, + { + "epoch": 0.7259740259740259, + "grad_norm": 7.617847442626953, + "learning_rate": 9.9402061302608e-05, + "loss": 0.6313, + "step": 559 + }, + { + "epoch": 0.7272727272727273, + "grad_norm": 8.378815650939941, + "learning_rate": 9.938956775257318e-05, + "loss": 0.7771, + "step": 560 + }, + { + "epoch": 0.7285714285714285, + "grad_norm": 5.534984111785889, + "learning_rate": 9.937694591731841e-05, + "loss": 0.4077, + "step": 561 + }, + { + "epoch": 0.7298701298701299, + "grad_norm": 8.180028915405273, + "learning_rate": 9.936419583332062e-05, + "loss": 0.6628, + "step": 562 + }, + { + "epoch": 0.7311688311688311, + "grad_norm": 7.878411769866943, + "learning_rate": 9.935131753742737e-05, + "loss": 0.5646, + "step": 563 + }, + { + "epoch": 0.7324675324675325, + "grad_norm": 7.941530704498291, + "learning_rate": 9.933831106685679e-05, + "loss": 0.5972, + "step": 564 + }, + { + "epoch": 0.7337662337662337, + "grad_norm": 10.171013832092285, + "learning_rate": 9.932517645919738e-05, + "loss": 1.0101, + "step": 565 + }, + { + "epoch": 0.7350649350649351, + "grad_norm": 9.271905899047852, + "learning_rate": 9.931191375240792e-05, + "loss": 0.9496, + "step": 566 + }, + { + "epoch": 0.7363636363636363, + "grad_norm": 7.886529445648193, + "learning_rate": 9.92985229848175e-05, + "loss": 0.6219, + "step": 567 + }, + { + "epoch": 0.7376623376623377, + "grad_norm": 7.918776035308838, + "learning_rate": 9.928500419512521e-05, + "loss": 0.7275, + "step": 568 + }, + { + "epoch": 0.7389610389610389, + "grad_norm": 8.45152759552002, + "learning_rate": 9.927135742240022e-05, + "loss": 0.905, + "step": 569 + }, + { + "epoch": 0.7402597402597403, + "grad_norm": 7.562143325805664, + "learning_rate": 9.925758270608144e-05, + "loss": 0.7303, + "step": 570 + }, + { + "epoch": 0.7415584415584415, + "grad_norm": 7.238564968109131, + "learning_rate": 9.924368008597763e-05, + "loss": 0.6518, + "step": 571 + }, + { + "epoch": 0.7428571428571429, + "grad_norm": 6.896720886230469, + "learning_rate": 9.922964960226718e-05, + "loss": 0.6725, + "step": 572 + }, + { + "epoch": 0.7441558441558441, + "grad_norm": 7.941315650939941, + "learning_rate": 9.921549129549798e-05, + "loss": 0.8026, + "step": 573 + }, + { + "epoch": 0.7454545454545455, + "grad_norm": 6.776406288146973, + "learning_rate": 9.920120520658732e-05, + "loss": 0.6042, + "step": 574 + }, + { + "epoch": 0.7467532467532467, + "grad_norm": 7.763830661773682, + "learning_rate": 9.91867913768218e-05, + "loss": 0.7192, + "step": 575 + }, + { + "epoch": 0.7480519480519481, + "grad_norm": 7.134865760803223, + "learning_rate": 9.91722498478572e-05, + "loss": 0.6089, + "step": 576 + }, + { + "epoch": 0.7493506493506493, + "grad_norm": 8.958261489868164, + "learning_rate": 9.915758066171833e-05, + "loss": 0.92, + "step": 577 + }, + { + "epoch": 0.7506493506493507, + "grad_norm": 8.438769340515137, + "learning_rate": 9.91427838607989e-05, + "loss": 0.81, + "step": 578 + }, + { + "epoch": 0.7519480519480519, + "grad_norm": 8.106558799743652, + "learning_rate": 9.912785948786149e-05, + "loss": 0.7004, + "step": 579 + }, + { + "epoch": 0.7532467532467533, + "grad_norm": 7.914773464202881, + "learning_rate": 9.911280758603728e-05, + "loss": 0.636, + "step": 580 + }, + { + "epoch": 0.7545454545454545, + "grad_norm": 7.522397994995117, + "learning_rate": 9.90976281988261e-05, + "loss": 0.6059, + "step": 581 + }, + { + "epoch": 0.7558441558441559, + "grad_norm": 6.786513328552246, + "learning_rate": 9.908232137009617e-05, + "loss": 0.5995, + "step": 582 + }, + { + "epoch": 0.7571428571428571, + "grad_norm": 8.496878623962402, + "learning_rate": 9.906688714408396e-05, + "loss": 0.8563, + "step": 583 + }, + { + "epoch": 0.7584415584415585, + "grad_norm": 7.118294715881348, + "learning_rate": 9.905132556539418e-05, + "loss": 0.6008, + "step": 584 + }, + { + "epoch": 0.7597402597402597, + "grad_norm": 7.351891994476318, + "learning_rate": 9.90356366789996e-05, + "loss": 0.6576, + "step": 585 + }, + { + "epoch": 0.7610389610389611, + "grad_norm": 6.669191360473633, + "learning_rate": 9.901982053024083e-05, + "loss": 0.5438, + "step": 586 + }, + { + "epoch": 0.7623376623376623, + "grad_norm": 7.092779636383057, + "learning_rate": 9.900387716482637e-05, + "loss": 0.6347, + "step": 587 + }, + { + "epoch": 0.7636363636363637, + "grad_norm": 6.913083553314209, + "learning_rate": 9.898780662883227e-05, + "loss": 0.6002, + "step": 588 + }, + { + "epoch": 0.7649350649350649, + "grad_norm": 8.093656539916992, + "learning_rate": 9.897160896870218e-05, + "loss": 0.726, + "step": 589 + }, + { + "epoch": 0.7662337662337663, + "grad_norm": 8.512179374694824, + "learning_rate": 9.89552842312471e-05, + "loss": 0.8955, + "step": 590 + }, + { + "epoch": 0.7675324675324675, + "grad_norm": 7.220069408416748, + "learning_rate": 9.89388324636453e-05, + "loss": 0.5638, + "step": 591 + }, + { + "epoch": 0.7688311688311689, + "grad_norm": 7.283459186553955, + "learning_rate": 9.892225371344214e-05, + "loss": 0.6315, + "step": 592 + }, + { + "epoch": 0.7701298701298701, + "grad_norm": 7.870151042938232, + "learning_rate": 9.890554802854995e-05, + "loss": 0.7253, + "step": 593 + }, + { + "epoch": 0.7714285714285715, + "grad_norm": 7.145277500152588, + "learning_rate": 9.888871545724798e-05, + "loss": 0.6148, + "step": 594 + }, + { + "epoch": 0.7727272727272727, + "grad_norm": 6.762304782867432, + "learning_rate": 9.887175604818206e-05, + "loss": 0.4651, + "step": 595 + }, + { + "epoch": 0.7740259740259741, + "grad_norm": 6.68051290512085, + "learning_rate": 9.885466985036468e-05, + "loss": 0.5097, + "step": 596 + }, + { + "epoch": 0.7753246753246753, + "grad_norm": 8.16653060913086, + "learning_rate": 9.883745691317472e-05, + "loss": 0.7487, + "step": 597 + }, + { + "epoch": 0.7766233766233767, + "grad_norm": 7.994803428649902, + "learning_rate": 9.88201172863573e-05, + "loss": 0.7269, + "step": 598 + }, + { + "epoch": 0.7779220779220779, + "grad_norm": 8.129690170288086, + "learning_rate": 9.880265102002369e-05, + "loss": 0.8212, + "step": 599 + }, + { + "epoch": 0.7792207792207793, + "grad_norm": 8.369062423706055, + "learning_rate": 9.878505816465115e-05, + "loss": 0.822, + "step": 600 + }, + { + "epoch": 0.7805194805194805, + "grad_norm": 7.65264892578125, + "learning_rate": 9.876733877108281e-05, + "loss": 0.6172, + "step": 601 + }, + { + "epoch": 0.7818181818181819, + "grad_norm": 7.348762035369873, + "learning_rate": 9.874949289052744e-05, + "loss": 0.6488, + "step": 602 + }, + { + "epoch": 0.7831168831168831, + "grad_norm": 8.416467666625977, + "learning_rate": 9.873152057455939e-05, + "loss": 0.8928, + "step": 603 + }, + { + "epoch": 0.7844155844155845, + "grad_norm": 7.411664962768555, + "learning_rate": 9.871342187511838e-05, + "loss": 0.7068, + "step": 604 + }, + { + "epoch": 0.7857142857142857, + "grad_norm": 7.342609882354736, + "learning_rate": 9.869519684450943e-05, + "loss": 0.6558, + "step": 605 + }, + { + "epoch": 0.787012987012987, + "grad_norm": 6.897357940673828, + "learning_rate": 9.86768455354026e-05, + "loss": 0.6012, + "step": 606 + }, + { + "epoch": 0.7883116883116883, + "grad_norm": 7.639064788818359, + "learning_rate": 9.865836800083291e-05, + "loss": 0.7806, + "step": 607 + }, + { + "epoch": 0.7896103896103897, + "grad_norm": 6.563958168029785, + "learning_rate": 9.863976429420017e-05, + "loss": 0.5802, + "step": 608 + }, + { + "epoch": 0.7909090909090909, + "grad_norm": 7.272040367126465, + "learning_rate": 9.862103446926885e-05, + "loss": 0.7414, + "step": 609 + }, + { + "epoch": 0.7922077922077922, + "grad_norm": 7.528412818908691, + "learning_rate": 9.860217858016784e-05, + "loss": 0.6715, + "step": 610 + }, + { + "epoch": 0.7935064935064935, + "grad_norm": 6.993316173553467, + "learning_rate": 9.858319668139041e-05, + "loss": 0.6947, + "step": 611 + }, + { + "epoch": 0.7948051948051948, + "grad_norm": 6.731951713562012, + "learning_rate": 9.856408882779398e-05, + "loss": 0.6908, + "step": 612 + }, + { + "epoch": 0.7961038961038961, + "grad_norm": 6.824806213378906, + "learning_rate": 9.85448550746e-05, + "loss": 0.587, + "step": 613 + }, + { + "epoch": 0.7974025974025974, + "grad_norm": 7.066167831420898, + "learning_rate": 9.85254954773937e-05, + "loss": 0.642, + "step": 614 + }, + { + "epoch": 0.7987012987012987, + "grad_norm": 6.381121635437012, + "learning_rate": 9.850601009212407e-05, + "loss": 0.5082, + "step": 615 + }, + { + "epoch": 0.8, + "grad_norm": 7.728446960449219, + "learning_rate": 9.848639897510358e-05, + "loss": 0.6574, + "step": 616 + }, + { + "epoch": 0.8, + "eval_allNLI--triplets-1024_cosine_accuracy": 0.9453125, + "eval_allNLI--triplets-128_cosine_accuracy": 0.9296875, + "eval_allNLI--triplets-256_cosine_accuracy": 0.9453125, + "eval_allNLI--triplets-32_cosine_accuracy": 0.9296875, + "eval_allNLI--triplets-512_cosine_accuracy": 0.9453125, + "eval_allNLI-triplets_cosine_accuracy": 0.9453125, + "eval_global_dataset_loss": 0.6188308000564575, + "eval_global_dataset_runtime": 113.7163, + "eval_global_dataset_samples_per_second": 9.418, + "eval_global_dataset_steps_per_second": 0.079, + "eval_sequential_score": 0.9296875, + "eval_sts-test-1024_pearson_cosine": 0.8912631824974158, + "eval_sts-test-1024_spearman_cosine": 0.9274389830759132, + "eval_sts-test-128_pearson_cosine": 0.8876748515587677, + "eval_sts-test-128_spearman_cosine": 0.9237690075302462, + "eval_sts-test-256_pearson_cosine": 0.8892868596959533, + "eval_sts-test-256_spearman_cosine": 0.9269749549483829, + "eval_sts-test-32_pearson_cosine": 0.8512951958187567, + "eval_sts-test-32_spearman_cosine": 0.9137630429839818, + "eval_sts-test-512_pearson_cosine": 0.8923752440183839, + "eval_sts-test-512_spearman_cosine": 0.9280265372096147, + "eval_sts-test-64_pearson_cosine": 0.8733490483495416, + "eval_sts-test-64_spearman_cosine": 0.9214732140474348, + "eval_sts-test_pearson_cosine": 0.8935100137551328, + "eval_sts-test_spearman_cosine": 0.9288851324641034, + "step": 616 + }, + { + "epoch": 0.8012987012987013, + "grad_norm": 6.461012840270996, + "learning_rate": 9.846666218300807e-05, + "loss": 0.5828, + "step": 617 + }, + { + "epoch": 0.8025974025974026, + "grad_norm": 8.968891143798828, + "learning_rate": 9.844679977287661e-05, + "loss": 0.8306, + "step": 618 + }, + { + "epoch": 0.8038961038961039, + "grad_norm": 7.8341546058654785, + "learning_rate": 9.84268118021113e-05, + "loss": 0.6332, + "step": 619 + }, + { + "epoch": 0.8051948051948052, + "grad_norm": 6.980321884155273, + "learning_rate": 9.840669832847705e-05, + "loss": 0.6006, + "step": 620 + }, + { + "epoch": 0.8064935064935065, + "grad_norm": 6.770340442657471, + "learning_rate": 9.838645941010154e-05, + "loss": 0.5365, + "step": 621 + }, + { + "epoch": 0.8077922077922078, + "grad_norm": 7.772369384765625, + "learning_rate": 9.836609510547494e-05, + "loss": 0.6386, + "step": 622 + }, + { + "epoch": 0.8090909090909091, + "grad_norm": 7.803502082824707, + "learning_rate": 9.834560547344981e-05, + "loss": 0.684, + "step": 623 + }, + { + "epoch": 0.8103896103896104, + "grad_norm": 8.83973503112793, + "learning_rate": 9.83249905732409e-05, + "loss": 0.9585, + "step": 624 + }, + { + "epoch": 0.8116883116883117, + "grad_norm": 6.967188835144043, + "learning_rate": 9.830425046442496e-05, + "loss": 0.6687, + "step": 625 + }, + { + "epoch": 0.812987012987013, + "grad_norm": 7.9906487464904785, + "learning_rate": 9.828338520694064e-05, + "loss": 0.7117, + "step": 626 + }, + { + "epoch": 0.8142857142857143, + "grad_norm": 7.777108192443848, + "learning_rate": 9.826239486108822e-05, + "loss": 0.7052, + "step": 627 + }, + { + "epoch": 0.8155844155844156, + "grad_norm": 7.411710262298584, + "learning_rate": 9.82412794875295e-05, + "loss": 0.7474, + "step": 628 + }, + { + "epoch": 0.8168831168831169, + "grad_norm": 6.999947547912598, + "learning_rate": 9.822003914728759e-05, + "loss": 0.7309, + "step": 629 + }, + { + "epoch": 0.8181818181818182, + "grad_norm": 6.437720775604248, + "learning_rate": 9.81986739017468e-05, + "loss": 0.6185, + "step": 630 + }, + { + "epoch": 0.8194805194805195, + "grad_norm": 6.909036159515381, + "learning_rate": 9.81771838126524e-05, + "loss": 0.7055, + "step": 631 + }, + { + "epoch": 0.8207792207792208, + "grad_norm": 7.5900349617004395, + "learning_rate": 9.815556894211038e-05, + "loss": 0.8739, + "step": 632 + }, + { + "epoch": 0.8220779220779221, + "grad_norm": 6.764601230621338, + "learning_rate": 9.813382935258749e-05, + "loss": 0.7134, + "step": 633 + }, + { + "epoch": 0.8233766233766234, + "grad_norm": 6.6621012687683105, + "learning_rate": 9.811196510691077e-05, + "loss": 0.7014, + "step": 634 + }, + { + "epoch": 0.8246753246753247, + "grad_norm": 6.744335651397705, + "learning_rate": 9.808997626826762e-05, + "loss": 0.6907, + "step": 635 + }, + { + "epoch": 0.825974025974026, + "grad_norm": 6.413692474365234, + "learning_rate": 9.806786290020544e-05, + "loss": 0.6316, + "step": 636 + }, + { + "epoch": 0.8272727272727273, + "grad_norm": 8.33804988861084, + "learning_rate": 9.804562506663157e-05, + "loss": 1.013, + "step": 637 + }, + { + "epoch": 0.8285714285714286, + "grad_norm": 7.601145267486572, + "learning_rate": 9.802326283181302e-05, + "loss": 0.7022, + "step": 638 + }, + { + "epoch": 0.8298701298701299, + "grad_norm": 6.36918830871582, + "learning_rate": 9.800077626037634e-05, + "loss": 0.5908, + "step": 639 + }, + { + "epoch": 0.8311688311688312, + "grad_norm": 6.497655391693115, + "learning_rate": 9.79781654173074e-05, + "loss": 0.6008, + "step": 640 + }, + { + "epoch": 0.8324675324675325, + "grad_norm": 6.970991134643555, + "learning_rate": 9.795543036795122e-05, + "loss": 0.6932, + "step": 641 + }, + { + "epoch": 0.8337662337662337, + "grad_norm": 6.388566970825195, + "learning_rate": 9.793257117801176e-05, + "loss": 0.5935, + "step": 642 + }, + { + "epoch": 0.8350649350649351, + "grad_norm": 7.75444221496582, + "learning_rate": 9.790958791355175e-05, + "loss": 0.7817, + "step": 643 + }, + { + "epoch": 0.8363636363636363, + "grad_norm": 6.7867960929870605, + "learning_rate": 9.78864806409925e-05, + "loss": 0.5923, + "step": 644 + }, + { + "epoch": 0.8376623376623377, + "grad_norm": 6.315074920654297, + "learning_rate": 9.786324942711372e-05, + "loss": 0.5689, + "step": 645 + }, + { + "epoch": 0.8389610389610389, + "grad_norm": 6.039573669433594, + "learning_rate": 9.783989433905328e-05, + "loss": 0.5501, + "step": 646 + }, + { + "epoch": 0.8402597402597403, + "grad_norm": 7.127732753753662, + "learning_rate": 9.781641544430703e-05, + "loss": 0.7422, + "step": 647 + }, + { + "epoch": 0.8415584415584415, + "grad_norm": 8.375782012939453, + "learning_rate": 9.779281281072868e-05, + "loss": 0.9285, + "step": 648 + }, + { + "epoch": 0.8428571428571429, + "grad_norm": 6.235222816467285, + "learning_rate": 9.776908650652946e-05, + "loss": 0.6054, + "step": 649 + }, + { + "epoch": 0.8441558441558441, + "grad_norm": 6.5698771476745605, + "learning_rate": 9.774523660027807e-05, + "loss": 0.6312, + "step": 650 + }, + { + "epoch": 0.8454545454545455, + "grad_norm": 8.005461692810059, + "learning_rate": 9.772126316090041e-05, + "loss": 0.9075, + "step": 651 + }, + { + "epoch": 0.8467532467532467, + "grad_norm": 6.392460823059082, + "learning_rate": 9.769716625767939e-05, + "loss": 0.5705, + "step": 652 + }, + { + "epoch": 0.8480519480519481, + "grad_norm": 8.403264045715332, + "learning_rate": 9.767294596025469e-05, + "loss": 0.9817, + "step": 653 + }, + { + "epoch": 0.8493506493506493, + "grad_norm": 7.119625568389893, + "learning_rate": 9.764860233862263e-05, + "loss": 0.6819, + "step": 654 + }, + { + "epoch": 0.8506493506493507, + "grad_norm": 8.16954231262207, + "learning_rate": 9.762413546313596e-05, + "loss": 0.9261, + "step": 655 + }, + { + "epoch": 0.8519480519480519, + "grad_norm": 5.286291599273682, + "learning_rate": 9.759954540450357e-05, + "loss": 0.3939, + "step": 656 + }, + { + "epoch": 0.8532467532467533, + "grad_norm": 6.879117488861084, + "learning_rate": 9.757483223379038e-05, + "loss": 0.7817, + "step": 657 + }, + { + "epoch": 0.8545454545454545, + "grad_norm": 6.944469451904297, + "learning_rate": 9.754999602241713e-05, + "loss": 0.5585, + "step": 658 + }, + { + "epoch": 0.8558441558441559, + "grad_norm": 6.0197906494140625, + "learning_rate": 9.752503684216007e-05, + "loss": 0.4809, + "step": 659 + }, + { + "epoch": 0.8571428571428571, + "grad_norm": 9.095551490783691, + "learning_rate": 9.749995476515094e-05, + "loss": 0.9696, + "step": 660 + }, + { + "epoch": 0.8584415584415584, + "grad_norm": 6.5533928871154785, + "learning_rate": 9.747474986387654e-05, + "loss": 0.5146, + "step": 661 + }, + { + "epoch": 0.8597402597402597, + "grad_norm": 8.780946731567383, + "learning_rate": 9.744942221117869e-05, + "loss": 0.8808, + "step": 662 + }, + { + "epoch": 0.861038961038961, + "grad_norm": 6.859992504119873, + "learning_rate": 9.742397188025393e-05, + "loss": 0.5708, + "step": 663 + }, + { + "epoch": 0.8623376623376623, + "grad_norm": 6.31803560256958, + "learning_rate": 9.73983989446534e-05, + "loss": 0.4975, + "step": 664 + }, + { + "epoch": 0.8636363636363636, + "grad_norm": 6.68372106552124, + "learning_rate": 9.737270347828248e-05, + "loss": 0.5205, + "step": 665 + }, + { + "epoch": 0.8649350649350649, + "grad_norm": 8.428847312927246, + "learning_rate": 9.734688555540071e-05, + "loss": 0.9157, + "step": 666 + }, + { + "epoch": 0.8662337662337662, + "grad_norm": 7.586736679077148, + "learning_rate": 9.732094525062153e-05, + "loss": 0.7465, + "step": 667 + }, + { + "epoch": 0.8675324675324675, + "grad_norm": 8.633830070495605, + "learning_rate": 9.729488263891204e-05, + "loss": 0.8935, + "step": 668 + }, + { + "epoch": 0.8688311688311688, + "grad_norm": 6.911459922790527, + "learning_rate": 9.726869779559281e-05, + "loss": 0.7008, + "step": 669 + }, + { + "epoch": 0.8701298701298701, + "grad_norm": 5.816353797912598, + "learning_rate": 9.724239079633769e-05, + "loss": 0.4422, + "step": 670 + }, + { + "epoch": 0.8714285714285714, + "grad_norm": 5.5716423988342285, + "learning_rate": 9.721596171717352e-05, + "loss": 0.4216, + "step": 671 + }, + { + "epoch": 0.8727272727272727, + "grad_norm": 7.347598075866699, + "learning_rate": 9.718941063447997e-05, + "loss": 0.739, + "step": 672 + }, + { + "epoch": 0.874025974025974, + "grad_norm": 6.3041253089904785, + "learning_rate": 9.716273762498929e-05, + "loss": 0.5473, + "step": 673 + }, + { + "epoch": 0.8753246753246753, + "grad_norm": 6.651629447937012, + "learning_rate": 9.713594276578608e-05, + "loss": 0.6101, + "step": 674 + }, + { + "epoch": 0.8766233766233766, + "grad_norm": 6.883923530578613, + "learning_rate": 9.710902613430713e-05, + "loss": 0.6453, + "step": 675 + }, + { + "epoch": 0.8779220779220779, + "grad_norm": 6.905819892883301, + "learning_rate": 9.70819878083411e-05, + "loss": 0.6317, + "step": 676 + }, + { + "epoch": 0.8792207792207792, + "grad_norm": 6.912679672241211, + "learning_rate": 9.705482786602837e-05, + "loss": 0.6964, + "step": 677 + }, + { + "epoch": 0.8805194805194805, + "grad_norm": 6.441966533660889, + "learning_rate": 9.702754638586082e-05, + "loss": 0.617, + "step": 678 + }, + { + "epoch": 0.8818181818181818, + "grad_norm": 6.045241355895996, + "learning_rate": 9.700014344668151e-05, + "loss": 0.4839, + "step": 679 + }, + { + "epoch": 0.8831168831168831, + "grad_norm": 6.609492778778076, + "learning_rate": 9.697261912768454e-05, + "loss": 0.6383, + "step": 680 + }, + { + "epoch": 0.8844155844155844, + "grad_norm": 6.745547294616699, + "learning_rate": 9.69449735084148e-05, + "loss": 0.595, + "step": 681 + }, + { + "epoch": 0.8857142857142857, + "grad_norm": 6.410647869110107, + "learning_rate": 9.691720666876777e-05, + "loss": 0.5053, + "step": 682 + }, + { + "epoch": 0.887012987012987, + "grad_norm": 7.867794513702393, + "learning_rate": 9.688931868898919e-05, + "loss": 0.8086, + "step": 683 + }, + { + "epoch": 0.8883116883116883, + "grad_norm": 7.473386764526367, + "learning_rate": 9.686130964967495e-05, + "loss": 0.7465, + "step": 684 + }, + { + "epoch": 0.8896103896103896, + "grad_norm": 8.719533920288086, + "learning_rate": 9.683317963177075e-05, + "loss": 0.9109, + "step": 685 + }, + { + "epoch": 0.8909090909090909, + "grad_norm": 8.01264762878418, + "learning_rate": 9.680492871657194e-05, + "loss": 0.8457, + "step": 686 + }, + { + "epoch": 0.8922077922077922, + "grad_norm": 7.10344934463501, + "learning_rate": 9.677655698572326e-05, + "loss": 0.7412, + "step": 687 + }, + { + "epoch": 0.8935064935064935, + "grad_norm": 7.437696933746338, + "learning_rate": 9.674806452121865e-05, + "loss": 0.6259, + "step": 688 + }, + { + "epoch": 0.8948051948051948, + "grad_norm": 8.253927230834961, + "learning_rate": 9.671945140540091e-05, + "loss": 0.8406, + "step": 689 + }, + { + "epoch": 0.8961038961038961, + "grad_norm": 6.132811069488525, + "learning_rate": 9.66907177209615e-05, + "loss": 0.5437, + "step": 690 + }, + { + "epoch": 0.8974025974025974, + "grad_norm": 7.053062438964844, + "learning_rate": 9.66618635509404e-05, + "loss": 0.7564, + "step": 691 + }, + { + "epoch": 0.8987012987012987, + "grad_norm": 7.324159145355225, + "learning_rate": 9.663288897872576e-05, + "loss": 0.7379, + "step": 692 + }, + { + "epoch": 0.9, + "grad_norm": 6.331752300262451, + "learning_rate": 9.660379408805365e-05, + "loss": 0.6142, + "step": 693 + }, + { + "epoch": 0.9, + "eval_allNLI--triplets-1024_cosine_accuracy": 0.9453125, + "eval_allNLI--triplets-128_cosine_accuracy": 0.90625, + "eval_allNLI--triplets-256_cosine_accuracy": 0.9375, + "eval_allNLI--triplets-32_cosine_accuracy": 0.90625, + "eval_allNLI--triplets-512_cosine_accuracy": 0.9375, + "eval_allNLI-triplets_cosine_accuracy": 0.9375, + "eval_global_dataset_loss": 0.6449323296546936, + "eval_global_dataset_runtime": 113.6072, + "eval_global_dataset_samples_per_second": 9.427, + "eval_global_dataset_steps_per_second": 0.079, + "eval_sequential_score": 0.90625, + "eval_sts-test-1024_pearson_cosine": 0.8851609078570057, + "eval_sts-test-1024_spearman_cosine": 0.9256469608704436, + "eval_sts-test-128_pearson_cosine": 0.8741462790740726, + "eval_sts-test-128_spearman_cosine": 0.9201083411908414, + "eval_sts-test-256_pearson_cosine": 0.876310078043887, + "eval_sts-test-256_spearman_cosine": 0.9244446410770436, + "eval_sts-test-32_pearson_cosine": 0.8577692639868538, + "eval_sts-test-32_spearman_cosine": 0.9079687781785645, + "eval_sts-test-512_pearson_cosine": 0.8840830849913406, + "eval_sts-test-512_spearman_cosine": 0.9270361808818767, + "eval_sts-test-64_pearson_cosine": 0.869592400395789, + "eval_sts-test-64_spearman_cosine": 0.9186414251117587, + "eval_sts-test_pearson_cosine": 0.8862542788008725, + "eval_sts-test_spearman_cosine": 0.9256408740817337, + "step": 693 + }, + { + "epoch": 0.9012987012987013, + "grad_norm": 5.754309177398682, + "learning_rate": 9.657457896300791e-05, + "loss": 0.5799, + "step": 694 + }, + { + "epoch": 0.9025974025974026, + "grad_norm": 6.375608444213867, + "learning_rate": 9.654524368801981e-05, + "loss": 0.5429, + "step": 695 + }, + { + "epoch": 0.9038961038961039, + "grad_norm": 7.073978900909424, + "learning_rate": 9.651578834786792e-05, + "loss": 0.6803, + "step": 696 + }, + { + "epoch": 0.9051948051948052, + "grad_norm": 6.796176910400391, + "learning_rate": 9.648621302767772e-05, + "loss": 0.5692, + "step": 697 + }, + { + "epoch": 0.9064935064935065, + "grad_norm": 7.01423978805542, + "learning_rate": 9.645651781292147e-05, + "loss": 0.665, + "step": 698 + }, + { + "epoch": 0.9077922077922078, + "grad_norm": 7.380173683166504, + "learning_rate": 9.642670278941794e-05, + "loss": 0.7442, + "step": 699 + }, + { + "epoch": 0.9090909090909091, + "grad_norm": 6.801253318786621, + "learning_rate": 9.63967680433321e-05, + "loss": 0.5755, + "step": 700 + }, + { + "epoch": 0.9103896103896104, + "grad_norm": 7.75513219833374, + "learning_rate": 9.636671366117496e-05, + "loss": 0.9233, + "step": 701 + }, + { + "epoch": 0.9116883116883117, + "grad_norm": 7.614108562469482, + "learning_rate": 9.633653972980323e-05, + "loss": 0.8297, + "step": 702 + }, + { + "epoch": 0.912987012987013, + "grad_norm": 6.449255466461182, + "learning_rate": 9.630624633641918e-05, + "loss": 0.7288, + "step": 703 + }, + { + "epoch": 0.9142857142857143, + "grad_norm": 7.443954944610596, + "learning_rate": 9.627583356857026e-05, + "loss": 0.8476, + "step": 704 + }, + { + "epoch": 0.9155844155844156, + "grad_norm": 6.5813679695129395, + "learning_rate": 9.624530151414893e-05, + "loss": 0.6464, + "step": 705 + }, + { + "epoch": 0.9168831168831169, + "grad_norm": 6.9515485763549805, + "learning_rate": 9.621465026139242e-05, + "loss": 0.8881, + "step": 706 + }, + { + "epoch": 0.9181818181818182, + "grad_norm": 6.7394022941589355, + "learning_rate": 9.618387989888239e-05, + "loss": 0.7609, + "step": 707 + }, + { + "epoch": 0.9194805194805195, + "grad_norm": 6.180837631225586, + "learning_rate": 9.615299051554479e-05, + "loss": 0.6834, + "step": 708 + }, + { + "epoch": 0.9207792207792208, + "grad_norm": 7.189302921295166, + "learning_rate": 9.612198220064944e-05, + "loss": 0.8218, + "step": 709 + }, + { + "epoch": 0.922077922077922, + "grad_norm": 7.317821979522705, + "learning_rate": 9.609085504380996e-05, + "loss": 0.7413, + "step": 710 + }, + { + "epoch": 0.9233766233766234, + "grad_norm": 6.8858442306518555, + "learning_rate": 9.605960913498342e-05, + "loss": 0.6379, + "step": 711 + }, + { + "epoch": 0.9246753246753247, + "grad_norm": 7.520847797393799, + "learning_rate": 9.602824456446999e-05, + "loss": 0.8378, + "step": 712 + }, + { + "epoch": 0.925974025974026, + "grad_norm": 6.346597194671631, + "learning_rate": 9.59967614229129e-05, + "loss": 0.5754, + "step": 713 + }, + { + "epoch": 0.9272727272727272, + "grad_norm": 7.224513053894043, + "learning_rate": 9.596515980129792e-05, + "loss": 0.7367, + "step": 714 + }, + { + "epoch": 0.9285714285714286, + "grad_norm": 6.537326812744141, + "learning_rate": 9.593343979095333e-05, + "loss": 0.6389, + "step": 715 + }, + { + "epoch": 0.9298701298701298, + "grad_norm": 5.621442794799805, + "learning_rate": 9.590160148354949e-05, + "loss": 0.4474, + "step": 716 + }, + { + "epoch": 0.9311688311688312, + "grad_norm": 6.461991786956787, + "learning_rate": 9.586964497109868e-05, + "loss": 0.6341, + "step": 717 + }, + { + "epoch": 0.9324675324675324, + "grad_norm": 5.925861358642578, + "learning_rate": 9.583757034595472e-05, + "loss": 0.4793, + "step": 718 + }, + { + "epoch": 0.9337662337662338, + "grad_norm": 6.9430646896362305, + "learning_rate": 9.580537770081285e-05, + "loss": 0.7057, + "step": 719 + }, + { + "epoch": 0.935064935064935, + "grad_norm": 7.913745403289795, + "learning_rate": 9.577306712870936e-05, + "loss": 0.9687, + "step": 720 + }, + { + "epoch": 0.9363636363636364, + "grad_norm": 6.996697425842285, + "learning_rate": 9.574063872302135e-05, + "loss": 0.7017, + "step": 721 + }, + { + "epoch": 0.9376623376623376, + "grad_norm": 7.043035984039307, + "learning_rate": 9.570809257746643e-05, + "loss": 0.7511, + "step": 722 + }, + { + "epoch": 0.938961038961039, + "grad_norm": 7.160142421722412, + "learning_rate": 9.567542878610251e-05, + "loss": 0.7509, + "step": 723 + }, + { + "epoch": 0.9402597402597402, + "grad_norm": 5.701127529144287, + "learning_rate": 9.564264744332748e-05, + "loss": 0.5742, + "step": 724 + }, + { + "epoch": 0.9415584415584416, + "grad_norm": 5.027484893798828, + "learning_rate": 9.560974864387896e-05, + "loss": 0.4425, + "step": 725 + }, + { + "epoch": 0.9428571428571428, + "grad_norm": 6.028113842010498, + "learning_rate": 9.557673248283401e-05, + "loss": 0.5795, + "step": 726 + }, + { + "epoch": 0.9441558441558442, + "grad_norm": 6.112645149230957, + "learning_rate": 9.554359905560886e-05, + "loss": 0.5996, + "step": 727 + }, + { + "epoch": 0.9454545454545454, + "grad_norm": 6.774581432342529, + "learning_rate": 9.551034845795865e-05, + "loss": 0.6483, + "step": 728 + }, + { + "epoch": 0.9467532467532468, + "grad_norm": 6.578814506530762, + "learning_rate": 9.547698078597714e-05, + "loss": 0.6893, + "step": 729 + }, + { + "epoch": 0.948051948051948, + "grad_norm": 6.666228294372559, + "learning_rate": 9.544349613609643e-05, + "loss": 0.5996, + "step": 730 + }, + { + "epoch": 0.9493506493506494, + "grad_norm": 7.729548931121826, + "learning_rate": 9.540989460508666e-05, + "loss": 0.7856, + "step": 731 + }, + { + "epoch": 0.9506493506493506, + "grad_norm": 7.698365211486816, + "learning_rate": 9.53761762900558e-05, + "loss": 0.7376, + "step": 732 + }, + { + "epoch": 0.951948051948052, + "grad_norm": 5.8187255859375, + "learning_rate": 9.53423412884493e-05, + "loss": 0.4758, + "step": 733 + }, + { + "epoch": 0.9532467532467532, + "grad_norm": 6.393637657165527, + "learning_rate": 9.530838969804979e-05, + "loss": 0.52, + "step": 734 + }, + { + "epoch": 0.9545454545454546, + "grad_norm": 7.343430042266846, + "learning_rate": 9.527432161697694e-05, + "loss": 0.6945, + "step": 735 + }, + { + "epoch": 0.9558441558441558, + "grad_norm": 6.76441764831543, + "learning_rate": 9.524013714368701e-05, + "loss": 0.5963, + "step": 736 + }, + { + "epoch": 0.9571428571428572, + "grad_norm": 6.522793769836426, + "learning_rate": 9.520583637697262e-05, + "loss": 0.5071, + "step": 737 + }, + { + "epoch": 0.9584415584415584, + "grad_norm": 7.000353813171387, + "learning_rate": 9.517141941596253e-05, + "loss": 0.7511, + "step": 738 + }, + { + "epoch": 0.9597402597402598, + "grad_norm": 6.261977195739746, + "learning_rate": 9.513688636012124e-05, + "loss": 0.4206, + "step": 739 + }, + { + "epoch": 0.961038961038961, + "grad_norm": 6.369211673736572, + "learning_rate": 9.510223730924879e-05, + "loss": 0.4838, + "step": 740 + }, + { + "epoch": 0.9623376623376624, + "grad_norm": 7.286876678466797, + "learning_rate": 9.506747236348045e-05, + "loss": 0.6777, + "step": 741 + }, + { + "epoch": 0.9636363636363636, + "grad_norm": 7.349566459655762, + "learning_rate": 9.503259162328642e-05, + "loss": 0.7201, + "step": 742 + }, + { + "epoch": 0.964935064935065, + "grad_norm": 6.486627101898193, + "learning_rate": 9.499759518947156e-05, + "loss": 0.5443, + "step": 743 + }, + { + "epoch": 0.9662337662337662, + "grad_norm": 7.116005897521973, + "learning_rate": 9.496248316317504e-05, + "loss": 0.7611, + "step": 744 + }, + { + "epoch": 0.9675324675324676, + "grad_norm": 7.029176712036133, + "learning_rate": 9.492725564587015e-05, + "loss": 0.7433, + "step": 745 + }, + { + "epoch": 0.9688311688311688, + "grad_norm": 8.111961364746094, + "learning_rate": 9.489191273936388e-05, + "loss": 0.8613, + "step": 746 + }, + { + "epoch": 0.9701298701298702, + "grad_norm": 5.125340938568115, + "learning_rate": 9.485645454579674e-05, + "loss": 0.4005, + "step": 747 + }, + { + "epoch": 0.9714285714285714, + "grad_norm": 6.340237617492676, + "learning_rate": 9.482088116764242e-05, + "loss": 0.5841, + "step": 748 + }, + { + "epoch": 0.9727272727272728, + "grad_norm": 6.906500816345215, + "learning_rate": 9.478519270770745e-05, + "loss": 0.7196, + "step": 749 + }, + { + "epoch": 0.974025974025974, + "grad_norm": 6.116445541381836, + "learning_rate": 9.474938926913098e-05, + "loss": 0.5471, + "step": 750 + }, + { + "epoch": 0.9753246753246754, + "grad_norm": 6.587038993835449, + "learning_rate": 9.471347095538446e-05, + "loss": 0.7167, + "step": 751 + }, + { + "epoch": 0.9766233766233766, + "grad_norm": 7.6972222328186035, + "learning_rate": 9.467743787027129e-05, + "loss": 0.7802, + "step": 752 + }, + { + "epoch": 0.977922077922078, + "grad_norm": 5.8324360847473145, + "learning_rate": 9.464129011792657e-05, + "loss": 0.4997, + "step": 753 + }, + { + "epoch": 0.9792207792207792, + "grad_norm": 6.904268741607666, + "learning_rate": 9.46050278028168e-05, + "loss": 0.6485, + "step": 754 + }, + { + "epoch": 0.9805194805194806, + "grad_norm": 7.760578155517578, + "learning_rate": 9.456865102973955e-05, + "loss": 0.7916, + "step": 755 + }, + { + "epoch": 0.9818181818181818, + "grad_norm": 7.374014377593994, + "learning_rate": 9.453215990382317e-05, + "loss": 0.6993, + "step": 756 + }, + { + "epoch": 0.9831168831168832, + "grad_norm": 7.127100944519043, + "learning_rate": 9.449555453052651e-05, + "loss": 0.7207, + "step": 757 + }, + { + "epoch": 0.9844155844155844, + "grad_norm": 6.48353385925293, + "learning_rate": 9.445883501563855e-05, + "loss": 0.6119, + "step": 758 + }, + { + "epoch": 0.9857142857142858, + "grad_norm": 7.246218204498291, + "learning_rate": 9.442200146527823e-05, + "loss": 0.7745, + "step": 759 + }, + { + "epoch": 0.987012987012987, + "grad_norm": 6.130473613739014, + "learning_rate": 9.438505398589392e-05, + "loss": 0.5289, + "step": 760 + }, + { + "epoch": 0.9883116883116884, + "grad_norm": 6.276796340942383, + "learning_rate": 9.434799268426335e-05, + "loss": 0.5566, + "step": 761 + }, + { + "epoch": 0.9896103896103896, + "grad_norm": 7.320113658905029, + "learning_rate": 9.431081766749312e-05, + "loss": 0.8124, + "step": 762 + }, + { + "epoch": 0.990909090909091, + "grad_norm": 6.15302848815918, + "learning_rate": 9.427352904301852e-05, + "loss": 0.632, + "step": 763 + }, + { + "epoch": 0.9922077922077922, + "grad_norm": 5.9906439781188965, + "learning_rate": 9.423612691860316e-05, + "loss": 0.5499, + "step": 764 + }, + { + "epoch": 0.9935064935064936, + "grad_norm": 6.963850498199463, + "learning_rate": 9.419861140233864e-05, + "loss": 0.7703, + "step": 765 + }, + { + "epoch": 0.9948051948051948, + "grad_norm": 6.3005595207214355, + "learning_rate": 9.416098260264425e-05, + "loss": 0.5896, + "step": 766 + }, + { + "epoch": 0.9961038961038962, + "grad_norm": 7.499933242797852, + "learning_rate": 9.41232406282667e-05, + "loss": 0.8109, + "step": 767 + }, + { + "epoch": 0.9974025974025974, + "grad_norm": 6.345822334289551, + "learning_rate": 9.408538558827975e-05, + "loss": 0.6031, + "step": 768 + }, + { + "epoch": 0.9987012987012988, + "grad_norm": 6.637183666229248, + "learning_rate": 9.404741759208395e-05, + "loss": 0.5933, + "step": 769 + }, + { + "epoch": 1.0, + "grad_norm": 6.882605075836182, + "learning_rate": 9.400933674940625e-05, + "loss": 0.5364, + "step": 770 + }, + { + "epoch": 1.0, + "eval_allNLI--triplets-1024_cosine_accuracy": 0.9453125, + "eval_allNLI--triplets-128_cosine_accuracy": 0.9375, + "eval_allNLI--triplets-256_cosine_accuracy": 0.9453125, + "eval_allNLI--triplets-32_cosine_accuracy": 0.921875, + "eval_allNLI--triplets-512_cosine_accuracy": 0.9453125, + "eval_allNLI-triplets_cosine_accuracy": 0.9453125, + "eval_global_dataset_loss": 0.6763572096824646, + "eval_global_dataset_runtime": 113.6773, + "eval_global_dataset_samples_per_second": 9.421, + "eval_global_dataset_steps_per_second": 0.079, + "eval_sequential_score": 0.921875, + "eval_sts-test-1024_pearson_cosine": 0.8891517259069235, + "eval_sts-test-1024_spearman_cosine": 0.9288554146133434, + "eval_sts-test-128_pearson_cosine": 0.8824459040276136, + "eval_sts-test-128_spearman_cosine": 0.9266928143893601, + "eval_sts-test-256_pearson_cosine": 0.8867567584518057, + "eval_sts-test-256_spearman_cosine": 0.9309693205276476, + "eval_sts-test-32_pearson_cosine": 0.8620118716806239, + "eval_sts-test-32_spearman_cosine": 0.9141934147504104, + "eval_sts-test-512_pearson_cosine": 0.8891832703981848, + "eval_sts-test-512_spearman_cosine": 0.9302840197281932, + "eval_sts-test-64_pearson_cosine": 0.8738410245116717, + "eval_sts-test-64_spearman_cosine": 0.9216490148272323, + "eval_sts-test_pearson_cosine": 0.8897698289886751, + "eval_sts-test_spearman_cosine": 0.9294207698705734, + "step": 770 + }, + { + "epoch": 1.0012987012987014, + "grad_norm": 6.3086981773376465, + "learning_rate": 9.397114317029975e-05, + "loss": 0.5231, + "step": 771 + }, + { + "epoch": 1.0025974025974025, + "grad_norm": 6.194589614868164, + "learning_rate": 9.393283696514334e-05, + "loss": 0.5183, + "step": 772 + }, + { + "epoch": 1.0038961038961038, + "grad_norm": 6.340659141540527, + "learning_rate": 9.389441824464144e-05, + "loss": 0.5389, + "step": 773 + }, + { + "epoch": 1.0051948051948052, + "grad_norm": 7.020819664001465, + "learning_rate": 9.385588711982357e-05, + "loss": 0.6834, + "step": 774 + }, + { + "epoch": 1.0064935064935066, + "grad_norm": 5.873781681060791, + "learning_rate": 9.381724370204413e-05, + "loss": 0.5017, + "step": 775 + }, + { + "epoch": 1.0077922077922077, + "grad_norm": 6.680530548095703, + "learning_rate": 9.377848810298209e-05, + "loss": 0.6083, + "step": 776 + }, + { + "epoch": 1.009090909090909, + "grad_norm": 6.47283935546875, + "learning_rate": 9.373962043464056e-05, + "loss": 0.5966, + "step": 777 + }, + { + "epoch": 1.0103896103896104, + "grad_norm": 6.902966499328613, + "learning_rate": 9.370064080934653e-05, + "loss": 0.6968, + "step": 778 + }, + { + "epoch": 1.0116883116883117, + "grad_norm": 6.695742130279541, + "learning_rate": 9.366154933975058e-05, + "loss": 0.6885, + "step": 779 + }, + { + "epoch": 1.0129870129870129, + "grad_norm": 5.6577653884887695, + "learning_rate": 9.362234613882651e-05, + "loss": 0.4656, + "step": 780 + }, + { + "epoch": 1.0142857142857142, + "grad_norm": 5.678228378295898, + "learning_rate": 9.3583031319871e-05, + "loss": 0.5064, + "step": 781 + }, + { + "epoch": 1.0155844155844156, + "grad_norm": 6.301676273345947, + "learning_rate": 9.354360499650332e-05, + "loss": 0.5485, + "step": 782 + }, + { + "epoch": 1.016883116883117, + "grad_norm": 6.376684665679932, + "learning_rate": 9.3504067282665e-05, + "loss": 0.6034, + "step": 783 + }, + { + "epoch": 1.018181818181818, + "grad_norm": 6.012096405029297, + "learning_rate": 9.346441829261944e-05, + "loss": 0.5317, + "step": 784 + }, + { + "epoch": 1.0194805194805194, + "grad_norm": 6.788561820983887, + "learning_rate": 9.342465814095167e-05, + "loss": 0.6418, + "step": 785 + }, + { + "epoch": 1.0207792207792208, + "grad_norm": 6.6580915451049805, + "learning_rate": 9.338478694256798e-05, + "loss": 0.5612, + "step": 786 + }, + { + "epoch": 1.0220779220779221, + "grad_norm": 6.925287246704102, + "learning_rate": 9.334480481269555e-05, + "loss": 0.6258, + "step": 787 + }, + { + "epoch": 1.0233766233766233, + "grad_norm": 5.296406269073486, + "learning_rate": 9.330471186688216e-05, + "loss": 0.44, + "step": 788 + }, + { + "epoch": 1.0246753246753246, + "grad_norm": 5.672299861907959, + "learning_rate": 9.326450822099588e-05, + "loss": 0.5192, + "step": 789 + }, + { + "epoch": 1.025974025974026, + "grad_norm": 7.410915374755859, + "learning_rate": 9.322419399122467e-05, + "loss": 0.7895, + "step": 790 + }, + { + "epoch": 1.0272727272727273, + "grad_norm": 6.18645715713501, + "learning_rate": 9.318376929407607e-05, + "loss": 0.5412, + "step": 791 + }, + { + "epoch": 1.0285714285714285, + "grad_norm": 6.232503414154053, + "learning_rate": 9.314323424637687e-05, + "loss": 0.5783, + "step": 792 + }, + { + "epoch": 1.0298701298701298, + "grad_norm": 7.006043434143066, + "learning_rate": 9.310258896527278e-05, + "loss": 0.7388, + "step": 793 + }, + { + "epoch": 1.0311688311688312, + "grad_norm": 5.843970775604248, + "learning_rate": 9.306183356822812e-05, + "loss": 0.5155, + "step": 794 + }, + { + "epoch": 1.0324675324675325, + "grad_norm": 5.6648783683776855, + "learning_rate": 9.30209681730254e-05, + "loss": 0.5151, + "step": 795 + }, + { + "epoch": 1.0337662337662337, + "grad_norm": 6.363714694976807, + "learning_rate": 9.2979992897765e-05, + "loss": 0.6496, + "step": 796 + }, + { + "epoch": 1.035064935064935, + "grad_norm": 5.969563007354736, + "learning_rate": 9.293890786086489e-05, + "loss": 0.5297, + "step": 797 + }, + { + "epoch": 1.0363636363636364, + "grad_norm": 6.924633026123047, + "learning_rate": 9.289771318106027e-05, + "loss": 0.7569, + "step": 798 + }, + { + "epoch": 1.0376623376623377, + "grad_norm": 6.2910895347595215, + "learning_rate": 9.285640897740315e-05, + "loss": 0.5531, + "step": 799 + }, + { + "epoch": 1.0389610389610389, + "grad_norm": 6.823774814605713, + "learning_rate": 9.281499536926212e-05, + "loss": 0.6787, + "step": 800 + }, + { + "epoch": 1.0402597402597402, + "grad_norm": 6.377769470214844, + "learning_rate": 9.27734724763219e-05, + "loss": 0.6457, + "step": 801 + }, + { + "epoch": 1.0415584415584416, + "grad_norm": 6.330393314361572, + "learning_rate": 9.273184041858306e-05, + "loss": 0.5036, + "step": 802 + }, + { + "epoch": 1.042857142857143, + "grad_norm": 6.70945930480957, + "learning_rate": 9.269009931636166e-05, + "loss": 0.6496, + "step": 803 + }, + { + "epoch": 1.044155844155844, + "grad_norm": 6.34543514251709, + "learning_rate": 9.264824929028889e-05, + "loss": 0.5846, + "step": 804 + }, + { + "epoch": 1.0454545454545454, + "grad_norm": 6.833179950714111, + "learning_rate": 9.260629046131073e-05, + "loss": 0.6225, + "step": 805 + }, + { + "epoch": 1.0467532467532468, + "grad_norm": 5.559639930725098, + "learning_rate": 9.25642229506876e-05, + "loss": 0.4491, + "step": 806 + }, + { + "epoch": 1.0480519480519481, + "grad_norm": 6.042374610900879, + "learning_rate": 9.252204687999402e-05, + "loss": 0.5019, + "step": 807 + }, + { + "epoch": 1.0493506493506493, + "grad_norm": 7.4053215980529785, + "learning_rate": 9.247976237111823e-05, + "loss": 0.6818, + "step": 808 + }, + { + "epoch": 1.0506493506493506, + "grad_norm": 6.882972717285156, + "learning_rate": 9.243736954626186e-05, + "loss": 0.6625, + "step": 809 + }, + { + "epoch": 1.051948051948052, + "grad_norm": 5.182650089263916, + "learning_rate": 9.239486852793952e-05, + "loss": 0.3794, + "step": 810 + }, + { + "epoch": 1.0532467532467533, + "grad_norm": 7.047555923461914, + "learning_rate": 9.235225943897863e-05, + "loss": 0.573, + "step": 811 + }, + { + "epoch": 1.0545454545454545, + "grad_norm": 5.860465049743652, + "learning_rate": 9.230954240251881e-05, + "loss": 0.4855, + "step": 812 + }, + { + "epoch": 1.0558441558441558, + "grad_norm": 6.186687469482422, + "learning_rate": 9.226671754201169e-05, + "loss": 0.5567, + "step": 813 + }, + { + "epoch": 1.0571428571428572, + "grad_norm": 6.923488616943359, + "learning_rate": 9.222378498122052e-05, + "loss": 0.5972, + "step": 814 + }, + { + "epoch": 1.0584415584415585, + "grad_norm": 5.582354545593262, + "learning_rate": 9.218074484421978e-05, + "loss": 0.493, + "step": 815 + }, + { + "epoch": 1.0597402597402596, + "grad_norm": 5.751039028167725, + "learning_rate": 9.213759725539484e-05, + "loss": 0.4468, + "step": 816 + }, + { + "epoch": 1.061038961038961, + "grad_norm": 6.912971496582031, + "learning_rate": 9.209434233944167e-05, + "loss": 0.6582, + "step": 817 + }, + { + "epoch": 1.0623376623376624, + "grad_norm": 6.241170406341553, + "learning_rate": 9.20509802213663e-05, + "loss": 0.6123, + "step": 818 + }, + { + "epoch": 1.0636363636363637, + "grad_norm": 6.001036167144775, + "learning_rate": 9.200751102648467e-05, + "loss": 0.49, + "step": 819 + }, + { + "epoch": 1.0649350649350648, + "grad_norm": 6.102304458618164, + "learning_rate": 9.196393488042213e-05, + "loss": 0.5702, + "step": 820 + }, + { + "epoch": 1.0662337662337662, + "grad_norm": 6.685356140136719, + "learning_rate": 9.192025190911312e-05, + "loss": 0.6142, + "step": 821 + }, + { + "epoch": 1.0675324675324676, + "grad_norm": 5.738699913024902, + "learning_rate": 9.18764622388008e-05, + "loss": 0.4589, + "step": 822 + }, + { + "epoch": 1.068831168831169, + "grad_norm": 6.65635347366333, + "learning_rate": 9.183256599603671e-05, + "loss": 0.6596, + "step": 823 + }, + { + "epoch": 1.07012987012987, + "grad_norm": 6.769857406616211, + "learning_rate": 9.178856330768036e-05, + "loss": 0.6645, + "step": 824 + }, + { + "epoch": 1.0714285714285714, + "grad_norm": 6.2122368812561035, + "learning_rate": 9.17444543008989e-05, + "loss": 0.5507, + "step": 825 + }, + { + "epoch": 1.0727272727272728, + "grad_norm": 6.053091049194336, + "learning_rate": 9.17002391031667e-05, + "loss": 0.5414, + "step": 826 + }, + { + "epoch": 1.074025974025974, + "grad_norm": 5.982730388641357, + "learning_rate": 9.165591784226511e-05, + "loss": 0.4573, + "step": 827 + }, + { + "epoch": 1.0753246753246752, + "grad_norm": 5.181983947753906, + "learning_rate": 9.16114906462819e-05, + "loss": 0.4044, + "step": 828 + }, + { + "epoch": 1.0766233766233766, + "grad_norm": 6.529760360717773, + "learning_rate": 9.156695764361107e-05, + "loss": 0.5288, + "step": 829 + }, + { + "epoch": 1.077922077922078, + "grad_norm": 5.713877201080322, + "learning_rate": 9.152231896295232e-05, + "loss": 0.473, + "step": 830 + }, + { + "epoch": 1.0792207792207793, + "grad_norm": 5.574084281921387, + "learning_rate": 9.147757473331082e-05, + "loss": 0.4046, + "step": 831 + }, + { + "epoch": 1.0805194805194804, + "grad_norm": 6.5338358879089355, + "learning_rate": 9.143272508399678e-05, + "loss": 0.5648, + "step": 832 + }, + { + "epoch": 1.0818181818181818, + "grad_norm": 7.523197174072266, + "learning_rate": 9.138777014462503e-05, + "loss": 0.7126, + "step": 833 + }, + { + "epoch": 1.0831168831168831, + "grad_norm": 7.040456295013428, + "learning_rate": 9.13427100451147e-05, + "loss": 0.5931, + "step": 834 + }, + { + "epoch": 1.0844155844155845, + "grad_norm": 5.61920166015625, + "learning_rate": 9.129754491568886e-05, + "loss": 0.5465, + "step": 835 + }, + { + "epoch": 1.0857142857142856, + "grad_norm": 5.607574462890625, + "learning_rate": 9.125227488687407e-05, + "loss": 0.4738, + "step": 836 + }, + { + "epoch": 1.087012987012987, + "grad_norm": 6.3649516105651855, + "learning_rate": 9.120690008950008e-05, + "loss": 0.5459, + "step": 837 + }, + { + "epoch": 1.0883116883116883, + "grad_norm": 5.816140174865723, + "learning_rate": 9.11614206546994e-05, + "loss": 0.4774, + "step": 838 + }, + { + "epoch": 1.0896103896103897, + "grad_norm": 5.179698467254639, + "learning_rate": 9.111583671390697e-05, + "loss": 0.3781, + "step": 839 + }, + { + "epoch": 1.0909090909090908, + "grad_norm": 5.196139812469482, + "learning_rate": 9.107014839885971e-05, + "loss": 0.4029, + "step": 840 + }, + { + "epoch": 1.0922077922077922, + "grad_norm": 5.626153945922852, + "learning_rate": 9.102435584159622e-05, + "loss": 0.516, + "step": 841 + }, + { + "epoch": 1.0935064935064935, + "grad_norm": 6.147073745727539, + "learning_rate": 9.097845917445633e-05, + "loss": 0.558, + "step": 842 + }, + { + "epoch": 1.094805194805195, + "grad_norm": 6.763444423675537, + "learning_rate": 9.093245853008076e-05, + "loss": 0.6146, + "step": 843 + }, + { + "epoch": 1.096103896103896, + "grad_norm": 7.35480260848999, + "learning_rate": 9.088635404141069e-05, + "loss": 0.6729, + "step": 844 + }, + { + "epoch": 1.0974025974025974, + "grad_norm": 5.741674900054932, + "learning_rate": 9.084014584168747e-05, + "loss": 0.4631, + "step": 845 + }, + { + "epoch": 1.0987012987012987, + "grad_norm": 6.2829484939575195, + "learning_rate": 9.079383406445214e-05, + "loss": 0.5166, + "step": 846 + }, + { + "epoch": 1.1, + "grad_norm": 7.058021545410156, + "learning_rate": 9.074741884354506e-05, + "loss": 0.6677, + "step": 847 + }, + { + "epoch": 1.1, + "eval_allNLI--triplets-1024_cosine_accuracy": 0.9296875, + "eval_allNLI--triplets-128_cosine_accuracy": 0.921875, + "eval_allNLI--triplets-256_cosine_accuracy": 0.921875, + "eval_allNLI--triplets-32_cosine_accuracy": 0.9140625, + "eval_allNLI--triplets-512_cosine_accuracy": 0.921875, + "eval_allNLI-triplets_cosine_accuracy": 0.9296875, + "eval_global_dataset_loss": 0.7927160263061523, + "eval_global_dataset_runtime": 113.5705, + "eval_global_dataset_samples_per_second": 9.43, + "eval_global_dataset_steps_per_second": 0.079, + "eval_sequential_score": 0.9140625, + "eval_sts-test-1024_pearson_cosine": 0.8833424951570886, + "eval_sts-test-1024_spearman_cosine": 0.9211738872614664, + "eval_sts-test-128_pearson_cosine": 0.8763123791960121, + "eval_sts-test-128_spearman_cosine": 0.9178787862910495, + "eval_sts-test-256_pearson_cosine": 0.8816487151898631, + "eval_sts-test-256_spearman_cosine": 0.9213876409591016, + "eval_sts-test-32_pearson_cosine": 0.8488917028735847, + "eval_sts-test-32_spearman_cosine": 0.9061946582928297, + "eval_sts-test-512_pearson_cosine": 0.8854829980855135, + "eval_sts-test-512_spearman_cosine": 0.9220568296707946, + "eval_sts-test-64_pearson_cosine": 0.8676984844858082, + "eval_sts-test-64_spearman_cosine": 0.9131711922935439, + "eval_sts-test_pearson_cosine": 0.88398317384196, + "eval_sts-test_spearman_cosine": 0.9202243482227238, + "step": 847 + }, + { + "epoch": 1.1012987012987012, + "grad_norm": 5.547793865203857, + "learning_rate": 9.070090031310558e-05, + "loss": 0.4758, + "step": 848 + }, + { + "epoch": 1.1025974025974026, + "grad_norm": 7.1977105140686035, + "learning_rate": 9.065427860757159e-05, + "loss": 0.6897, + "step": 849 + }, + { + "epoch": 1.103896103896104, + "grad_norm": 6.090529441833496, + "learning_rate": 9.060755386167912e-05, + "loss": 0.5571, + "step": 850 + }, + { + "epoch": 1.1051948051948053, + "grad_norm": 7.271042823791504, + "learning_rate": 9.056072621046206e-05, + "loss": 0.7302, + "step": 851 + }, + { + "epoch": 1.1064935064935064, + "grad_norm": 6.639366149902344, + "learning_rate": 9.051379578925165e-05, + "loss": 0.5423, + "step": 852 + }, + { + "epoch": 1.1077922077922078, + "grad_norm": 6.408458709716797, + "learning_rate": 9.046676273367613e-05, + "loss": 0.6124, + "step": 853 + }, + { + "epoch": 1.1090909090909091, + "grad_norm": 6.25244665145874, + "learning_rate": 9.041962717966035e-05, + "loss": 0.5472, + "step": 854 + }, + { + "epoch": 1.1103896103896105, + "grad_norm": 6.482189178466797, + "learning_rate": 9.037238926342544e-05, + "loss": 0.6467, + "step": 855 + }, + { + "epoch": 1.1116883116883116, + "grad_norm": 5.9097490310668945, + "learning_rate": 9.032504912148826e-05, + "loss": 0.5758, + "step": 856 + }, + { + "epoch": 1.112987012987013, + "grad_norm": 6.042409896850586, + "learning_rate": 9.027760689066116e-05, + "loss": 0.5486, + "step": 857 + }, + { + "epoch": 1.1142857142857143, + "grad_norm": 6.9155964851379395, + "learning_rate": 9.023006270805151e-05, + "loss": 0.7601, + "step": 858 + }, + { + "epoch": 1.1155844155844157, + "grad_norm": 5.6852850914001465, + "learning_rate": 9.018241671106134e-05, + "loss": 0.48, + "step": 859 + }, + { + "epoch": 1.1168831168831168, + "grad_norm": 4.734926223754883, + "learning_rate": 9.01346690373869e-05, + "loss": 0.3987, + "step": 860 + }, + { + "epoch": 1.1181818181818182, + "grad_norm": 5.621240139007568, + "learning_rate": 9.008681982501825e-05, + "loss": 0.5175, + "step": 861 + }, + { + "epoch": 1.1194805194805195, + "grad_norm": 5.820254325866699, + "learning_rate": 9.003886921223899e-05, + "loss": 0.546, + "step": 862 + }, + { + "epoch": 1.1207792207792209, + "grad_norm": 5.572368621826172, + "learning_rate": 8.999081733762568e-05, + "loss": 0.4782, + "step": 863 + }, + { + "epoch": 1.122077922077922, + "grad_norm": 6.293596267700195, + "learning_rate": 8.994266434004755e-05, + "loss": 0.5394, + "step": 864 + }, + { + "epoch": 1.1233766233766234, + "grad_norm": 6.250242233276367, + "learning_rate": 8.989441035866606e-05, + "loss": 0.5649, + "step": 865 + }, + { + "epoch": 1.1246753246753247, + "grad_norm": 6.430608749389648, + "learning_rate": 8.984605553293461e-05, + "loss": 0.6247, + "step": 866 + }, + { + "epoch": 1.1259740259740258, + "grad_norm": 5.867380142211914, + "learning_rate": 8.979760000259787e-05, + "loss": 0.5004, + "step": 867 + }, + { + "epoch": 1.1272727272727272, + "grad_norm": 5.570036888122559, + "learning_rate": 8.974904390769168e-05, + "loss": 0.4551, + "step": 868 + }, + { + "epoch": 1.1285714285714286, + "grad_norm": 5.702778339385986, + "learning_rate": 8.970038738854245e-05, + "loss": 0.4896, + "step": 869 + }, + { + "epoch": 1.12987012987013, + "grad_norm": 6.742293357849121, + "learning_rate": 8.965163058576683e-05, + "loss": 0.5858, + "step": 870 + }, + { + "epoch": 1.1311688311688313, + "grad_norm": 7.0269036293029785, + "learning_rate": 8.96027736402713e-05, + "loss": 0.6222, + "step": 871 + }, + { + "epoch": 1.1324675324675324, + "grad_norm": 7.605057239532471, + "learning_rate": 8.955381669325171e-05, + "loss": 0.6812, + "step": 872 + }, + { + "epoch": 1.1337662337662338, + "grad_norm": 6.691396713256836, + "learning_rate": 8.950475988619298e-05, + "loss": 0.6444, + "step": 873 + }, + { + "epoch": 1.135064935064935, + "grad_norm": 5.929075241088867, + "learning_rate": 8.945560336086855e-05, + "loss": 0.4732, + "step": 874 + }, + { + "epoch": 1.1363636363636362, + "grad_norm": 6.509552001953125, + "learning_rate": 8.94063472593401e-05, + "loss": 0.4766, + "step": 875 + }, + { + "epoch": 1.1376623376623376, + "grad_norm": 6.235232353210449, + "learning_rate": 8.935699172395707e-05, + "loss": 0.5361, + "step": 876 + }, + { + "epoch": 1.138961038961039, + "grad_norm": 6.687936305999756, + "learning_rate": 8.930753689735622e-05, + "loss": 0.6461, + "step": 877 + }, + { + "epoch": 1.1402597402597403, + "grad_norm": 6.929695129394531, + "learning_rate": 8.925798292246134e-05, + "loss": 0.6055, + "step": 878 + }, + { + "epoch": 1.1415584415584417, + "grad_norm": 6.169885635375977, + "learning_rate": 8.920832994248267e-05, + "loss": 0.5212, + "step": 879 + }, + { + "epoch": 1.1428571428571428, + "grad_norm": 5.577329158782959, + "learning_rate": 8.915857810091665e-05, + "loss": 0.5049, + "step": 880 + }, + { + "epoch": 1.1441558441558441, + "grad_norm": 6.382843971252441, + "learning_rate": 8.910872754154539e-05, + "loss": 0.6102, + "step": 881 + }, + { + "epoch": 1.1454545454545455, + "grad_norm": 6.197054386138916, + "learning_rate": 8.90587784084363e-05, + "loss": 0.5279, + "step": 882 + }, + { + "epoch": 1.1467532467532466, + "grad_norm": 6.374361991882324, + "learning_rate": 8.900873084594164e-05, + "loss": 0.6135, + "step": 883 + }, + { + "epoch": 1.148051948051948, + "grad_norm": 5.588046073913574, + "learning_rate": 8.895858499869816e-05, + "loss": 0.4196, + "step": 884 + }, + { + "epoch": 1.1493506493506493, + "grad_norm": 6.311435699462891, + "learning_rate": 8.890834101162668e-05, + "loss": 0.634, + "step": 885 + }, + { + "epoch": 1.1506493506493507, + "grad_norm": 5.719446182250977, + "learning_rate": 8.885799902993157e-05, + "loss": 0.5867, + "step": 886 + }, + { + "epoch": 1.151948051948052, + "grad_norm": 6.009184837341309, + "learning_rate": 8.880755919910047e-05, + "loss": 0.5583, + "step": 887 + }, + { + "epoch": 1.1532467532467532, + "grad_norm": 5.596704959869385, + "learning_rate": 8.875702166490373e-05, + "loss": 0.4851, + "step": 888 + }, + { + "epoch": 1.1545454545454545, + "grad_norm": 5.781062602996826, + "learning_rate": 8.870638657339417e-05, + "loss": 0.5288, + "step": 889 + }, + { + "epoch": 1.155844155844156, + "grad_norm": 8.139880180358887, + "learning_rate": 8.865565407090644e-05, + "loss": 0.8795, + "step": 890 + }, + { + "epoch": 1.157142857142857, + "grad_norm": 5.296769618988037, + "learning_rate": 8.860482430405678e-05, + "loss": 0.4514, + "step": 891 + }, + { + "epoch": 1.1584415584415584, + "grad_norm": 6.376003265380859, + "learning_rate": 8.855389741974244e-05, + "loss": 0.5311, + "step": 892 + }, + { + "epoch": 1.1597402597402597, + "grad_norm": 3.899746894836426, + "learning_rate": 8.850287356514146e-05, + "loss": 0.2328, + "step": 893 + }, + { + "epoch": 1.161038961038961, + "grad_norm": 6.138718605041504, + "learning_rate": 8.845175288771201e-05, + "loss": 0.4935, + "step": 894 + }, + { + "epoch": 1.1623376623376624, + "grad_norm": 6.556604385375977, + "learning_rate": 8.840053553519215e-05, + "loss": 0.605, + "step": 895 + }, + { + "epoch": 1.1636363636363636, + "grad_norm": 6.4802374839782715, + "learning_rate": 8.834922165559927e-05, + "loss": 0.5583, + "step": 896 + }, + { + "epoch": 1.164935064935065, + "grad_norm": 7.814708232879639, + "learning_rate": 8.829781139722979e-05, + "loss": 0.7555, + "step": 897 + }, + { + "epoch": 1.1662337662337663, + "grad_norm": 4.639040470123291, + "learning_rate": 8.824630490865858e-05, + "loss": 0.3022, + "step": 898 + }, + { + "epoch": 1.1675324675324674, + "grad_norm": 5.5277533531188965, + "learning_rate": 8.819470233873868e-05, + "loss": 0.4693, + "step": 899 + }, + { + "epoch": 1.1688311688311688, + "grad_norm": 7.185070514678955, + "learning_rate": 8.81430038366008e-05, + "loss": 0.6197, + "step": 900 + }, + { + "epoch": 1.1701298701298701, + "grad_norm": 6.97157096862793, + "learning_rate": 8.809120955165288e-05, + "loss": 0.5576, + "step": 901 + }, + { + "epoch": 1.1714285714285715, + "grad_norm": 7.55079460144043, + "learning_rate": 8.803931963357962e-05, + "loss": 0.6272, + "step": 902 + }, + { + "epoch": 1.1727272727272728, + "grad_norm": 7.3252153396606445, + "learning_rate": 8.798733423234218e-05, + "loss": 0.6684, + "step": 903 + }, + { + "epoch": 1.174025974025974, + "grad_norm": 6.965551853179932, + "learning_rate": 8.793525349817765e-05, + "loss": 0.6356, + "step": 904 + }, + { + "epoch": 1.1753246753246753, + "grad_norm": 7.822068214416504, + "learning_rate": 8.788307758159859e-05, + "loss": 0.729, + "step": 905 + }, + { + "epoch": 1.1766233766233767, + "grad_norm": 6.392927646636963, + "learning_rate": 8.783080663339264e-05, + "loss": 0.5553, + "step": 906 + }, + { + "epoch": 1.1779220779220778, + "grad_norm": 5.718196868896484, + "learning_rate": 8.777844080462212e-05, + "loss": 0.466, + "step": 907 + }, + { + "epoch": 1.1792207792207792, + "grad_norm": 4.9061384201049805, + "learning_rate": 8.772598024662351e-05, + "loss": 0.4107, + "step": 908 + }, + { + "epoch": 1.1805194805194805, + "grad_norm": 7.346360683441162, + "learning_rate": 8.767342511100712e-05, + "loss": 0.8187, + "step": 909 + }, + { + "epoch": 1.1818181818181819, + "grad_norm": 6.1015801429748535, + "learning_rate": 8.762077554965651e-05, + "loss": 0.5597, + "step": 910 + }, + { + "epoch": 1.1831168831168832, + "grad_norm": 6.522135257720947, + "learning_rate": 8.756803171472816e-05, + "loss": 0.6618, + "step": 911 + }, + { + "epoch": 1.1844155844155844, + "grad_norm": 5.506206035614014, + "learning_rate": 8.751519375865103e-05, + "loss": 0.5037, + "step": 912 + }, + { + "epoch": 1.1857142857142857, + "grad_norm": 6.1652302742004395, + "learning_rate": 8.746226183412603e-05, + "loss": 0.6033, + "step": 913 + }, + { + "epoch": 1.187012987012987, + "grad_norm": 4.877734184265137, + "learning_rate": 8.74092360941257e-05, + "loss": 0.3695, + "step": 914 + }, + { + "epoch": 1.1883116883116882, + "grad_norm": 6.115694522857666, + "learning_rate": 8.735611669189365e-05, + "loss": 0.5632, + "step": 915 + }, + { + "epoch": 1.1896103896103896, + "grad_norm": 6.231703281402588, + "learning_rate": 8.730290378094422e-05, + "loss": 0.6387, + "step": 916 + }, + { + "epoch": 1.190909090909091, + "grad_norm": 5.317518711090088, + "learning_rate": 8.724959751506196e-05, + "loss": 0.4989, + "step": 917 + }, + { + "epoch": 1.1922077922077923, + "grad_norm": 6.745793342590332, + "learning_rate": 8.71961980483012e-05, + "loss": 0.7159, + "step": 918 + }, + { + "epoch": 1.1935064935064936, + "grad_norm": 5.351443767547607, + "learning_rate": 8.714270553498567e-05, + "loss": 0.4639, + "step": 919 + }, + { + "epoch": 1.1948051948051948, + "grad_norm": 5.908309459686279, + "learning_rate": 8.708912012970796e-05, + "loss": 0.52, + "step": 920 + }, + { + "epoch": 1.1961038961038961, + "grad_norm": 5.1110687255859375, + "learning_rate": 8.703544198732911e-05, + "loss": 0.431, + "step": 921 + }, + { + "epoch": 1.1974025974025975, + "grad_norm": 5.573983669281006, + "learning_rate": 8.698167126297823e-05, + "loss": 0.5008, + "step": 922 + }, + { + "epoch": 1.1987012987012986, + "grad_norm": 6.01815938949585, + "learning_rate": 8.692780811205192e-05, + "loss": 0.5209, + "step": 923 + }, + { + "epoch": 1.2, + "grad_norm": 5.274326801300049, + "learning_rate": 8.687385269021392e-05, + "loss": 0.4301, + "step": 924 + }, + { + "epoch": 1.2, + "eval_allNLI--triplets-1024_cosine_accuracy": 0.9296875, + "eval_allNLI--triplets-128_cosine_accuracy": 0.9296875, + "eval_allNLI--triplets-256_cosine_accuracy": 0.9296875, + "eval_allNLI--triplets-32_cosine_accuracy": 0.921875, + "eval_allNLI--triplets-512_cosine_accuracy": 0.9296875, + "eval_allNLI-triplets_cosine_accuracy": 0.9296875, + "eval_global_dataset_loss": 0.6650819778442383, + "eval_global_dataset_runtime": 113.6493, + "eval_global_dataset_samples_per_second": 9.424, + "eval_global_dataset_steps_per_second": 0.079, + "eval_sequential_score": 0.921875, + "eval_sts-test-1024_pearson_cosine": 0.885149365257635, + "eval_sts-test-1024_spearman_cosine": 0.9258567760577375, + "eval_sts-test-128_pearson_cosine": 0.880812025351224, + "eval_sts-test-128_spearman_cosine": 0.9247529190228797, + "eval_sts-test-256_pearson_cosine": 0.8861095686328364, + "eval_sts-test-256_spearman_cosine": 0.9268503548030278, + "eval_sts-test-32_pearson_cosine": 0.8553627166015102, + "eval_sts-test-32_spearman_cosine": 0.9153789063632594, + "eval_sts-test-512_pearson_cosine": 0.88725994150817, + "eval_sts-test-512_spearman_cosine": 0.9272581696465901, + "eval_sts-test-64_pearson_cosine": 0.8741180224496476, + "eval_sts-test-64_spearman_cosine": 0.922292066152112, + "eval_sts-test_pearson_cosine": 0.8878947010894737, + "eval_sts-test_spearman_cosine": 0.9258002047273748, + "step": 924 + } + ], + "logging_steps": 1, + "max_steps": 2310, + "num_input_tokens_seen": 0, + "num_train_epochs": 3, + "save_steps": 231, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 0.0, + "train_batch_size": 192, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-924/training_args.bin b/checkpoint-924/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..792c593f3faf30c2f0b16520bd3c97d97741b53a --- /dev/null +++ b/checkpoint-924/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fadd592bad93c127ab2cc1e37bb17c0477dfea67bb61a8baf05d9892c2d39d8 +size 5880