Training in progress, step 231

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

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
+}

eval/similarity_evaluation_sts-test-1024_results.csv

@@ -0,0 +1,4 @@
+epoch,steps,cosine_pearson,cosine_spearman
+0.1,77,0.8570094674494524,0.9032869635214775
+0.2,154,0.8637686212043777,0.9158389959804479
+0.3,231,0.8787763074934598,0.9210331750283494

eval/similarity_evaluation_sts-test-128_results.csv

@@ -0,0 +1,4 @@
+epoch,steps,cosine_pearson,cosine_spearman
+0.1,77,0.8454774972598778,0.8941657316165149
+0.2,154,0.8587735042324499,0.9079734327816954
+0.3,231,0.8722131705651872,0.9158898385684954

eval/similarity_evaluation_sts-test-256_results.csv

@@ -0,0 +1,4 @@
+epoch,steps,cosine_pearson,cosine_spearman
+0.1,77,0.846547357013354,0.8961152942356522
+0.2,154,0.8614854438059253,0.9113397849846575
+0.3,231,0.8732650189534636,0.9174469823390422

eval/similarity_evaluation_sts-test-32_results.csv

@@ -0,0 +1,4 @@
+epoch,steps,cosine_pearson,cosine_spearman
+0.1,77,0.8158296423835969,0.8781449456856982
+0.2,154,0.8204607604412608,0.8866968838230891
+0.3,231,0.8348374873613509,0.8928345151210231

eval/similarity_evaluation_sts-test-512_results.csv

@@ -0,0 +1,4 @@
+epoch,steps,cosine_pearson,cosine_spearman
+0.1,77,0.8548761563192739,0.9013753538201782
+0.2,154,0.8636960327159487,0.9151565595521514
+0.3,231,0.8784119512407846,0.9211549108025473

eval/similarity_evaluation_sts-test-64_results.csv

@@ -0,0 +1,4 @@
+epoch,steps,cosine_pearson,cosine_spearman
+0.1,77,0.8326302932611978,0.8899336232311702
+0.2,154,0.8415761749347184,0.9004612613745113
+0.3,231,0.8606305478646585,0.9075380483657413

eval/similarity_evaluation_sts-test_results.csv

@@ -0,0 +1,4 @@
+epoch,steps,cosine_pearson,cosine_spearman
+0.1,77,0.8635863698279433,0.906139519148046
+0.2,154,0.8701225080029533,0.9182271654330917
+0.3,231,0.8837500780432396,0.9228735334971034

eval/triplet_evaluation_allNLI--triplets-1024_results.csv

@@ -0,0 +1,4 @@
+epoch,steps,accuracy_cosine
+0.1,77,0.9453125
+0.2,154,0.9375
+0.3,231,0.953125

eval/triplet_evaluation_allNLI--triplets-128_results.csv

@@ -0,0 +1,7 @@
+epoch,steps,accuracy_cosine
+0.1,77,0.9140625
+0.1,77,0.90625
+0.2,154,0.921875
+0.2,154,0.90625
+0.3,231,0.9296875
+0.3,231,0.8984375

eval/triplet_evaluation_allNLI--triplets-256_results.csv

@@ -0,0 +1,4 @@
+epoch,steps,accuracy_cosine
+0.1,77,0.9296875
+0.2,154,0.90625
+0.3,231,0.921875

eval/triplet_evaluation_allNLI--triplets-32_results.csv

@@ -0,0 +1,4 @@
+epoch,steps,accuracy_cosine
+0.1,77,0.9140625
+0.2,154,0.9140625
+0.3,231,0.9140625

eval/triplet_evaluation_allNLI--triplets-512_results.csv

@@ -0,0 +1,4 @@
+epoch,steps,accuracy_cosine
+0.1,77,0.9375
+0.2,154,0.921875
+0.3,231,0.9375

eval/triplet_evaluation_allNLI-triplets_results.csv

@@ -0,0 +1,4 @@
+epoch,steps,accuracy_cosine
+0.1,77,0.9375
+0.2,154,0.9453125
+0.3,231,0.9453125

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e969b03be79a3f792216f1febef058e86c2b7f27374fb1e044d87938ceea1ba
+size 2271151270

runs/Apr28_01-50-34_27bc822c91b2/events.out.tfevents.1745805038.27bc822c91b2.19.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44afa943f4f62b62d05a07506d4afe1b8e56af25e519efc396da53f93300619c
+size 58328

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9a6af42442a3e3e9f05f618eae0bb2d98ca4f6a6406cb80ef7a4fa865204d61
+size 17083052

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fadd592bad93c127ab2cc1e37bb17c0477dfea67bb61a8baf05d9892c2d39d8
+size 5880