End of training
Browse files- README.md +3 -2
- all_results.json +12 -0
- eval_results.json +7 -0
- train_results.json +8 -0
- trainer_state.json +2851 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: mit
|
|
| 4 |
base_model: klyang/MentaLLaMA-chat-7B-hf
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: MentaLLaMA-chat-7B-PsyCourse-fold7
|
|
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# MentaLLaMA-chat-7B-PsyCourse-fold7
|
| 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-fold7
|
|
|
|
| 16 |
|
| 17 |
# MentaLLaMA-chat-7B-PsyCourse-fold7
|
| 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-fold7 dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.0272
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.9961802902979375,
|
| 3 |
+
"eval_loss": 0.027184655889868736,
|
| 4 |
+
"eval_runtime": 196.9853,
|
| 5 |
+
"eval_samples_per_second": 5.909,
|
| 6 |
+
"eval_steps_per_second": 5.909,
|
| 7 |
+
"total_flos": 8.84620635703935e+17,
|
| 8 |
+
"train_loss": 0.04931148957939596,
|
| 9 |
+
"train_runtime": 42656.8883,
|
| 10 |
+
"train_samples_per_second": 1.227,
|
| 11 |
+
"train_steps_per_second": 0.077
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.9961802902979375,
|
| 3 |
+
"eval_loss": 0.027184655889868736,
|
| 4 |
+
"eval_runtime": 196.9853,
|
| 5 |
+
"eval_samples_per_second": 5.909,
|
| 6 |
+
"eval_steps_per_second": 5.909
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.9961802902979375,
|
| 3 |
+
"total_flos": 8.84620635703935e+17,
|
| 4 |
+
"train_loss": 0.04931148957939596,
|
| 5 |
+
"train_runtime": 42656.8883,
|
| 6 |
+
"train_samples_per_second": 1.227,
|
| 7 |
+
"train_steps_per_second": 0.077
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2851 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.027184655889868736,
|
| 3 |
+
"best_model_checkpoint": "saves/psy-course/MentaLLaMA-chat-7B/train/fold7/checkpoint-1800",
|
| 4 |
+
"epoch": 4.9961802902979375,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 3270,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.015278838808250574,
|
| 13 |
+
"grad_norm": 1.848912000656128,
|
| 14 |
+
"learning_rate": 3.0581039755351682e-06,
|
| 15 |
+
"loss": 1.7007,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.030557677616501147,
|
| 20 |
+
"grad_norm": 1.845645785331726,
|
| 21 |
+
"learning_rate": 6.1162079510703365e-06,
|
| 22 |
+
"loss": 1.6546,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.04583651642475172,
|
| 27 |
+
"grad_norm": 2.5136754512786865,
|
| 28 |
+
"learning_rate": 9.174311926605506e-06,
|
| 29 |
+
"loss": 1.5461,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.061115355233002294,
|
| 34 |
+
"grad_norm": 3.130951404571533,
|
| 35 |
+
"learning_rate": 1.2232415902140673e-05,
|
| 36 |
+
"loss": 1.3083,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.07639419404125286,
|
| 41 |
+
"grad_norm": 0.9243296384811401,
|
| 42 |
+
"learning_rate": 1.5290519877675842e-05,
|
| 43 |
+
"loss": 0.8412,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.07639419404125286,
|
| 48 |
+
"eval_loss": 0.6190279722213745,
|
| 49 |
+
"eval_runtime": 219.3498,
|
| 50 |
+
"eval_samples_per_second": 5.307,
|
| 51 |
+
"eval_steps_per_second": 5.307,
|
| 52 |
+
"step": 50
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.09167303284950344,
|
| 56 |
+
"grad_norm": 1.0339502096176147,
|
| 57 |
+
"learning_rate": 1.834862385321101e-05,
|
| 58 |
+
"loss": 0.6464,
|
| 59 |
+
"step": 60
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.10695187165775401,
|
| 63 |
+
"grad_norm": 1.244530200958252,
|
| 64 |
+
"learning_rate": 2.140672782874618e-05,
|
| 65 |
+
"loss": 0.4868,
|
| 66 |
+
"step": 70
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.12223071046600459,
|
| 70 |
+
"grad_norm": 0.8109800815582275,
|
| 71 |
+
"learning_rate": 2.4464831804281346e-05,
|
| 72 |
+
"loss": 0.3051,
|
| 73 |
+
"step": 80
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.13750954927425516,
|
| 77 |
+
"grad_norm": 0.551679253578186,
|
| 78 |
+
"learning_rate": 2.7522935779816515e-05,
|
| 79 |
+
"loss": 0.1913,
|
| 80 |
+
"step": 90
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.15278838808250572,
|
| 84 |
+
"grad_norm": 0.790469765663147,
|
| 85 |
+
"learning_rate": 3.0581039755351684e-05,
|
| 86 |
+
"loss": 0.1455,
|
| 87 |
+
"step": 100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.15278838808250572,
|
| 91 |
+
"eval_loss": 0.10693324357271194,
|
| 92 |
+
"eval_runtime": 219.1206,
|
| 93 |
+
"eval_samples_per_second": 5.312,
|
| 94 |
+
"eval_steps_per_second": 5.312,
|
| 95 |
+
"step": 100
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.16806722689075632,
|
| 99 |
+
"grad_norm": 0.5916261672973633,
|
| 100 |
+
"learning_rate": 3.363914373088685e-05,
|
| 101 |
+
"loss": 0.1072,
|
| 102 |
+
"step": 110
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.18334606569900688,
|
| 106 |
+
"grad_norm": 0.5760579705238342,
|
| 107 |
+
"learning_rate": 3.669724770642202e-05,
|
| 108 |
+
"loss": 0.096,
|
| 109 |
+
"step": 120
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.19862490450725745,
|
| 113 |
+
"grad_norm": 0.6538326740264893,
|
| 114 |
+
"learning_rate": 3.9755351681957185e-05,
|
| 115 |
+
"loss": 0.0842,
|
| 116 |
+
"step": 130
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.21390374331550802,
|
| 120 |
+
"grad_norm": 0.6428112983703613,
|
| 121 |
+
"learning_rate": 4.281345565749236e-05,
|
| 122 |
+
"loss": 0.0834,
|
| 123 |
+
"step": 140
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.22918258212375858,
|
| 127 |
+
"grad_norm": 0.6178712248802185,
|
| 128 |
+
"learning_rate": 4.587155963302753e-05,
|
| 129 |
+
"loss": 0.0861,
|
| 130 |
+
"step": 150
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.22918258212375858,
|
| 134 |
+
"eval_loss": 0.06472994387149811,
|
| 135 |
+
"eval_runtime": 218.5605,
|
| 136 |
+
"eval_samples_per_second": 5.326,
|
| 137 |
+
"eval_steps_per_second": 5.326,
|
| 138 |
+
"step": 150
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.24446142093200918,
|
| 142 |
+
"grad_norm": 0.7672821283340454,
|
| 143 |
+
"learning_rate": 4.892966360856269e-05,
|
| 144 |
+
"loss": 0.0823,
|
| 145 |
+
"step": 160
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.2597402597402597,
|
| 149 |
+
"grad_norm": 0.593714714050293,
|
| 150 |
+
"learning_rate": 5.1987767584097854e-05,
|
| 151 |
+
"loss": 0.0676,
|
| 152 |
+
"step": 170
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.2750190985485103,
|
| 156 |
+
"grad_norm": 0.5263367295265198,
|
| 157 |
+
"learning_rate": 5.504587155963303e-05,
|
| 158 |
+
"loss": 0.0731,
|
| 159 |
+
"step": 180
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.2902979373567609,
|
| 163 |
+
"grad_norm": 0.8246402740478516,
|
| 164 |
+
"learning_rate": 5.81039755351682e-05,
|
| 165 |
+
"loss": 0.0799,
|
| 166 |
+
"step": 190
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.30557677616501144,
|
| 170 |
+
"grad_norm": 0.7266839742660522,
|
| 171 |
+
"learning_rate": 6.116207951070337e-05,
|
| 172 |
+
"loss": 0.0575,
|
| 173 |
+
"step": 200
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.30557677616501144,
|
| 177 |
+
"eval_loss": 0.05183817818760872,
|
| 178 |
+
"eval_runtime": 217.88,
|
| 179 |
+
"eval_samples_per_second": 5.342,
|
| 180 |
+
"eval_steps_per_second": 5.342,
|
| 181 |
+
"step": 200
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.32085561497326204,
|
| 185 |
+
"grad_norm": 0.5840321779251099,
|
| 186 |
+
"learning_rate": 6.422018348623854e-05,
|
| 187 |
+
"loss": 0.0501,
|
| 188 |
+
"step": 210
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.33613445378151263,
|
| 192 |
+
"grad_norm": 0.6017265915870667,
|
| 193 |
+
"learning_rate": 6.72782874617737e-05,
|
| 194 |
+
"loss": 0.0637,
|
| 195 |
+
"step": 220
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.35141329258976317,
|
| 199 |
+
"grad_norm": 0.6707488894462585,
|
| 200 |
+
"learning_rate": 7.033639143730886e-05,
|
| 201 |
+
"loss": 0.057,
|
| 202 |
+
"step": 230
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.36669213139801377,
|
| 206 |
+
"grad_norm": 0.41309818625450134,
|
| 207 |
+
"learning_rate": 7.339449541284404e-05,
|
| 208 |
+
"loss": 0.0494,
|
| 209 |
+
"step": 240
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.3819709702062643,
|
| 213 |
+
"grad_norm": 0.5365416407585144,
|
| 214 |
+
"learning_rate": 7.645259938837921e-05,
|
| 215 |
+
"loss": 0.0643,
|
| 216 |
+
"step": 250
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.3819709702062643,
|
| 220 |
+
"eval_loss": 0.04688103497028351,
|
| 221 |
+
"eval_runtime": 218.0282,
|
| 222 |
+
"eval_samples_per_second": 5.339,
|
| 223 |
+
"eval_steps_per_second": 5.339,
|
| 224 |
+
"step": 250
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.3972498090145149,
|
| 228 |
+
"grad_norm": 0.2568855285644531,
|
| 229 |
+
"learning_rate": 7.951070336391437e-05,
|
| 230 |
+
"loss": 0.0436,
|
| 231 |
+
"step": 260
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.4125286478227655,
|
| 235 |
+
"grad_norm": 0.808674693107605,
|
| 236 |
+
"learning_rate": 8.256880733944955e-05,
|
| 237 |
+
"loss": 0.0708,
|
| 238 |
+
"step": 270
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.42780748663101603,
|
| 242 |
+
"grad_norm": 0.32300978899002075,
|
| 243 |
+
"learning_rate": 8.562691131498472e-05,
|
| 244 |
+
"loss": 0.0634,
|
| 245 |
+
"step": 280
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.4430863254392666,
|
| 249 |
+
"grad_norm": 0.24263863265514374,
|
| 250 |
+
"learning_rate": 8.868501529051988e-05,
|
| 251 |
+
"loss": 0.0507,
|
| 252 |
+
"step": 290
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.45836516424751717,
|
| 256 |
+
"grad_norm": 0.45118218660354614,
|
| 257 |
+
"learning_rate": 9.174311926605506e-05,
|
| 258 |
+
"loss": 0.0341,
|
| 259 |
+
"step": 300
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 0.45836516424751717,
|
| 263 |
+
"eval_loss": 0.043478548526763916,
|
| 264 |
+
"eval_runtime": 218.6129,
|
| 265 |
+
"eval_samples_per_second": 5.324,
|
| 266 |
+
"eval_steps_per_second": 5.324,
|
| 267 |
+
"step": 300
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.47364400305576776,
|
| 271 |
+
"grad_norm": 0.44334620237350464,
|
| 272 |
+
"learning_rate": 9.480122324159021e-05,
|
| 273 |
+
"loss": 0.0361,
|
| 274 |
+
"step": 310
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.48892284186401835,
|
| 278 |
+
"grad_norm": 0.27677738666534424,
|
| 279 |
+
"learning_rate": 9.785932721712538e-05,
|
| 280 |
+
"loss": 0.0466,
|
| 281 |
+
"step": 320
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.5042016806722689,
|
| 285 |
+
"grad_norm": 0.4536680281162262,
|
| 286 |
+
"learning_rate": 9.999974360983129e-05,
|
| 287 |
+
"loss": 0.0556,
|
| 288 |
+
"step": 330
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.5194805194805194,
|
| 292 |
+
"grad_norm": 0.4593944549560547,
|
| 293 |
+
"learning_rate": 9.999518563553522e-05,
|
| 294 |
+
"loss": 0.0652,
|
| 295 |
+
"step": 340
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.5347593582887701,
|
| 299 |
+
"grad_norm": 0.290985107421875,
|
| 300 |
+
"learning_rate": 9.998493069976636e-05,
|
| 301 |
+
"loss": 0.0641,
|
| 302 |
+
"step": 350
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.5347593582887701,
|
| 306 |
+
"eval_loss": 0.041326772421598434,
|
| 307 |
+
"eval_runtime": 218.3999,
|
| 308 |
+
"eval_samples_per_second": 5.33,
|
| 309 |
+
"eval_steps_per_second": 5.33,
|
| 310 |
+
"step": 350
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.5500381970970206,
|
| 314 |
+
"grad_norm": 0.4909442663192749,
|
| 315 |
+
"learning_rate": 9.99689799710767e-05,
|
| 316 |
+
"loss": 0.0574,
|
| 317 |
+
"step": 360
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.5653170359052712,
|
| 321 |
+
"grad_norm": 0.5292761921882629,
|
| 322 |
+
"learning_rate": 9.994733526705501e-05,
|
| 323 |
+
"loss": 0.0535,
|
| 324 |
+
"step": 370
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.5805958747135218,
|
| 328 |
+
"grad_norm": 0.3746335804462433,
|
| 329 |
+
"learning_rate": 9.991999905411966e-05,
|
| 330 |
+
"loss": 0.0432,
|
| 331 |
+
"step": 380
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.5958747135217723,
|
| 335 |
+
"grad_norm": 0.18307775259017944,
|
| 336 |
+
"learning_rate": 9.988697444723762e-05,
|
| 337 |
+
"loss": 0.0345,
|
| 338 |
+
"step": 390
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.6111535523300229,
|
| 342 |
+
"grad_norm": 0.22528858482837677,
|
| 343 |
+
"learning_rate": 9.984826520956949e-05,
|
| 344 |
+
"loss": 0.0405,
|
| 345 |
+
"step": 400
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.6111535523300229,
|
| 349 |
+
"eval_loss": 0.04191767796874046,
|
| 350 |
+
"eval_runtime": 218.4167,
|
| 351 |
+
"eval_samples_per_second": 5.329,
|
| 352 |
+
"eval_steps_per_second": 5.329,
|
| 353 |
+
"step": 400
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.6264323911382735,
|
| 357 |
+
"grad_norm": 0.299173504114151,
|
| 358 |
+
"learning_rate": 9.980387575204072e-05,
|
| 359 |
+
"loss": 0.0363,
|
| 360 |
+
"step": 410
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.6417112299465241,
|
| 364 |
+
"grad_norm": 0.5245795249938965,
|
| 365 |
+
"learning_rate": 9.975381113283891e-05,
|
| 366 |
+
"loss": 0.0346,
|
| 367 |
+
"step": 420
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.6569900687547746,
|
| 371 |
+
"grad_norm": 0.3329148292541504,
|
| 372 |
+
"learning_rate": 9.969807705683751e-05,
|
| 373 |
+
"loss": 0.0441,
|
| 374 |
+
"step": 430
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.6722689075630253,
|
| 378 |
+
"grad_norm": 0.23399081826210022,
|
| 379 |
+
"learning_rate": 9.96366798749457e-05,
|
| 380 |
+
"loss": 0.0301,
|
| 381 |
+
"step": 440
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.6875477463712758,
|
| 385 |
+
"grad_norm": 0.1943167895078659,
|
| 386 |
+
"learning_rate": 9.956962658338473e-05,
|
| 387 |
+
"loss": 0.0531,
|
| 388 |
+
"step": 450
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.6875477463712758,
|
| 392 |
+
"eval_loss": 0.03845739737153053,
|
| 393 |
+
"eval_runtime": 217.3338,
|
| 394 |
+
"eval_samples_per_second": 5.356,
|
| 395 |
+
"eval_steps_per_second": 5.356,
|
| 396 |
+
"step": 450
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.7028265851795263,
|
| 400 |
+
"grad_norm": 0.2697027027606964,
|
| 401 |
+
"learning_rate": 9.94969248228907e-05,
|
| 402 |
+
"loss": 0.0363,
|
| 403 |
+
"step": 460
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.7181054239877769,
|
| 407 |
+
"grad_norm": 0.3219946026802063,
|
| 408 |
+
"learning_rate": 9.941858287784383e-05,
|
| 409 |
+
"loss": 0.0447,
|
| 410 |
+
"step": 470
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.7333842627960275,
|
| 414 |
+
"grad_norm": 0.4683067798614502,
|
| 415 |
+
"learning_rate": 9.933460967532453e-05,
|
| 416 |
+
"loss": 0.043,
|
| 417 |
+
"step": 480
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.7486631016042781,
|
| 421 |
+
"grad_norm": 0.3924793004989624,
|
| 422 |
+
"learning_rate": 9.924501478409618e-05,
|
| 423 |
+
"loss": 0.0468,
|
| 424 |
+
"step": 490
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.7639419404125286,
|
| 428 |
+
"grad_norm": 0.25234106183052063,
|
| 429 |
+
"learning_rate": 9.914980841351465e-05,
|
| 430 |
+
"loss": 0.041,
|
| 431 |
+
"step": 500
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.7639419404125286,
|
| 435 |
+
"eval_loss": 0.03724617511034012,
|
| 436 |
+
"eval_runtime": 213.7645,
|
| 437 |
+
"eval_samples_per_second": 5.445,
|
| 438 |
+
"eval_steps_per_second": 5.445,
|
| 439 |
+
"step": 500
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.7792207792207793,
|
| 443 |
+
"grad_norm": 0.21722671389579773,
|
| 444 |
+
"learning_rate": 9.904900141236506e-05,
|
| 445 |
+
"loss": 0.0254,
|
| 446 |
+
"step": 510
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.7944996180290298,
|
| 450 |
+
"grad_norm": 0.3712560534477234,
|
| 451 |
+
"learning_rate": 9.894260526762548e-05,
|
| 452 |
+
"loss": 0.0495,
|
| 453 |
+
"step": 520
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.8097784568372803,
|
| 457 |
+
"grad_norm": 0.32290956377983093,
|
| 458 |
+
"learning_rate": 9.883063210315804e-05,
|
| 459 |
+
"loss": 0.0556,
|
| 460 |
+
"step": 530
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.825057295645531,
|
| 464 |
+
"grad_norm": 0.397980272769928,
|
| 465 |
+
"learning_rate": 9.871309467832738e-05,
|
| 466 |
+
"loss": 0.0381,
|
| 467 |
+
"step": 540
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.8403361344537815,
|
| 471 |
+
"grad_norm": 0.24909217655658722,
|
| 472 |
+
"learning_rate": 9.859000638654674e-05,
|
| 473 |
+
"loss": 0.0283,
|
| 474 |
+
"step": 550
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.8403361344537815,
|
| 478 |
+
"eval_loss": 0.03525731340050697,
|
| 479 |
+
"eval_runtime": 209.1141,
|
| 480 |
+
"eval_samples_per_second": 5.566,
|
| 481 |
+
"eval_steps_per_second": 5.566,
|
| 482 |
+
"step": 550
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.8556149732620321,
|
| 486 |
+
"grad_norm": 0.2012615203857422,
|
| 487 |
+
"learning_rate": 9.846138125375175e-05,
|
| 488 |
+
"loss": 0.0501,
|
| 489 |
+
"step": 560
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.8708938120702827,
|
| 493 |
+
"grad_norm": 0.19848772883415222,
|
| 494 |
+
"learning_rate": 9.83272339368022e-05,
|
| 495 |
+
"loss": 0.0298,
|
| 496 |
+
"step": 570
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.8861726508785333,
|
| 500 |
+
"grad_norm": 0.27441200613975525,
|
| 501 |
+
"learning_rate": 9.818757972181191e-05,
|
| 502 |
+
"loss": 0.043,
|
| 503 |
+
"step": 580
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 0.9014514896867838,
|
| 507 |
+
"grad_norm": 0.3285536766052246,
|
| 508 |
+
"learning_rate": 9.804243452240675e-05,
|
| 509 |
+
"loss": 0.0335,
|
| 510 |
+
"step": 590
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 0.9167303284950343,
|
| 514 |
+
"grad_norm": 0.48698437213897705,
|
| 515 |
+
"learning_rate": 9.789181487791146e-05,
|
| 516 |
+
"loss": 0.041,
|
| 517 |
+
"step": 600
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 0.9167303284950343,
|
| 521 |
+
"eval_loss": 0.03299807012081146,
|
| 522 |
+
"eval_runtime": 207.055,
|
| 523 |
+
"eval_samples_per_second": 5.622,
|
| 524 |
+
"eval_steps_per_second": 5.622,
|
| 525 |
+
"step": 600
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.932009167303285,
|
| 529 |
+
"grad_norm": 0.37265974283218384,
|
| 530 |
+
"learning_rate": 9.773573795146485e-05,
|
| 531 |
+
"loss": 0.044,
|
| 532 |
+
"step": 610
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.9472880061115355,
|
| 536 |
+
"grad_norm": 0.22519999742507935,
|
| 537 |
+
"learning_rate": 9.757422152806415e-05,
|
| 538 |
+
"loss": 0.0284,
|
| 539 |
+
"step": 620
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.9625668449197861,
|
| 543 |
+
"grad_norm": 0.24463610351085663,
|
| 544 |
+
"learning_rate": 9.74072840125383e-05,
|
| 545 |
+
"loss": 0.0417,
|
| 546 |
+
"step": 630
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.9778456837280367,
|
| 550 |
+
"grad_norm": 0.3929882347583771,
|
| 551 |
+
"learning_rate": 9.723494442745085e-05,
|
| 552 |
+
"loss": 0.0395,
|
| 553 |
+
"step": 640
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.9931245225362872,
|
| 557 |
+
"grad_norm": 0.40377989411354065,
|
| 558 |
+
"learning_rate": 9.705722241093223e-05,
|
| 559 |
+
"loss": 0.0553,
|
| 560 |
+
"step": 650
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.9931245225362872,
|
| 564 |
+
"eval_loss": 0.0362694077193737,
|
| 565 |
+
"eval_runtime": 205.7921,
|
| 566 |
+
"eval_samples_per_second": 5.656,
|
| 567 |
+
"eval_steps_per_second": 5.656,
|
| 568 |
+
"step": 650
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 1.0084033613445378,
|
| 572 |
+
"grad_norm": 0.14314551651477814,
|
| 573 |
+
"learning_rate": 9.687413821444199e-05,
|
| 574 |
+
"loss": 0.0376,
|
| 575 |
+
"step": 660
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 1.0236822001527883,
|
| 579 |
+
"grad_norm": 0.2880457937717438,
|
| 580 |
+
"learning_rate": 9.668571270046122e-05,
|
| 581 |
+
"loss": 0.0351,
|
| 582 |
+
"step": 670
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 1.0389610389610389,
|
| 586 |
+
"grad_norm": 0.19249747693538666,
|
| 587 |
+
"learning_rate": 9.649196734011519e-05,
|
| 588 |
+
"loss": 0.0288,
|
| 589 |
+
"step": 680
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 1.0542398777692896,
|
| 593 |
+
"grad_norm": 0.46998459100723267,
|
| 594 |
+
"learning_rate": 9.629292421072671e-05,
|
| 595 |
+
"loss": 0.0295,
|
| 596 |
+
"step": 690
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 1.0695187165775402,
|
| 600 |
+
"grad_norm": 0.1609886735677719,
|
| 601 |
+
"learning_rate": 9.608860599330048e-05,
|
| 602 |
+
"loss": 0.0314,
|
| 603 |
+
"step": 700
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 1.0695187165775402,
|
| 607 |
+
"eval_loss": 0.03102213703095913,
|
| 608 |
+
"eval_runtime": 204.7184,
|
| 609 |
+
"eval_samples_per_second": 5.686,
|
| 610 |
+
"eval_steps_per_second": 5.686,
|
| 611 |
+
"step": 700
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.0847975553857907,
|
| 615 |
+
"grad_norm": 0.2983687222003937,
|
| 616 |
+
"learning_rate": 9.587903596993854e-05,
|
| 617 |
+
"loss": 0.0297,
|
| 618 |
+
"step": 710
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.1000763941940412,
|
| 622 |
+
"grad_norm": 0.3572332561016083,
|
| 623 |
+
"learning_rate": 9.566423802118724e-05,
|
| 624 |
+
"loss": 0.0301,
|
| 625 |
+
"step": 720
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.1153552330022918,
|
| 629 |
+
"grad_norm": 0.10540549457073212,
|
| 630 |
+
"learning_rate": 9.544423662331612e-05,
|
| 631 |
+
"loss": 0.0438,
|
| 632 |
+
"step": 730
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.1306340718105423,
|
| 636 |
+
"grad_norm": 0.332472026348114,
|
| 637 |
+
"learning_rate": 9.521905684552877e-05,
|
| 638 |
+
"loss": 0.0354,
|
| 639 |
+
"step": 740
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.1459129106187929,
|
| 643 |
+
"grad_norm": 0.19438593089580536,
|
| 644 |
+
"learning_rate": 9.498872434710623e-05,
|
| 645 |
+
"loss": 0.0211,
|
| 646 |
+
"step": 750
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.1459129106187929,
|
| 650 |
+
"eval_loss": 0.031196942552924156,
|
| 651 |
+
"eval_runtime": 204.1433,
|
| 652 |
+
"eval_samples_per_second": 5.702,
|
| 653 |
+
"eval_steps_per_second": 5.702,
|
| 654 |
+
"step": 750
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.1611917494270436,
|
| 658 |
+
"grad_norm": 0.22115331888198853,
|
| 659 |
+
"learning_rate": 9.475326537448307e-05,
|
| 660 |
+
"loss": 0.0285,
|
| 661 |
+
"step": 760
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.1764705882352942,
|
| 665 |
+
"grad_norm": 0.16889172792434692,
|
| 666 |
+
"learning_rate": 9.451270675825665e-05,
|
| 667 |
+
"loss": 0.0287,
|
| 668 |
+
"step": 770
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.1917494270435447,
|
| 672 |
+
"grad_norm": 0.330474853515625,
|
| 673 |
+
"learning_rate": 9.426707591012976e-05,
|
| 674 |
+
"loss": 0.0261,
|
| 675 |
+
"step": 780
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.2070282658517952,
|
| 679 |
+
"grad_norm": 0.4934603273868561,
|
| 680 |
+
"learning_rate": 9.4016400819787e-05,
|
| 681 |
+
"loss": 0.0404,
|
| 682 |
+
"step": 790
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.2223071046600458,
|
| 686 |
+
"grad_norm": 0.39667800068855286,
|
| 687 |
+
"learning_rate": 9.376071005170539e-05,
|
| 688 |
+
"loss": 0.0314,
|
| 689 |
+
"step": 800
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.2223071046600458,
|
| 693 |
+
"eval_loss": 0.03202859312295914,
|
| 694 |
+
"eval_runtime": 203.9785,
|
| 695 |
+
"eval_samples_per_second": 5.706,
|
| 696 |
+
"eval_steps_per_second": 5.706,
|
| 697 |
+
"step": 800
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 1.2375859434682965,
|
| 701 |
+
"grad_norm": 0.2728429138660431,
|
| 702 |
+
"learning_rate": 9.350003274189949e-05,
|
| 703 |
+
"loss": 0.0361,
|
| 704 |
+
"step": 810
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 1.2528647822765469,
|
| 708 |
+
"grad_norm": 0.23270060122013092,
|
| 709 |
+
"learning_rate": 9.323439859460122e-05,
|
| 710 |
+
"loss": 0.0312,
|
| 711 |
+
"step": 820
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 1.2681436210847976,
|
| 715 |
+
"grad_norm": 0.21153134107589722,
|
| 716 |
+
"learning_rate": 9.296383787887519e-05,
|
| 717 |
+
"loss": 0.0311,
|
| 718 |
+
"step": 830
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 1.2834224598930482,
|
| 722 |
+
"grad_norm": 0.18999841809272766,
|
| 723 |
+
"learning_rate": 9.268838142516943e-05,
|
| 724 |
+
"loss": 0.0405,
|
| 725 |
+
"step": 840
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 1.2987012987012987,
|
| 729 |
+
"grad_norm": 0.28957971930503845,
|
| 730 |
+
"learning_rate": 9.240806062180234e-05,
|
| 731 |
+
"loss": 0.0325,
|
| 732 |
+
"step": 850
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 1.2987012987012987,
|
| 736 |
+
"eval_loss": 0.03146594762802124,
|
| 737 |
+
"eval_runtime": 203.4351,
|
| 738 |
+
"eval_samples_per_second": 5.722,
|
| 739 |
+
"eval_steps_per_second": 5.722,
|
| 740 |
+
"step": 850
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 1.3139801375095492,
|
| 744 |
+
"grad_norm": 0.12776818871498108,
|
| 745 |
+
"learning_rate": 9.212290741138592e-05,
|
| 746 |
+
"loss": 0.0172,
|
| 747 |
+
"step": 860
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 1.3292589763177998,
|
| 751 |
+
"grad_norm": 0.1620066910982132,
|
| 752 |
+
"learning_rate": 9.183295428718592e-05,
|
| 753 |
+
"loss": 0.0285,
|
| 754 |
+
"step": 870
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 1.3445378151260505,
|
| 758 |
+
"grad_norm": 0.2502717971801758,
|
| 759 |
+
"learning_rate": 9.153823428941924e-05,
|
| 760 |
+
"loss": 0.0395,
|
| 761 |
+
"step": 880
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 1.359816653934301,
|
| 765 |
+
"grad_norm": 0.23712791502475739,
|
| 766 |
+
"learning_rate": 9.1238781001489e-05,
|
| 767 |
+
"loss": 0.0276,
|
| 768 |
+
"step": 890
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 1.3750954927425516,
|
| 772 |
+
"grad_norm": 0.27235275506973267,
|
| 773 |
+
"learning_rate": 9.093462854615766e-05,
|
| 774 |
+
"loss": 0.0351,
|
| 775 |
+
"step": 900
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 1.3750954927425516,
|
| 779 |
+
"eval_loss": 0.030502911657094955,
|
| 780 |
+
"eval_runtime": 203.3489,
|
| 781 |
+
"eval_samples_per_second": 5.724,
|
| 782 |
+
"eval_steps_per_second": 5.724,
|
| 783 |
+
"step": 900
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 1.3903743315508021,
|
| 787 |
+
"grad_norm": 0.2629202604293823,
|
| 788 |
+
"learning_rate": 9.062581158165876e-05,
|
| 789 |
+
"loss": 0.0323,
|
| 790 |
+
"step": 910
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 1.4056531703590527,
|
| 794 |
+
"grad_norm": 0.2535449266433716,
|
| 795 |
+
"learning_rate": 9.031236529774764e-05,
|
| 796 |
+
"loss": 0.0222,
|
| 797 |
+
"step": 920
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 1.4209320091673032,
|
| 801 |
+
"grad_norm": 0.19801892340183258,
|
| 802 |
+
"learning_rate": 8.999432541169145e-05,
|
| 803 |
+
"loss": 0.0273,
|
| 804 |
+
"step": 930
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 1.4362108479755538,
|
| 808 |
+
"grad_norm": 0.19468438625335693,
|
| 809 |
+
"learning_rate": 8.967172816419927e-05,
|
| 810 |
+
"loss": 0.0274,
|
| 811 |
+
"step": 940
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 1.4514896867838045,
|
| 815 |
+
"grad_norm": 0.268258273601532,
|
| 816 |
+
"learning_rate": 8.934461031529242e-05,
|
| 817 |
+
"loss": 0.0402,
|
| 818 |
+
"step": 950
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 1.4514896867838045,
|
| 822 |
+
"eval_loss": 0.03139554709196091,
|
| 823 |
+
"eval_runtime": 203.1165,
|
| 824 |
+
"eval_samples_per_second": 5.731,
|
| 825 |
+
"eval_steps_per_second": 5.731,
|
| 826 |
+
"step": 950
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 1.466768525592055,
|
| 830 |
+
"grad_norm": 0.21832090616226196,
|
| 831 |
+
"learning_rate": 8.901300914011569e-05,
|
| 832 |
+
"loss": 0.0308,
|
| 833 |
+
"step": 960
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 1.4820473644003056,
|
| 837 |
+
"grad_norm": 0.12288864701986313,
|
| 838 |
+
"learning_rate": 8.867696242468976e-05,
|
| 839 |
+
"loss": 0.0228,
|
| 840 |
+
"step": 970
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 1.4973262032085561,
|
| 844 |
+
"grad_norm": 0.2422870695590973,
|
| 845 |
+
"learning_rate": 8.833650846160555e-05,
|
| 846 |
+
"loss": 0.0321,
|
| 847 |
+
"step": 980
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 1.5126050420168067,
|
| 851 |
+
"grad_norm": 0.20795999467372894,
|
| 852 |
+
"learning_rate": 8.79916860456607e-05,
|
| 853 |
+
"loss": 0.0269,
|
| 854 |
+
"step": 990
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 1.5278838808250574,
|
| 858 |
+
"grad_norm": 0.13397260010242462,
|
| 859 |
+
"learning_rate": 8.7642534469439e-05,
|
| 860 |
+
"loss": 0.0262,
|
| 861 |
+
"step": 1000
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 1.5278838808250574,
|
| 865 |
+
"eval_loss": 0.029931625351309776,
|
| 866 |
+
"eval_runtime": 202.6566,
|
| 867 |
+
"eval_samples_per_second": 5.744,
|
| 868 |
+
"eval_steps_per_second": 5.744,
|
| 869 |
+
"step": 1000
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 1.5431627196333078,
|
| 873 |
+
"grad_norm": 0.5128399729728699,
|
| 874 |
+
"learning_rate": 8.728909351883283e-05,
|
| 875 |
+
"loss": 0.0295,
|
| 876 |
+
"step": 1010
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 1.5584415584415585,
|
| 880 |
+
"grad_norm": 0.24673043191432953,
|
| 881 |
+
"learning_rate": 8.693140346850975e-05,
|
| 882 |
+
"loss": 0.0379,
|
| 883 |
+
"step": 1020
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 1.573720397249809,
|
| 887 |
+
"grad_norm": 0.16341492533683777,
|
| 888 |
+
"learning_rate": 8.656950507732303e-05,
|
| 889 |
+
"loss": 0.0247,
|
| 890 |
+
"step": 1030
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 1.5889992360580596,
|
| 894 |
+
"grad_norm": 0.11685626953840256,
|
| 895 |
+
"learning_rate": 8.620343958366718e-05,
|
| 896 |
+
"loss": 0.0284,
|
| 897 |
+
"step": 1040
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 1.6042780748663101,
|
| 901 |
+
"grad_norm": 0.25839105248451233,
|
| 902 |
+
"learning_rate": 8.5833248700779e-05,
|
| 903 |
+
"loss": 0.026,
|
| 904 |
+
"step": 1050
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 1.6042780748663101,
|
| 908 |
+
"eval_loss": 0.030233880504965782,
|
| 909 |
+
"eval_runtime": 202.0854,
|
| 910 |
+
"eval_samples_per_second": 5.76,
|
| 911 |
+
"eval_steps_per_second": 5.76,
|
| 912 |
+
"step": 1050
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 1.6195569136745607,
|
| 916 |
+
"grad_norm": 0.12446019053459167,
|
| 917 |
+
"learning_rate": 8.545897461198413e-05,
|
| 918 |
+
"loss": 0.0269,
|
| 919 |
+
"step": 1060
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 1.6348357524828114,
|
| 923 |
+
"grad_norm": 0.13764119148254395,
|
| 924 |
+
"learning_rate": 8.508065996589036e-05,
|
| 925 |
+
"loss": 0.0295,
|
| 926 |
+
"step": 1070
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 1.6501145912910617,
|
| 930 |
+
"grad_norm": 0.1417740285396576,
|
| 931 |
+
"learning_rate": 8.469834787152783e-05,
|
| 932 |
+
"loss": 0.0235,
|
| 933 |
+
"step": 1080
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 1.6653934300993125,
|
| 937 |
+
"grad_norm": 0.1833825260400772,
|
| 938 |
+
"learning_rate": 8.43120818934367e-05,
|
| 939 |
+
"loss": 0.0267,
|
| 940 |
+
"step": 1090
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.680672268907563,
|
| 944 |
+
"grad_norm": 0.259737104177475,
|
| 945 |
+
"learning_rate": 8.392190604670293e-05,
|
| 946 |
+
"loss": 0.024,
|
| 947 |
+
"step": 1100
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 1.680672268907563,
|
| 951 |
+
"eval_loss": 0.031445007771253586,
|
| 952 |
+
"eval_runtime": 201.7681,
|
| 953 |
+
"eval_samples_per_second": 5.769,
|
| 954 |
+
"eval_steps_per_second": 5.769,
|
| 955 |
+
"step": 1100
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.6959511077158136,
|
| 959 |
+
"grad_norm": 0.3111629784107208,
|
| 960 |
+
"learning_rate": 8.352786479194288e-05,
|
| 961 |
+
"loss": 0.0351,
|
| 962 |
+
"step": 1110
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.7112299465240641,
|
| 966 |
+
"grad_norm": 0.36554020643234253,
|
| 967 |
+
"learning_rate": 8.313000303023688e-05,
|
| 968 |
+
"loss": 0.0245,
|
| 969 |
+
"step": 1120
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.7265087853323147,
|
| 973 |
+
"grad_norm": 0.18379883468151093,
|
| 974 |
+
"learning_rate": 8.27283660980128e-05,
|
| 975 |
+
"loss": 0.0371,
|
| 976 |
+
"step": 1130
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.7417876241405654,
|
| 980 |
+
"grad_norm": 0.13640639185905457,
|
| 981 |
+
"learning_rate": 8.232299976187999e-05,
|
| 982 |
+
"loss": 0.0334,
|
| 983 |
+
"step": 1140
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.7570664629488157,
|
| 987 |
+
"grad_norm": 0.205993190407753,
|
| 988 |
+
"learning_rate": 8.191395021341408e-05,
|
| 989 |
+
"loss": 0.0487,
|
| 990 |
+
"step": 1150
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.7570664629488157,
|
| 994 |
+
"eval_loss": 0.03015304170548916,
|
| 995 |
+
"eval_runtime": 201.7837,
|
| 996 |
+
"eval_samples_per_second": 5.769,
|
| 997 |
+
"eval_steps_per_second": 5.769,
|
| 998 |
+
"step": 1150
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 1.7723453017570665,
|
| 1002 |
+
"grad_norm": 0.30252721905708313,
|
| 1003 |
+
"learning_rate": 8.150126406389352e-05,
|
| 1004 |
+
"loss": 0.0299,
|
| 1005 |
+
"step": 1160
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 1.787624140565317,
|
| 1009 |
+
"grad_norm": 0.21577638387680054,
|
| 1010 |
+
"learning_rate": 8.108498833898815e-05,
|
| 1011 |
+
"loss": 0.0315,
|
| 1012 |
+
"step": 1170
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 1.8029029793735676,
|
| 1016 |
+
"grad_norm": 0.34054169058799744,
|
| 1017 |
+
"learning_rate": 8.066517047340066e-05,
|
| 1018 |
+
"loss": 0.0348,
|
| 1019 |
+
"step": 1180
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 1.8181818181818183,
|
| 1023 |
+
"grad_norm": 0.06973261386156082,
|
| 1024 |
+
"learning_rate": 8.02418583054614e-05,
|
| 1025 |
+
"loss": 0.0213,
|
| 1026 |
+
"step": 1190
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 1.8334606569900687,
|
| 1030 |
+
"grad_norm": 0.21064534783363342,
|
| 1031 |
+
"learning_rate": 7.981510007167719e-05,
|
| 1032 |
+
"loss": 0.0251,
|
| 1033 |
+
"step": 1200
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 1.8334606569900687,
|
| 1037 |
+
"eval_loss": 0.030031004920601845,
|
| 1038 |
+
"eval_runtime": 201.7876,
|
| 1039 |
+
"eval_samples_per_second": 5.768,
|
| 1040 |
+
"eval_steps_per_second": 5.768,
|
| 1041 |
+
"step": 1200
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 1.8487394957983194,
|
| 1045 |
+
"grad_norm": 0.3094477355480194,
|
| 1046 |
+
"learning_rate": 7.938494440123468e-05,
|
| 1047 |
+
"loss": 0.0295,
|
| 1048 |
+
"step": 1210
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 1.8640183346065697,
|
| 1052 |
+
"grad_norm": 0.15358871221542358,
|
| 1053 |
+
"learning_rate": 7.895144031045918e-05,
|
| 1054 |
+
"loss": 0.0287,
|
| 1055 |
+
"step": 1220
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 1.8792971734148205,
|
| 1059 |
+
"grad_norm": 0.14194321632385254,
|
| 1060 |
+
"learning_rate": 7.851463719722913e-05,
|
| 1061 |
+
"loss": 0.025,
|
| 1062 |
+
"step": 1230
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 1.894576012223071,
|
| 1066 |
+
"grad_norm": 0.1547326147556305,
|
| 1067 |
+
"learning_rate": 7.80745848353473e-05,
|
| 1068 |
+
"loss": 0.0294,
|
| 1069 |
+
"step": 1240
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 1.9098548510313216,
|
| 1073 |
+
"grad_norm": 0.42348071932792664,
|
| 1074 |
+
"learning_rate": 7.763133336886892e-05,
|
| 1075 |
+
"loss": 0.028,
|
| 1076 |
+
"step": 1250
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 1.9098548510313216,
|
| 1080 |
+
"eval_loss": 0.031990259885787964,
|
| 1081 |
+
"eval_runtime": 201.9183,
|
| 1082 |
+
"eval_samples_per_second": 5.765,
|
| 1083 |
+
"eval_steps_per_second": 5.765,
|
| 1084 |
+
"step": 1250
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 1.9251336898395723,
|
| 1088 |
+
"grad_norm": 0.10496515035629272,
|
| 1089 |
+
"learning_rate": 7.718493330638789e-05,
|
| 1090 |
+
"loss": 0.0205,
|
| 1091 |
+
"step": 1260
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 1.9404125286478227,
|
| 1095 |
+
"grad_norm": 0.07516542822122574,
|
| 1096 |
+
"learning_rate": 7.673543551528122e-05,
|
| 1097 |
+
"loss": 0.0346,
|
| 1098 |
+
"step": 1270
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 1.9556913674560734,
|
| 1102 |
+
"grad_norm": 0.5417054891586304,
|
| 1103 |
+
"learning_rate": 7.628289121591277e-05,
|
| 1104 |
+
"loss": 0.0314,
|
| 1105 |
+
"step": 1280
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 1.970970206264324,
|
| 1109 |
+
"grad_norm": 0.17793487012386322,
|
| 1110 |
+
"learning_rate": 7.582735197579656e-05,
|
| 1111 |
+
"loss": 0.0282,
|
| 1112 |
+
"step": 1290
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 1.9862490450725745,
|
| 1116 |
+
"grad_norm": 0.1875259131193161,
|
| 1117 |
+
"learning_rate": 7.536886970372078e-05,
|
| 1118 |
+
"loss": 0.0244,
|
| 1119 |
+
"step": 1300
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 1.9862490450725745,
|
| 1123 |
+
"eval_loss": 0.029929550364613533,
|
| 1124 |
+
"eval_runtime": 201.5395,
|
| 1125 |
+
"eval_samples_per_second": 5.776,
|
| 1126 |
+
"eval_steps_per_second": 5.776,
|
| 1127 |
+
"step": 1300
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 2.0015278838808253,
|
| 1131 |
+
"grad_norm": 0.14435645937919617,
|
| 1132 |
+
"learning_rate": 7.490749664383271e-05,
|
| 1133 |
+
"loss": 0.0372,
|
| 1134 |
+
"step": 1310
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 2.0168067226890756,
|
| 1138 |
+
"grad_norm": 0.09202131628990173,
|
| 1139 |
+
"learning_rate": 7.444328536968538e-05,
|
| 1140 |
+
"loss": 0.0258,
|
| 1141 |
+
"step": 1320
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 2.0320855614973263,
|
| 1145 |
+
"grad_norm": 0.43767938017845154,
|
| 1146 |
+
"learning_rate": 7.397628877824701e-05,
|
| 1147 |
+
"loss": 0.024,
|
| 1148 |
+
"step": 1330
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 2.0473644003055766,
|
| 1152 |
+
"grad_norm": 0.13443796336650848,
|
| 1153 |
+
"learning_rate": 7.350656008387327e-05,
|
| 1154 |
+
"loss": 0.0192,
|
| 1155 |
+
"step": 1340
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 2.0626432391138274,
|
| 1159 |
+
"grad_norm": 0.21498188376426697,
|
| 1160 |
+
"learning_rate": 7.303415281224346e-05,
|
| 1161 |
+
"loss": 0.0211,
|
| 1162 |
+
"step": 1350
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 2.0626432391138274,
|
| 1166 |
+
"eval_loss": 0.0282374769449234,
|
| 1167 |
+
"eval_runtime": 202.0409,
|
| 1168 |
+
"eval_samples_per_second": 5.761,
|
| 1169 |
+
"eval_steps_per_second": 5.761,
|
| 1170 |
+
"step": 1350
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 2.0779220779220777,
|
| 1174 |
+
"grad_norm": 0.1617782562971115,
|
| 1175 |
+
"learning_rate": 7.255912079426136e-05,
|
| 1176 |
+
"loss": 0.0155,
|
| 1177 |
+
"step": 1360
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 2.0932009167303285,
|
| 1181 |
+
"grad_norm": 0.07547878473997116,
|
| 1182 |
+
"learning_rate": 7.208151815992107e-05,
|
| 1183 |
+
"loss": 0.0172,
|
| 1184 |
+
"step": 1370
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 2.1084797555385792,
|
| 1188 |
+
"grad_norm": 0.34869226813316345,
|
| 1189 |
+
"learning_rate": 7.160139933213898e-05,
|
| 1190 |
+
"loss": 0.0254,
|
| 1191 |
+
"step": 1380
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 2.1237585943468296,
|
| 1195 |
+
"grad_norm": 0.2867926061153412,
|
| 1196 |
+
"learning_rate": 7.111881902055223e-05,
|
| 1197 |
+
"loss": 0.0226,
|
| 1198 |
+
"step": 1390
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 2.1390374331550803,
|
| 1202 |
+
"grad_norm": 0.26209303736686707,
|
| 1203 |
+
"learning_rate": 7.06338322152845e-05,
|
| 1204 |
+
"loss": 0.019,
|
| 1205 |
+
"step": 1400
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 2.1390374331550803,
|
| 1209 |
+
"eval_loss": 0.02854863740503788,
|
| 1210 |
+
"eval_runtime": 201.0589,
|
| 1211 |
+
"eval_samples_per_second": 5.789,
|
| 1212 |
+
"eval_steps_per_second": 5.789,
|
| 1213 |
+
"step": 1400
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 2.1543162719633306,
|
| 1217 |
+
"grad_norm": 0.17289575934410095,
|
| 1218 |
+
"learning_rate": 7.014649418067994e-05,
|
| 1219 |
+
"loss": 0.0176,
|
| 1220 |
+
"step": 1410
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 2.1695951107715814,
|
| 1224 |
+
"grad_norm": 0.22034431993961334,
|
| 1225 |
+
"learning_rate": 6.965686044900577e-05,
|
| 1226 |
+
"loss": 0.0163,
|
| 1227 |
+
"step": 1420
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 2.184873949579832,
|
| 1231 |
+
"grad_norm": 0.2867283821105957,
|
| 1232 |
+
"learning_rate": 6.91649868141243e-05,
|
| 1233 |
+
"loss": 0.0154,
|
| 1234 |
+
"step": 1430
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 2.2001527883880825,
|
| 1238 |
+
"grad_norm": 0.17423681914806366,
|
| 1239 |
+
"learning_rate": 6.86709293251353e-05,
|
| 1240 |
+
"loss": 0.0142,
|
| 1241 |
+
"step": 1440
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 2.2154316271963332,
|
| 1245 |
+
"grad_norm": 0.10424409806728363,
|
| 1246 |
+
"learning_rate": 6.817474427998916e-05,
|
| 1247 |
+
"loss": 0.012,
|
| 1248 |
+
"step": 1450
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 2.2154316271963332,
|
| 1252 |
+
"eval_loss": 0.030223889276385307,
|
| 1253 |
+
"eval_runtime": 200.9988,
|
| 1254 |
+
"eval_samples_per_second": 5.791,
|
| 1255 |
+
"eval_steps_per_second": 5.791,
|
| 1256 |
+
"step": 1450
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 2.2307104660045836,
|
| 1260 |
+
"grad_norm": 0.325139582157135,
|
| 1261 |
+
"learning_rate": 6.767648821907172e-05,
|
| 1262 |
+
"loss": 0.0192,
|
| 1263 |
+
"step": 1460
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 2.2459893048128343,
|
| 1267 |
+
"grad_norm": 0.11585790663957596,
|
| 1268 |
+
"learning_rate": 6.717621791876147e-05,
|
| 1269 |
+
"loss": 0.0302,
|
| 1270 |
+
"step": 1470
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 2.2612681436210846,
|
| 1274 |
+
"grad_norm": 0.16039828956127167,
|
| 1275 |
+
"learning_rate": 6.667399038495986e-05,
|
| 1276 |
+
"loss": 0.0207,
|
| 1277 |
+
"step": 1480
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 2.2765469824293354,
|
| 1281 |
+
"grad_norm": 0.18742448091506958,
|
| 1282 |
+
"learning_rate": 6.616986284659556e-05,
|
| 1283 |
+
"loss": 0.0247,
|
| 1284 |
+
"step": 1490
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 2.2918258212375857,
|
| 1288 |
+
"grad_norm": 0.07378096133470535,
|
| 1289 |
+
"learning_rate": 6.566389274910309e-05,
|
| 1290 |
+
"loss": 0.0181,
|
| 1291 |
+
"step": 1500
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 2.2918258212375857,
|
| 1295 |
+
"eval_loss": 0.02827996388077736,
|
| 1296 |
+
"eval_runtime": 201.0916,
|
| 1297 |
+
"eval_samples_per_second": 5.788,
|
| 1298 |
+
"eval_steps_per_second": 5.788,
|
| 1299 |
+
"step": 1500
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 2.3071046600458365,
|
| 1303 |
+
"grad_norm": 0.10507321357727051,
|
| 1304 |
+
"learning_rate": 6.515613774787697e-05,
|
| 1305 |
+
"loss": 0.019,
|
| 1306 |
+
"step": 1510
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 2.3223834988540872,
|
| 1310 |
+
"grad_norm": 0.10831980407238007,
|
| 1311 |
+
"learning_rate": 6.464665570170186e-05,
|
| 1312 |
+
"loss": 0.0215,
|
| 1313 |
+
"step": 1520
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 2.3376623376623376,
|
| 1317 |
+
"grad_norm": 0.10839013010263443,
|
| 1318 |
+
"learning_rate": 6.413550466615952e-05,
|
| 1319 |
+
"loss": 0.017,
|
| 1320 |
+
"step": 1530
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 2.3529411764705883,
|
| 1324 |
+
"grad_norm": 0.12335723638534546,
|
| 1325 |
+
"learning_rate": 6.362274288701342e-05,
|
| 1326 |
+
"loss": 0.0174,
|
| 1327 |
+
"step": 1540
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 2.3682200152788386,
|
| 1331 |
+
"grad_norm": 0.16996541619300842,
|
| 1332 |
+
"learning_rate": 6.310842879357158e-05,
|
| 1333 |
+
"loss": 0.0176,
|
| 1334 |
+
"step": 1550
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 2.3682200152788386,
|
| 1338 |
+
"eval_loss": 0.028811601921916008,
|
| 1339 |
+
"eval_runtime": 201.2139,
|
| 1340 |
+
"eval_samples_per_second": 5.785,
|
| 1341 |
+
"eval_steps_per_second": 5.785,
|
| 1342 |
+
"step": 1550
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 2.3834988540870894,
|
| 1346 |
+
"grad_norm": 0.22573326528072357,
|
| 1347 |
+
"learning_rate": 6.25926209920285e-05,
|
| 1348 |
+
"loss": 0.0117,
|
| 1349 |
+
"step": 1560
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 2.39877769289534,
|
| 1353 |
+
"grad_norm": 0.24418701231479645,
|
| 1354 |
+
"learning_rate": 6.207537825878708e-05,
|
| 1355 |
+
"loss": 0.0165,
|
| 1356 |
+
"step": 1570
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 2.4140565317035905,
|
| 1360 |
+
"grad_norm": 0.15098631381988525,
|
| 1361 |
+
"learning_rate": 6.155675953376095e-05,
|
| 1362 |
+
"loss": 0.027,
|
| 1363 |
+
"step": 1580
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 2.4293353705118412,
|
| 1367 |
+
"grad_norm": 0.1565188765525818,
|
| 1368 |
+
"learning_rate": 6.103682391365828e-05,
|
| 1369 |
+
"loss": 0.0185,
|
| 1370 |
+
"step": 1590
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 2.4446142093200915,
|
| 1374 |
+
"grad_norm": 0.0722580999135971,
|
| 1375 |
+
"learning_rate": 6.05156306452477e-05,
|
| 1376 |
+
"loss": 0.0136,
|
| 1377 |
+
"step": 1600
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 2.4446142093200915,
|
| 1381 |
+
"eval_loss": 0.027694666758179665,
|
| 1382 |
+
"eval_runtime": 201.4813,
|
| 1383 |
+
"eval_samples_per_second": 5.777,
|
| 1384 |
+
"eval_steps_per_second": 5.777,
|
| 1385 |
+
"step": 1600
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 2.4598930481283423,
|
| 1389 |
+
"grad_norm": 0.2664923667907715,
|
| 1390 |
+
"learning_rate": 5.9993239118607124e-05,
|
| 1391 |
+
"loss": 0.0251,
|
| 1392 |
+
"step": 1610
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 2.475171886936593,
|
| 1396 |
+
"grad_norm": 0.15546078979969025,
|
| 1397 |
+
"learning_rate": 5.9469708860356246e-05,
|
| 1398 |
+
"loss": 0.0207,
|
| 1399 |
+
"step": 1620
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 2.4904507257448434,
|
| 1403 |
+
"grad_norm": 0.14643099904060364,
|
| 1404 |
+
"learning_rate": 5.89450995268734e-05,
|
| 1405 |
+
"loss": 0.0195,
|
| 1406 |
+
"step": 1630
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 2.5057295645530937,
|
| 1410 |
+
"grad_norm": 0.1590198427438736,
|
| 1411 |
+
"learning_rate": 5.841947089749783e-05,
|
| 1412 |
+
"loss": 0.0251,
|
| 1413 |
+
"step": 1640
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 2.5210084033613445,
|
| 1417 |
+
"grad_norm": 0.19299504160881042,
|
| 1418 |
+
"learning_rate": 5.78928828677177e-05,
|
| 1419 |
+
"loss": 0.0217,
|
| 1420 |
+
"step": 1650
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 2.5210084033613445,
|
| 1424 |
+
"eval_loss": 0.028578663244843483,
|
| 1425 |
+
"eval_runtime": 201.0706,
|
| 1426 |
+
"eval_samples_per_second": 5.789,
|
| 1427 |
+
"eval_steps_per_second": 5.789,
|
| 1428 |
+
"step": 1650
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 2.5362872421695952,
|
| 1432 |
+
"grad_norm": 0.18513061106204987,
|
| 1433 |
+
"learning_rate": 5.7365395442345085e-05,
|
| 1434 |
+
"loss": 0.0143,
|
| 1435 |
+
"step": 1660
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 2.5515660809778455,
|
| 1439 |
+
"grad_norm": 0.1994353085756302,
|
| 1440 |
+
"learning_rate": 5.683706872867833e-05,
|
| 1441 |
+
"loss": 0.0149,
|
| 1442 |
+
"step": 1670
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 2.5668449197860963,
|
| 1446 |
+
"grad_norm": 0.20116868615150452,
|
| 1447 |
+
"learning_rate": 5.630796292965288e-05,
|
| 1448 |
+
"loss": 0.0255,
|
| 1449 |
+
"step": 1680
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 2.5821237585943466,
|
| 1453 |
+
"grad_norm": 0.1676681637763977,
|
| 1454 |
+
"learning_rate": 5.57781383369811e-05,
|
| 1455 |
+
"loss": 0.02,
|
| 1456 |
+
"step": 1690
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 2.5974025974025974,
|
| 1460 |
+
"grad_norm": 0.1904657781124115,
|
| 1461 |
+
"learning_rate": 5.524765532428203e-05,
|
| 1462 |
+
"loss": 0.0156,
|
| 1463 |
+
"step": 1700
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 2.5974025974025974,
|
| 1467 |
+
"eval_loss": 0.029410608112812042,
|
| 1468 |
+
"eval_runtime": 200.9522,
|
| 1469 |
+
"eval_samples_per_second": 5.792,
|
| 1470 |
+
"eval_steps_per_second": 5.792,
|
| 1471 |
+
"step": 1700
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 2.612681436210848,
|
| 1475 |
+
"grad_norm": 0.15733115375041962,
|
| 1476 |
+
"learning_rate": 5.471657434020182e-05,
|
| 1477 |
+
"loss": 0.0187,
|
| 1478 |
+
"step": 1710
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 2.6279602750190985,
|
| 1482 |
+
"grad_norm": 0.20242205262184143,
|
| 1483 |
+
"learning_rate": 5.418495590152557e-05,
|
| 1484 |
+
"loss": 0.0231,
|
| 1485 |
+
"step": 1720
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 2.643239113827349,
|
| 1489 |
+
"grad_norm": 0.1593477725982666,
|
| 1490 |
+
"learning_rate": 5.365286058628145e-05,
|
| 1491 |
+
"loss": 0.0212,
|
| 1492 |
+
"step": 1730
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 2.6585179526355995,
|
| 1496 |
+
"grad_norm": 0.3499566912651062,
|
| 1497 |
+
"learning_rate": 5.312034902683779e-05,
|
| 1498 |
+
"loss": 0.0268,
|
| 1499 |
+
"step": 1740
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 2.6737967914438503,
|
| 1503 |
+
"grad_norm": 0.1606576293706894,
|
| 1504 |
+
"learning_rate": 5.258748190299404e-05,
|
| 1505 |
+
"loss": 0.0191,
|
| 1506 |
+
"step": 1750
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 2.6737967914438503,
|
| 1510 |
+
"eval_loss": 0.028579337522387505,
|
| 1511 |
+
"eval_runtime": 200.7556,
|
| 1512 |
+
"eval_samples_per_second": 5.798,
|
| 1513 |
+
"eval_steps_per_second": 5.798,
|
| 1514 |
+
"step": 1750
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 2.689075630252101,
|
| 1518 |
+
"grad_norm": 0.26182451844215393,
|
| 1519 |
+
"learning_rate": 5.20543199350663e-05,
|
| 1520 |
+
"loss": 0.0217,
|
| 1521 |
+
"step": 1760
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 2.7043544690603514,
|
| 1525 |
+
"grad_norm": 0.17532721161842346,
|
| 1526 |
+
"learning_rate": 5.152092387696821e-05,
|
| 1527 |
+
"loss": 0.0215,
|
| 1528 |
+
"step": 1770
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 2.719633307868602,
|
| 1532 |
+
"grad_norm": 0.23950158059597015,
|
| 1533 |
+
"learning_rate": 5.0987354509287985e-05,
|
| 1534 |
+
"loss": 0.0224,
|
| 1535 |
+
"step": 1780
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 2.7349121466768525,
|
| 1539 |
+
"grad_norm": 0.3977627754211426,
|
| 1540 |
+
"learning_rate": 5.045367263236257e-05,
|
| 1541 |
+
"loss": 0.017,
|
| 1542 |
+
"step": 1790
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 2.750190985485103,
|
| 1546 |
+
"grad_norm": 0.10810764133930206,
|
| 1547 |
+
"learning_rate": 4.991993905934931e-05,
|
| 1548 |
+
"loss": 0.0249,
|
| 1549 |
+
"step": 1800
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 2.750190985485103,
|
| 1553 |
+
"eval_loss": 0.027184655889868736,
|
| 1554 |
+
"eval_runtime": 200.6455,
|
| 1555 |
+
"eval_samples_per_second": 5.801,
|
| 1556 |
+
"eval_steps_per_second": 5.801,
|
| 1557 |
+
"step": 1800
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 2.765469824293354,
|
| 1561 |
+
"grad_norm": 0.23987551033496857,
|
| 1562 |
+
"learning_rate": 4.938621460929639e-05,
|
| 1563 |
+
"loss": 0.0182,
|
| 1564 |
+
"step": 1810
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 2.7807486631016043,
|
| 1568 |
+
"grad_norm": 0.2798612415790558,
|
| 1569 |
+
"learning_rate": 4.885256010021233e-05,
|
| 1570 |
+
"loss": 0.0193,
|
| 1571 |
+
"step": 1820
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 2.7960275019098546,
|
| 1575 |
+
"grad_norm": 0.16607950627803802,
|
| 1576 |
+
"learning_rate": 4.831903634213599e-05,
|
| 1577 |
+
"loss": 0.0199,
|
| 1578 |
+
"step": 1830
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 2.8113063407181054,
|
| 1582 |
+
"grad_norm": 0.04422255605459213,
|
| 1583 |
+
"learning_rate": 4.778570413020702e-05,
|
| 1584 |
+
"loss": 0.0211,
|
| 1585 |
+
"step": 1840
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 2.826585179526356,
|
| 1589 |
+
"grad_norm": 0.24929310381412506,
|
| 1590 |
+
"learning_rate": 4.725262423773838e-05,
|
| 1591 |
+
"loss": 0.0237,
|
| 1592 |
+
"step": 1850
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 2.826585179526356,
|
| 1596 |
+
"eval_loss": 0.02900101989507675,
|
| 1597 |
+
"eval_runtime": 201.0849,
|
| 1598 |
+
"eval_samples_per_second": 5.789,
|
| 1599 |
+
"eval_steps_per_second": 5.789,
|
| 1600 |
+
"step": 1850
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 2.8418640183346064,
|
| 1604 |
+
"grad_norm": 0.2282838672399521,
|
| 1605 |
+
"learning_rate": 4.671985740929123e-05,
|
| 1606 |
+
"loss": 0.0165,
|
| 1607 |
+
"step": 1860
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 2.857142857142857,
|
| 1611 |
+
"grad_norm": 0.06340071558952332,
|
| 1612 |
+
"learning_rate": 4.618746435375295e-05,
|
| 1613 |
+
"loss": 0.023,
|
| 1614 |
+
"step": 1870
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 2.8724216959511075,
|
| 1618 |
+
"grad_norm": 0.04884711280465126,
|
| 1619 |
+
"learning_rate": 4.565550573741942e-05,
|
| 1620 |
+
"loss": 0.0159,
|
| 1621 |
+
"step": 1880
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 2.8877005347593583,
|
| 1625 |
+
"grad_norm": 0.24351294338703156,
|
| 1626 |
+
"learning_rate": 4.512404217708217e-05,
|
| 1627 |
+
"loss": 0.0227,
|
| 1628 |
+
"step": 1890
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 2.902979373567609,
|
| 1632 |
+
"grad_norm": 0.12852653861045837,
|
| 1633 |
+
"learning_rate": 4.45931342331209e-05,
|
| 1634 |
+
"loss": 0.021,
|
| 1635 |
+
"step": 1900
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 2.902979373567609,
|
| 1639 |
+
"eval_loss": 0.02777683548629284,
|
| 1640 |
+
"eval_runtime": 200.6223,
|
| 1641 |
+
"eval_samples_per_second": 5.802,
|
| 1642 |
+
"eval_steps_per_second": 5.802,
|
| 1643 |
+
"step": 1900
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 2.9182582123758594,
|
| 1647 |
+
"grad_norm": 0.1962100714445114,
|
| 1648 |
+
"learning_rate": 4.406284240260278e-05,
|
| 1649 |
+
"loss": 0.023,
|
| 1650 |
+
"step": 1910
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 2.93353705118411,
|
| 1654 |
+
"grad_norm": 0.16242529451847076,
|
| 1655 |
+
"learning_rate": 4.3533227112388694e-05,
|
| 1656 |
+
"loss": 0.0165,
|
| 1657 |
+
"step": 1920
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 2.9488158899923604,
|
| 1661 |
+
"grad_norm": 0.15565882623195648,
|
| 1662 |
+
"learning_rate": 4.300434871224763e-05,
|
| 1663 |
+
"loss": 0.0234,
|
| 1664 |
+
"step": 1930
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 2.964094728800611,
|
| 1668 |
+
"grad_norm": 0.1874658316373825,
|
| 1669 |
+
"learning_rate": 4.247626746797983e-05,
|
| 1670 |
+
"loss": 0.0207,
|
| 1671 |
+
"step": 1940
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 2.979373567608862,
|
| 1675 |
+
"grad_norm": 0.1462504267692566,
|
| 1676 |
+
"learning_rate": 4.1949043554549406e-05,
|
| 1677 |
+
"loss": 0.0174,
|
| 1678 |
+
"step": 1950
|
| 1679 |
+
},
|
| 1680 |
+
{
|
| 1681 |
+
"epoch": 2.979373567608862,
|
| 1682 |
+
"eval_loss": 0.028289297595620155,
|
| 1683 |
+
"eval_runtime": 200.8115,
|
| 1684 |
+
"eval_samples_per_second": 5.796,
|
| 1685 |
+
"eval_steps_per_second": 5.796,
|
| 1686 |
+
"step": 1950
|
| 1687 |
+
},
|
| 1688 |
+
{
|
| 1689 |
+
"epoch": 2.9946524064171123,
|
| 1690 |
+
"grad_norm": 0.3352892994880676,
|
| 1691 |
+
"learning_rate": 4.14227370492275e-05,
|
| 1692 |
+
"loss": 0.0261,
|
| 1693 |
+
"step": 1960
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 3.009931245225363,
|
| 1697 |
+
"grad_norm": 0.15284225344657898,
|
| 1698 |
+
"learning_rate": 4.08974079247464e-05,
|
| 1699 |
+
"loss": 0.0172,
|
| 1700 |
+
"step": 1970
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 3.0252100840336134,
|
| 1704 |
+
"grad_norm": 0.06005563586950302,
|
| 1705 |
+
"learning_rate": 4.037311604246565e-05,
|
| 1706 |
+
"loss": 0.0115,
|
| 1707 |
+
"step": 1980
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 3.040488922841864,
|
| 1711 |
+
"grad_norm": 0.21838952600955963,
|
| 1712 |
+
"learning_rate": 3.9849921145550805e-05,
|
| 1713 |
+
"loss": 0.0129,
|
| 1714 |
+
"step": 1990
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 3.0557677616501144,
|
| 1718 |
+
"grad_norm": 0.11845885962247849,
|
| 1719 |
+
"learning_rate": 3.9327882852165795e-05,
|
| 1720 |
+
"loss": 0.0122,
|
| 1721 |
+
"step": 2000
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 3.0557677616501144,
|
| 1725 |
+
"eval_loss": 0.028973255306482315,
|
| 1726 |
+
"eval_runtime": 200.9411,
|
| 1727 |
+
"eval_samples_per_second": 5.793,
|
| 1728 |
+
"eval_steps_per_second": 5.793,
|
| 1729 |
+
"step": 2000
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 3.071046600458365,
|
| 1733 |
+
"grad_norm": 0.09495562314987183,
|
| 1734 |
+
"learning_rate": 3.880706064867926e-05,
|
| 1735 |
+
"loss": 0.0125,
|
| 1736 |
+
"step": 2010
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 3.0863254392666155,
|
| 1740 |
+
"grad_norm": 0.16284717619419098,
|
| 1741 |
+
"learning_rate": 3.8287513882886196e-05,
|
| 1742 |
+
"loss": 0.009,
|
| 1743 |
+
"step": 2020
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 3.1016042780748663,
|
| 1747 |
+
"grad_norm": 0.1330808848142624,
|
| 1748 |
+
"learning_rate": 3.776930175724521e-05,
|
| 1749 |
+
"loss": 0.011,
|
| 1750 |
+
"step": 2030
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 3.116883116883117,
|
| 1754 |
+
"grad_norm": 0.1752845197916031,
|
| 1755 |
+
"learning_rate": 3.7252483322132386e-05,
|
| 1756 |
+
"loss": 0.0128,
|
| 1757 |
+
"step": 2040
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 3.1321619556913673,
|
| 1761 |
+
"grad_norm": 0.09726885706186295,
|
| 1762 |
+
"learning_rate": 3.673711746911252e-05,
|
| 1763 |
+
"loss": 0.0137,
|
| 1764 |
+
"step": 2050
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 3.1321619556913673,
|
| 1768 |
+
"eval_loss": 0.030082957819104195,
|
| 1769 |
+
"eval_runtime": 200.9521,
|
| 1770 |
+
"eval_samples_per_second": 5.792,
|
| 1771 |
+
"eval_steps_per_second": 5.792,
|
| 1772 |
+
"step": 2050
|
| 1773 |
+
},
|
| 1774 |
+
{
|
| 1775 |
+
"epoch": 3.147440794499618,
|
| 1776 |
+
"grad_norm": 0.09027769416570663,
|
| 1777 |
+
"learning_rate": 3.6223262924228344e-05,
|
| 1778 |
+
"loss": 0.0078,
|
| 1779 |
+
"step": 2060
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 3.1627196333078684,
|
| 1783 |
+
"grad_norm": 0.08661149442195892,
|
| 1784 |
+
"learning_rate": 3.5710978241308733e-05,
|
| 1785 |
+
"loss": 0.013,
|
| 1786 |
+
"step": 2070
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 3.177998472116119,
|
| 1790 |
+
"grad_norm": 0.19561336934566498,
|
| 1791 |
+
"learning_rate": 3.520032179529652e-05,
|
| 1792 |
+
"loss": 0.0123,
|
| 1793 |
+
"step": 2080
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 3.19327731092437,
|
| 1797 |
+
"grad_norm": 0.28915536403656006,
|
| 1798 |
+
"learning_rate": 3.4691351775596564e-05,
|
| 1799 |
+
"loss": 0.0135,
|
| 1800 |
+
"step": 2090
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"epoch": 3.2085561497326203,
|
| 1804 |
+
"grad_norm": 0.12461555749177933,
|
| 1805 |
+
"learning_rate": 3.41841261794451e-05,
|
| 1806 |
+
"loss": 0.0086,
|
| 1807 |
+
"step": 2100
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 3.2085561497326203,
|
| 1811 |
+
"eval_loss": 0.030945168808102608,
|
| 1812 |
+
"eval_runtime": 200.348,
|
| 1813 |
+
"eval_samples_per_second": 5.81,
|
| 1814 |
+
"eval_steps_per_second": 5.81,
|
| 1815 |
+
"step": 2100
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 3.223834988540871,
|
| 1819 |
+
"grad_norm": 0.17976081371307373,
|
| 1820 |
+
"learning_rate": 3.367870280530101e-05,
|
| 1821 |
+
"loss": 0.0176,
|
| 1822 |
+
"step": 2110
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 3.2391138273491213,
|
| 1826 |
+
"grad_norm": 0.17633405327796936,
|
| 1827 |
+
"learning_rate": 3.3175139246259536e-05,
|
| 1828 |
+
"loss": 0.0109,
|
| 1829 |
+
"step": 2120
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 3.254392666157372,
|
| 1833 |
+
"grad_norm": 0.23417995870113373,
|
| 1834 |
+
"learning_rate": 3.2673492883489696e-05,
|
| 1835 |
+
"loss": 0.0105,
|
| 1836 |
+
"step": 2130
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 3.2696715049656224,
|
| 1840 |
+
"grad_norm": 0.385770320892334,
|
| 1841 |
+
"learning_rate": 3.2173820879695535e-05,
|
| 1842 |
+
"loss": 0.0166,
|
| 1843 |
+
"step": 2140
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 3.284950343773873,
|
| 1847 |
+
"grad_norm": 0.1962185502052307,
|
| 1848 |
+
"learning_rate": 3.1676180172602525e-05,
|
| 1849 |
+
"loss": 0.0136,
|
| 1850 |
+
"step": 2150
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 3.284950343773873,
|
| 1854 |
+
"eval_loss": 0.030590800568461418,
|
| 1855 |
+
"eval_runtime": 199.5546,
|
| 1856 |
+
"eval_samples_per_second": 5.833,
|
| 1857 |
+
"eval_steps_per_second": 5.833,
|
| 1858 |
+
"step": 2150
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 3.300229182582124,
|
| 1862 |
+
"grad_norm": 0.07931424677371979,
|
| 1863 |
+
"learning_rate": 3.11806274684695e-05,
|
| 1864 |
+
"loss": 0.0115,
|
| 1865 |
+
"step": 2160
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 3.3155080213903743,
|
| 1869 |
+
"grad_norm": 0.12415704876184464,
|
| 1870 |
+
"learning_rate": 3.068721923562688e-05,
|
| 1871 |
+
"loss": 0.0076,
|
| 1872 |
+
"step": 2170
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 3.330786860198625,
|
| 1876 |
+
"grad_norm": 0.1858009248971939,
|
| 1877 |
+
"learning_rate": 3.019601169804216e-05,
|
| 1878 |
+
"loss": 0.0109,
|
| 1879 |
+
"step": 2180
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 3.3460656990068753,
|
| 1883 |
+
"grad_norm": 0.15695886313915253,
|
| 1884 |
+
"learning_rate": 2.9707060828913225e-05,
|
| 1885 |
+
"loss": 0.0086,
|
| 1886 |
+
"step": 2190
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 3.361344537815126,
|
| 1890 |
+
"grad_norm": 0.5040724277496338,
|
| 1891 |
+
"learning_rate": 2.9220422344290056e-05,
|
| 1892 |
+
"loss": 0.0111,
|
| 1893 |
+
"step": 2200
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 3.361344537815126,
|
| 1897 |
+
"eval_loss": 0.03102887235581875,
|
| 1898 |
+
"eval_runtime": 200.5885,
|
| 1899 |
+
"eval_samples_per_second": 5.803,
|
| 1900 |
+
"eval_steps_per_second": 5.803,
|
| 1901 |
+
"step": 2200
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"epoch": 3.3766233766233764,
|
| 1905 |
+
"grad_norm": 0.2534728944301605,
|
| 1906 |
+
"learning_rate": 2.873615169672601e-05,
|
| 1907 |
+
"loss": 0.0099,
|
| 1908 |
+
"step": 2210
|
| 1909 |
+
},
|
| 1910 |
+
{
|
| 1911 |
+
"epoch": 3.391902215431627,
|
| 1912 |
+
"grad_norm": 0.10433147847652435,
|
| 1913 |
+
"learning_rate": 2.8254304068958927e-05,
|
| 1914 |
+
"loss": 0.011,
|
| 1915 |
+
"step": 2220
|
| 1916 |
+
},
|
| 1917 |
+
{
|
| 1918 |
+
"epoch": 3.407181054239878,
|
| 1919 |
+
"grad_norm": 0.09524795413017273,
|
| 1920 |
+
"learning_rate": 2.7774934367622996e-05,
|
| 1921 |
+
"loss": 0.0159,
|
| 1922 |
+
"step": 2230
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 3.4224598930481283,
|
| 1926 |
+
"grad_norm": 0.1627880036830902,
|
| 1927 |
+
"learning_rate": 2.7298097216992284e-05,
|
| 1928 |
+
"loss": 0.0095,
|
| 1929 |
+
"step": 2240
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 3.437738731856379,
|
| 1933 |
+
"grad_norm": 0.24664515256881714,
|
| 1934 |
+
"learning_rate": 2.6823846952756125e-05,
|
| 1935 |
+
"loss": 0.0142,
|
| 1936 |
+
"step": 2250
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 3.437738731856379,
|
| 1940 |
+
"eval_loss": 0.03270566090941429,
|
| 1941 |
+
"eval_runtime": 200.5417,
|
| 1942 |
+
"eval_samples_per_second": 5.804,
|
| 1943 |
+
"eval_steps_per_second": 5.804,
|
| 1944 |
+
"step": 2250
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"epoch": 3.4530175706646293,
|
| 1948 |
+
"grad_norm": 0.2718111276626587,
|
| 1949 |
+
"learning_rate": 2.6352237615827636e-05,
|
| 1950 |
+
"loss": 0.0077,
|
| 1951 |
+
"step": 2260
|
| 1952 |
+
},
|
| 1953 |
+
{
|
| 1954 |
+
"epoch": 3.46829640947288,
|
| 1955 |
+
"grad_norm": 0.2555138170719147,
|
| 1956 |
+
"learning_rate": 2.5883322946185777e-05,
|
| 1957 |
+
"loss": 0.0129,
|
| 1958 |
+
"step": 2270
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 3.483575248281131,
|
| 1962 |
+
"grad_norm": 0.23297752439975739,
|
| 1963 |
+
"learning_rate": 2.5417156376751562e-05,
|
| 1964 |
+
"loss": 0.0124,
|
| 1965 |
+
"step": 2280
|
| 1966 |
+
},
|
| 1967 |
+
{
|
| 1968 |
+
"epoch": 3.498854087089381,
|
| 1969 |
+
"grad_norm": 0.24713806807994843,
|
| 1970 |
+
"learning_rate": 2.4953791027299506e-05,
|
| 1971 |
+
"loss": 0.008,
|
| 1972 |
+
"step": 2290
|
| 1973 |
+
},
|
| 1974 |
+
{
|
| 1975 |
+
"epoch": 3.514132925897632,
|
| 1976 |
+
"grad_norm": 0.15914295613765717,
|
| 1977 |
+
"learning_rate": 2.4493279698404493e-05,
|
| 1978 |
+
"loss": 0.0114,
|
| 1979 |
+
"step": 2300
|
| 1980 |
+
},
|
| 1981 |
+
{
|
| 1982 |
+
"epoch": 3.514132925897632,
|
| 1983 |
+
"eval_loss": 0.031200075522065163,
|
| 1984 |
+
"eval_runtime": 200.6578,
|
| 1985 |
+
"eval_samples_per_second": 5.801,
|
| 1986 |
+
"eval_steps_per_second": 5.801,
|
| 1987 |
+
"step": 2300
|
| 1988 |
+
},
|
| 1989 |
+
{
|
| 1990 |
+
"epoch": 3.5294117647058822,
|
| 1991 |
+
"grad_norm": 0.14958317577838898,
|
| 1992 |
+
"learning_rate": 2.403567486542518e-05,
|
| 1993 |
+
"loss": 0.0107,
|
| 1994 |
+
"step": 2310
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 3.544690603514133,
|
| 1998 |
+
"grad_norm": 0.10404475033283234,
|
| 1999 |
+
"learning_rate": 2.3581028672524485e-05,
|
| 2000 |
+
"loss": 0.0111,
|
| 2001 |
+
"step": 2320
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 3.5599694423223838,
|
| 2005 |
+
"grad_norm": 0.11570907384157181,
|
| 2006 |
+
"learning_rate": 2.312939292672765e-05,
|
| 2007 |
+
"loss": 0.0088,
|
| 2008 |
+
"step": 2330
|
| 2009 |
+
},
|
| 2010 |
+
{
|
| 2011 |
+
"epoch": 3.575248281130634,
|
| 2012 |
+
"grad_norm": 0.1450202912092209,
|
| 2013 |
+
"learning_rate": 2.268081909201885e-05,
|
| 2014 |
+
"loss": 0.0087,
|
| 2015 |
+
"step": 2340
|
| 2016 |
+
},
|
| 2017 |
+
{
|
| 2018 |
+
"epoch": 3.5905271199388844,
|
| 2019 |
+
"grad_norm": 0.1596309393644333,
|
| 2020 |
+
"learning_rate": 2.2235358283476936e-05,
|
| 2021 |
+
"loss": 0.015,
|
| 2022 |
+
"step": 2350
|
| 2023 |
+
},
|
| 2024 |
+
{
|
| 2025 |
+
"epoch": 3.5905271199388844,
|
| 2026 |
+
"eval_loss": 0.031868599355220795,
|
| 2027 |
+
"eval_runtime": 200.4001,
|
| 2028 |
+
"eval_samples_per_second": 5.808,
|
| 2029 |
+
"eval_steps_per_second": 5.808,
|
| 2030 |
+
"step": 2350
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 3.605805958747135,
|
| 2034 |
+
"grad_norm": 0.13130627572536469,
|
| 2035 |
+
"learning_rate": 2.179306126145075e-05,
|
| 2036 |
+
"loss": 0.0135,
|
| 2037 |
+
"step": 2360
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"epoch": 3.621084797555386,
|
| 2041 |
+
"grad_norm": 0.2653070390224457,
|
| 2042 |
+
"learning_rate": 2.1353978425775008e-05,
|
| 2043 |
+
"loss": 0.0129,
|
| 2044 |
+
"step": 2370
|
| 2045 |
+
},
|
| 2046 |
+
{
|
| 2047 |
+
"epoch": 3.6363636363636362,
|
| 2048 |
+
"grad_norm": 0.20412729680538177,
|
| 2049 |
+
"learning_rate": 2.091815981002731e-05,
|
| 2050 |
+
"loss": 0.0101,
|
| 2051 |
+
"step": 2380
|
| 2052 |
+
},
|
| 2053 |
+
{
|
| 2054 |
+
"epoch": 3.651642475171887,
|
| 2055 |
+
"grad_norm": 0.18179409205913544,
|
| 2056 |
+
"learning_rate": 2.0485655075826667e-05,
|
| 2057 |
+
"loss": 0.0141,
|
| 2058 |
+
"step": 2390
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 3.6669213139801373,
|
| 2062 |
+
"grad_norm": 0.3348677158355713,
|
| 2063 |
+
"learning_rate": 2.0056513507174685e-05,
|
| 2064 |
+
"loss": 0.0088,
|
| 2065 |
+
"step": 2400
|
| 2066 |
+
},
|
| 2067 |
+
{
|
| 2068 |
+
"epoch": 3.6669213139801373,
|
| 2069 |
+
"eval_loss": 0.030020447447896004,
|
| 2070 |
+
"eval_runtime": 200.0438,
|
| 2071 |
+
"eval_samples_per_second": 5.819,
|
| 2072 |
+
"eval_steps_per_second": 5.819,
|
| 2073 |
+
"step": 2400
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 3.682200152788388,
|
| 2077 |
+
"grad_norm": 0.25341227650642395,
|
| 2078 |
+
"learning_rate": 1.963078400483953e-05,
|
| 2079 |
+
"loss": 0.0111,
|
| 2080 |
+
"step": 2410
|
| 2081 |
+
},
|
| 2082 |
+
{
|
| 2083 |
+
"epoch": 3.697478991596639,
|
| 2084 |
+
"grad_norm": 0.2232055962085724,
|
| 2085 |
+
"learning_rate": 1.9208515080783723e-05,
|
| 2086 |
+
"loss": 0.0087,
|
| 2087 |
+
"step": 2420
|
| 2088 |
+
},
|
| 2089 |
+
{
|
| 2090 |
+
"epoch": 3.712757830404889,
|
| 2091 |
+
"grad_norm": 0.29884758591651917,
|
| 2092 |
+
"learning_rate": 1.8789754852636245e-05,
|
| 2093 |
+
"loss": 0.0084,
|
| 2094 |
+
"step": 2430
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 3.72803666921314,
|
| 2098 |
+
"grad_norm": 0.2963765859603882,
|
| 2099 |
+
"learning_rate": 1.837455103820942e-05,
|
| 2100 |
+
"loss": 0.0173,
|
| 2101 |
+
"step": 2440
|
| 2102 |
+
},
|
| 2103 |
+
{
|
| 2104 |
+
"epoch": 3.7433155080213902,
|
| 2105 |
+
"grad_norm": 0.06125696748495102,
|
| 2106 |
+
"learning_rate": 1.7962950950061502e-05,
|
| 2107 |
+
"loss": 0.0068,
|
| 2108 |
+
"step": 2450
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 3.7433155080213902,
|
| 2112 |
+
"eval_loss": 0.03097730502486229,
|
| 2113 |
+
"eval_runtime": 199.2868,
|
| 2114 |
+
"eval_samples_per_second": 5.841,
|
| 2115 |
+
"eval_steps_per_second": 5.841,
|
| 2116 |
+
"step": 2450
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 3.758594346829641,
|
| 2120 |
+
"grad_norm": 0.330082505941391,
|
| 2121 |
+
"learning_rate": 1.7555001490105488e-05,
|
| 2122 |
+
"loss": 0.0103,
|
| 2123 |
+
"step": 2460
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 3.7738731856378918,
|
| 2127 |
+
"grad_norm": 0.3047909438610077,
|
| 2128 |
+
"learning_rate": 1.7150749144264462e-05,
|
| 2129 |
+
"loss": 0.0123,
|
| 2130 |
+
"step": 2470
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 3.789152024446142,
|
| 2134 |
+
"grad_norm": 0.09779535233974457,
|
| 2135 |
+
"learning_rate": 1.6750239977174682e-05,
|
| 2136 |
+
"loss": 0.0097,
|
| 2137 |
+
"step": 2480
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 3.8044308632543924,
|
| 2141 |
+
"grad_norm": 0.3834091126918793,
|
| 2142 |
+
"learning_rate": 1.6353519626936397e-05,
|
| 2143 |
+
"loss": 0.0145,
|
| 2144 |
+
"step": 2490
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 3.819709702062643,
|
| 2148 |
+
"grad_norm": 0.12687507271766663,
|
| 2149 |
+
"learning_rate": 1.596063329991341e-05,
|
| 2150 |
+
"loss": 0.0098,
|
| 2151 |
+
"step": 2500
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 3.819709702062643,
|
| 2155 |
+
"eval_loss": 0.02996741607785225,
|
| 2156 |
+
"eval_runtime": 199.4136,
|
| 2157 |
+
"eval_samples_per_second": 5.837,
|
| 2158 |
+
"eval_steps_per_second": 5.837,
|
| 2159 |
+
"step": 2500
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 3.834988540870894,
|
| 2163 |
+
"grad_norm": 0.10428875684738159,
|
| 2164 |
+
"learning_rate": 1.5571625765581832e-05,
|
| 2165 |
+
"loss": 0.0081,
|
| 2166 |
+
"step": 2510
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 3.8502673796791442,
|
| 2170 |
+
"grad_norm": 0.2717987895011902,
|
| 2171 |
+
"learning_rate": 1.5186541351428545e-05,
|
| 2172 |
+
"loss": 0.012,
|
| 2173 |
+
"step": 2520
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 3.865546218487395,
|
| 2177 |
+
"grad_norm": 0.6217739582061768,
|
| 2178 |
+
"learning_rate": 1.4805423937900087e-05,
|
| 2179 |
+
"loss": 0.0138,
|
| 2180 |
+
"step": 2530
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 3.8808250572956453,
|
| 2184 |
+
"grad_norm": 0.14223617315292358,
|
| 2185 |
+
"learning_rate": 1.4428316953402526e-05,
|
| 2186 |
+
"loss": 0.0095,
|
| 2187 |
+
"step": 2540
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 3.896103896103896,
|
| 2191 |
+
"grad_norm": 0.42163944244384766,
|
| 2192 |
+
"learning_rate": 1.4055263369352672e-05,
|
| 2193 |
+
"loss": 0.0088,
|
| 2194 |
+
"step": 2550
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 3.896103896103896,
|
| 2198 |
+
"eval_loss": 0.02977598085999489,
|
| 2199 |
+
"eval_runtime": 199.4878,
|
| 2200 |
+
"eval_samples_per_second": 5.835,
|
| 2201 |
+
"eval_steps_per_second": 5.835,
|
| 2202 |
+
"step": 2550
|
| 2203 |
+
},
|
| 2204 |
+
{
|
| 2205 |
+
"epoch": 3.911382734912147,
|
| 2206 |
+
"grad_norm": 0.27528712153434753,
|
| 2207 |
+
"learning_rate": 1.3686305695281559e-05,
|
| 2208 |
+
"loss": 0.0111,
|
| 2209 |
+
"step": 2560
|
| 2210 |
+
},
|
| 2211 |
+
{
|
| 2212 |
+
"epoch": 3.926661573720397,
|
| 2213 |
+
"grad_norm": 0.07628080993890762,
|
| 2214 |
+
"learning_rate": 1.3321485973990494e-05,
|
| 2215 |
+
"loss": 0.0083,
|
| 2216 |
+
"step": 2570
|
| 2217 |
+
},
|
| 2218 |
+
{
|
| 2219 |
+
"epoch": 3.941940412528648,
|
| 2220 |
+
"grad_norm": 0.3497057855129242,
|
| 2221 |
+
"learning_rate": 1.2960845776760156e-05,
|
| 2222 |
+
"loss": 0.0164,
|
| 2223 |
+
"step": 2580
|
| 2224 |
+
},
|
| 2225 |
+
{
|
| 2226 |
+
"epoch": 3.9572192513368982,
|
| 2227 |
+
"grad_norm": 0.1905433088541031,
|
| 2228 |
+
"learning_rate": 1.2604426198613688e-05,
|
| 2229 |
+
"loss": 0.0089,
|
| 2230 |
+
"step": 2590
|
| 2231 |
+
},
|
| 2232 |
+
{
|
| 2233 |
+
"epoch": 3.972498090145149,
|
| 2234 |
+
"grad_norm": 0.29687440395355225,
|
| 2235 |
+
"learning_rate": 1.2252267853633798e-05,
|
| 2236 |
+
"loss": 0.0081,
|
| 2237 |
+
"step": 2600
|
| 2238 |
+
},
|
| 2239 |
+
{
|
| 2240 |
+
"epoch": 3.972498090145149,
|
| 2241 |
+
"eval_loss": 0.030624018982052803,
|
| 2242 |
+
"eval_runtime": 199.6483,
|
| 2243 |
+
"eval_samples_per_second": 5.83,
|
| 2244 |
+
"eval_steps_per_second": 5.83,
|
| 2245 |
+
"step": 2600
|
| 2246 |
+
},
|
| 2247 |
+
{
|
| 2248 |
+
"epoch": 3.9877769289533997,
|
| 2249 |
+
"grad_norm": 0.16313646733760834,
|
| 2250 |
+
"learning_rate": 1.1904410870334803e-05,
|
| 2251 |
+
"loss": 0.0132,
|
| 2252 |
+
"step": 2610
|
| 2253 |
+
},
|
| 2254 |
+
{
|
| 2255 |
+
"epoch": 4.0030557677616505,
|
| 2256 |
+
"grad_norm": 0.20121262967586517,
|
| 2257 |
+
"learning_rate": 1.1560894887090052e-05,
|
| 2258 |
+
"loss": 0.011,
|
| 2259 |
+
"step": 2620
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"epoch": 4.0183346065699,
|
| 2263 |
+
"grad_norm": 0.3056090772151947,
|
| 2264 |
+
"learning_rate": 1.1221759047615004e-05,
|
| 2265 |
+
"loss": 0.0084,
|
| 2266 |
+
"step": 2630
|
| 2267 |
+
},
|
| 2268 |
+
{
|
| 2269 |
+
"epoch": 4.033613445378151,
|
| 2270 |
+
"grad_norm": 0.07052377611398697,
|
| 2271 |
+
"learning_rate": 1.0887041996506859e-05,
|
| 2272 |
+
"loss": 0.0041,
|
| 2273 |
+
"step": 2640
|
| 2274 |
+
},
|
| 2275 |
+
{
|
| 2276 |
+
"epoch": 4.048892284186402,
|
| 2277 |
+
"grad_norm": 0.07718514651060104,
|
| 2278 |
+
"learning_rate": 1.0556781874841027e-05,
|
| 2279 |
+
"loss": 0.0052,
|
| 2280 |
+
"step": 2650
|
| 2281 |
+
},
|
| 2282 |
+
{
|
| 2283 |
+
"epoch": 4.048892284186402,
|
| 2284 |
+
"eval_loss": 0.031373970210552216,
|
| 2285 |
+
"eval_runtime": 199.7835,
|
| 2286 |
+
"eval_samples_per_second": 5.826,
|
| 2287 |
+
"eval_steps_per_second": 5.826,
|
| 2288 |
+
"step": 2650
|
| 2289 |
+
},
|
| 2290 |
+
{
|
| 2291 |
+
"epoch": 4.064171122994653,
|
| 2292 |
+
"grad_norm": 0.09308119118213654,
|
| 2293 |
+
"learning_rate": 1.0231016315824875e-05,
|
| 2294 |
+
"loss": 0.0042,
|
| 2295 |
+
"step": 2660
|
| 2296 |
+
},
|
| 2297 |
+
{
|
| 2298 |
+
"epoch": 4.0794499618029025,
|
| 2299 |
+
"grad_norm": 0.04948989301919937,
|
| 2300 |
+
"learning_rate": 9.909782440509491e-06,
|
| 2301 |
+
"loss": 0.0063,
|
| 2302 |
+
"step": 2670
|
| 2303 |
+
},
|
| 2304 |
+
{
|
| 2305 |
+
"epoch": 4.094728800611153,
|
| 2306 |
+
"grad_norm": 0.328868567943573,
|
| 2307 |
+
"learning_rate": 9.593116853559648e-06,
|
| 2308 |
+
"loss": 0.0076,
|
| 2309 |
+
"step": 2680
|
| 2310 |
+
},
|
| 2311 |
+
{
|
| 2312 |
+
"epoch": 4.110007639419404,
|
| 2313 |
+
"grad_norm": 0.03805866092443466,
|
| 2314 |
+
"learning_rate": 9.281055639082747e-06,
|
| 2315 |
+
"loss": 0.009,
|
| 2316 |
+
"step": 2690
|
| 2317 |
+
},
|
| 2318 |
+
{
|
| 2319 |
+
"epoch": 4.125286478227655,
|
| 2320 |
+
"grad_norm": 0.16321790218353271,
|
| 2321 |
+
"learning_rate": 8.973634356517063e-06,
|
| 2322 |
+
"loss": 0.0076,
|
| 2323 |
+
"step": 2700
|
| 2324 |
+
},
|
| 2325 |
+
{
|
| 2326 |
+
"epoch": 4.125286478227655,
|
| 2327 |
+
"eval_loss": 0.03259371221065521,
|
| 2328 |
+
"eval_runtime": 199.7271,
|
| 2329 |
+
"eval_samples_per_second": 5.828,
|
| 2330 |
+
"eval_steps_per_second": 5.828,
|
| 2331 |
+
"step": 2700
|
| 2332 |
+
},
|
| 2333 |
+
{
|
| 2334 |
+
"epoch": 4.140565317035906,
|
| 2335 |
+
"grad_norm": 0.2903512120246887,
|
| 2336 |
+
"learning_rate": 8.670888036579639e-06,
|
| 2337 |
+
"loss": 0.0056,
|
| 2338 |
+
"step": 2710
|
| 2339 |
+
},
|
| 2340 |
+
{
|
| 2341 |
+
"epoch": 4.1558441558441555,
|
| 2342 |
+
"grad_norm": 0.06461212784051895,
|
| 2343 |
+
"learning_rate": 8.372851177274604e-06,
|
| 2344 |
+
"loss": 0.0064,
|
| 2345 |
+
"step": 2720
|
| 2346 |
+
},
|
| 2347 |
+
{
|
| 2348 |
+
"epoch": 4.171122994652406,
|
| 2349 |
+
"grad_norm": 0.3396087884902954,
|
| 2350 |
+
"learning_rate": 8.079557739962128e-06,
|
| 2351 |
+
"loss": 0.0063,
|
| 2352 |
+
"step": 2730
|
| 2353 |
+
},
|
| 2354 |
+
{
|
| 2355 |
+
"epoch": 4.186401833460657,
|
| 2356 |
+
"grad_norm": 0.14997313916683197,
|
| 2357 |
+
"learning_rate": 7.791041145488454e-06,
|
| 2358 |
+
"loss": 0.0065,
|
| 2359 |
+
"step": 2740
|
| 2360 |
+
},
|
| 2361 |
+
{
|
| 2362 |
+
"epoch": 4.201680672268908,
|
| 2363 |
+
"grad_norm": 0.1173219084739685,
|
| 2364 |
+
"learning_rate": 7.507334270377619e-06,
|
| 2365 |
+
"loss": 0.0091,
|
| 2366 |
+
"step": 2750
|
| 2367 |
+
},
|
| 2368 |
+
{
|
| 2369 |
+
"epoch": 4.201680672268908,
|
| 2370 |
+
"eval_loss": 0.03307883441448212,
|
| 2371 |
+
"eval_runtime": 199.4548,
|
| 2372 |
+
"eval_samples_per_second": 5.836,
|
| 2373 |
+
"eval_steps_per_second": 5.836,
|
| 2374 |
+
"step": 2750
|
| 2375 |
+
},
|
| 2376 |
+
{
|
| 2377 |
+
"epoch": 4.2169595110771585,
|
| 2378 |
+
"grad_norm": 0.14040367305278778,
|
| 2379 |
+
"learning_rate": 7.228469443085206e-06,
|
| 2380 |
+
"loss": 0.0072,
|
| 2381 |
+
"step": 2760
|
| 2382 |
+
},
|
| 2383 |
+
{
|
| 2384 |
+
"epoch": 4.232238349885408,
|
| 2385 |
+
"grad_norm": 0.11947222054004669,
|
| 2386 |
+
"learning_rate": 6.954478440314427e-06,
|
| 2387 |
+
"loss": 0.0079,
|
| 2388 |
+
"step": 2770
|
| 2389 |
+
},
|
| 2390 |
+
{
|
| 2391 |
+
"epoch": 4.247517188693659,
|
| 2392 |
+
"grad_norm": 0.08814125508069992,
|
| 2393 |
+
"learning_rate": 6.685392483395259e-06,
|
| 2394 |
+
"loss": 0.0029,
|
| 2395 |
+
"step": 2780
|
| 2396 |
+
},
|
| 2397 |
+
{
|
| 2398 |
+
"epoch": 4.26279602750191,
|
| 2399 |
+
"grad_norm": 0.13022877275943756,
|
| 2400 |
+
"learning_rate": 6.421242234726682e-06,
|
| 2401 |
+
"loss": 0.0055,
|
| 2402 |
+
"step": 2790
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 4.278074866310161,
|
| 2406 |
+
"grad_norm": 0.22816994786262512,
|
| 2407 |
+
"learning_rate": 6.1620577942827166e-06,
|
| 2408 |
+
"loss": 0.0045,
|
| 2409 |
+
"step": 2800
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 4.278074866310161,
|
| 2413 |
+
"eval_loss": 0.0341590940952301,
|
| 2414 |
+
"eval_runtime": 199.141,
|
| 2415 |
+
"eval_samples_per_second": 5.845,
|
| 2416 |
+
"eval_steps_per_second": 5.845,
|
| 2417 |
+
"step": 2800
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 4.293353705118411,
|
| 2421 |
+
"grad_norm": 0.7083064317703247,
|
| 2422 |
+
"learning_rate": 5.907868696182584e-06,
|
| 2423 |
+
"loss": 0.0058,
|
| 2424 |
+
"step": 2810
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 4.308632543926661,
|
| 2428 |
+
"grad_norm": 0.029391461983323097,
|
| 2429 |
+
"learning_rate": 5.658703905325186e-06,
|
| 2430 |
+
"loss": 0.0078,
|
| 2431 |
+
"step": 2820
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 4.323911382734912,
|
| 2435 |
+
"grad_norm": 0.17884346842765808,
|
| 2436 |
+
"learning_rate": 5.414591814088627e-06,
|
| 2437 |
+
"loss": 0.0077,
|
| 2438 |
+
"step": 2830
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 4.339190221543163,
|
| 2442 |
+
"grad_norm": 0.07933899760246277,
|
| 2443 |
+
"learning_rate": 5.17556023909489e-06,
|
| 2444 |
+
"loss": 0.0059,
|
| 2445 |
+
"step": 2840
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 4.354469060351414,
|
| 2449 |
+
"grad_norm": 0.22485603392124176,
|
| 2450 |
+
"learning_rate": 4.941636418040058e-06,
|
| 2451 |
+
"loss": 0.0047,
|
| 2452 |
+
"step": 2850
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 4.354469060351414,
|
| 2456 |
+
"eval_loss": 0.034740038216114044,
|
| 2457 |
+
"eval_runtime": 199.1325,
|
| 2458 |
+
"eval_samples_per_second": 5.845,
|
| 2459 |
+
"eval_steps_per_second": 5.845,
|
| 2460 |
+
"step": 2850
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 4.369747899159664,
|
| 2464 |
+
"grad_norm": 0.30258139967918396,
|
| 2465 |
+
"learning_rate": 4.7128470065906925e-06,
|
| 2466 |
+
"loss": 0.0041,
|
| 2467 |
+
"step": 2860
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 4.385026737967914,
|
| 2471 |
+
"grad_norm": 0.20538049936294556,
|
| 2472 |
+
"learning_rate": 4.4892180753462744e-06,
|
| 2473 |
+
"loss": 0.0039,
|
| 2474 |
+
"step": 2870
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 4.400305576776165,
|
| 2478 |
+
"grad_norm": 0.1709292232990265,
|
| 2479 |
+
"learning_rate": 4.270775106868586e-06,
|
| 2480 |
+
"loss": 0.004,
|
| 2481 |
+
"step": 2880
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 4.415584415584416,
|
| 2485 |
+
"grad_norm": 0.12943388521671295,
|
| 2486 |
+
"learning_rate": 4.057542992777868e-06,
|
| 2487 |
+
"loss": 0.0057,
|
| 2488 |
+
"step": 2890
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 4.4308632543926665,
|
| 2492 |
+
"grad_norm": 0.07701294124126434,
|
| 2493 |
+
"learning_rate": 3.849546030916473e-06,
|
| 2494 |
+
"loss": 0.0047,
|
| 2495 |
+
"step": 2900
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 4.4308632543926665,
|
| 2499 |
+
"eval_loss": 0.03577398136258125,
|
| 2500 |
+
"eval_runtime": 199.2545,
|
| 2501 |
+
"eval_samples_per_second": 5.842,
|
| 2502 |
+
"eval_steps_per_second": 5.842,
|
| 2503 |
+
"step": 2900
|
| 2504 |
+
},
|
| 2505 |
+
{
|
| 2506 |
+
"epoch": 4.446142093200916,
|
| 2507 |
+
"grad_norm": 0.42437708377838135,
|
| 2508 |
+
"learning_rate": 3.646807922580098e-06,
|
| 2509 |
+
"loss": 0.004,
|
| 2510 |
+
"step": 2910
|
| 2511 |
+
},
|
| 2512 |
+
{
|
| 2513 |
+
"epoch": 4.461420932009167,
|
| 2514 |
+
"grad_norm": 0.21150662004947662,
|
| 2515 |
+
"learning_rate": 3.4493517698170164e-06,
|
| 2516 |
+
"loss": 0.0082,
|
| 2517 |
+
"step": 2920
|
| 2518 |
+
},
|
| 2519 |
+
{
|
| 2520 |
+
"epoch": 4.476699770817418,
|
| 2521 |
+
"grad_norm": 0.15437455475330353,
|
| 2522 |
+
"learning_rate": 3.2572000727956186e-06,
|
| 2523 |
+
"loss": 0.0058,
|
| 2524 |
+
"step": 2930
|
| 2525 |
+
},
|
| 2526 |
+
{
|
| 2527 |
+
"epoch": 4.491978609625669,
|
| 2528 |
+
"grad_norm": 0.3453219532966614,
|
| 2529 |
+
"learning_rate": 3.070374727240466e-06,
|
| 2530 |
+
"loss": 0.0043,
|
| 2531 |
+
"step": 2940
|
| 2532 |
+
},
|
| 2533 |
+
{
|
| 2534 |
+
"epoch": 4.507257448433919,
|
| 2535 |
+
"grad_norm": 0.1276451051235199,
|
| 2536 |
+
"learning_rate": 2.8888970219373314e-06,
|
| 2537 |
+
"loss": 0.005,
|
| 2538 |
+
"step": 2950
|
| 2539 |
+
},
|
| 2540 |
+
{
|
| 2541 |
+
"epoch": 4.507257448433919,
|
| 2542 |
+
"eval_loss": 0.03592822700738907,
|
| 2543 |
+
"eval_runtime": 199.3782,
|
| 2544 |
+
"eval_samples_per_second": 5.838,
|
| 2545 |
+
"eval_steps_per_second": 5.838,
|
| 2546 |
+
"step": 2950
|
| 2547 |
+
},
|
| 2548 |
+
{
|
| 2549 |
+
"epoch": 4.522536287242169,
|
| 2550 |
+
"grad_norm": 0.09260442107915878,
|
| 2551 |
+
"learning_rate": 2.7127876363072736e-06,
|
| 2552 |
+
"loss": 0.0031,
|
| 2553 |
+
"step": 2960
|
| 2554 |
+
},
|
| 2555 |
+
{
|
| 2556 |
+
"epoch": 4.53781512605042,
|
| 2557 |
+
"grad_norm": 0.21995659172534943,
|
| 2558 |
+
"learning_rate": 2.54206663805025e-06,
|
| 2559 |
+
"loss": 0.0057,
|
| 2560 |
+
"step": 2970
|
| 2561 |
+
},
|
| 2562 |
+
{
|
| 2563 |
+
"epoch": 4.553093964858671,
|
| 2564 |
+
"grad_norm": 0.0280003622174263,
|
| 2565 |
+
"learning_rate": 2.3767534808584125e-06,
|
| 2566 |
+
"loss": 0.0026,
|
| 2567 |
+
"step": 2980
|
| 2568 |
+
},
|
| 2569 |
+
{
|
| 2570 |
+
"epoch": 4.5683728036669216,
|
| 2571 |
+
"grad_norm": 0.11262509971857071,
|
| 2572 |
+
"learning_rate": 2.2168670021993075e-06,
|
| 2573 |
+
"loss": 0.0078,
|
| 2574 |
+
"step": 2990
|
| 2575 |
+
},
|
| 2576 |
+
{
|
| 2577 |
+
"epoch": 4.583651642475171,
|
| 2578 |
+
"grad_norm": 0.32838335633277893,
|
| 2579 |
+
"learning_rate": 2.0624254211693894e-06,
|
| 2580 |
+
"loss": 0.0049,
|
| 2581 |
+
"step": 3000
|
| 2582 |
+
},
|
| 2583 |
+
{
|
| 2584 |
+
"epoch": 4.583651642475171,
|
| 2585 |
+
"eval_loss": 0.0363006666302681,
|
| 2586 |
+
"eval_runtime": 199.2158,
|
| 2587 |
+
"eval_samples_per_second": 5.843,
|
| 2588 |
+
"eval_steps_per_second": 5.843,
|
| 2589 |
+
"step": 3000
|
| 2590 |
+
},
|
| 2591 |
+
{
|
| 2592 |
+
"epoch": 4.598930481283422,
|
| 2593 |
+
"grad_norm": 0.17691144347190857,
|
| 2594 |
+
"learning_rate": 1.9134463364179177e-06,
|
| 2595 |
+
"loss": 0.007,
|
| 2596 |
+
"step": 3010
|
| 2597 |
+
},
|
| 2598 |
+
{
|
| 2599 |
+
"epoch": 4.614209320091673,
|
| 2600 |
+
"grad_norm": 0.4434875547885895,
|
| 2601 |
+
"learning_rate": 1.7699467241416024e-06,
|
| 2602 |
+
"loss": 0.0073,
|
| 2603 |
+
"step": 3020
|
| 2604 |
+
},
|
| 2605 |
+
{
|
| 2606 |
+
"epoch": 4.629488158899924,
|
| 2607 |
+
"grad_norm": 0.17472083866596222,
|
| 2608 |
+
"learning_rate": 1.6319429361501714e-06,
|
| 2609 |
+
"loss": 0.0045,
|
| 2610 |
+
"step": 3030
|
| 2611 |
+
},
|
| 2612 |
+
{
|
| 2613 |
+
"epoch": 4.6447669977081745,
|
| 2614 |
+
"grad_norm": 0.05675290897488594,
|
| 2615 |
+
"learning_rate": 1.4994506980030577e-06,
|
| 2616 |
+
"loss": 0.0019,
|
| 2617 |
+
"step": 3040
|
| 2618 |
+
},
|
| 2619 |
+
{
|
| 2620 |
+
"epoch": 4.660045836516424,
|
| 2621 |
+
"grad_norm": 0.3393559157848358,
|
| 2622 |
+
"learning_rate": 1.3724851072174917e-06,
|
| 2623 |
+
"loss": 0.0039,
|
| 2624 |
+
"step": 3050
|
| 2625 |
+
},
|
| 2626 |
+
{
|
| 2627 |
+
"epoch": 4.660045836516424,
|
| 2628 |
+
"eval_loss": 0.036286067217588425,
|
| 2629 |
+
"eval_runtime": 198.942,
|
| 2630 |
+
"eval_samples_per_second": 5.851,
|
| 2631 |
+
"eval_steps_per_second": 5.851,
|
| 2632 |
+
"step": 3050
|
| 2633 |
+
},
|
| 2634 |
+
{
|
| 2635 |
+
"epoch": 4.675324675324675,
|
| 2636 |
+
"grad_norm": 0.2996921241283417,
|
| 2637 |
+
"learning_rate": 1.251060631548112e-06,
|
| 2638 |
+
"loss": 0.0107,
|
| 2639 |
+
"step": 3060
|
| 2640 |
+
},
|
| 2641 |
+
{
|
| 2642 |
+
"epoch": 4.690603514132926,
|
| 2643 |
+
"grad_norm": 0.1846129596233368,
|
| 2644 |
+
"learning_rate": 1.135191107338368e-06,
|
| 2645 |
+
"loss": 0.0029,
|
| 2646 |
+
"step": 3070
|
| 2647 |
+
},
|
| 2648 |
+
{
|
| 2649 |
+
"epoch": 4.705882352941177,
|
| 2650 |
+
"grad_norm": 0.33350446820259094,
|
| 2651 |
+
"learning_rate": 1.0248897379438904e-06,
|
| 2652 |
+
"loss": 0.0054,
|
| 2653 |
+
"step": 3080
|
| 2654 |
+
},
|
| 2655 |
+
{
|
| 2656 |
+
"epoch": 4.721161191749427,
|
| 2657 |
+
"grad_norm": 0.18361401557922363,
|
| 2658 |
+
"learning_rate": 9.201690922279405e-07,
|
| 2659 |
+
"loss": 0.0052,
|
| 2660 |
+
"step": 3090
|
| 2661 |
+
},
|
| 2662 |
+
{
|
| 2663 |
+
"epoch": 4.736440030557677,
|
| 2664 |
+
"grad_norm": 0.1535758525133133,
|
| 2665 |
+
"learning_rate": 8.210411031291776e-07,
|
| 2666 |
+
"loss": 0.0062,
|
| 2667 |
+
"step": 3100
|
| 2668 |
+
},
|
| 2669 |
+
{
|
| 2670 |
+
"epoch": 4.736440030557677,
|
| 2671 |
+
"eval_loss": 0.03661744296550751,
|
| 2672 |
+
"eval_runtime": 199.1326,
|
| 2673 |
+
"eval_samples_per_second": 5.845,
|
| 2674 |
+
"eval_steps_per_second": 5.845,
|
| 2675 |
+
"step": 3100
|
| 2676 |
+
},
|
| 2677 |
+
{
|
| 2678 |
+
"epoch": 4.751718869365928,
|
| 2679 |
+
"grad_norm": 0.1135258898139,
|
| 2680 |
+
"learning_rate": 7.275170663019415e-07,
|
| 2681 |
+
"loss": 0.0061,
|
| 2682 |
+
"step": 3110
|
| 2683 |
+
},
|
| 2684 |
+
{
|
| 2685 |
+
"epoch": 4.766997708174179,
|
| 2686 |
+
"grad_norm": 0.3599923253059387,
|
| 2687 |
+
"learning_rate": 6.396076388290484e-07,
|
| 2688 |
+
"loss": 0.0043,
|
| 2689 |
+
"step": 3120
|
| 2690 |
+
},
|
| 2691 |
+
{
|
| 2692 |
+
"epoch": 4.7822765469824295,
|
| 2693 |
+
"grad_norm": 0.06559276580810547,
|
| 2694 |
+
"learning_rate": 5.573228380074736e-07,
|
| 2695 |
+
"loss": 0.0054,
|
| 2696 |
+
"step": 3130
|
| 2697 |
+
},
|
| 2698 |
+
{
|
| 2699 |
+
"epoch": 4.79755538579068,
|
| 2700 |
+
"grad_norm": 0.02168980799615383,
|
| 2701 |
+
"learning_rate": 4.806720402068477e-07,
|
| 2702 |
+
"loss": 0.0031,
|
| 2703 |
+
"step": 3140
|
| 2704 |
+
},
|
| 2705 |
+
{
|
| 2706 |
+
"epoch": 4.81283422459893,
|
| 2707 |
+
"grad_norm": 0.08103174716234207,
|
| 2708 |
+
"learning_rate": 4.0966397980100604e-07,
|
| 2709 |
+
"loss": 0.0054,
|
| 2710 |
+
"step": 3150
|
| 2711 |
+
},
|
| 2712 |
+
{
|
| 2713 |
+
"epoch": 4.81283422459893,
|
| 2714 |
+
"eval_loss": 0.03663839399814606,
|
| 2715 |
+
"eval_runtime": 198.8473,
|
| 2716 |
+
"eval_samples_per_second": 5.854,
|
| 2717 |
+
"eval_steps_per_second": 5.854,
|
| 2718 |
+
"step": 3150
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 4.828113063407181,
|
| 2722 |
+
"grad_norm": 0.16072829067707062,
|
| 2723 |
+
"learning_rate": 3.4430674817274575e-07,
|
| 2724 |
+
"loss": 0.0043,
|
| 2725 |
+
"step": 3160
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 4.843391902215432,
|
| 2729 |
+
"grad_norm": 0.05386335402727127,
|
| 2730 |
+
"learning_rate": 2.8460779279176896e-07,
|
| 2731 |
+
"loss": 0.0071,
|
| 2732 |
+
"step": 3170
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 4.8586707410236825,
|
| 2736 |
+
"grad_norm": 0.18377594649791718,
|
| 2737 |
+
"learning_rate": 2.3057391636606696e-07,
|
| 2738 |
+
"loss": 0.0035,
|
| 2739 |
+
"step": 3180
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 4.873949579831933,
|
| 2743 |
+
"grad_norm": 0.5214228630065918,
|
| 2744 |
+
"learning_rate": 1.8221127606674605e-07,
|
| 2745 |
+
"loss": 0.0078,
|
| 2746 |
+
"step": 3190
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 4.889228418640183,
|
| 2750 |
+
"grad_norm": 0.09072000533342361,
|
| 2751 |
+
"learning_rate": 1.3952538282639982e-07,
|
| 2752 |
+
"loss": 0.0041,
|
| 2753 |
+
"step": 3200
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 4.889228418640183,
|
| 2757 |
+
"eval_loss": 0.03660115599632263,
|
| 2758 |
+
"eval_runtime": 198.4598,
|
| 2759 |
+
"eval_samples_per_second": 5.865,
|
| 2760 |
+
"eval_steps_per_second": 5.865,
|
| 2761 |
+
"step": 3200
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 4.904507257448434,
|
| 2765 |
+
"grad_norm": 0.4262472093105316,
|
| 2766 |
+
"learning_rate": 1.025211007111615e-07,
|
| 2767 |
+
"loss": 0.0048,
|
| 2768 |
+
"step": 3210
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 4.919786096256685,
|
| 2772 |
+
"grad_norm": 0.13413435220718384,
|
| 2773 |
+
"learning_rate": 7.120264636643615e-08,
|
| 2774 |
+
"loss": 0.0023,
|
| 2775 |
+
"step": 3220
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 4.935064935064935,
|
| 2779 |
+
"grad_norm": 0.03055586665868759,
|
| 2780 |
+
"learning_rate": 4.5573588536407254e-08,
|
| 2781 |
+
"loss": 0.006,
|
| 2782 |
+
"step": 3230
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 4.950343773873186,
|
| 2786 |
+
"grad_norm": 0.36961618065834045,
|
| 2787 |
+
"learning_rate": 2.5636847657367623e-08,
|
| 2788 |
+
"loss": 0.0094,
|
| 2789 |
+
"step": 3240
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 4.965622612681436,
|
| 2793 |
+
"grad_norm": 0.05908333510160446,
|
| 2794 |
+
"learning_rate": 1.1394695524963306e-08,
|
| 2795 |
+
"loss": 0.0047,
|
| 2796 |
+
"step": 3250
|
| 2797 |
+
},
|
| 2798 |
+
{
|
| 2799 |
+
"epoch": 4.965622612681436,
|
| 2800 |
+
"eval_loss": 0.03658132627606392,
|
| 2801 |
+
"eval_runtime": 198.452,
|
| 2802 |
+
"eval_samples_per_second": 5.865,
|
| 2803 |
+
"eval_steps_per_second": 5.865,
|
| 2804 |
+
"step": 3250
|
| 2805 |
+
},
|
| 2806 |
+
{
|
| 2807 |
+
"epoch": 4.980901451489687,
|
| 2808 |
+
"grad_norm": 0.10072652250528336,
|
| 2809 |
+
"learning_rate": 2.8487550352951363e-09,
|
| 2810 |
+
"loss": 0.0064,
|
| 2811 |
+
"step": 3260
|
| 2812 |
+
},
|
| 2813 |
+
{
|
| 2814 |
+
"epoch": 4.9961802902979375,
|
| 2815 |
+
"grad_norm": 0.12432490289211273,
|
| 2816 |
+
"learning_rate": 0.0,
|
| 2817 |
+
"loss": 0.0078,
|
| 2818 |
+
"step": 3270
|
| 2819 |
+
},
|
| 2820 |
+
{
|
| 2821 |
+
"epoch": 4.9961802902979375,
|
| 2822 |
+
"step": 3270,
|
| 2823 |
+
"total_flos": 8.84620635703935e+17,
|
| 2824 |
+
"train_loss": 0.04931148957939596,
|
| 2825 |
+
"train_runtime": 42656.8883,
|
| 2826 |
+
"train_samples_per_second": 1.227,
|
| 2827 |
+
"train_steps_per_second": 0.077
|
| 2828 |
+
}
|
| 2829 |
+
],
|
| 2830 |
+
"logging_steps": 10,
|
| 2831 |
+
"max_steps": 3270,
|
| 2832 |
+
"num_input_tokens_seen": 0,
|
| 2833 |
+
"num_train_epochs": 5,
|
| 2834 |
+
"save_steps": 50,
|
| 2835 |
+
"stateful_callbacks": {
|
| 2836 |
+
"TrainerControl": {
|
| 2837 |
+
"args": {
|
| 2838 |
+
"should_epoch_stop": false,
|
| 2839 |
+
"should_evaluate": false,
|
| 2840 |
+
"should_log": false,
|
| 2841 |
+
"should_save": true,
|
| 2842 |
+
"should_training_stop": true
|
| 2843 |
+
},
|
| 2844 |
+
"attributes": {}
|
| 2845 |
+
}
|
| 2846 |
+
},
|
| 2847 |
+
"total_flos": 8.84620635703935e+17,
|
| 2848 |
+
"train_batch_size": 1,
|
| 2849 |
+
"trial_name": null,
|
| 2850 |
+
"trial_params": null
|
| 2851 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|