Model save
Browse files- README.md +68 -0
- adapter_model.safetensors +1 -1
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +1172 -0
README.md
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- sft
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: mistralai/Mistral-7B-Instruct-v0.2
|
| 9 |
+
model-index:
|
| 10 |
+
- name: Mistral-7B-Instruct-v0.2-mirage-gpt-4o-sft-instruct-mistral
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# Mistral-7B-Instruct-v0.2-mirage-gpt-4o-sft-instruct-mistral
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.2326
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 0.0002
|
| 41 |
+
- train_batch_size: 8
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- distributed_type: multi-GPU
|
| 45 |
+
- num_devices: 4
|
| 46 |
+
- total_train_batch_size: 32
|
| 47 |
+
- total_eval_batch_size: 32
|
| 48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
+
- lr_scheduler_type: cosine
|
| 50 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 51 |
+
- num_epochs: 1
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 56 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 57 |
+
| 0.3189 | 0.2535 | 200 | 0.2828 |
|
| 58 |
+
| 0.2906 | 0.5070 | 400 | 0.2465 |
|
| 59 |
+
| 0.2525 | 0.7605 | 600 | 0.2326 |
|
| 60 |
+
|
| 61 |
+
|
| 62 |
+
### Framework versions
|
| 63 |
+
|
| 64 |
+
- PEFT 0.7.1
|
| 65 |
+
- Transformers 4.41.2
|
| 66 |
+
- Pytorch 2.3.0+cu121
|
| 67 |
+
- Datasets 2.20.0
|
| 68 |
+
- Tokenizers 0.19.1
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 83946192
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:421842c06b301217070ca85feb1cc9a24bb21739151f1c272bc36fd434a3c933
|
| 3 |
size 83946192
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 1.0371979095834624e+16,
|
| 4 |
+
"train_loss": 0.2726454405050314,
|
| 5 |
+
"train_runtime": 20804.2809,
|
| 6 |
+
"train_samples": 25235,
|
| 7 |
+
"train_samples_per_second": 1.213,
|
| 8 |
+
"train_steps_per_second": 0.038
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 1.0371979095834624e+16,
|
| 4 |
+
"train_loss": 0.2726454405050314,
|
| 5 |
+
"train_runtime": 20804.2809,
|
| 6 |
+
"train_samples": 25235,
|
| 7 |
+
"train_samples_per_second": 1.213,
|
| 8 |
+
"train_steps_per_second": 0.038
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1172 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 200,
|
| 6 |
+
"global_step": 789,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0012674271229404308,
|
| 13 |
+
"grad_norm": 0.8615043469450224,
|
| 14 |
+
"learning_rate": 2.531645569620253e-06,
|
| 15 |
+
"loss": 0.479,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0063371356147021544,
|
| 20 |
+
"grad_norm": 1.2064683000577734,
|
| 21 |
+
"learning_rate": 1.2658227848101267e-05,
|
| 22 |
+
"loss": 0.5395,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.012674271229404309,
|
| 27 |
+
"grad_norm": 1.0410453983480228,
|
| 28 |
+
"learning_rate": 2.5316455696202533e-05,
|
| 29 |
+
"loss": 0.6061,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.019011406844106463,
|
| 34 |
+
"grad_norm": 0.6487558463156515,
|
| 35 |
+
"learning_rate": 3.79746835443038e-05,
|
| 36 |
+
"loss": 0.5462,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.025348542458808618,
|
| 41 |
+
"grad_norm": 0.5370587969238408,
|
| 42 |
+
"learning_rate": 5.0632911392405066e-05,
|
| 43 |
+
"loss": 0.4583,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.031685678073510776,
|
| 48 |
+
"grad_norm": 0.5034416625324662,
|
| 49 |
+
"learning_rate": 6.329113924050633e-05,
|
| 50 |
+
"loss": 0.4883,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03802281368821293,
|
| 55 |
+
"grad_norm": 0.39983399371170963,
|
| 56 |
+
"learning_rate": 7.59493670886076e-05,
|
| 57 |
+
"loss": 0.3405,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.044359949302915085,
|
| 62 |
+
"grad_norm": 0.43348705894690165,
|
| 63 |
+
"learning_rate": 8.860759493670887e-05,
|
| 64 |
+
"loss": 0.4164,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.050697084917617236,
|
| 69 |
+
"grad_norm": 0.38455150629020124,
|
| 70 |
+
"learning_rate": 0.00010126582278481013,
|
| 71 |
+
"loss": 0.3655,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.057034220532319393,
|
| 76 |
+
"grad_norm": 0.4620346635793738,
|
| 77 |
+
"learning_rate": 0.0001139240506329114,
|
| 78 |
+
"loss": 0.321,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.06337135614702155,
|
| 83 |
+
"grad_norm": 0.5487179791839946,
|
| 84 |
+
"learning_rate": 0.00012658227848101267,
|
| 85 |
+
"loss": 0.3917,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.0697084917617237,
|
| 90 |
+
"grad_norm": 0.4322988318215336,
|
| 91 |
+
"learning_rate": 0.00013924050632911395,
|
| 92 |
+
"loss": 0.2954,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.07604562737642585,
|
| 97 |
+
"grad_norm": 0.45659465975830865,
|
| 98 |
+
"learning_rate": 0.0001518987341772152,
|
| 99 |
+
"loss": 0.3362,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.08238276299112801,
|
| 104 |
+
"grad_norm": 0.5012029391973714,
|
| 105 |
+
"learning_rate": 0.00016455696202531648,
|
| 106 |
+
"loss": 0.3201,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.08871989860583017,
|
| 111 |
+
"grad_norm": 0.4257121777036391,
|
| 112 |
+
"learning_rate": 0.00017721518987341773,
|
| 113 |
+
"loss": 0.3103,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.09505703422053231,
|
| 118 |
+
"grad_norm": 0.49930786967179713,
|
| 119 |
+
"learning_rate": 0.00018987341772151899,
|
| 120 |
+
"loss": 0.3895,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.10139416983523447,
|
| 125 |
+
"grad_norm": 0.3987283812690162,
|
| 126 |
+
"learning_rate": 0.00019999902106840922,
|
| 127 |
+
"loss": 0.2607,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.10773130544993663,
|
| 132 |
+
"grad_norm": 0.4941124105408692,
|
| 133 |
+
"learning_rate": 0.00019996476047513454,
|
| 134 |
+
"loss": 0.3509,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.11406844106463879,
|
| 139 |
+
"grad_norm": 0.35089312674321954,
|
| 140 |
+
"learning_rate": 0.00019988157246677513,
|
| 141 |
+
"loss": 0.323,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.12040557667934093,
|
| 146 |
+
"grad_norm": 0.4238705680350401,
|
| 147 |
+
"learning_rate": 0.00019974949775942134,
|
| 148 |
+
"loss": 0.2834,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.1267427122940431,
|
| 153 |
+
"grad_norm": 0.45602469539148643,
|
| 154 |
+
"learning_rate": 0.00019956860099659346,
|
| 155 |
+
"loss": 0.3492,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.13307984790874525,
|
| 160 |
+
"grad_norm": 0.40420721250262537,
|
| 161 |
+
"learning_rate": 0.00019933897071760235,
|
| 162 |
+
"loss": 0.2865,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.1394169835234474,
|
| 167 |
+
"grad_norm": 0.47242229343887376,
|
| 168 |
+
"learning_rate": 0.00019906071931421413,
|
| 169 |
+
"loss": 0.3047,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.14575411913814956,
|
| 174 |
+
"grad_norm": 0.3662230634874705,
|
| 175 |
+
"learning_rate": 0.00019873398297564037,
|
| 176 |
+
"loss": 0.3183,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.1520912547528517,
|
| 181 |
+
"grad_norm": 0.3786550636833906,
|
| 182 |
+
"learning_rate": 0.00019835892162188066,
|
| 183 |
+
"loss": 0.2903,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.15842839036755388,
|
| 188 |
+
"grad_norm": 0.42556611928998644,
|
| 189 |
+
"learning_rate": 0.00019793571882545047,
|
| 190 |
+
"loss": 0.3298,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.16476552598225602,
|
| 195 |
+
"grad_norm": 0.3477579859642712,
|
| 196 |
+
"learning_rate": 0.0001974645817215322,
|
| 197 |
+
"loss": 0.2811,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.17110266159695817,
|
| 202 |
+
"grad_norm": 0.338149840344514,
|
| 203 |
+
"learning_rate": 0.0001969457409065933,
|
| 204 |
+
"loss": 0.3218,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.17743979721166034,
|
| 209 |
+
"grad_norm": 0.31604418234996284,
|
| 210 |
+
"learning_rate": 0.0001963794503255219,
|
| 211 |
+
"loss": 0.3181,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.18377693282636248,
|
| 216 |
+
"grad_norm": 0.37941148877648684,
|
| 217 |
+
"learning_rate": 0.00019576598714733431,
|
| 218 |
+
"loss": 0.2708,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.19011406844106463,
|
| 223 |
+
"grad_norm": 0.41662892297732984,
|
| 224 |
+
"learning_rate": 0.00019510565162951537,
|
| 225 |
+
"loss": 0.3133,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.1964512040557668,
|
| 230 |
+
"grad_norm": 0.33440472234808516,
|
| 231 |
+
"learning_rate": 0.0001943987669710586,
|
| 232 |
+
"loss": 0.3027,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.20278833967046894,
|
| 237 |
+
"grad_norm": 0.3858834779514916,
|
| 238 |
+
"learning_rate": 0.0001936456791542776,
|
| 239 |
+
"loss": 0.3148,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.20912547528517111,
|
| 244 |
+
"grad_norm": 0.3588666651678752,
|
| 245 |
+
"learning_rate": 0.000192846756775466,
|
| 246 |
+
"loss": 0.3038,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.21546261089987326,
|
| 251 |
+
"grad_norm": 0.3923595420574365,
|
| 252 |
+
"learning_rate": 0.00019200239086448933,
|
| 253 |
+
"loss": 0.251,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.2217997465145754,
|
| 258 |
+
"grad_norm": 0.3720411933468231,
|
| 259 |
+
"learning_rate": 0.0001911129946933968,
|
| 260 |
+
"loss": 0.3066,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.22813688212927757,
|
| 265 |
+
"grad_norm": 0.32287305381502635,
|
| 266 |
+
"learning_rate": 0.00019017900357414669,
|
| 267 |
+
"loss": 0.3021,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.23447401774397972,
|
| 272 |
+
"grad_norm": 0.3574163723783811,
|
| 273 |
+
"learning_rate": 0.00018920087464554427,
|
| 274 |
+
"loss": 0.3156,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.24081115335868186,
|
| 279 |
+
"grad_norm": 0.4152681195493882,
|
| 280 |
+
"learning_rate": 0.0001881790866494969,
|
| 281 |
+
"loss": 0.2839,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.24714828897338403,
|
| 286 |
+
"grad_norm": 0.36834582922377895,
|
| 287 |
+
"learning_rate": 0.00018711413969669526,
|
| 288 |
+
"loss": 0.2945,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.2534854245880862,
|
| 293 |
+
"grad_norm": 0.39981519235640095,
|
| 294 |
+
"learning_rate": 0.00018600655502183612,
|
| 295 |
+
"loss": 0.3189,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.2534854245880862,
|
| 300 |
+
"eval_loss": 0.28277337551116943,
|
| 301 |
+
"eval_runtime": 1084.4496,
|
| 302 |
+
"eval_samples_per_second": 3.689,
|
| 303 |
+
"eval_steps_per_second": 0.115,
|
| 304 |
+
"step": 200
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.2598225602027883,
|
| 308 |
+
"grad_norm": 0.31219177577589374,
|
| 309 |
+
"learning_rate": 0.0001848568747285054,
|
| 310 |
+
"loss": 0.2299,
|
| 311 |
+
"step": 205
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.2661596958174905,
|
| 315 |
+
"grad_norm": 0.37017559919032633,
|
| 316 |
+
"learning_rate": 0.00018366566152384773,
|
| 317 |
+
"loss": 0.2753,
|
| 318 |
+
"step": 210
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.27249683143219267,
|
| 322 |
+
"grad_norm": 0.29894743373031823,
|
| 323 |
+
"learning_rate": 0.00018243349844315117,
|
| 324 |
+
"loss": 0.2734,
|
| 325 |
+
"step": 215
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.2788339670468948,
|
| 329 |
+
"grad_norm": 0.3227139696142255,
|
| 330 |
+
"learning_rate": 0.00018116098856448253,
|
| 331 |
+
"loss": 0.2595,
|
| 332 |
+
"step": 220
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.28517110266159695,
|
| 336 |
+
"grad_norm": 0.3780707564332847,
|
| 337 |
+
"learning_rate": 0.00017984875471351302,
|
| 338 |
+
"loss": 0.3107,
|
| 339 |
+
"step": 225
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.2915082382762991,
|
| 343 |
+
"grad_norm": 0.31519655631233245,
|
| 344 |
+
"learning_rate": 0.00017849743915867807,
|
| 345 |
+
"loss": 0.2336,
|
| 346 |
+
"step": 230
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.29784537389100124,
|
| 350 |
+
"grad_norm": 0.35840275346083816,
|
| 351 |
+
"learning_rate": 0.00017710770329682144,
|
| 352 |
+
"loss": 0.2939,
|
| 353 |
+
"step": 235
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.3041825095057034,
|
| 357 |
+
"grad_norm": 0.2971942370747859,
|
| 358 |
+
"learning_rate": 0.0001756802273294766,
|
| 359 |
+
"loss": 0.2959,
|
| 360 |
+
"step": 240
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.3105196451204056,
|
| 364 |
+
"grad_norm": 0.3247193570102783,
|
| 365 |
+
"learning_rate": 0.0001742157099299445,
|
| 366 |
+
"loss": 0.2373,
|
| 367 |
+
"step": 245
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.31685678073510776,
|
| 371 |
+
"grad_norm": 0.38491700907647547,
|
| 372 |
+
"learning_rate": 0.00017271486790133023,
|
| 373 |
+
"loss": 0.3272,
|
| 374 |
+
"step": 250
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.3231939163498099,
|
| 378 |
+
"grad_norm": 0.3075011053275653,
|
| 379 |
+
"learning_rate": 0.00017117843582570608,
|
| 380 |
+
"loss": 0.2377,
|
| 381 |
+
"step": 255
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.32953105196451205,
|
| 385 |
+
"grad_norm": 0.31453423737207853,
|
| 386 |
+
"learning_rate": 0.00016960716570457292,
|
| 387 |
+
"loss": 0.2842,
|
| 388 |
+
"step": 260
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.3358681875792142,
|
| 392 |
+
"grad_norm": 0.24817557882025235,
|
| 393 |
+
"learning_rate": 0.00016800182659079568,
|
| 394 |
+
"loss": 0.2721,
|
| 395 |
+
"step": 265
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.34220532319391633,
|
| 399 |
+
"grad_norm": 0.3377039172873109,
|
| 400 |
+
"learning_rate": 0.00016636320421219278,
|
| 401 |
+
"loss": 0.2463,
|
| 402 |
+
"step": 270
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.3485424588086185,
|
| 406 |
+
"grad_norm": 0.3661471684768712,
|
| 407 |
+
"learning_rate": 0.00016469210058696446,
|
| 408 |
+
"loss": 0.3025,
|
| 409 |
+
"step": 275
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.3548795944233207,
|
| 413 |
+
"grad_norm": 0.27351558488185734,
|
| 414 |
+
"learning_rate": 0.0001629893336311477,
|
| 415 |
+
"loss": 0.2335,
|
| 416 |
+
"step": 280
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.3612167300380228,
|
| 420 |
+
"grad_norm": 0.4358770290773004,
|
| 421 |
+
"learning_rate": 0.00016125573675828983,
|
| 422 |
+
"loss": 0.279,
|
| 423 |
+
"step": 285
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.36755386565272496,
|
| 427 |
+
"grad_norm": 0.2774172437400498,
|
| 428 |
+
"learning_rate": 0.00015949215847153717,
|
| 429 |
+
"loss": 0.2581,
|
| 430 |
+
"step": 290
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.37389100126742714,
|
| 434 |
+
"grad_norm": 0.28991353506835355,
|
| 435 |
+
"learning_rate": 0.00015769946194833817,
|
| 436 |
+
"loss": 0.2314,
|
| 437 |
+
"step": 295
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.38022813688212925,
|
| 441 |
+
"grad_norm": 0.4117767724226869,
|
| 442 |
+
"learning_rate": 0.00015587852461796376,
|
| 443 |
+
"loss": 0.3218,
|
| 444 |
+
"step": 300
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.3865652724968314,
|
| 448 |
+
"grad_norm": 0.31038917537934363,
|
| 449 |
+
"learning_rate": 0.00015403023773205286,
|
| 450 |
+
"loss": 0.2315,
|
| 451 |
+
"step": 305
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.3929024081115336,
|
| 455 |
+
"grad_norm": 0.3358971163136089,
|
| 456 |
+
"learning_rate": 0.00015215550592839218,
|
| 457 |
+
"loss": 0.302,
|
| 458 |
+
"step": 310
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.39923954372623577,
|
| 462 |
+
"grad_norm": 0.24064351622215968,
|
| 463 |
+
"learning_rate": 0.00015025524678814427,
|
| 464 |
+
"loss": 0.2795,
|
| 465 |
+
"step": 315
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.4055766793409379,
|
| 469 |
+
"grad_norm": 0.32648334764287845,
|
| 470 |
+
"learning_rate": 0.00014833039038674047,
|
| 471 |
+
"loss": 0.2398,
|
| 472 |
+
"step": 320
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.41191381495564006,
|
| 476 |
+
"grad_norm": 0.4100611479861272,
|
| 477 |
+
"learning_rate": 0.0001463818788386588,
|
| 478 |
+
"loss": 0.2849,
|
| 479 |
+
"step": 325
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.41825095057034223,
|
| 483 |
+
"grad_norm": 0.333871597957756,
|
| 484 |
+
"learning_rate": 0.00014441066583630906,
|
| 485 |
+
"loss": 0.2297,
|
| 486 |
+
"step": 330
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.42458808618504434,
|
| 490 |
+
"grad_norm": 0.34174204454819196,
|
| 491 |
+
"learning_rate": 0.00014241771618325123,
|
| 492 |
+
"loss": 0.2704,
|
| 493 |
+
"step": 335
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.4309252217997465,
|
| 497 |
+
"grad_norm": 0.2539128471983557,
|
| 498 |
+
"learning_rate": 0.00014040400532197583,
|
| 499 |
+
"loss": 0.2579,
|
| 500 |
+
"step": 340
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.4372623574144487,
|
| 504 |
+
"grad_norm": 0.29762852904975656,
|
| 505 |
+
"learning_rate": 0.0001383705188564767,
|
| 506 |
+
"loss": 0.255,
|
| 507 |
+
"step": 345
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.4435994930291508,
|
| 511 |
+
"grad_norm": 0.3477101390224288,
|
| 512 |
+
"learning_rate": 0.00013631825206985063,
|
| 513 |
+
"loss": 0.2841,
|
| 514 |
+
"step": 350
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.449936628643853,
|
| 518 |
+
"grad_norm": 0.2807172517529508,
|
| 519 |
+
"learning_rate": 0.0001342482094371591,
|
| 520 |
+
"loss": 0.2112,
|
| 521 |
+
"step": 355
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.45627376425855515,
|
| 525 |
+
"grad_norm": 0.3838095185531826,
|
| 526 |
+
"learning_rate": 0.00013216140413379167,
|
| 527 |
+
"loss": 0.282,
|
| 528 |
+
"step": 360
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.46261089987325726,
|
| 532 |
+
"grad_norm": 0.2421625693621495,
|
| 533 |
+
"learning_rate": 0.00013005885753957048,
|
| 534 |
+
"loss": 0.2473,
|
| 535 |
+
"step": 365
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.46894803548795944,
|
| 539 |
+
"grad_norm": 0.32700829134754156,
|
| 540 |
+
"learning_rate": 0.0001279415987388395,
|
| 541 |
+
"loss": 0.2174,
|
| 542 |
+
"step": 370
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.4752851711026616,
|
| 546 |
+
"grad_norm": 0.3713274528328548,
|
| 547 |
+
"learning_rate": 0.0001258106640167826,
|
| 548 |
+
"loss": 0.283,
|
| 549 |
+
"step": 375
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.4816223067173637,
|
| 553 |
+
"grad_norm": 0.27730345855582755,
|
| 554 |
+
"learning_rate": 0.0001236670963522172,
|
| 555 |
+
"loss": 0.2021,
|
| 556 |
+
"step": 380
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.4879594423320659,
|
| 560 |
+
"grad_norm": 0.34446917830376517,
|
| 561 |
+
"learning_rate": 0.00012151194490711178,
|
| 562 |
+
"loss": 0.2561,
|
| 563 |
+
"step": 385
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.49429657794676807,
|
| 567 |
+
"grad_norm": 0.2522933072667094,
|
| 568 |
+
"learning_rate": 0.00011934626451307726,
|
| 569 |
+
"loss": 0.2433,
|
| 570 |
+
"step": 390
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.5006337135614702,
|
| 574 |
+
"grad_norm": 0.3469006061112617,
|
| 575 |
+
"learning_rate": 0.00011717111515508319,
|
| 576 |
+
"loss": 0.2266,
|
| 577 |
+
"step": 395
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.5069708491761724,
|
| 581 |
+
"grad_norm": 0.3778944814729631,
|
| 582 |
+
"learning_rate": 0.00011498756145265144,
|
| 583 |
+
"loss": 0.2906,
|
| 584 |
+
"step": 400
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.5069708491761724,
|
| 588 |
+
"eval_loss": 0.2465018332004547,
|
| 589 |
+
"eval_runtime": 1086.0248,
|
| 590 |
+
"eval_samples_per_second": 3.683,
|
| 591 |
+
"eval_steps_per_second": 0.115,
|
| 592 |
+
"step": 400
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.5133079847908745,
|
| 596 |
+
"grad_norm": 0.2906640770941992,
|
| 597 |
+
"learning_rate": 0.00011279667213878205,
|
| 598 |
+
"loss": 0.2329,
|
| 599 |
+
"step": 405
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.5196451204055766,
|
| 603 |
+
"grad_norm": 0.3562675808467966,
|
| 604 |
+
"learning_rate": 0.00011059951953686535,
|
| 605 |
+
"loss": 0.2727,
|
| 606 |
+
"step": 410
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.5259822560202788,
|
| 610 |
+
"grad_norm": 0.23100289329465973,
|
| 611 |
+
"learning_rate": 0.00010839717903583684,
|
| 612 |
+
"loss": 0.2559,
|
| 613 |
+
"step": 415
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.532319391634981,
|
| 617 |
+
"grad_norm": 0.31979110117969145,
|
| 618 |
+
"learning_rate": 0.00010619072856383181,
|
| 619 |
+
"loss": 0.2413,
|
| 620 |
+
"step": 420
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.5386565272496832,
|
| 624 |
+
"grad_norm": 0.3131449805956835,
|
| 625 |
+
"learning_rate": 0.00010398124806059701,
|
| 626 |
+
"loss": 0.2807,
|
| 627 |
+
"step": 425
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.5449936628643853,
|
| 631 |
+
"grad_norm": 0.30855801225213353,
|
| 632 |
+
"learning_rate": 0.00010176981894891768,
|
| 633 |
+
"loss": 0.1961,
|
| 634 |
+
"step": 430
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.5513307984790875,
|
| 638 |
+
"grad_norm": 0.3422494582211193,
|
| 639 |
+
"learning_rate": 9.955752360531896e-05,
|
| 640 |
+
"loss": 0.2805,
|
| 641 |
+
"step": 435
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.5576679340937896,
|
| 645 |
+
"grad_norm": 0.26688868743798966,
|
| 646 |
+
"learning_rate": 9.734544483030026e-05,
|
| 647 |
+
"loss": 0.2597,
|
| 648 |
+
"step": 440
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.5640050697084917,
|
| 652 |
+
"grad_norm": 0.3161252521303147,
|
| 653 |
+
"learning_rate": 9.513466531836221e-05,
|
| 654 |
+
"loss": 0.2166,
|
| 655 |
+
"step": 445
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.5703422053231939,
|
| 659 |
+
"grad_norm": 0.3401785018630494,
|
| 660 |
+
"learning_rate": 9.292626712808556e-05,
|
| 661 |
+
"loss": 0.2827,
|
| 662 |
+
"step": 450
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.5766793409378961,
|
| 666 |
+
"grad_norm": 0.3036061299387351,
|
| 667 |
+
"learning_rate": 9.072133115252112e-05,
|
| 668 |
+
"loss": 0.2254,
|
| 669 |
+
"step": 455
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.5830164765525983,
|
| 673 |
+
"grad_norm": 0.35415945685790207,
|
| 674 |
+
"learning_rate": 8.85209365901505e-05,
|
| 675 |
+
"loss": 0.2692,
|
| 676 |
+
"step": 460
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.5893536121673004,
|
| 680 |
+
"grad_norm": 0.25401069755470806,
|
| 681 |
+
"learning_rate": 8.632616041667577e-05,
|
| 682 |
+
"loss": 0.2539,
|
| 683 |
+
"step": 465
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.5956907477820025,
|
| 687 |
+
"grad_norm": 0.31003086790259704,
|
| 688 |
+
"learning_rate": 8.41380768578976e-05,
|
| 689 |
+
"loss": 0.2271,
|
| 690 |
+
"step": 470
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.6020278833967047,
|
| 694 |
+
"grad_norm": 0.3237135373224526,
|
| 695 |
+
"learning_rate": 8.195775686393897e-05,
|
| 696 |
+
"loss": 0.2792,
|
| 697 |
+
"step": 475
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.6083650190114068,
|
| 701 |
+
"grad_norm": 0.2952913468902984,
|
| 702 |
+
"learning_rate": 7.978626758507217e-05,
|
| 703 |
+
"loss": 0.2033,
|
| 704 |
+
"step": 480
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.614702154626109,
|
| 708 |
+
"grad_norm": 0.32514176968318775,
|
| 709 |
+
"learning_rate": 7.762467184940574e-05,
|
| 710 |
+
"loss": 0.2632,
|
| 711 |
+
"step": 485
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.6210392902408112,
|
| 715 |
+
"grad_norm": 0.2704128994845209,
|
| 716 |
+
"learning_rate": 7.547402764268689e-05,
|
| 717 |
+
"loss": 0.2657,
|
| 718 |
+
"step": 490
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.6273764258555133,
|
| 722 |
+
"grad_norm": 0.3419677722251191,
|
| 723 |
+
"learning_rate": 7.333538759047389e-05,
|
| 724 |
+
"loss": 0.2432,
|
| 725 |
+
"step": 495
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.6337135614702155,
|
| 729 |
+
"grad_norm": 0.3336718483492428,
|
| 730 |
+
"learning_rate": 7.120979844293201e-05,
|
| 731 |
+
"loss": 0.2789,
|
| 732 |
+
"step": 500
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 0.6400506970849176,
|
| 736 |
+
"grad_norm": 0.28861366582406006,
|
| 737 |
+
"learning_rate": 6.909830056250527e-05,
|
| 738 |
+
"loss": 0.2185,
|
| 739 |
+
"step": 505
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 0.6463878326996197,
|
| 743 |
+
"grad_norm": 0.3292639675337998,
|
| 744 |
+
"learning_rate": 6.700192741471447e-05,
|
| 745 |
+
"loss": 0.2622,
|
| 746 |
+
"step": 510
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.6527249683143219,
|
| 750 |
+
"grad_norm": 0.2539285743910528,
|
| 751 |
+
"learning_rate": 6.4921705062331e-05,
|
| 752 |
+
"loss": 0.2442,
|
| 753 |
+
"step": 515
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.6590621039290241,
|
| 757 |
+
"grad_norm": 0.3067269034698268,
|
| 758 |
+
"learning_rate": 6.285865166317386e-05,
|
| 759 |
+
"loss": 0.2143,
|
| 760 |
+
"step": 520
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 0.6653992395437263,
|
| 764 |
+
"grad_norm": 0.3245132022152399,
|
| 765 |
+
"learning_rate": 6.081377697177576e-05,
|
| 766 |
+
"loss": 0.2719,
|
| 767 |
+
"step": 525
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 0.6717363751584284,
|
| 771 |
+
"grad_norm": 0.27285602978719187,
|
| 772 |
+
"learning_rate": 5.8788081845162246e-05,
|
| 773 |
+
"loss": 0.205,
|
| 774 |
+
"step": 530
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 0.6780735107731305,
|
| 778 |
+
"grad_norm": 0.33017438859174614,
|
| 779 |
+
"learning_rate": 5.678255775298542e-05,
|
| 780 |
+
"loss": 0.2595,
|
| 781 |
+
"step": 535
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 0.6844106463878327,
|
| 785 |
+
"grad_norm": 0.22042843479196494,
|
| 786 |
+
"learning_rate": 5.479818629225259e-05,
|
| 787 |
+
"loss": 0.2508,
|
| 788 |
+
"step": 540
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.6907477820025348,
|
| 792 |
+
"grad_norm": 0.3262775579247169,
|
| 793 |
+
"learning_rate": 5.2835938706886966e-05,
|
| 794 |
+
"loss": 0.2252,
|
| 795 |
+
"step": 545
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.697084917617237,
|
| 799 |
+
"grad_norm": 0.3604718135367501,
|
| 800 |
+
"learning_rate": 5.0896775412355434e-05,
|
| 801 |
+
"loss": 0.2703,
|
| 802 |
+
"step": 550
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 0.7034220532319392,
|
| 806 |
+
"grad_norm": 0.2849330234510489,
|
| 807 |
+
"learning_rate": 4.89816455255966e-05,
|
| 808 |
+
"loss": 0.1977,
|
| 809 |
+
"step": 555
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 0.7097591888466414,
|
| 813 |
+
"grad_norm": 0.2992590502661103,
|
| 814 |
+
"learning_rate": 4.7091486400478604e-05,
|
| 815 |
+
"loss": 0.252,
|
| 816 |
+
"step": 560
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 0.7160963244613435,
|
| 820 |
+
"grad_norm": 0.2424976560859796,
|
| 821 |
+
"learning_rate": 4.5227223169014456e-05,
|
| 822 |
+
"loss": 0.2465,
|
| 823 |
+
"step": 565
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 0.7224334600760456,
|
| 827 |
+
"grad_norm": 0.35965307208087977,
|
| 828 |
+
"learning_rate": 4.338976828855939e-05,
|
| 829 |
+
"loss": 0.2249,
|
| 830 |
+
"step": 570
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.7287705956907478,
|
| 834 |
+
"grad_norm": 0.3741830397170476,
|
| 835 |
+
"learning_rate": 4.1580021095211486e-05,
|
| 836 |
+
"loss": 0.284,
|
| 837 |
+
"step": 575
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.7351077313054499,
|
| 841 |
+
"grad_norm": 0.2903803822883755,
|
| 842 |
+
"learning_rate": 3.9798867363634814e-05,
|
| 843 |
+
"loss": 0.2123,
|
| 844 |
+
"step": 580
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 0.7414448669201521,
|
| 848 |
+
"grad_norm": 0.31710020807356026,
|
| 849 |
+
"learning_rate": 3.804717887351991e-05,
|
| 850 |
+
"loss": 0.2605,
|
| 851 |
+
"step": 585
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 0.7477820025348543,
|
| 855 |
+
"grad_norm": 0.24733722916292933,
|
| 856 |
+
"learning_rate": 3.632581298289427e-05,
|
| 857 |
+
"loss": 0.2289,
|
| 858 |
+
"step": 590
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 0.7541191381495564,
|
| 862 |
+
"grad_norm": 0.3001878742603873,
|
| 863 |
+
"learning_rate": 3.4635612208491194e-05,
|
| 864 |
+
"loss": 0.2322,
|
| 865 |
+
"step": 595
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 0.7604562737642585,
|
| 869 |
+
"grad_norm": 0.3250883573895976,
|
| 870 |
+
"learning_rate": 3.2977403813382926e-05,
|
| 871 |
+
"loss": 0.2525,
|
| 872 |
+
"step": 600
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 0.7604562737642585,
|
| 876 |
+
"eval_loss": 0.2325838953256607,
|
| 877 |
+
"eval_runtime": 1086.1174,
|
| 878 |
+
"eval_samples_per_second": 3.683,
|
| 879 |
+
"eval_steps_per_second": 0.115,
|
| 880 |
+
"step": 600
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.7667934093789607,
|
| 884 |
+
"grad_norm": 0.3246331902911399,
|
| 885 |
+
"learning_rate": 3.135199940207947e-05,
|
| 886 |
+
"loss": 0.2206,
|
| 887 |
+
"step": 605
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.7731305449936628,
|
| 891 |
+
"grad_norm": 0.3364965552008111,
|
| 892 |
+
"learning_rate": 2.976019452329153e-05,
|
| 893 |
+
"loss": 0.2566,
|
| 894 |
+
"step": 610
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.779467680608365,
|
| 898 |
+
"grad_norm": 0.22924356326780843,
|
| 899 |
+
"learning_rate": 2.8202768280551894e-05,
|
| 900 |
+
"loss": 0.2448,
|
| 901 |
+
"step": 615
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.7858048162230672,
|
| 905 |
+
"grad_norm": 0.3207071242715804,
|
| 906 |
+
"learning_rate": 2.6680482950885777e-05,
|
| 907 |
+
"loss": 0.2269,
|
| 908 |
+
"step": 620
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.7921419518377694,
|
| 912 |
+
"grad_norm": 0.37606836614121164,
|
| 913 |
+
"learning_rate": 2.5194083611716935e-05,
|
| 914 |
+
"loss": 0.27,
|
| 915 |
+
"step": 625
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.7984790874524715,
|
| 919 |
+
"grad_norm": 0.2830616844795413,
|
| 920 |
+
"learning_rate": 2.374429777619205e-05,
|
| 921 |
+
"loss": 0.1848,
|
| 922 |
+
"step": 630
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.8048162230671736,
|
| 926 |
+
"grad_norm": 0.3123281734582231,
|
| 927 |
+
"learning_rate": 2.2331835037101823e-05,
|
| 928 |
+
"loss": 0.2562,
|
| 929 |
+
"step": 635
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.8111533586818758,
|
| 933 |
+
"grad_norm": 0.27281906149266577,
|
| 934 |
+
"learning_rate": 2.0957386719573224e-05,
|
| 935 |
+
"loss": 0.2417,
|
| 936 |
+
"step": 640
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.8174904942965779,
|
| 940 |
+
"grad_norm": 0.3463842809980822,
|
| 941 |
+
"learning_rate": 1.962162554270267e-05,
|
| 942 |
+
"loss": 0.2108,
|
| 943 |
+
"step": 645
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.8238276299112801,
|
| 947 |
+
"grad_norm": 0.35511851586585724,
|
| 948 |
+
"learning_rate": 1.83252052902961e-05,
|
| 949 |
+
"loss": 0.2789,
|
| 950 |
+
"step": 650
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.8301647655259823,
|
| 954 |
+
"grad_norm": 0.2720460231999165,
|
| 955 |
+
"learning_rate": 1.7068760490876422e-05,
|
| 956 |
+
"loss": 0.1886,
|
| 957 |
+
"step": 655
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.8365019011406845,
|
| 961 |
+
"grad_norm": 0.323785370919597,
|
| 962 |
+
"learning_rate": 1.5852906107115893e-05,
|
| 963 |
+
"loss": 0.2617,
|
| 964 |
+
"step": 660
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.8428390367553865,
|
| 968 |
+
"grad_norm": 0.23954436901187928,
|
| 969 |
+
"learning_rate": 1.4678237234844649e-05,
|
| 970 |
+
"loss": 0.2501,
|
| 971 |
+
"step": 665
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.8491761723700887,
|
| 975 |
+
"grad_norm": 0.3169133202131331,
|
| 976 |
+
"learning_rate": 1.354532881178301e-05,
|
| 977 |
+
"loss": 0.1988,
|
| 978 |
+
"step": 670
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.8555133079847909,
|
| 982 |
+
"grad_norm": 0.3516256902668012,
|
| 983 |
+
"learning_rate": 1.2454735336140167e-05,
|
| 984 |
+
"loss": 0.2765,
|
| 985 |
+
"step": 675
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.861850443599493,
|
| 989 |
+
"grad_norm": 0.2923347791144997,
|
| 990 |
+
"learning_rate": 1.1406990595216971e-05,
|
| 991 |
+
"loss": 0.2065,
|
| 992 |
+
"step": 680
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.8681875792141952,
|
| 996 |
+
"grad_norm": 0.30823497046755327,
|
| 997 |
+
"learning_rate": 1.0402607404145449e-05,
|
| 998 |
+
"loss": 0.2623,
|
| 999 |
+
"step": 685
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.8745247148288974,
|
| 1003 |
+
"grad_norm": 0.25292131222665615,
|
| 1004 |
+
"learning_rate": 9.442077354893198e-06,
|
| 1005 |
+
"loss": 0.2461,
|
| 1006 |
+
"step": 690
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.8808618504435995,
|
| 1010 |
+
"grad_norm": 0.32414756933713984,
|
| 1011 |
+
"learning_rate": 8.525870575655392e-06,
|
| 1012 |
+
"loss": 0.217,
|
| 1013 |
+
"step": 695
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.8871989860583016,
|
| 1017 |
+
"grad_norm": 0.3423100582401461,
|
| 1018 |
+
"learning_rate": 7.654435500752055e-06,
|
| 1019 |
+
"loss": 0.2675,
|
| 1020 |
+
"step": 700
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.8935361216730038,
|
| 1024 |
+
"grad_norm": 0.29544160874192754,
|
| 1025 |
+
"learning_rate": 6.828198651143425e-06,
|
| 1026 |
+
"loss": 0.1927,
|
| 1027 |
+
"step": 705
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.899873257287706,
|
| 1031 |
+
"grad_norm": 0.32477510117980407,
|
| 1032 |
+
"learning_rate": 6.047564425670749e-06,
|
| 1033 |
+
"loss": 0.2613,
|
| 1034 |
+
"step": 710
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.9062103929024081,
|
| 1038 |
+
"grad_norm": 0.23676655623304554,
|
| 1039 |
+
"learning_rate": 5.312914903124566e-06,
|
| 1040 |
+
"loss": 0.2414,
|
| 1041 |
+
"step": 715
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.9125475285171103,
|
| 1045 |
+
"grad_norm": 0.2967989522178623,
|
| 1046 |
+
"learning_rate": 4.624609655237544e-06,
|
| 1047 |
+
"loss": 0.2002,
|
| 1048 |
+
"step": 720
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.9188846641318125,
|
| 1052 |
+
"grad_norm": 0.340334151463555,
|
| 1053 |
+
"learning_rate": 3.982985570693354e-06,
|
| 1054 |
+
"loss": 0.2764,
|
| 1055 |
+
"step": 725
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.9252217997465145,
|
| 1059 |
+
"grad_norm": 0.2776495387493925,
|
| 1060 |
+
"learning_rate": 3.388356690237582e-06,
|
| 1061 |
+
"loss": 0.1859,
|
| 1062 |
+
"step": 730
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.9315589353612167,
|
| 1066 |
+
"grad_norm": 0.37073108669893173,
|
| 1067 |
+
"learning_rate": 2.84101405297158e-06,
|
| 1068 |
+
"loss": 0.2378,
|
| 1069 |
+
"step": 735
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.9378960709759189,
|
| 1073 |
+
"grad_norm": 0.2570912693772944,
|
| 1074 |
+
"learning_rate": 2.341225553904336e-06,
|
| 1075 |
+
"loss": 0.2398,
|
| 1076 |
+
"step": 740
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.944233206590621,
|
| 1080 |
+
"grad_norm": 0.3306131510091784,
|
| 1081 |
+
"learning_rate": 1.8892358128322018e-06,
|
| 1082 |
+
"loss": 0.2092,
|
| 1083 |
+
"step": 745
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.9505703422053232,
|
| 1087 |
+
"grad_norm": 0.33888565708232804,
|
| 1088 |
+
"learning_rate": 1.4852660546105234e-06,
|
| 1089 |
+
"loss": 0.2873,
|
| 1090 |
+
"step": 750
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 0.9569074778200254,
|
| 1094 |
+
"grad_norm": 0.2906867586955816,
|
| 1095 |
+
"learning_rate": 1.1295140008758864e-06,
|
| 1096 |
+
"loss": 0.2079,
|
| 1097 |
+
"step": 755
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 0.9632446134347274,
|
| 1101 |
+
"grad_norm": 0.34402820600782946,
|
| 1102 |
+
"learning_rate": 8.221537732719275e-07,
|
| 1103 |
+
"loss": 0.2648,
|
| 1104 |
+
"step": 760
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 0.9695817490494296,
|
| 1108 |
+
"grad_norm": 0.26017431588284967,
|
| 1109 |
+
"learning_rate": 5.633358082260954e-07,
|
| 1110 |
+
"loss": 0.2481,
|
| 1111 |
+
"step": 765
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 0.9759188846641318,
|
| 1115 |
+
"grad_norm": 0.3339069885340444,
|
| 1116 |
+
"learning_rate": 3.5318678331904833e-07,
|
| 1117 |
+
"loss": 0.2237,
|
| 1118 |
+
"step": 770
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 0.982256020278834,
|
| 1122 |
+
"grad_norm": 0.34754105161997045,
|
| 1123 |
+
"learning_rate": 1.9180955528270706e-07,
|
| 1124 |
+
"loss": 0.27,
|
| 1125 |
+
"step": 775
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 0.9885931558935361,
|
| 1129 |
+
"grad_norm": 0.3246226295094946,
|
| 1130 |
+
"learning_rate": 7.928310965742425e-08,
|
| 1131 |
+
"loss": 0.2226,
|
| 1132 |
+
"step": 780
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 0.9949302915082383,
|
| 1136 |
+
"grad_norm": 0.31594487456225406,
|
| 1137 |
+
"learning_rate": 1.5662522132742218e-08,
|
| 1138 |
+
"loss": 0.2444,
|
| 1139 |
+
"step": 785
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 1.0,
|
| 1143 |
+
"step": 789,
|
| 1144 |
+
"total_flos": 1.0371979095834624e+16,
|
| 1145 |
+
"train_loss": 0.2726454405050314,
|
| 1146 |
+
"train_runtime": 20804.2809,
|
| 1147 |
+
"train_samples_per_second": 1.213,
|
| 1148 |
+
"train_steps_per_second": 0.038
|
| 1149 |
+
}
|
| 1150 |
+
],
|
| 1151 |
+
"logging_steps": 5,
|
| 1152 |
+
"max_steps": 789,
|
| 1153 |
+
"num_input_tokens_seen": 0,
|
| 1154 |
+
"num_train_epochs": 1,
|
| 1155 |
+
"save_steps": 200,
|
| 1156 |
+
"stateful_callbacks": {
|
| 1157 |
+
"TrainerControl": {
|
| 1158 |
+
"args": {
|
| 1159 |
+
"should_epoch_stop": false,
|
| 1160 |
+
"should_evaluate": false,
|
| 1161 |
+
"should_log": false,
|
| 1162 |
+
"should_save": true,
|
| 1163 |
+
"should_training_stop": false
|
| 1164 |
+
},
|
| 1165 |
+
"attributes": {}
|
| 1166 |
+
}
|
| 1167 |
+
},
|
| 1168 |
+
"total_flos": 1.0371979095834624e+16,
|
| 1169 |
+
"train_batch_size": 8,
|
| 1170 |
+
"trial_name": null,
|
| 1171 |
+
"trial_params": null
|
| 1172 |
+
}
|