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 +2851 -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-fold4
|
|
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# MentaLLaMA-chat-7B-PsyCourse-fold4
|
| 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-fold4
|
|
|
|
| 16 |
|
| 17 |
# MentaLLaMA-chat-7B-PsyCourse-fold4
|
| 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-fold4 dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.0289
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.999522946283752,
|
| 3 |
+
"eval_loss": 0.028858734294772148,
|
| 4 |
+
"eval_runtime": 175.4545,
|
| 5 |
+
"eval_samples_per_second": 6.64,
|
| 6 |
+
"eval_steps_per_second": 6.64,
|
| 7 |
+
"total_flos": 8.8535579239868e+17,
|
| 8 |
+
"train_loss": 0.048749475333526845,
|
| 9 |
+
"train_runtime": 37525.7545,
|
| 10 |
+
"train_samples_per_second": 1.397,
|
| 11 |
+
"train_steps_per_second": 0.087
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.999522946283752,
|
| 3 |
+
"eval_loss": 0.028858734294772148,
|
| 4 |
+
"eval_runtime": 175.4545,
|
| 5 |
+
"eval_samples_per_second": 6.64,
|
| 6 |
+
"eval_steps_per_second": 6.64
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.999522946283752,
|
| 3 |
+
"total_flos": 8.8535579239868e+17,
|
| 4 |
+
"train_loss": 0.048749475333526845,
|
| 5 |
+
"train_runtime": 37525.7545,
|
| 6 |
+
"train_samples_per_second": 1.397,
|
| 7 |
+
"train_steps_per_second": 0.087
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2851 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.028858734294772148,
|
| 3 |
+
"best_model_checkpoint": "saves/psy-course/MentaLLaMA-chat-7B/train/fold4/checkpoint-1250",
|
| 4 |
+
"epoch": 4.999522946283752,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 3275,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.015265718919950386,
|
| 13 |
+
"grad_norm": 1.6029620170593262,
|
| 14 |
+
"learning_rate": 3.0487804878048782e-06,
|
| 15 |
+
"loss": 1.7277,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.030531437839900772,
|
| 20 |
+
"grad_norm": 2.1076600551605225,
|
| 21 |
+
"learning_rate": 6.0975609756097564e-06,
|
| 22 |
+
"loss": 1.689,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.04579715675985116,
|
| 27 |
+
"grad_norm": 2.5429253578186035,
|
| 28 |
+
"learning_rate": 9.146341463414634e-06,
|
| 29 |
+
"loss": 1.6402,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.061062875679801544,
|
| 34 |
+
"grad_norm": 2.8307013511657715,
|
| 35 |
+
"learning_rate": 1.2195121951219513e-05,
|
| 36 |
+
"loss": 1.437,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.07632859459975193,
|
| 41 |
+
"grad_norm": 0.9449720978736877,
|
| 42 |
+
"learning_rate": 1.524390243902439e-05,
|
| 43 |
+
"loss": 0.796,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.07632859459975193,
|
| 48 |
+
"eval_loss": 0.614504337310791,
|
| 49 |
+
"eval_runtime": 178.8075,
|
| 50 |
+
"eval_samples_per_second": 6.515,
|
| 51 |
+
"eval_steps_per_second": 6.515,
|
| 52 |
+
"step": 50
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.09159431351970232,
|
| 56 |
+
"grad_norm": 1.0583168268203735,
|
| 57 |
+
"learning_rate": 1.8292682926829268e-05,
|
| 58 |
+
"loss": 0.5954,
|
| 59 |
+
"step": 60
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.10686003243965271,
|
| 63 |
+
"grad_norm": 0.9122205972671509,
|
| 64 |
+
"learning_rate": 2.134146341463415e-05,
|
| 65 |
+
"loss": 0.4645,
|
| 66 |
+
"step": 70
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.12212575135960309,
|
| 70 |
+
"grad_norm": 0.8755609393119812,
|
| 71 |
+
"learning_rate": 2.4390243902439026e-05,
|
| 72 |
+
"loss": 0.3116,
|
| 73 |
+
"step": 80
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.13739147027955348,
|
| 77 |
+
"grad_norm": 0.8426439166069031,
|
| 78 |
+
"learning_rate": 2.7439024390243906e-05,
|
| 79 |
+
"loss": 0.1824,
|
| 80 |
+
"step": 90
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.15265718919950386,
|
| 84 |
+
"grad_norm": 0.43453994393348694,
|
| 85 |
+
"learning_rate": 3.048780487804878e-05,
|
| 86 |
+
"loss": 0.1534,
|
| 87 |
+
"step": 100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.15265718919950386,
|
| 91 |
+
"eval_loss": 0.104978546500206,
|
| 92 |
+
"eval_runtime": 178.8662,
|
| 93 |
+
"eval_samples_per_second": 6.513,
|
| 94 |
+
"eval_steps_per_second": 6.513,
|
| 95 |
+
"step": 100
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.16792290811945426,
|
| 99 |
+
"grad_norm": 0.4413648843765259,
|
| 100 |
+
"learning_rate": 3.353658536585366e-05,
|
| 101 |
+
"loss": 0.1087,
|
| 102 |
+
"step": 110
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.18318862703940464,
|
| 106 |
+
"grad_norm": 0.8687300682067871,
|
| 107 |
+
"learning_rate": 3.6585365853658535e-05,
|
| 108 |
+
"loss": 0.096,
|
| 109 |
+
"step": 120
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.19845434595935502,
|
| 113 |
+
"grad_norm": 0.6343626379966736,
|
| 114 |
+
"learning_rate": 3.9634146341463416e-05,
|
| 115 |
+
"loss": 0.0853,
|
| 116 |
+
"step": 130
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.21372006487930542,
|
| 120 |
+
"grad_norm": 0.7491863369941711,
|
| 121 |
+
"learning_rate": 4.26829268292683e-05,
|
| 122 |
+
"loss": 0.0767,
|
| 123 |
+
"step": 140
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.2289857837992558,
|
| 127 |
+
"grad_norm": 0.495426744222641,
|
| 128 |
+
"learning_rate": 4.573170731707318e-05,
|
| 129 |
+
"loss": 0.0619,
|
| 130 |
+
"step": 150
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.2289857837992558,
|
| 134 |
+
"eval_loss": 0.06294012069702148,
|
| 135 |
+
"eval_runtime": 178.9812,
|
| 136 |
+
"eval_samples_per_second": 6.509,
|
| 137 |
+
"eval_steps_per_second": 6.509,
|
| 138 |
+
"step": 150
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.24425150271920618,
|
| 142 |
+
"grad_norm": 0.7597019076347351,
|
| 143 |
+
"learning_rate": 4.878048780487805e-05,
|
| 144 |
+
"loss": 0.0873,
|
| 145 |
+
"step": 160
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.2595172216391566,
|
| 149 |
+
"grad_norm": 0.804664671421051,
|
| 150 |
+
"learning_rate": 5.182926829268293e-05,
|
| 151 |
+
"loss": 0.0739,
|
| 152 |
+
"step": 170
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.27478294055910696,
|
| 156 |
+
"grad_norm": 0.3810129165649414,
|
| 157 |
+
"learning_rate": 5.487804878048781e-05,
|
| 158 |
+
"loss": 0.0792,
|
| 159 |
+
"step": 180
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.29004865947905734,
|
| 163 |
+
"grad_norm": 0.6029999852180481,
|
| 164 |
+
"learning_rate": 5.792682926829268e-05,
|
| 165 |
+
"loss": 0.0695,
|
| 166 |
+
"step": 190
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.3053143783990077,
|
| 170 |
+
"grad_norm": 0.6588765382766724,
|
| 171 |
+
"learning_rate": 6.097560975609756e-05,
|
| 172 |
+
"loss": 0.0535,
|
| 173 |
+
"step": 200
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.3053143783990077,
|
| 177 |
+
"eval_loss": 0.05500848591327667,
|
| 178 |
+
"eval_runtime": 179.0405,
|
| 179 |
+
"eval_samples_per_second": 6.507,
|
| 180 |
+
"eval_steps_per_second": 6.507,
|
| 181 |
+
"step": 200
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.3205800973189581,
|
| 185 |
+
"grad_norm": 0.5788701772689819,
|
| 186 |
+
"learning_rate": 6.402439024390244e-05,
|
| 187 |
+
"loss": 0.0593,
|
| 188 |
+
"step": 210
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.3358458162389085,
|
| 192 |
+
"grad_norm": 0.7792841196060181,
|
| 193 |
+
"learning_rate": 6.707317073170732e-05,
|
| 194 |
+
"loss": 0.0566,
|
| 195 |
+
"step": 220
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.3511115351588589,
|
| 199 |
+
"grad_norm": 0.7082734704017639,
|
| 200 |
+
"learning_rate": 7.012195121951219e-05,
|
| 201 |
+
"loss": 0.0449,
|
| 202 |
+
"step": 230
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.3663772540788093,
|
| 206 |
+
"grad_norm": 0.5391858816146851,
|
| 207 |
+
"learning_rate": 7.317073170731707e-05,
|
| 208 |
+
"loss": 0.0636,
|
| 209 |
+
"step": 240
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.38164297299875966,
|
| 213 |
+
"grad_norm": 0.47337889671325684,
|
| 214 |
+
"learning_rate": 7.621951219512195e-05,
|
| 215 |
+
"loss": 0.0576,
|
| 216 |
+
"step": 250
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.38164297299875966,
|
| 220 |
+
"eval_loss": 0.04678180441260338,
|
| 221 |
+
"eval_runtime": 178.9876,
|
| 222 |
+
"eval_samples_per_second": 6.509,
|
| 223 |
+
"eval_steps_per_second": 6.509,
|
| 224 |
+
"step": 250
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.39690869191871003,
|
| 228 |
+
"grad_norm": 0.7037196159362793,
|
| 229 |
+
"learning_rate": 7.926829268292683e-05,
|
| 230 |
+
"loss": 0.0537,
|
| 231 |
+
"step": 260
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.4121744108386604,
|
| 235 |
+
"grad_norm": 0.44716084003448486,
|
| 236 |
+
"learning_rate": 8.231707317073171e-05,
|
| 237 |
+
"loss": 0.0513,
|
| 238 |
+
"step": 270
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.42744012975861084,
|
| 242 |
+
"grad_norm": 0.288339227437973,
|
| 243 |
+
"learning_rate": 8.53658536585366e-05,
|
| 244 |
+
"loss": 0.0524,
|
| 245 |
+
"step": 280
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.4427058486785612,
|
| 249 |
+
"grad_norm": 0.5624875426292419,
|
| 250 |
+
"learning_rate": 8.841463414634147e-05,
|
| 251 |
+
"loss": 0.0575,
|
| 252 |
+
"step": 290
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.4579715675985116,
|
| 256 |
+
"grad_norm": 0.3156270682811737,
|
| 257 |
+
"learning_rate": 9.146341463414635e-05,
|
| 258 |
+
"loss": 0.0501,
|
| 259 |
+
"step": 300
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 0.4579715675985116,
|
| 263 |
+
"eval_loss": 0.046911776065826416,
|
| 264 |
+
"eval_runtime": 178.9736,
|
| 265 |
+
"eval_samples_per_second": 6.509,
|
| 266 |
+
"eval_steps_per_second": 6.509,
|
| 267 |
+
"step": 300
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.473237286518462,
|
| 271 |
+
"grad_norm": 0.5870501399040222,
|
| 272 |
+
"learning_rate": 9.451219512195122e-05,
|
| 273 |
+
"loss": 0.0536,
|
| 274 |
+
"step": 310
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.48850300543841235,
|
| 278 |
+
"grad_norm": 0.27398020029067993,
|
| 279 |
+
"learning_rate": 9.75609756097561e-05,
|
| 280 |
+
"loss": 0.0369,
|
| 281 |
+
"step": 320
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.5037687243583627,
|
| 285 |
+
"grad_norm": 0.6370400190353394,
|
| 286 |
+
"learning_rate": 9.999988635788465e-05,
|
| 287 |
+
"loss": 0.0474,
|
| 288 |
+
"step": 330
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.5190344432783132,
|
| 292 |
+
"grad_norm": 0.6367189288139343,
|
| 293 |
+
"learning_rate": 9.999590893808788e-05,
|
| 294 |
+
"loss": 0.0455,
|
| 295 |
+
"step": 340
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.5343001621982635,
|
| 299 |
+
"grad_norm": 0.47603678703308105,
|
| 300 |
+
"learning_rate": 9.998624992909386e-05,
|
| 301 |
+
"loss": 0.0456,
|
| 302 |
+
"step": 350
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.5343001621982635,
|
| 306 |
+
"eval_loss": 0.042300350964069366,
|
| 307 |
+
"eval_runtime": 178.9958,
|
| 308 |
+
"eval_samples_per_second": 6.509,
|
| 309 |
+
"eval_steps_per_second": 6.509,
|
| 310 |
+
"step": 350
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.5495658811182139,
|
| 314 |
+
"grad_norm": 0.17798028886318207,
|
| 315 |
+
"learning_rate": 9.997091042856284e-05,
|
| 316 |
+
"loss": 0.0413,
|
| 317 |
+
"step": 360
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.5648316000381643,
|
| 321 |
+
"grad_norm": 0.2773096561431885,
|
| 322 |
+
"learning_rate": 9.994989217969224e-05,
|
| 323 |
+
"loss": 0.0513,
|
| 324 |
+
"step": 370
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.5800973189581147,
|
| 328 |
+
"grad_norm": 0.7576242685317993,
|
| 329 |
+
"learning_rate": 9.992319757101863e-05,
|
| 330 |
+
"loss": 0.0538,
|
| 331 |
+
"step": 380
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.5953630378780651,
|
| 335 |
+
"grad_norm": 0.39998742938041687,
|
| 336 |
+
"learning_rate": 9.98908296361462e-05,
|
| 337 |
+
"loss": 0.0593,
|
| 338 |
+
"step": 390
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.6106287567980154,
|
| 342 |
+
"grad_norm": 0.32975825667381287,
|
| 343 |
+
"learning_rate": 9.98527920534021e-05,
|
| 344 |
+
"loss": 0.0487,
|
| 345 |
+
"step": 400
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.6106287567980154,
|
| 349 |
+
"eval_loss": 0.03924345597624779,
|
| 350 |
+
"eval_runtime": 179.019,
|
| 351 |
+
"eval_samples_per_second": 6.508,
|
| 352 |
+
"eval_steps_per_second": 6.508,
|
| 353 |
+
"step": 400
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.6258944757179659,
|
| 357 |
+
"grad_norm": 0.4215024709701538,
|
| 358 |
+
"learning_rate": 9.980908914541844e-05,
|
| 359 |
+
"loss": 0.0436,
|
| 360 |
+
"step": 410
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.6411601946379162,
|
| 364 |
+
"grad_norm": 0.27699562907218933,
|
| 365 |
+
"learning_rate": 9.975972587864095e-05,
|
| 366 |
+
"loss": 0.0507,
|
| 367 |
+
"step": 420
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.6564259135578666,
|
| 371 |
+
"grad_norm": 0.559887170791626,
|
| 372 |
+
"learning_rate": 9.970470786276467e-05,
|
| 373 |
+
"loss": 0.0378,
|
| 374 |
+
"step": 430
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.671691632477817,
|
| 378 |
+
"grad_norm": 0.42969998717308044,
|
| 379 |
+
"learning_rate": 9.964404135009648e-05,
|
| 380 |
+
"loss": 0.0495,
|
| 381 |
+
"step": 440
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.6869573513977674,
|
| 385 |
+
"grad_norm": 0.2953483462333679,
|
| 386 |
+
"learning_rate": 9.957773323484454e-05,
|
| 387 |
+
"loss": 0.0543,
|
| 388 |
+
"step": 450
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.6869573513977674,
|
| 392 |
+
"eval_loss": 0.03886280581355095,
|
| 393 |
+
"eval_runtime": 179.0976,
|
| 394 |
+
"eval_samples_per_second": 6.505,
|
| 395 |
+
"eval_steps_per_second": 6.505,
|
| 396 |
+
"step": 450
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.7022230703177178,
|
| 400 |
+
"grad_norm": 0.2300979197025299,
|
| 401 |
+
"learning_rate": 9.950579105233483e-05,
|
| 402 |
+
"loss": 0.0386,
|
| 403 |
+
"step": 460
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.7174887892376681,
|
| 407 |
+
"grad_norm": 0.2619139552116394,
|
| 408 |
+
"learning_rate": 9.94282229781548e-05,
|
| 409 |
+
"loss": 0.0402,
|
| 410 |
+
"step": 470
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.7327545081576186,
|
| 414 |
+
"grad_norm": 0.49340057373046875,
|
| 415 |
+
"learning_rate": 9.934503782722438e-05,
|
| 416 |
+
"loss": 0.0444,
|
| 417 |
+
"step": 480
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.748020227077569,
|
| 421 |
+
"grad_norm": 0.23474624752998352,
|
| 422 |
+
"learning_rate": 9.925624505279411e-05,
|
| 423 |
+
"loss": 0.0383,
|
| 424 |
+
"step": 490
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.7632859459975193,
|
| 428 |
+
"grad_norm": 0.12562145292758942,
|
| 429 |
+
"learning_rate": 9.916185474537098e-05,
|
| 430 |
+
"loss": 0.0298,
|
| 431 |
+
"step": 500
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.7632859459975193,
|
| 435 |
+
"eval_loss": 0.03485063835978508,
|
| 436 |
+
"eval_runtime": 179.1055,
|
| 437 |
+
"eval_samples_per_second": 6.505,
|
| 438 |
+
"eval_steps_per_second": 6.505,
|
| 439 |
+
"step": 500
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.7785516649174697,
|
| 443 |
+
"grad_norm": 0.33692803978919983,
|
| 444 |
+
"learning_rate": 9.906187763157168e-05,
|
| 445 |
+
"loss": 0.0472,
|
| 446 |
+
"step": 510
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.7938173838374201,
|
| 450 |
+
"grad_norm": 0.28782883286476135,
|
| 451 |
+
"learning_rate": 9.895632507290362e-05,
|
| 452 |
+
"loss": 0.0479,
|
| 453 |
+
"step": 520
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.8090831027573705,
|
| 457 |
+
"grad_norm": 0.2520039677619934,
|
| 458 |
+
"learning_rate": 9.884520906447379e-05,
|
| 459 |
+
"loss": 0.0359,
|
| 460 |
+
"step": 530
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.8243488216773208,
|
| 464 |
+
"grad_norm": 0.3067379295825958,
|
| 465 |
+
"learning_rate": 9.872854223362562e-05,
|
| 466 |
+
"loss": 0.035,
|
| 467 |
+
"step": 540
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.8396145405972713,
|
| 471 |
+
"grad_norm": 0.5226966738700867,
|
| 472 |
+
"learning_rate": 9.860633783850406e-05,
|
| 473 |
+
"loss": 0.0378,
|
| 474 |
+
"step": 550
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.8396145405972713,
|
| 478 |
+
"eval_loss": 0.03473576903343201,
|
| 479 |
+
"eval_runtime": 179.0927,
|
| 480 |
+
"eval_samples_per_second": 6.505,
|
| 481 |
+
"eval_steps_per_second": 6.505,
|
| 482 |
+
"step": 550
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.8548802595172217,
|
| 486 |
+
"grad_norm": 0.16309522092342377,
|
| 487 |
+
"learning_rate": 9.847860976654879e-05,
|
| 488 |
+
"loss": 0.0404,
|
| 489 |
+
"step": 560
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.870145978437172,
|
| 493 |
+
"grad_norm": 0.18132278323173523,
|
| 494 |
+
"learning_rate": 9.834537253291616e-05,
|
| 495 |
+
"loss": 0.0401,
|
| 496 |
+
"step": 570
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.8854116973571224,
|
| 500 |
+
"grad_norm": 0.583713948726654,
|
| 501 |
+
"learning_rate": 9.820664127882957e-05,
|
| 502 |
+
"loss": 0.0468,
|
| 503 |
+
"step": 580
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 0.9006774162770728,
|
| 507 |
+
"grad_norm": 0.3539969325065613,
|
| 508 |
+
"learning_rate": 9.806243176985888e-05,
|
| 509 |
+
"loss": 0.0437,
|
| 510 |
+
"step": 590
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 0.9159431351970232,
|
| 514 |
+
"grad_norm": 0.3411082923412323,
|
| 515 |
+
"learning_rate": 9.791276039412875e-05,
|
| 516 |
+
"loss": 0.0387,
|
| 517 |
+
"step": 600
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 0.9159431351970232,
|
| 521 |
+
"eval_loss": 0.032861627638339996,
|
| 522 |
+
"eval_runtime": 179.1835,
|
| 523 |
+
"eval_samples_per_second": 6.502,
|
| 524 |
+
"eval_steps_per_second": 6.502,
|
| 525 |
+
"step": 600
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.9312088541169735,
|
| 529 |
+
"grad_norm": 0.22567597031593323,
|
| 530 |
+
"learning_rate": 9.775764416045628e-05,
|
| 531 |
+
"loss": 0.0502,
|
| 532 |
+
"step": 610
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.946474573036924,
|
| 536 |
+
"grad_norm": 0.29538026452064514,
|
| 537 |
+
"learning_rate": 9.759710069641814e-05,
|
| 538 |
+
"loss": 0.042,
|
| 539 |
+
"step": 620
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.9617402919568744,
|
| 543 |
+
"grad_norm": 0.20513112843036652,
|
| 544 |
+
"learning_rate": 9.743114824634734e-05,
|
| 545 |
+
"loss": 0.0283,
|
| 546 |
+
"step": 630
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.9770060108768247,
|
| 550 |
+
"grad_norm": 0.26253455877304077,
|
| 551 |
+
"learning_rate": 9.725980566925989e-05,
|
| 552 |
+
"loss": 0.0367,
|
| 553 |
+
"step": 640
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.9922717297967751,
|
| 557 |
+
"grad_norm": 0.2190350592136383,
|
| 558 |
+
"learning_rate": 9.708309243671165e-05,
|
| 559 |
+
"loss": 0.0275,
|
| 560 |
+
"step": 650
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.9922717297967751,
|
| 564 |
+
"eval_loss": 0.035241108387708664,
|
| 565 |
+
"eval_runtime": 179.2823,
|
| 566 |
+
"eval_samples_per_second": 6.498,
|
| 567 |
+
"eval_steps_per_second": 6.498,
|
| 568 |
+
"step": 650
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 1.0075374487167255,
|
| 572 |
+
"grad_norm": 0.09830069541931152,
|
| 573 |
+
"learning_rate": 9.690102863058563e-05,
|
| 574 |
+
"loss": 0.0321,
|
| 575 |
+
"step": 660
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 1.0228031676366758,
|
| 579 |
+
"grad_norm": 0.2949357032775879,
|
| 580 |
+
"learning_rate": 9.67136349408098e-05,
|
| 581 |
+
"loss": 0.0293,
|
| 582 |
+
"step": 670
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 1.0380688865566263,
|
| 586 |
+
"grad_norm": 0.10271728783845901,
|
| 587 |
+
"learning_rate": 9.652093266300583e-05,
|
| 588 |
+
"loss": 0.0309,
|
| 589 |
+
"step": 680
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 1.0533346054765766,
|
| 593 |
+
"grad_norm": 0.2911938726902008,
|
| 594 |
+
"learning_rate": 9.632294369606916e-05,
|
| 595 |
+
"loss": 0.0213,
|
| 596 |
+
"step": 690
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 1.068600324396527,
|
| 600 |
+
"grad_norm": 0.23335903882980347,
|
| 601 |
+
"learning_rate": 9.61196905396802e-05,
|
| 602 |
+
"loss": 0.0348,
|
| 603 |
+
"step": 700
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 1.068600324396527,
|
| 607 |
+
"eval_loss": 0.03389936685562134,
|
| 608 |
+
"eval_runtime": 179.1248,
|
| 609 |
+
"eval_samples_per_second": 6.504,
|
| 610 |
+
"eval_steps_per_second": 6.504,
|
| 611 |
+
"step": 700
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.0838660433164775,
|
| 615 |
+
"grad_norm": 0.26263928413391113,
|
| 616 |
+
"learning_rate": 9.591119629174764e-05,
|
| 617 |
+
"loss": 0.0398,
|
| 618 |
+
"step": 710
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.0991317622364278,
|
| 622 |
+
"grad_norm": 0.15275321900844574,
|
| 623 |
+
"learning_rate": 9.569748464578343e-05,
|
| 624 |
+
"loss": 0.0229,
|
| 625 |
+
"step": 720
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.1143974811563782,
|
| 629 |
+
"grad_norm": 0.23484571278095245,
|
| 630 |
+
"learning_rate": 9.54785798882103e-05,
|
| 631 |
+
"loss": 0.029,
|
| 632 |
+
"step": 730
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.1296632000763287,
|
| 636 |
+
"grad_norm": 0.18005479872226715,
|
| 637 |
+
"learning_rate": 9.525450689560181e-05,
|
| 638 |
+
"loss": 0.0266,
|
| 639 |
+
"step": 740
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.144928918996279,
|
| 643 |
+
"grad_norm": 0.17082622647285461,
|
| 644 |
+
"learning_rate": 9.502529113185532e-05,
|
| 645 |
+
"loss": 0.0346,
|
| 646 |
+
"step": 750
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.144928918996279,
|
| 650 |
+
"eval_loss": 0.03384435176849365,
|
| 651 |
+
"eval_runtime": 179.1418,
|
| 652 |
+
"eval_samples_per_second": 6.503,
|
| 653 |
+
"eval_steps_per_second": 6.503,
|
| 654 |
+
"step": 750
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.1601946379162293,
|
| 658 |
+
"grad_norm": 0.31557226181030273,
|
| 659 |
+
"learning_rate": 9.479095864529828e-05,
|
| 660 |
+
"loss": 0.0297,
|
| 661 |
+
"step": 760
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.1754603568361797,
|
| 665 |
+
"grad_norm": 0.17261050641536713,
|
| 666 |
+
"learning_rate": 9.455153606572806e-05,
|
| 667 |
+
"loss": 0.0242,
|
| 668 |
+
"step": 770
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.1907260757561302,
|
| 672 |
+
"grad_norm": 0.25501230359077454,
|
| 673 |
+
"learning_rate": 9.430705060138569e-05,
|
| 674 |
+
"loss": 0.0325,
|
| 675 |
+
"step": 780
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.2059917946760805,
|
| 679 |
+
"grad_norm": 0.47437065839767456,
|
| 680 |
+
"learning_rate": 9.405753003586395e-05,
|
| 681 |
+
"loss": 0.0288,
|
| 682 |
+
"step": 790
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.2212575135960309,
|
| 686 |
+
"grad_norm": 0.20840288698673248,
|
| 687 |
+
"learning_rate": 9.38030027249499e-05,
|
| 688 |
+
"loss": 0.0321,
|
| 689 |
+
"step": 800
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.2212575135960309,
|
| 693 |
+
"eval_loss": 0.033740561455488205,
|
| 694 |
+
"eval_runtime": 179.1979,
|
| 695 |
+
"eval_samples_per_second": 6.501,
|
| 696 |
+
"eval_steps_per_second": 6.501,
|
| 697 |
+
"step": 800
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 1.2365232325159814,
|
| 701 |
+
"grad_norm": 0.24225717782974243,
|
| 702 |
+
"learning_rate": 9.354349759340263e-05,
|
| 703 |
+
"loss": 0.0278,
|
| 704 |
+
"step": 810
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 1.2517889514359317,
|
| 708 |
+
"grad_norm": 0.20259130001068115,
|
| 709 |
+
"learning_rate": 9.327904413166615e-05,
|
| 710 |
+
"loss": 0.0291,
|
| 711 |
+
"step": 820
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 1.267054670355882,
|
| 715 |
+
"grad_norm": 0.4767257273197174,
|
| 716 |
+
"learning_rate": 9.300967239251798e-05,
|
| 717 |
+
"loss": 0.0374,
|
| 718 |
+
"step": 830
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 1.2823203892758324,
|
| 722 |
+
"grad_norm": 0.20219506323337555,
|
| 723 |
+
"learning_rate": 9.27354129876541e-05,
|
| 724 |
+
"loss": 0.03,
|
| 725 |
+
"step": 840
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 1.297586108195783,
|
| 729 |
+
"grad_norm": 0.19528479874134064,
|
| 730 |
+
"learning_rate": 9.245629708421008e-05,
|
| 731 |
+
"loss": 0.0288,
|
| 732 |
+
"step": 850
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 1.297586108195783,
|
| 736 |
+
"eval_loss": 0.0333208329975605,
|
| 737 |
+
"eval_runtime": 179.2291,
|
| 738 |
+
"eval_samples_per_second": 6.5,
|
| 739 |
+
"eval_steps_per_second": 6.5,
|
| 740 |
+
"step": 850
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 1.3128518271157332,
|
| 744 |
+
"grad_norm": 0.3612363934516907,
|
| 745 |
+
"learning_rate": 9.217235640121926e-05,
|
| 746 |
+
"loss": 0.0311,
|
| 747 |
+
"step": 860
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 1.3281175460356835,
|
| 751 |
+
"grad_norm": 0.4072886109352112,
|
| 752 |
+
"learning_rate": 9.188362320600812e-05,
|
| 753 |
+
"loss": 0.0371,
|
| 754 |
+
"step": 870
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 1.343383264955634,
|
| 758 |
+
"grad_norm": 0.2643483281135559,
|
| 759 |
+
"learning_rate": 9.159013031052943e-05,
|
| 760 |
+
"loss": 0.0266,
|
| 761 |
+
"step": 880
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 1.3586489838755844,
|
| 765 |
+
"grad_norm": 0.30413269996643066,
|
| 766 |
+
"learning_rate": 9.129191106763346e-05,
|
| 767 |
+
"loss": 0.0276,
|
| 768 |
+
"step": 890
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 1.3739147027955347,
|
| 772 |
+
"grad_norm": 0.23679038882255554,
|
| 773 |
+
"learning_rate": 9.098899936727771e-05,
|
| 774 |
+
"loss": 0.028,
|
| 775 |
+
"step": 900
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 1.3739147027955347,
|
| 779 |
+
"eval_loss": 0.03594866767525673,
|
| 780 |
+
"eval_runtime": 179.217,
|
| 781 |
+
"eval_samples_per_second": 6.501,
|
| 782 |
+
"eval_steps_per_second": 6.501,
|
| 783 |
+
"step": 900
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 1.3891804217154853,
|
| 787 |
+
"grad_norm": 0.4948261082172394,
|
| 788 |
+
"learning_rate": 9.068142963267558e-05,
|
| 789 |
+
"loss": 0.0262,
|
| 790 |
+
"step": 910
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 1.4044461406354356,
|
| 794 |
+
"grad_norm": 0.27103114128112793,
|
| 795 |
+
"learning_rate": 9.036923681638463e-05,
|
| 796 |
+
"loss": 0.0291,
|
| 797 |
+
"step": 920
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 1.419711859555386,
|
| 801 |
+
"grad_norm": 0.17580902576446533,
|
| 802 |
+
"learning_rate": 9.00524563963343e-05,
|
| 803 |
+
"loss": 0.0205,
|
| 804 |
+
"step": 930
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 1.4349775784753362,
|
| 808 |
+
"grad_norm": 0.22460690140724182,
|
| 809 |
+
"learning_rate": 8.973112437179436e-05,
|
| 810 |
+
"loss": 0.033,
|
| 811 |
+
"step": 940
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 1.4502432973952868,
|
| 815 |
+
"grad_norm": 0.16176696121692657,
|
| 816 |
+
"learning_rate": 8.940527725928383e-05,
|
| 817 |
+
"loss": 0.0277,
|
| 818 |
+
"step": 950
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 1.4502432973952868,
|
| 822 |
+
"eval_loss": 0.03296082094311714,
|
| 823 |
+
"eval_runtime": 179.256,
|
| 824 |
+
"eval_samples_per_second": 6.499,
|
| 825 |
+
"eval_steps_per_second": 6.499,
|
| 826 |
+
"step": 950
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 1.4655090163152371,
|
| 830 |
+
"grad_norm": 0.16683737933635712,
|
| 831 |
+
"learning_rate": 8.90749520884212e-05,
|
| 832 |
+
"loss": 0.028,
|
| 833 |
+
"step": 960
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 1.4807747352351874,
|
| 837 |
+
"grad_norm": 0.23072558641433716,
|
| 838 |
+
"learning_rate": 8.874018639771637e-05,
|
| 839 |
+
"loss": 0.031,
|
| 840 |
+
"step": 970
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 1.4960404541551378,
|
| 844 |
+
"grad_norm": 0.18204113841056824,
|
| 845 |
+
"learning_rate": 8.840101823030471e-05,
|
| 846 |
+
"loss": 0.0261,
|
| 847 |
+
"step": 980
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 1.5113061730750883,
|
| 851 |
+
"grad_norm": 0.2924092411994934,
|
| 852 |
+
"learning_rate": 8.805748612962382e-05,
|
| 853 |
+
"loss": 0.0295,
|
| 854 |
+
"step": 990
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 1.5265718919950386,
|
| 858 |
+
"grad_norm": 0.1391419917345047,
|
| 859 |
+
"learning_rate": 8.77096291350334e-05,
|
| 860 |
+
"loss": 0.0202,
|
| 861 |
+
"step": 1000
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 1.5265718919950386,
|
| 865 |
+
"eval_loss": 0.03339965641498566,
|
| 866 |
+
"eval_runtime": 179.5613,
|
| 867 |
+
"eval_samples_per_second": 6.488,
|
| 868 |
+
"eval_steps_per_second": 6.488,
|
| 869 |
+
"step": 1000
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 1.541837610914989,
|
| 873 |
+
"grad_norm": 0.2946327030658722,
|
| 874 |
+
"learning_rate": 8.735748677737874e-05,
|
| 875 |
+
"loss": 0.0299,
|
| 876 |
+
"step": 1010
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 1.5571033298349395,
|
| 880 |
+
"grad_norm": 0.8059619069099426,
|
| 881 |
+
"learning_rate": 8.700109907449845e-05,
|
| 882 |
+
"loss": 0.0223,
|
| 883 |
+
"step": 1020
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 1.5723690487548898,
|
| 887 |
+
"grad_norm": 0.09737138450145721,
|
| 888 |
+
"learning_rate": 8.66405065266768e-05,
|
| 889 |
+
"loss": 0.0251,
|
| 890 |
+
"step": 1030
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 1.5876347676748401,
|
| 894 |
+
"grad_norm": 0.20474199950695038,
|
| 895 |
+
"learning_rate": 8.627575011204115e-05,
|
| 896 |
+
"loss": 0.0241,
|
| 897 |
+
"step": 1040
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 1.6029004865947907,
|
| 901 |
+
"grad_norm": 0.13863246142864227,
|
| 902 |
+
"learning_rate": 8.590687128190516e-05,
|
| 903 |
+
"loss": 0.0291,
|
| 904 |
+
"step": 1050
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 1.6029004865947907,
|
| 908 |
+
"eval_loss": 0.03433850780129433,
|
| 909 |
+
"eval_runtime": 179.7512,
|
| 910 |
+
"eval_samples_per_second": 6.481,
|
| 911 |
+
"eval_steps_per_second": 6.481,
|
| 912 |
+
"step": 1050
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 1.618166205514741,
|
| 916 |
+
"grad_norm": 0.12294421344995499,
|
| 917 |
+
"learning_rate": 8.553391195605833e-05,
|
| 918 |
+
"loss": 0.0247,
|
| 919 |
+
"step": 1060
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 1.6334319244346913,
|
| 923 |
+
"grad_norm": 0.2797018587589264,
|
| 924 |
+
"learning_rate": 8.515691451800205e-05,
|
| 925 |
+
"loss": 0.0426,
|
| 926 |
+
"step": 1070
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 1.6486976433546419,
|
| 930 |
+
"grad_norm": 0.19925975799560547,
|
| 931 |
+
"learning_rate": 8.477592181013316e-05,
|
| 932 |
+
"loss": 0.0237,
|
| 933 |
+
"step": 1080
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 1.663963362274592,
|
| 937 |
+
"grad_norm": 0.16685841977596283,
|
| 938 |
+
"learning_rate": 8.439097712887531e-05,
|
| 939 |
+
"loss": 0.0274,
|
| 940 |
+
"step": 1090
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.6792290811945425,
|
| 944 |
+
"grad_norm": 0.2913149893283844,
|
| 945 |
+
"learning_rate": 8.400212421975865e-05,
|
| 946 |
+
"loss": 0.0402,
|
| 947 |
+
"step": 1100
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 1.6792290811945425,
|
| 951 |
+
"eval_loss": 0.03206111863255501,
|
| 952 |
+
"eval_runtime": 179.642,
|
| 953 |
+
"eval_samples_per_second": 6.485,
|
| 954 |
+
"eval_steps_per_second": 6.485,
|
| 955 |
+
"step": 1100
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.694494800114493,
|
| 959 |
+
"grad_norm": 0.19945311546325684,
|
| 960 |
+
"learning_rate": 8.360940727244859e-05,
|
| 961 |
+
"loss": 0.0343,
|
| 962 |
+
"step": 1110
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.7097605190344431,
|
| 966 |
+
"grad_norm": 0.20246616005897522,
|
| 967 |
+
"learning_rate": 8.321287091572403e-05,
|
| 968 |
+
"loss": 0.0233,
|
| 969 |
+
"step": 1120
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.7250262379543937,
|
| 973 |
+
"grad_norm": 0.455074667930603,
|
| 974 |
+
"learning_rate": 8.281256021240566e-05,
|
| 975 |
+
"loss": 0.0283,
|
| 976 |
+
"step": 1130
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.740291956874344,
|
| 980 |
+
"grad_norm": 0.1479114294052124,
|
| 981 |
+
"learning_rate": 8.240852065423506e-05,
|
| 982 |
+
"loss": 0.0351,
|
| 983 |
+
"step": 1140
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.7555576757942943,
|
| 987 |
+
"grad_norm": 0.3095378577709198,
|
| 988 |
+
"learning_rate": 8.20007981567048e-05,
|
| 989 |
+
"loss": 0.0268,
|
| 990 |
+
"step": 1150
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.7555576757942943,
|
| 994 |
+
"eval_loss": 0.03280867636203766,
|
| 995 |
+
"eval_runtime": 179.7524,
|
| 996 |
+
"eval_samples_per_second": 6.481,
|
| 997 |
+
"eval_steps_per_second": 6.481,
|
| 998 |
+
"step": 1150
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 1.7708233947142449,
|
| 1002 |
+
"grad_norm": 0.1850660890340805,
|
| 1003 |
+
"learning_rate": 8.158943905384082e-05,
|
| 1004 |
+
"loss": 0.0322,
|
| 1005 |
+
"step": 1160
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 1.7860891136341952,
|
| 1009 |
+
"grad_norm": 0.23737244307994843,
|
| 1010 |
+
"learning_rate": 8.117449009293668e-05,
|
| 1011 |
+
"loss": 0.0291,
|
| 1012 |
+
"step": 1170
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 1.8013548325541455,
|
| 1016 |
+
"grad_norm": 0.18103042244911194,
|
| 1017 |
+
"learning_rate": 8.075599842924139e-05,
|
| 1018 |
+
"loss": 0.0276,
|
| 1019 |
+
"step": 1180
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 1.816620551474096,
|
| 1023 |
+
"grad_norm": 0.18441970646381378,
|
| 1024 |
+
"learning_rate": 8.033401162060049e-05,
|
| 1025 |
+
"loss": 0.0343,
|
| 1026 |
+
"step": 1190
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 1.8318862703940464,
|
| 1030 |
+
"grad_norm": 0.36745738983154297,
|
| 1031 |
+
"learning_rate": 7.990857762205157e-05,
|
| 1032 |
+
"loss": 0.0411,
|
| 1033 |
+
"step": 1200
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 1.8318862703940464,
|
| 1037 |
+
"eval_loss": 0.032041117548942566,
|
| 1038 |
+
"eval_runtime": 179.8085,
|
| 1039 |
+
"eval_samples_per_second": 6.479,
|
| 1040 |
+
"eval_steps_per_second": 6.479,
|
| 1041 |
+
"step": 1200
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 1.8471519893139967,
|
| 1045 |
+
"grad_norm": 0.28123798966407776,
|
| 1046 |
+
"learning_rate": 7.947974478037468e-05,
|
| 1047 |
+
"loss": 0.0355,
|
| 1048 |
+
"step": 1210
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 1.8624177082339473,
|
| 1052 |
+
"grad_norm": 0.6014788150787354,
|
| 1053 |
+
"learning_rate": 7.904756182859797e-05,
|
| 1054 |
+
"loss": 0.0235,
|
| 1055 |
+
"step": 1220
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 1.8776834271538976,
|
| 1059 |
+
"grad_norm": 0.11423056572675705,
|
| 1060 |
+
"learning_rate": 7.861207788045984e-05,
|
| 1061 |
+
"loss": 0.0327,
|
| 1062 |
+
"step": 1230
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 1.892949146073848,
|
| 1066 |
+
"grad_norm": 0.33343955874443054,
|
| 1067 |
+
"learning_rate": 7.817334242482738e-05,
|
| 1068 |
+
"loss": 0.028,
|
| 1069 |
+
"step": 1240
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 1.9082148649937984,
|
| 1073 |
+
"grad_norm": 0.12100326269865036,
|
| 1074 |
+
"learning_rate": 7.773140532007262e-05,
|
| 1075 |
+
"loss": 0.0262,
|
| 1076 |
+
"step": 1250
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 1.9082148649937984,
|
| 1080 |
+
"eval_loss": 0.028858734294772148,
|
| 1081 |
+
"eval_runtime": 179.691,
|
| 1082 |
+
"eval_samples_per_second": 6.483,
|
| 1083 |
+
"eval_steps_per_second": 6.483,
|
| 1084 |
+
"step": 1250
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 1.9234805839137485,
|
| 1088 |
+
"grad_norm": 0.1283182054758072,
|
| 1089 |
+
"learning_rate": 7.728631678840638e-05,
|
| 1090 |
+
"loss": 0.0267,
|
| 1091 |
+
"step": 1260
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 1.938746302833699,
|
| 1095 |
+
"grad_norm": 0.11831828206777573,
|
| 1096 |
+
"learning_rate": 7.683812741017112e-05,
|
| 1097 |
+
"loss": 0.0252,
|
| 1098 |
+
"step": 1270
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 1.9540120217536494,
|
| 1102 |
+
"grad_norm": 0.33695539832115173,
|
| 1103 |
+
"learning_rate": 7.638688811809274e-05,
|
| 1104 |
+
"loss": 0.0294,
|
| 1105 |
+
"step": 1280
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 1.9692777406735997,
|
| 1109 |
+
"grad_norm": 0.19394966959953308,
|
| 1110 |
+
"learning_rate": 7.593265019149275e-05,
|
| 1111 |
+
"loss": 0.029,
|
| 1112 |
+
"step": 1290
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 1.9845434595935503,
|
| 1116 |
+
"grad_norm": 0.24795125424861908,
|
| 1117 |
+
"learning_rate": 7.547546525046073e-05,
|
| 1118 |
+
"loss": 0.0318,
|
| 1119 |
+
"step": 1300
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 1.9845434595935503,
|
| 1123 |
+
"eval_loss": 0.02917238511145115,
|
| 1124 |
+
"eval_runtime": 179.7965,
|
| 1125 |
+
"eval_samples_per_second": 6.48,
|
| 1126 |
+
"eval_steps_per_second": 6.48,
|
| 1127 |
+
"step": 1300
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 1.9998091785135006,
|
| 1131 |
+
"grad_norm": 0.08313370496034622,
|
| 1132 |
+
"learning_rate": 7.501538524998812e-05,
|
| 1133 |
+
"loss": 0.0305,
|
| 1134 |
+
"step": 1310
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 2.015074897433451,
|
| 1138 |
+
"grad_norm": 0.16452887654304504,
|
| 1139 |
+
"learning_rate": 7.455246247406406e-05,
|
| 1140 |
+
"loss": 0.0137,
|
| 1141 |
+
"step": 1320
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 2.0303406163534015,
|
| 1145 |
+
"grad_norm": 0.26041746139526367,
|
| 1146 |
+
"learning_rate": 7.408674952973382e-05,
|
| 1147 |
+
"loss": 0.0173,
|
| 1148 |
+
"step": 1330
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 2.0456063352733516,
|
| 1152 |
+
"grad_norm": 0.19397439062595367,
|
| 1153 |
+
"learning_rate": 7.361829934112036e-05,
|
| 1154 |
+
"loss": 0.0217,
|
| 1155 |
+
"step": 1340
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 2.060872054193302,
|
| 1159 |
+
"grad_norm": 0.19004268944263458,
|
| 1160 |
+
"learning_rate": 7.314716514341006e-05,
|
| 1161 |
+
"loss": 0.0159,
|
| 1162 |
+
"step": 1350
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 2.060872054193302,
|
| 1166 |
+
"eval_loss": 0.030632687732577324,
|
| 1167 |
+
"eval_runtime": 179.7659,
|
| 1168 |
+
"eval_samples_per_second": 6.481,
|
| 1169 |
+
"eval_steps_per_second": 6.481,
|
| 1170 |
+
"step": 1350
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 2.0761377731132526,
|
| 1174 |
+
"grad_norm": 0.2005777806043625,
|
| 1175 |
+
"learning_rate": 7.267340047680305e-05,
|
| 1176 |
+
"loss": 0.0168,
|
| 1177 |
+
"step": 1360
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 2.0914034920332027,
|
| 1181 |
+
"grad_norm": 0.2647518813610077,
|
| 1182 |
+
"learning_rate": 7.21970591804287e-05,
|
| 1183 |
+
"loss": 0.0159,
|
| 1184 |
+
"step": 1370
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 2.1066692109531533,
|
| 1188 |
+
"grad_norm": 0.27719810605049133,
|
| 1189 |
+
"learning_rate": 7.171819538622747e-05,
|
| 1190 |
+
"loss": 0.0202,
|
| 1191 |
+
"step": 1380
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 2.121934929873104,
|
| 1195 |
+
"grad_norm": 0.17780855298042297,
|
| 1196 |
+
"learning_rate": 7.123686351279914e-05,
|
| 1197 |
+
"loss": 0.0182,
|
| 1198 |
+
"step": 1390
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 2.137200648793054,
|
| 1202 |
+
"grad_norm": 0.2095697820186615,
|
| 1203 |
+
"learning_rate": 7.07531182592187e-05,
|
| 1204 |
+
"loss": 0.019,
|
| 1205 |
+
"step": 1400
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 2.137200648793054,
|
| 1209 |
+
"eval_loss": 0.031268153339624405,
|
| 1210 |
+
"eval_runtime": 179.7579,
|
| 1211 |
+
"eval_samples_per_second": 6.481,
|
| 1212 |
+
"eval_steps_per_second": 6.481,
|
| 1213 |
+
"step": 1400
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 2.1524663677130045,
|
| 1217 |
+
"grad_norm": 0.3520405888557434,
|
| 1218 |
+
"learning_rate": 7.026701459882026e-05,
|
| 1219 |
+
"loss": 0.0271,
|
| 1220 |
+
"step": 1410
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 2.167732086632955,
|
| 1224 |
+
"grad_norm": 0.16760867834091187,
|
| 1225 |
+
"learning_rate": 6.977860777294988e-05,
|
| 1226 |
+
"loss": 0.0193,
|
| 1227 |
+
"step": 1420
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 2.182997805552905,
|
| 1231 |
+
"grad_norm": 0.1556943655014038,
|
| 1232 |
+
"learning_rate": 6.92879532846878e-05,
|
| 1233 |
+
"loss": 0.017,
|
| 1234 |
+
"step": 1430
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 2.1982635244728557,
|
| 1238 |
+
"grad_norm": 0.17596006393432617,
|
| 1239 |
+
"learning_rate": 6.879510689254104e-05,
|
| 1240 |
+
"loss": 0.016,
|
| 1241 |
+
"step": 1440
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 2.213529243392806,
|
| 1245 |
+
"grad_norm": 0.18705613911151886,
|
| 1246 |
+
"learning_rate": 6.830012460410697e-05,
|
| 1247 |
+
"loss": 0.022,
|
| 1248 |
+
"step": 1450
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 2.213529243392806,
|
| 1252 |
+
"eval_loss": 0.03142455592751503,
|
| 1253 |
+
"eval_runtime": 179.7594,
|
| 1254 |
+
"eval_samples_per_second": 6.481,
|
| 1255 |
+
"eval_steps_per_second": 6.481,
|
| 1256 |
+
"step": 1450
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 2.2287949623127563,
|
| 1260 |
+
"grad_norm": 0.22514861822128296,
|
| 1261 |
+
"learning_rate": 6.780306266970851e-05,
|
| 1262 |
+
"loss": 0.0143,
|
| 1263 |
+
"step": 1460
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 2.244060681232707,
|
| 1267 |
+
"grad_norm": 0.3207738995552063,
|
| 1268 |
+
"learning_rate": 6.73039775760018e-05,
|
| 1269 |
+
"loss": 0.0203,
|
| 1270 |
+
"step": 1470
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 2.2593264001526574,
|
| 1274 |
+
"grad_norm": 0.14879602193832397,
|
| 1275 |
+
"learning_rate": 6.680292603955702e-05,
|
| 1276 |
+
"loss": 0.0153,
|
| 1277 |
+
"step": 1480
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 2.2745921190726075,
|
| 1281 |
+
"grad_norm": 0.16453400254249573,
|
| 1282 |
+
"learning_rate": 6.629996500041299e-05,
|
| 1283 |
+
"loss": 0.0181,
|
| 1284 |
+
"step": 1490
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 2.289857837992558,
|
| 1288 |
+
"grad_norm": 0.23307697474956512,
|
| 1289 |
+
"learning_rate": 6.579515161560649e-05,
|
| 1290 |
+
"loss": 0.0133,
|
| 1291 |
+
"step": 1500
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 2.289857837992558,
|
| 1295 |
+
"eval_loss": 0.032863009721040726,
|
| 1296 |
+
"eval_runtime": 179.7521,
|
| 1297 |
+
"eval_samples_per_second": 6.481,
|
| 1298 |
+
"eval_steps_per_second": 6.481,
|
| 1299 |
+
"step": 1500
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 2.305123556912508,
|
| 1303 |
+
"grad_norm": 0.29715099930763245,
|
| 1304 |
+
"learning_rate": 6.528854325267692e-05,
|
| 1305 |
+
"loss": 0.0225,
|
| 1306 |
+
"step": 1510
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 2.3203892758324587,
|
| 1310 |
+
"grad_norm": 0.27671730518341064,
|
| 1311 |
+
"learning_rate": 6.478019748314686e-05,
|
| 1312 |
+
"loss": 0.0193,
|
| 1313 |
+
"step": 1520
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 2.3356549947524092,
|
| 1317 |
+
"grad_norm": 0.08666820079088211,
|
| 1318 |
+
"learning_rate": 6.42701720759797e-05,
|
| 1319 |
+
"loss": 0.0206,
|
| 1320 |
+
"step": 1530
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 2.3509207136723593,
|
| 1324 |
+
"grad_norm": 0.08629153668880463,
|
| 1325 |
+
"learning_rate": 6.375852499101467e-05,
|
| 1326 |
+
"loss": 0.0147,
|
| 1327 |
+
"step": 1540
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 2.36618643259231,
|
| 1331 |
+
"grad_norm": 0.11571142822504044,
|
| 1332 |
+
"learning_rate": 6.324531437238019e-05,
|
| 1333 |
+
"loss": 0.0134,
|
| 1334 |
+
"step": 1550
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 2.36618643259231,
|
| 1338 |
+
"eval_loss": 0.031696803867816925,
|
| 1339 |
+
"eval_runtime": 179.7802,
|
| 1340 |
+
"eval_samples_per_second": 6.48,
|
| 1341 |
+
"eval_steps_per_second": 6.48,
|
| 1342 |
+
"step": 1550
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 2.3814521515122604,
|
| 1346 |
+
"grad_norm": 0.2257205992937088,
|
| 1347 |
+
"learning_rate": 6.273059854188636e-05,
|
| 1348 |
+
"loss": 0.0228,
|
| 1349 |
+
"step": 1560
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 2.3967178704322105,
|
| 1353 |
+
"grad_norm": 0.44024819135665894,
|
| 1354 |
+
"learning_rate": 6.221443599239721e-05,
|
| 1355 |
+
"loss": 0.0203,
|
| 1356 |
+
"step": 1570
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 2.411983589352161,
|
| 1360 |
+
"grad_norm": 0.20170512795448303,
|
| 1361 |
+
"learning_rate": 6.169688538118342e-05,
|
| 1362 |
+
"loss": 0.0227,
|
| 1363 |
+
"step": 1580
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 2.4272493082721116,
|
| 1367 |
+
"grad_norm": 0.15628792345523834,
|
| 1368 |
+
"learning_rate": 6.117800552325655e-05,
|
| 1369 |
+
"loss": 0.0181,
|
| 1370 |
+
"step": 1590
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 2.4425150271920617,
|
| 1374 |
+
"grad_norm": 0.17330731451511383,
|
| 1375 |
+
"learning_rate": 6.06578553846852e-05,
|
| 1376 |
+
"loss": 0.0185,
|
| 1377 |
+
"step": 1600
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 2.4425150271920617,
|
| 1381 |
+
"eval_loss": 0.029930831864476204,
|
| 1382 |
+
"eval_runtime": 179.7394,
|
| 1383 |
+
"eval_samples_per_second": 6.482,
|
| 1384 |
+
"eval_steps_per_second": 6.482,
|
| 1385 |
+
"step": 1600
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 2.4577807461120122,
|
| 1389 |
+
"grad_norm": 0.23071150481700897,
|
| 1390 |
+
"learning_rate": 6.013649407589401e-05,
|
| 1391 |
+
"loss": 0.0236,
|
| 1392 |
+
"step": 1610
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 2.473046465031963,
|
| 1396 |
+
"grad_norm": 0.17635267972946167,
|
| 1397 |
+
"learning_rate": 5.961398084494634e-05,
|
| 1398 |
+
"loss": 0.0211,
|
| 1399 |
+
"step": 1620
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 2.488312183951913,
|
| 1403 |
+
"grad_norm": 0.2662081718444824,
|
| 1404 |
+
"learning_rate": 5.909037507081121e-05,
|
| 1405 |
+
"loss": 0.0247,
|
| 1406 |
+
"step": 1630
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 2.5035779028718634,
|
| 1410 |
+
"grad_norm": 0.16230575740337372,
|
| 1411 |
+
"learning_rate": 5.8565736256615434e-05,
|
| 1412 |
+
"loss": 0.0243,
|
| 1413 |
+
"step": 1640
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 2.518843621791814,
|
| 1417 |
+
"grad_norm": 0.11765624582767487,
|
| 1418 |
+
"learning_rate": 5.8040124022881625e-05,
|
| 1419 |
+
"loss": 0.0229,
|
| 1420 |
+
"step": 1650
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 2.518843621791814,
|
| 1424 |
+
"eval_loss": 0.030760467052459717,
|
| 1425 |
+
"eval_runtime": 179.8009,
|
| 1426 |
+
"eval_samples_per_second": 6.479,
|
| 1427 |
+
"eval_steps_per_second": 6.479,
|
| 1428 |
+
"step": 1650
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 2.534109340711764,
|
| 1432 |
+
"grad_norm": 0.2117856740951538,
|
| 1433 |
+
"learning_rate": 5.751359810075284e-05,
|
| 1434 |
+
"loss": 0.0155,
|
| 1435 |
+
"step": 1660
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 2.5493750596317146,
|
| 1439 |
+
"grad_norm": 0.1411379873752594,
|
| 1440 |
+
"learning_rate": 5.6986218325204676e-05,
|
| 1441 |
+
"loss": 0.0133,
|
| 1442 |
+
"step": 1670
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 2.5646407785516647,
|
| 1446 |
+
"grad_norm": 0.1770981103181839,
|
| 1447 |
+
"learning_rate": 5.645804462824556e-05,
|
| 1448 |
+
"loss": 0.0159,
|
| 1449 |
+
"step": 1680
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 2.5799064974716153,
|
| 1453 |
+
"grad_norm": 0.3099724352359772,
|
| 1454 |
+
"learning_rate": 5.5929137032106005e-05,
|
| 1455 |
+
"loss": 0.0182,
|
| 1456 |
+
"step": 1690
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 2.595172216391566,
|
| 1460 |
+
"grad_norm": 0.22490672767162323,
|
| 1461 |
+
"learning_rate": 5.53995556424176e-05,
|
| 1462 |
+
"loss": 0.0224,
|
| 1463 |
+
"step": 1700
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 2.595172216391566,
|
| 1467 |
+
"eval_loss": 0.030679209157824516,
|
| 1468 |
+
"eval_runtime": 179.8574,
|
| 1469 |
+
"eval_samples_per_second": 6.477,
|
| 1470 |
+
"eval_steps_per_second": 6.477,
|
| 1471 |
+
"step": 1700
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 2.610437935311516,
|
| 1475 |
+
"grad_norm": 0.13174369931221008,
|
| 1476 |
+
"learning_rate": 5.4869360641382615e-05,
|
| 1477 |
+
"loss": 0.0152,
|
| 1478 |
+
"step": 1710
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 2.6257036542314665,
|
| 1482 |
+
"grad_norm": 0.21557074785232544,
|
| 1483 |
+
"learning_rate": 5.433861228093471e-05,
|
| 1484 |
+
"loss": 0.0209,
|
| 1485 |
+
"step": 1720
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 2.640969373151417,
|
| 1489 |
+
"grad_norm": 0.13589583337306976,
|
| 1490 |
+
"learning_rate": 5.380737087589197e-05,
|
| 1491 |
+
"loss": 0.0144,
|
| 1492 |
+
"step": 1730
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 2.656235092071367,
|
| 1496 |
+
"grad_norm": 0.23737147450447083,
|
| 1497 |
+
"learning_rate": 5.327569679710256e-05,
|
| 1498 |
+
"loss": 0.0236,
|
| 1499 |
+
"step": 1740
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 2.6715008109913176,
|
| 1503 |
+
"grad_norm": 0.15822412073612213,
|
| 1504 |
+
"learning_rate": 5.274365046458416e-05,
|
| 1505 |
+
"loss": 0.0159,
|
| 1506 |
+
"step": 1750
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 2.6715008109913176,
|
| 1510 |
+
"eval_loss": 0.03090774454176426,
|
| 1511 |
+
"eval_runtime": 179.9376,
|
| 1512 |
+
"eval_samples_per_second": 6.474,
|
| 1513 |
+
"eval_steps_per_second": 6.474,
|
| 1514 |
+
"step": 1750
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 2.686766529911268,
|
| 1518 |
+
"grad_norm": 0.31121695041656494,
|
| 1519 |
+
"learning_rate": 5.2211292340657804e-05,
|
| 1520 |
+
"loss": 0.0209,
|
| 1521 |
+
"step": 1760
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 2.7020322488312183,
|
| 1525 |
+
"grad_norm": 0.1423243284225464,
|
| 1526 |
+
"learning_rate": 5.167868292307678e-05,
|
| 1527 |
+
"loss": 0.0225,
|
| 1528 |
+
"step": 1770
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 2.717297967751169,
|
| 1532 |
+
"grad_norm": 0.18490996956825256,
|
| 1533 |
+
"learning_rate": 5.114588273815173e-05,
|
| 1534 |
+
"loss": 0.019,
|
| 1535 |
+
"step": 1780
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 2.732563686671119,
|
| 1539 |
+
"grad_norm": 0.2611638307571411,
|
| 1540 |
+
"learning_rate": 5.061295233387223e-05,
|
| 1541 |
+
"loss": 0.0228,
|
| 1542 |
+
"step": 1790
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 2.7478294055910695,
|
| 1546 |
+
"grad_norm": 0.15606072545051575,
|
| 1547 |
+
"learning_rate": 5.007995227302617e-05,
|
| 1548 |
+
"loss": 0.0185,
|
| 1549 |
+
"step": 1800
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 2.7478294055910695,
|
| 1553 |
+
"eval_loss": 0.03144565969705582,
|
| 1554 |
+
"eval_runtime": 179.8019,
|
| 1555 |
+
"eval_samples_per_second": 6.479,
|
| 1556 |
+
"eval_steps_per_second": 6.479,
|
| 1557 |
+
"step": 1800
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 2.76309512451102,
|
| 1561 |
+
"grad_norm": 0.09613101929426193,
|
| 1562 |
+
"learning_rate": 4.954694312631729e-05,
|
| 1563 |
+
"loss": 0.0176,
|
| 1564 |
+
"step": 1810
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 2.7783608434309706,
|
| 1568 |
+
"grad_norm": 0.23314177989959717,
|
| 1569 |
+
"learning_rate": 4.901398546548181e-05,
|
| 1570 |
+
"loss": 0.0179,
|
| 1571 |
+
"step": 1820
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 2.7936265623509207,
|
| 1575 |
+
"grad_norm": 0.2562658488750458,
|
| 1576 |
+
"learning_rate": 4.848113985640513e-05,
|
| 1577 |
+
"loss": 0.0163,
|
| 1578 |
+
"step": 1830
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 2.808892281270871,
|
| 1582 |
+
"grad_norm": 0.13945740461349487,
|
| 1583 |
+
"learning_rate": 4.794846685223884e-05,
|
| 1584 |
+
"loss": 0.0194,
|
| 1585 |
+
"step": 1840
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 2.8241580001908213,
|
| 1589 |
+
"grad_norm": 0.2183397263288498,
|
| 1590 |
+
"learning_rate": 4.741602698651966e-05,
|
| 1591 |
+
"loss": 0.0203,
|
| 1592 |
+
"step": 1850
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 2.8241580001908213,
|
| 1596 |
+
"eval_loss": 0.03035680390894413,
|
| 1597 |
+
"eval_runtime": 179.8704,
|
| 1598 |
+
"eval_samples_per_second": 6.477,
|
| 1599 |
+
"eval_steps_per_second": 6.477,
|
| 1600 |
+
"step": 1850
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 2.839423719110772,
|
| 1604 |
+
"grad_norm": 0.10274723172187805,
|
| 1605 |
+
"learning_rate": 4.6883880766290086e-05,
|
| 1606 |
+
"loss": 0.0208,
|
| 1607 |
+
"step": 1860
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 2.8546894380307224,
|
| 1611 |
+
"grad_norm": 0.1990806758403778,
|
| 1612 |
+
"learning_rate": 4.635208866522251e-05,
|
| 1613 |
+
"loss": 0.0149,
|
| 1614 |
+
"step": 1870
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 2.8699551569506725,
|
| 1618 |
+
"grad_norm": 0.15856200456619263,
|
| 1619 |
+
"learning_rate": 4.5820711116746785e-05,
|
| 1620 |
+
"loss": 0.0134,
|
| 1621 |
+
"step": 1880
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 2.885220875870623,
|
| 1625 |
+
"grad_norm": 0.30222058296203613,
|
| 1626 |
+
"learning_rate": 4.528980850718255e-05,
|
| 1627 |
+
"loss": 0.0216,
|
| 1628 |
+
"step": 1890
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 2.9004865947905736,
|
| 1632 |
+
"grad_norm": 0.13257752358913422,
|
| 1633 |
+
"learning_rate": 4.475944116887695e-05,
|
| 1634 |
+
"loss": 0.0159,
|
| 1635 |
+
"step": 1900
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 2.9004865947905736,
|
| 1639 |
+
"eval_loss": 0.031748704612255096,
|
| 1640 |
+
"eval_runtime": 179.7821,
|
| 1641 |
+
"eval_samples_per_second": 6.48,
|
| 1642 |
+
"eval_steps_per_second": 6.48,
|
| 1643 |
+
"step": 1900
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 2.9157523137105237,
|
| 1647 |
+
"grad_norm": 0.2612052261829376,
|
| 1648 |
+
"learning_rate": 4.4229669373348226e-05,
|
| 1649 |
+
"loss": 0.0215,
|
| 1650 |
+
"step": 1910
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 2.9310180326304742,
|
| 1654 |
+
"grad_norm": 0.15642981231212616,
|
| 1655 |
+
"learning_rate": 4.3700553324436575e-05,
|
| 1656 |
+
"loss": 0.0191,
|
| 1657 |
+
"step": 1920
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 2.9462837515504248,
|
| 1661 |
+
"grad_norm": 0.24419263005256653,
|
| 1662 |
+
"learning_rate": 4.317215315146238e-05,
|
| 1663 |
+
"loss": 0.0232,
|
| 1664 |
+
"step": 1930
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 2.961549470470375,
|
| 1668 |
+
"grad_norm": 0.12495076656341553,
|
| 1669 |
+
"learning_rate": 4.264452890239315e-05,
|
| 1670 |
+
"loss": 0.0223,
|
| 1671 |
+
"step": 1940
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 2.9768151893903254,
|
| 1675 |
+
"grad_norm": 0.26308339834213257,
|
| 1676 |
+
"learning_rate": 4.211774053701952e-05,
|
| 1677 |
+
"loss": 0.0229,
|
| 1678 |
+
"step": 1950
|
| 1679 |
+
},
|
| 1680 |
+
{
|
| 1681 |
+
"epoch": 2.9768151893903254,
|
| 1682 |
+
"eval_loss": 0.030370745807886124,
|
| 1683 |
+
"eval_runtime": 179.8091,
|
| 1684 |
+
"eval_samples_per_second": 6.479,
|
| 1685 |
+
"eval_steps_per_second": 6.479,
|
| 1686 |
+
"step": 1950
|
| 1687 |
+
},
|
| 1688 |
+
{
|
| 1689 |
+
"epoch": 2.9920809083102755,
|
| 1690 |
+
"grad_norm": 0.21157263219356537,
|
| 1691 |
+
"learning_rate": 4.159184792014145e-05,
|
| 1692 |
+
"loss": 0.0163,
|
| 1693 |
+
"step": 1960
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 3.007346627230226,
|
| 1697 |
+
"grad_norm": 0.062321823090314865,
|
| 1698 |
+
"learning_rate": 4.1066910814765016e-05,
|
| 1699 |
+
"loss": 0.0113,
|
| 1700 |
+
"step": 1970
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 3.0226123461501766,
|
| 1704 |
+
"grad_norm": 0.1957968771457672,
|
| 1705 |
+
"learning_rate": 4.0542988875310995e-05,
|
| 1706 |
+
"loss": 0.0138,
|
| 1707 |
+
"step": 1980
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 3.0378780650701267,
|
| 1711 |
+
"grad_norm": 0.12392223626375198,
|
| 1712 |
+
"learning_rate": 4.002014164083552e-05,
|
| 1713 |
+
"loss": 0.012,
|
| 1714 |
+
"step": 1990
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 3.0531437839900772,
|
| 1718 |
+
"grad_norm": 0.09297648817300797,
|
| 1719 |
+
"learning_rate": 3.9498428528264204e-05,
|
| 1720 |
+
"loss": 0.0087,
|
| 1721 |
+
"step": 2000
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 3.0531437839900772,
|
| 1725 |
+
"eval_loss": 0.032914210110902786,
|
| 1726 |
+
"eval_runtime": 179.7483,
|
| 1727 |
+
"eval_samples_per_second": 6.481,
|
| 1728 |
+
"eval_steps_per_second": 6.481,
|
| 1729 |
+
"step": 2000
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 3.068409502910028,
|
| 1733 |
+
"grad_norm": 0.1610821634531021,
|
| 1734 |
+
"learning_rate": 3.89779088256397e-05,
|
| 1735 |
+
"loss": 0.0093,
|
| 1736 |
+
"step": 2010
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 3.083675221829978,
|
| 1740 |
+
"grad_norm": 0.18227307498455048,
|
| 1741 |
+
"learning_rate": 3.845864168538437e-05,
|
| 1742 |
+
"loss": 0.0129,
|
| 1743 |
+
"step": 2020
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 3.0989409407499284,
|
| 1747 |
+
"grad_norm": 0.26220542192459106,
|
| 1748 |
+
"learning_rate": 3.794068611757794e-05,
|
| 1749 |
+
"loss": 0.0136,
|
| 1750 |
+
"step": 2030
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 3.114206659669879,
|
| 1754 |
+
"grad_norm": 0.15985815227031708,
|
| 1755 |
+
"learning_rate": 3.7424100983251695e-05,
|
| 1756 |
+
"loss": 0.0122,
|
| 1757 |
+
"step": 2040
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 3.129472378589829,
|
| 1761 |
+
"grad_norm": 0.06649836152791977,
|
| 1762 |
+
"learning_rate": 3.6908944987699345e-05,
|
| 1763 |
+
"loss": 0.0073,
|
| 1764 |
+
"step": 2050
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 3.129472378589829,
|
| 1768 |
+
"eval_loss": 0.033551715314388275,
|
| 1769 |
+
"eval_runtime": 179.8686,
|
| 1770 |
+
"eval_samples_per_second": 6.477,
|
| 1771 |
+
"eval_steps_per_second": 6.477,
|
| 1772 |
+
"step": 2050
|
| 1773 |
+
},
|
| 1774 |
+
{
|
| 1775 |
+
"epoch": 3.1447380975097796,
|
| 1776 |
+
"grad_norm": 0.11365962028503418,
|
| 1777 |
+
"learning_rate": 3.639527667380571e-05,
|
| 1778 |
+
"loss": 0.0084,
|
| 1779 |
+
"step": 2060
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 3.16000381642973,
|
| 1783 |
+
"grad_norm": 0.1839054673910141,
|
| 1784 |
+
"learning_rate": 3.5883154415393885e-05,
|
| 1785 |
+
"loss": 0.0101,
|
| 1786 |
+
"step": 2070
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 3.1752695353496803,
|
| 1790 |
+
"grad_norm": 0.20857231318950653,
|
| 1791 |
+
"learning_rate": 3.537263641059152e-05,
|
| 1792 |
+
"loss": 0.0107,
|
| 1793 |
+
"step": 2080
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 3.190535254269631,
|
| 1797 |
+
"grad_norm": 0.15886227786540985,
|
| 1798 |
+
"learning_rate": 3.486378067521718e-05,
|
| 1799 |
+
"loss": 0.0114,
|
| 1800 |
+
"step": 2090
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"epoch": 3.2058009731895813,
|
| 1804 |
+
"grad_norm": 0.10763030499219894,
|
| 1805 |
+
"learning_rate": 3.435664503618732e-05,
|
| 1806 |
+
"loss": 0.0068,
|
| 1807 |
+
"step": 2100
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 3.2058009731895813,
|
| 1811 |
+
"eval_loss": 0.03458699211478233,
|
| 1812 |
+
"eval_runtime": 179.8039,
|
| 1813 |
+
"eval_samples_per_second": 6.479,
|
| 1814 |
+
"eval_steps_per_second": 6.479,
|
| 1815 |
+
"step": 2100
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 3.2210666921095314,
|
| 1819 |
+
"grad_norm": 0.15906715393066406,
|
| 1820 |
+
"learning_rate": 3.3851287124944756e-05,
|
| 1821 |
+
"loss": 0.0091,
|
| 1822 |
+
"step": 2110
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 3.236332411029482,
|
| 1826 |
+
"grad_norm": 0.07679519057273865,
|
| 1827 |
+
"learning_rate": 3.334776437090944e-05,
|
| 1828 |
+
"loss": 0.0094,
|
| 1829 |
+
"step": 2120
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 3.251598129949432,
|
| 1833 |
+
"grad_norm": 0.07010853290557861,
|
| 1834 |
+
"learning_rate": 3.2846133994952046e-05,
|
| 1835 |
+
"loss": 0.0091,
|
| 1836 |
+
"step": 2130
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 3.2668638488693826,
|
| 1840 |
+
"grad_norm": 0.28941255807876587,
|
| 1841 |
+
"learning_rate": 3.234645300289136e-05,
|
| 1842 |
+
"loss": 0.0051,
|
| 1843 |
+
"step": 2140
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 3.282129567789333,
|
| 1847 |
+
"grad_norm": 0.2712288796901703,
|
| 1848 |
+
"learning_rate": 3.1848778179016075e-05,
|
| 1849 |
+
"loss": 0.0099,
|
| 1850 |
+
"step": 2150
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 3.282129567789333,
|
| 1854 |
+
"eval_loss": 0.03673892095685005,
|
| 1855 |
+
"eval_runtime": 179.9183,
|
| 1856 |
+
"eval_samples_per_second": 6.475,
|
| 1857 |
+
"eval_steps_per_second": 6.475,
|
| 1858 |
+
"step": 2150
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 3.2973952867092833,
|
| 1862 |
+
"grad_norm": 0.3802885413169861,
|
| 1863 |
+
"learning_rate": 3.135316607963176e-05,
|
| 1864 |
+
"loss": 0.0108,
|
| 1865 |
+
"step": 2160
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 3.312661005629234,
|
| 1869 |
+
"grad_norm": 0.19786600768566132,
|
| 1870 |
+
"learning_rate": 3.085967302663375e-05,
|
| 1871 |
+
"loss": 0.0082,
|
| 1872 |
+
"step": 2170
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 3.3279267245491844,
|
| 1876 |
+
"grad_norm": 0.25580260157585144,
|
| 1877 |
+
"learning_rate": 3.0368355101106615e-05,
|
| 1878 |
+
"loss": 0.0153,
|
| 1879 |
+
"step": 2180
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 3.3431924434691345,
|
| 1883 |
+
"grad_norm": 0.18568645417690277,
|
| 1884 |
+
"learning_rate": 2.987926813695116e-05,
|
| 1885 |
+
"loss": 0.0092,
|
| 1886 |
+
"step": 2190
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 3.358458162389085,
|
| 1890 |
+
"grad_norm": 0.15619678795337677,
|
| 1891 |
+
"learning_rate": 2.939246771453924e-05,
|
| 1892 |
+
"loss": 0.0124,
|
| 1893 |
+
"step": 2200
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 3.358458162389085,
|
| 1897 |
+
"eval_loss": 0.035190921276807785,
|
| 1898 |
+
"eval_runtime": 180.011,
|
| 1899 |
+
"eval_samples_per_second": 6.472,
|
| 1900 |
+
"eval_steps_per_second": 6.472,
|
| 1901 |
+
"step": 2200
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"epoch": 3.3737238813090356,
|
| 1905 |
+
"grad_norm": 0.2756540775299072,
|
| 1906 |
+
"learning_rate": 2.890800915439772e-05,
|
| 1907 |
+
"loss": 0.0112,
|
| 1908 |
+
"step": 2210
|
| 1909 |
+
},
|
| 1910 |
+
{
|
| 1911 |
+
"epoch": 3.3889896002289857,
|
| 1912 |
+
"grad_norm": 0.15437598526477814,
|
| 1913 |
+
"learning_rate": 2.842594751092159e-05,
|
| 1914 |
+
"loss": 0.0095,
|
| 1915 |
+
"step": 2220
|
| 1916 |
+
},
|
| 1917 |
+
{
|
| 1918 |
+
"epoch": 3.404255319148936,
|
| 1919 |
+
"grad_norm": 0.21479307115077972,
|
| 1920 |
+
"learning_rate": 2.794633756611776e-05,
|
| 1921 |
+
"loss": 0.0122,
|
| 1922 |
+
"step": 2230
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 3.4195210380688867,
|
| 1926 |
+
"grad_norm": 0.21604545414447784,
|
| 1927 |
+
"learning_rate": 2.7469233823379347e-05,
|
| 1928 |
+
"loss": 0.0089,
|
| 1929 |
+
"step": 2240
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 3.434786756988837,
|
| 1933 |
+
"grad_norm": 0.38754087686538696,
|
| 1934 |
+
"learning_rate": 2.6994690501292032e-05,
|
| 1935 |
+
"loss": 0.0087,
|
| 1936 |
+
"step": 2250
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 3.434786756988837,
|
| 1940 |
+
"eval_loss": 0.03597886487841606,
|
| 1941 |
+
"eval_runtime": 179.9469,
|
| 1942 |
+
"eval_samples_per_second": 6.474,
|
| 1943 |
+
"eval_steps_per_second": 6.474,
|
| 1944 |
+
"step": 2250
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"epoch": 3.4500524759087874,
|
| 1948 |
+
"grad_norm": 0.2704348862171173,
|
| 1949 |
+
"learning_rate": 2.652276152747246e-05,
|
| 1950 |
+
"loss": 0.0072,
|
| 1951 |
+
"step": 2260
|
| 1952 |
+
},
|
| 1953 |
+
{
|
| 1954 |
+
"epoch": 3.465318194828738,
|
| 1955 |
+
"grad_norm": 0.27907001972198486,
|
| 1956 |
+
"learning_rate": 2.6053500532439968e-05,
|
| 1957 |
+
"loss": 0.0078,
|
| 1958 |
+
"step": 2270
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 3.480583913748688,
|
| 1962 |
+
"grad_norm": 0.024898068979382515,
|
| 1963 |
+
"learning_rate": 2.5586960843521824e-05,
|
| 1964 |
+
"loss": 0.0098,
|
| 1965 |
+
"step": 2280
|
| 1966 |
+
},
|
| 1967 |
+
{
|
| 1968 |
+
"epoch": 3.4958496326686386,
|
| 1969 |
+
"grad_norm": 0.4165664315223694,
|
| 1970 |
+
"learning_rate": 2.5123195478793217e-05,
|
| 1971 |
+
"loss": 0.0106,
|
| 1972 |
+
"step": 2290
|
| 1973 |
+
},
|
| 1974 |
+
{
|
| 1975 |
+
"epoch": 3.5111153515885887,
|
| 1976 |
+
"grad_norm": 0.17015843093395233,
|
| 1977 |
+
"learning_rate": 2.466225714105202e-05,
|
| 1978 |
+
"loss": 0.0131,
|
| 1979 |
+
"step": 2300
|
| 1980 |
+
},
|
| 1981 |
+
{
|
| 1982 |
+
"epoch": 3.5111153515885887,
|
| 1983 |
+
"eval_loss": 0.03541536629199982,
|
| 1984 |
+
"eval_runtime": 179.5955,
|
| 1985 |
+
"eval_samples_per_second": 6.487,
|
| 1986 |
+
"eval_steps_per_second": 6.487,
|
| 1987 |
+
"step": 2300
|
| 1988 |
+
},
|
| 1989 |
+
{
|
| 1990 |
+
"epoch": 3.526381070508539,
|
| 1991 |
+
"grad_norm": 0.10995722562074661,
|
| 1992 |
+
"learning_rate": 2.420419821182982e-05,
|
| 1993 |
+
"loss": 0.0118,
|
| 1994 |
+
"step": 2310
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 3.5416467894284898,
|
| 1998 |
+
"grad_norm": 0.1612035483121872,
|
| 1999 |
+
"learning_rate": 2.3749070745438996e-05,
|
| 2000 |
+
"loss": 0.0063,
|
| 2001 |
+
"step": 2320
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 3.5569125083484403,
|
| 2005 |
+
"grad_norm": 0.15208382904529572,
|
| 2006 |
+
"learning_rate": 2.3296926463057396e-05,
|
| 2007 |
+
"loss": 0.0102,
|
| 2008 |
+
"step": 2330
|
| 2009 |
+
},
|
| 2010 |
+
{
|
| 2011 |
+
"epoch": 3.5721782272683904,
|
| 2012 |
+
"grad_norm": 0.19346974790096283,
|
| 2013 |
+
"learning_rate": 2.284781674685058e-05,
|
| 2014 |
+
"loss": 0.0079,
|
| 2015 |
+
"step": 2340
|
| 2016 |
+
},
|
| 2017 |
+
{
|
| 2018 |
+
"epoch": 3.587443946188341,
|
| 2019 |
+
"grad_norm": 0.43242356181144714,
|
| 2020 |
+
"learning_rate": 2.2401792634132708e-05,
|
| 2021 |
+
"loss": 0.0143,
|
| 2022 |
+
"step": 2350
|
| 2023 |
+
},
|
| 2024 |
+
{
|
| 2025 |
+
"epoch": 3.587443946188341,
|
| 2026 |
+
"eval_loss": 0.036229364573955536,
|
| 2027 |
+
"eval_runtime": 178.755,
|
| 2028 |
+
"eval_samples_per_second": 6.517,
|
| 2029 |
+
"eval_steps_per_second": 6.517,
|
| 2030 |
+
"step": 2350
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 3.602709665108291,
|
| 2034 |
+
"grad_norm": 0.35156679153442383,
|
| 2035 |
+
"learning_rate": 2.195890481156666e-05,
|
| 2036 |
+
"loss": 0.0097,
|
| 2037 |
+
"step": 2360
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"epoch": 3.6179753840282416,
|
| 2041 |
+
"grad_norm": 0.09875629097223282,
|
| 2042 |
+
"learning_rate": 2.151920360940387e-05,
|
| 2043 |
+
"loss": 0.0112,
|
| 2044 |
+
"step": 2370
|
| 2045 |
+
},
|
| 2046 |
+
{
|
| 2047 |
+
"epoch": 3.633241102948192,
|
| 2048 |
+
"grad_norm": 0.26106587052345276,
|
| 2049 |
+
"learning_rate": 2.1082738995764785e-05,
|
| 2050 |
+
"loss": 0.0078,
|
| 2051 |
+
"step": 2380
|
| 2052 |
+
},
|
| 2053 |
+
{
|
| 2054 |
+
"epoch": 3.6485068218681422,
|
| 2055 |
+
"grad_norm": 0.15816567838191986,
|
| 2056 |
+
"learning_rate": 2.0649560570960465e-05,
|
| 2057 |
+
"loss": 0.0046,
|
| 2058 |
+
"step": 2390
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 3.663772540788093,
|
| 2062 |
+
"grad_norm": 0.2872539460659027,
|
| 2063 |
+
"learning_rate": 2.0219717561855855e-05,
|
| 2064 |
+
"loss": 0.0066,
|
| 2065 |
+
"step": 2400
|
| 2066 |
+
},
|
| 2067 |
+
{
|
| 2068 |
+
"epoch": 3.663772540788093,
|
| 2069 |
+
"eval_loss": 0.036142896860837936,
|
| 2070 |
+
"eval_runtime": 177.8777,
|
| 2071 |
+
"eval_samples_per_second": 6.549,
|
| 2072 |
+
"eval_steps_per_second": 6.549,
|
| 2073 |
+
"step": 2400
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 3.679038259708043,
|
| 2077 |
+
"grad_norm": 0.16133087873458862,
|
| 2078 |
+
"learning_rate": 1.9793258816275728e-05,
|
| 2079 |
+
"loss": 0.0112,
|
| 2080 |
+
"step": 2410
|
| 2081 |
+
},
|
| 2082 |
+
{
|
| 2083 |
+
"epoch": 3.6943039786279934,
|
| 2084 |
+
"grad_norm": 0.32570400834083557,
|
| 2085 |
+
"learning_rate": 1.9370232797453402e-05,
|
| 2086 |
+
"loss": 0.009,
|
| 2087 |
+
"step": 2420
|
| 2088 |
+
},
|
| 2089 |
+
{
|
| 2090 |
+
"epoch": 3.709569697547944,
|
| 2091 |
+
"grad_norm": 0.21927714347839355,
|
| 2092 |
+
"learning_rate": 1.8950687578523502e-05,
|
| 2093 |
+
"loss": 0.0085,
|
| 2094 |
+
"step": 2430
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 3.7248354164678945,
|
| 2098 |
+
"grad_norm": 0.2975069284439087,
|
| 2099 |
+
"learning_rate": 1.853467083705869e-05,
|
| 2100 |
+
"loss": 0.0057,
|
| 2101 |
+
"step": 2440
|
| 2102 |
+
},
|
| 2103 |
+
{
|
| 2104 |
+
"epoch": 3.7401011353878446,
|
| 2105 |
+
"grad_norm": 0.19914095103740692,
|
| 2106 |
+
"learning_rate": 1.8122229849651716e-05,
|
| 2107 |
+
"loss": 0.0093,
|
| 2108 |
+
"step": 2450
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 3.7401011353878446,
|
| 2112 |
+
"eval_loss": 0.03722745552659035,
|
| 2113 |
+
"eval_runtime": 177.626,
|
| 2114 |
+
"eval_samples_per_second": 6.559,
|
| 2115 |
+
"eval_steps_per_second": 6.559,
|
| 2116 |
+
"step": 2450
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 3.755366854307795,
|
| 2120 |
+
"grad_norm": 0.20476055145263672,
|
| 2121 |
+
"learning_rate": 1.7713411486542707e-05,
|
| 2122 |
+
"loss": 0.0091,
|
| 2123 |
+
"step": 2460
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 3.7706325732277453,
|
| 2127 |
+
"grad_norm": 0.22789469361305237,
|
| 2128 |
+
"learning_rate": 1.7308262206292897e-05,
|
| 2129 |
+
"loss": 0.0111,
|
| 2130 |
+
"step": 2470
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 3.785898292147696,
|
| 2134 |
+
"grad_norm": 0.16632677614688873,
|
| 2135 |
+
"learning_rate": 1.6906828050504907e-05,
|
| 2136 |
+
"loss": 0.014,
|
| 2137 |
+
"step": 2480
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 3.8011640110676463,
|
| 2141 |
+
"grad_norm": 0.23071546852588654,
|
| 2142 |
+
"learning_rate": 1.650915463859068e-05,
|
| 2143 |
+
"loss": 0.0092,
|
| 2144 |
+
"step": 2490
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 3.8164297299875964,
|
| 2148 |
+
"grad_norm": 0.08320309221744537,
|
| 2149 |
+
"learning_rate": 1.6115287162587055e-05,
|
| 2150 |
+
"loss": 0.0074,
|
| 2151 |
+
"step": 2500
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 3.8164297299875964,
|
| 2155 |
+
"eval_loss": 0.03621383011341095,
|
| 2156 |
+
"eval_runtime": 177.3254,
|
| 2157 |
+
"eval_samples_per_second": 6.57,
|
| 2158 |
+
"eval_steps_per_second": 6.57,
|
| 2159 |
+
"step": 2500
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 3.831695448907547,
|
| 2163 |
+
"grad_norm": 0.07662249356508255,
|
| 2164 |
+
"learning_rate": 1.57252703820203e-05,
|
| 2165 |
+
"loss": 0.0069,
|
| 2166 |
+
"step": 2510
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 3.8469611678274975,
|
| 2170 |
+
"grad_norm": 0.35770368576049805,
|
| 2171 |
+
"learning_rate": 1.5339148618819393e-05,
|
| 2172 |
+
"loss": 0.0093,
|
| 2173 |
+
"step": 2520
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 3.8622268867474476,
|
| 2177 |
+
"grad_norm": 0.17595680058002472,
|
| 2178 |
+
"learning_rate": 1.4956965752279395e-05,
|
| 2179 |
+
"loss": 0.0105,
|
| 2180 |
+
"step": 2530
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 3.877492605667398,
|
| 2184 |
+
"grad_norm": 0.28761520981788635,
|
| 2185 |
+
"learning_rate": 1.457876521407484e-05,
|
| 2186 |
+
"loss": 0.0124,
|
| 2187 |
+
"step": 2540
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 3.8927583245873487,
|
| 2191 |
+
"grad_norm": 0.24026645720005035,
|
| 2192 |
+
"learning_rate": 1.4204589983324173e-05,
|
| 2193 |
+
"loss": 0.0081,
|
| 2194 |
+
"step": 2550
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 3.8927583245873487,
|
| 2198 |
+
"eval_loss": 0.03659246861934662,
|
| 2199 |
+
"eval_runtime": 177.2547,
|
| 2200 |
+
"eval_samples_per_second": 6.572,
|
| 2201 |
+
"eval_steps_per_second": 6.572,
|
| 2202 |
+
"step": 2550
|
| 2203 |
+
},
|
| 2204 |
+
{
|
| 2205 |
+
"epoch": 3.908024043507299,
|
| 2206 |
+
"grad_norm": 0.1325196474790573,
|
| 2207 |
+
"learning_rate": 1.383448258170557e-05,
|
| 2208 |
+
"loss": 0.0097,
|
| 2209 |
+
"step": 2560
|
| 2210 |
+
},
|
| 2211 |
+
{
|
| 2212 |
+
"epoch": 3.9232897624272494,
|
| 2213 |
+
"grad_norm": 0.18720892071723938,
|
| 2214 |
+
"learning_rate": 1.3468485068624653e-05,
|
| 2215 |
+
"loss": 0.009,
|
| 2216 |
+
"step": 2570
|
| 2217 |
+
},
|
| 2218 |
+
{
|
| 2219 |
+
"epoch": 3.9385554813471995,
|
| 2220 |
+
"grad_norm": 0.03328974172472954,
|
| 2221 |
+
"learning_rate": 1.310663903643492e-05,
|
| 2222 |
+
"loss": 0.009,
|
| 2223 |
+
"step": 2580
|
| 2224 |
+
},
|
| 2225 |
+
{
|
| 2226 |
+
"epoch": 3.95382120026715,
|
| 2227 |
+
"grad_norm": 0.08329346030950546,
|
| 2228 |
+
"learning_rate": 1.2748985605711028e-05,
|
| 2229 |
+
"loss": 0.0087,
|
| 2230 |
+
"step": 2590
|
| 2231 |
+
},
|
| 2232 |
+
{
|
| 2233 |
+
"epoch": 3.9690869191871005,
|
| 2234 |
+
"grad_norm": 0.1863928586244583,
|
| 2235 |
+
"learning_rate": 1.2395565420575932e-05,
|
| 2236 |
+
"loss": 0.0088,
|
| 2237 |
+
"step": 2600
|
| 2238 |
+
},
|
| 2239 |
+
{
|
| 2240 |
+
"epoch": 3.9690869191871005,
|
| 2241 |
+
"eval_loss": 0.03702830523252487,
|
| 2242 |
+
"eval_runtime": 176.9895,
|
| 2243 |
+
"eval_samples_per_second": 6.582,
|
| 2244 |
+
"eval_steps_per_second": 6.582,
|
| 2245 |
+
"step": 2600
|
| 2246 |
+
},
|
| 2247 |
+
{
|
| 2248 |
+
"epoch": 3.984352638107051,
|
| 2249 |
+
"grad_norm": 0.1559509038925171,
|
| 2250 |
+
"learning_rate": 1.2046418644081903e-05,
|
| 2251 |
+
"loss": 0.0178,
|
| 2252 |
+
"step": 2610
|
| 2253 |
+
},
|
| 2254 |
+
{
|
| 2255 |
+
"epoch": 3.999618357027001,
|
| 2256 |
+
"grad_norm": 0.302651584148407,
|
| 2257 |
+
"learning_rate": 1.1701584953646505e-05,
|
| 2258 |
+
"loss": 0.0086,
|
| 2259 |
+
"step": 2620
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"epoch": 4.014884075946951,
|
| 2263 |
+
"grad_norm": 0.19416853785514832,
|
| 2264 |
+
"learning_rate": 1.1361103536543466e-05,
|
| 2265 |
+
"loss": 0.0047,
|
| 2266 |
+
"step": 2630
|
| 2267 |
+
},
|
| 2268 |
+
{
|
| 2269 |
+
"epoch": 4.030149794866902,
|
| 2270 |
+
"grad_norm": 0.0938921868801117,
|
| 2271 |
+
"learning_rate": 1.1025013085449527e-05,
|
| 2272 |
+
"loss": 0.0035,
|
| 2273 |
+
"step": 2640
|
| 2274 |
+
},
|
| 2275 |
+
{
|
| 2276 |
+
"epoch": 4.045415513786852,
|
| 2277 |
+
"grad_norm": 0.1689745932817459,
|
| 2278 |
+
"learning_rate": 1.0693351794047224e-05,
|
| 2279 |
+
"loss": 0.0052,
|
| 2280 |
+
"step": 2650
|
| 2281 |
+
},
|
| 2282 |
+
{
|
| 2283 |
+
"epoch": 4.045415513786852,
|
| 2284 |
+
"eval_loss": 0.037683501839637756,
|
| 2285 |
+
"eval_runtime": 176.8431,
|
| 2286 |
+
"eval_samples_per_second": 6.588,
|
| 2287 |
+
"eval_steps_per_second": 6.588,
|
| 2288 |
+
"step": 2650
|
| 2289 |
+
},
|
| 2290 |
+
{
|
| 2291 |
+
"epoch": 4.060681232706803,
|
| 2292 |
+
"grad_norm": 0.13139070570468903,
|
| 2293 |
+
"learning_rate": 1.036615735268468e-05,
|
| 2294 |
+
"loss": 0.0041,
|
| 2295 |
+
"step": 2660
|
| 2296 |
+
},
|
| 2297 |
+
{
|
| 2298 |
+
"epoch": 4.0759469516267535,
|
| 2299 |
+
"grad_norm": 0.04985181987285614,
|
| 2300 |
+
"learning_rate": 1.0043466944092272e-05,
|
| 2301 |
+
"loss": 0.0059,
|
| 2302 |
+
"step": 2670
|
| 2303 |
+
},
|
| 2304 |
+
{
|
| 2305 |
+
"epoch": 4.091212670546703,
|
| 2306 |
+
"grad_norm": 0.09271463006734848,
|
| 2307 |
+
"learning_rate": 9.72531723915726e-06,
|
| 2308 |
+
"loss": 0.0086,
|
| 2309 |
+
"step": 2680
|
| 2310 |
+
},
|
| 2311 |
+
{
|
| 2312 |
+
"epoch": 4.106478389466654,
|
| 2313 |
+
"grad_norm": 0.03634309768676758,
|
| 2314 |
+
"learning_rate": 9.411744392756405e-06,
|
| 2315 |
+
"loss": 0.0052,
|
| 2316 |
+
"step": 2690
|
| 2317 |
+
},
|
| 2318 |
+
{
|
| 2319 |
+
"epoch": 4.121744108386604,
|
| 2320 |
+
"grad_norm": 0.06921113282442093,
|
| 2321 |
+
"learning_rate": 9.102784039647339e-06,
|
| 2322 |
+
"loss": 0.0053,
|
| 2323 |
+
"step": 2700
|
| 2324 |
+
},
|
| 2325 |
+
{
|
| 2326 |
+
"epoch": 4.121744108386604,
|
| 2327 |
+
"eval_loss": 0.039026983082294464,
|
| 2328 |
+
"eval_runtime": 176.6518,
|
| 2329 |
+
"eval_samples_per_second": 6.595,
|
| 2330 |
+
"eval_steps_per_second": 6.595,
|
| 2331 |
+
"step": 2700
|
| 2332 |
+
},
|
| 2333 |
+
{
|
| 2334 |
+
"epoch": 4.137009827306555,
|
| 2335 |
+
"grad_norm": 0.046318791806697845,
|
| 2336 |
+
"learning_rate": 8.79847129041893e-06,
|
| 2337 |
+
"loss": 0.0039,
|
| 2338 |
+
"step": 2710
|
| 2339 |
+
},
|
| 2340 |
+
{
|
| 2341 |
+
"epoch": 4.152275546226505,
|
| 2342 |
+
"grad_norm": 0.07762674242258072,
|
| 2343 |
+
"learning_rate": 8.498840727501316e-06,
|
| 2344 |
+
"loss": 0.0049,
|
| 2345 |
+
"step": 2720
|
| 2346 |
+
},
|
| 2347 |
+
{
|
| 2348 |
+
"epoch": 4.167541265146456,
|
| 2349 |
+
"grad_norm": 0.0868455171585083,
|
| 2350 |
+
"learning_rate": 8.203926401235957e-06,
|
| 2351 |
+
"loss": 0.0043,
|
| 2352 |
+
"step": 2730
|
| 2353 |
+
},
|
| 2354 |
+
{
|
| 2355 |
+
"epoch": 4.1828069840664055,
|
| 2356 |
+
"grad_norm": 0.13933709263801575,
|
| 2357 |
+
"learning_rate": 7.913761826006017e-06,
|
| 2358 |
+
"loss": 0.0037,
|
| 2359 |
+
"step": 2740
|
| 2360 |
+
},
|
| 2361 |
+
{
|
| 2362 |
+
"epoch": 4.198072702986356,
|
| 2363 |
+
"grad_norm": 0.11513333767652512,
|
| 2364 |
+
"learning_rate": 7.628379976427868e-06,
|
| 2365 |
+
"loss": 0.0025,
|
| 2366 |
+
"step": 2750
|
| 2367 |
+
},
|
| 2368 |
+
{
|
| 2369 |
+
"epoch": 4.198072702986356,
|
| 2370 |
+
"eval_loss": 0.040155019611120224,
|
| 2371 |
+
"eval_runtime": 176.5921,
|
| 2372 |
+
"eval_samples_per_second": 6.597,
|
| 2373 |
+
"eval_steps_per_second": 6.597,
|
| 2374 |
+
"step": 2750
|
| 2375 |
+
},
|
| 2376 |
+
{
|
| 2377 |
+
"epoch": 4.213338421906307,
|
| 2378 |
+
"grad_norm": 0.3080286681652069,
|
| 2379 |
+
"learning_rate": 7.347813283603705e-06,
|
| 2380 |
+
"loss": 0.0067,
|
| 2381 |
+
"step": 2760
|
| 2382 |
+
},
|
| 2383 |
+
{
|
| 2384 |
+
"epoch": 4.228604140826257,
|
| 2385 |
+
"grad_norm": 0.06484497338533401,
|
| 2386 |
+
"learning_rate": 7.072093631436161e-06,
|
| 2387 |
+
"loss": 0.0041,
|
| 2388 |
+
"step": 2770
|
| 2389 |
+
},
|
| 2390 |
+
{
|
| 2391 |
+
"epoch": 4.243869859746208,
|
| 2392 |
+
"grad_norm": 0.023219596594572067,
|
| 2393 |
+
"learning_rate": 6.801252353004867e-06,
|
| 2394 |
+
"loss": 0.0039,
|
| 2395 |
+
"step": 2780
|
| 2396 |
+
},
|
| 2397 |
+
{
|
| 2398 |
+
"epoch": 4.259135578666158,
|
| 2399 |
+
"grad_norm": 0.13570910692214966,
|
| 2400 |
+
"learning_rate": 6.535320227005826e-06,
|
| 2401 |
+
"loss": 0.0059,
|
| 2402 |
+
"step": 2790
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 4.274401297586108,
|
| 2406 |
+
"grad_norm": 0.0693252682685852,
|
| 2407 |
+
"learning_rate": 6.274327474253611e-06,
|
| 2408 |
+
"loss": 0.0027,
|
| 2409 |
+
"step": 2800
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 4.274401297586108,
|
| 2413 |
+
"eval_loss": 0.04144105687737465,
|
| 2414 |
+
"eval_runtime": 176.6226,
|
| 2415 |
+
"eval_samples_per_second": 6.596,
|
| 2416 |
+
"eval_steps_per_second": 6.596,
|
| 2417 |
+
"step": 2800
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 4.289667016506058,
|
| 2421 |
+
"grad_norm": 0.10616520047187805,
|
| 2422 |
+
"learning_rate": 6.018303754247112e-06,
|
| 2423 |
+
"loss": 0.0051,
|
| 2424 |
+
"step": 2810
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 4.304932735426009,
|
| 2428 |
+
"grad_norm": 0.14562755823135376,
|
| 2429 |
+
"learning_rate": 5.767278161798911e-06,
|
| 2430 |
+
"loss": 0.0042,
|
| 2431 |
+
"step": 2820
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 4.3201984543459595,
|
| 2435 |
+
"grad_norm": 0.1878853291273117,
|
| 2436 |
+
"learning_rate": 5.521279223729026e-06,
|
| 2437 |
+
"loss": 0.0035,
|
| 2438 |
+
"step": 2830
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 4.33546417326591,
|
| 2442 |
+
"grad_norm": 0.17619742453098297,
|
| 2443 |
+
"learning_rate": 5.280334895622968e-06,
|
| 2444 |
+
"loss": 0.004,
|
| 2445 |
+
"step": 2840
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 4.350729892185861,
|
| 2449 |
+
"grad_norm": 0.15715391933918,
|
| 2450 |
+
"learning_rate": 5.044472558654961e-06,
|
| 2451 |
+
"loss": 0.0076,
|
| 2452 |
+
"step": 2850
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 4.350729892185861,
|
| 2456 |
+
"eval_loss": 0.04184148460626602,
|
| 2457 |
+
"eval_runtime": 176.611,
|
| 2458 |
+
"eval_samples_per_second": 6.596,
|
| 2459 |
+
"eval_steps_per_second": 6.596,
|
| 2460 |
+
"step": 2850
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 4.36599561110581,
|
| 2464 |
+
"grad_norm": 0.05749718099832535,
|
| 2465 |
+
"learning_rate": 4.813719016476203e-06,
|
| 2466 |
+
"loss": 0.0029,
|
| 2467 |
+
"step": 2860
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 4.381261330025761,
|
| 2471 |
+
"grad_norm": 0.27915164828300476,
|
| 2472 |
+
"learning_rate": 4.588100492168973e-06,
|
| 2473 |
+
"loss": 0.003,
|
| 2474 |
+
"step": 2870
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 4.396527048945711,
|
| 2478 |
+
"grad_norm": 0.26044297218322754,
|
| 2479 |
+
"learning_rate": 4.367642625266511e-06,
|
| 2480 |
+
"loss": 0.0027,
|
| 2481 |
+
"step": 2880
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 4.411792767865662,
|
| 2485 |
+
"grad_norm": 0.09349619597196579,
|
| 2486 |
+
"learning_rate": 4.1523704688394176e-06,
|
| 2487 |
+
"loss": 0.0042,
|
| 2488 |
+
"step": 2890
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 4.427058486785612,
|
| 2492 |
+
"grad_norm": 0.06762149930000305,
|
| 2493 |
+
"learning_rate": 3.9423084866484884e-06,
|
| 2494 |
+
"loss": 0.0022,
|
| 2495 |
+
"step": 2900
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 4.427058486785612,
|
| 2499 |
+
"eval_loss": 0.04281175881624222,
|
| 2500 |
+
"eval_runtime": 176.5277,
|
| 2501 |
+
"eval_samples_per_second": 6.6,
|
| 2502 |
+
"eval_steps_per_second": 6.6,
|
| 2503 |
+
"step": 2900
|
| 2504 |
+
},
|
| 2505 |
+
{
|
| 2506 |
+
"epoch": 4.442324205705562,
|
| 2507 |
+
"grad_norm": 0.15383104979991913,
|
| 2508 |
+
"learning_rate": 3.737480550364736e-06,
|
| 2509 |
+
"loss": 0.0062,
|
| 2510 |
+
"step": 2910
|
| 2511 |
+
},
|
| 2512 |
+
{
|
| 2513 |
+
"epoch": 4.457589924625513,
|
| 2514 |
+
"grad_norm": 0.21743904054164886,
|
| 2515 |
+
"learning_rate": 3.5379099368564817e-06,
|
| 2516 |
+
"loss": 0.0056,
|
| 2517 |
+
"step": 2920
|
| 2518 |
+
},
|
| 2519 |
+
{
|
| 2520 |
+
"epoch": 4.472855643545463,
|
| 2521 |
+
"grad_norm": 0.05257946625351906,
|
| 2522 |
+
"learning_rate": 3.3436193255442396e-06,
|
| 2523 |
+
"loss": 0.0034,
|
| 2524 |
+
"step": 2930
|
| 2525 |
+
},
|
| 2526 |
+
{
|
| 2527 |
+
"epoch": 4.488121362465414,
|
| 2528 |
+
"grad_norm": 0.05678296461701393,
|
| 2529 |
+
"learning_rate": 3.1546307958233214e-06,
|
| 2530 |
+
"loss": 0.0065,
|
| 2531 |
+
"step": 2940
|
| 2532 |
+
},
|
| 2533 |
+
{
|
| 2534 |
+
"epoch": 4.503387081385364,
|
| 2535 |
+
"grad_norm": 0.09029638022184372,
|
| 2536 |
+
"learning_rate": 2.9709658245547834e-06,
|
| 2537 |
+
"loss": 0.0036,
|
| 2538 |
+
"step": 2950
|
| 2539 |
+
},
|
| 2540 |
+
{
|
| 2541 |
+
"epoch": 4.503387081385364,
|
| 2542 |
+
"eval_loss": 0.04338888078927994,
|
| 2543 |
+
"eval_runtime": 176.4344,
|
| 2544 |
+
"eval_samples_per_second": 6.603,
|
| 2545 |
+
"eval_steps_per_second": 6.603,
|
| 2546 |
+
"step": 2950
|
| 2547 |
+
},
|
| 2548 |
+
{
|
| 2549 |
+
"epoch": 4.518652800305315,
|
| 2550 |
+
"grad_norm": 0.017809836193919182,
|
| 2551 |
+
"learning_rate": 2.792645283624712e-06,
|
| 2552 |
+
"loss": 0.0051,
|
| 2553 |
+
"step": 2960
|
| 2554 |
+
},
|
| 2555 |
+
{
|
| 2556 |
+
"epoch": 4.5339185192252645,
|
| 2557 |
+
"grad_norm": 0.08156479895114899,
|
| 2558 |
+
"learning_rate": 2.6196894375723645e-06,
|
| 2559 |
+
"loss": 0.0016,
|
| 2560 |
+
"step": 2970
|
| 2561 |
+
},
|
| 2562 |
+
{
|
| 2563 |
+
"epoch": 4.549184238145215,
|
| 2564 |
+
"grad_norm": 0.24031901359558105,
|
| 2565 |
+
"learning_rate": 2.452117941287246e-06,
|
| 2566 |
+
"loss": 0.0049,
|
| 2567 |
+
"step": 2980
|
| 2568 |
+
},
|
| 2569 |
+
{
|
| 2570 |
+
"epoch": 4.5644499570651655,
|
| 2571 |
+
"grad_norm": 0.2679056227207184,
|
| 2572 |
+
"learning_rate": 2.2899498377755566e-06,
|
| 2573 |
+
"loss": 0.0024,
|
| 2574 |
+
"step": 2990
|
| 2575 |
+
},
|
| 2576 |
+
{
|
| 2577 |
+
"epoch": 4.579715675985116,
|
| 2578 |
+
"grad_norm": 0.1409529745578766,
|
| 2579 |
+
"learning_rate": 2.1332035559960663e-06,
|
| 2580 |
+
"loss": 0.003,
|
| 2581 |
+
"step": 3000
|
| 2582 |
+
},
|
| 2583 |
+
{
|
| 2584 |
+
"epoch": 4.579715675985116,
|
| 2585 |
+
"eval_loss": 0.04322050139307976,
|
| 2586 |
+
"eval_runtime": 176.3389,
|
| 2587 |
+
"eval_samples_per_second": 6.607,
|
| 2588 |
+
"eval_steps_per_second": 6.607,
|
| 2589 |
+
"step": 3000
|
| 2590 |
+
},
|
| 2591 |
+
{
|
| 2592 |
+
"epoch": 4.594981394905067,
|
| 2593 |
+
"grad_norm": 0.3694174289703369,
|
| 2594 |
+
"learning_rate": 1.9818969087658735e-06,
|
| 2595 |
+
"loss": 0.0034,
|
| 2596 |
+
"step": 3010
|
| 2597 |
+
},
|
| 2598 |
+
{
|
| 2599 |
+
"epoch": 4.610247113825016,
|
| 2600 |
+
"grad_norm": 0.007240964099764824,
|
| 2601 |
+
"learning_rate": 1.8360470907361093e-06,
|
| 2602 |
+
"loss": 0.002,
|
| 2603 |
+
"step": 3020
|
| 2604 |
+
},
|
| 2605 |
+
{
|
| 2606 |
+
"epoch": 4.625512832744967,
|
| 2607 |
+
"grad_norm": 0.21716032922267914,
|
| 2608 |
+
"learning_rate": 1.6956706764379438e-06,
|
| 2609 |
+
"loss": 0.0046,
|
| 2610 |
+
"step": 3030
|
| 2611 |
+
},
|
| 2612 |
+
{
|
| 2613 |
+
"epoch": 4.640778551664917,
|
| 2614 |
+
"grad_norm": 0.10940048843622208,
|
| 2615 |
+
"learning_rate": 1.5607836183989921e-06,
|
| 2616 |
+
"loss": 0.0033,
|
| 2617 |
+
"step": 3040
|
| 2618 |
+
},
|
| 2619 |
+
{
|
| 2620 |
+
"epoch": 4.656044270584868,
|
| 2621 |
+
"grad_norm": 0.14919409155845642,
|
| 2622 |
+
"learning_rate": 1.4314012453305215e-06,
|
| 2623 |
+
"loss": 0.002,
|
| 2624 |
+
"step": 3050
|
| 2625 |
+
},
|
| 2626 |
+
{
|
| 2627 |
+
"epoch": 4.656044270584868,
|
| 2628 |
+
"eval_loss": 0.043372880667448044,
|
| 2629 |
+
"eval_runtime": 176.3259,
|
| 2630 |
+
"eval_samples_per_second": 6.607,
|
| 2631 |
+
"eval_steps_per_second": 6.607,
|
| 2632 |
+
"step": 3050
|
| 2633 |
+
},
|
| 2634 |
+
{
|
| 2635 |
+
"epoch": 4.6713099895048185,
|
| 2636 |
+
"grad_norm": 0.21336524188518524,
|
| 2637 |
+
"learning_rate": 1.3075382603854157e-06,
|
| 2638 |
+
"loss": 0.003,
|
| 2639 |
+
"step": 3060
|
| 2640 |
+
},
|
| 2641 |
+
{
|
| 2642 |
+
"epoch": 4.686575708424769,
|
| 2643 |
+
"grad_norm": 0.1394193321466446,
|
| 2644 |
+
"learning_rate": 1.1892087394873353e-06,
|
| 2645 |
+
"loss": 0.0034,
|
| 2646 |
+
"step": 3070
|
| 2647 |
+
},
|
| 2648 |
+
{
|
| 2649 |
+
"epoch": 4.701841427344719,
|
| 2650 |
+
"grad_norm": 0.02440819889307022,
|
| 2651 |
+
"learning_rate": 1.076426129731084e-06,
|
| 2652 |
+
"loss": 0.0036,
|
| 2653 |
+
"step": 3080
|
| 2654 |
+
},
|
| 2655 |
+
{
|
| 2656 |
+
"epoch": 4.717107146264669,
|
| 2657 |
+
"grad_norm": 0.14676684141159058,
|
| 2658 |
+
"learning_rate": 9.692032478545e-07,
|
| 2659 |
+
"loss": 0.0069,
|
| 2660 |
+
"step": 3090
|
| 2661 |
+
},
|
| 2662 |
+
{
|
| 2663 |
+
"epoch": 4.73237286518462,
|
| 2664 |
+
"grad_norm": 0.01789388246834278,
|
| 2665 |
+
"learning_rate": 8.675522787819023e-07,
|
| 2666 |
+
"loss": 0.0078,
|
| 2667 |
+
"step": 3100
|
| 2668 |
+
},
|
| 2669 |
+
{
|
| 2670 |
+
"epoch": 4.73237286518462,
|
| 2671 |
+
"eval_loss": 0.043460384011268616,
|
| 2672 |
+
"eval_runtime": 176.2874,
|
| 2673 |
+
"eval_samples_per_second": 6.609,
|
| 2674 |
+
"eval_steps_per_second": 6.609,
|
| 2675 |
+
"step": 3100
|
| 2676 |
+
},
|
| 2677 |
+
{
|
| 2678 |
+
"epoch": 4.74763858410457,
|
| 2679 |
+
"grad_norm": 0.04277348518371582,
|
| 2680 |
+
"learning_rate": 7.714847742394337e-07,
|
| 2681 |
+
"loss": 0.0053,
|
| 2682 |
+
"step": 3110
|
| 2683 |
+
},
|
| 2684 |
+
{
|
| 2685 |
+
"epoch": 4.762904303024521,
|
| 2686 |
+
"grad_norm": 0.26189810037612915,
|
| 2687 |
+
"learning_rate": 6.810116514422593e-07,
|
| 2688 |
+
"loss": 0.005,
|
| 2689 |
+
"step": 3120
|
| 2690 |
+
},
|
| 2691 |
+
{
|
| 2692 |
+
"epoch": 4.7781700219444705,
|
| 2693 |
+
"grad_norm": 0.054308198392391205,
|
| 2694 |
+
"learning_rate": 5.961431918539817e-07,
|
| 2695 |
+
"loss": 0.0032,
|
| 2696 |
+
"step": 3130
|
| 2697 |
+
},
|
| 2698 |
+
{
|
| 2699 |
+
"epoch": 4.793435740864421,
|
| 2700 |
+
"grad_norm": 0.10629548877477646,
|
| 2701 |
+
"learning_rate": 5.16889040018187e-07,
|
| 2702 |
+
"loss": 0.0055,
|
| 2703 |
+
"step": 3140
|
| 2704 |
+
},
|
| 2705 |
+
{
|
| 2706 |
+
"epoch": 4.808701459784372,
|
| 2707 |
+
"grad_norm": 0.05638623237609863,
|
| 2708 |
+
"learning_rate": 4.432582024624543e-07,
|
| 2709 |
+
"loss": 0.0033,
|
| 2710 |
+
"step": 3150
|
| 2711 |
+
},
|
| 2712 |
+
{
|
| 2713 |
+
"epoch": 4.808701459784372,
|
| 2714 |
+
"eval_loss": 0.04357059299945831,
|
| 2715 |
+
"eval_runtime": 176.3321,
|
| 2716 |
+
"eval_samples_per_second": 6.607,
|
| 2717 |
+
"eval_steps_per_second": 6.607,
|
| 2718 |
+
"step": 3150
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 4.823967178704322,
|
| 2722 |
+
"grad_norm": 0.035809215158224106,
|
| 2723 |
+
"learning_rate": 3.7525904667484737e-07,
|
| 2724 |
+
"loss": 0.0029,
|
| 2725 |
+
"step": 3160
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 4.839232897624273,
|
| 2729 |
+
"grad_norm": 0.25203967094421387,
|
| 2730 |
+
"learning_rate": 3.128993001530245e-07,
|
| 2731 |
+
"loss": 0.0059,
|
| 2732 |
+
"step": 3170
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 4.854498616544223,
|
| 2736 |
+
"grad_norm": 0.04179414361715317,
|
| 2737 |
+
"learning_rate": 2.5618604952605816e-07,
|
| 2738 |
+
"loss": 0.0046,
|
| 2739 |
+
"step": 3180
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 4.869764335464174,
|
| 2743 |
+
"grad_norm": 0.14175380766391754,
|
| 2744 |
+
"learning_rate": 2.0512573974912908e-07,
|
| 2745 |
+
"loss": 0.0038,
|
| 2746 |
+
"step": 3190
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 4.885030054384123,
|
| 2750 |
+
"grad_norm": 0.20164638757705688,
|
| 2751 |
+
"learning_rate": 1.597241733711008e-07,
|
| 2752 |
+
"loss": 0.0055,
|
| 2753 |
+
"step": 3200
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 4.885030054384123,
|
| 2757 |
+
"eval_loss": 0.043629422783851624,
|
| 2758 |
+
"eval_runtime": 176.2217,
|
| 2759 |
+
"eval_samples_per_second": 6.611,
|
| 2760 |
+
"eval_steps_per_second": 6.611,
|
| 2761 |
+
"step": 3200
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 4.900295773304074,
|
| 2765 |
+
"grad_norm": 0.10687878727912903,
|
| 2766 |
+
"learning_rate": 1.1998650987510295e-07,
|
| 2767 |
+
"loss": 0.0035,
|
| 2768 |
+
"step": 3210
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 4.9155614922240245,
|
| 2772 |
+
"grad_norm": 0.010824548080563545,
|
| 2773 |
+
"learning_rate": 8.591726509222242e-08,
|
| 2774 |
+
"loss": 0.0074,
|
| 2775 |
+
"step": 3220
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 4.930827211143975,
|
| 2779 |
+
"grad_norm": 0.13975496590137482,
|
| 2780 |
+
"learning_rate": 5.752031068830266e-08,
|
| 2781 |
+
"loss": 0.0041,
|
| 2782 |
+
"step": 3230
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 4.946092930063926,
|
| 2786 |
+
"grad_norm": 0.08203299343585968,
|
| 2787 |
+
"learning_rate": 3.4798873723984605e-08,
|
| 2788 |
+
"loss": 0.0032,
|
| 2789 |
+
"step": 3240
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 4.961358648983875,
|
| 2793 |
+
"grad_norm": 0.22268716990947723,
|
| 2794 |
+
"learning_rate": 1.7755536287944464e-08,
|
| 2795 |
+
"loss": 0.006,
|
| 2796 |
+
"step": 3250
|
| 2797 |
+
},
|
| 2798 |
+
{
|
| 2799 |
+
"epoch": 4.961358648983875,
|
| 2800 |
+
"eval_loss": 0.043610408902168274,
|
| 2801 |
+
"eval_runtime": 176.2018,
|
| 2802 |
+
"eval_samples_per_second": 6.612,
|
| 2803 |
+
"eval_steps_per_second": 6.612,
|
| 2804 |
+
"step": 3250
|
| 2805 |
+
},
|
| 2806 |
+
{
|
| 2807 |
+
"epoch": 4.976624367903826,
|
| 2808 |
+
"grad_norm": 0.07115557044744492,
|
| 2809 |
+
"learning_rate": 6.3922352034895276e-09,
|
| 2810 |
+
"loss": 0.0103,
|
| 2811 |
+
"step": 3260
|
| 2812 |
+
},
|
| 2813 |
+
{
|
| 2814 |
+
"epoch": 4.991890086823776,
|
| 2815 |
+
"grad_norm": 0.18499644100666046,
|
| 2816 |
+
"learning_rate": 7.102618084620094e-10,
|
| 2817 |
+
"loss": 0.0049,
|
| 2818 |
+
"step": 3270
|
| 2819 |
+
},
|
| 2820 |
+
{
|
| 2821 |
+
"epoch": 4.999522946283752,
|
| 2822 |
+
"step": 3275,
|
| 2823 |
+
"total_flos": 8.8535579239868e+17,
|
| 2824 |
+
"train_loss": 0.048749475333526845,
|
| 2825 |
+
"train_runtime": 37525.7545,
|
| 2826 |
+
"train_samples_per_second": 1.397,
|
| 2827 |
+
"train_steps_per_second": 0.087
|
| 2828 |
+
}
|
| 2829 |
+
],
|
| 2830 |
+
"logging_steps": 10,
|
| 2831 |
+
"max_steps": 3275,
|
| 2832 |
+
"num_input_tokens_seen": 0,
|
| 2833 |
+
"num_train_epochs": 5,
|
| 2834 |
+
"save_steps": 50,
|
| 2835 |
+
"stateful_callbacks": {
|
| 2836 |
+
"TrainerControl": {
|
| 2837 |
+
"args": {
|
| 2838 |
+
"should_epoch_stop": false,
|
| 2839 |
+
"should_evaluate": false,
|
| 2840 |
+
"should_log": false,
|
| 2841 |
+
"should_save": true,
|
| 2842 |
+
"should_training_stop": true
|
| 2843 |
+
},
|
| 2844 |
+
"attributes": {}
|
| 2845 |
+
}
|
| 2846 |
+
},
|
| 2847 |
+
"total_flos": 8.8535579239868e+17,
|
| 2848 |
+
"train_batch_size": 1,
|
| 2849 |
+
"trial_name": null,
|
| 2850 |
+
"trial_params": null
|
| 2851 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|