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 +2808 -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-fold2
|
|
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# MentaLLaMA-chat-7B-PsyCourse-fold2
|
| 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-fold2
|
|
|
|
| 16 |
|
| 17 |
# MentaLLaMA-chat-7B-PsyCourse-fold2
|
| 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-fold2 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": 5.0,
|
| 3 |
+
"eval_loss": 0.02887474000453949,
|
| 4 |
+
"eval_runtime": 173.2039,
|
| 5 |
+
"eval_samples_per_second": 6.622,
|
| 6 |
+
"eval_steps_per_second": 6.622,
|
| 7 |
+
"total_flos": 8.718478050646426e+17,
|
| 8 |
+
"train_loss": 0.049027663960821866,
|
| 9 |
+
"train_runtime": 36714.2196,
|
| 10 |
+
"train_samples_per_second": 1.405,
|
| 11 |
+
"train_steps_per_second": 0.088
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_loss": 0.02887474000453949,
|
| 4 |
+
"eval_runtime": 173.2039,
|
| 5 |
+
"eval_samples_per_second": 6.622,
|
| 6 |
+
"eval_steps_per_second": 6.622
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"total_flos": 8.718478050646426e+17,
|
| 4 |
+
"train_loss": 0.049027663960821866,
|
| 5 |
+
"train_runtime": 36714.2196,
|
| 6 |
+
"train_samples_per_second": 1.405,
|
| 7 |
+
"train_steps_per_second": 0.088
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2808 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.02887474000453949,
|
| 3 |
+
"best_model_checkpoint": "saves/psy-course/MentaLLaMA-chat-7B/train/fold2/checkpoint-1900",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 3225,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.015503875968992248,
|
| 13 |
+
"grad_norm": 1.8097485303878784,
|
| 14 |
+
"learning_rate": 3.0959752321981426e-06,
|
| 15 |
+
"loss": 1.678,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.031007751937984496,
|
| 20 |
+
"grad_norm": 1.9774603843688965,
|
| 21 |
+
"learning_rate": 6.191950464396285e-06,
|
| 22 |
+
"loss": 1.7145,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.046511627906976744,
|
| 27 |
+
"grad_norm": 2.036001443862915,
|
| 28 |
+
"learning_rate": 9.287925696594429e-06,
|
| 29 |
+
"loss": 1.5924,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.06201550387596899,
|
| 34 |
+
"grad_norm": 3.265268087387085,
|
| 35 |
+
"learning_rate": 1.238390092879257e-05,
|
| 36 |
+
"loss": 1.2457,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.07751937984496124,
|
| 41 |
+
"grad_norm": 1.1102505922317505,
|
| 42 |
+
"learning_rate": 1.5479876160990712e-05,
|
| 43 |
+
"loss": 0.7519,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.07751937984496124,
|
| 48 |
+
"eval_loss": 0.638915479183197,
|
| 49 |
+
"eval_runtime": 177.4395,
|
| 50 |
+
"eval_samples_per_second": 6.464,
|
| 51 |
+
"eval_steps_per_second": 6.464,
|
| 52 |
+
"step": 50
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.09302325581395349,
|
| 56 |
+
"grad_norm": 0.6308065056800842,
|
| 57 |
+
"learning_rate": 1.8575851393188857e-05,
|
| 58 |
+
"loss": 0.6351,
|
| 59 |
+
"step": 60
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.10852713178294573,
|
| 63 |
+
"grad_norm": 0.8012827634811401,
|
| 64 |
+
"learning_rate": 2.1671826625387e-05,
|
| 65 |
+
"loss": 0.4782,
|
| 66 |
+
"step": 70
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.12403100775193798,
|
| 70 |
+
"grad_norm": 0.6199682354927063,
|
| 71 |
+
"learning_rate": 2.476780185758514e-05,
|
| 72 |
+
"loss": 0.2779,
|
| 73 |
+
"step": 80
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.13953488372093023,
|
| 77 |
+
"grad_norm": 0.5094736218452454,
|
| 78 |
+
"learning_rate": 2.7863777089783283e-05,
|
| 79 |
+
"loss": 0.1896,
|
| 80 |
+
"step": 90
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.15503875968992248,
|
| 84 |
+
"grad_norm": 0.5959056615829468,
|
| 85 |
+
"learning_rate": 3.0959752321981425e-05,
|
| 86 |
+
"loss": 0.1485,
|
| 87 |
+
"step": 100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.15503875968992248,
|
| 91 |
+
"eval_loss": 0.11244650185108185,
|
| 92 |
+
"eval_runtime": 177.3837,
|
| 93 |
+
"eval_samples_per_second": 6.466,
|
| 94 |
+
"eval_steps_per_second": 6.466,
|
| 95 |
+
"step": 100
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.17054263565891473,
|
| 99 |
+
"grad_norm": 0.919588029384613,
|
| 100 |
+
"learning_rate": 3.4055727554179566e-05,
|
| 101 |
+
"loss": 0.1271,
|
| 102 |
+
"step": 110
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.18604651162790697,
|
| 106 |
+
"grad_norm": 0.9113105535507202,
|
| 107 |
+
"learning_rate": 3.7151702786377715e-05,
|
| 108 |
+
"loss": 0.101,
|
| 109 |
+
"step": 120
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.20155038759689922,
|
| 113 |
+
"grad_norm": 0.74349045753479,
|
| 114 |
+
"learning_rate": 4.024767801857585e-05,
|
| 115 |
+
"loss": 0.1009,
|
| 116 |
+
"step": 130
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.21705426356589147,
|
| 120 |
+
"grad_norm": 0.6830365061759949,
|
| 121 |
+
"learning_rate": 4.3343653250774e-05,
|
| 122 |
+
"loss": 0.096,
|
| 123 |
+
"step": 140
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.23255813953488372,
|
| 127 |
+
"grad_norm": 0.5473061203956604,
|
| 128 |
+
"learning_rate": 4.6439628482972134e-05,
|
| 129 |
+
"loss": 0.074,
|
| 130 |
+
"step": 150
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.23255813953488372,
|
| 134 |
+
"eval_loss": 0.06496970355510712,
|
| 135 |
+
"eval_runtime": 177.3867,
|
| 136 |
+
"eval_samples_per_second": 6.466,
|
| 137 |
+
"eval_steps_per_second": 6.466,
|
| 138 |
+
"step": 150
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.24806201550387597,
|
| 142 |
+
"grad_norm": 0.45949482917785645,
|
| 143 |
+
"learning_rate": 4.953560371517028e-05,
|
| 144 |
+
"loss": 0.076,
|
| 145 |
+
"step": 160
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.26356589147286824,
|
| 149 |
+
"grad_norm": 0.6822295188903809,
|
| 150 |
+
"learning_rate": 5.2631578947368424e-05,
|
| 151 |
+
"loss": 0.0689,
|
| 152 |
+
"step": 170
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.27906976744186046,
|
| 156 |
+
"grad_norm": 0.5395657420158386,
|
| 157 |
+
"learning_rate": 5.5727554179566566e-05,
|
| 158 |
+
"loss": 0.0634,
|
| 159 |
+
"step": 180
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.29457364341085274,
|
| 163 |
+
"grad_norm": 1.2032052278518677,
|
| 164 |
+
"learning_rate": 5.882352941176471e-05,
|
| 165 |
+
"loss": 0.0687,
|
| 166 |
+
"step": 190
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.31007751937984496,
|
| 170 |
+
"grad_norm": 0.8278073072433472,
|
| 171 |
+
"learning_rate": 6.191950464396285e-05,
|
| 172 |
+
"loss": 0.0655,
|
| 173 |
+
"step": 200
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.31007751937984496,
|
| 177 |
+
"eval_loss": 0.06194576248526573,
|
| 178 |
+
"eval_runtime": 177.5104,
|
| 179 |
+
"eval_samples_per_second": 6.462,
|
| 180 |
+
"eval_steps_per_second": 6.462,
|
| 181 |
+
"step": 200
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.32558139534883723,
|
| 185 |
+
"grad_norm": 0.48666349053382874,
|
| 186 |
+
"learning_rate": 6.501547987616098e-05,
|
| 187 |
+
"loss": 0.0591,
|
| 188 |
+
"step": 210
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.34108527131782945,
|
| 192 |
+
"grad_norm": 0.6362942457199097,
|
| 193 |
+
"learning_rate": 6.811145510835913e-05,
|
| 194 |
+
"loss": 0.0557,
|
| 195 |
+
"step": 220
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.35658914728682173,
|
| 199 |
+
"grad_norm": 0.44466376304626465,
|
| 200 |
+
"learning_rate": 7.120743034055728e-05,
|
| 201 |
+
"loss": 0.0531,
|
| 202 |
+
"step": 230
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.37209302325581395,
|
| 206 |
+
"grad_norm": 0.473111093044281,
|
| 207 |
+
"learning_rate": 7.430340557275543e-05,
|
| 208 |
+
"loss": 0.0704,
|
| 209 |
+
"step": 240
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.3875968992248062,
|
| 213 |
+
"grad_norm": 0.6141083836555481,
|
| 214 |
+
"learning_rate": 7.739938080495357e-05,
|
| 215 |
+
"loss": 0.0598,
|
| 216 |
+
"step": 250
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.3875968992248062,
|
| 220 |
+
"eval_loss": 0.05116499215364456,
|
| 221 |
+
"eval_runtime": 177.5255,
|
| 222 |
+
"eval_samples_per_second": 6.461,
|
| 223 |
+
"eval_steps_per_second": 6.461,
|
| 224 |
+
"step": 250
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.40310077519379844,
|
| 228 |
+
"grad_norm": 0.34960028529167175,
|
| 229 |
+
"learning_rate": 8.04953560371517e-05,
|
| 230 |
+
"loss": 0.0502,
|
| 231 |
+
"step": 260
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.4186046511627907,
|
| 235 |
+
"grad_norm": 0.6346738338470459,
|
| 236 |
+
"learning_rate": 8.359133126934985e-05,
|
| 237 |
+
"loss": 0.0469,
|
| 238 |
+
"step": 270
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.43410852713178294,
|
| 242 |
+
"grad_norm": 0.34611088037490845,
|
| 243 |
+
"learning_rate": 8.6687306501548e-05,
|
| 244 |
+
"loss": 0.0769,
|
| 245 |
+
"step": 280
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.4496124031007752,
|
| 249 |
+
"grad_norm": 0.746246337890625,
|
| 250 |
+
"learning_rate": 8.978328173374613e-05,
|
| 251 |
+
"loss": 0.0547,
|
| 252 |
+
"step": 290
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.46511627906976744,
|
| 256 |
+
"grad_norm": 0.3229033350944519,
|
| 257 |
+
"learning_rate": 9.287925696594427e-05,
|
| 258 |
+
"loss": 0.0414,
|
| 259 |
+
"step": 300
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 0.46511627906976744,
|
| 263 |
+
"eval_loss": 0.04494742304086685,
|
| 264 |
+
"eval_runtime": 177.4386,
|
| 265 |
+
"eval_samples_per_second": 6.464,
|
| 266 |
+
"eval_steps_per_second": 6.464,
|
| 267 |
+
"step": 300
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.4806201550387597,
|
| 271 |
+
"grad_norm": 0.7018037438392639,
|
| 272 |
+
"learning_rate": 9.597523219814242e-05,
|
| 273 |
+
"loss": 0.0469,
|
| 274 |
+
"step": 310
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.49612403100775193,
|
| 278 |
+
"grad_norm": 0.3599799871444702,
|
| 279 |
+
"learning_rate": 9.907120743034056e-05,
|
| 280 |
+
"loss": 0.0377,
|
| 281 |
+
"step": 320
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.5116279069767442,
|
| 285 |
+
"grad_norm": 0.3153678774833679,
|
| 286 |
+
"learning_rate": 9.999856438185238e-05,
|
| 287 |
+
"loss": 0.0441,
|
| 288 |
+
"step": 330
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.5271317829457365,
|
| 292 |
+
"grad_norm": 0.2962203621864319,
|
| 293 |
+
"learning_rate": 9.999153298122152e-05,
|
| 294 |
+
"loss": 0.0522,
|
| 295 |
+
"step": 340
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.5426356589147286,
|
| 299 |
+
"grad_norm": 0.1656709760427475,
|
| 300 |
+
"learning_rate": 9.997864293614054e-05,
|
| 301 |
+
"loss": 0.0427,
|
| 302 |
+
"step": 350
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.5426356589147286,
|
| 306 |
+
"eval_loss": 0.04140669107437134,
|
| 307 |
+
"eval_runtime": 177.5437,
|
| 308 |
+
"eval_samples_per_second": 6.46,
|
| 309 |
+
"eval_steps_per_second": 6.46,
|
| 310 |
+
"step": 350
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.5581395348837209,
|
| 314 |
+
"grad_norm": 0.2917194068431854,
|
| 315 |
+
"learning_rate": 9.995989575722902e-05,
|
| 316 |
+
"loss": 0.047,
|
| 317 |
+
"step": 360
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.5736434108527132,
|
| 321 |
+
"grad_norm": 0.3477674424648285,
|
| 322 |
+
"learning_rate": 9.993529364152018e-05,
|
| 323 |
+
"loss": 0.0501,
|
| 324 |
+
"step": 370
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.5891472868217055,
|
| 328 |
+
"grad_norm": 0.48425808548927307,
|
| 329 |
+
"learning_rate": 9.990483947220319e-05,
|
| 330 |
+
"loss": 0.0593,
|
| 331 |
+
"step": 380
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.6046511627906976,
|
| 335 |
+
"grad_norm": 0.21694518625736237,
|
| 336 |
+
"learning_rate": 9.986853681828546e-05,
|
| 337 |
+
"loss": 0.0513,
|
| 338 |
+
"step": 390
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.6201550387596899,
|
| 342 |
+
"grad_norm": 0.5227199792861938,
|
| 343 |
+
"learning_rate": 9.982638993417425e-05,
|
| 344 |
+
"loss": 0.0471,
|
| 345 |
+
"step": 400
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.6201550387596899,
|
| 349 |
+
"eval_loss": 0.038663338869810104,
|
| 350 |
+
"eval_runtime": 177.5346,
|
| 351 |
+
"eval_samples_per_second": 6.461,
|
| 352 |
+
"eval_steps_per_second": 6.461,
|
| 353 |
+
"step": 400
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.6356589147286822,
|
| 357 |
+
"grad_norm": 0.25696733593940735,
|
| 358 |
+
"learning_rate": 9.977840375917817e-05,
|
| 359 |
+
"loss": 0.0475,
|
| 360 |
+
"step": 410
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.6511627906976745,
|
| 364 |
+
"grad_norm": 0.22936882078647614,
|
| 365 |
+
"learning_rate": 9.972458391692827e-05,
|
| 366 |
+
"loss": 0.0405,
|
| 367 |
+
"step": 420
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.6666666666666666,
|
| 371 |
+
"grad_norm": 0.31321045756340027,
|
| 372 |
+
"learning_rate": 9.966493671471904e-05,
|
| 373 |
+
"loss": 0.0449,
|
| 374 |
+
"step": 430
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.6821705426356589,
|
| 378 |
+
"grad_norm": 0.3151184916496277,
|
| 379 |
+
"learning_rate": 9.959946914276922e-05,
|
| 380 |
+
"loss": 0.056,
|
| 381 |
+
"step": 440
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.6976744186046512,
|
| 385 |
+
"grad_norm": 0.50681471824646,
|
| 386 |
+
"learning_rate": 9.952818887340257e-05,
|
| 387 |
+
"loss": 0.0433,
|
| 388 |
+
"step": 450
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.6976744186046512,
|
| 392 |
+
"eval_loss": 0.03619127348065376,
|
| 393 |
+
"eval_runtime": 177.5548,
|
| 394 |
+
"eval_samples_per_second": 6.46,
|
| 395 |
+
"eval_steps_per_second": 6.46,
|
| 396 |
+
"step": 450
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.7131782945736435,
|
| 400 |
+
"grad_norm": 0.31854957342147827,
|
| 401 |
+
"learning_rate": 9.945110426014878e-05,
|
| 402 |
+
"loss": 0.0494,
|
| 403 |
+
"step": 460
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.7286821705426356,
|
| 407 |
+
"grad_norm": 0.28269049525260925,
|
| 408 |
+
"learning_rate": 9.936822433676444e-05,
|
| 409 |
+
"loss": 0.0387,
|
| 410 |
+
"step": 470
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.7441860465116279,
|
| 414 |
+
"grad_norm": 0.24601627886295319,
|
| 415 |
+
"learning_rate": 9.927955881617444e-05,
|
| 416 |
+
"loss": 0.0479,
|
| 417 |
+
"step": 480
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.7596899224806202,
|
| 421 |
+
"grad_norm": 0.19982942938804626,
|
| 422 |
+
"learning_rate": 9.918511808933358e-05,
|
| 423 |
+
"loss": 0.0378,
|
| 424 |
+
"step": 490
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.7751937984496124,
|
| 428 |
+
"grad_norm": 0.20261038839817047,
|
| 429 |
+
"learning_rate": 9.908491322400885e-05,
|
| 430 |
+
"loss": 0.0432,
|
| 431 |
+
"step": 500
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.7751937984496124,
|
| 435 |
+
"eval_loss": 0.03534514829516411,
|
| 436 |
+
"eval_runtime": 177.4652,
|
| 437 |
+
"eval_samples_per_second": 6.463,
|
| 438 |
+
"eval_steps_per_second": 6.463,
|
| 439 |
+
"step": 500
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.7906976744186046,
|
| 443 |
+
"grad_norm": 0.1283186674118042,
|
| 444 |
+
"learning_rate": 9.897895596348247e-05,
|
| 445 |
+
"loss": 0.0395,
|
| 446 |
+
"step": 510
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.8062015503875969,
|
| 450 |
+
"grad_norm": 0.2949117124080658,
|
| 451 |
+
"learning_rate": 9.886725872517552e-05,
|
| 452 |
+
"loss": 0.0326,
|
| 453 |
+
"step": 520
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.8217054263565892,
|
| 457 |
+
"grad_norm": 0.42478370666503906,
|
| 458 |
+
"learning_rate": 9.874983459919277e-05,
|
| 459 |
+
"loss": 0.0442,
|
| 460 |
+
"step": 530
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.8372093023255814,
|
| 464 |
+
"grad_norm": 0.270944207906723,
|
| 465 |
+
"learning_rate": 9.862669734678867e-05,
|
| 466 |
+
"loss": 0.038,
|
| 467 |
+
"step": 540
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.8527131782945736,
|
| 471 |
+
"grad_norm": 0.19820506870746613,
|
| 472 |
+
"learning_rate": 9.849786139875452e-05,
|
| 473 |
+
"loss": 0.0445,
|
| 474 |
+
"step": 550
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.8527131782945736,
|
| 478 |
+
"eval_loss": 0.03533301129937172,
|
| 479 |
+
"eval_runtime": 177.5388,
|
| 480 |
+
"eval_samples_per_second": 6.461,
|
| 481 |
+
"eval_steps_per_second": 6.461,
|
| 482 |
+
"step": 550
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.8682170542635659,
|
| 486 |
+
"grad_norm": 0.33879902958869934,
|
| 487 |
+
"learning_rate": 9.836334185372738e-05,
|
| 488 |
+
"loss": 0.0464,
|
| 489 |
+
"step": 560
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.8837209302325582,
|
| 493 |
+
"grad_norm": 0.330963134765625,
|
| 494 |
+
"learning_rate": 9.822315447642056e-05,
|
| 495 |
+
"loss": 0.0368,
|
| 496 |
+
"step": 570
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.8992248062015504,
|
| 500 |
+
"grad_norm": 0.22305184602737427,
|
| 501 |
+
"learning_rate": 9.807731569577615e-05,
|
| 502 |
+
"loss": 0.0296,
|
| 503 |
+
"step": 580
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 0.9147286821705426,
|
| 507 |
+
"grad_norm": 0.28611594438552856,
|
| 508 |
+
"learning_rate": 9.792584260303964e-05,
|
| 509 |
+
"loss": 0.0364,
|
| 510 |
+
"step": 590
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 0.9302325581395349,
|
| 514 |
+
"grad_norm": 0.24084076285362244,
|
| 515 |
+
"learning_rate": 9.776875294975698e-05,
|
| 516 |
+
"loss": 0.0529,
|
| 517 |
+
"step": 600
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 0.9302325581395349,
|
| 521 |
+
"eval_loss": 0.03533976525068283,
|
| 522 |
+
"eval_runtime": 177.6164,
|
| 523 |
+
"eval_samples_per_second": 6.458,
|
| 524 |
+
"eval_steps_per_second": 6.458,
|
| 525 |
+
"step": 600
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.9457364341085271,
|
| 529 |
+
"grad_norm": 0.28942936658859253,
|
| 530 |
+
"learning_rate": 9.760606514569416e-05,
|
| 531 |
+
"loss": 0.0381,
|
| 532 |
+
"step": 610
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.9612403100775194,
|
| 536 |
+
"grad_norm": 0.2056342214345932,
|
| 537 |
+
"learning_rate": 9.743779825667984e-05,
|
| 538 |
+
"loss": 0.0337,
|
| 539 |
+
"step": 620
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.9767441860465116,
|
| 543 |
+
"grad_norm": 0.14191323518753052,
|
| 544 |
+
"learning_rate": 9.726397200237085e-05,
|
| 545 |
+
"loss": 0.0368,
|
| 546 |
+
"step": 630
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.9922480620155039,
|
| 550 |
+
"grad_norm": 0.33825528621673584,
|
| 551 |
+
"learning_rate": 9.708460675394126e-05,
|
| 552 |
+
"loss": 0.0465,
|
| 553 |
+
"step": 640
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 1.0077519379844961,
|
| 557 |
+
"grad_norm": 0.12557874619960785,
|
| 558 |
+
"learning_rate": 9.689972353169499e-05,
|
| 559 |
+
"loss": 0.0313,
|
| 560 |
+
"step": 650
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 1.0077519379844961,
|
| 564 |
+
"eval_loss": 0.03178540617227554,
|
| 565 |
+
"eval_runtime": 177.627,
|
| 566 |
+
"eval_samples_per_second": 6.457,
|
| 567 |
+
"eval_steps_per_second": 6.457,
|
| 568 |
+
"step": 650
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 1.0232558139534884,
|
| 572 |
+
"grad_norm": 0.35606396198272705,
|
| 573 |
+
"learning_rate": 9.67093440026024e-05,
|
| 574 |
+
"loss": 0.0303,
|
| 575 |
+
"step": 660
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 1.0387596899224807,
|
| 579 |
+
"grad_norm": 0.183203786611557,
|
| 580 |
+
"learning_rate": 9.651349047776112e-05,
|
| 581 |
+
"loss": 0.0386,
|
| 582 |
+
"step": 670
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 1.054263565891473,
|
| 586 |
+
"grad_norm": 0.23599869012832642,
|
| 587 |
+
"learning_rate": 9.631218590978126e-05,
|
| 588 |
+
"loss": 0.0222,
|
| 589 |
+
"step": 680
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 1.069767441860465,
|
| 593 |
+
"grad_norm": 0.13795703649520874,
|
| 594 |
+
"learning_rate": 9.610545389009562e-05,
|
| 595 |
+
"loss": 0.0307,
|
| 596 |
+
"step": 690
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 1.0852713178294573,
|
| 600 |
+
"grad_norm": 0.2756401002407074,
|
| 601 |
+
"learning_rate": 9.589331864619486e-05,
|
| 602 |
+
"loss": 0.0301,
|
| 603 |
+
"step": 700
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 1.0852713178294573,
|
| 607 |
+
"eval_loss": 0.03220707178115845,
|
| 608 |
+
"eval_runtime": 177.6556,
|
| 609 |
+
"eval_samples_per_second": 6.456,
|
| 610 |
+
"eval_steps_per_second": 6.456,
|
| 611 |
+
"step": 700
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.1007751937984496,
|
| 615 |
+
"grad_norm": 0.22982142865657806,
|
| 616 |
+
"learning_rate": 9.567580503878833e-05,
|
| 617 |
+
"loss": 0.025,
|
| 618 |
+
"step": 710
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.1162790697674418,
|
| 622 |
+
"grad_norm": 0.21597911417484283,
|
| 623 |
+
"learning_rate": 9.545293855889043e-05,
|
| 624 |
+
"loss": 0.0342,
|
| 625 |
+
"step": 720
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.1317829457364341,
|
| 629 |
+
"grad_norm": 0.16282838582992554,
|
| 630 |
+
"learning_rate": 9.522474532483337e-05,
|
| 631 |
+
"loss": 0.0275,
|
| 632 |
+
"step": 730
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.1472868217054264,
|
| 636 |
+
"grad_norm": 0.32020196318626404,
|
| 637 |
+
"learning_rate": 9.499125207920622e-05,
|
| 638 |
+
"loss": 0.0402,
|
| 639 |
+
"step": 740
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.1627906976744187,
|
| 643 |
+
"grad_norm": 0.12987101078033447,
|
| 644 |
+
"learning_rate": 9.475248618572096e-05,
|
| 645 |
+
"loss": 0.0289,
|
| 646 |
+
"step": 750
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.1627906976744187,
|
| 650 |
+
"eval_loss": 0.03383904695510864,
|
| 651 |
+
"eval_runtime": 177.667,
|
| 652 |
+
"eval_samples_per_second": 6.456,
|
| 653 |
+
"eval_steps_per_second": 6.456,
|
| 654 |
+
"step": 750
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.178294573643411,
|
| 658 |
+
"grad_norm": 0.37133800983428955,
|
| 659 |
+
"learning_rate": 9.45084756260055e-05,
|
| 660 |
+
"loss": 0.035,
|
| 661 |
+
"step": 760
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.193798449612403,
|
| 665 |
+
"grad_norm": 0.07524913549423218,
|
| 666 |
+
"learning_rate": 9.425924899632458e-05,
|
| 667 |
+
"loss": 0.0291,
|
| 668 |
+
"step": 770
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.2093023255813953,
|
| 672 |
+
"grad_norm": 0.14250116050243378,
|
| 673 |
+
"learning_rate": 9.400483550422845e-05,
|
| 674 |
+
"loss": 0.0221,
|
| 675 |
+
"step": 780
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.2248062015503876,
|
| 679 |
+
"grad_norm": 0.33380234241485596,
|
| 680 |
+
"learning_rate": 9.374526496512992e-05,
|
| 681 |
+
"loss": 0.0303,
|
| 682 |
+
"step": 790
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.2403100775193798,
|
| 686 |
+
"grad_norm": 0.6035688519477844,
|
| 687 |
+
"learning_rate": 9.348056779881025e-05,
|
| 688 |
+
"loss": 0.0267,
|
| 689 |
+
"step": 800
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.2403100775193798,
|
| 693 |
+
"eval_loss": 0.03135337680578232,
|
| 694 |
+
"eval_runtime": 177.6172,
|
| 695 |
+
"eval_samples_per_second": 6.458,
|
| 696 |
+
"eval_steps_per_second": 6.458,
|
| 697 |
+
"step": 800
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 1.255813953488372,
|
| 701 |
+
"grad_norm": 0.25495055317878723,
|
| 702 |
+
"learning_rate": 9.321077502585417e-05,
|
| 703 |
+
"loss": 0.0267,
|
| 704 |
+
"step": 810
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 1.2713178294573644,
|
| 708 |
+
"grad_norm": 0.352885365486145,
|
| 709 |
+
"learning_rate": 9.293591826401451e-05,
|
| 710 |
+
"loss": 0.0351,
|
| 711 |
+
"step": 820
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 1.2868217054263567,
|
| 715 |
+
"grad_norm": 0.25123533606529236,
|
| 716 |
+
"learning_rate": 9.265602972450673e-05,
|
| 717 |
+
"loss": 0.0328,
|
| 718 |
+
"step": 830
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 1.302325581395349,
|
| 722 |
+
"grad_norm": 0.47959160804748535,
|
| 723 |
+
"learning_rate": 9.237114220823413e-05,
|
| 724 |
+
"loss": 0.0326,
|
| 725 |
+
"step": 840
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 1.3178294573643412,
|
| 729 |
+
"grad_norm": 0.13225722312927246,
|
| 730 |
+
"learning_rate": 9.208128910194377e-05,
|
| 731 |
+
"loss": 0.0314,
|
| 732 |
+
"step": 850
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 1.3178294573643412,
|
| 736 |
+
"eval_loss": 0.03171215206384659,
|
| 737 |
+
"eval_runtime": 177.6409,
|
| 738 |
+
"eval_samples_per_second": 6.457,
|
| 739 |
+
"eval_steps_per_second": 6.457,
|
| 740 |
+
"step": 850
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 1.3333333333333333,
|
| 744 |
+
"grad_norm": 0.27190810441970825,
|
| 745 |
+
"learning_rate": 9.17865043743138e-05,
|
| 746 |
+
"loss": 0.031,
|
| 747 |
+
"step": 860
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 1.3488372093023255,
|
| 751 |
+
"grad_norm": 0.10395022481679916,
|
| 752 |
+
"learning_rate": 9.148682257197245e-05,
|
| 753 |
+
"loss": 0.0238,
|
| 754 |
+
"step": 870
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 1.3643410852713178,
|
| 758 |
+
"grad_norm": 0.33697041869163513,
|
| 759 |
+
"learning_rate": 9.118227881544967e-05,
|
| 760 |
+
"loss": 0.0397,
|
| 761 |
+
"step": 880
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 1.37984496124031,
|
| 765 |
+
"grad_norm": 0.2214643359184265,
|
| 766 |
+
"learning_rate": 9.087290879506104e-05,
|
| 767 |
+
"loss": 0.0281,
|
| 768 |
+
"step": 890
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 1.3953488372093024,
|
| 772 |
+
"grad_norm": 0.11761048436164856,
|
| 773 |
+
"learning_rate": 9.055874876672519e-05,
|
| 774 |
+
"loss": 0.0382,
|
| 775 |
+
"step": 900
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 1.3953488372093024,
|
| 779 |
+
"eval_loss": 0.03273608908057213,
|
| 780 |
+
"eval_runtime": 177.7052,
|
| 781 |
+
"eval_samples_per_second": 6.455,
|
| 782 |
+
"eval_steps_per_second": 6.455,
|
| 783 |
+
"step": 900
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 1.4108527131782946,
|
| 787 |
+
"grad_norm": 0.17550455033779144,
|
| 788 |
+
"learning_rate": 9.023983554771492e-05,
|
| 789 |
+
"loss": 0.0263,
|
| 790 |
+
"step": 910
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 1.4263565891472867,
|
| 794 |
+
"grad_norm": 0.21578268706798553,
|
| 795 |
+
"learning_rate": 8.991620651234242e-05,
|
| 796 |
+
"loss": 0.0261,
|
| 797 |
+
"step": 920
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 1.441860465116279,
|
| 801 |
+
"grad_norm": 0.21228443086147308,
|
| 802 |
+
"learning_rate": 8.958789958757928e-05,
|
| 803 |
+
"loss": 0.029,
|
| 804 |
+
"step": 930
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 1.4573643410852712,
|
| 808 |
+
"grad_norm": 0.2734227180480957,
|
| 809 |
+
"learning_rate": 8.925495324861177e-05,
|
| 810 |
+
"loss": 0.0286,
|
| 811 |
+
"step": 940
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 1.4728682170542635,
|
| 815 |
+
"grad_norm": 0.4174731373786926,
|
| 816 |
+
"learning_rate": 8.89174065143318e-05,
|
| 817 |
+
"loss": 0.0354,
|
| 818 |
+
"step": 950
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 1.4728682170542635,
|
| 822 |
+
"eval_loss": 0.031981565058231354,
|
| 823 |
+
"eval_runtime": 177.7226,
|
| 824 |
+
"eval_samples_per_second": 6.454,
|
| 825 |
+
"eval_steps_per_second": 6.454,
|
| 826 |
+
"step": 950
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 1.4883720930232558,
|
| 830 |
+
"grad_norm": 0.3433147370815277,
|
| 831 |
+
"learning_rate": 8.857529894276412e-05,
|
| 832 |
+
"loss": 0.0352,
|
| 833 |
+
"step": 960
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 1.503875968992248,
|
| 837 |
+
"grad_norm": 0.21089136600494385,
|
| 838 |
+
"learning_rate": 8.822867062643059e-05,
|
| 839 |
+
"loss": 0.0298,
|
| 840 |
+
"step": 970
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 1.5193798449612403,
|
| 844 |
+
"grad_norm": 0.1780281960964203,
|
| 845 |
+
"learning_rate": 8.78775621876514e-05,
|
| 846 |
+
"loss": 0.0319,
|
| 847 |
+
"step": 980
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 1.5348837209302326,
|
| 851 |
+
"grad_norm": 0.3001708686351776,
|
| 852 |
+
"learning_rate": 8.752201477378459e-05,
|
| 853 |
+
"loss": 0.0217,
|
| 854 |
+
"step": 990
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 1.550387596899225,
|
| 858 |
+
"grad_norm": 0.15130403637886047,
|
| 859 |
+
"learning_rate": 8.716207005240382e-05,
|
| 860 |
+
"loss": 0.0265,
|
| 861 |
+
"step": 1000
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 1.550387596899225,
|
| 865 |
+
"eval_loss": 0.03209313005208969,
|
| 866 |
+
"eval_runtime": 177.6849,
|
| 867 |
+
"eval_samples_per_second": 6.455,
|
| 868 |
+
"eval_steps_per_second": 6.455,
|
| 869 |
+
"step": 1000
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 1.5658914728682172,
|
| 873 |
+
"grad_norm": 0.28896772861480713,
|
| 874 |
+
"learning_rate": 8.679777020641525e-05,
|
| 875 |
+
"loss": 0.0345,
|
| 876 |
+
"step": 1010
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 1.5813953488372094,
|
| 880 |
+
"grad_norm": 0.4542350471019745,
|
| 881 |
+
"learning_rate": 8.6429157929114e-05,
|
| 882 |
+
"loss": 0.033,
|
| 883 |
+
"step": 1020
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 1.5968992248062015,
|
| 887 |
+
"grad_norm": 0.26365530490875244,
|
| 888 |
+
"learning_rate": 8.60562764191808e-05,
|
| 889 |
+
"loss": 0.0277,
|
| 890 |
+
"step": 1030
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 1.6124031007751938,
|
| 894 |
+
"grad_norm": 0.17537464201450348,
|
| 895 |
+
"learning_rate": 8.567916937561944e-05,
|
| 896 |
+
"loss": 0.0307,
|
| 897 |
+
"step": 1040
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 1.627906976744186,
|
| 901 |
+
"grad_norm": 0.39150458574295044,
|
| 902 |
+
"learning_rate": 8.529788099263554e-05,
|
| 903 |
+
"loss": 0.0301,
|
| 904 |
+
"step": 1050
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 1.627906976744186,
|
| 908 |
+
"eval_loss": 0.03326583281159401,
|
| 909 |
+
"eval_runtime": 177.6473,
|
| 910 |
+
"eval_samples_per_second": 6.457,
|
| 911 |
+
"eval_steps_per_second": 6.457,
|
| 912 |
+
"step": 1050
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 1.6434108527131783,
|
| 916 |
+
"grad_norm": 0.2252993881702423,
|
| 917 |
+
"learning_rate": 8.49124559544573e-05,
|
| 918 |
+
"loss": 0.0279,
|
| 919 |
+
"step": 1060
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 1.6589147286821704,
|
| 923 |
+
"grad_norm": 0.3254898488521576,
|
| 924 |
+
"learning_rate": 8.452293943009889e-05,
|
| 925 |
+
"loss": 0.0269,
|
| 926 |
+
"step": 1070
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 1.6744186046511627,
|
| 930 |
+
"grad_norm": 0.2006569355726242,
|
| 931 |
+
"learning_rate": 8.412937706806692e-05,
|
| 932 |
+
"loss": 0.0361,
|
| 933 |
+
"step": 1080
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 1.689922480620155,
|
| 937 |
+
"grad_norm": 0.2423427700996399,
|
| 938 |
+
"learning_rate": 8.373181499101077e-05,
|
| 939 |
+
"loss": 0.0301,
|
| 940 |
+
"step": 1090
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.7054263565891472,
|
| 944 |
+
"grad_norm": 0.36214545369148254,
|
| 945 |
+
"learning_rate": 8.333029979031737e-05,
|
| 946 |
+
"loss": 0.0262,
|
| 947 |
+
"step": 1100
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 1.7054263565891472,
|
| 951 |
+
"eval_loss": 0.031156621873378754,
|
| 952 |
+
"eval_runtime": 177.8049,
|
| 953 |
+
"eval_samples_per_second": 6.451,
|
| 954 |
+
"eval_steps_per_second": 6.451,
|
| 955 |
+
"step": 1100
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.7209302325581395,
|
| 959 |
+
"grad_norm": 0.17312179505825043,
|
| 960 |
+
"learning_rate": 8.292487852065104e-05,
|
| 961 |
+
"loss": 0.0392,
|
| 962 |
+
"step": 1110
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.7364341085271318,
|
| 966 |
+
"grad_norm": 0.275713711977005,
|
| 967 |
+
"learning_rate": 8.251559869443897e-05,
|
| 968 |
+
"loss": 0.0322,
|
| 969 |
+
"step": 1120
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.751937984496124,
|
| 973 |
+
"grad_norm": 0.33000582456588745,
|
| 974 |
+
"learning_rate": 8.210250827630313e-05,
|
| 975 |
+
"loss": 0.029,
|
| 976 |
+
"step": 1130
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.7674418604651163,
|
| 980 |
+
"grad_norm": 0.29563483595848083,
|
| 981 |
+
"learning_rate": 8.168565567743924e-05,
|
| 982 |
+
"loss": 0.0263,
|
| 983 |
+
"step": 1140
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.7829457364341086,
|
| 987 |
+
"grad_norm": 0.31916943192481995,
|
| 988 |
+
"learning_rate": 8.126508974994321e-05,
|
| 989 |
+
"loss": 0.0273,
|
| 990 |
+
"step": 1150
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.7829457364341086,
|
| 994 |
+
"eval_loss": 0.030605774372816086,
|
| 995 |
+
"eval_runtime": 177.725,
|
| 996 |
+
"eval_samples_per_second": 6.454,
|
| 997 |
+
"eval_steps_per_second": 6.454,
|
| 998 |
+
"step": 1150
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 1.7984496124031009,
|
| 1002 |
+
"grad_norm": 0.1885177344083786,
|
| 1003 |
+
"learning_rate": 8.084085978108611e-05,
|
| 1004 |
+
"loss": 0.0169,
|
| 1005 |
+
"step": 1160
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 1.8139534883720931,
|
| 1009 |
+
"grad_norm": 0.15678612887859344,
|
| 1010 |
+
"learning_rate": 8.041301548753804e-05,
|
| 1011 |
+
"loss": 0.0284,
|
| 1012 |
+
"step": 1170
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 1.8294573643410854,
|
| 1016 |
+
"grad_norm": 0.24891909956932068,
|
| 1017 |
+
"learning_rate": 7.998160700954165e-05,
|
| 1018 |
+
"loss": 0.0244,
|
| 1019 |
+
"step": 1180
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 1.8449612403100775,
|
| 1023 |
+
"grad_norm": 0.27802011370658875,
|
| 1024 |
+
"learning_rate": 7.954668490503621e-05,
|
| 1025 |
+
"loss": 0.027,
|
| 1026 |
+
"step": 1190
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 1.8604651162790697,
|
| 1030 |
+
"grad_norm": 0.2340599000453949,
|
| 1031 |
+
"learning_rate": 7.910830014373237e-05,
|
| 1032 |
+
"loss": 0.0283,
|
| 1033 |
+
"step": 1200
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 1.8604651162790697,
|
| 1037 |
+
"eval_loss": 0.029726749286055565,
|
| 1038 |
+
"eval_runtime": 177.8483,
|
| 1039 |
+
"eval_samples_per_second": 6.449,
|
| 1040 |
+
"eval_steps_per_second": 6.449,
|
| 1041 |
+
"step": 1200
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 1.875968992248062,
|
| 1045 |
+
"grad_norm": 0.13624481856822968,
|
| 1046 |
+
"learning_rate": 7.866650410113907e-05,
|
| 1047 |
+
"loss": 0.0243,
|
| 1048 |
+
"step": 1210
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 1.8914728682170543,
|
| 1052 |
+
"grad_norm": 0.30038079619407654,
|
| 1053 |
+
"learning_rate": 7.822134855254263e-05,
|
| 1054 |
+
"loss": 0.0296,
|
| 1055 |
+
"step": 1220
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 1.9069767441860463,
|
| 1059 |
+
"grad_norm": 0.23166057467460632,
|
| 1060 |
+
"learning_rate": 7.777288566693905e-05,
|
| 1061 |
+
"loss": 0.0273,
|
| 1062 |
+
"step": 1230
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 1.9224806201550386,
|
| 1066 |
+
"grad_norm": 0.26034536957740784,
|
| 1067 |
+
"learning_rate": 7.732116800092018e-05,
|
| 1068 |
+
"loss": 0.029,
|
| 1069 |
+
"step": 1240
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 1.937984496124031,
|
| 1073 |
+
"grad_norm": 0.2269134223461151,
|
| 1074 |
+
"learning_rate": 7.686624849251453e-05,
|
| 1075 |
+
"loss": 0.0381,
|
| 1076 |
+
"step": 1250
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 1.937984496124031,
|
| 1080 |
+
"eval_loss": 0.029867732897400856,
|
| 1081 |
+
"eval_runtime": 177.8147,
|
| 1082 |
+
"eval_samples_per_second": 6.451,
|
| 1083 |
+
"eval_steps_per_second": 6.451,
|
| 1084 |
+
"step": 1250
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 1.9534883720930232,
|
| 1088 |
+
"grad_norm": 0.30028459429740906,
|
| 1089 |
+
"learning_rate": 7.640818045498324e-05,
|
| 1090 |
+
"loss": 0.0378,
|
| 1091 |
+
"step": 1260
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 1.9689922480620154,
|
| 1095 |
+
"grad_norm": 0.10794702172279358,
|
| 1096 |
+
"learning_rate": 7.59470175705722e-05,
|
| 1097 |
+
"loss": 0.0303,
|
| 1098 |
+
"step": 1270
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 1.9844961240310077,
|
| 1102 |
+
"grad_norm": 0.27119511365890503,
|
| 1103 |
+
"learning_rate": 7.548281388422088e-05,
|
| 1104 |
+
"loss": 0.0361,
|
| 1105 |
+
"step": 1280
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 2.0,
|
| 1109 |
+
"grad_norm": 0.22147968411445618,
|
| 1110 |
+
"learning_rate": 7.50156237972286e-05,
|
| 1111 |
+
"loss": 0.0263,
|
| 1112 |
+
"step": 1290
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 2.0155038759689923,
|
| 1116 |
+
"grad_norm": 0.12922464311122894,
|
| 1117 |
+
"learning_rate": 7.454550206087921e-05,
|
| 1118 |
+
"loss": 0.0207,
|
| 1119 |
+
"step": 1300
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 2.0155038759689923,
|
| 1123 |
+
"eval_loss": 0.029372563585639,
|
| 1124 |
+
"eval_runtime": 177.7077,
|
| 1125 |
+
"eval_samples_per_second": 6.454,
|
| 1126 |
+
"eval_steps_per_second": 6.454,
|
| 1127 |
+
"step": 1300
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 2.0310077519379846,
|
| 1131 |
+
"grad_norm": 0.20252908766269684,
|
| 1132 |
+
"learning_rate": 7.407250377002451e-05,
|
| 1133 |
+
"loss": 0.0184,
|
| 1134 |
+
"step": 1310
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 2.046511627906977,
|
| 1138 |
+
"grad_norm": 0.20628713071346283,
|
| 1139 |
+
"learning_rate": 7.359668435662757e-05,
|
| 1140 |
+
"loss": 0.0216,
|
| 1141 |
+
"step": 1320
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 2.062015503875969,
|
| 1145 |
+
"grad_norm": 0.16820959746837616,
|
| 1146 |
+
"learning_rate": 7.311809958326659e-05,
|
| 1147 |
+
"loss": 0.0153,
|
| 1148 |
+
"step": 1330
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 2.0775193798449614,
|
| 1152 |
+
"grad_norm": 0.28085780143737793,
|
| 1153 |
+
"learning_rate": 7.263680553659983e-05,
|
| 1154 |
+
"loss": 0.0172,
|
| 1155 |
+
"step": 1340
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 2.0930232558139537,
|
| 1159 |
+
"grad_norm": 0.4147201180458069,
|
| 1160 |
+
"learning_rate": 7.21528586207927e-05,
|
| 1161 |
+
"loss": 0.0163,
|
| 1162 |
+
"step": 1350
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 2.0930232558139537,
|
| 1166 |
+
"eval_loss": 0.03293036296963692,
|
| 1167 |
+
"eval_runtime": 177.2709,
|
| 1168 |
+
"eval_samples_per_second": 6.47,
|
| 1169 |
+
"eval_steps_per_second": 6.47,
|
| 1170 |
+
"step": 1350
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 2.108527131782946,
|
| 1174 |
+
"grad_norm": 0.2516096830368042,
|
| 1175 |
+
"learning_rate": 7.166631555090759e-05,
|
| 1176 |
+
"loss": 0.025,
|
| 1177 |
+
"step": 1360
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 2.124031007751938,
|
| 1181 |
+
"grad_norm": 0.26919105648994446,
|
| 1182 |
+
"learning_rate": 7.117723334625731e-05,
|
| 1183 |
+
"loss": 0.024,
|
| 1184 |
+
"step": 1370
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 2.13953488372093,
|
| 1188 |
+
"grad_norm": 0.228290855884552,
|
| 1189 |
+
"learning_rate": 7.068566932372278e-05,
|
| 1190 |
+
"loss": 0.0183,
|
| 1191 |
+
"step": 1380
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 2.1550387596899223,
|
| 1195 |
+
"grad_norm": 0.28446343541145325,
|
| 1196 |
+
"learning_rate": 7.019168109103599e-05,
|
| 1197 |
+
"loss": 0.0162,
|
| 1198 |
+
"step": 1390
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 2.1705426356589146,
|
| 1202 |
+
"grad_norm": 0.19133096933364868,
|
| 1203 |
+
"learning_rate": 6.96953265400287e-05,
|
| 1204 |
+
"loss": 0.0236,
|
| 1205 |
+
"step": 1400
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 2.1705426356589146,
|
| 1209 |
+
"eval_loss": 0.031053410843014717,
|
| 1210 |
+
"eval_runtime": 176.3297,
|
| 1211 |
+
"eval_samples_per_second": 6.505,
|
| 1212 |
+
"eval_steps_per_second": 6.505,
|
| 1213 |
+
"step": 1400
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 2.186046511627907,
|
| 1217 |
+
"grad_norm": 0.14185263216495514,
|
| 1218 |
+
"learning_rate": 6.9196663839848e-05,
|
| 1219 |
+
"loss": 0.0142,
|
| 1220 |
+
"step": 1410
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 2.201550387596899,
|
| 1224 |
+
"grad_norm": 0.2277035117149353,
|
| 1225 |
+
"learning_rate": 6.869575143013934e-05,
|
| 1226 |
+
"loss": 0.0166,
|
| 1227 |
+
"step": 1420
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 2.2170542635658914,
|
| 1231 |
+
"grad_norm": 0.24037382006645203,
|
| 1232 |
+
"learning_rate": 6.819264801419771e-05,
|
| 1233 |
+
"loss": 0.0274,
|
| 1234 |
+
"step": 1430
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 2.2325581395348837,
|
| 1238 |
+
"grad_norm": 0.10074973106384277,
|
| 1239 |
+
"learning_rate": 6.768741255208813e-05,
|
| 1240 |
+
"loss": 0.0154,
|
| 1241 |
+
"step": 1440
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 2.248062015503876,
|
| 1245 |
+
"grad_norm": 0.24921472370624542,
|
| 1246 |
+
"learning_rate": 6.718010425373599e-05,
|
| 1247 |
+
"loss": 0.0191,
|
| 1248 |
+
"step": 1450
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 2.248062015503876,
|
| 1252 |
+
"eval_loss": 0.030957119539380074,
|
| 1253 |
+
"eval_runtime": 175.6681,
|
| 1254 |
+
"eval_samples_per_second": 6.529,
|
| 1255 |
+
"eval_steps_per_second": 6.529,
|
| 1256 |
+
"step": 1450
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 2.2635658914728682,
|
| 1260 |
+
"grad_norm": 0.22070886194705963,
|
| 1261 |
+
"learning_rate": 6.667078257198796e-05,
|
| 1262 |
+
"loss": 0.0184,
|
| 1263 |
+
"step": 1460
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 2.2790697674418605,
|
| 1267 |
+
"grad_norm": 0.39727696776390076,
|
| 1268 |
+
"learning_rate": 6.615950719564466e-05,
|
| 1269 |
+
"loss": 0.0142,
|
| 1270 |
+
"step": 1470
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 2.294573643410853,
|
| 1274 |
+
"grad_norm": 0.31478437781333923,
|
| 1275 |
+
"learning_rate": 6.56463380424655e-05,
|
| 1276 |
+
"loss": 0.0252,
|
| 1277 |
+
"step": 1480
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 2.310077519379845,
|
| 1281 |
+
"grad_norm": 0.1986107975244522,
|
| 1282 |
+
"learning_rate": 6.51313352521468e-05,
|
| 1283 |
+
"loss": 0.0151,
|
| 1284 |
+
"step": 1490
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 2.3255813953488373,
|
| 1288 |
+
"grad_norm": 0.3045531213283539,
|
| 1289 |
+
"learning_rate": 6.46145591792738e-05,
|
| 1290 |
+
"loss": 0.0243,
|
| 1291 |
+
"step": 1500
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 2.3255813953488373,
|
| 1295 |
+
"eval_loss": 0.03084620088338852,
|
| 1296 |
+
"eval_runtime": 175.2668,
|
| 1297 |
+
"eval_samples_per_second": 6.544,
|
| 1298 |
+
"eval_steps_per_second": 6.544,
|
| 1299 |
+
"step": 1500
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 2.3410852713178296,
|
| 1303 |
+
"grad_norm": 0.08667182922363281,
|
| 1304 |
+
"learning_rate": 6.409607038624759e-05,
|
| 1305 |
+
"loss": 0.0142,
|
| 1306 |
+
"step": 1510
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 2.356589147286822,
|
| 1310 |
+
"grad_norm": 0.17333078384399414,
|
| 1311 |
+
"learning_rate": 6.357592963618761e-05,
|
| 1312 |
+
"loss": 0.0241,
|
| 1313 |
+
"step": 1520
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 2.3720930232558137,
|
| 1317 |
+
"grad_norm": 0.20276910066604614,
|
| 1318 |
+
"learning_rate": 6.305419788581067e-05,
|
| 1319 |
+
"loss": 0.0185,
|
| 1320 |
+
"step": 1530
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 2.387596899224806,
|
| 1324 |
+
"grad_norm": 0.287349134683609,
|
| 1325 |
+
"learning_rate": 6.253093627828724e-05,
|
| 1326 |
+
"loss": 0.0176,
|
| 1327 |
+
"step": 1540
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 2.4031007751937983,
|
| 1331 |
+
"grad_norm": 0.32019197940826416,
|
| 1332 |
+
"learning_rate": 6.200620613607597e-05,
|
| 1333 |
+
"loss": 0.0165,
|
| 1334 |
+
"step": 1550
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 2.4031007751937983,
|
| 1338 |
+
"eval_loss": 0.03274994716048241,
|
| 1339 |
+
"eval_runtime": 174.5607,
|
| 1340 |
+
"eval_samples_per_second": 6.571,
|
| 1341 |
+
"eval_steps_per_second": 6.571,
|
| 1342 |
+
"step": 1550
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 2.4186046511627906,
|
| 1346 |
+
"grad_norm": 0.34726911783218384,
|
| 1347 |
+
"learning_rate": 6.148006895373706e-05,
|
| 1348 |
+
"loss": 0.0196,
|
| 1349 |
+
"step": 1560
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 2.434108527131783,
|
| 1353 |
+
"grad_norm": 0.15877018868923187,
|
| 1354 |
+
"learning_rate": 6.0952586390725644e-05,
|
| 1355 |
+
"loss": 0.0171,
|
| 1356 |
+
"step": 1570
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 2.449612403100775,
|
| 1360 |
+
"grad_norm": 0.21150444447994232,
|
| 1361 |
+
"learning_rate": 6.042382026416563e-05,
|
| 1362 |
+
"loss": 0.0164,
|
| 1363 |
+
"step": 1580
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 2.4651162790697674,
|
| 1367 |
+
"grad_norm": 0.19103744626045227,
|
| 1368 |
+
"learning_rate": 5.989383254160529e-05,
|
| 1369 |
+
"loss": 0.0171,
|
| 1370 |
+
"step": 1590
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 2.4806201550387597,
|
| 1374 |
+
"grad_norm": 0.44117987155914307,
|
| 1375 |
+
"learning_rate": 5.936268533375506e-05,
|
| 1376 |
+
"loss": 0.0224,
|
| 1377 |
+
"step": 1600
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 2.4806201550387597,
|
| 1381 |
+
"eval_loss": 0.03294115141034126,
|
| 1382 |
+
"eval_runtime": 174.4995,
|
| 1383 |
+
"eval_samples_per_second": 6.573,
|
| 1384 |
+
"eval_steps_per_second": 6.573,
|
| 1385 |
+
"step": 1600
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 2.496124031007752,
|
| 1389 |
+
"grad_norm": 0.3606320321559906,
|
| 1390 |
+
"learning_rate": 5.883044088720865e-05,
|
| 1391 |
+
"loss": 0.0214,
|
| 1392 |
+
"step": 1610
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 2.511627906976744,
|
| 1396 |
+
"grad_norm": 0.13814851641654968,
|
| 1397 |
+
"learning_rate": 5.829716157714814e-05,
|
| 1398 |
+
"loss": 0.0177,
|
| 1399 |
+
"step": 1620
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 2.5271317829457365,
|
| 1403 |
+
"grad_norm": 0.23484356701374054,
|
| 1404 |
+
"learning_rate": 5.77629099000341e-05,
|
| 1405 |
+
"loss": 0.0263,
|
| 1406 |
+
"step": 1630
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 2.5426356589147288,
|
| 1410 |
+
"grad_norm": 0.21404676139354706,
|
| 1411 |
+
"learning_rate": 5.7227748466281486e-05,
|
| 1412 |
+
"loss": 0.0187,
|
| 1413 |
+
"step": 1640
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 2.558139534883721,
|
| 1417 |
+
"grad_norm": 0.3276318609714508,
|
| 1418 |
+
"learning_rate": 5.669173999292208e-05,
|
| 1419 |
+
"loss": 0.0289,
|
| 1420 |
+
"step": 1650
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 2.558139534883721,
|
| 1424 |
+
"eval_loss": 0.03190125152468681,
|
| 1425 |
+
"eval_runtime": 174.4148,
|
| 1426 |
+
"eval_samples_per_second": 6.576,
|
| 1427 |
+
"eval_steps_per_second": 6.576,
|
| 1428 |
+
"step": 1650
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 2.5736434108527133,
|
| 1432 |
+
"grad_norm": 0.41611889004707336,
|
| 1433 |
+
"learning_rate": 5.615494729625458e-05,
|
| 1434 |
+
"loss": 0.0237,
|
| 1435 |
+
"step": 1660
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 2.5891472868217056,
|
| 1439 |
+
"grad_norm": 0.372302383184433,
|
| 1440 |
+
"learning_rate": 5.561743328448296e-05,
|
| 1441 |
+
"loss": 0.0246,
|
| 1442 |
+
"step": 1670
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 2.604651162790698,
|
| 1446 |
+
"grad_norm": 0.1654350608587265,
|
| 1447 |
+
"learning_rate": 5.5079260950344035e-05,
|
| 1448 |
+
"loss": 0.019,
|
| 1449 |
+
"step": 1680
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 2.62015503875969,
|
| 1453 |
+
"grad_norm": 0.09135215729475021,
|
| 1454 |
+
"learning_rate": 5.454049336372531e-05,
|
| 1455 |
+
"loss": 0.0165,
|
| 1456 |
+
"step": 1690
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 2.6356589147286824,
|
| 1460 |
+
"grad_norm": 0.24403300881385803,
|
| 1461 |
+
"learning_rate": 5.4001193664273454e-05,
|
| 1462 |
+
"loss": 0.014,
|
| 1463 |
+
"step": 1700
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 2.6356589147286824,
|
| 1467 |
+
"eval_loss": 0.03161098435521126,
|
| 1468 |
+
"eval_runtime": 174.2648,
|
| 1469 |
+
"eval_samples_per_second": 6.582,
|
| 1470 |
+
"eval_steps_per_second": 6.582,
|
| 1471 |
+
"step": 1700
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 2.6511627906976747,
|
| 1475 |
+
"grad_norm": 0.19514554738998413,
|
| 1476 |
+
"learning_rate": 5.346142505399495e-05,
|
| 1477 |
+
"loss": 0.0198,
|
| 1478 |
+
"step": 1710
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 2.6666666666666665,
|
| 1482 |
+
"grad_norm": 0.13203318417072296,
|
| 1483 |
+
"learning_rate": 5.292125078984925e-05,
|
| 1484 |
+
"loss": 0.0181,
|
| 1485 |
+
"step": 1720
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 2.682170542635659,
|
| 1489 |
+
"grad_norm": 0.09618645161390305,
|
| 1490 |
+
"learning_rate": 5.2380734176335425e-05,
|
| 1491 |
+
"loss": 0.0171,
|
| 1492 |
+
"step": 1730
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 2.697674418604651,
|
| 1496 |
+
"grad_norm": 0.17840640246868134,
|
| 1497 |
+
"learning_rate": 5.183993855807343e-05,
|
| 1498 |
+
"loss": 0.0186,
|
| 1499 |
+
"step": 1740
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 2.7131782945736433,
|
| 1503 |
+
"grad_norm": 0.12565214931964874,
|
| 1504 |
+
"learning_rate": 5.1298927312380586e-05,
|
| 1505 |
+
"loss": 0.0182,
|
| 1506 |
+
"step": 1750
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 2.7131782945736433,
|
| 1510 |
+
"eval_loss": 0.03337998315691948,
|
| 1511 |
+
"eval_runtime": 174.2061,
|
| 1512 |
+
"eval_samples_per_second": 6.584,
|
| 1513 |
+
"eval_steps_per_second": 6.584,
|
| 1514 |
+
"step": 1750
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 2.7286821705426356,
|
| 1518 |
+
"grad_norm": 0.1932082623243332,
|
| 1519 |
+
"learning_rate": 5.075776384184411e-05,
|
| 1520 |
+
"loss": 0.0275,
|
| 1521 |
+
"step": 1760
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 2.744186046511628,
|
| 1525 |
+
"grad_norm": 0.14624637365341187,
|
| 1526 |
+
"learning_rate": 5.021651156689094e-05,
|
| 1527 |
+
"loss": 0.0284,
|
| 1528 |
+
"step": 1770
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 2.75968992248062,
|
| 1532 |
+
"grad_norm": 0.20881560444831848,
|
| 1533 |
+
"learning_rate": 4.967523391835521e-05,
|
| 1534 |
+
"loss": 0.0217,
|
| 1535 |
+
"step": 1780
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 2.7751937984496124,
|
| 1539 |
+
"grad_norm": 0.2833938002586365,
|
| 1540 |
+
"learning_rate": 4.9133994330044644e-05,
|
| 1541 |
+
"loss": 0.0234,
|
| 1542 |
+
"step": 1790
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 2.7906976744186047,
|
| 1546 |
+
"grad_norm": 0.23201899230480194,
|
| 1547 |
+
"learning_rate": 4.85928562313066e-05,
|
| 1548 |
+
"loss": 0.0175,
|
| 1549 |
+
"step": 1800
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 2.7906976744186047,
|
| 1553 |
+
"eval_loss": 0.029777053743600845,
|
| 1554 |
+
"eval_runtime": 174.1005,
|
| 1555 |
+
"eval_samples_per_second": 6.588,
|
| 1556 |
+
"eval_steps_per_second": 6.588,
|
| 1557 |
+
"step": 1800
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 2.806201550387597,
|
| 1561 |
+
"grad_norm": 0.2119215726852417,
|
| 1562 |
+
"learning_rate": 4.8051883039594616e-05,
|
| 1563 |
+
"loss": 0.0151,
|
| 1564 |
+
"step": 1810
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 2.8217054263565893,
|
| 1568 |
+
"grad_norm": 0.30587702989578247,
|
| 1569 |
+
"learning_rate": 4.751113815303624e-05,
|
| 1570 |
+
"loss": 0.0187,
|
| 1571 |
+
"step": 1820
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 2.8372093023255816,
|
| 1575 |
+
"grad_norm": 0.18018727004528046,
|
| 1576 |
+
"learning_rate": 4.697068494300343e-05,
|
| 1577 |
+
"loss": 0.0151,
|
| 1578 |
+
"step": 1830
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 2.8527131782945734,
|
| 1582 |
+
"grad_norm": 0.21248644590377808,
|
| 1583 |
+
"learning_rate": 4.6430586746685724e-05,
|
| 1584 |
+
"loss": 0.0222,
|
| 1585 |
+
"step": 1840
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 2.8682170542635657,
|
| 1589 |
+
"grad_norm": 0.18737761676311493,
|
| 1590 |
+
"learning_rate": 4.589090685966758e-05,
|
| 1591 |
+
"loss": 0.0218,
|
| 1592 |
+
"step": 1850
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 2.8682170542635657,
|
| 1596 |
+
"eval_loss": 0.029682571068406105,
|
| 1597 |
+
"eval_runtime": 174.0789,
|
| 1598 |
+
"eval_samples_per_second": 6.589,
|
| 1599 |
+
"eval_steps_per_second": 6.589,
|
| 1600 |
+
"step": 1850
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 2.883720930232558,
|
| 1604 |
+
"grad_norm": 0.3078942894935608,
|
| 1605 |
+
"learning_rate": 4.535170852851073e-05,
|
| 1606 |
+
"loss": 0.0265,
|
| 1607 |
+
"step": 1860
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 2.89922480620155,
|
| 1611 |
+
"grad_norm": 0.2036602944135666,
|
| 1612 |
+
"learning_rate": 4.481305494334201e-05,
|
| 1613 |
+
"loss": 0.0167,
|
| 1614 |
+
"step": 1870
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 2.9147286821705425,
|
| 1618 |
+
"grad_norm": 0.08146923035383224,
|
| 1619 |
+
"learning_rate": 4.427500923044801e-05,
|
| 1620 |
+
"loss": 0.0199,
|
| 1621 |
+
"step": 1880
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 2.9302325581395348,
|
| 1625 |
+
"grad_norm": 0.12505419552326202,
|
| 1626 |
+
"learning_rate": 4.373763444487705e-05,
|
| 1627 |
+
"loss": 0.0179,
|
| 1628 |
+
"step": 1890
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 2.945736434108527,
|
| 1632 |
+
"grad_norm": 0.18068896234035492,
|
| 1633 |
+
"learning_rate": 4.3200993563049725e-05,
|
| 1634 |
+
"loss": 0.018,
|
| 1635 |
+
"step": 1900
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 2.945736434108527,
|
| 1639 |
+
"eval_loss": 0.02887474000453949,
|
| 1640 |
+
"eval_runtime": 173.8738,
|
| 1641 |
+
"eval_samples_per_second": 6.597,
|
| 1642 |
+
"eval_steps_per_second": 6.597,
|
| 1643 |
+
"step": 1900
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 2.9612403100775193,
|
| 1647 |
+
"grad_norm": 0.19300121068954468,
|
| 1648 |
+
"learning_rate": 4.266514947537839e-05,
|
| 1649 |
+
"loss": 0.0157,
|
| 1650 |
+
"step": 1910
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 2.9767441860465116,
|
| 1654 |
+
"grad_norm": 0.1891685128211975,
|
| 1655 |
+
"learning_rate": 4.2130164978896916e-05,
|
| 1656 |
+
"loss": 0.0188,
|
| 1657 |
+
"step": 1920
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 2.992248062015504,
|
| 1661 |
+
"grad_norm": 0.027009131386876106,
|
| 1662 |
+
"learning_rate": 4.159610276990137e-05,
|
| 1663 |
+
"loss": 0.0118,
|
| 1664 |
+
"step": 1930
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 3.007751937984496,
|
| 1668 |
+
"grad_norm": 0.11215299367904663,
|
| 1669 |
+
"learning_rate": 4.106302543660235e-05,
|
| 1670 |
+
"loss": 0.0164,
|
| 1671 |
+
"step": 1940
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 3.0232558139534884,
|
| 1675 |
+
"grad_norm": 0.07163859158754349,
|
| 1676 |
+
"learning_rate": 4.053099545179028e-05,
|
| 1677 |
+
"loss": 0.01,
|
| 1678 |
+
"step": 1950
|
| 1679 |
+
},
|
| 1680 |
+
{
|
| 1681 |
+
"epoch": 3.0232558139534884,
|
| 1682 |
+
"eval_loss": 0.030872860923409462,
|
| 1683 |
+
"eval_runtime": 173.945,
|
| 1684 |
+
"eval_samples_per_second": 6.594,
|
| 1685 |
+
"eval_steps_per_second": 6.594,
|
| 1686 |
+
"step": 1950
|
| 1687 |
+
},
|
| 1688 |
+
{
|
| 1689 |
+
"epoch": 3.0387596899224807,
|
| 1690 |
+
"grad_norm": 0.12158221006393433,
|
| 1691 |
+
"learning_rate": 4.0000075165513845e-05,
|
| 1692 |
+
"loss": 0.014,
|
| 1693 |
+
"step": 1960
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 3.054263565891473,
|
| 1697 |
+
"grad_norm": 0.17903171479701996,
|
| 1698 |
+
"learning_rate": 3.9470326797773216e-05,
|
| 1699 |
+
"loss": 0.0085,
|
| 1700 |
+
"step": 1970
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 3.0697674418604652,
|
| 1704 |
+
"grad_norm": 0.23486894369125366,
|
| 1705 |
+
"learning_rate": 3.8941812431228166e-05,
|
| 1706 |
+
"loss": 0.012,
|
| 1707 |
+
"step": 1980
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 3.0852713178294575,
|
| 1711 |
+
"grad_norm": 0.19141437113285065,
|
| 1712 |
+
"learning_rate": 3.8414594003922515e-05,
|
| 1713 |
+
"loss": 0.0141,
|
| 1714 |
+
"step": 1990
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 3.10077519379845,
|
| 1718 |
+
"grad_norm": 0.047276828438043594,
|
| 1719 |
+
"learning_rate": 3.788873330202544e-05,
|
| 1720 |
+
"loss": 0.0109,
|
| 1721 |
+
"step": 2000
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 3.10077519379845,
|
| 1725 |
+
"eval_loss": 0.033768460154533386,
|
| 1726 |
+
"eval_runtime": 173.8687,
|
| 1727 |
+
"eval_samples_per_second": 6.597,
|
| 1728 |
+
"eval_steps_per_second": 6.597,
|
| 1729 |
+
"step": 2000
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 3.116279069767442,
|
| 1733 |
+
"grad_norm": 0.3079964518547058,
|
| 1734 |
+
"learning_rate": 3.736429195259051e-05,
|
| 1735 |
+
"loss": 0.0069,
|
| 1736 |
+
"step": 2010
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 3.1317829457364343,
|
| 1740 |
+
"grad_norm": 0.207097128033638,
|
| 1741 |
+
"learning_rate": 3.684133141633358e-05,
|
| 1742 |
+
"loss": 0.009,
|
| 1743 |
+
"step": 2020
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 3.147286821705426,
|
| 1747 |
+
"grad_norm": 0.16703131794929504,
|
| 1748 |
+
"learning_rate": 3.6319912980429846e-05,
|
| 1749 |
+
"loss": 0.0098,
|
| 1750 |
+
"step": 2030
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 3.1627906976744184,
|
| 1754 |
+
"grad_norm": 0.1511267125606537,
|
| 1755 |
+
"learning_rate": 3.580009775133168e-05,
|
| 1756 |
+
"loss": 0.0076,
|
| 1757 |
+
"step": 2040
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 3.1782945736434107,
|
| 1761 |
+
"grad_norm": 0.184535413980484,
|
| 1762 |
+
"learning_rate": 3.528194664760714e-05,
|
| 1763 |
+
"loss": 0.0076,
|
| 1764 |
+
"step": 2050
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 3.1782945736434107,
|
| 1768 |
+
"eval_loss": 0.03470822051167488,
|
| 1769 |
+
"eval_runtime": 173.7828,
|
| 1770 |
+
"eval_samples_per_second": 6.6,
|
| 1771 |
+
"eval_steps_per_second": 6.6,
|
| 1772 |
+
"step": 2050
|
| 1773 |
+
},
|
| 1774 |
+
{
|
| 1775 |
+
"epoch": 3.193798449612403,
|
| 1776 |
+
"grad_norm": 0.19592364132404327,
|
| 1777 |
+
"learning_rate": 3.476552039280096e-05,
|
| 1778 |
+
"loss": 0.0089,
|
| 1779 |
+
"step": 2060
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 3.2093023255813953,
|
| 1783 |
+
"grad_norm": 0.1496165543794632,
|
| 1784 |
+
"learning_rate": 3.42508795083181e-05,
|
| 1785 |
+
"loss": 0.0092,
|
| 1786 |
+
"step": 2070
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 3.2248062015503876,
|
| 1790 |
+
"grad_norm": 0.19381049275398254,
|
| 1791 |
+
"learning_rate": 3.373808430633106e-05,
|
| 1792 |
+
"loss": 0.0086,
|
| 1793 |
+
"step": 2080
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 3.24031007751938,
|
| 1797 |
+
"grad_norm": 0.30487295985221863,
|
| 1798 |
+
"learning_rate": 3.32271948827118e-05,
|
| 1799 |
+
"loss": 0.0099,
|
| 1800 |
+
"step": 2090
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"epoch": 3.255813953488372,
|
| 1804 |
+
"grad_norm": 0.21724191308021545,
|
| 1805 |
+
"learning_rate": 3.2718271109988863e-05,
|
| 1806 |
+
"loss": 0.0087,
|
| 1807 |
+
"step": 2100
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 3.255813953488372,
|
| 1811 |
+
"eval_loss": 0.03577126935124397,
|
| 1812 |
+
"eval_runtime": 173.7017,
|
| 1813 |
+
"eval_samples_per_second": 6.603,
|
| 1814 |
+
"eval_steps_per_second": 6.603,
|
| 1815 |
+
"step": 2100
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 3.2713178294573644,
|
| 1819 |
+
"grad_norm": 0.8536518812179565,
|
| 1820 |
+
"learning_rate": 3.2211372630330835e-05,
|
| 1821 |
+
"loss": 0.0094,
|
| 1822 |
+
"step": 2110
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 3.2868217054263567,
|
| 1826 |
+
"grad_norm": 0.23373013734817505,
|
| 1827 |
+
"learning_rate": 3.170655884855661e-05,
|
| 1828 |
+
"loss": 0.0121,
|
| 1829 |
+
"step": 2120
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 3.302325581395349,
|
| 1833 |
+
"grad_norm": 0.09981165081262589,
|
| 1834 |
+
"learning_rate": 3.120388892517368e-05,
|
| 1835 |
+
"loss": 0.0193,
|
| 1836 |
+
"step": 2130
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 3.317829457364341,
|
| 1840 |
+
"grad_norm": 0.2072608470916748,
|
| 1841 |
+
"learning_rate": 3.070342176944494e-05,
|
| 1842 |
+
"loss": 0.0135,
|
| 1843 |
+
"step": 2140
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 3.3333333333333335,
|
| 1847 |
+
"grad_norm": 0.07687430083751678,
|
| 1848 |
+
"learning_rate": 3.0205216032484805e-05,
|
| 1849 |
+
"loss": 0.0092,
|
| 1850 |
+
"step": 2150
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 3.3333333333333335,
|
| 1854 |
+
"eval_loss": 0.032335054129362106,
|
| 1855 |
+
"eval_runtime": 173.7494,
|
| 1856 |
+
"eval_samples_per_second": 6.601,
|
| 1857 |
+
"eval_steps_per_second": 6.601,
|
| 1858 |
+
"step": 2150
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 3.3488372093023258,
|
| 1862 |
+
"grad_norm": 0.2054612785577774,
|
| 1863 |
+
"learning_rate": 2.970933010038599e-05,
|
| 1864 |
+
"loss": 0.013,
|
| 1865 |
+
"step": 2160
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 3.3643410852713176,
|
| 1869 |
+
"grad_norm": 0.17977559566497803,
|
| 1870 |
+
"learning_rate": 2.921582208737681e-05,
|
| 1871 |
+
"loss": 0.0088,
|
| 1872 |
+
"step": 2170
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 3.37984496124031,
|
| 1876 |
+
"grad_norm": 0.23377564549446106,
|
| 1877 |
+
"learning_rate": 2.872474982901081e-05,
|
| 1878 |
+
"loss": 0.0136,
|
| 1879 |
+
"step": 2180
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 3.395348837209302,
|
| 1883 |
+
"grad_norm": 0.16202200949192047,
|
| 1884 |
+
"learning_rate": 2.8236170875388744e-05,
|
| 1885 |
+
"loss": 0.01,
|
| 1886 |
+
"step": 2190
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 3.4108527131782944,
|
| 1890 |
+
"grad_norm": 0.2739998698234558,
|
| 1891 |
+
"learning_rate": 2.775014248441422e-05,
|
| 1892 |
+
"loss": 0.0078,
|
| 1893 |
+
"step": 2200
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 3.4108527131782944,
|
| 1897 |
+
"eval_loss": 0.03312241658568382,
|
| 1898 |
+
"eval_runtime": 173.7097,
|
| 1899 |
+
"eval_samples_per_second": 6.603,
|
| 1900 |
+
"eval_steps_per_second": 6.603,
|
| 1901 |
+
"step": 2200
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"epoch": 3.4263565891472867,
|
| 1905 |
+
"grad_norm": 0.10180757939815521,
|
| 1906 |
+
"learning_rate": 2.726672161508341e-05,
|
| 1907 |
+
"loss": 0.0098,
|
| 1908 |
+
"step": 2210
|
| 1909 |
+
},
|
| 1910 |
+
{
|
| 1911 |
+
"epoch": 3.441860465116279,
|
| 1912 |
+
"grad_norm": 0.27830150723457336,
|
| 1913 |
+
"learning_rate": 2.678596492080984e-05,
|
| 1914 |
+
"loss": 0.0077,
|
| 1915 |
+
"step": 2220
|
| 1916 |
+
},
|
| 1917 |
+
{
|
| 1918 |
+
"epoch": 3.4573643410852712,
|
| 1919 |
+
"grad_norm": 0.25859320163726807,
|
| 1920 |
+
"learning_rate": 2.630792874278516e-05,
|
| 1921 |
+
"loss": 0.0099,
|
| 1922 |
+
"step": 2230
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 3.4728682170542635,
|
| 1926 |
+
"grad_norm": 0.4165274500846863,
|
| 1927 |
+
"learning_rate": 2.583266910337624e-05,
|
| 1928 |
+
"loss": 0.0095,
|
| 1929 |
+
"step": 2240
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 3.488372093023256,
|
| 1933 |
+
"grad_norm": 0.5020641684532166,
|
| 1934 |
+
"learning_rate": 2.5360241699559816e-05,
|
| 1935 |
+
"loss": 0.0109,
|
| 1936 |
+
"step": 2250
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 3.488372093023256,
|
| 1940 |
+
"eval_loss": 0.035617418587207794,
|
| 1941 |
+
"eval_runtime": 173.6138,
|
| 1942 |
+
"eval_samples_per_second": 6.607,
|
| 1943 |
+
"eval_steps_per_second": 6.607,
|
| 1944 |
+
"step": 2250
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"epoch": 3.503875968992248,
|
| 1948 |
+
"grad_norm": 0.19337324798107147,
|
| 1949 |
+
"learning_rate": 2.4890701896395146e-05,
|
| 1950 |
+
"loss": 0.0104,
|
| 1951 |
+
"step": 2260
|
| 1952 |
+
},
|
| 1953 |
+
{
|
| 1954 |
+
"epoch": 3.5193798449612403,
|
| 1955 |
+
"grad_norm": 0.1879683881998062,
|
| 1956 |
+
"learning_rate": 2.4424104720535735e-05,
|
| 1957 |
+
"loss": 0.0101,
|
| 1958 |
+
"step": 2270
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 3.5348837209302326,
|
| 1962 |
+
"grad_norm": 0.063876673579216,
|
| 1963 |
+
"learning_rate": 2.3960504853780462e-05,
|
| 1964 |
+
"loss": 0.0115,
|
| 1965 |
+
"step": 2280
|
| 1966 |
+
},
|
| 1967 |
+
{
|
| 1968 |
+
"epoch": 3.550387596899225,
|
| 1969 |
+
"grad_norm": 0.11843185126781464,
|
| 1970 |
+
"learning_rate": 2.349995662666547e-05,
|
| 1971 |
+
"loss": 0.0085,
|
| 1972 |
+
"step": 2290
|
| 1973 |
+
},
|
| 1974 |
+
{
|
| 1975 |
+
"epoch": 3.565891472868217,
|
| 1976 |
+
"grad_norm": 0.21422308683395386,
|
| 1977 |
+
"learning_rate": 2.3042514012096843e-05,
|
| 1978 |
+
"loss": 0.0137,
|
| 1979 |
+
"step": 2300
|
| 1980 |
+
},
|
| 1981 |
+
{
|
| 1982 |
+
"epoch": 3.565891472868217,
|
| 1983 |
+
"eval_loss": 0.035960037261247635,
|
| 1984 |
+
"eval_runtime": 173.6653,
|
| 1985 |
+
"eval_samples_per_second": 6.605,
|
| 1986 |
+
"eval_steps_per_second": 6.605,
|
| 1987 |
+
"step": 2300
|
| 1988 |
+
},
|
| 1989 |
+
{
|
| 1990 |
+
"epoch": 3.5813953488372094,
|
| 1991 |
+
"grad_norm": 0.354839563369751,
|
| 1992 |
+
"learning_rate": 2.2588230619025407e-05,
|
| 1993 |
+
"loss": 0.0159,
|
| 1994 |
+
"step": 2310
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 3.5968992248062017,
|
| 1998 |
+
"grad_norm": 0.2568114995956421,
|
| 1999 |
+
"learning_rate": 2.213715968616425e-05,
|
| 2000 |
+
"loss": 0.0109,
|
| 2001 |
+
"step": 2320
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 3.612403100775194,
|
| 2005 |
+
"grad_norm": 0.06852281093597412,
|
| 2006 |
+
"learning_rate": 2.16893540757494e-05,
|
| 2007 |
+
"loss": 0.0091,
|
| 2008 |
+
"step": 2330
|
| 2009 |
+
},
|
| 2010 |
+
{
|
| 2011 |
+
"epoch": 3.6279069767441863,
|
| 2012 |
+
"grad_norm": 0.194693461060524,
|
| 2013 |
+
"learning_rate": 2.1244866267344866e-05,
|
| 2014 |
+
"loss": 0.0084,
|
| 2015 |
+
"step": 2340
|
| 2016 |
+
},
|
| 2017 |
+
{
|
| 2018 |
+
"epoch": 3.6434108527131785,
|
| 2019 |
+
"grad_norm": 0.3488699495792389,
|
| 2020 |
+
"learning_rate": 2.080374835169235e-05,
|
| 2021 |
+
"loss": 0.013,
|
| 2022 |
+
"step": 2350
|
| 2023 |
+
},
|
| 2024 |
+
{
|
| 2025 |
+
"epoch": 3.6434108527131785,
|
| 2026 |
+
"eval_loss": 0.03496725112199783,
|
| 2027 |
+
"eval_runtime": 173.6559,
|
| 2028 |
+
"eval_samples_per_second": 6.605,
|
| 2029 |
+
"eval_steps_per_second": 6.605,
|
| 2030 |
+
"step": 2350
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 3.6589147286821704,
|
| 2034 |
+
"grad_norm": 0.16774657368659973,
|
| 2035 |
+
"learning_rate": 2.0366052024606612e-05,
|
| 2036 |
+
"loss": 0.0082,
|
| 2037 |
+
"step": 2360
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"epoch": 3.6744186046511627,
|
| 2041 |
+
"grad_norm": 0.2563646733760834,
|
| 2042 |
+
"learning_rate": 1.9931828580917107e-05,
|
| 2043 |
+
"loss": 0.0114,
|
| 2044 |
+
"step": 2370
|
| 2045 |
+
},
|
| 2046 |
+
{
|
| 2047 |
+
"epoch": 3.689922480620155,
|
| 2048 |
+
"grad_norm": 0.254089891910553,
|
| 2049 |
+
"learning_rate": 1.9501128908456523e-05,
|
| 2050 |
+
"loss": 0.0087,
|
| 2051 |
+
"step": 2380
|
| 2052 |
+
},
|
| 2053 |
+
{
|
| 2054 |
+
"epoch": 3.705426356589147,
|
| 2055 |
+
"grad_norm": 0.2673187255859375,
|
| 2056 |
+
"learning_rate": 1.9074003482097258e-05,
|
| 2057 |
+
"loss": 0.0093,
|
| 2058 |
+
"step": 2390
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 3.7209302325581395,
|
| 2062 |
+
"grad_norm": 0.47327151894569397,
|
| 2063 |
+
"learning_rate": 1.8650502357835925e-05,
|
| 2064 |
+
"loss": 0.0133,
|
| 2065 |
+
"step": 2400
|
| 2066 |
+
},
|
| 2067 |
+
{
|
| 2068 |
+
"epoch": 3.7209302325581395,
|
| 2069 |
+
"eval_loss": 0.03533458709716797,
|
| 2070 |
+
"eval_runtime": 173.6028,
|
| 2071 |
+
"eval_samples_per_second": 6.607,
|
| 2072 |
+
"eval_steps_per_second": 6.607,
|
| 2073 |
+
"step": 2400
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 3.7364341085271318,
|
| 2077 |
+
"grad_norm": 0.4366307556629181,
|
| 2078 |
+
"learning_rate": 1.82306751669274e-05,
|
| 2079 |
+
"loss": 0.0085,
|
| 2080 |
+
"step": 2410
|
| 2081 |
+
},
|
| 2082 |
+
{
|
| 2083 |
+
"epoch": 3.751937984496124,
|
| 2084 |
+
"grad_norm": 0.39723125100135803,
|
| 2085 |
+
"learning_rate": 1.7814571110068135e-05,
|
| 2086 |
+
"loss": 0.0123,
|
| 2087 |
+
"step": 2420
|
| 2088 |
+
},
|
| 2089 |
+
{
|
| 2090 |
+
"epoch": 3.7674418604651163,
|
| 2091 |
+
"grad_norm": 0.16450275480747223,
|
| 2092 |
+
"learning_rate": 1.740223895163039e-05,
|
| 2093 |
+
"loss": 0.0091,
|
| 2094 |
+
"step": 2430
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 3.7829457364341086,
|
| 2098 |
+
"grad_norm": 0.06844169646501541,
|
| 2099 |
+
"learning_rate": 1.6993727013947336e-05,
|
| 2100 |
+
"loss": 0.0109,
|
| 2101 |
+
"step": 2440
|
| 2102 |
+
},
|
| 2103 |
+
{
|
| 2104 |
+
"epoch": 3.798449612403101,
|
| 2105 |
+
"grad_norm": 0.29116564989089966,
|
| 2106 |
+
"learning_rate": 1.6589083171649977e-05,
|
| 2107 |
+
"loss": 0.0068,
|
| 2108 |
+
"step": 2450
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 3.798449612403101,
|
| 2112 |
+
"eval_loss": 0.035682931542396545,
|
| 2113 |
+
"eval_runtime": 173.5613,
|
| 2114 |
+
"eval_samples_per_second": 6.609,
|
| 2115 |
+
"eval_steps_per_second": 6.609,
|
| 2116 |
+
"step": 2450
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 3.813953488372093,
|
| 2120 |
+
"grad_norm": 0.1012692078948021,
|
| 2121 |
+
"learning_rate": 1.6188354846056698e-05,
|
| 2122 |
+
"loss": 0.008,
|
| 2123 |
+
"step": 2460
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 3.8294573643410854,
|
| 2127 |
+
"grad_norm": 0.1340951770544052,
|
| 2128 |
+
"learning_rate": 1.579158899961575e-05,
|
| 2129 |
+
"loss": 0.0054,
|
| 2130 |
+
"step": 2470
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 3.8449612403100772,
|
| 2134 |
+
"grad_norm": 0.22337476909160614,
|
| 2135 |
+
"learning_rate": 1.5398832130401637e-05,
|
| 2136 |
+
"loss": 0.0147,
|
| 2137 |
+
"step": 2480
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 3.8604651162790695,
|
| 2141 |
+
"grad_norm": 0.18346606194972992,
|
| 2142 |
+
"learning_rate": 1.5010130266665807e-05,
|
| 2143 |
+
"loss": 0.0108,
|
| 2144 |
+
"step": 2490
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 3.875968992248062,
|
| 2148 |
+
"grad_norm": 0.2582853436470032,
|
| 2149 |
+
"learning_rate": 1.4625528961442591e-05,
|
| 2150 |
+
"loss": 0.012,
|
| 2151 |
+
"step": 2500
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 3.875968992248062,
|
| 2155 |
+
"eval_loss": 0.034770578145980835,
|
| 2156 |
+
"eval_runtime": 173.5234,
|
| 2157 |
+
"eval_samples_per_second": 6.61,
|
| 2158 |
+
"eval_steps_per_second": 6.61,
|
| 2159 |
+
"step": 2500
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 3.891472868217054,
|
| 2163 |
+
"grad_norm": 0.22837190330028534,
|
| 2164 |
+
"learning_rate": 1.4245073287210608e-05,
|
| 2165 |
+
"loss": 0.0098,
|
| 2166 |
+
"step": 2510
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 3.9069767441860463,
|
| 2170 |
+
"grad_norm": 0.49539613723754883,
|
| 2171 |
+
"learning_rate": 1.3868807830610653e-05,
|
| 2172 |
+
"loss": 0.016,
|
| 2173 |
+
"step": 2520
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 3.9224806201550386,
|
| 2177 |
+
"grad_norm": 0.17993128299713135,
|
| 2178 |
+
"learning_rate": 1.3496776687220514e-05,
|
| 2179 |
+
"loss": 0.0129,
|
| 2180 |
+
"step": 2530
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 3.937984496124031,
|
| 2184 |
+
"grad_norm": 0.25489673018455505,
|
| 2185 |
+
"learning_rate": 1.3129023456387151e-05,
|
| 2186 |
+
"loss": 0.0068,
|
| 2187 |
+
"step": 2540
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 3.953488372093023,
|
| 2191 |
+
"grad_norm": 0.06681143492460251,
|
| 2192 |
+
"learning_rate": 1.2765591236117324e-05,
|
| 2193 |
+
"loss": 0.0088,
|
| 2194 |
+
"step": 2550
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 3.953488372093023,
|
| 2198 |
+
"eval_loss": 0.034369926899671555,
|
| 2199 |
+
"eval_runtime": 173.574,
|
| 2200 |
+
"eval_samples_per_second": 6.608,
|
| 2201 |
+
"eval_steps_per_second": 6.608,
|
| 2202 |
+
"step": 2550
|
| 2203 |
+
},
|
| 2204 |
+
{
|
| 2205 |
+
"epoch": 3.9689922480620154,
|
| 2206 |
+
"grad_norm": 0.14447127282619476,
|
| 2207 |
+
"learning_rate": 1.240652261802669e-05,
|
| 2208 |
+
"loss": 0.0105,
|
| 2209 |
+
"step": 2560
|
| 2210 |
+
},
|
| 2211 |
+
{
|
| 2212 |
+
"epoch": 3.9844961240310077,
|
| 2213 |
+
"grad_norm": 0.2608015239238739,
|
| 2214 |
+
"learning_rate": 1.205185968234847e-05,
|
| 2215 |
+
"loss": 0.0136,
|
| 2216 |
+
"step": 2570
|
| 2217 |
+
},
|
| 2218 |
+
{
|
| 2219 |
+
"epoch": 4.0,
|
| 2220 |
+
"grad_norm": 0.17687876522541046,
|
| 2221 |
+
"learning_rate": 1.1701643993001916e-05,
|
| 2222 |
+
"loss": 0.0093,
|
| 2223 |
+
"step": 2580
|
| 2224 |
+
},
|
| 2225 |
+
{
|
| 2226 |
+
"epoch": 4.015503875968992,
|
| 2227 |
+
"grad_norm": 0.1070009246468544,
|
| 2228 |
+
"learning_rate": 1.1355916592721316e-05,
|
| 2229 |
+
"loss": 0.0045,
|
| 2230 |
+
"step": 2590
|
| 2231 |
+
},
|
| 2232 |
+
{
|
| 2233 |
+
"epoch": 4.0310077519379846,
|
| 2234 |
+
"grad_norm": 0.11302992701530457,
|
| 2235 |
+
"learning_rate": 1.1014717998246099e-05,
|
| 2236 |
+
"loss": 0.0066,
|
| 2237 |
+
"step": 2600
|
| 2238 |
+
},
|
| 2239 |
+
{
|
| 2240 |
+
"epoch": 4.0310077519379846,
|
| 2241 |
+
"eval_loss": 0.03459889069199562,
|
| 2242 |
+
"eval_runtime": 173.5445,
|
| 2243 |
+
"eval_samples_per_second": 6.609,
|
| 2244 |
+
"eval_steps_per_second": 6.609,
|
| 2245 |
+
"step": 2600
|
| 2246 |
+
},
|
| 2247 |
+
{
|
| 2248 |
+
"epoch": 4.046511627906977,
|
| 2249 |
+
"grad_norm": 0.107364721596241,
|
| 2250 |
+
"learning_rate": 1.0678088195572517e-05,
|
| 2251 |
+
"loss": 0.0053,
|
| 2252 |
+
"step": 2610
|
| 2253 |
+
},
|
| 2254 |
+
{
|
| 2255 |
+
"epoch": 4.062015503875969,
|
| 2256 |
+
"grad_norm": 0.2821330428123474,
|
| 2257 |
+
"learning_rate": 1.0346066635267676e-05,
|
| 2258 |
+
"loss": 0.0069,
|
| 2259 |
+
"step": 2620
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"epoch": 4.077519379844961,
|
| 2263 |
+
"grad_norm": 0.17317578196525574,
|
| 2264 |
+
"learning_rate": 1.001869222784611e-05,
|
| 2265 |
+
"loss": 0.0064,
|
| 2266 |
+
"step": 2630
|
| 2267 |
+
},
|
| 2268 |
+
{
|
| 2269 |
+
"epoch": 4.093023255813954,
|
| 2270 |
+
"grad_norm": 0.08701343834400177,
|
| 2271 |
+
"learning_rate": 9.696003339209819e-06,
|
| 2272 |
+
"loss": 0.007,
|
| 2273 |
+
"step": 2640
|
| 2274 |
+
},
|
| 2275 |
+
{
|
| 2276 |
+
"epoch": 4.108527131782946,
|
| 2277 |
+
"grad_norm": 0.23731686174869537,
|
| 2278 |
+
"learning_rate": 9.378037786152055e-06,
|
| 2279 |
+
"loss": 0.0052,
|
| 2280 |
+
"step": 2650
|
| 2281 |
+
},
|
| 2282 |
+
{
|
| 2283 |
+
"epoch": 4.108527131782946,
|
| 2284 |
+
"eval_loss": 0.03613542765378952,
|
| 2285 |
+
"eval_runtime": 173.8232,
|
| 2286 |
+
"eval_samples_per_second": 6.599,
|
| 2287 |
+
"eval_steps_per_second": 6.599,
|
| 2288 |
+
"step": 2650
|
| 2289 |
+
},
|
| 2290 |
+
{
|
| 2291 |
+
"epoch": 4.124031007751938,
|
| 2292 |
+
"grad_norm": 0.13787880539894104,
|
| 2293 |
+
"learning_rate": 9.064832831925441e-06,
|
| 2294 |
+
"loss": 0.0054,
|
| 2295 |
+
"step": 2660
|
| 2296 |
+
},
|
| 2297 |
+
{
|
| 2298 |
+
"epoch": 4.1395348837209305,
|
| 2299 |
+
"grad_norm": 0.1381884068250656,
|
| 2300 |
+
"learning_rate": 8.756425181875028e-06,
|
| 2301 |
+
"loss": 0.0035,
|
| 2302 |
+
"step": 2670
|
| 2303 |
+
},
|
| 2304 |
+
{
|
| 2305 |
+
"epoch": 4.155038759689923,
|
| 2306 |
+
"grad_norm": 0.16911053657531738,
|
| 2307 |
+
"learning_rate": 8.452850979136617e-06,
|
| 2308 |
+
"loss": 0.0045,
|
| 2309 |
+
"step": 2680
|
| 2310 |
+
},
|
| 2311 |
+
{
|
| 2312 |
+
"epoch": 4.170542635658915,
|
| 2313 |
+
"grad_norm": 0.04475264623761177,
|
| 2314 |
+
"learning_rate": 8.15414580040117e-06,
|
| 2315 |
+
"loss": 0.0032,
|
| 2316 |
+
"step": 2690
|
| 2317 |
+
},
|
| 2318 |
+
{
|
| 2319 |
+
"epoch": 4.186046511627907,
|
| 2320 |
+
"grad_norm": 0.09773126989603043,
|
| 2321 |
+
"learning_rate": 7.860344651745366e-06,
|
| 2322 |
+
"loss": 0.008,
|
| 2323 |
+
"step": 2700
|
| 2324 |
+
},
|
| 2325 |
+
{
|
| 2326 |
+
"epoch": 4.186046511627907,
|
| 2327 |
+
"eval_loss": 0.037369657307863235,
|
| 2328 |
+
"eval_runtime": 173.9253,
|
| 2329 |
+
"eval_samples_per_second": 6.595,
|
| 2330 |
+
"eval_steps_per_second": 6.595,
|
| 2331 |
+
"step": 2700
|
| 2332 |
+
},
|
| 2333 |
+
{
|
| 2334 |
+
"epoch": 4.2015503875969,
|
| 2335 |
+
"grad_norm": 0.1751956194639206,
|
| 2336 |
+
"learning_rate": 7.571481964529226e-06,
|
| 2337 |
+
"loss": 0.0057,
|
| 2338 |
+
"step": 2710
|
| 2339 |
+
},
|
| 2340 |
+
{
|
| 2341 |
+
"epoch": 4.217054263565892,
|
| 2342 |
+
"grad_norm": 0.06625787168741226,
|
| 2343 |
+
"learning_rate": 7.287591591360926e-06,
|
| 2344 |
+
"loss": 0.0028,
|
| 2345 |
+
"step": 2720
|
| 2346 |
+
},
|
| 2347 |
+
{
|
| 2348 |
+
"epoch": 4.232558139534884,
|
| 2349 |
+
"grad_norm": 0.1029408872127533,
|
| 2350 |
+
"learning_rate": 7.008706802129606e-06,
|
| 2351 |
+
"loss": 0.0069,
|
| 2352 |
+
"step": 2730
|
| 2353 |
+
},
|
| 2354 |
+
{
|
| 2355 |
+
"epoch": 4.248062015503876,
|
| 2356 |
+
"grad_norm": 0.01715020090341568,
|
| 2357 |
+
"learning_rate": 6.734860280106292e-06,
|
| 2358 |
+
"loss": 0.0021,
|
| 2359 |
+
"step": 2740
|
| 2360 |
+
},
|
| 2361 |
+
{
|
| 2362 |
+
"epoch": 4.263565891472869,
|
| 2363 |
+
"grad_norm": 0.5773080587387085,
|
| 2364 |
+
"learning_rate": 6.466084118113735e-06,
|
| 2365 |
+
"loss": 0.0062,
|
| 2366 |
+
"step": 2750
|
| 2367 |
+
},
|
| 2368 |
+
{
|
| 2369 |
+
"epoch": 4.263565891472869,
|
| 2370 |
+
"eval_loss": 0.0383269228041172,
|
| 2371 |
+
"eval_runtime": 173.7893,
|
| 2372 |
+
"eval_samples_per_second": 6.6,
|
| 2373 |
+
"eval_steps_per_second": 6.6,
|
| 2374 |
+
"step": 2750
|
| 2375 |
+
},
|
| 2376 |
+
{
|
| 2377 |
+
"epoch": 4.27906976744186,
|
| 2378 |
+
"grad_norm": 0.09289313852787018,
|
| 2379 |
+
"learning_rate": 6.202409814765325e-06,
|
| 2380 |
+
"loss": 0.0043,
|
| 2381 |
+
"step": 2760
|
| 2382 |
+
},
|
| 2383 |
+
{
|
| 2384 |
+
"epoch": 4.294573643410852,
|
| 2385 |
+
"grad_norm": 0.16086533665657043,
|
| 2386 |
+
"learning_rate": 5.9438682707736725e-06,
|
| 2387 |
+
"loss": 0.0064,
|
| 2388 |
+
"step": 2770
|
| 2389 |
+
},
|
| 2390 |
+
{
|
| 2391 |
+
"epoch": 4.310077519379845,
|
| 2392 |
+
"grad_norm": 0.175432026386261,
|
| 2393 |
+
"learning_rate": 5.690489785329301e-06,
|
| 2394 |
+
"loss": 0.0052,
|
| 2395 |
+
"step": 2780
|
| 2396 |
+
},
|
| 2397 |
+
{
|
| 2398 |
+
"epoch": 4.325581395348837,
|
| 2399 |
+
"grad_norm": 0.03287180885672569,
|
| 2400 |
+
"learning_rate": 5.442304052549752e-06,
|
| 2401 |
+
"loss": 0.0037,
|
| 2402 |
+
"step": 2790
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 4.341085271317829,
|
| 2406 |
+
"grad_norm": 0.09991113096475601,
|
| 2407 |
+
"learning_rate": 5.199340157999733e-06,
|
| 2408 |
+
"loss": 0.005,
|
| 2409 |
+
"step": 2800
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 4.341085271317829,
|
| 2413 |
+
"eval_loss": 0.038646504282951355,
|
| 2414 |
+
"eval_runtime": 173.5908,
|
| 2415 |
+
"eval_samples_per_second": 6.607,
|
| 2416 |
+
"eval_steps_per_second": 6.607,
|
| 2417 |
+
"step": 2800
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 4.3565891472868215,
|
| 2421 |
+
"grad_norm": 0.07446504384279251,
|
| 2422 |
+
"learning_rate": 4.961626575282396e-06,
|
| 2423 |
+
"loss": 0.0028,
|
| 2424 |
+
"step": 2810
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 4.372093023255814,
|
| 2428 |
+
"grad_norm": 0.1563124656677246,
|
| 2429 |
+
"learning_rate": 4.7291911627025235e-06,
|
| 2430 |
+
"loss": 0.0045,
|
| 2431 |
+
"step": 2820
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 4.387596899224806,
|
| 2435 |
+
"grad_norm": 0.09954715520143509,
|
| 2436 |
+
"learning_rate": 4.502061160001725e-06,
|
| 2437 |
+
"loss": 0.0038,
|
| 2438 |
+
"step": 2830
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 4.403100775193798,
|
| 2442 |
+
"grad_norm": 0.03728143870830536,
|
| 2443 |
+
"learning_rate": 4.280263185166078e-06,
|
| 2444 |
+
"loss": 0.007,
|
| 2445 |
+
"step": 2840
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 4.4186046511627906,
|
| 2449 |
+
"grad_norm": 0.14879867434501648,
|
| 2450 |
+
"learning_rate": 4.063823231306757e-06,
|
| 2451 |
+
"loss": 0.004,
|
| 2452 |
+
"step": 2850
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 4.4186046511627906,
|
| 2456 |
+
"eval_loss": 0.03950056806206703,
|
| 2457 |
+
"eval_runtime": 173.7546,
|
| 2458 |
+
"eval_samples_per_second": 6.601,
|
| 2459 |
+
"eval_steps_per_second": 6.601,
|
| 2460 |
+
"step": 2850
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 4.434108527131783,
|
| 2464 |
+
"grad_norm": 0.04011745750904083,
|
| 2465 |
+
"learning_rate": 3.8527666636137885e-06,
|
| 2466 |
+
"loss": 0.0039,
|
| 2467 |
+
"step": 2860
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 4.449612403100775,
|
| 2471 |
+
"grad_norm": 0.16904973983764648,
|
| 2472 |
+
"learning_rate": 3.6471182163834825e-06,
|
| 2473 |
+
"loss": 0.0075,
|
| 2474 |
+
"step": 2870
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 4.465116279069767,
|
| 2478 |
+
"grad_norm": 0.05882781371474266,
|
| 2479 |
+
"learning_rate": 3.4469019901197054e-06,
|
| 2480 |
+
"loss": 0.0027,
|
| 2481 |
+
"step": 2880
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 4.48062015503876,
|
| 2485 |
+
"grad_norm": 0.36288192868232727,
|
| 2486 |
+
"learning_rate": 3.252141448709495e-06,
|
| 2487 |
+
"loss": 0.0052,
|
| 2488 |
+
"step": 2890
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 4.496124031007752,
|
| 2492 |
+
"grad_norm": 0.25636863708496094,
|
| 2493 |
+
"learning_rate": 3.0628594166732693e-06,
|
| 2494 |
+
"loss": 0.0075,
|
| 2495 |
+
"step": 2900
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 4.496124031007752,
|
| 2499 |
+
"eval_loss": 0.040012069046497345,
|
| 2500 |
+
"eval_runtime": 173.5684,
|
| 2501 |
+
"eval_samples_per_second": 6.608,
|
| 2502 |
+
"eval_steps_per_second": 6.608,
|
| 2503 |
+
"step": 2900
|
| 2504 |
+
},
|
| 2505 |
+
{
|
| 2506 |
+
"epoch": 4.511627906976744,
|
| 2507 |
+
"grad_norm": 0.07002587616443634,
|
| 2508 |
+
"learning_rate": 2.8790780764899384e-06,
|
| 2509 |
+
"loss": 0.0053,
|
| 2510 |
+
"step": 2910
|
| 2511 |
+
},
|
| 2512 |
+
{
|
| 2513 |
+
"epoch": 4.5271317829457365,
|
| 2514 |
+
"grad_norm": 0.18481026589870453,
|
| 2515 |
+
"learning_rate": 2.700818965997315e-06,
|
| 2516 |
+
"loss": 0.0064,
|
| 2517 |
+
"step": 2920
|
| 2518 |
+
},
|
| 2519 |
+
{
|
| 2520 |
+
"epoch": 4.542635658914729,
|
| 2521 |
+
"grad_norm": 0.1123792976140976,
|
| 2522 |
+
"learning_rate": 2.528102975867991e-06,
|
| 2523 |
+
"loss": 0.0033,
|
| 2524 |
+
"step": 2930
|
| 2525 |
+
},
|
| 2526 |
+
{
|
| 2527 |
+
"epoch": 4.558139534883721,
|
| 2528 |
+
"grad_norm": 0.039597250521183014,
|
| 2529 |
+
"learning_rate": 2.3609503471611284e-06,
|
| 2530 |
+
"loss": 0.0041,
|
| 2531 |
+
"step": 2940
|
| 2532 |
+
},
|
| 2533 |
+
{
|
| 2534 |
+
"epoch": 4.573643410852713,
|
| 2535 |
+
"grad_norm": 0.05195772275328636,
|
| 2536 |
+
"learning_rate": 2.1993806689503738e-06,
|
| 2537 |
+
"loss": 0.003,
|
| 2538 |
+
"step": 2950
|
| 2539 |
+
},
|
| 2540 |
+
{
|
| 2541 |
+
"epoch": 4.573643410852713,
|
| 2542 |
+
"eval_loss": 0.040207840502262115,
|
| 2543 |
+
"eval_runtime": 173.5139,
|
| 2544 |
+
"eval_samples_per_second": 6.61,
|
| 2545 |
+
"eval_steps_per_second": 6.61,
|
| 2546 |
+
"step": 2950
|
| 2547 |
+
},
|
| 2548 |
+
{
|
| 2549 |
+
"epoch": 4.589147286821706,
|
| 2550 |
+
"grad_norm": 0.06371759623289108,
|
| 2551 |
+
"learning_rate": 2.0434128760281167e-06,
|
| 2552 |
+
"loss": 0.0021,
|
| 2553 |
+
"step": 2960
|
| 2554 |
+
},
|
| 2555 |
+
{
|
| 2556 |
+
"epoch": 4.604651162790698,
|
| 2557 |
+
"grad_norm": 0.0519726499915123,
|
| 2558 |
+
"learning_rate": 1.893065246686504e-06,
|
| 2559 |
+
"loss": 0.0029,
|
| 2560 |
+
"step": 2970
|
| 2561 |
+
},
|
| 2562 |
+
{
|
| 2563 |
+
"epoch": 4.62015503875969,
|
| 2564 |
+
"grad_norm": 0.05901438370347023,
|
| 2565 |
+
"learning_rate": 1.74835540057533e-06,
|
| 2566 |
+
"loss": 0.0067,
|
| 2567 |
+
"step": 2980
|
| 2568 |
+
},
|
| 2569 |
+
{
|
| 2570 |
+
"epoch": 4.635658914728682,
|
| 2571 |
+
"grad_norm": 0.16322703659534454,
|
| 2572 |
+
"learning_rate": 1.6093002966371617e-06,
|
| 2573 |
+
"loss": 0.0044,
|
| 2574 |
+
"step": 2990
|
| 2575 |
+
},
|
| 2576 |
+
{
|
| 2577 |
+
"epoch": 4.651162790697675,
|
| 2578 |
+
"grad_norm": 0.25651177763938904,
|
| 2579 |
+
"learning_rate": 1.4759162311198783e-06,
|
| 2580 |
+
"loss": 0.0066,
|
| 2581 |
+
"step": 3000
|
| 2582 |
+
},
|
| 2583 |
+
{
|
| 2584 |
+
"epoch": 4.651162790697675,
|
| 2585 |
+
"eval_loss": 0.0405086986720562,
|
| 2586 |
+
"eval_runtime": 173.4642,
|
| 2587 |
+
"eval_samples_per_second": 6.612,
|
| 2588 |
+
"eval_steps_per_second": 6.612,
|
| 2589 |
+
"step": 3000
|
| 2590 |
+
},
|
| 2591 |
+
{
|
| 2592 |
+
"epoch": 4.666666666666667,
|
| 2593 |
+
"grad_norm": 0.009503856301307678,
|
| 2594 |
+
"learning_rate": 1.348218835666859e-06,
|
| 2595 |
+
"loss": 0.0032,
|
| 2596 |
+
"step": 3010
|
| 2597 |
+
},
|
| 2598 |
+
{
|
| 2599 |
+
"epoch": 4.682170542635659,
|
| 2600 |
+
"grad_norm": 0.12524276971817017,
|
| 2601 |
+
"learning_rate": 1.2262230754850445e-06,
|
| 2602 |
+
"loss": 0.0032,
|
| 2603 |
+
"step": 3020
|
| 2604 |
+
},
|
| 2605 |
+
{
|
| 2606 |
+
"epoch": 4.6976744186046515,
|
| 2607 |
+
"grad_norm": 0.06170937791466713,
|
| 2608 |
+
"learning_rate": 1.109943247591172e-06,
|
| 2609 |
+
"loss": 0.0045,
|
| 2610 |
+
"step": 3030
|
| 2611 |
+
},
|
| 2612 |
+
{
|
| 2613 |
+
"epoch": 4.713178294573644,
|
| 2614 |
+
"grad_norm": 0.12521466612815857,
|
| 2615 |
+
"learning_rate": 9.993929791362323e-07,
|
| 2616 |
+
"loss": 0.0052,
|
| 2617 |
+
"step": 3040
|
| 2618 |
+
},
|
| 2619 |
+
{
|
| 2620 |
+
"epoch": 4.728682170542635,
|
| 2621 |
+
"grad_norm": 0.17083865404129028,
|
| 2622 |
+
"learning_rate": 8.945852258084863e-07,
|
| 2623 |
+
"loss": 0.005,
|
| 2624 |
+
"step": 3050
|
| 2625 |
+
},
|
| 2626 |
+
{
|
| 2627 |
+
"epoch": 4.728682170542635,
|
| 2628 |
+
"eval_loss": 0.04061457887291908,
|
| 2629 |
+
"eval_runtime": 173.5187,
|
| 2630 |
+
"eval_samples_per_second": 6.61,
|
| 2631 |
+
"eval_steps_per_second": 6.61,
|
| 2632 |
+
"step": 3050
|
| 2633 |
+
},
|
| 2634 |
+
{
|
| 2635 |
+
"epoch": 4.7441860465116275,
|
| 2636 |
+
"grad_norm": 0.35159188508987427,
|
| 2637 |
+
"learning_rate": 7.955322703151358e-07,
|
| 2638 |
+
"loss": 0.0046,
|
| 2639 |
+
"step": 3060
|
| 2640 |
+
},
|
| 2641 |
+
{
|
| 2642 |
+
"epoch": 4.75968992248062,
|
| 2643 |
+
"grad_norm": 0.2449195384979248,
|
| 2644 |
+
"learning_rate": 7.022457209428901e-07,
|
| 2645 |
+
"loss": 0.0044,
|
| 2646 |
+
"step": 3070
|
| 2647 |
+
},
|
| 2648 |
+
{
|
| 2649 |
+
"epoch": 4.775193798449612,
|
| 2650 |
+
"grad_norm": 0.2619343101978302,
|
| 2651 |
+
"learning_rate": 6.147365101975666e-07,
|
| 2652 |
+
"loss": 0.0035,
|
| 2653 |
+
"step": 3080
|
| 2654 |
+
},
|
| 2655 |
+
{
|
| 2656 |
+
"epoch": 4.790697674418604,
|
| 2657 |
+
"grad_norm": 0.09077528119087219,
|
| 2658 |
+
"learning_rate": 5.33014893522854e-07,
|
| 2659 |
+
"loss": 0.0032,
|
| 2660 |
+
"step": 3090
|
| 2661 |
+
},
|
| 2662 |
+
{
|
| 2663 |
+
"epoch": 4.8062015503875966,
|
| 2664 |
+
"grad_norm": 0.14284414052963257,
|
| 2665 |
+
"learning_rate": 4.57090448098485e-07,
|
| 2666 |
+
"loss": 0.0067,
|
| 2667 |
+
"step": 3100
|
| 2668 |
+
},
|
| 2669 |
+
{
|
| 2670 |
+
"epoch": 4.8062015503875966,
|
| 2671 |
+
"eval_loss": 0.04071947932243347,
|
| 2672 |
+
"eval_runtime": 173.7232,
|
| 2673 |
+
"eval_samples_per_second": 6.602,
|
| 2674 |
+
"eval_steps_per_second": 6.602,
|
| 2675 |
+
"step": 3100
|
| 2676 |
+
},
|
| 2677 |
+
{
|
| 2678 |
+
"epoch": 4.821705426356589,
|
| 2679 |
+
"grad_norm": 0.10482044517993927,
|
| 2680 |
+
"learning_rate": 3.8697207171781714e-07,
|
| 2681 |
+
"loss": 0.0037,
|
| 2682 |
+
"step": 3110
|
| 2683 |
+
},
|
| 2684 |
+
{
|
| 2685 |
+
"epoch": 4.837209302325581,
|
| 2686 |
+
"grad_norm": 0.03253592178225517,
|
| 2687 |
+
"learning_rate": 3.2266798174512837e-07,
|
| 2688 |
+
"loss": 0.0045,
|
| 2689 |
+
"step": 3120
|
| 2690 |
+
},
|
| 2691 |
+
{
|
| 2692 |
+
"epoch": 4.852713178294573,
|
| 2693 |
+
"grad_norm": 0.03622818365693092,
|
| 2694 |
+
"learning_rate": 2.6418571415255387e-07,
|
| 2695 |
+
"loss": 0.0093,
|
| 2696 |
+
"step": 3130
|
| 2697 |
+
},
|
| 2698 |
+
{
|
| 2699 |
+
"epoch": 4.868217054263566,
|
| 2700 |
+
"grad_norm": 0.09220151603221893,
|
| 2701 |
+
"learning_rate": 2.1153212263695378e-07,
|
| 2702 |
+
"loss": 0.0046,
|
| 2703 |
+
"step": 3140
|
| 2704 |
+
},
|
| 2705 |
+
{
|
| 2706 |
+
"epoch": 4.883720930232558,
|
| 2707 |
+
"grad_norm": 0.1942395716905594,
|
| 2708 |
+
"learning_rate": 1.6471337781669982e-07,
|
| 2709 |
+
"loss": 0.0067,
|
| 2710 |
+
"step": 3150
|
| 2711 |
+
},
|
| 2712 |
+
{
|
| 2713 |
+
"epoch": 4.883720930232558,
|
| 2714 |
+
"eval_loss": 0.040707945823669434,
|
| 2715 |
+
"eval_runtime": 173.7396,
|
| 2716 |
+
"eval_samples_per_second": 6.602,
|
| 2717 |
+
"eval_steps_per_second": 6.602,
|
| 2718 |
+
"step": 3150
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 4.89922480620155,
|
| 2722 |
+
"grad_norm": 0.09173876792192459,
|
| 2723 |
+
"learning_rate": 1.237349665085097e-07,
|
| 2724 |
+
"loss": 0.0049,
|
| 2725 |
+
"step": 3160
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 4.9147286821705425,
|
| 2729 |
+
"grad_norm": 0.045584529638290405,
|
| 2730 |
+
"learning_rate": 8.86016910844667e-08,
|
| 2731 |
+
"loss": 0.003,
|
| 2732 |
+
"step": 3170
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 4.930232558139535,
|
| 2736 |
+
"grad_norm": 0.46576347947120667,
|
| 2737 |
+
"learning_rate": 5.9317668909192323e-08,
|
| 2738 |
+
"loss": 0.0061,
|
| 2739 |
+
"step": 3180
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 4.945736434108527,
|
| 2743 |
+
"grad_norm": 0.059987977147102356,
|
| 2744 |
+
"learning_rate": 3.588633185730994e-08,
|
| 2745 |
+
"loss": 0.0062,
|
| 2746 |
+
"step": 3190
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 4.961240310077519,
|
| 2750 |
+
"grad_norm": 0.2531404197216034,
|
| 2751 |
+
"learning_rate": 1.8310425911294283e-08,
|
| 2752 |
+
"loss": 0.006,
|
| 2753 |
+
"step": 3200
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 4.961240310077519,
|
| 2757 |
+
"eval_loss": 0.04073048010468483,
|
| 2758 |
+
"eval_runtime": 173.54,
|
| 2759 |
+
"eval_samples_per_second": 6.609,
|
| 2760 |
+
"eval_steps_per_second": 6.609,
|
| 2761 |
+
"step": 3200
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 4.976744186046512,
|
| 2765 |
+
"grad_norm": 0.24996767938137054,
|
| 2766 |
+
"learning_rate": 6.592010839612251e-09,
|
| 2767 |
+
"loss": 0.0076,
|
| 2768 |
+
"step": 3210
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 4.992248062015504,
|
| 2772 |
+
"grad_norm": 0.020084669813513756,
|
| 2773 |
+
"learning_rate": 7.324599553770739e-10,
|
| 2774 |
+
"loss": 0.0025,
|
| 2775 |
+
"step": 3220
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 5.0,
|
| 2779 |
+
"step": 3225,
|
| 2780 |
+
"total_flos": 8.718478050646426e+17,
|
| 2781 |
+
"train_loss": 0.049027663960821866,
|
| 2782 |
+
"train_runtime": 36714.2196,
|
| 2783 |
+
"train_samples_per_second": 1.405,
|
| 2784 |
+
"train_steps_per_second": 0.088
|
| 2785 |
+
}
|
| 2786 |
+
],
|
| 2787 |
+
"logging_steps": 10,
|
| 2788 |
+
"max_steps": 3225,
|
| 2789 |
+
"num_input_tokens_seen": 0,
|
| 2790 |
+
"num_train_epochs": 5,
|
| 2791 |
+
"save_steps": 50,
|
| 2792 |
+
"stateful_callbacks": {
|
| 2793 |
+
"TrainerControl": {
|
| 2794 |
+
"args": {
|
| 2795 |
+
"should_epoch_stop": false,
|
| 2796 |
+
"should_evaluate": false,
|
| 2797 |
+
"should_log": false,
|
| 2798 |
+
"should_save": true,
|
| 2799 |
+
"should_training_stop": true
|
| 2800 |
+
},
|
| 2801 |
+
"attributes": {}
|
| 2802 |
+
}
|
| 2803 |
+
},
|
| 2804 |
+
"total_flos": 8.718478050646426e+17,
|
| 2805 |
+
"train_batch_size": 1,
|
| 2806 |
+
"trial_name": null,
|
| 2807 |
+
"trial_params": null
|
| 2808 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|