End of training
Browse files- README.md +2 -1
- all_results.json +12 -0
- eval_results.json +7 -0
- train_results.json +8 -0
- trainer_state.json +1466 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: apache-2.0
|
|
| 4 |
base_model: mistralai/Mistral-7B-v0.3
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: hp_ablations_grid_mistral_bsz512_lr5e-6_scheduler-cosine-warmup0.15-mistralv0.3
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# hp_ablations_grid_mistral_bsz512_lr5e-6_scheduler-cosine-warmup0.15-mistralv0.3
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 0.0582
|
| 21 |
|
|
|
|
| 4 |
base_model: mistralai/Mistral-7B-v0.3
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: hp_ablations_grid_mistral_bsz512_lr5e-6_scheduler-cosine-warmup0.15-mistralv0.3
|
|
|
|
| 16 |
|
| 17 |
# hp_ablations_grid_mistral_bsz512_lr5e-6_scheduler-cosine-warmup0.15-mistralv0.3
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on the mlfoundations-dev/oh-dcft-v3-llama3.1-nemotron-70b_shareGPT_format dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.0582
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9994378864530633,
|
| 3 |
+
"eval_loss": 0.058169443160295486,
|
| 4 |
+
"eval_runtime": 449.8161,
|
| 5 |
+
"eval_samples_per_second": 39.965,
|
| 6 |
+
"eval_steps_per_second": 0.625,
|
| 7 |
+
"total_flos": 3351540148469760.0,
|
| 8 |
+
"train_loss": 0.4023907120408921,
|
| 9 |
+
"train_runtime": 64801.3882,
|
| 10 |
+
"train_samples_per_second": 15.812,
|
| 11 |
+
"train_steps_per_second": 0.031
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9994378864530633,
|
| 3 |
+
"eval_loss": 0.058169443160295486,
|
| 4 |
+
"eval_runtime": 449.8161,
|
| 5 |
+
"eval_samples_per_second": 39.965,
|
| 6 |
+
"eval_steps_per_second": 0.625
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9994378864530633,
|
| 3 |
+
"total_flos": 3351540148469760.0,
|
| 4 |
+
"train_loss": 0.4023907120408921,
|
| 5 |
+
"train_runtime": 64801.3882,
|
| 6 |
+
"train_samples_per_second": 15.812,
|
| 7 |
+
"train_steps_per_second": 0.031
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1466 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9994378864530633,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2001,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.014989694584972832,
|
| 13 |
+
"grad_norm": 12.777873823078783,
|
| 14 |
+
"learning_rate": 1.6611295681063126e-07,
|
| 15 |
+
"loss": 0.902,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.029979389169945664,
|
| 20 |
+
"grad_norm": 7.3435241316074045,
|
| 21 |
+
"learning_rate": 3.322259136212625e-07,
|
| 22 |
+
"loss": 0.8565,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.044969083754918496,
|
| 27 |
+
"grad_norm": 3.9849563392808864,
|
| 28 |
+
"learning_rate": 4.983388704318938e-07,
|
| 29 |
+
"loss": 0.7765,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.05995877833989133,
|
| 34 |
+
"grad_norm": 1.8633726457542599,
|
| 35 |
+
"learning_rate": 6.64451827242525e-07,
|
| 36 |
+
"loss": 0.7102,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.07494847292486416,
|
| 41 |
+
"grad_norm": 1.4954062046250922,
|
| 42 |
+
"learning_rate": 8.305647840531563e-07,
|
| 43 |
+
"loss": 0.6762,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.08993816750983699,
|
| 48 |
+
"grad_norm": 1.3750012507878848,
|
| 49 |
+
"learning_rate": 9.966777408637875e-07,
|
| 50 |
+
"loss": 0.6471,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.10492786209480982,
|
| 55 |
+
"grad_norm": 1.4482820464395114,
|
| 56 |
+
"learning_rate": 1.1627906976744188e-06,
|
| 57 |
+
"loss": 0.6264,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.11991755667978266,
|
| 62 |
+
"grad_norm": 1.862315554960826,
|
| 63 |
+
"learning_rate": 1.32890365448505e-06,
|
| 64 |
+
"loss": 0.6131,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.13490725126475547,
|
| 69 |
+
"grad_norm": 1.6724167400141936,
|
| 70 |
+
"learning_rate": 1.4950166112956813e-06,
|
| 71 |
+
"loss": 0.6011,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.14989694584972832,
|
| 76 |
+
"grad_norm": 1.6824102308369775,
|
| 77 |
+
"learning_rate": 1.6611295681063126e-06,
|
| 78 |
+
"loss": 0.5888,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.16488664043470114,
|
| 83 |
+
"grad_norm": 1.7516516157128537,
|
| 84 |
+
"learning_rate": 1.8272425249169438e-06,
|
| 85 |
+
"loss": 0.5836,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.17987633501967398,
|
| 90 |
+
"grad_norm": 1.623499220073038,
|
| 91 |
+
"learning_rate": 1.993355481727575e-06,
|
| 92 |
+
"loss": 0.5767,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.1948660296046468,
|
| 97 |
+
"grad_norm": 2.0314714470085358,
|
| 98 |
+
"learning_rate": 2.1594684385382063e-06,
|
| 99 |
+
"loss": 0.5689,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.20985572418961965,
|
| 104 |
+
"grad_norm": 1.6951555702146335,
|
| 105 |
+
"learning_rate": 2.3255813953488376e-06,
|
| 106 |
+
"loss": 0.5694,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.22484541877459246,
|
| 111 |
+
"grad_norm": 1.894679433473508,
|
| 112 |
+
"learning_rate": 2.4916943521594684e-06,
|
| 113 |
+
"loss": 0.5576,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.2398351133595653,
|
| 118 |
+
"grad_norm": 1.7422683371902348,
|
| 119 |
+
"learning_rate": 2.6578073089701e-06,
|
| 120 |
+
"loss": 0.5556,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.25482480794453816,
|
| 125 |
+
"grad_norm": 1.9008699070898252,
|
| 126 |
+
"learning_rate": 2.8239202657807313e-06,
|
| 127 |
+
"loss": 0.5521,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.26981450252951095,
|
| 132 |
+
"grad_norm": 1.844172367351659,
|
| 133 |
+
"learning_rate": 2.9900332225913626e-06,
|
| 134 |
+
"loss": 0.5471,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.2848041971144838,
|
| 139 |
+
"grad_norm": 1.785147460867048,
|
| 140 |
+
"learning_rate": 3.156146179401994e-06,
|
| 141 |
+
"loss": 0.5444,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.29979389169945664,
|
| 146 |
+
"grad_norm": 1.8204441132637552,
|
| 147 |
+
"learning_rate": 3.322259136212625e-06,
|
| 148 |
+
"loss": 0.5385,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.31478358628442943,
|
| 153 |
+
"grad_norm": 1.849611308520918,
|
| 154 |
+
"learning_rate": 3.4883720930232564e-06,
|
| 155 |
+
"loss": 0.5351,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.3297732808694023,
|
| 160 |
+
"grad_norm": 1.8876145088553256,
|
| 161 |
+
"learning_rate": 3.6544850498338876e-06,
|
| 162 |
+
"loss": 0.5363,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.3447629754543751,
|
| 167 |
+
"grad_norm": 2.4886914406463867,
|
| 168 |
+
"learning_rate": 3.8205980066445185e-06,
|
| 169 |
+
"loss": 0.5334,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.35975267003934797,
|
| 174 |
+
"grad_norm": 2.421754684568758,
|
| 175 |
+
"learning_rate": 3.98671096345515e-06,
|
| 176 |
+
"loss": 0.5316,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.37474236462432076,
|
| 181 |
+
"grad_norm": 1.6687380919697075,
|
| 182 |
+
"learning_rate": 4.152823920265781e-06,
|
| 183 |
+
"loss": 0.5268,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.3897320592092936,
|
| 188 |
+
"grad_norm": 1.8499077931578278,
|
| 189 |
+
"learning_rate": 4.318936877076413e-06,
|
| 190 |
+
"loss": 0.5289,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.40472175379426645,
|
| 195 |
+
"grad_norm": 2.4628946829032587,
|
| 196 |
+
"learning_rate": 4.4850498338870435e-06,
|
| 197 |
+
"loss": 0.5235,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.4197114483792393,
|
| 202 |
+
"grad_norm": 2.204174864640197,
|
| 203 |
+
"learning_rate": 4.651162790697675e-06,
|
| 204 |
+
"loss": 0.5265,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.4347011429642121,
|
| 209 |
+
"grad_norm": 2.366488200680214,
|
| 210 |
+
"learning_rate": 4.817275747508306e-06,
|
| 211 |
+
"loss": 0.5193,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.44969083754918493,
|
| 216 |
+
"grad_norm": 2.8012926552797257,
|
| 217 |
+
"learning_rate": 4.983388704318937e-06,
|
| 218 |
+
"loss": 0.5156,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.4646805321341578,
|
| 223 |
+
"grad_norm": 4.139795722954455,
|
| 224 |
+
"learning_rate": 4.999654230307899e-06,
|
| 225 |
+
"loss": 0.5177,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.4796702267191306,
|
| 230 |
+
"grad_norm": 3.952786519090627,
|
| 231 |
+
"learning_rate": 4.998459099844914e-06,
|
| 232 |
+
"loss": 0.512,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.4946599213041034,
|
| 237 |
+
"grad_norm": 2.9745265076009946,
|
| 238 |
+
"learning_rate": 4.996410747888184e-06,
|
| 239 |
+
"loss": 0.5104,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.5096496158890763,
|
| 244 |
+
"grad_norm": 3.279789637235632,
|
| 245 |
+
"learning_rate": 4.993509873948025e-06,
|
| 246 |
+
"loss": 0.5083,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.5246393104740491,
|
| 251 |
+
"grad_norm": 3.4046254908112803,
|
| 252 |
+
"learning_rate": 4.989757468670231e-06,
|
| 253 |
+
"loss": 0.5049,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.5396290050590219,
|
| 258 |
+
"grad_norm": 2.5862130652191,
|
| 259 |
+
"learning_rate": 4.985154813497765e-06,
|
| 260 |
+
"loss": 0.5093,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.5546186996439948,
|
| 265 |
+
"grad_norm": 1.8501758264267991,
|
| 266 |
+
"learning_rate": 4.979703480233156e-06,
|
| 267 |
+
"loss": 0.5034,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.5696083942289676,
|
| 272 |
+
"grad_norm": 2.2116554860251667,
|
| 273 |
+
"learning_rate": 4.973405330501715e-06,
|
| 274 |
+
"loss": 0.5023,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.5845980888139404,
|
| 279 |
+
"grad_norm": 2.2510169713465586,
|
| 280 |
+
"learning_rate": 4.966262515115808e-06,
|
| 281 |
+
"loss": 0.4999,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.5995877833989133,
|
| 286 |
+
"grad_norm": 2.6499432191306025,
|
| 287 |
+
"learning_rate": 4.958277473340345e-06,
|
| 288 |
+
"loss": 0.5043,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.6145774779838861,
|
| 293 |
+
"grad_norm": 1.8449367407295139,
|
| 294 |
+
"learning_rate": 4.949452932059777e-06,
|
| 295 |
+
"loss": 0.5012,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.6295671725688589,
|
| 300 |
+
"grad_norm": 1.9215837970775265,
|
| 301 |
+
"learning_rate": 4.939791904846869e-06,
|
| 302 |
+
"loss": 0.4969,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.6445568671538318,
|
| 307 |
+
"grad_norm": 2.1023812126184387,
|
| 308 |
+
"learning_rate": 4.929297690933561e-06,
|
| 309 |
+
"loss": 0.4976,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.6595465617388045,
|
| 314 |
+
"grad_norm": 2.042184330044649,
|
| 315 |
+
"learning_rate": 4.917973874084293e-06,
|
| 316 |
+
"loss": 0.494,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.6745362563237775,
|
| 321 |
+
"grad_norm": 2.517472777976901,
|
| 322 |
+
"learning_rate": 4.905824321372143e-06,
|
| 323 |
+
"loss": 0.4946,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.6895259509087502,
|
| 328 |
+
"grad_norm": 1.6569332477157788,
|
| 329 |
+
"learning_rate": 4.892853181858234e-06,
|
| 330 |
+
"loss": 0.4883,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.704515645493723,
|
| 335 |
+
"grad_norm": 1.771900963881147,
|
| 336 |
+
"learning_rate": 4.879064885174825e-06,
|
| 337 |
+
"loss": 0.4873,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.7195053400786959,
|
| 342 |
+
"grad_norm": 1.927208700693383,
|
| 343 |
+
"learning_rate": 4.8644641400126035e-06,
|
| 344 |
+
"loss": 0.4922,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.7344950346636687,
|
| 349 |
+
"grad_norm": 1.732154103024004,
|
| 350 |
+
"learning_rate": 4.849055932512666e-06,
|
| 351 |
+
"loss": 0.4911,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.7494847292486415,
|
| 356 |
+
"grad_norm": 1.7314920101435785,
|
| 357 |
+
"learning_rate": 4.832845524563758e-06,
|
| 358 |
+
"loss": 0.4884,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.7644744238336144,
|
| 363 |
+
"grad_norm": 2.0936474922460304,
|
| 364 |
+
"learning_rate": 4.815838452005344e-06,
|
| 365 |
+
"loss": 0.4941,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.7794641184185872,
|
| 370 |
+
"grad_norm": 2.075312501604676,
|
| 371 |
+
"learning_rate": 4.798040522737122e-06,
|
| 372 |
+
"loss": 0.4873,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.7944538130035601,
|
| 377 |
+
"grad_norm": 1.6868419550348641,
|
| 378 |
+
"learning_rate": 4.779457814735632e-06,
|
| 379 |
+
"loss": 0.4841,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.8094435075885329,
|
| 384 |
+
"grad_norm": 1.6894890638345692,
|
| 385 |
+
"learning_rate": 4.760096673978634e-06,
|
| 386 |
+
"loss": 0.4824,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.8244332021735057,
|
| 391 |
+
"grad_norm": 1.7041316420782846,
|
| 392 |
+
"learning_rate": 4.73996371227796e-06,
|
| 393 |
+
"loss": 0.4872,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.8394228967584786,
|
| 398 |
+
"grad_norm": 1.5724665047442083,
|
| 399 |
+
"learning_rate": 4.719065805021584e-06,
|
| 400 |
+
"loss": 0.4839,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.8544125913434514,
|
| 405 |
+
"grad_norm": 1.493096241789178,
|
| 406 |
+
"learning_rate": 4.697410088825692e-06,
|
| 407 |
+
"loss": 0.4832,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.8694022859284242,
|
| 412 |
+
"grad_norm": 2.031583132991568,
|
| 413 |
+
"learning_rate": 4.675003959097525e-06,
|
| 414 |
+
"loss": 0.4767,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.8843919805133971,
|
| 419 |
+
"grad_norm": 1.4245462788100998,
|
| 420 |
+
"learning_rate": 4.65185506750986e-06,
|
| 421 |
+
"loss": 0.4782,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.8993816750983699,
|
| 426 |
+
"grad_norm": 1.5793606614864946,
|
| 427 |
+
"learning_rate": 4.627971319387965e-06,
|
| 428 |
+
"loss": 0.4795,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.9143713696833426,
|
| 433 |
+
"grad_norm": 1.4355119503255267,
|
| 434 |
+
"learning_rate": 4.603360871009946e-06,
|
| 435 |
+
"loss": 0.4774,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.9293610642683156,
|
| 440 |
+
"grad_norm": 1.52114987838548,
|
| 441 |
+
"learning_rate": 4.578032126821377e-06,
|
| 442 |
+
"loss": 0.4771,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.9443507588532883,
|
| 447 |
+
"grad_norm": 1.5400335880344016,
|
| 448 |
+
"learning_rate": 4.5519937365651945e-06,
|
| 449 |
+
"loss": 0.4785,
|
| 450 |
+
"step": 630
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.9593404534382612,
|
| 454 |
+
"grad_norm": 1.6430985109756742,
|
| 455 |
+
"learning_rate": 4.525254592327817e-06,
|
| 456 |
+
"loss": 0.4712,
|
| 457 |
+
"step": 640
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.974330148023234,
|
| 461 |
+
"grad_norm": 1.4624345774601337,
|
| 462 |
+
"learning_rate": 4.497823825502507e-06,
|
| 463 |
+
"loss": 0.4746,
|
| 464 |
+
"step": 650
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.9893198426082068,
|
| 468 |
+
"grad_norm": 1.9756966886927916,
|
| 469 |
+
"learning_rate": 4.469710803671004e-06,
|
| 470 |
+
"loss": 0.4707,
|
| 471 |
+
"step": 660
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.9998126288176878,
|
| 475 |
+
"eval_loss": 0.058926939964294434,
|
| 476 |
+
"eval_runtime": 456.5855,
|
| 477 |
+
"eval_samples_per_second": 39.373,
|
| 478 |
+
"eval_steps_per_second": 0.615,
|
| 479 |
+
"step": 667
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.0043095371931796,
|
| 483 |
+
"grad_norm": 2.6844759304769448,
|
| 484 |
+
"learning_rate": 4.440925127404512e-06,
|
| 485 |
+
"loss": 0.4526,
|
| 486 |
+
"step": 670
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.0192992317781526,
|
| 490 |
+
"grad_norm": 1.6812914263129781,
|
| 491 |
+
"learning_rate": 4.411476626985102e-06,
|
| 492 |
+
"loss": 0.3995,
|
| 493 |
+
"step": 680
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.0342889263631254,
|
| 497 |
+
"grad_norm": 1.6671947730035994,
|
| 498 |
+
"learning_rate": 4.381375359048691e-06,
|
| 499 |
+
"loss": 0.3918,
|
| 500 |
+
"step": 690
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.0492786209480982,
|
| 504 |
+
"grad_norm": 1.541048196484826,
|
| 505 |
+
"learning_rate": 4.350631603150702e-06,
|
| 506 |
+
"loss": 0.3933,
|
| 507 |
+
"step": 700
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.064268315533071,
|
| 511 |
+
"grad_norm": 1.7329710214895389,
|
| 512 |
+
"learning_rate": 4.319255858255612e-06,
|
| 513 |
+
"loss": 0.3901,
|
| 514 |
+
"step": 710
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.0792580101180438,
|
| 518 |
+
"grad_norm": 1.7281442329309784,
|
| 519 |
+
"learning_rate": 4.287258839151557e-06,
|
| 520 |
+
"loss": 0.3926,
|
| 521 |
+
"step": 720
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.0942477047030166,
|
| 525 |
+
"grad_norm": 1.4548547056485654,
|
| 526 |
+
"learning_rate": 4.254651472791249e-06,
|
| 527 |
+
"loss": 0.3964,
|
| 528 |
+
"step": 730
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.1092373992879896,
|
| 532 |
+
"grad_norm": 1.5263837537606915,
|
| 533 |
+
"learning_rate": 4.221444894560429e-06,
|
| 534 |
+
"loss": 0.3915,
|
| 535 |
+
"step": 740
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.1242270938729624,
|
| 539 |
+
"grad_norm": 1.8283686921084465,
|
| 540 |
+
"learning_rate": 4.1876504444751406e-06,
|
| 541 |
+
"loss": 0.393,
|
| 542 |
+
"step": 750
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.1392167884579352,
|
| 546 |
+
"grad_norm": 1.9745034884067223,
|
| 547 |
+
"learning_rate": 4.15327966330913e-06,
|
| 548 |
+
"loss": 0.3933,
|
| 549 |
+
"step": 760
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.154206483042908,
|
| 553 |
+
"grad_norm": 2.0006637742508473,
|
| 554 |
+
"learning_rate": 4.1183442886526784e-06,
|
| 555 |
+
"loss": 0.3927,
|
| 556 |
+
"step": 770
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.1691961776278808,
|
| 560 |
+
"grad_norm": 2.398957927996368,
|
| 561 |
+
"learning_rate": 4.082856250904224e-06,
|
| 562 |
+
"loss": 0.3946,
|
| 563 |
+
"step": 780
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.1841858722128538,
|
| 567 |
+
"grad_norm": 2.1339474482590086,
|
| 568 |
+
"learning_rate": 4.04682766919615e-06,
|
| 569 |
+
"loss": 0.3912,
|
| 570 |
+
"step": 790
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.1991755667978266,
|
| 574 |
+
"grad_norm": 2.0801601343322735,
|
| 575 |
+
"learning_rate": 4.010270847256104e-06,
|
| 576 |
+
"loss": 0.3872,
|
| 577 |
+
"step": 800
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.2141652613827993,
|
| 581 |
+
"grad_norm": 2.241507677816275,
|
| 582 |
+
"learning_rate": 3.973198269205286e-06,
|
| 583 |
+
"loss": 0.3911,
|
| 584 |
+
"step": 810
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.2291549559677721,
|
| 588 |
+
"grad_norm": 1.9465898484553392,
|
| 589 |
+
"learning_rate": 3.9356225952951384e-06,
|
| 590 |
+
"loss": 0.3934,
|
| 591 |
+
"step": 820
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.244144650552745,
|
| 595 |
+
"grad_norm": 1.73525671044772,
|
| 596 |
+
"learning_rate": 3.8975566575838805e-06,
|
| 597 |
+
"loss": 0.3905,
|
| 598 |
+
"step": 830
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.259134345137718,
|
| 602 |
+
"grad_norm": 1.8854981866970535,
|
| 603 |
+
"learning_rate": 3.859013455554366e-06,
|
| 604 |
+
"loss": 0.385,
|
| 605 |
+
"step": 840
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.2741240397226907,
|
| 609 |
+
"grad_norm": 1.9676037916759839,
|
| 610 |
+
"learning_rate": 3.82000615167478e-06,
|
| 611 |
+
"loss": 0.3874,
|
| 612 |
+
"step": 850
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.2891137343076635,
|
| 616 |
+
"grad_norm": 1.6949021870149008,
|
| 617 |
+
"learning_rate": 3.780548066903661e-06,
|
| 618 |
+
"loss": 0.3879,
|
| 619 |
+
"step": 860
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.3041034288926363,
|
| 623 |
+
"grad_norm": 1.847929926533703,
|
| 624 |
+
"learning_rate": 3.740652676140812e-06,
|
| 625 |
+
"loss": 0.3923,
|
| 626 |
+
"step": 870
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.319093123477609,
|
| 630 |
+
"grad_norm": 1.8219949958766242,
|
| 631 |
+
"learning_rate": 3.700333603625629e-06,
|
| 632 |
+
"loss": 0.3871,
|
| 633 |
+
"step": 880
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.334082818062582,
|
| 637 |
+
"grad_norm": 2.1571236655174233,
|
| 638 |
+
"learning_rate": 3.65960461828444e-06,
|
| 639 |
+
"loss": 0.3915,
|
| 640 |
+
"step": 890
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.3490725126475547,
|
| 644 |
+
"grad_norm": 2.028728831427641,
|
| 645 |
+
"learning_rate": 3.6184796290284267e-06,
|
| 646 |
+
"loss": 0.3815,
|
| 647 |
+
"step": 900
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.3640622072325277,
|
| 651 |
+
"grad_norm": 1.907400343061468,
|
| 652 |
+
"learning_rate": 3.5769726800037462e-06,
|
| 653 |
+
"loss": 0.3915,
|
| 654 |
+
"step": 910
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.3790519018175005,
|
| 658 |
+
"grad_norm": 2.1829895016343897,
|
| 659 |
+
"learning_rate": 3.5350979457954638e-06,
|
| 660 |
+
"loss": 0.39,
|
| 661 |
+
"step": 920
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.3940415964024733,
|
| 665 |
+
"grad_norm": 1.886862579732133,
|
| 666 |
+
"learning_rate": 3.4928697265869516e-06,
|
| 667 |
+
"loss": 0.3872,
|
| 668 |
+
"step": 930
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.409031290987446,
|
| 672 |
+
"grad_norm": 1.819745393510499,
|
| 673 |
+
"learning_rate": 3.4503024432763838e-06,
|
| 674 |
+
"loss": 0.3867,
|
| 675 |
+
"step": 940
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.4240209855724189,
|
| 679 |
+
"grad_norm": 1.8714086663251082,
|
| 680 |
+
"learning_rate": 3.4074106325520133e-06,
|
| 681 |
+
"loss": 0.3879,
|
| 682 |
+
"step": 950
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.4390106801573919,
|
| 686 |
+
"grad_norm": 1.4361408847037231,
|
| 687 |
+
"learning_rate": 3.3642089419279107e-06,
|
| 688 |
+
"loss": 0.386,
|
| 689 |
+
"step": 960
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.4540003747423647,
|
| 693 |
+
"grad_norm": 1.477381601060273,
|
| 694 |
+
"learning_rate": 3.3207121247418456e-06,
|
| 695 |
+
"loss": 0.3888,
|
| 696 |
+
"step": 970
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.4689900693273374,
|
| 700 |
+
"grad_norm": 1.4721765084901293,
|
| 701 |
+
"learning_rate": 3.2769350351170405e-06,
|
| 702 |
+
"loss": 0.3867,
|
| 703 |
+
"step": 980
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.4839797639123102,
|
| 707 |
+
"grad_norm": 1.4925458845511457,
|
| 708 |
+
"learning_rate": 3.232892622889497e-06,
|
| 709 |
+
"loss": 0.3891,
|
| 710 |
+
"step": 990
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.498969458497283,
|
| 714 |
+
"grad_norm": 1.4566645795724527,
|
| 715 |
+
"learning_rate": 3.1885999285026438e-06,
|
| 716 |
+
"loss": 0.3881,
|
| 717 |
+
"step": 1000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.513959153082256,
|
| 721 |
+
"grad_norm": 1.5822180202872997,
|
| 722 |
+
"learning_rate": 3.1440720778710365e-06,
|
| 723 |
+
"loss": 0.3866,
|
| 724 |
+
"step": 1010
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.5289488476672288,
|
| 728 |
+
"grad_norm": 1.4373920553624056,
|
| 729 |
+
"learning_rate": 3.0993242772148753e-06,
|
| 730 |
+
"loss": 0.3881,
|
| 731 |
+
"step": 1020
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.5439385422522016,
|
| 735 |
+
"grad_norm": 1.381099707101281,
|
| 736 |
+
"learning_rate": 3.054371807867088e-06,
|
| 737 |
+
"loss": 0.3888,
|
| 738 |
+
"step": 1030
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.5589282368371744,
|
| 742 |
+
"grad_norm": 1.3759750364038397,
|
| 743 |
+
"learning_rate": 3.0092300210547775e-06,
|
| 744 |
+
"loss": 0.3869,
|
| 745 |
+
"step": 1040
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.5739179314221472,
|
| 749 |
+
"grad_norm": 1.4366787735561277,
|
| 750 |
+
"learning_rate": 2.9639143326567847e-06,
|
| 751 |
+
"loss": 0.3865,
|
| 752 |
+
"step": 1050
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.5889076260071202,
|
| 756 |
+
"grad_norm": 1.369352819988061,
|
| 757 |
+
"learning_rate": 2.918440217939185e-06,
|
| 758 |
+
"loss": 0.3862,
|
| 759 |
+
"step": 1060
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.6038973205920928,
|
| 763 |
+
"grad_norm": 1.5096071928255457,
|
| 764 |
+
"learning_rate": 2.872823206270494e-06,
|
| 765 |
+
"loss": 0.3894,
|
| 766 |
+
"step": 1070
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.6188870151770658,
|
| 770 |
+
"grad_norm": 1.4303634190845425,
|
| 771 |
+
"learning_rate": 2.8270788758184076e-06,
|
| 772 |
+
"loss": 0.3864,
|
| 773 |
+
"step": 1080
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.6338767097620386,
|
| 777 |
+
"grad_norm": 1.4207147216727412,
|
| 778 |
+
"learning_rate": 2.7812228482298674e-06,
|
| 779 |
+
"loss": 0.3876,
|
| 780 |
+
"step": 1090
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.6488664043470114,
|
| 784 |
+
"grad_norm": 1.3978109627955357,
|
| 785 |
+
"learning_rate": 2.7352707832962865e-06,
|
| 786 |
+
"loss": 0.3882,
|
| 787 |
+
"step": 1100
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.6638560989319844,
|
| 791 |
+
"grad_norm": 1.4425647311953784,
|
| 792 |
+
"learning_rate": 2.689238373605742e-06,
|
| 793 |
+
"loss": 0.3847,
|
| 794 |
+
"step": 1110
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.678845793516957,
|
| 798 |
+
"grad_norm": 1.3945982747038834,
|
| 799 |
+
"learning_rate": 2.6431413391839746e-06,
|
| 800 |
+
"loss": 0.3848,
|
| 801 |
+
"step": 1120
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.69383548810193,
|
| 805 |
+
"grad_norm": 1.4307341663030686,
|
| 806 |
+
"learning_rate": 2.5969954221260076e-06,
|
| 807 |
+
"loss": 0.3823,
|
| 808 |
+
"step": 1130
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.7088251826869028,
|
| 812 |
+
"grad_norm": 1.4833837652546649,
|
| 813 |
+
"learning_rate": 2.550816381220243e-06,
|
| 814 |
+
"loss": 0.3846,
|
| 815 |
+
"step": 1140
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.7238148772718755,
|
| 819 |
+
"grad_norm": 1.36133901438266,
|
| 820 |
+
"learning_rate": 2.5046199865668455e-06,
|
| 821 |
+
"loss": 0.3831,
|
| 822 |
+
"step": 1150
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.7388045718568486,
|
| 826 |
+
"grad_norm": 1.4439860851050665,
|
| 827 |
+
"learning_rate": 2.458422014192267e-06,
|
| 828 |
+
"loss": 0.3811,
|
| 829 |
+
"step": 1160
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.7537942664418211,
|
| 833 |
+
"grad_norm": 1.4534544264872151,
|
| 834 |
+
"learning_rate": 2.412238240661751e-06,
|
| 835 |
+
"loss": 0.3803,
|
| 836 |
+
"step": 1170
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.7687839610267941,
|
| 840 |
+
"grad_norm": 1.4387117913666696,
|
| 841 |
+
"learning_rate": 2.366084437691651e-06,
|
| 842 |
+
"loss": 0.3824,
|
| 843 |
+
"step": 1180
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.783773655611767,
|
| 847 |
+
"grad_norm": 1.5378659951687177,
|
| 848 |
+
"learning_rate": 2.319976366763399e-06,
|
| 849 |
+
"loss": 0.3826,
|
| 850 |
+
"step": 1190
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.7987633501967397,
|
| 854 |
+
"grad_norm": 1.483205097472637,
|
| 855 |
+
"learning_rate": 2.2739297737409762e-06,
|
| 856 |
+
"loss": 0.3835,
|
| 857 |
+
"step": 1200
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.8137530447817127,
|
| 861 |
+
"grad_norm": 1.3300069022725933,
|
| 862 |
+
"learning_rate": 2.2279603834937174e-06,
|
| 863 |
+
"loss": 0.3812,
|
| 864 |
+
"step": 1210
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.8287427393666853,
|
| 868 |
+
"grad_norm": 1.3109923177187024,
|
| 869 |
+
"learning_rate": 2.1820838945262777e-06,
|
| 870 |
+
"loss": 0.3812,
|
| 871 |
+
"step": 1220
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.8437324339516583,
|
| 875 |
+
"grad_norm": 1.2956220619232373,
|
| 876 |
+
"learning_rate": 2.1363159736176124e-06,
|
| 877 |
+
"loss": 0.3835,
|
| 878 |
+
"step": 1230
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.858722128536631,
|
| 882 |
+
"grad_norm": 1.346364686268756,
|
| 883 |
+
"learning_rate": 2.090672250470785e-06,
|
| 884 |
+
"loss": 0.3801,
|
| 885 |
+
"step": 1240
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.873711823121604,
|
| 889 |
+
"grad_norm": 1.3161532319413825,
|
| 890 |
+
"learning_rate": 2.0451683123754335e-06,
|
| 891 |
+
"loss": 0.3817,
|
| 892 |
+
"step": 1250
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.8887015177065767,
|
| 896 |
+
"grad_norm": 1.4484501985394258,
|
| 897 |
+
"learning_rate": 1.9998196988847323e-06,
|
| 898 |
+
"loss": 0.3805,
|
| 899 |
+
"step": 1260
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.9036912122915495,
|
| 903 |
+
"grad_norm": 1.4224251098150107,
|
| 904 |
+
"learning_rate": 1.9546418965086444e-06,
|
| 905 |
+
"loss": 0.3793,
|
| 906 |
+
"step": 1270
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.9186809068765225,
|
| 910 |
+
"grad_norm": 1.3230244176007022,
|
| 911 |
+
"learning_rate": 1.9096503334252925e-06,
|
| 912 |
+
"loss": 0.3789,
|
| 913 |
+
"step": 1280
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.9336706014614953,
|
| 917 |
+
"grad_norm": 1.2689730119223448,
|
| 918 |
+
"learning_rate": 1.864860374212254e-06,
|
| 919 |
+
"loss": 0.3756,
|
| 920 |
+
"step": 1290
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.948660296046468,
|
| 924 |
+
"grad_norm": 1.5073419751839903,
|
| 925 |
+
"learning_rate": 1.820287314599567e-06,
|
| 926 |
+
"loss": 0.3774,
|
| 927 |
+
"step": 1300
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.9636499906314409,
|
| 931 |
+
"grad_norm": 1.372795270016621,
|
| 932 |
+
"learning_rate": 1.775946376246256e-06,
|
| 933 |
+
"loss": 0.3788,
|
| 934 |
+
"step": 1310
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.9786396852164136,
|
| 938 |
+
"grad_norm": 1.3705608316142892,
|
| 939 |
+
"learning_rate": 1.7318527015421476e-06,
|
| 940 |
+
"loss": 0.3788,
|
| 941 |
+
"step": 1320
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.9936293798013867,
|
| 945 |
+
"grad_norm": 1.3066140520804252,
|
| 946 |
+
"learning_rate": 1.6880213484367574e-06,
|
| 947 |
+
"loss": 0.3775,
|
| 948 |
+
"step": 1330
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.9996252576353757,
|
| 952 |
+
"eval_loss": 0.055769529193639755,
|
| 953 |
+
"eval_runtime": 447.0633,
|
| 954 |
+
"eval_samples_per_second": 40.211,
|
| 955 |
+
"eval_steps_per_second": 0.629,
|
| 956 |
+
"step": 1334
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 2.0086190743863592,
|
| 960 |
+
"grad_norm": 2.4434187554731905,
|
| 961 |
+
"learning_rate": 1.6444672852970194e-06,
|
| 962 |
+
"loss": 0.3289,
|
| 963 |
+
"step": 1340
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 2.0236087689713322,
|
| 967 |
+
"grad_norm": 1.6962075463721413,
|
| 968 |
+
"learning_rate": 1.6012053857955943e-06,
|
| 969 |
+
"loss": 0.2871,
|
| 970 |
+
"step": 1350
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 2.0385984635563053,
|
| 974 |
+
"grad_norm": 1.4546619427160516,
|
| 975 |
+
"learning_rate": 1.5582504238315293e-06,
|
| 976 |
+
"loss": 0.2842,
|
| 977 |
+
"step": 1360
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 2.053588158141278,
|
| 981 |
+
"grad_norm": 1.4039067144529458,
|
| 982 |
+
"learning_rate": 1.5156170684849844e-06,
|
| 983 |
+
"loss": 0.2841,
|
| 984 |
+
"step": 1370
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 2.068577852726251,
|
| 988 |
+
"grad_norm": 1.4415471956114632,
|
| 989 |
+
"learning_rate": 1.4733198790077518e-06,
|
| 990 |
+
"loss": 0.2841,
|
| 991 |
+
"step": 1380
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 2.0835675473112234,
|
| 995 |
+
"grad_norm": 1.3650988765023055,
|
| 996 |
+
"learning_rate": 1.4313732998512927e-06,
|
| 997 |
+
"loss": 0.2841,
|
| 998 |
+
"step": 1390
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 2.0985572418961964,
|
| 1002 |
+
"grad_norm": 1.334414412623332,
|
| 1003 |
+
"learning_rate": 1.389791655733959e-06,
|
| 1004 |
+
"loss": 0.283,
|
| 1005 |
+
"step": 1400
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 2.1135469364811694,
|
| 1009 |
+
"grad_norm": 1.455857794359506,
|
| 1010 |
+
"learning_rate": 1.3485891467491247e-06,
|
| 1011 |
+
"loss": 0.2822,
|
| 1012 |
+
"step": 1410
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 2.128536631066142,
|
| 1016 |
+
"grad_norm": 1.4035493431707644,
|
| 1017 |
+
"learning_rate": 1.3077798435158615e-06,
|
| 1018 |
+
"loss": 0.2858,
|
| 1019 |
+
"step": 1420
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 2.143526325651115,
|
| 1023 |
+
"grad_norm": 1.3923539809440533,
|
| 1024 |
+
"learning_rate": 1.2673776823738385e-06,
|
| 1025 |
+
"loss": 0.2832,
|
| 1026 |
+
"step": 1430
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 2.1585160202360876,
|
| 1030 |
+
"grad_norm": 1.4708372198575632,
|
| 1031 |
+
"learning_rate": 1.2273964606240718e-06,
|
| 1032 |
+
"loss": 0.2849,
|
| 1033 |
+
"step": 1440
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 2.1735057148210606,
|
| 1037 |
+
"grad_norm": 1.3821731614793016,
|
| 1038 |
+
"learning_rate": 1.1878498318171641e-06,
|
| 1039 |
+
"loss": 0.2814,
|
| 1040 |
+
"step": 1450
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 2.188495409406033,
|
| 1044 |
+
"grad_norm": 1.3685254042104387,
|
| 1045 |
+
"learning_rate": 1.1487513010906232e-06,
|
| 1046 |
+
"loss": 0.2832,
|
| 1047 |
+
"step": 1460
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 2.203485103991006,
|
| 1051 |
+
"grad_norm": 1.4477117467489642,
|
| 1052 |
+
"learning_rate": 1.1101142205568734e-06,
|
| 1053 |
+
"loss": 0.2849,
|
| 1054 |
+
"step": 1470
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 2.218474798575979,
|
| 1058 |
+
"grad_norm": 1.3837837548677747,
|
| 1059 |
+
"learning_rate": 1.0719517847435218e-06,
|
| 1060 |
+
"loss": 0.2866,
|
| 1061 |
+
"step": 1480
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 2.2334644931609517,
|
| 1065 |
+
"grad_norm": 1.3463627570256054,
|
| 1066 |
+
"learning_rate": 1.0342770260874365e-06,
|
| 1067 |
+
"loss": 0.2857,
|
| 1068 |
+
"step": 1490
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 2.2484541877459248,
|
| 1072 |
+
"grad_norm": 1.3928362831606316,
|
| 1073 |
+
"learning_rate": 9.971028104841869e-07,
|
| 1074 |
+
"loss": 0.2817,
|
| 1075 |
+
"step": 1500
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 2.2634438823308973,
|
| 1079 |
+
"grad_norm": 1.3461504649063996,
|
| 1080 |
+
"learning_rate": 9.604418328943447e-07,
|
| 1081 |
+
"loss": 0.2821,
|
| 1082 |
+
"step": 1510
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 2.2784335769158703,
|
| 1086 |
+
"grad_norm": 1.4687885214881415,
|
| 1087 |
+
"learning_rate": 9.243066130081713e-07,
|
| 1088 |
+
"loss": 0.2835,
|
| 1089 |
+
"step": 1520
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 2.2934232715008434,
|
| 1093 |
+
"grad_norm": 1.3886295267035924,
|
| 1094 |
+
"learning_rate": 8.887094909701547e-07,
|
| 1095 |
+
"loss": 0.2834,
|
| 1096 |
+
"step": 1530
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 2.308412966085816,
|
| 1100 |
+
"grad_norm": 1.407350206723039,
|
| 1101 |
+
"learning_rate": 8.536626231648595e-07,
|
| 1102 |
+
"loss": 0.2842,
|
| 1103 |
+
"step": 1540
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 2.323402660670789,
|
| 1107 |
+
"grad_norm": 1.4132800816314468,
|
| 1108 |
+
"learning_rate": 8.191779780655354e-07,
|
| 1109 |
+
"loss": 0.2832,
|
| 1110 |
+
"step": 1550
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 2.3383923552557615,
|
| 1114 |
+
"grad_norm": 1.3897894960759776,
|
| 1115 |
+
"learning_rate": 7.852673321468918e-07,
|
| 1116 |
+
"loss": 0.2843,
|
| 1117 |
+
"step": 1560
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 2.3533820498407345,
|
| 1121 |
+
"grad_norm": 1.3674616825887331,
|
| 1122 |
+
"learning_rate": 7.519422658634443e-07,
|
| 1123 |
+
"loss": 0.2823,
|
| 1124 |
+
"step": 1570
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 2.3683717444257075,
|
| 1128 |
+
"grad_norm": 1.3431475279285507,
|
| 1129 |
+
"learning_rate": 7.19214159694799e-07,
|
| 1130 |
+
"loss": 0.2828,
|
| 1131 |
+
"step": 1580
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 2.38336143901068,
|
| 1135 |
+
"grad_norm": 1.36945515422048,
|
| 1136 |
+
"learning_rate": 6.870941902592307e-07,
|
| 1137 |
+
"loss": 0.2825,
|
| 1138 |
+
"step": 1590
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 2.398351133595653,
|
| 1142 |
+
"grad_norm": 1.3520131185837208,
|
| 1143 |
+
"learning_rate": 6.555933264968753e-07,
|
| 1144 |
+
"loss": 0.2822,
|
| 1145 |
+
"step": 1600
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 2.4133408281806257,
|
| 1149 |
+
"grad_norm": 1.3647629196713102,
|
| 1150 |
+
"learning_rate": 6.247223259238511e-07,
|
| 1151 |
+
"loss": 0.2836,
|
| 1152 |
+
"step": 1610
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 2.4283305227655987,
|
| 1156 |
+
"grad_norm": 1.3570825621596334,
|
| 1157 |
+
"learning_rate": 5.944917309585721e-07,
|
| 1158 |
+
"loss": 0.2826,
|
| 1159 |
+
"step": 1620
|
| 1160 |
+
},
|
| 1161 |
+
{
|
| 1162 |
+
"epoch": 2.4433202173505713,
|
| 1163 |
+
"grad_norm": 1.3656854475785716,
|
| 1164 |
+
"learning_rate": 5.649118653215243e-07,
|
| 1165 |
+
"loss": 0.2812,
|
| 1166 |
+
"step": 1630
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 2.4583099119355443,
|
| 1170 |
+
"grad_norm": 1.363047695272134,
|
| 1171 |
+
"learning_rate": 5.359928305097245e-07,
|
| 1172 |
+
"loss": 0.2831,
|
| 1173 |
+
"step": 1640
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 2.4732996065205173,
|
| 1177 |
+
"grad_norm": 1.3184093693943801,
|
| 1178 |
+
"learning_rate": 5.077445023470676e-07,
|
| 1179 |
+
"loss": 0.2811,
|
| 1180 |
+
"step": 1650
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 2.48828930110549,
|
| 1184 |
+
"grad_norm": 1.3684794544811556,
|
| 1185 |
+
"learning_rate": 4.801765276117437e-07,
|
| 1186 |
+
"loss": 0.2808,
|
| 1187 |
+
"step": 1660
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 2.503278995690463,
|
| 1191 |
+
"grad_norm": 1.3593878648901627,
|
| 1192 |
+
"learning_rate": 4.5329832074186953e-07,
|
| 1193 |
+
"loss": 0.2794,
|
| 1194 |
+
"step": 1670
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 2.518268690275436,
|
| 1198 |
+
"grad_norm": 1.3880945115426904,
|
| 1199 |
+
"learning_rate": 4.271190606204681e-07,
|
| 1200 |
+
"loss": 0.2826,
|
| 1201 |
+
"step": 1680
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 2.5332583848604084,
|
| 1205 |
+
"grad_norm": 1.3996837354689144,
|
| 1206 |
+
"learning_rate": 4.016476874408867e-07,
|
| 1207 |
+
"loss": 0.2828,
|
| 1208 |
+
"step": 1690
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 2.5482480794453815,
|
| 1212 |
+
"grad_norm": 1.3109833857184636,
|
| 1213 |
+
"learning_rate": 3.768928996537319e-07,
|
| 1214 |
+
"loss": 0.2803,
|
| 1215 |
+
"step": 1700
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 2.563237774030354,
|
| 1219 |
+
"grad_norm": 1.3073342543118396,
|
| 1220 |
+
"learning_rate": 3.528631509963562e-07,
|
| 1221 |
+
"loss": 0.2799,
|
| 1222 |
+
"step": 1710
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 2.578227468615327,
|
| 1226 |
+
"grad_norm": 1.2885685486893088,
|
| 1227 |
+
"learning_rate": 3.2956664760591143e-07,
|
| 1228 |
+
"loss": 0.2829,
|
| 1229 |
+
"step": 1720
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 2.5932171632002996,
|
| 1233 |
+
"grad_norm": 1.290934296805027,
|
| 1234 |
+
"learning_rate": 3.0701134521696373e-07,
|
| 1235 |
+
"loss": 0.2832,
|
| 1236 |
+
"step": 1730
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 2.6082068577852726,
|
| 1240 |
+
"grad_norm": 1.3206650202687746,
|
| 1241 |
+
"learning_rate": 2.852049464446158e-07,
|
| 1242 |
+
"loss": 0.2815,
|
| 1243 |
+
"step": 1740
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 2.6231965523702456,
|
| 1247 |
+
"grad_norm": 1.3086968161796841,
|
| 1248 |
+
"learning_rate": 2.641548981540712e-07,
|
| 1249 |
+
"loss": 0.2818,
|
| 1250 |
+
"step": 1750
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 2.638186246955218,
|
| 1254 |
+
"grad_norm": 1.3204039831254113,
|
| 1255 |
+
"learning_rate": 2.4386838891753695e-07,
|
| 1256 |
+
"loss": 0.2804,
|
| 1257 |
+
"step": 1760
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 2.653175941540191,
|
| 1261 |
+
"grad_norm": 1.2730494032898578,
|
| 1262 |
+
"learning_rate": 2.2435234655933363e-07,
|
| 1263 |
+
"loss": 0.2802,
|
| 1264 |
+
"step": 1770
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 2.668165636125164,
|
| 1268 |
+
"grad_norm": 1.3271281759783882,
|
| 1269 |
+
"learning_rate": 2.0561343579004716e-07,
|
| 1270 |
+
"loss": 0.2824,
|
| 1271 |
+
"step": 1780
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 2.683155330710137,
|
| 1275 |
+
"grad_norm": 1.272138432855408,
|
| 1276 |
+
"learning_rate": 1.8765805593053855e-07,
|
| 1277 |
+
"loss": 0.2818,
|
| 1278 |
+
"step": 1790
|
| 1279 |
+
},
|
| 1280 |
+
{
|
| 1281 |
+
"epoch": 2.6981450252951094,
|
| 1282 |
+
"grad_norm": 1.3350408814644847,
|
| 1283 |
+
"learning_rate": 1.7049233872658084e-07,
|
| 1284 |
+
"loss": 0.2852,
|
| 1285 |
+
"step": 1800
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 2.7131347198800824,
|
| 1289 |
+
"grad_norm": 1.2658770429218549,
|
| 1290 |
+
"learning_rate": 1.5412214625487336e-07,
|
| 1291 |
+
"loss": 0.2824,
|
| 1292 |
+
"step": 1810
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 2.7281244144650554,
|
| 1296 |
+
"grad_norm": 1.274527251752829,
|
| 1297 |
+
"learning_rate": 1.3855306892114867e-07,
|
| 1298 |
+
"loss": 0.2814,
|
| 1299 |
+
"step": 1820
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 2.743114109050028,
|
| 1303 |
+
"grad_norm": 1.3482622846337229,
|
| 1304 |
+
"learning_rate": 1.2379042355105314e-07,
|
| 1305 |
+
"loss": 0.2774,
|
| 1306 |
+
"step": 1830
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 2.758103803635001,
|
| 1310 |
+
"grad_norm": 1.2728958780405912,
|
| 1311 |
+
"learning_rate": 1.0983925157445674e-07,
|
| 1312 |
+
"loss": 0.2836,
|
| 1313 |
+
"step": 1840
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 2.773093498219974,
|
| 1317 |
+
"grad_norm": 1.3207497967530821,
|
| 1318 |
+
"learning_rate": 9.670431730380847e-08,
|
| 1319 |
+
"loss": 0.2821,
|
| 1320 |
+
"step": 1850
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 2.7880831928049465,
|
| 1324 |
+
"grad_norm": 1.2622090696282842,
|
| 1325 |
+
"learning_rate": 8.439010630712841e-08,
|
| 1326 |
+
"loss": 0.2816,
|
| 1327 |
+
"step": 1860
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 2.8030728873899196,
|
| 1331 |
+
"grad_norm": 1.2844690751523753,
|
| 1332 |
+
"learning_rate": 7.29008238761919e-08,
|
| 1333 |
+
"loss": 0.2808,
|
| 1334 |
+
"step": 1870
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 2.818062581974892,
|
| 1338 |
+
"grad_norm": 1.2941614154033414,
|
| 1339 |
+
"learning_rate": 6.224039359042284e-08,
|
| 1340 |
+
"loss": 0.2819,
|
| 1341 |
+
"step": 1880
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 2.833052276559865,
|
| 1345 |
+
"grad_norm": 1.2887376421660586,
|
| 1346 |
+
"learning_rate": 5.2412455976998125e-08,
|
| 1347 |
+
"loss": 0.2815,
|
| 1348 |
+
"step": 1890
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 2.8480419711448377,
|
| 1352 |
+
"grad_norm": 1.3081913600486883,
|
| 1353 |
+
"learning_rate": 4.342036726760895e-08,
|
| 1354 |
+
"loss": 0.2823,
|
| 1355 |
+
"step": 1900
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 2.8630316657298107,
|
| 1359 |
+
"grad_norm": 1.288972689881046,
|
| 1360 |
+
"learning_rate": 3.5267198252312286e-08,
|
| 1361 |
+
"loss": 0.2847,
|
| 1362 |
+
"step": 1910
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 2.8780213603147837,
|
| 1366 |
+
"grad_norm": 1.270248787618671,
|
| 1367 |
+
"learning_rate": 2.795573323085721e-08,
|
| 1368 |
+
"loss": 0.2794,
|
| 1369 |
+
"step": 1920
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 2.8930110548997563,
|
| 1373 |
+
"grad_norm": 1.2837754103434724,
|
| 1374 |
+
"learning_rate": 2.148846906185109e-08,
|
| 1375 |
+
"loss": 0.2798,
|
| 1376 |
+
"step": 1930
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 2.9080007494847293,
|
| 1380 |
+
"grad_norm": 1.2838868602793667,
|
| 1381 |
+
"learning_rate": 1.586761431008249e-08,
|
| 1382 |
+
"loss": 0.2798,
|
| 1383 |
+
"step": 1940
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 2.9229904440697023,
|
| 1387 |
+
"grad_norm": 1.3051039321280986,
|
| 1388 |
+
"learning_rate": 1.109508849230001e-08,
|
| 1389 |
+
"loss": 0.281,
|
| 1390 |
+
"step": 1950
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"epoch": 2.937980138654675,
|
| 1394 |
+
"grad_norm": 1.3082478451744641,
|
| 1395 |
+
"learning_rate": 7.172521421698331e-09,
|
| 1396 |
+
"loss": 0.2805,
|
| 1397 |
+
"step": 1960
|
| 1398 |
+
},
|
| 1399 |
+
{
|
| 1400 |
+
"epoch": 2.952969833239648,
|
| 1401 |
+
"grad_norm": 1.2997068680343178,
|
| 1402 |
+
"learning_rate": 4.101252651338428e-09,
|
| 1403 |
+
"loss": 0.2816,
|
| 1404 |
+
"step": 1970
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 2.9679595278246205,
|
| 1408 |
+
"grad_norm": 1.280634823351821,
|
| 1409 |
+
"learning_rate": 1.8823310166918297e-09,
|
| 1410 |
+
"loss": 0.2806,
|
| 1411 |
+
"step": 1980
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 2.9829492224095935,
|
| 1415 |
+
"grad_norm": 1.2887159666168426,
|
| 1416 |
+
"learning_rate": 5.165142774640752e-10,
|
| 1417 |
+
"loss": 0.28,
|
| 1418 |
+
"step": 1990
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 2.997938916994566,
|
| 1422 |
+
"grad_norm": 1.2890732808929788,
|
| 1423 |
+
"learning_rate": 4.26885882032213e-12,
|
| 1424 |
+
"loss": 0.2791,
|
| 1425 |
+
"step": 2000
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 2.9994378864530633,
|
| 1429 |
+
"eval_loss": 0.058169443160295486,
|
| 1430 |
+
"eval_runtime": 450.8985,
|
| 1431 |
+
"eval_samples_per_second": 39.869,
|
| 1432 |
+
"eval_steps_per_second": 0.623,
|
| 1433 |
+
"step": 2001
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 2.9994378864530633,
|
| 1437 |
+
"step": 2001,
|
| 1438 |
+
"total_flos": 3351540148469760.0,
|
| 1439 |
+
"train_loss": 0.4023907120408921,
|
| 1440 |
+
"train_runtime": 64801.3882,
|
| 1441 |
+
"train_samples_per_second": 15.812,
|
| 1442 |
+
"train_steps_per_second": 0.031
|
| 1443 |
+
}
|
| 1444 |
+
],
|
| 1445 |
+
"logging_steps": 10,
|
| 1446 |
+
"max_steps": 2001,
|
| 1447 |
+
"num_input_tokens_seen": 0,
|
| 1448 |
+
"num_train_epochs": 3,
|
| 1449 |
+
"save_steps": 500,
|
| 1450 |
+
"stateful_callbacks": {
|
| 1451 |
+
"TrainerControl": {
|
| 1452 |
+
"args": {
|
| 1453 |
+
"should_epoch_stop": false,
|
| 1454 |
+
"should_evaluate": false,
|
| 1455 |
+
"should_log": false,
|
| 1456 |
+
"should_save": true,
|
| 1457 |
+
"should_training_stop": true
|
| 1458 |
+
},
|
| 1459 |
+
"attributes": {}
|
| 1460 |
+
}
|
| 1461 |
+
},
|
| 1462 |
+
"total_flos": 3351540148469760.0,
|
| 1463 |
+
"train_batch_size": 8,
|
| 1464 |
+
"trial_name": null,
|
| 1465 |
+
"trial_params": null
|
| 1466 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|