End of training
Browse files- README.md +3 -2
- all_results.json +12 -0
- eval_results.json +7 -0
- train_results.json +8 -0
- trainer_state.json +2865 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: mit
|
|
| 4 |
base_model: klyang/MentaLLaMA-chat-7B-hf
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: MentaLLaMA-chat-7B-PsyCourse-fold5
|
|
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# MentaLLaMA-chat-7B-PsyCourse-fold5
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [klyang/MentaLLaMA-chat-7B-hf](https://huggingface.co/klyang/MentaLLaMA-chat-7B-hf) on
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: 0.
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 4 |
base_model: klyang/MentaLLaMA-chat-7B-hf
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- lora
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: MentaLLaMA-chat-7B-PsyCourse-fold5
|
|
|
|
| 16 |
|
| 17 |
# MentaLLaMA-chat-7B-PsyCourse-fold5
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [klyang/MentaLLaMA-chat-7B-hf](https://huggingface.co/klyang/MentaLLaMA-chat-7B-hf) on the course-train-fold5 dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.0295
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.9971563981042655,
|
| 3 |
+
"eval_loss": 0.029545707628130913,
|
| 4 |
+
"eval_runtime": 176.0523,
|
| 5 |
+
"eval_samples_per_second": 6.663,
|
| 6 |
+
"eval_steps_per_second": 6.663,
|
| 7 |
+
"total_flos": 8.907449267845202e+17,
|
| 8 |
+
"train_loss": 0.04891899318543117,
|
| 9 |
+
"train_runtime": 37195.0472,
|
| 10 |
+
"train_samples_per_second": 1.418,
|
| 11 |
+
"train_steps_per_second": 0.089
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.9971563981042655,
|
| 3 |
+
"eval_loss": 0.029545707628130913,
|
| 4 |
+
"eval_runtime": 176.0523,
|
| 5 |
+
"eval_samples_per_second": 6.663,
|
| 6 |
+
"eval_steps_per_second": 6.663
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.9971563981042655,
|
| 3 |
+
"total_flos": 8.907449267845202e+17,
|
| 4 |
+
"train_loss": 0.04891899318543117,
|
| 5 |
+
"train_runtime": 37195.0472,
|
| 6 |
+
"train_samples_per_second": 1.418,
|
| 7 |
+
"train_steps_per_second": 0.089
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2865 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.029545707628130913,
|
| 3 |
+
"best_model_checkpoint": "saves/psy-course/MentaLLaMA-chat-7B/train/fold5/checkpoint-1250",
|
| 4 |
+
"epoch": 4.9971563981042655,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 3295,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.015165876777251185,
|
| 13 |
+
"grad_norm": 2.013413429260254,
|
| 14 |
+
"learning_rate": 3.0303030303030305e-06,
|
| 15 |
+
"loss": 1.6489,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.03033175355450237,
|
| 20 |
+
"grad_norm": 1.7110595703125,
|
| 21 |
+
"learning_rate": 6.060606060606061e-06,
|
| 22 |
+
"loss": 1.6363,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.04549763033175355,
|
| 27 |
+
"grad_norm": 2.262253761291504,
|
| 28 |
+
"learning_rate": 9.090909090909091e-06,
|
| 29 |
+
"loss": 1.6613,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.06066350710900474,
|
| 34 |
+
"grad_norm": 3.292367696762085,
|
| 35 |
+
"learning_rate": 1.2121212121212122e-05,
|
| 36 |
+
"loss": 1.2702,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.07582938388625593,
|
| 41 |
+
"grad_norm": 0.9315681457519531,
|
| 42 |
+
"learning_rate": 1.5151515151515153e-05,
|
| 43 |
+
"loss": 0.8836,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.07582938388625593,
|
| 48 |
+
"eval_loss": 0.6509825587272644,
|
| 49 |
+
"eval_runtime": 177.0,
|
| 50 |
+
"eval_samples_per_second": 6.627,
|
| 51 |
+
"eval_steps_per_second": 6.627,
|
| 52 |
+
"step": 50
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.0909952606635071,
|
| 56 |
+
"grad_norm": 1.0166341066360474,
|
| 57 |
+
"learning_rate": 1.8181818181818182e-05,
|
| 58 |
+
"loss": 0.7411,
|
| 59 |
+
"step": 60
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.1061611374407583,
|
| 63 |
+
"grad_norm": 1.0003480911254883,
|
| 64 |
+
"learning_rate": 2.1212121212121215e-05,
|
| 65 |
+
"loss": 0.4577,
|
| 66 |
+
"step": 70
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.12132701421800948,
|
| 70 |
+
"grad_norm": 0.6172419190406799,
|
| 71 |
+
"learning_rate": 2.4242424242424244e-05,
|
| 72 |
+
"loss": 0.338,
|
| 73 |
+
"step": 80
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.13649289099526066,
|
| 77 |
+
"grad_norm": 0.6985596418380737,
|
| 78 |
+
"learning_rate": 2.7272727272727273e-05,
|
| 79 |
+
"loss": 0.1643,
|
| 80 |
+
"step": 90
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.15165876777251186,
|
| 84 |
+
"grad_norm": 0.6572972536087036,
|
| 85 |
+
"learning_rate": 3.0303030303030306e-05,
|
| 86 |
+
"loss": 0.1276,
|
| 87 |
+
"step": 100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.15165876777251186,
|
| 91 |
+
"eval_loss": 0.11501473188400269,
|
| 92 |
+
"eval_runtime": 176.988,
|
| 93 |
+
"eval_samples_per_second": 6.628,
|
| 94 |
+
"eval_steps_per_second": 6.628,
|
| 95 |
+
"step": 100
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.16682464454976303,
|
| 99 |
+
"grad_norm": 0.4842168986797333,
|
| 100 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 101 |
+
"loss": 0.1344,
|
| 102 |
+
"step": 110
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.1819905213270142,
|
| 106 |
+
"grad_norm": 0.6832391023635864,
|
| 107 |
+
"learning_rate": 3.6363636363636364e-05,
|
| 108 |
+
"loss": 0.0992,
|
| 109 |
+
"step": 120
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.1971563981042654,
|
| 113 |
+
"grad_norm": 0.7095351815223694,
|
| 114 |
+
"learning_rate": 3.939393939393939e-05,
|
| 115 |
+
"loss": 0.0818,
|
| 116 |
+
"step": 130
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.2123222748815166,
|
| 120 |
+
"grad_norm": 0.7936357855796814,
|
| 121 |
+
"learning_rate": 4.242424242424243e-05,
|
| 122 |
+
"loss": 0.0765,
|
| 123 |
+
"step": 140
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.22748815165876776,
|
| 127 |
+
"grad_norm": 0.8350841999053955,
|
| 128 |
+
"learning_rate": 4.545454545454546e-05,
|
| 129 |
+
"loss": 0.0848,
|
| 130 |
+
"step": 150
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.22748815165876776,
|
| 134 |
+
"eval_loss": 0.07310865074396133,
|
| 135 |
+
"eval_runtime": 177.0391,
|
| 136 |
+
"eval_samples_per_second": 6.626,
|
| 137 |
+
"eval_steps_per_second": 6.626,
|
| 138 |
+
"step": 150
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.24265402843601896,
|
| 142 |
+
"grad_norm": 0.9234074950218201,
|
| 143 |
+
"learning_rate": 4.848484848484849e-05,
|
| 144 |
+
"loss": 0.084,
|
| 145 |
+
"step": 160
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.25781990521327014,
|
| 149 |
+
"grad_norm": 0.9987066984176636,
|
| 150 |
+
"learning_rate": 5.151515151515152e-05,
|
| 151 |
+
"loss": 0.0789,
|
| 152 |
+
"step": 170
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.2729857819905213,
|
| 156 |
+
"grad_norm": 0.5734285712242126,
|
| 157 |
+
"learning_rate": 5.4545454545454546e-05,
|
| 158 |
+
"loss": 0.0655,
|
| 159 |
+
"step": 180
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.2881516587677725,
|
| 163 |
+
"grad_norm": 0.5533661246299744,
|
| 164 |
+
"learning_rate": 5.757575757575758e-05,
|
| 165 |
+
"loss": 0.0537,
|
| 166 |
+
"step": 190
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.3033175355450237,
|
| 170 |
+
"grad_norm": 0.674788236618042,
|
| 171 |
+
"learning_rate": 6.060606060606061e-05,
|
| 172 |
+
"loss": 0.0545,
|
| 173 |
+
"step": 200
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.3033175355450237,
|
| 177 |
+
"eval_loss": 0.0569460466504097,
|
| 178 |
+
"eval_runtime": 177.0841,
|
| 179 |
+
"eval_samples_per_second": 6.624,
|
| 180 |
+
"eval_steps_per_second": 6.624,
|
| 181 |
+
"step": 200
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.3184834123222749,
|
| 185 |
+
"grad_norm": 0.6172575354576111,
|
| 186 |
+
"learning_rate": 6.363636363636364e-05,
|
| 187 |
+
"loss": 0.0637,
|
| 188 |
+
"step": 210
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.33364928909952607,
|
| 192 |
+
"grad_norm": 0.2991991341114044,
|
| 193 |
+
"learning_rate": 6.666666666666667e-05,
|
| 194 |
+
"loss": 0.0772,
|
| 195 |
+
"step": 220
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.34881516587677724,
|
| 199 |
+
"grad_norm": 0.7083033919334412,
|
| 200 |
+
"learning_rate": 6.96969696969697e-05,
|
| 201 |
+
"loss": 0.0482,
|
| 202 |
+
"step": 230
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.3639810426540284,
|
| 206 |
+
"grad_norm": 0.3638122081756592,
|
| 207 |
+
"learning_rate": 7.272727272727273e-05,
|
| 208 |
+
"loss": 0.0454,
|
| 209 |
+
"step": 240
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.3791469194312796,
|
| 213 |
+
"grad_norm": 0.5038028955459595,
|
| 214 |
+
"learning_rate": 7.575757575757576e-05,
|
| 215 |
+
"loss": 0.0542,
|
| 216 |
+
"step": 250
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.3791469194312796,
|
| 220 |
+
"eval_loss": 0.04985937476158142,
|
| 221 |
+
"eval_runtime": 177.0515,
|
| 222 |
+
"eval_samples_per_second": 6.625,
|
| 223 |
+
"eval_steps_per_second": 6.625,
|
| 224 |
+
"step": 250
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.3943127962085308,
|
| 228 |
+
"grad_norm": 0.8618497252464294,
|
| 229 |
+
"learning_rate": 7.878787878787879e-05,
|
| 230 |
+
"loss": 0.0507,
|
| 231 |
+
"step": 260
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.409478672985782,
|
| 235 |
+
"grad_norm": 0.7346657514572144,
|
| 236 |
+
"learning_rate": 8.181818181818183e-05,
|
| 237 |
+
"loss": 0.0433,
|
| 238 |
+
"step": 270
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.4246445497630332,
|
| 242 |
+
"grad_norm": 0.42429229617118835,
|
| 243 |
+
"learning_rate": 8.484848484848486e-05,
|
| 244 |
+
"loss": 0.0452,
|
| 245 |
+
"step": 280
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.43981042654028435,
|
| 249 |
+
"grad_norm": 0.8676588535308838,
|
| 250 |
+
"learning_rate": 8.787878787878789e-05,
|
| 251 |
+
"loss": 0.0555,
|
| 252 |
+
"step": 290
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.4549763033175355,
|
| 256 |
+
"grad_norm": 0.42583391070365906,
|
| 257 |
+
"learning_rate": 9.090909090909092e-05,
|
| 258 |
+
"loss": 0.0466,
|
| 259 |
+
"step": 300
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 0.4549763033175355,
|
| 263 |
+
"eval_loss": 0.05100926011800766,
|
| 264 |
+
"eval_runtime": 176.973,
|
| 265 |
+
"eval_samples_per_second": 6.628,
|
| 266 |
+
"eval_steps_per_second": 6.628,
|
| 267 |
+
"step": 300
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.47014218009478675,
|
| 271 |
+
"grad_norm": 0.2199127972126007,
|
| 272 |
+
"learning_rate": 9.393939393939395e-05,
|
| 273 |
+
"loss": 0.0506,
|
| 274 |
+
"step": 310
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.48530805687203793,
|
| 278 |
+
"grad_norm": 0.45029717683792114,
|
| 279 |
+
"learning_rate": 9.696969696969698e-05,
|
| 280 |
+
"loss": 0.0408,
|
| 281 |
+
"step": 320
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.500473933649289,
|
| 285 |
+
"grad_norm": 0.32426029443740845,
|
| 286 |
+
"learning_rate": 0.0001,
|
| 287 |
+
"loss": 0.0497,
|
| 288 |
+
"step": 330
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.5156398104265403,
|
| 292 |
+
"grad_norm": 0.28149813413619995,
|
| 293 |
+
"learning_rate": 9.999719336268101e-05,
|
| 294 |
+
"loss": 0.0544,
|
| 295 |
+
"step": 340
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.5308056872037915,
|
| 299 |
+
"grad_norm": 0.6782774329185486,
|
| 300 |
+
"learning_rate": 9.998877376581251e-05,
|
| 301 |
+
"loss": 0.0517,
|
| 302 |
+
"step": 350
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.5308056872037915,
|
| 306 |
+
"eval_loss": 0.04681693762540817,
|
| 307 |
+
"eval_runtime": 176.9687,
|
| 308 |
+
"eval_samples_per_second": 6.628,
|
| 309 |
+
"eval_steps_per_second": 6.628,
|
| 310 |
+
"step": 350
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.5459715639810426,
|
| 314 |
+
"grad_norm": 0.5462453961372375,
|
| 315 |
+
"learning_rate": 9.997474215462472e-05,
|
| 316 |
+
"loss": 0.0539,
|
| 317 |
+
"step": 360
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.5611374407582939,
|
| 321 |
+
"grad_norm": 0.3318583071231842,
|
| 322 |
+
"learning_rate": 9.995510010438337e-05,
|
| 323 |
+
"loss": 0.0322,
|
| 324 |
+
"step": 370
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.576303317535545,
|
| 328 |
+
"grad_norm": 0.41357553005218506,
|
| 329 |
+
"learning_rate": 9.992984982021295e-05,
|
| 330 |
+
"loss": 0.0644,
|
| 331 |
+
"step": 380
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.5914691943127962,
|
| 335 |
+
"grad_norm": 0.3177831470966339,
|
| 336 |
+
"learning_rate": 9.9898994136849e-05,
|
| 337 |
+
"loss": 0.0582,
|
| 338 |
+
"step": 390
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.6066350710900474,
|
| 342 |
+
"grad_norm": 0.44203853607177734,
|
| 343 |
+
"learning_rate": 9.986253651832005e-05,
|
| 344 |
+
"loss": 0.058,
|
| 345 |
+
"step": 400
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.6066350710900474,
|
| 349 |
+
"eval_loss": 0.04563398286700249,
|
| 350 |
+
"eval_runtime": 176.9795,
|
| 351 |
+
"eval_samples_per_second": 6.628,
|
| 352 |
+
"eval_steps_per_second": 6.628,
|
| 353 |
+
"step": 400
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.6218009478672986,
|
| 357 |
+
"grad_norm": 0.4002712368965149,
|
| 358 |
+
"learning_rate": 9.982048105755859e-05,
|
| 359 |
+
"loss": 0.0374,
|
| 360 |
+
"step": 410
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.6369668246445498,
|
| 364 |
+
"grad_norm": 0.3213963806629181,
|
| 365 |
+
"learning_rate": 9.977283247594166e-05,
|
| 366 |
+
"loss": 0.0351,
|
| 367 |
+
"step": 420
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.6521327014218009,
|
| 371 |
+
"grad_norm": 0.3570813834667206,
|
| 372 |
+
"learning_rate": 9.971959612276076e-05,
|
| 373 |
+
"loss": 0.0564,
|
| 374 |
+
"step": 430
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.6672985781990521,
|
| 378 |
+
"grad_norm": 0.37261441349983215,
|
| 379 |
+
"learning_rate": 9.966077797462129e-05,
|
| 380 |
+
"loss": 0.0455,
|
| 381 |
+
"step": 440
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.6824644549763034,
|
| 385 |
+
"grad_norm": 0.647449791431427,
|
| 386 |
+
"learning_rate": 9.959638463477165e-05,
|
| 387 |
+
"loss": 0.0521,
|
| 388 |
+
"step": 450
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.6824644549763034,
|
| 392 |
+
"eval_loss": 0.04050007835030556,
|
| 393 |
+
"eval_runtime": 177.0646,
|
| 394 |
+
"eval_samples_per_second": 6.625,
|
| 395 |
+
"eval_steps_per_second": 6.625,
|
| 396 |
+
"step": 450
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.6976303317535545,
|
| 400 |
+
"grad_norm": 0.3081929385662079,
|
| 401 |
+
"learning_rate": 9.952642333236186e-05,
|
| 402 |
+
"loss": 0.045,
|
| 403 |
+
"step": 460
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.7127962085308057,
|
| 407 |
+
"grad_norm": 0.356259822845459,
|
| 408 |
+
"learning_rate": 9.945090192163202e-05,
|
| 409 |
+
"loss": 0.0407,
|
| 410 |
+
"step": 470
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.7279620853080568,
|
| 414 |
+
"grad_norm": 0.2743074297904968,
|
| 415 |
+
"learning_rate": 9.936982888103051e-05,
|
| 416 |
+
"loss": 0.0328,
|
| 417 |
+
"step": 480
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.7431279620853081,
|
| 421 |
+
"grad_norm": 0.2799587547779083,
|
| 422 |
+
"learning_rate": 9.928321331226219e-05,
|
| 423 |
+
"loss": 0.0515,
|
| 424 |
+
"step": 490
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.7582938388625592,
|
| 428 |
+
"grad_norm": 0.7967923283576965,
|
| 429 |
+
"learning_rate": 9.919106493926655e-05,
|
| 430 |
+
"loss": 0.0317,
|
| 431 |
+
"step": 500
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.7582938388625592,
|
| 435 |
+
"eval_loss": 0.038231153041124344,
|
| 436 |
+
"eval_runtime": 177.1303,
|
| 437 |
+
"eval_samples_per_second": 6.622,
|
| 438 |
+
"eval_steps_per_second": 6.622,
|
| 439 |
+
"step": 500
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.7734597156398104,
|
| 443 |
+
"grad_norm": 0.4232497811317444,
|
| 444 |
+
"learning_rate": 9.909339410712612e-05,
|
| 445 |
+
"loss": 0.0453,
|
| 446 |
+
"step": 510
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.7886255924170616,
|
| 450 |
+
"grad_norm": 0.17073428630828857,
|
| 451 |
+
"learning_rate": 9.8990211780905e-05,
|
| 452 |
+
"loss": 0.0286,
|
| 453 |
+
"step": 520
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.8037914691943128,
|
| 457 |
+
"grad_norm": 0.5338394045829773,
|
| 458 |
+
"learning_rate": 9.888152954441785e-05,
|
| 459 |
+
"loss": 0.0489,
|
| 460 |
+
"step": 530
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.818957345971564,
|
| 464 |
+
"grad_norm": 0.2233201563358307,
|
| 465 |
+
"learning_rate": 9.876735959892953e-05,
|
| 466 |
+
"loss": 0.0411,
|
| 467 |
+
"step": 540
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.8341232227488151,
|
| 471 |
+
"grad_norm": 0.25685688853263855,
|
| 472 |
+
"learning_rate": 9.864771476178522e-05,
|
| 473 |
+
"loss": 0.0281,
|
| 474 |
+
"step": 550
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.8341232227488151,
|
| 478 |
+
"eval_loss": 0.038973063230514526,
|
| 479 |
+
"eval_runtime": 177.0687,
|
| 480 |
+
"eval_samples_per_second": 6.625,
|
| 481 |
+
"eval_steps_per_second": 6.625,
|
| 482 |
+
"step": 550
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.8492890995260663,
|
| 486 |
+
"grad_norm": 0.2585074007511139,
|
| 487 |
+
"learning_rate": 9.852260846497153e-05,
|
| 488 |
+
"loss": 0.0357,
|
| 489 |
+
"step": 560
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.8644549763033176,
|
| 493 |
+
"grad_norm": 0.3039783537387848,
|
| 494 |
+
"learning_rate": 9.839205475360851e-05,
|
| 495 |
+
"loss": 0.0425,
|
| 496 |
+
"step": 570
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.8796208530805687,
|
| 500 |
+
"grad_norm": 0.34413889050483704,
|
| 501 |
+
"learning_rate": 9.825606828437291e-05,
|
| 502 |
+
"loss": 0.0428,
|
| 503 |
+
"step": 580
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 0.8947867298578199,
|
| 507 |
+
"grad_norm": 0.23396067321300507,
|
| 508 |
+
"learning_rate": 9.811466432385267e-05,
|
| 509 |
+
"loss": 0.0472,
|
| 510 |
+
"step": 590
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 0.909952606635071,
|
| 514 |
+
"grad_norm": 0.15519942343235016,
|
| 515 |
+
"learning_rate": 9.796785874683314e-05,
|
| 516 |
+
"loss": 0.0388,
|
| 517 |
+
"step": 600
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 0.909952606635071,
|
| 521 |
+
"eval_loss": 0.03878552094101906,
|
| 522 |
+
"eval_runtime": 177.1078,
|
| 523 |
+
"eval_samples_per_second": 6.623,
|
| 524 |
+
"eval_steps_per_second": 6.623,
|
| 525 |
+
"step": 600
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.9251184834123223,
|
| 529 |
+
"grad_norm": 0.16990838944911957,
|
| 530 |
+
"learning_rate": 9.781566803451475e-05,
|
| 531 |
+
"loss": 0.0319,
|
| 532 |
+
"step": 610
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.9402843601895735,
|
| 536 |
+
"grad_norm": 0.21462449431419373,
|
| 537 |
+
"learning_rate": 9.765810927266281e-05,
|
| 538 |
+
"loss": 0.0288,
|
| 539 |
+
"step": 620
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.9554502369668246,
|
| 543 |
+
"grad_norm": 0.37621375918388367,
|
| 544 |
+
"learning_rate": 9.749520014968934e-05,
|
| 545 |
+
"loss": 0.0382,
|
| 546 |
+
"step": 630
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.9706161137440759,
|
| 550 |
+
"grad_norm": 0.15480560064315796,
|
| 551 |
+
"learning_rate": 9.732695895466735e-05,
|
| 552 |
+
"loss": 0.0362,
|
| 553 |
+
"step": 640
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.985781990521327,
|
| 557 |
+
"grad_norm": 0.2805449068546295,
|
| 558 |
+
"learning_rate": 9.715340457527746e-05,
|
| 559 |
+
"loss": 0.0459,
|
| 560 |
+
"step": 650
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.985781990521327,
|
| 564 |
+
"eval_loss": 0.03554915264248848,
|
| 565 |
+
"eval_runtime": 177.0579,
|
| 566 |
+
"eval_samples_per_second": 6.625,
|
| 567 |
+
"eval_steps_per_second": 6.625,
|
| 568 |
+
"step": 650
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 1.000947867298578,
|
| 572 |
+
"grad_norm": 0.20941686630249023,
|
| 573 |
+
"learning_rate": 9.697455649568761e-05,
|
| 574 |
+
"loss": 0.0373,
|
| 575 |
+
"step": 660
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 1.0161137440758294,
|
| 579 |
+
"grad_norm": 0.2722059190273285,
|
| 580 |
+
"learning_rate": 9.679043479436556e-05,
|
| 581 |
+
"loss": 0.0344,
|
| 582 |
+
"step": 670
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 1.0312796208530806,
|
| 586 |
+
"grad_norm": 0.2699989080429077,
|
| 587 |
+
"learning_rate": 9.660106014182489e-05,
|
| 588 |
+
"loss": 0.0325,
|
| 589 |
+
"step": 680
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 1.0464454976303317,
|
| 593 |
+
"grad_norm": 0.27695226669311523,
|
| 594 |
+
"learning_rate": 9.640645379830424e-05,
|
| 595 |
+
"loss": 0.0328,
|
| 596 |
+
"step": 690
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 1.061611374407583,
|
| 600 |
+
"grad_norm": 0.16520464420318604,
|
| 601 |
+
"learning_rate": 9.620663761138067e-05,
|
| 602 |
+
"loss": 0.0277,
|
| 603 |
+
"step": 700
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 1.061611374407583,
|
| 607 |
+
"eval_loss": 0.036762021481990814,
|
| 608 |
+
"eval_runtime": 177.0707,
|
| 609 |
+
"eval_samples_per_second": 6.624,
|
| 610 |
+
"eval_steps_per_second": 6.624,
|
| 611 |
+
"step": 700
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.0767772511848341,
|
| 615 |
+
"grad_norm": 0.13298264145851135,
|
| 616 |
+
"learning_rate": 9.600163401351688e-05,
|
| 617 |
+
"loss": 0.0281,
|
| 618 |
+
"step": 710
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.0919431279620853,
|
| 622 |
+
"grad_norm": 0.26888322830200195,
|
| 623 |
+
"learning_rate": 9.579146601954276e-05,
|
| 624 |
+
"loss": 0.0395,
|
| 625 |
+
"step": 720
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.1071090047393364,
|
| 629 |
+
"grad_norm": 0.23041464388370514,
|
| 630 |
+
"learning_rate": 9.557615722407177e-05,
|
| 631 |
+
"loss": 0.0356,
|
| 632 |
+
"step": 730
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.1222748815165877,
|
| 636 |
+
"grad_norm": 0.2705337703227997,
|
| 637 |
+
"learning_rate": 9.535573179885191e-05,
|
| 638 |
+
"loss": 0.0362,
|
| 639 |
+
"step": 740
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.1374407582938388,
|
| 643 |
+
"grad_norm": 0.1421772986650467,
|
| 644 |
+
"learning_rate": 9.513021449005214e-05,
|
| 645 |
+
"loss": 0.0342,
|
| 646 |
+
"step": 750
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.1374407582938388,
|
| 650 |
+
"eval_loss": 0.036910828202962875,
|
| 651 |
+
"eval_runtime": 177.1757,
|
| 652 |
+
"eval_samples_per_second": 6.621,
|
| 653 |
+
"eval_steps_per_second": 6.621,
|
| 654 |
+
"step": 750
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.15260663507109,
|
| 658 |
+
"grad_norm": 0.10349958389997482,
|
| 659 |
+
"learning_rate": 9.489963061548428e-05,
|
| 660 |
+
"loss": 0.0262,
|
| 661 |
+
"step": 760
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.1677725118483413,
|
| 665 |
+
"grad_norm": 0.3369249999523163,
|
| 666 |
+
"learning_rate": 9.466400606176062e-05,
|
| 667 |
+
"loss": 0.0335,
|
| 668 |
+
"step": 770
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.1829383886255924,
|
| 672 |
+
"grad_norm": 0.28793764114379883,
|
| 673 |
+
"learning_rate": 9.442336728138779e-05,
|
| 674 |
+
"loss": 0.0424,
|
| 675 |
+
"step": 780
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.1981042654028435,
|
| 679 |
+
"grad_norm": 0.30771031975746155,
|
| 680 |
+
"learning_rate": 9.417774128979706e-05,
|
| 681 |
+
"loss": 0.0344,
|
| 682 |
+
"step": 790
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.2132701421800949,
|
| 686 |
+
"grad_norm": 0.20611123740673065,
|
| 687 |
+
"learning_rate": 9.39271556623114e-05,
|
| 688 |
+
"loss": 0.0323,
|
| 689 |
+
"step": 800
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.2132701421800949,
|
| 693 |
+
"eval_loss": 0.033734481781721115,
|
| 694 |
+
"eval_runtime": 177.1941,
|
| 695 |
+
"eval_samples_per_second": 6.62,
|
| 696 |
+
"eval_steps_per_second": 6.62,
|
| 697 |
+
"step": 800
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 1.228436018957346,
|
| 701 |
+
"grad_norm": 0.20823083817958832,
|
| 702 |
+
"learning_rate": 9.367163853104975e-05,
|
| 703 |
+
"loss": 0.0301,
|
| 704 |
+
"step": 810
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 1.2436018957345971,
|
| 708 |
+
"grad_norm": 0.18224073946475983,
|
| 709 |
+
"learning_rate": 9.341121858176876e-05,
|
| 710 |
+
"loss": 0.0327,
|
| 711 |
+
"step": 820
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 1.2587677725118485,
|
| 715 |
+
"grad_norm": 0.2314557433128357,
|
| 716 |
+
"learning_rate": 9.314592505064239e-05,
|
| 717 |
+
"loss": 0.0292,
|
| 718 |
+
"step": 830
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 1.2739336492890996,
|
| 722 |
+
"grad_norm": 0.20037536323070526,
|
| 723 |
+
"learning_rate": 9.28757877209796e-05,
|
| 724 |
+
"loss": 0.0249,
|
| 725 |
+
"step": 840
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 1.2890995260663507,
|
| 729 |
+
"grad_norm": 0.26872518658638,
|
| 730 |
+
"learning_rate": 9.260083691988084e-05,
|
| 731 |
+
"loss": 0.0257,
|
| 732 |
+
"step": 850
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 1.2890995260663507,
|
| 736 |
+
"eval_loss": 0.03507881239056587,
|
| 737 |
+
"eval_runtime": 177.211,
|
| 738 |
+
"eval_samples_per_second": 6.619,
|
| 739 |
+
"eval_steps_per_second": 6.619,
|
| 740 |
+
"step": 850
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 1.3042654028436018,
|
| 744 |
+
"grad_norm": 0.2439725548028946,
|
| 745 |
+
"learning_rate": 9.232110351483327e-05,
|
| 746 |
+
"loss": 0.0407,
|
| 747 |
+
"step": 860
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 1.3194312796208532,
|
| 751 |
+
"grad_norm": 0.5988721251487732,
|
| 752 |
+
"learning_rate": 9.203661891024547e-05,
|
| 753 |
+
"loss": 0.0349,
|
| 754 |
+
"step": 870
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 1.3345971563981043,
|
| 758 |
+
"grad_norm": 0.1617327779531479,
|
| 759 |
+
"learning_rate": 9.174741504392173e-05,
|
| 760 |
+
"loss": 0.029,
|
| 761 |
+
"step": 880
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 1.3497630331753554,
|
| 765 |
+
"grad_norm": 0.11666741967201233,
|
| 766 |
+
"learning_rate": 9.145352438347662e-05,
|
| 767 |
+
"loss": 0.0251,
|
| 768 |
+
"step": 890
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 1.3649289099526065,
|
| 772 |
+
"grad_norm": 0.12099427729845047,
|
| 773 |
+
"learning_rate": 9.115497992268995e-05,
|
| 774 |
+
"loss": 0.0218,
|
| 775 |
+
"step": 900
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 1.3649289099526065,
|
| 779 |
+
"eval_loss": 0.034569546580314636,
|
| 780 |
+
"eval_runtime": 177.2771,
|
| 781 |
+
"eval_samples_per_second": 6.617,
|
| 782 |
+
"eval_steps_per_second": 6.617,
|
| 783 |
+
"step": 900
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 1.3800947867298579,
|
| 787 |
+
"grad_norm": 0.24614952504634857,
|
| 788 |
+
"learning_rate": 9.085181517780273e-05,
|
| 789 |
+
"loss": 0.0316,
|
| 790 |
+
"step": 910
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 1.395260663507109,
|
| 794 |
+
"grad_norm": 0.2466830164194107,
|
| 795 |
+
"learning_rate": 9.054406418375443e-05,
|
| 796 |
+
"loss": 0.0406,
|
| 797 |
+
"step": 920
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 1.41042654028436,
|
| 801 |
+
"grad_norm": 0.21008533239364624,
|
| 802 |
+
"learning_rate": 9.023176149036203e-05,
|
| 803 |
+
"loss": 0.0282,
|
| 804 |
+
"step": 930
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 1.4255924170616114,
|
| 808 |
+
"grad_norm": 0.32955440878868103,
|
| 809 |
+
"learning_rate": 8.991494215844132e-05,
|
| 810 |
+
"loss": 0.0307,
|
| 811 |
+
"step": 940
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 1.4407582938388626,
|
| 815 |
+
"grad_norm": 0.2300134152173996,
|
| 816 |
+
"learning_rate": 8.959364175587069e-05,
|
| 817 |
+
"loss": 0.0266,
|
| 818 |
+
"step": 950
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 1.4407582938388626,
|
| 822 |
+
"eval_loss": 0.03766226768493652,
|
| 823 |
+
"eval_runtime": 177.2737,
|
| 824 |
+
"eval_samples_per_second": 6.617,
|
| 825 |
+
"eval_steps_per_second": 6.617,
|
| 826 |
+
"step": 950
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 1.4559241706161137,
|
| 830 |
+
"grad_norm": 0.2171100676059723,
|
| 831 |
+
"learning_rate": 8.926789635359817e-05,
|
| 832 |
+
"loss": 0.0327,
|
| 833 |
+
"step": 960
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 1.471090047393365,
|
| 837 |
+
"grad_norm": 0.2776648998260498,
|
| 838 |
+
"learning_rate": 8.893774252159187e-05,
|
| 839 |
+
"loss": 0.0272,
|
| 840 |
+
"step": 970
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 1.4862559241706161,
|
| 844 |
+
"grad_norm": 0.3400368392467499,
|
| 845 |
+
"learning_rate": 8.860321732473439e-05,
|
| 846 |
+
"loss": 0.0263,
|
| 847 |
+
"step": 980
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 1.5014218009478673,
|
| 851 |
+
"grad_norm": 0.22292691469192505,
|
| 852 |
+
"learning_rate": 8.826435831866184e-05,
|
| 853 |
+
"loss": 0.0293,
|
| 854 |
+
"step": 990
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 1.5165876777251186,
|
| 858 |
+
"grad_norm": 0.10112936049699783,
|
| 859 |
+
"learning_rate": 8.79212035455475e-05,
|
| 860 |
+
"loss": 0.0344,
|
| 861 |
+
"step": 1000
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 1.5165876777251186,
|
| 865 |
+
"eval_loss": 0.03224053233861923,
|
| 866 |
+
"eval_runtime": 177.3774,
|
| 867 |
+
"eval_samples_per_second": 6.613,
|
| 868 |
+
"eval_steps_per_second": 6.613,
|
| 869 |
+
"step": 1000
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 1.5317535545023697,
|
| 873 |
+
"grad_norm": 0.18599554896354675,
|
| 874 |
+
"learning_rate": 8.757379152983103e-05,
|
| 875 |
+
"loss": 0.0254,
|
| 876 |
+
"step": 1010
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 1.5469194312796208,
|
| 880 |
+
"grad_norm": 0.32951050996780396,
|
| 881 |
+
"learning_rate": 8.722216127389363e-05,
|
| 882 |
+
"loss": 0.0225,
|
| 883 |
+
"step": 1020
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 1.5620853080568722,
|
| 887 |
+
"grad_norm": 0.22721748054027557,
|
| 888 |
+
"learning_rate": 8.686635225367919e-05,
|
| 889 |
+
"loss": 0.0191,
|
| 890 |
+
"step": 1030
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 1.577251184834123,
|
| 894 |
+
"grad_norm": 0.30656304955482483,
|
| 895 |
+
"learning_rate": 8.650640441426274e-05,
|
| 896 |
+
"loss": 0.0393,
|
| 897 |
+
"step": 1040
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 1.5924170616113744,
|
| 901 |
+
"grad_norm": 0.07620204240083694,
|
| 902 |
+
"learning_rate": 8.614235816536582e-05,
|
| 903 |
+
"loss": 0.0244,
|
| 904 |
+
"step": 1050
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 1.5924170616113744,
|
| 908 |
+
"eval_loss": 0.03148987516760826,
|
| 909 |
+
"eval_runtime": 177.3647,
|
| 910 |
+
"eval_samples_per_second": 6.613,
|
| 911 |
+
"eval_steps_per_second": 6.613,
|
| 912 |
+
"step": 1050
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 1.6075829383886255,
|
| 916 |
+
"grad_norm": 0.1325739324092865,
|
| 917 |
+
"learning_rate": 8.577425437681994e-05,
|
| 918 |
+
"loss": 0.0298,
|
| 919 |
+
"step": 1060
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 1.6227488151658767,
|
| 923 |
+
"grad_norm": 0.2656315863132477,
|
| 924 |
+
"learning_rate": 8.540213437397833e-05,
|
| 925 |
+
"loss": 0.0319,
|
| 926 |
+
"step": 1070
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 1.637914691943128,
|
| 930 |
+
"grad_norm": 0.1368637979030609,
|
| 931 |
+
"learning_rate": 8.502603993307647e-05,
|
| 932 |
+
"loss": 0.0302,
|
| 933 |
+
"step": 1080
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 1.6530805687203791,
|
| 937 |
+
"grad_norm": 0.267149418592453,
|
| 938 |
+
"learning_rate": 8.464601327654207e-05,
|
| 939 |
+
"loss": 0.0308,
|
| 940 |
+
"step": 1090
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.6682464454976302,
|
| 944 |
+
"grad_norm": 0.09801731258630753,
|
| 945 |
+
"learning_rate": 8.4262097068255e-05,
|
| 946 |
+
"loss": 0.0227,
|
| 947 |
+
"step": 1100
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 1.6682464454976302,
|
| 951 |
+
"eval_loss": 0.03317200392484665,
|
| 952 |
+
"eval_runtime": 177.3004,
|
| 953 |
+
"eval_samples_per_second": 6.616,
|
| 954 |
+
"eval_steps_per_second": 6.616,
|
| 955 |
+
"step": 1100
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.6834123222748816,
|
| 959 |
+
"grad_norm": 0.202189639210701,
|
| 960 |
+
"learning_rate": 8.387433440875758e-05,
|
| 961 |
+
"loss": 0.0312,
|
| 962 |
+
"step": 1110
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.6985781990521327,
|
| 966 |
+
"grad_norm": 0.12905538082122803,
|
| 967 |
+
"learning_rate": 8.348276883041583e-05,
|
| 968 |
+
"loss": 0.0271,
|
| 969 |
+
"step": 1120
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.7137440758293838,
|
| 973 |
+
"grad_norm": 0.18460094928741455,
|
| 974 |
+
"learning_rate": 8.308744429253238e-05,
|
| 975 |
+
"loss": 0.0272,
|
| 976 |
+
"step": 1130
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.7289099526066352,
|
| 980 |
+
"grad_norm": 0.1906091421842575,
|
| 981 |
+
"learning_rate": 8.268840517641123e-05,
|
| 982 |
+
"loss": 0.0233,
|
| 983 |
+
"step": 1140
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.7440758293838863,
|
| 987 |
+
"grad_norm": 0.21823492646217346,
|
| 988 |
+
"learning_rate": 8.228569628037543e-05,
|
| 989 |
+
"loss": 0.0243,
|
| 990 |
+
"step": 1150
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.7440758293838863,
|
| 994 |
+
"eval_loss": 0.03176503628492355,
|
| 995 |
+
"eval_runtime": 177.2561,
|
| 996 |
+
"eval_samples_per_second": 6.618,
|
| 997 |
+
"eval_steps_per_second": 6.618,
|
| 998 |
+
"step": 1150
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 1.7592417061611374,
|
| 1002 |
+
"grad_norm": 0.22984248399734497,
|
| 1003 |
+
"learning_rate": 8.187936281473758e-05,
|
| 1004 |
+
"loss": 0.0318,
|
| 1005 |
+
"step": 1160
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 1.7744075829383887,
|
| 1009 |
+
"grad_norm": 0.1078776940703392,
|
| 1010 |
+
"learning_rate": 8.146945039672446e-05,
|
| 1011 |
+
"loss": 0.0264,
|
| 1012 |
+
"step": 1170
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 1.7895734597156399,
|
| 1016 |
+
"grad_norm": 0.14255861937999725,
|
| 1017 |
+
"learning_rate": 8.105600504535567e-05,
|
| 1018 |
+
"loss": 0.02,
|
| 1019 |
+
"step": 1180
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 1.804739336492891,
|
| 1023 |
+
"grad_norm": 0.19624319672584534,
|
| 1024 |
+
"learning_rate": 8.06390731762773e-05,
|
| 1025 |
+
"loss": 0.0362,
|
| 1026 |
+
"step": 1190
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 1.8199052132701423,
|
| 1030 |
+
"grad_norm": 0.2134467512369156,
|
| 1031 |
+
"learning_rate": 8.021870159655109e-05,
|
| 1032 |
+
"loss": 0.03,
|
| 1033 |
+
"step": 1200
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 1.8199052132701423,
|
| 1037 |
+
"eval_loss": 0.031138954684138298,
|
| 1038 |
+
"eval_runtime": 177.2477,
|
| 1039 |
+
"eval_samples_per_second": 6.618,
|
| 1040 |
+
"eval_steps_per_second": 6.618,
|
| 1041 |
+
"step": 1200
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 1.8350710900473932,
|
| 1045 |
+
"grad_norm": 0.2627793252468109,
|
| 1046 |
+
"learning_rate": 7.979493749939955e-05,
|
| 1047 |
+
"loss": 0.0242,
|
| 1048 |
+
"step": 1210
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 1.8502369668246446,
|
| 1052 |
+
"grad_norm": 0.16796381771564484,
|
| 1053 |
+
"learning_rate": 7.93678284589079e-05,
|
| 1054 |
+
"loss": 0.0242,
|
| 1055 |
+
"step": 1220
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 1.865402843601896,
|
| 1059 |
+
"grad_norm": 0.23527124524116516,
|
| 1060 |
+
"learning_rate": 7.893742242468301e-05,
|
| 1061 |
+
"loss": 0.0262,
|
| 1062 |
+
"step": 1230
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 1.8805687203791468,
|
| 1066 |
+
"grad_norm": 0.27677977085113525,
|
| 1067 |
+
"learning_rate": 7.850376771647038e-05,
|
| 1068 |
+
"loss": 0.0366,
|
| 1069 |
+
"step": 1240
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 1.8957345971563981,
|
| 1073 |
+
"grad_norm": 0.2223452478647232,
|
| 1074 |
+
"learning_rate": 7.806691301872958e-05,
|
| 1075 |
+
"loss": 0.0307,
|
| 1076 |
+
"step": 1250
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 1.8957345971563981,
|
| 1080 |
+
"eval_loss": 0.029545707628130913,
|
| 1081 |
+
"eval_runtime": 177.2472,
|
| 1082 |
+
"eval_samples_per_second": 6.618,
|
| 1083 |
+
"eval_steps_per_second": 6.618,
|
| 1084 |
+
"step": 1250
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 1.9109004739336493,
|
| 1088 |
+
"grad_norm": 0.12168317288160324,
|
| 1089 |
+
"learning_rate": 7.762690737516846e-05,
|
| 1090 |
+
"loss": 0.0328,
|
| 1091 |
+
"step": 1260
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 1.9260663507109004,
|
| 1095 |
+
"grad_norm": 0.44124069809913635,
|
| 1096 |
+
"learning_rate": 7.718380018323742e-05,
|
| 1097 |
+
"loss": 0.0373,
|
| 1098 |
+
"step": 1270
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 1.9412322274881517,
|
| 1102 |
+
"grad_norm": 0.1568044126033783,
|
| 1103 |
+
"learning_rate": 7.673764118858371e-05,
|
| 1104 |
+
"loss": 0.0218,
|
| 1105 |
+
"step": 1280
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 1.9563981042654028,
|
| 1109 |
+
"grad_norm": 0.3564736545085907,
|
| 1110 |
+
"learning_rate": 7.628848047946675e-05,
|
| 1111 |
+
"loss": 0.0376,
|
| 1112 |
+
"step": 1290
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 1.971563981042654,
|
| 1116 |
+
"grad_norm": 0.3387766480445862,
|
| 1117 |
+
"learning_rate": 7.583636848113483e-05,
|
| 1118 |
+
"loss": 0.0344,
|
| 1119 |
+
"step": 1300
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 1.971563981042654,
|
| 1123 |
+
"eval_loss": 0.030506150797009468,
|
| 1124 |
+
"eval_runtime": 177.2118,
|
| 1125 |
+
"eval_samples_per_second": 6.619,
|
| 1126 |
+
"eval_steps_per_second": 6.619,
|
| 1127 |
+
"step": 1300
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 1.9867298578199053,
|
| 1131 |
+
"grad_norm": 0.24238063395023346,
|
| 1132 |
+
"learning_rate": 7.538135595016423e-05,
|
| 1133 |
+
"loss": 0.03,
|
| 1134 |
+
"step": 1310
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 2.001895734597156,
|
| 1138 |
+
"grad_norm": 0.11398116499185562,
|
| 1139 |
+
"learning_rate": 7.492349396876096e-05,
|
| 1140 |
+
"loss": 0.0356,
|
| 1141 |
+
"step": 1320
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 2.0170616113744075,
|
| 1145 |
+
"grad_norm": 0.08749754726886749,
|
| 1146 |
+
"learning_rate": 7.4462833939026e-05,
|
| 1147 |
+
"loss": 0.0198,
|
| 1148 |
+
"step": 1330
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 2.032227488151659,
|
| 1152 |
+
"grad_norm": 0.06967737525701523,
|
| 1153 |
+
"learning_rate": 7.399942757718455e-05,
|
| 1154 |
+
"loss": 0.0196,
|
| 1155 |
+
"step": 1340
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 2.0473933649289098,
|
| 1159 |
+
"grad_norm": 0.08232049643993378,
|
| 1160 |
+
"learning_rate": 7.35333269077802e-05,
|
| 1161 |
+
"loss": 0.0214,
|
| 1162 |
+
"step": 1350
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 2.0473933649289098,
|
| 1166 |
+
"eval_loss": 0.030749354511499405,
|
| 1167 |
+
"eval_runtime": 176.5322,
|
| 1168 |
+
"eval_samples_per_second": 6.645,
|
| 1169 |
+
"eval_steps_per_second": 6.645,
|
| 1170 |
+
"step": 1350
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 2.062559241706161,
|
| 1174 |
+
"grad_norm": 0.18698251247406006,
|
| 1175 |
+
"learning_rate": 7.306458425783426e-05,
|
| 1176 |
+
"loss": 0.0174,
|
| 1177 |
+
"step": 1360
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 2.0777251184834125,
|
| 1181 |
+
"grad_norm": 0.16593368351459503,
|
| 1182 |
+
"learning_rate": 7.25932522509713e-05,
|
| 1183 |
+
"loss": 0.0177,
|
| 1184 |
+
"step": 1370
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 2.0928909952606634,
|
| 1188 |
+
"grad_norm": 0.23132416605949402,
|
| 1189 |
+
"learning_rate": 7.211938380151133e-05,
|
| 1190 |
+
"loss": 0.0144,
|
| 1191 |
+
"step": 1380
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 2.1080568720379147,
|
| 1195 |
+
"grad_norm": 0.1467525064945221,
|
| 1196 |
+
"learning_rate": 7.164303210852934e-05,
|
| 1197 |
+
"loss": 0.0227,
|
| 1198 |
+
"step": 1390
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 2.123222748815166,
|
| 1202 |
+
"grad_norm": 0.19721190631389618,
|
| 1203 |
+
"learning_rate": 7.116425064988286e-05,
|
| 1204 |
+
"loss": 0.0178,
|
| 1205 |
+
"step": 1400
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 2.123222748815166,
|
| 1209 |
+
"eval_loss": 0.031973257660865784,
|
| 1210 |
+
"eval_runtime": 176.3775,
|
| 1211 |
+
"eval_samples_per_second": 6.651,
|
| 1212 |
+
"eval_steps_per_second": 6.651,
|
| 1213 |
+
"step": 1400
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 2.138388625592417,
|
| 1217 |
+
"grad_norm": 0.21327702701091766,
|
| 1218 |
+
"learning_rate": 7.068309317620827e-05,
|
| 1219 |
+
"loss": 0.0186,
|
| 1220 |
+
"step": 1410
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 2.1535545023696683,
|
| 1224 |
+
"grad_norm": 0.19219304621219635,
|
| 1225 |
+
"learning_rate": 7.019961370488645e-05,
|
| 1226 |
+
"loss": 0.0174,
|
| 1227 |
+
"step": 1420
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 2.1687203791469196,
|
| 1231 |
+
"grad_norm": 0.218804731965065,
|
| 1232 |
+
"learning_rate": 6.971386651397849e-05,
|
| 1233 |
+
"loss": 0.0189,
|
| 1234 |
+
"step": 1430
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 2.1838862559241705,
|
| 1238 |
+
"grad_norm": 0.4009787142276764,
|
| 1239 |
+
"learning_rate": 6.922590613613211e-05,
|
| 1240 |
+
"loss": 0.0178,
|
| 1241 |
+
"step": 1440
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 2.199052132701422,
|
| 1245 |
+
"grad_norm": 0.060959890484809875,
|
| 1246 |
+
"learning_rate": 6.873578735245961e-05,
|
| 1247 |
+
"loss": 0.0167,
|
| 1248 |
+
"step": 1450
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 2.199052132701422,
|
| 1252 |
+
"eval_loss": 0.03211337700486183,
|
| 1253 |
+
"eval_runtime": 176.3627,
|
| 1254 |
+
"eval_samples_per_second": 6.651,
|
| 1255 |
+
"eval_steps_per_second": 6.651,
|
| 1256 |
+
"step": 1450
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 2.2142180094786728,
|
| 1260 |
+
"grad_norm": 0.1430092453956604,
|
| 1261 |
+
"learning_rate": 6.824356518638775e-05,
|
| 1262 |
+
"loss": 0.017,
|
| 1263 |
+
"step": 1460
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 2.229383886255924,
|
| 1267 |
+
"grad_norm": 0.18788497149944305,
|
| 1268 |
+
"learning_rate": 6.774929489748052e-05,
|
| 1269 |
+
"loss": 0.0229,
|
| 1270 |
+
"step": 1470
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 2.2445497630331754,
|
| 1274 |
+
"grad_norm": 0.1279352605342865,
|
| 1275 |
+
"learning_rate": 6.725303197523548e-05,
|
| 1276 |
+
"loss": 0.0195,
|
| 1277 |
+
"step": 1480
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 2.259715639810427,
|
| 1281 |
+
"grad_norm": 0.22916962206363678,
|
| 1282 |
+
"learning_rate": 6.675483213285412e-05,
|
| 1283 |
+
"loss": 0.0194,
|
| 1284 |
+
"step": 1490
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 2.2748815165876777,
|
| 1288 |
+
"grad_norm": 0.11649148911237717,
|
| 1289 |
+
"learning_rate": 6.625475130098728e-05,
|
| 1290 |
+
"loss": 0.0115,
|
| 1291 |
+
"step": 1500
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 2.2748815165876777,
|
| 1295 |
+
"eval_loss": 0.032478559762239456,
|
| 1296 |
+
"eval_runtime": 176.381,
|
| 1297 |
+
"eval_samples_per_second": 6.65,
|
| 1298 |
+
"eval_steps_per_second": 6.65,
|
| 1299 |
+
"step": 1500
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 2.290047393364929,
|
| 1303 |
+
"grad_norm": 0.12490870803594589,
|
| 1304 |
+
"learning_rate": 6.575284562145593e-05,
|
| 1305 |
+
"loss": 0.0246,
|
| 1306 |
+
"step": 1510
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 2.30521327014218,
|
| 1310 |
+
"grad_norm": 0.3091743290424347,
|
| 1311 |
+
"learning_rate": 6.524917144094851e-05,
|
| 1312 |
+
"loss": 0.0168,
|
| 1313 |
+
"step": 1520
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 2.3203791469194313,
|
| 1317 |
+
"grad_norm": 0.18049876391887665,
|
| 1318 |
+
"learning_rate": 6.474378530469509e-05,
|
| 1319 |
+
"loss": 0.0238,
|
| 1320 |
+
"step": 1530
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 2.3355450236966826,
|
| 1324 |
+
"grad_norm": 0.08443621546030045,
|
| 1325 |
+
"learning_rate": 6.42367439501193e-05,
|
| 1326 |
+
"loss": 0.0169,
|
| 1327 |
+
"step": 1540
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 2.3507109004739335,
|
| 1331 |
+
"grad_norm": 0.2367069274187088,
|
| 1332 |
+
"learning_rate": 6.372810430046862e-05,
|
| 1333 |
+
"loss": 0.0192,
|
| 1334 |
+
"step": 1550
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 2.3507109004739335,
|
| 1338 |
+
"eval_loss": 0.03184814006090164,
|
| 1339 |
+
"eval_runtime": 176.4492,
|
| 1340 |
+
"eval_samples_per_second": 6.648,
|
| 1341 |
+
"eval_steps_per_second": 6.648,
|
| 1342 |
+
"step": 1550
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 2.365876777251185,
|
| 1346 |
+
"grad_norm": 0.1728668063879013,
|
| 1347 |
+
"learning_rate": 6.321792345842402e-05,
|
| 1348 |
+
"loss": 0.0151,
|
| 1349 |
+
"step": 1560
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 2.381042654028436,
|
| 1353 |
+
"grad_norm": 0.3039005994796753,
|
| 1354 |
+
"learning_rate": 6.270625869968906e-05,
|
| 1355 |
+
"loss": 0.0154,
|
| 1356 |
+
"step": 1570
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 2.396208530805687,
|
| 1360 |
+
"grad_norm": 0.16306930780410767,
|
| 1361 |
+
"learning_rate": 6.219316746656007e-05,
|
| 1362 |
+
"loss": 0.0175,
|
| 1363 |
+
"step": 1580
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 2.4113744075829384,
|
| 1367 |
+
"grad_norm": 0.09183406829833984,
|
| 1368 |
+
"learning_rate": 6.167870736147713e-05,
|
| 1369 |
+
"loss": 0.0218,
|
| 1370 |
+
"step": 1590
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 2.4265402843601898,
|
| 1374 |
+
"grad_norm": 0.3515900671482086,
|
| 1375 |
+
"learning_rate": 6.116293614055744e-05,
|
| 1376 |
+
"loss": 0.0233,
|
| 1377 |
+
"step": 1600
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 2.4265402843601898,
|
| 1381 |
+
"eval_loss": 0.032726142555475235,
|
| 1382 |
+
"eval_runtime": 176.5984,
|
| 1383 |
+
"eval_samples_per_second": 6.642,
|
| 1384 |
+
"eval_steps_per_second": 6.642,
|
| 1385 |
+
"step": 1600
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 2.4417061611374407,
|
| 1389 |
+
"grad_norm": 0.1969446986913681,
|
| 1390 |
+
"learning_rate": 6.06459117071113e-05,
|
| 1391 |
+
"loss": 0.0163,
|
| 1392 |
+
"step": 1610
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 2.456872037914692,
|
| 1396 |
+
"grad_norm": 0.10922811925411224,
|
| 1397 |
+
"learning_rate": 6.012769210514146e-05,
|
| 1398 |
+
"loss": 0.0209,
|
| 1399 |
+
"step": 1620
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 2.472037914691943,
|
| 1403 |
+
"grad_norm": 0.13068976998329163,
|
| 1404 |
+
"learning_rate": 5.9608335512826915e-05,
|
| 1405 |
+
"loss": 0.0153,
|
| 1406 |
+
"step": 1630
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 2.4872037914691942,
|
| 1410 |
+
"grad_norm": 0.1942068338394165,
|
| 1411 |
+
"learning_rate": 5.908790023599144e-05,
|
| 1412 |
+
"loss": 0.0186,
|
| 1413 |
+
"step": 1640
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 2.5023696682464456,
|
| 1417 |
+
"grad_norm": 0.20405402779579163,
|
| 1418 |
+
"learning_rate": 5.856644470155781e-05,
|
| 1419 |
+
"loss": 0.0108,
|
| 1420 |
+
"step": 1650
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 2.5023696682464456,
|
| 1424 |
+
"eval_loss": 0.03395625576376915,
|
| 1425 |
+
"eval_runtime": 176.6011,
|
| 1426 |
+
"eval_samples_per_second": 6.642,
|
| 1427 |
+
"eval_steps_per_second": 6.642,
|
| 1428 |
+
"step": 1650
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 2.517535545023697,
|
| 1432 |
+
"grad_norm": 0.1378117799758911,
|
| 1433 |
+
"learning_rate": 5.8044027450988546e-05,
|
| 1434 |
+
"loss": 0.0224,
|
| 1435 |
+
"step": 1660
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 2.532701421800948,
|
| 1439 |
+
"grad_norm": 0.4658917486667633,
|
| 1440 |
+
"learning_rate": 5.752070713371371e-05,
|
| 1441 |
+
"loss": 0.0156,
|
| 1442 |
+
"step": 1670
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 2.547867298578199,
|
| 1446 |
+
"grad_norm": 0.21184688806533813,
|
| 1447 |
+
"learning_rate": 5.699654250054662e-05,
|
| 1448 |
+
"loss": 0.0276,
|
| 1449 |
+
"step": 1680
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 2.56303317535545,
|
| 1453 |
+
"grad_norm": 0.3075418174266815,
|
| 1454 |
+
"learning_rate": 5.647159239708809e-05,
|
| 1455 |
+
"loss": 0.0264,
|
| 1456 |
+
"step": 1690
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 2.5781990521327014,
|
| 1460 |
+
"grad_norm": 0.24572160840034485,
|
| 1461 |
+
"learning_rate": 5.5945915757120146e-05,
|
| 1462 |
+
"loss": 0.0256,
|
| 1463 |
+
"step": 1700
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 2.5781990521327014,
|
| 1467 |
+
"eval_loss": 0.0314929336309433,
|
| 1468 |
+
"eval_runtime": 176.6685,
|
| 1469 |
+
"eval_samples_per_second": 6.64,
|
| 1470 |
+
"eval_steps_per_second": 6.64,
|
| 1471 |
+
"step": 1700
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 2.5933649289099527,
|
| 1475 |
+
"grad_norm": 0.30421316623687744,
|
| 1476 |
+
"learning_rate": 5.5419571595989825e-05,
|
| 1477 |
+
"loss": 0.0266,
|
| 1478 |
+
"step": 1710
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 2.6085308056872036,
|
| 1482 |
+
"grad_norm": 0.1892070770263672,
|
| 1483 |
+
"learning_rate": 5.4892619003983734e-05,
|
| 1484 |
+
"loss": 0.0177,
|
| 1485 |
+
"step": 1720
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 2.623696682464455,
|
| 1489 |
+
"grad_norm": 0.23157517611980438,
|
| 1490 |
+
"learning_rate": 5.436511713969428e-05,
|
| 1491 |
+
"loss": 0.0199,
|
| 1492 |
+
"step": 1730
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 2.6388625592417063,
|
| 1496 |
+
"grad_norm": 0.18666303157806396,
|
| 1497 |
+
"learning_rate": 5.383712522337817e-05,
|
| 1498 |
+
"loss": 0.0221,
|
| 1499 |
+
"step": 1740
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 2.654028436018957,
|
| 1503 |
+
"grad_norm": 0.0699646845459938,
|
| 1504 |
+
"learning_rate": 5.3308702530308076e-05,
|
| 1505 |
+
"loss": 0.019,
|
| 1506 |
+
"step": 1750
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 2.654028436018957,
|
| 1510 |
+
"eval_loss": 0.030023746192455292,
|
| 1511 |
+
"eval_runtime": 176.6593,
|
| 1512 |
+
"eval_samples_per_second": 6.64,
|
| 1513 |
+
"eval_steps_per_second": 6.64,
|
| 1514 |
+
"step": 1750
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 2.6691943127962086,
|
| 1518 |
+
"grad_norm": 0.16548389196395874,
|
| 1519 |
+
"learning_rate": 5.2779908384118025e-05,
|
| 1520 |
+
"loss": 0.0166,
|
| 1521 |
+
"step": 1760
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 2.68436018957346,
|
| 1525 |
+
"grad_norm": 0.20772500336170197,
|
| 1526 |
+
"learning_rate": 5.22508021501434e-05,
|
| 1527 |
+
"loss": 0.0155,
|
| 1528 |
+
"step": 1770
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 2.699526066350711,
|
| 1532 |
+
"grad_norm": 0.22350798547267914,
|
| 1533 |
+
"learning_rate": 5.1721443228756284e-05,
|
| 1534 |
+
"loss": 0.0152,
|
| 1535 |
+
"step": 1780
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 2.714691943127962,
|
| 1539 |
+
"grad_norm": 0.10424303263425827,
|
| 1540 |
+
"learning_rate": 5.119189104869683e-05,
|
| 1541 |
+
"loss": 0.0248,
|
| 1542 |
+
"step": 1790
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 2.729857819905213,
|
| 1546 |
+
"grad_norm": 0.4774502217769623,
|
| 1547 |
+
"learning_rate": 5.066220506040148e-05,
|
| 1548 |
+
"loss": 0.0205,
|
| 1549 |
+
"step": 1800
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 2.729857819905213,
|
| 1553 |
+
"eval_loss": 0.030218223109841347,
|
| 1554 |
+
"eval_runtime": 176.6117,
|
| 1555 |
+
"eval_samples_per_second": 6.642,
|
| 1556 |
+
"eval_steps_per_second": 6.642,
|
| 1557 |
+
"step": 1800
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 2.7450236966824644,
|
| 1561 |
+
"grad_norm": 0.13609637320041656,
|
| 1562 |
+
"learning_rate": 5.013244472932872e-05,
|
| 1563 |
+
"loss": 0.0199,
|
| 1564 |
+
"step": 1810
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 2.7601895734597157,
|
| 1568 |
+
"grad_norm": 0.19494231045246124,
|
| 1569 |
+
"learning_rate": 4.960266952928316e-05,
|
| 1570 |
+
"loss": 0.0203,
|
| 1571 |
+
"step": 1820
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 2.775355450236967,
|
| 1575 |
+
"grad_norm": 0.27867355942726135,
|
| 1576 |
+
"learning_rate": 4.907293893573867e-05,
|
| 1577 |
+
"loss": 0.0179,
|
| 1578 |
+
"step": 1830
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 2.790521327014218,
|
| 1582 |
+
"grad_norm": 0.18963003158569336,
|
| 1583 |
+
"learning_rate": 4.8543312419161396e-05,
|
| 1584 |
+
"loss": 0.0104,
|
| 1585 |
+
"step": 1840
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 2.8056872037914693,
|
| 1589 |
+
"grad_norm": 0.33311042189598083,
|
| 1590 |
+
"learning_rate": 4.8013849438333165e-05,
|
| 1591 |
+
"loss": 0.0197,
|
| 1592 |
+
"step": 1850
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 2.8056872037914693,
|
| 1596 |
+
"eval_loss": 0.030651915818452835,
|
| 1597 |
+
"eval_runtime": 176.8032,
|
| 1598 |
+
"eval_samples_per_second": 6.634,
|
| 1599 |
+
"eval_steps_per_second": 6.634,
|
| 1600 |
+
"step": 1850
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 2.82085308056872,
|
| 1604 |
+
"grad_norm": 0.2615697383880615,
|
| 1605 |
+
"learning_rate": 4.748460943367643e-05,
|
| 1606 |
+
"loss": 0.0203,
|
| 1607 |
+
"step": 1860
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 2.8360189573459715,
|
| 1611 |
+
"grad_norm": 0.19395503401756287,
|
| 1612 |
+
"learning_rate": 4.695565182058113e-05,
|
| 1613 |
+
"loss": 0.0146,
|
| 1614 |
+
"step": 1870
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 2.851184834123223,
|
| 1618 |
+
"grad_norm": 0.11207451671361923,
|
| 1619 |
+
"learning_rate": 4.642703598273431e-05,
|
| 1620 |
+
"loss": 0.0137,
|
| 1621 |
+
"step": 1880
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 2.8663507109004738,
|
| 1625 |
+
"grad_norm": 0.2404172271490097,
|
| 1626 |
+
"learning_rate": 4.589882126545352e-05,
|
| 1627 |
+
"loss": 0.0158,
|
| 1628 |
+
"step": 1890
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 2.881516587677725,
|
| 1632 |
+
"grad_norm": 0.11668932437896729,
|
| 1633 |
+
"learning_rate": 4.537106696902425e-05,
|
| 1634 |
+
"loss": 0.0161,
|
| 1635 |
+
"step": 1900
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 2.881516587677725,
|
| 1639 |
+
"eval_loss": 0.030294641852378845,
|
| 1640 |
+
"eval_runtime": 176.8559,
|
| 1641 |
+
"eval_samples_per_second": 6.633,
|
| 1642 |
+
"eval_steps_per_second": 6.633,
|
| 1643 |
+
"step": 1900
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 2.8966824644549765,
|
| 1647 |
+
"grad_norm": 0.12421189993619919,
|
| 1648 |
+
"learning_rate": 4.484383234204266e-05,
|
| 1649 |
+
"loss": 0.0166,
|
| 1650 |
+
"step": 1910
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 2.9118483412322274,
|
| 1654 |
+
"grad_norm": 0.1858258843421936,
|
| 1655 |
+
"learning_rate": 4.4317176574763935e-05,
|
| 1656 |
+
"loss": 0.0205,
|
| 1657 |
+
"step": 1920
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 2.9270142180094787,
|
| 1661 |
+
"grad_norm": 0.07033693790435791,
|
| 1662 |
+
"learning_rate": 4.3791158792457334e-05,
|
| 1663 |
+
"loss": 0.0164,
|
| 1664 |
+
"step": 1930
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 2.94218009478673,
|
| 1668 |
+
"grad_norm": 0.5009151697158813,
|
| 1669 |
+
"learning_rate": 4.3265838048768334e-05,
|
| 1670 |
+
"loss": 0.0278,
|
| 1671 |
+
"step": 1940
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 2.957345971563981,
|
| 1675 |
+
"grad_norm": 0.2717853784561157,
|
| 1676 |
+
"learning_rate": 4.274127331908915e-05,
|
| 1677 |
+
"loss": 0.0235,
|
| 1678 |
+
"step": 1950
|
| 1679 |
+
},
|
| 1680 |
+
{
|
| 1681 |
+
"epoch": 2.957345971563981,
|
| 1682 |
+
"eval_loss": 0.030197137966752052,
|
| 1683 |
+
"eval_runtime": 176.9858,
|
| 1684 |
+
"eval_samples_per_second": 6.628,
|
| 1685 |
+
"eval_steps_per_second": 6.628,
|
| 1686 |
+
"step": 1950
|
| 1687 |
+
},
|
| 1688 |
+
{
|
| 1689 |
+
"epoch": 2.9725118483412323,
|
| 1690 |
+
"grad_norm": 0.16889254748821259,
|
| 1691 |
+
"learning_rate": 4.221752349393758e-05,
|
| 1692 |
+
"loss": 0.0221,
|
| 1693 |
+
"step": 1960
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 2.987677725118483,
|
| 1697 |
+
"grad_norm": 0.39976805448532104,
|
| 1698 |
+
"learning_rate": 4.1694647372345886e-05,
|
| 1699 |
+
"loss": 0.026,
|
| 1700 |
+
"step": 1970
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 3.0028436018957345,
|
| 1704 |
+
"grad_norm": 0.08540892601013184,
|
| 1705 |
+
"learning_rate": 4.117270365525946e-05,
|
| 1706 |
+
"loss": 0.0212,
|
| 1707 |
+
"step": 1980
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 3.018009478672986,
|
| 1711 |
+
"grad_norm": 0.22224882245063782,
|
| 1712 |
+
"learning_rate": 4.065175093894694e-05,
|
| 1713 |
+
"loss": 0.0144,
|
| 1714 |
+
"step": 1990
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 3.0331753554502368,
|
| 1718 |
+
"grad_norm": 0.14129629731178284,
|
| 1719 |
+
"learning_rate": 4.013184770842167e-05,
|
| 1720 |
+
"loss": 0.01,
|
| 1721 |
+
"step": 2000
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 3.0331753554502368,
|
| 1725 |
+
"eval_loss": 0.03006371296942234,
|
| 1726 |
+
"eval_runtime": 176.7015,
|
| 1727 |
+
"eval_samples_per_second": 6.638,
|
| 1728 |
+
"eval_steps_per_second": 6.638,
|
| 1729 |
+
"step": 2000
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 3.048341232227488,
|
| 1733 |
+
"grad_norm": 0.14608627557754517,
|
| 1734 |
+
"learning_rate": 3.9613052330876064e-05,
|
| 1735 |
+
"loss": 0.0149,
|
| 1736 |
+
"step": 2010
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 3.0635071090047394,
|
| 1740 |
+
"grad_norm": 0.04342254251241684,
|
| 1741 |
+
"learning_rate": 3.909542304912881e-05,
|
| 1742 |
+
"loss": 0.0124,
|
| 1743 |
+
"step": 2020
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 3.0786729857819903,
|
| 1747 |
+
"grad_norm": 0.14242447912693024,
|
| 1748 |
+
"learning_rate": 3.857901797508628e-05,
|
| 1749 |
+
"loss": 0.0102,
|
| 1750 |
+
"step": 2030
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 3.0938388625592417,
|
| 1754 |
+
"grad_norm": 0.22291754186153412,
|
| 1755 |
+
"learning_rate": 3.80638950832186e-05,
|
| 1756 |
+
"loss": 0.0128,
|
| 1757 |
+
"step": 2040
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 3.109004739336493,
|
| 1761 |
+
"grad_norm": 0.15756551921367645,
|
| 1762 |
+
"learning_rate": 3.7550112204051014e-05,
|
| 1763 |
+
"loss": 0.0073,
|
| 1764 |
+
"step": 2050
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 3.109004739336493,
|
| 1768 |
+
"eval_loss": 0.03245367109775543,
|
| 1769 |
+
"eval_runtime": 176.6878,
|
| 1770 |
+
"eval_samples_per_second": 6.639,
|
| 1771 |
+
"eval_steps_per_second": 6.639,
|
| 1772 |
+
"step": 2050
|
| 1773 |
+
},
|
| 1774 |
+
{
|
| 1775 |
+
"epoch": 3.124170616113744,
|
| 1776 |
+
"grad_norm": 0.13003289699554443,
|
| 1777 |
+
"learning_rate": 3.703772701767167e-05,
|
| 1778 |
+
"loss": 0.0132,
|
| 1779 |
+
"step": 2060
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 3.1393364928909953,
|
| 1783 |
+
"grad_norm": 0.1293676346540451,
|
| 1784 |
+
"learning_rate": 3.652679704725596e-05,
|
| 1785 |
+
"loss": 0.0066,
|
| 1786 |
+
"step": 2070
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 3.1545023696682466,
|
| 1790 |
+
"grad_norm": 0.1557125747203827,
|
| 1791 |
+
"learning_rate": 3.601737965260882e-05,
|
| 1792 |
+
"loss": 0.0144,
|
| 1793 |
+
"step": 2080
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 3.1696682464454975,
|
| 1797 |
+
"grad_norm": 0.3026883900165558,
|
| 1798 |
+
"learning_rate": 3.550953202372503e-05,
|
| 1799 |
+
"loss": 0.011,
|
| 1800 |
+
"step": 2090
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"epoch": 3.184834123222749,
|
| 1804 |
+
"grad_norm": 0.15523476898670197,
|
| 1805 |
+
"learning_rate": 3.500331117436895e-05,
|
| 1806 |
+
"loss": 0.0099,
|
| 1807 |
+
"step": 2100
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 3.184834123222749,
|
| 1811 |
+
"eval_loss": 0.03371278569102287,
|
| 1812 |
+
"eval_runtime": 176.9028,
|
| 1813 |
+
"eval_samples_per_second": 6.631,
|
| 1814 |
+
"eval_steps_per_second": 6.631,
|
| 1815 |
+
"step": 2100
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 3.2,
|
| 1819 |
+
"grad_norm": 0.21841643750667572,
|
| 1820 |
+
"learning_rate": 3.4498773935673626e-05,
|
| 1821 |
+
"loss": 0.0118,
|
| 1822 |
+
"step": 2110
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 3.215165876777251,
|
| 1826 |
+
"grad_norm": 0.8701363205909729,
|
| 1827 |
+
"learning_rate": 3.399597694976081e-05,
|
| 1828 |
+
"loss": 0.0115,
|
| 1829 |
+
"step": 2120
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 3.2303317535545024,
|
| 1833 |
+
"grad_norm": 0.16382525861263275,
|
| 1834 |
+
"learning_rate": 3.349497666338187e-05,
|
| 1835 |
+
"loss": 0.0102,
|
| 1836 |
+
"step": 2130
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 3.2454976303317538,
|
| 1840 |
+
"grad_norm": 0.17109428346157074,
|
| 1841 |
+
"learning_rate": 3.299582932158085e-05,
|
| 1842 |
+
"loss": 0.0092,
|
| 1843 |
+
"step": 2140
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 3.2606635071090047,
|
| 1847 |
+
"grad_norm": 0.07784170657396317,
|
| 1848 |
+
"learning_rate": 3.2498590961379996e-05,
|
| 1849 |
+
"loss": 0.0085,
|
| 1850 |
+
"step": 2150
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 3.2606635071090047,
|
| 1854 |
+
"eval_loss": 0.033658258616924286,
|
| 1855 |
+
"eval_runtime": 176.8981,
|
| 1856 |
+
"eval_samples_per_second": 6.631,
|
| 1857 |
+
"eval_steps_per_second": 6.631,
|
| 1858 |
+
"step": 2150
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 3.275829383886256,
|
| 1862 |
+
"grad_norm": 0.23731419444084167,
|
| 1863 |
+
"learning_rate": 3.200331740548887e-05,
|
| 1864 |
+
"loss": 0.0094,
|
| 1865 |
+
"step": 2160
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 3.2909952606635073,
|
| 1869 |
+
"grad_norm": 0.17054717242717743,
|
| 1870 |
+
"learning_rate": 3.1510064256037274e-05,
|
| 1871 |
+
"loss": 0.009,
|
| 1872 |
+
"step": 2170
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 3.3061611374407582,
|
| 1876 |
+
"grad_norm": 0.4204874634742737,
|
| 1877 |
+
"learning_rate": 3.1018886888333065e-05,
|
| 1878 |
+
"loss": 0.0082,
|
| 1879 |
+
"step": 2180
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 3.3213270142180096,
|
| 1883 |
+
"grad_norm": 0.3489740490913391,
|
| 1884 |
+
"learning_rate": 3.052984044464548e-05,
|
| 1885 |
+
"loss": 0.0139,
|
| 1886 |
+
"step": 2190
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 3.3364928909952605,
|
| 1890 |
+
"grad_norm": 0.22664600610733032,
|
| 1891 |
+
"learning_rate": 3.0042979828014496e-05,
|
| 1892 |
+
"loss": 0.0076,
|
| 1893 |
+
"step": 2200
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 3.3364928909952605,
|
| 1897 |
+
"eval_loss": 0.035356372594833374,
|
| 1898 |
+
"eval_runtime": 176.9834,
|
| 1899 |
+
"eval_samples_per_second": 6.628,
|
| 1900 |
+
"eval_steps_per_second": 6.628,
|
| 1901 |
+
"step": 2200
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"epoch": 3.351658767772512,
|
| 1905 |
+
"grad_norm": 0.23908552527427673,
|
| 1906 |
+
"learning_rate": 2.9558359696087152e-05,
|
| 1907 |
+
"loss": 0.0096,
|
| 1908 |
+
"step": 2210
|
| 1909 |
+
},
|
| 1910 |
+
{
|
| 1911 |
+
"epoch": 3.366824644549763,
|
| 1912 |
+
"grad_norm": 0.3297005295753479,
|
| 1913 |
+
"learning_rate": 2.9076034454981332e-05,
|
| 1914 |
+
"loss": 0.0097,
|
| 1915 |
+
"step": 2220
|
| 1916 |
+
},
|
| 1917 |
+
{
|
| 1918 |
+
"epoch": 3.381990521327014,
|
| 1919 |
+
"grad_norm": 0.1065937951207161,
|
| 1920 |
+
"learning_rate": 2.8596058253177932e-05,
|
| 1921 |
+
"loss": 0.0127,
|
| 1922 |
+
"step": 2230
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 3.3971563981042654,
|
| 1926 |
+
"grad_norm": 0.4293796122074127,
|
| 1927 |
+
"learning_rate": 2.811848497544175e-05,
|
| 1928 |
+
"loss": 0.0139,
|
| 1929 |
+
"step": 2240
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 3.4123222748815167,
|
| 1933 |
+
"grad_norm": 0.05868324264883995,
|
| 1934 |
+
"learning_rate": 2.764336823677216e-05,
|
| 1935 |
+
"loss": 0.0077,
|
| 1936 |
+
"step": 2250
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 3.4123222748815167,
|
| 1940 |
+
"eval_loss": 0.03412007540464401,
|
| 1941 |
+
"eval_runtime": 177.0155,
|
| 1942 |
+
"eval_samples_per_second": 6.627,
|
| 1943 |
+
"eval_steps_per_second": 6.627,
|
| 1944 |
+
"step": 2250
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"epoch": 3.4274881516587676,
|
| 1948 |
+
"grad_norm": 0.3067063093185425,
|
| 1949 |
+
"learning_rate": 2.717076137638388e-05,
|
| 1950 |
+
"loss": 0.0095,
|
| 1951 |
+
"step": 2260
|
| 1952 |
+
},
|
| 1953 |
+
{
|
| 1954 |
+
"epoch": 3.442654028436019,
|
| 1955 |
+
"grad_norm": 0.25318676233291626,
|
| 1956 |
+
"learning_rate": 2.6700717451719066e-05,
|
| 1957 |
+
"loss": 0.0133,
|
| 1958 |
+
"step": 2270
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 3.4578199052132703,
|
| 1962 |
+
"grad_norm": 0.1500188261270523,
|
| 1963 |
+
"learning_rate": 2.6233289232490447e-05,
|
| 1964 |
+
"loss": 0.0076,
|
| 1965 |
+
"step": 2280
|
| 1966 |
+
},
|
| 1967 |
+
{
|
| 1968 |
+
"epoch": 3.472985781990521,
|
| 1969 |
+
"grad_norm": 0.0972483903169632,
|
| 1970 |
+
"learning_rate": 2.5768529194757474e-05,
|
| 1971 |
+
"loss": 0.0118,
|
| 1972 |
+
"step": 2290
|
| 1973 |
+
},
|
| 1974 |
+
{
|
| 1975 |
+
"epoch": 3.4881516587677726,
|
| 1976 |
+
"grad_norm": 0.11835496872663498,
|
| 1977 |
+
"learning_rate": 2.5306489515034713e-05,
|
| 1978 |
+
"loss": 0.0107,
|
| 1979 |
+
"step": 2300
|
| 1980 |
+
},
|
| 1981 |
+
{
|
| 1982 |
+
"epoch": 3.4881516587677726,
|
| 1983 |
+
"eval_loss": 0.03378909453749657,
|
| 1984 |
+
"eval_runtime": 177.022,
|
| 1985 |
+
"eval_samples_per_second": 6.626,
|
| 1986 |
+
"eval_steps_per_second": 6.626,
|
| 1987 |
+
"step": 2300
|
| 1988 |
+
},
|
| 1989 |
+
{
|
| 1990 |
+
"epoch": 3.5033175355450235,
|
| 1991 |
+
"grad_norm": 0.4174239933490753,
|
| 1992 |
+
"learning_rate": 2.484722206443455e-05,
|
| 1993 |
+
"loss": 0.0146,
|
| 1994 |
+
"step": 2310
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 3.518483412322275,
|
| 1998 |
+
"grad_norm": 0.14443957805633545,
|
| 1999 |
+
"learning_rate": 2.4390778402843605e-05,
|
| 2000 |
+
"loss": 0.0096,
|
| 2001 |
+
"step": 2320
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 3.533649289099526,
|
| 2005 |
+
"grad_norm": 0.17293648421764374,
|
| 2006 |
+
"learning_rate": 2.3937209773134472e-05,
|
| 2007 |
+
"loss": 0.0093,
|
| 2008 |
+
"step": 2330
|
| 2009 |
+
},
|
| 2010 |
+
{
|
| 2011 |
+
"epoch": 3.5488151658767775,
|
| 2012 |
+
"grad_norm": 0.24881836771965027,
|
| 2013 |
+
"learning_rate": 2.3486567095412864e-05,
|
| 2014 |
+
"loss": 0.0114,
|
| 2015 |
+
"step": 2340
|
| 2016 |
+
},
|
| 2017 |
+
{
|
| 2018 |
+
"epoch": 3.5639810426540284,
|
| 2019 |
+
"grad_norm": 0.13191837072372437,
|
| 2020 |
+
"learning_rate": 2.3038900961301053e-05,
|
| 2021 |
+
"loss": 0.006,
|
| 2022 |
+
"step": 2350
|
| 2023 |
+
},
|
| 2024 |
+
{
|
| 2025 |
+
"epoch": 3.5639810426540284,
|
| 2026 |
+
"eval_loss": 0.03380955010652542,
|
| 2027 |
+
"eval_runtime": 176.8892,
|
| 2028 |
+
"eval_samples_per_second": 6.631,
|
| 2029 |
+
"eval_steps_per_second": 6.631,
|
| 2030 |
+
"step": 2350
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 3.5791469194312797,
|
| 2034 |
+
"grad_norm": 0.3207627236843109,
|
| 2035 |
+
"learning_rate": 2.259426162825819e-05,
|
| 2036 |
+
"loss": 0.0116,
|
| 2037 |
+
"step": 2360
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"epoch": 3.5943127962085306,
|
| 2041 |
+
"grad_norm": 0.13752657175064087,
|
| 2042 |
+
"learning_rate": 2.215269901393805e-05,
|
| 2043 |
+
"loss": 0.0074,
|
| 2044 |
+
"step": 2370
|
| 2045 |
+
},
|
| 2046 |
+
{
|
| 2047 |
+
"epoch": 3.609478672985782,
|
| 2048 |
+
"grad_norm": 0.22952240705490112,
|
| 2049 |
+
"learning_rate": 2.1714262690585192e-05,
|
| 2050 |
+
"loss": 0.011,
|
| 2051 |
+
"step": 2380
|
| 2052 |
+
},
|
| 2053 |
+
{
|
| 2054 |
+
"epoch": 3.6246445497630333,
|
| 2055 |
+
"grad_norm": 0.20379796624183655,
|
| 2056 |
+
"learning_rate": 2.1279001879469424e-05,
|
| 2057 |
+
"loss": 0.0134,
|
| 2058 |
+
"step": 2390
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 3.639810426540284,
|
| 2062 |
+
"grad_norm": 0.4424147605895996,
|
| 2063 |
+
"learning_rate": 2.084696544536025e-05,
|
| 2064 |
+
"loss": 0.0127,
|
| 2065 |
+
"step": 2400
|
| 2066 |
+
},
|
| 2067 |
+
{
|
| 2068 |
+
"epoch": 3.639810426540284,
|
| 2069 |
+
"eval_loss": 0.03356926888227463,
|
| 2070 |
+
"eval_runtime": 176.7652,
|
| 2071 |
+
"eval_samples_per_second": 6.636,
|
| 2072 |
+
"eval_steps_per_second": 6.636,
|
| 2073 |
+
"step": 2400
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 3.6549763033175355,
|
| 2077 |
+
"grad_norm": 0.14149199426174164,
|
| 2078 |
+
"learning_rate": 2.0418201891040778e-05,
|
| 2079 |
+
"loss": 0.0117,
|
| 2080 |
+
"step": 2410
|
| 2081 |
+
},
|
| 2082 |
+
{
|
| 2083 |
+
"epoch": 3.670142180094787,
|
| 2084 |
+
"grad_norm": 0.15457390248775482,
|
| 2085 |
+
"learning_rate": 1.9992759351862772e-05,
|
| 2086 |
+
"loss": 0.0085,
|
| 2087 |
+
"step": 2420
|
| 2088 |
+
},
|
| 2089 |
+
{
|
| 2090 |
+
"epoch": 3.6853080568720378,
|
| 2091 |
+
"grad_norm": 0.1752661019563675,
|
| 2092 |
+
"learning_rate": 1.9570685590342463e-05,
|
| 2093 |
+
"loss": 0.0066,
|
| 2094 |
+
"step": 2430
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 3.700473933649289,
|
| 2098 |
+
"grad_norm": 0.17715801298618317,
|
| 2099 |
+
"learning_rate": 1.9152027990798748e-05,
|
| 2100 |
+
"loss": 0.0053,
|
| 2101 |
+
"step": 2440
|
| 2102 |
+
},
|
| 2103 |
+
{
|
| 2104 |
+
"epoch": 3.7156398104265405,
|
| 2105 |
+
"grad_norm": 0.06656470149755478,
|
| 2106 |
+
"learning_rate": 1.8736833554033263e-05,
|
| 2107 |
+
"loss": 0.0099,
|
| 2108 |
+
"step": 2450
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 3.7156398104265405,
|
| 2112 |
+
"eval_loss": 0.033763591200113297,
|
| 2113 |
+
"eval_runtime": 176.8005,
|
| 2114 |
+
"eval_samples_per_second": 6.635,
|
| 2115 |
+
"eval_steps_per_second": 6.635,
|
| 2116 |
+
"step": 2450
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 3.7308056872037914,
|
| 2120 |
+
"grad_norm": 0.33968186378479004,
|
| 2121 |
+
"learning_rate": 1.8325148892054093e-05,
|
| 2122 |
+
"loss": 0.0107,
|
| 2123 |
+
"step": 2460
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 3.7459715639810427,
|
| 2127 |
+
"grad_norm": 0.1185387372970581,
|
| 2128 |
+
"learning_rate": 1.7917020222842662e-05,
|
| 2129 |
+
"loss": 0.0078,
|
| 2130 |
+
"step": 2470
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 3.7611374407582936,
|
| 2134 |
+
"grad_norm": 0.7232157588005066,
|
| 2135 |
+
"learning_rate": 1.751249336516513e-05,
|
| 2136 |
+
"loss": 0.0076,
|
| 2137 |
+
"step": 2480
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 3.776303317535545,
|
| 2141 |
+
"grad_norm": 0.3267844021320343,
|
| 2142 |
+
"learning_rate": 1.7111613733428522e-05,
|
| 2143 |
+
"loss": 0.0144,
|
| 2144 |
+
"step": 2490
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 3.7914691943127963,
|
| 2148 |
+
"grad_norm": 0.3364531397819519,
|
| 2149 |
+
"learning_rate": 1.671442633258218e-05,
|
| 2150 |
+
"loss": 0.014,
|
| 2151 |
+
"step": 2500
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 3.7914691943127963,
|
| 2155 |
+
"eval_loss": 0.03367255628108978,
|
| 2156 |
+
"eval_runtime": 176.7942,
|
| 2157 |
+
"eval_samples_per_second": 6.635,
|
| 2158 |
+
"eval_steps_per_second": 6.635,
|
| 2159 |
+
"step": 2500
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 3.8066350710900476,
|
| 2163 |
+
"grad_norm": 0.29441037774086,
|
| 2164 |
+
"learning_rate": 1.6320975753065453e-05,
|
| 2165 |
+
"loss": 0.0121,
|
| 2166 |
+
"step": 2510
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 3.8218009478672985,
|
| 2170 |
+
"grad_norm": 0.1159694567322731,
|
| 2171 |
+
"learning_rate": 1.5931306165801452e-05,
|
| 2172 |
+
"loss": 0.007,
|
| 2173 |
+
"step": 2520
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 3.83696682464455,
|
| 2177 |
+
"grad_norm": 0.06502162665128708,
|
| 2178 |
+
"learning_rate": 1.554546131723848e-05,
|
| 2179 |
+
"loss": 0.0102,
|
| 2180 |
+
"step": 2530
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 3.8521327014218008,
|
| 2184 |
+
"grad_norm": 0.2042492926120758,
|
| 2185 |
+
"learning_rate": 1.5163484524438516e-05,
|
| 2186 |
+
"loss": 0.0091,
|
| 2187 |
+
"step": 2540
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 3.867298578199052,
|
| 2191 |
+
"grad_norm": 0.16165339946746826,
|
| 2192 |
+
"learning_rate": 1.4785418670214496e-05,
|
| 2193 |
+
"loss": 0.0129,
|
| 2194 |
+
"step": 2550
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 3.867298578199052,
|
| 2198 |
+
"eval_loss": 0.03390151634812355,
|
| 2199 |
+
"eval_runtime": 176.7582,
|
| 2200 |
+
"eval_samples_per_second": 6.636,
|
| 2201 |
+
"eval_steps_per_second": 6.636,
|
| 2202 |
+
"step": 2550
|
| 2203 |
+
},
|
| 2204 |
+
{
|
| 2205 |
+
"epoch": 3.8824644549763034,
|
| 2206 |
+
"grad_norm": 0.1416504681110382,
|
| 2207 |
+
"learning_rate": 1.4411306198315777e-05,
|
| 2208 |
+
"loss": 0.0078,
|
| 2209 |
+
"step": 2560
|
| 2210 |
+
},
|
| 2211 |
+
{
|
| 2212 |
+
"epoch": 3.8976303317535548,
|
| 2213 |
+
"grad_norm": 0.20074276626110077,
|
| 2214 |
+
"learning_rate": 1.4041189108663421e-05,
|
| 2215 |
+
"loss": 0.0076,
|
| 2216 |
+
"step": 2570
|
| 2217 |
+
},
|
| 2218 |
+
{
|
| 2219 |
+
"epoch": 3.9127962085308057,
|
| 2220 |
+
"grad_norm": 0.44658246636390686,
|
| 2221 |
+
"learning_rate": 1.3675108952634824e-05,
|
| 2222 |
+
"loss": 0.0121,
|
| 2223 |
+
"step": 2580
|
| 2224 |
+
},
|
| 2225 |
+
{
|
| 2226 |
+
"epoch": 3.927962085308057,
|
| 2227 |
+
"grad_norm": 0.2680942714214325,
|
| 2228 |
+
"learning_rate": 1.3313106828399147e-05,
|
| 2229 |
+
"loss": 0.0132,
|
| 2230 |
+
"step": 2590
|
| 2231 |
+
},
|
| 2232 |
+
{
|
| 2233 |
+
"epoch": 3.943127962085308,
|
| 2234 |
+
"grad_norm": 0.2255931943655014,
|
| 2235 |
+
"learning_rate": 1.2955223376303205e-05,
|
| 2236 |
+
"loss": 0.0118,
|
| 2237 |
+
"step": 2600
|
| 2238 |
+
},
|
| 2239 |
+
{
|
| 2240 |
+
"epoch": 3.943127962085308,
|
| 2241 |
+
"eval_loss": 0.03499338775873184,
|
| 2242 |
+
"eval_runtime": 176.6361,
|
| 2243 |
+
"eval_samples_per_second": 6.641,
|
| 2244 |
+
"eval_steps_per_second": 6.641,
|
| 2245 |
+
"step": 2600
|
| 2246 |
+
},
|
| 2247 |
+
{
|
| 2248 |
+
"epoch": 3.9582938388625593,
|
| 2249 |
+
"grad_norm": 0.21901127696037292,
|
| 2250 |
+
"learning_rate": 1.2601498774309112e-05,
|
| 2251 |
+
"loss": 0.0085,
|
| 2252 |
+
"step": 2610
|
| 2253 |
+
},
|
| 2254 |
+
{
|
| 2255 |
+
"epoch": 3.9734597156398106,
|
| 2256 |
+
"grad_norm": 0.17668171226978302,
|
| 2257 |
+
"learning_rate": 1.2251972733483612e-05,
|
| 2258 |
+
"loss": 0.011,
|
| 2259 |
+
"step": 2620
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"epoch": 3.9886255924170615,
|
| 2263 |
+
"grad_norm": 0.17130517959594727,
|
| 2264 |
+
"learning_rate": 1.19066844935399e-05,
|
| 2265 |
+
"loss": 0.0095,
|
| 2266 |
+
"step": 2630
|
| 2267 |
+
},
|
| 2268 |
+
{
|
| 2269 |
+
"epoch": 4.003791469194312,
|
| 2270 |
+
"grad_norm": 0.10923975706100464,
|
| 2271 |
+
"learning_rate": 1.156567281843241e-05,
|
| 2272 |
+
"loss": 0.0124,
|
| 2273 |
+
"step": 2640
|
| 2274 |
+
},
|
| 2275 |
+
{
|
| 2276 |
+
"epoch": 4.018957345971564,
|
| 2277 |
+
"grad_norm": 0.19639810919761658,
|
| 2278 |
+
"learning_rate": 1.1228975992004842e-05,
|
| 2279 |
+
"loss": 0.0073,
|
| 2280 |
+
"step": 2650
|
| 2281 |
+
},
|
| 2282 |
+
{
|
| 2283 |
+
"epoch": 4.018957345971564,
|
| 2284 |
+
"eval_loss": 0.03456135094165802,
|
| 2285 |
+
"eval_runtime": 176.4872,
|
| 2286 |
+
"eval_samples_per_second": 6.646,
|
| 2287 |
+
"eval_steps_per_second": 6.646,
|
| 2288 |
+
"step": 2650
|
| 2289 |
+
},
|
| 2290 |
+
{
|
| 2291 |
+
"epoch": 4.034123222748815,
|
| 2292 |
+
"grad_norm": 0.030663151293992996,
|
| 2293 |
+
"learning_rate": 1.0896631813692377e-05,
|
| 2294 |
+
"loss": 0.0041,
|
| 2295 |
+
"step": 2660
|
| 2296 |
+
},
|
| 2297 |
+
{
|
| 2298 |
+
"epoch": 4.049289099526066,
|
| 2299 |
+
"grad_norm": 0.07115893065929413,
|
| 2300 |
+
"learning_rate": 1.0568677594277899e-05,
|
| 2301 |
+
"loss": 0.0051,
|
| 2302 |
+
"step": 2670
|
| 2303 |
+
},
|
| 2304 |
+
{
|
| 2305 |
+
"epoch": 4.064454976303318,
|
| 2306 |
+
"grad_norm": 0.04100283235311508,
|
| 2307 |
+
"learning_rate": 1.0245150151703509e-05,
|
| 2308 |
+
"loss": 0.0043,
|
| 2309 |
+
"step": 2680
|
| 2310 |
+
},
|
| 2311 |
+
{
|
| 2312 |
+
"epoch": 4.079620853080569,
|
| 2313 |
+
"grad_norm": 0.08858209103345871,
|
| 2314 |
+
"learning_rate": 9.926085806936918e-06,
|
| 2315 |
+
"loss": 0.006,
|
| 2316 |
+
"step": 2690
|
| 2317 |
+
},
|
| 2318 |
+
{
|
| 2319 |
+
"epoch": 4.0947867298578196,
|
| 2320 |
+
"grad_norm": 0.01757189631462097,
|
| 2321 |
+
"learning_rate": 9.611520379894068e-06,
|
| 2322 |
+
"loss": 0.0048,
|
| 2323 |
+
"step": 2700
|
| 2324 |
+
},
|
| 2325 |
+
{
|
| 2326 |
+
"epoch": 4.0947867298578196,
|
| 2327 |
+
"eval_loss": 0.0357203334569931,
|
| 2328 |
+
"eval_runtime": 176.4817,
|
| 2329 |
+
"eval_samples_per_second": 6.647,
|
| 2330 |
+
"eval_steps_per_second": 6.647,
|
| 2331 |
+
"step": 2700
|
| 2332 |
+
},
|
| 2333 |
+
{
|
| 2334 |
+
"epoch": 4.109952606635071,
|
| 2335 |
+
"grad_norm": 0.11255928874015808,
|
| 2336 |
+
"learning_rate": 9.301489185417578e-06,
|
| 2337 |
+
"loss": 0.0052,
|
| 2338 |
+
"step": 2710
|
| 2339 |
+
},
|
| 2340 |
+
{
|
| 2341 |
+
"epoch": 4.125118483412322,
|
| 2342 |
+
"grad_norm": 0.12291298806667328,
|
| 2343 |
+
"learning_rate": 8.996027029312314e-06,
|
| 2344 |
+
"loss": 0.0048,
|
| 2345 |
+
"step": 2720
|
| 2346 |
+
},
|
| 2347 |
+
{
|
| 2348 |
+
"epoch": 4.140284360189574,
|
| 2349 |
+
"grad_norm": 0.2394372820854187,
|
| 2350 |
+
"learning_rate": 8.695168204437721e-06,
|
| 2351 |
+
"loss": 0.0042,
|
| 2352 |
+
"step": 2730
|
| 2353 |
+
},
|
| 2354 |
+
{
|
| 2355 |
+
"epoch": 4.155450236966825,
|
| 2356 |
+
"grad_norm": 0.09991464763879776,
|
| 2357 |
+
"learning_rate": 8.398946486858029e-06,
|
| 2358 |
+
"loss": 0.0036,
|
| 2359 |
+
"step": 2740
|
| 2360 |
+
},
|
| 2361 |
+
{
|
| 2362 |
+
"epoch": 4.170616113744076,
|
| 2363 |
+
"grad_norm": 0.21715304255485535,
|
| 2364 |
+
"learning_rate": 8.107395132050333e-06,
|
| 2365 |
+
"loss": 0.0059,
|
| 2366 |
+
"step": 2750
|
| 2367 |
+
},
|
| 2368 |
+
{
|
| 2369 |
+
"epoch": 4.170616113744076,
|
| 2370 |
+
"eval_loss": 0.037330999970436096,
|
| 2371 |
+
"eval_runtime": 176.5966,
|
| 2372 |
+
"eval_samples_per_second": 6.642,
|
| 2373 |
+
"eval_steps_per_second": 6.642,
|
| 2374 |
+
"step": 2750
|
| 2375 |
+
},
|
| 2376 |
+
{
|
| 2377 |
+
"epoch": 4.185781990521327,
|
| 2378 |
+
"grad_norm": 0.06366084516048431,
|
| 2379 |
+
"learning_rate": 7.820546871171142e-06,
|
| 2380 |
+
"loss": 0.0045,
|
| 2381 |
+
"step": 2760
|
| 2382 |
+
},
|
| 2383 |
+
{
|
| 2384 |
+
"epoch": 4.200947867298578,
|
| 2385 |
+
"grad_norm": 0.12914450466632843,
|
| 2386 |
+
"learning_rate": 7.5384339073818145e-06,
|
| 2387 |
+
"loss": 0.0046,
|
| 2388 |
+
"step": 2770
|
| 2389 |
+
},
|
| 2390 |
+
{
|
| 2391 |
+
"epoch": 4.216113744075829,
|
| 2392 |
+
"grad_norm": 0.032806962728500366,
|
| 2393 |
+
"learning_rate": 7.261087912233228e-06,
|
| 2394 |
+
"loss": 0.0055,
|
| 2395 |
+
"step": 2780
|
| 2396 |
+
},
|
| 2397 |
+
{
|
| 2398 |
+
"epoch": 4.231279620853081,
|
| 2399 |
+
"grad_norm": 0.1332745999097824,
|
| 2400 |
+
"learning_rate": 6.988540022110235e-06,
|
| 2401 |
+
"loss": 0.0064,
|
| 2402 |
+
"step": 2790
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 4.246445497630332,
|
| 2406 |
+
"grad_norm": 0.07780851423740387,
|
| 2407 |
+
"learning_rate": 6.720820834735969e-06,
|
| 2408 |
+
"loss": 0.0053,
|
| 2409 |
+
"step": 2800
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 4.246445497630332,
|
| 2413 |
+
"eval_loss": 0.037292271852493286,
|
| 2414 |
+
"eval_runtime": 176.612,
|
| 2415 |
+
"eval_samples_per_second": 6.642,
|
| 2416 |
+
"eval_steps_per_second": 6.642,
|
| 2417 |
+
"step": 2800
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 4.2616113744075825,
|
| 2421 |
+
"grad_norm": 0.13824769854545593,
|
| 2422 |
+
"learning_rate": 6.457960405736968e-06,
|
| 2423 |
+
"loss": 0.0037,
|
| 2424 |
+
"step": 2810
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 4.276777251184834,
|
| 2428 |
+
"grad_norm": 0.15241014957427979,
|
| 2429 |
+
"learning_rate": 6.199988245268778e-06,
|
| 2430 |
+
"loss": 0.0043,
|
| 2431 |
+
"step": 2820
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 4.291943127962085,
|
| 2435 |
+
"grad_norm": 0.03748151287436485,
|
| 2436 |
+
"learning_rate": 5.946933314703157e-06,
|
| 2437 |
+
"loss": 0.0048,
|
| 2438 |
+
"step": 2830
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 4.3071090047393366,
|
| 2442 |
+
"grad_norm": 0.011155886575579643,
|
| 2443 |
+
"learning_rate": 5.698824023376531e-06,
|
| 2444 |
+
"loss": 0.003,
|
| 2445 |
+
"step": 2840
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 4.322274881516588,
|
| 2449 |
+
"grad_norm": 0.15347355604171753,
|
| 2450 |
+
"learning_rate": 5.455688225400802e-06,
|
| 2451 |
+
"loss": 0.0045,
|
| 2452 |
+
"step": 2850
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 4.322274881516588,
|
| 2456 |
+
"eval_loss": 0.03810197114944458,
|
| 2457 |
+
"eval_runtime": 176.7279,
|
| 2458 |
+
"eval_samples_per_second": 6.637,
|
| 2459 |
+
"eval_steps_per_second": 6.637,
|
| 2460 |
+
"step": 2850
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 4.337440758293839,
|
| 2464 |
+
"grad_norm": 0.18955792486667633,
|
| 2465 |
+
"learning_rate": 5.217553216536098e-06,
|
| 2466 |
+
"loss": 0.0075,
|
| 2467 |
+
"step": 2860
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 4.35260663507109,
|
| 2471 |
+
"grad_norm": 0.11830997467041016,
|
| 2472 |
+
"learning_rate": 4.984445731126542e-06,
|
| 2473 |
+
"loss": 0.0063,
|
| 2474 |
+
"step": 2870
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 4.367772511848341,
|
| 2478 |
+
"grad_norm": 0.09092006832361221,
|
| 2479 |
+
"learning_rate": 4.756391939098853e-06,
|
| 2480 |
+
"loss": 0.003,
|
| 2481 |
+
"step": 2880
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 4.382938388625592,
|
| 2485 |
+
"grad_norm": 0.049758732318878174,
|
| 2486 |
+
"learning_rate": 4.533417443024374e-06,
|
| 2487 |
+
"loss": 0.008,
|
| 2488 |
+
"step": 2890
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 4.398104265402844,
|
| 2492 |
+
"grad_norm": 0.39580151438713074,
|
| 2493 |
+
"learning_rate": 4.315547275244769e-06,
|
| 2494 |
+
"loss": 0.0054,
|
| 2495 |
+
"step": 2900
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 4.398104265402844,
|
| 2499 |
+
"eval_loss": 0.03884812071919441,
|
| 2500 |
+
"eval_runtime": 176.624,
|
| 2501 |
+
"eval_samples_per_second": 6.641,
|
| 2502 |
+
"eval_steps_per_second": 6.641,
|
| 2503 |
+
"step": 2900
|
| 2504 |
+
},
|
| 2505 |
+
{
|
| 2506 |
+
"epoch": 4.413270142180095,
|
| 2507 |
+
"grad_norm": 0.11998700350522995,
|
| 2508 |
+
"learning_rate": 4.10280589506179e-06,
|
| 2509 |
+
"loss": 0.0033,
|
| 2510 |
+
"step": 2910
|
| 2511 |
+
},
|
| 2512 |
+
{
|
| 2513 |
+
"epoch": 4.4284360189573455,
|
| 2514 |
+
"grad_norm": 0.5768892765045166,
|
| 2515 |
+
"learning_rate": 3.895217185991312e-06,
|
| 2516 |
+
"loss": 0.0077,
|
| 2517 |
+
"step": 2920
|
| 2518 |
+
},
|
| 2519 |
+
{
|
| 2520 |
+
"epoch": 4.443601895734597,
|
| 2521 |
+
"grad_norm": 0.13106589019298553,
|
| 2522 |
+
"learning_rate": 3.692804453082038e-06,
|
| 2523 |
+
"loss": 0.0087,
|
| 2524 |
+
"step": 2930
|
| 2525 |
+
},
|
| 2526 |
+
{
|
| 2527 |
+
"epoch": 4.458767772511848,
|
| 2528 |
+
"grad_norm": 0.23035043478012085,
|
| 2529 |
+
"learning_rate": 3.495590420299194e-06,
|
| 2530 |
+
"loss": 0.0049,
|
| 2531 |
+
"step": 2940
|
| 2532 |
+
},
|
| 2533 |
+
{
|
| 2534 |
+
"epoch": 4.4739336492890995,
|
| 2535 |
+
"grad_norm": 0.1375955194234848,
|
| 2536 |
+
"learning_rate": 3.3035972279733207e-06,
|
| 2537 |
+
"loss": 0.0085,
|
| 2538 |
+
"step": 2950
|
| 2539 |
+
},
|
| 2540 |
+
{
|
| 2541 |
+
"epoch": 4.4739336492890995,
|
| 2542 |
+
"eval_loss": 0.03845488652586937,
|
| 2543 |
+
"eval_runtime": 176.6446,
|
| 2544 |
+
"eval_samples_per_second": 6.64,
|
| 2545 |
+
"eval_steps_per_second": 6.64,
|
| 2546 |
+
"step": 2950
|
| 2547 |
+
},
|
| 2548 |
+
{
|
| 2549 |
+
"epoch": 4.489099526066351,
|
| 2550 |
+
"grad_norm": 0.10981747508049011,
|
| 2551 |
+
"learning_rate": 3.116846430314796e-06,
|
| 2552 |
+
"loss": 0.0035,
|
| 2553 |
+
"step": 2960
|
| 2554 |
+
},
|
| 2555 |
+
{
|
| 2556 |
+
"epoch": 4.504265402843602,
|
| 2557 |
+
"grad_norm": 0.0285560991615057,
|
| 2558 |
+
"learning_rate": 2.9353589929939087e-06,
|
| 2559 |
+
"loss": 0.0042,
|
| 2560 |
+
"step": 2970
|
| 2561 |
+
},
|
| 2562 |
+
{
|
| 2563 |
+
"epoch": 4.519431279620854,
|
| 2564 |
+
"grad_norm": 0.22480367124080658,
|
| 2565 |
+
"learning_rate": 2.7591552907872574e-06,
|
| 2566 |
+
"loss": 0.0059,
|
| 2567 |
+
"step": 2980
|
| 2568 |
+
},
|
| 2569 |
+
{
|
| 2570 |
+
"epoch": 4.534597156398104,
|
| 2571 |
+
"grad_norm": 0.26764968037605286,
|
| 2572 |
+
"learning_rate": 2.5882551052902883e-06,
|
| 2573 |
+
"loss": 0.006,
|
| 2574 |
+
"step": 2990
|
| 2575 |
+
},
|
| 2576 |
+
{
|
| 2577 |
+
"epoch": 4.549763033175355,
|
| 2578 |
+
"grad_norm": 0.21272222697734833,
|
| 2579 |
+
"learning_rate": 2.4226776226965453e-06,
|
| 2580 |
+
"loss": 0.0066,
|
| 2581 |
+
"step": 3000
|
| 2582 |
+
},
|
| 2583 |
+
{
|
| 2584 |
+
"epoch": 4.549763033175355,
|
| 2585 |
+
"eval_loss": 0.03843921050429344,
|
| 2586 |
+
"eval_runtime": 176.6472,
|
| 2587 |
+
"eval_samples_per_second": 6.64,
|
| 2588 |
+
"eval_steps_per_second": 6.64,
|
| 2589 |
+
"step": 3000
|
| 2590 |
+
},
|
| 2591 |
+
{
|
| 2592 |
+
"epoch": 4.564928909952607,
|
| 2593 |
+
"grad_norm": 0.10441111028194427,
|
| 2594 |
+
"learning_rate": 2.262441431643697e-06,
|
| 2595 |
+
"loss": 0.0053,
|
| 2596 |
+
"step": 3010
|
| 2597 |
+
},
|
| 2598 |
+
{
|
| 2599 |
+
"epoch": 4.580094786729858,
|
| 2600 |
+
"grad_norm": 0.1366783082485199,
|
| 2601 |
+
"learning_rate": 2.1075645211266927e-06,
|
| 2602 |
+
"loss": 0.0044,
|
| 2603 |
+
"step": 3020
|
| 2604 |
+
},
|
| 2605 |
+
{
|
| 2606 |
+
"epoch": 4.595260663507109,
|
| 2607 |
+
"grad_norm": 0.07694575935602188,
|
| 2608 |
+
"learning_rate": 1.9580642784782053e-06,
|
| 2609 |
+
"loss": 0.0062,
|
| 2610 |
+
"step": 3030
|
| 2611 |
+
},
|
| 2612 |
+
{
|
| 2613 |
+
"epoch": 4.61042654028436,
|
| 2614 |
+
"grad_norm": 0.08338585495948792,
|
| 2615 |
+
"learning_rate": 1.813957487416651e-06,
|
| 2616 |
+
"loss": 0.0053,
|
| 2617 |
+
"step": 3040
|
| 2618 |
+
},
|
| 2619 |
+
{
|
| 2620 |
+
"epoch": 4.625592417061611,
|
| 2621 |
+
"grad_norm": 0.28469717502593994,
|
| 2622 |
+
"learning_rate": 1.6752603261619315e-06,
|
| 2623 |
+
"loss": 0.0051,
|
| 2624 |
+
"step": 3050
|
| 2625 |
+
},
|
| 2626 |
+
{
|
| 2627 |
+
"epoch": 4.625592417061611,
|
| 2628 |
+
"eval_loss": 0.03863969072699547,
|
| 2629 |
+
"eval_runtime": 176.6381,
|
| 2630 |
+
"eval_samples_per_second": 6.641,
|
| 2631 |
+
"eval_steps_per_second": 6.641,
|
| 2632 |
+
"step": 3050
|
| 2633 |
+
},
|
| 2634 |
+
{
|
| 2635 |
+
"epoch": 4.6407582938388625,
|
| 2636 |
+
"grad_norm": 0.21466806530952454,
|
| 2637 |
+
"learning_rate": 1.541988365619207e-06,
|
| 2638 |
+
"loss": 0.0053,
|
| 2639 |
+
"step": 3060
|
| 2640 |
+
},
|
| 2641 |
+
{
|
| 2642 |
+
"epoch": 4.655924170616114,
|
| 2643 |
+
"grad_norm": 0.1829688400030136,
|
| 2644 |
+
"learning_rate": 1.4141565676307865e-06,
|
| 2645 |
+
"loss": 0.005,
|
| 2646 |
+
"step": 3070
|
| 2647 |
+
},
|
| 2648 |
+
{
|
| 2649 |
+
"epoch": 4.671090047393365,
|
| 2650 |
+
"grad_norm": 0.08133982867002487,
|
| 2651 |
+
"learning_rate": 1.291779283296468e-06,
|
| 2652 |
+
"loss": 0.0029,
|
| 2653 |
+
"step": 3080
|
| 2654 |
+
},
|
| 2655 |
+
{
|
| 2656 |
+
"epoch": 4.6862559241706165,
|
| 2657 |
+
"grad_norm": 0.03812313824892044,
|
| 2658 |
+
"learning_rate": 1.1748702513623922e-06,
|
| 2659 |
+
"loss": 0.0033,
|
| 2660 |
+
"step": 3090
|
| 2661 |
+
},
|
| 2662 |
+
{
|
| 2663 |
+
"epoch": 4.701421800947867,
|
| 2664 |
+
"grad_norm": 0.02549022249877453,
|
| 2665 |
+
"learning_rate": 1.0634425966786155e-06,
|
| 2666 |
+
"loss": 0.0052,
|
| 2667 |
+
"step": 3100
|
| 2668 |
+
},
|
| 2669 |
+
{
|
| 2670 |
+
"epoch": 4.701421800947867,
|
| 2671 |
+
"eval_loss": 0.038835834711790085,
|
| 2672 |
+
"eval_runtime": 176.5888,
|
| 2673 |
+
"eval_samples_per_second": 6.643,
|
| 2674 |
+
"eval_steps_per_second": 6.643,
|
| 2675 |
+
"step": 3100
|
| 2676 |
+
},
|
| 2677 |
+
{
|
| 2678 |
+
"epoch": 4.716587677725118,
|
| 2679 |
+
"grad_norm": 0.2480955272912979,
|
| 2680 |
+
"learning_rate": 9.575088287257118e-07,
|
| 2681 |
+
"loss": 0.0038,
|
| 2682 |
+
"step": 3110
|
| 2683 |
+
},
|
| 2684 |
+
{
|
| 2685 |
+
"epoch": 4.73175355450237,
|
| 2686 |
+
"grad_norm": 0.22870886325836182,
|
| 2687 |
+
"learning_rate": 8.570808402103392e-07,
|
| 2688 |
+
"loss": 0.0067,
|
| 2689 |
+
"step": 3120
|
| 2690 |
+
},
|
| 2691 |
+
{
|
| 2692 |
+
"epoch": 4.746919431279621,
|
| 2693 |
+
"grad_norm": 0.08617883920669556,
|
| 2694 |
+
"learning_rate": 7.62169905730109e-07,
|
| 2695 |
+
"loss": 0.006,
|
| 2696 |
+
"step": 3130
|
| 2697 |
+
},
|
| 2698 |
+
{
|
| 2699 |
+
"epoch": 4.762085308056872,
|
| 2700 |
+
"grad_norm": 0.19280649721622467,
|
| 2701 |
+
"learning_rate": 6.727866805078531e-07,
|
| 2702 |
+
"loss": 0.0045,
|
| 2703 |
+
"step": 3140
|
| 2704 |
+
},
|
| 2705 |
+
{
|
| 2706 |
+
"epoch": 4.777251184834123,
|
| 2707 |
+
"grad_norm": 0.1964663714170456,
|
| 2708 |
+
"learning_rate": 5.889411991953975e-07,
|
| 2709 |
+
"loss": 0.0065,
|
| 2710 |
+
"step": 3150
|
| 2711 |
+
},
|
| 2712 |
+
{
|
| 2713 |
+
"epoch": 4.777251184834123,
|
| 2714 |
+
"eval_loss": 0.03892850503325462,
|
| 2715 |
+
"eval_runtime": 176.5708,
|
| 2716 |
+
"eval_samples_per_second": 6.643,
|
| 2717 |
+
"eval_steps_per_second": 6.643,
|
| 2718 |
+
"step": 3150
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 4.792417061611374,
|
| 2722 |
+
"grad_norm": 0.022485673427581787,
|
| 2723 |
+
"learning_rate": 5.106428747470137e-07,
|
| 2724 |
+
"loss": 0.0054,
|
| 2725 |
+
"step": 3160
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 4.8075829383886255,
|
| 2729 |
+
"grad_norm": 0.11611665785312653,
|
| 2730 |
+
"learning_rate": 4.37900497362681e-07,
|
| 2731 |
+
"loss": 0.0046,
|
| 2732 |
+
"step": 3170
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 4.822748815165877,
|
| 2736 |
+
"grad_norm": 0.08721260726451874,
|
| 2737 |
+
"learning_rate": 3.7072223350124167e-07,
|
| 2738 |
+
"loss": 0.0054,
|
| 2739 |
+
"step": 3180
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 4.837914691943128,
|
| 2743 |
+
"grad_norm": 0.1968434751033783,
|
| 2744 |
+
"learning_rate": 3.0911562496358517e-07,
|
| 2745 |
+
"loss": 0.0035,
|
| 2746 |
+
"step": 3190
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 4.8530805687203795,
|
| 2750 |
+
"grad_norm": 0.10239926725625992,
|
| 2751 |
+
"learning_rate": 2.53087588045986e-07,
|
| 2752 |
+
"loss": 0.0036,
|
| 2753 |
+
"step": 3200
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 4.8530805687203795,
|
| 2757 |
+
"eval_loss": 0.03907202184200287,
|
| 2758 |
+
"eval_runtime": 176.5342,
|
| 2759 |
+
"eval_samples_per_second": 6.645,
|
| 2760 |
+
"eval_steps_per_second": 6.645,
|
| 2761 |
+
"step": 3200
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 4.86824644549763,
|
| 2765 |
+
"grad_norm": 0.19318081438541412,
|
| 2766 |
+
"learning_rate": 2.026444127636029e-07,
|
| 2767 |
+
"loss": 0.0025,
|
| 2768 |
+
"step": 3210
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 4.883412322274881,
|
| 2772 |
+
"grad_norm": 0.9325800538063049,
|
| 2773 |
+
"learning_rate": 1.577917621443825e-07,
|
| 2774 |
+
"loss": 0.0066,
|
| 2775 |
+
"step": 3220
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 4.898578199052133,
|
| 2779 |
+
"grad_norm": 0.1284843534231186,
|
| 2780 |
+
"learning_rate": 1.185346715932345e-07,
|
| 2781 |
+
"loss": 0.0061,
|
| 2782 |
+
"step": 3230
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 4.913744075829384,
|
| 2786 |
+
"grad_norm": 0.41085031628608704,
|
| 2787 |
+
"learning_rate": 8.48775483267783e-08,
|
| 2788 |
+
"loss": 0.0072,
|
| 2789 |
+
"step": 3240
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 4.928909952606635,
|
| 2793 |
+
"grad_norm": 0.053091879934072495,
|
| 2794 |
+
"learning_rate": 5.6824170878544414e-08,
|
| 2795 |
+
"loss": 0.0039,
|
| 2796 |
+
"step": 3250
|
| 2797 |
+
},
|
| 2798 |
+
{
|
| 2799 |
+
"epoch": 4.928909952606635,
|
| 2800 |
+
"eval_loss": 0.03911284729838371,
|
| 2801 |
+
"eval_runtime": 176.5645,
|
| 2802 |
+
"eval_samples_per_second": 6.643,
|
| 2803 |
+
"eval_steps_per_second": 6.643,
|
| 2804 |
+
"step": 3250
|
| 2805 |
+
},
|
| 2806 |
+
{
|
| 2807 |
+
"epoch": 4.944075829383886,
|
| 2808 |
+
"grad_norm": 0.18437696993350983,
|
| 2809 |
+
"learning_rate": 3.4377688674774866e-08,
|
| 2810 |
+
"loss": 0.0051,
|
| 2811 |
+
"step": 3260
|
| 2812 |
+
},
|
| 2813 |
+
{
|
| 2814 |
+
"epoch": 4.959241706161137,
|
| 2815 |
+
"grad_norm": 0.04348951205611229,
|
| 2816 |
+
"learning_rate": 1.7540621680850466e-08,
|
| 2817 |
+
"loss": 0.0026,
|
| 2818 |
+
"step": 3270
|
| 2819 |
+
},
|
| 2820 |
+
{
|
| 2821 |
+
"epoch": 4.9744075829383885,
|
| 2822 |
+
"grad_norm": 0.18638713657855988,
|
| 2823 |
+
"learning_rate": 6.314860118400434e-09,
|
| 2824 |
+
"loss": 0.0042,
|
| 2825 |
+
"step": 3280
|
| 2826 |
+
},
|
| 2827 |
+
{
|
| 2828 |
+
"epoch": 4.98957345971564,
|
| 2829 |
+
"grad_norm": 0.1402566283941269,
|
| 2830 |
+
"learning_rate": 7.016642530777162e-10,
|
| 2831 |
+
"loss": 0.0045,
|
| 2832 |
+
"step": 3290
|
| 2833 |
+
},
|
| 2834 |
+
{
|
| 2835 |
+
"epoch": 4.9971563981042655,
|
| 2836 |
+
"step": 3295,
|
| 2837 |
+
"total_flos": 8.907449267845202e+17,
|
| 2838 |
+
"train_loss": 0.04891899318543117,
|
| 2839 |
+
"train_runtime": 37195.0472,
|
| 2840 |
+
"train_samples_per_second": 1.418,
|
| 2841 |
+
"train_steps_per_second": 0.089
|
| 2842 |
+
}
|
| 2843 |
+
],
|
| 2844 |
+
"logging_steps": 10,
|
| 2845 |
+
"max_steps": 3295,
|
| 2846 |
+
"num_input_tokens_seen": 0,
|
| 2847 |
+
"num_train_epochs": 5,
|
| 2848 |
+
"save_steps": 50,
|
| 2849 |
+
"stateful_callbacks": {
|
| 2850 |
+
"TrainerControl": {
|
| 2851 |
+
"args": {
|
| 2852 |
+
"should_epoch_stop": false,
|
| 2853 |
+
"should_evaluate": false,
|
| 2854 |
+
"should_log": false,
|
| 2855 |
+
"should_save": true,
|
| 2856 |
+
"should_training_stop": true
|
| 2857 |
+
},
|
| 2858 |
+
"attributes": {}
|
| 2859 |
+
}
|
| 2860 |
+
},
|
| 2861 |
+
"total_flos": 8.907449267845202e+17,
|
| 2862 |
+
"train_batch_size": 1,
|
| 2863 |
+
"trial_name": null,
|
| 2864 |
+
"trial_params": null
|
| 2865 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|