End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +1344 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: apache-2.0
|
|
| 4 |
base_model: Qwen/Qwen2.5-7B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: seed_math_multiple_samples_scale_up_scaredy_cat_all
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# seed_math_multiple_samples_scale_up_scaredy_cat_all
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 4 |
base_model: Qwen/Qwen2.5-7B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: seed_math_multiple_samples_scale_up_scaredy_cat_all
|
|
|
|
| 16 |
|
| 17 |
# seed_math_multiple_samples_scale_up_scaredy_cat_all
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/seed_math_multiple_samples_scale_up_scaredy_cat_all dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.976,
|
| 3 |
+
"total_flos": 174730160373760.0,
|
| 4 |
+
"train_loss": 0.7767894777559465,
|
| 5 |
+
"train_runtime": 9646.7578,
|
| 6 |
+
"train_samples_per_second": 1.866,
|
| 7 |
+
"train_steps_per_second": 0.019
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.976,
|
| 3 |
+
"total_flos": 174730160373760.0,
|
| 4 |
+
"train_loss": 0.7767894777559465,
|
| 5 |
+
"train_runtime": 9646.7578,
|
| 6 |
+
"train_samples_per_second": 1.866,
|
| 7 |
+
"train_steps_per_second": 0.019
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1344 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.976,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 186,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.016,
|
| 13 |
+
"grad_norm": 6.730227470397949,
|
| 14 |
+
"learning_rate": 5.263157894736843e-07,
|
| 15 |
+
"loss": 1.1523,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.032,
|
| 20 |
+
"grad_norm": 6.815516471862793,
|
| 21 |
+
"learning_rate": 1.0526315789473685e-06,
|
| 22 |
+
"loss": 1.0848,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.048,
|
| 27 |
+
"grad_norm": 6.904061794281006,
|
| 28 |
+
"learning_rate": 1.5789473684210526e-06,
|
| 29 |
+
"loss": 1.122,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.064,
|
| 34 |
+
"grad_norm": 6.942016124725342,
|
| 35 |
+
"learning_rate": 2.105263157894737e-06,
|
| 36 |
+
"loss": 1.156,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.08,
|
| 41 |
+
"grad_norm": 6.446863174438477,
|
| 42 |
+
"learning_rate": 2.631578947368421e-06,
|
| 43 |
+
"loss": 1.1508,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.096,
|
| 48 |
+
"grad_norm": 5.2992448806762695,
|
| 49 |
+
"learning_rate": 3.157894736842105e-06,
|
| 50 |
+
"loss": 1.0912,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.112,
|
| 55 |
+
"grad_norm": 3.2127764225006104,
|
| 56 |
+
"learning_rate": 3.6842105263157896e-06,
|
| 57 |
+
"loss": 1.0696,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.128,
|
| 62 |
+
"grad_norm": 3.006808280944824,
|
| 63 |
+
"learning_rate": 4.210526315789474e-06,
|
| 64 |
+
"loss": 0.9636,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.144,
|
| 69 |
+
"grad_norm": 2.6999926567077637,
|
| 70 |
+
"learning_rate": 4.736842105263158e-06,
|
| 71 |
+
"loss": 1.0451,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.16,
|
| 76 |
+
"grad_norm": 4.881057262420654,
|
| 77 |
+
"learning_rate": 5.263157894736842e-06,
|
| 78 |
+
"loss": 0.9963,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.176,
|
| 83 |
+
"grad_norm": 5.270591735839844,
|
| 84 |
+
"learning_rate": 5.789473684210527e-06,
|
| 85 |
+
"loss": 1.0467,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.192,
|
| 90 |
+
"grad_norm": 5.079095840454102,
|
| 91 |
+
"learning_rate": 6.31578947368421e-06,
|
| 92 |
+
"loss": 0.9811,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.208,
|
| 97 |
+
"grad_norm": 4.550872802734375,
|
| 98 |
+
"learning_rate": 6.842105263157896e-06,
|
| 99 |
+
"loss": 0.8948,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.224,
|
| 104 |
+
"grad_norm": 4.438713073730469,
|
| 105 |
+
"learning_rate": 7.368421052631579e-06,
|
| 106 |
+
"loss": 0.9817,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.24,
|
| 111 |
+
"grad_norm": 3.3074262142181396,
|
| 112 |
+
"learning_rate": 7.894736842105265e-06,
|
| 113 |
+
"loss": 0.9298,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.256,
|
| 118 |
+
"grad_norm": 2.315544366836548,
|
| 119 |
+
"learning_rate": 8.421052631578948e-06,
|
| 120 |
+
"loss": 0.8977,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.272,
|
| 125 |
+
"grad_norm": 2.3322393894195557,
|
| 126 |
+
"learning_rate": 8.947368421052632e-06,
|
| 127 |
+
"loss": 0.8743,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.288,
|
| 132 |
+
"grad_norm": 2.2325220108032227,
|
| 133 |
+
"learning_rate": 9.473684210526315e-06,
|
| 134 |
+
"loss": 0.8894,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.304,
|
| 139 |
+
"grad_norm": 1.84722900390625,
|
| 140 |
+
"learning_rate": 1e-05,
|
| 141 |
+
"loss": 0.8557,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.32,
|
| 146 |
+
"grad_norm": 1.3653030395507812,
|
| 147 |
+
"learning_rate": 9.999115304121459e-06,
|
| 148 |
+
"loss": 0.8225,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.336,
|
| 153 |
+
"grad_norm": 1.3245904445648193,
|
| 154 |
+
"learning_rate": 9.996461529560553e-06,
|
| 155 |
+
"loss": 0.8603,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.352,
|
| 160 |
+
"grad_norm": 1.3776931762695312,
|
| 161 |
+
"learning_rate": 9.992039615430648e-06,
|
| 162 |
+
"loss": 0.91,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.368,
|
| 167 |
+
"grad_norm": 0.9725991487503052,
|
| 168 |
+
"learning_rate": 9.985851126551428e-06,
|
| 169 |
+
"loss": 0.8801,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.384,
|
| 174 |
+
"grad_norm": 1.2167686223983765,
|
| 175 |
+
"learning_rate": 9.977898252895133e-06,
|
| 176 |
+
"loss": 0.8212,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.4,
|
| 181 |
+
"grad_norm": 1.0246224403381348,
|
| 182 |
+
"learning_rate": 9.968183808811586e-06,
|
| 183 |
+
"loss": 0.935,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.416,
|
| 188 |
+
"grad_norm": 0.6772653460502625,
|
| 189 |
+
"learning_rate": 9.95671123203224e-06,
|
| 190 |
+
"loss": 0.8314,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.432,
|
| 195 |
+
"grad_norm": 1.0011200904846191,
|
| 196 |
+
"learning_rate": 9.943484582453653e-06,
|
| 197 |
+
"loss": 0.8173,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.448,
|
| 202 |
+
"grad_norm": 0.843679666519165,
|
| 203 |
+
"learning_rate": 9.928508540700775e-06,
|
| 204 |
+
"loss": 0.815,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.464,
|
| 209 |
+
"grad_norm": 0.9654056429862976,
|
| 210 |
+
"learning_rate": 9.91178840647057e-06,
|
| 211 |
+
"loss": 0.8322,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.48,
|
| 216 |
+
"grad_norm": 0.745801568031311,
|
| 217 |
+
"learning_rate": 9.893330096656576e-06,
|
| 218 |
+
"loss": 0.7899,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.496,
|
| 223 |
+
"grad_norm": 0.7176544070243835,
|
| 224 |
+
"learning_rate": 9.873140143255035e-06,
|
| 225 |
+
"loss": 0.8492,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.512,
|
| 230 |
+
"grad_norm": 0.7864421010017395,
|
| 231 |
+
"learning_rate": 9.851225691053382e-06,
|
| 232 |
+
"loss": 0.7706,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.528,
|
| 237 |
+
"grad_norm": 0.5818405747413635,
|
| 238 |
+
"learning_rate": 9.827594495101824e-06,
|
| 239 |
+
"loss": 0.8266,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.544,
|
| 244 |
+
"grad_norm": 0.7277098298072815,
|
| 245 |
+
"learning_rate": 9.802254917969033e-06,
|
| 246 |
+
"loss": 0.8182,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.56,
|
| 251 |
+
"grad_norm": 0.6454283595085144,
|
| 252 |
+
"learning_rate": 9.775215926782788e-06,
|
| 253 |
+
"loss": 0.8141,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.576,
|
| 258 |
+
"grad_norm": 0.6249303817749023,
|
| 259 |
+
"learning_rate": 9.746487090056712e-06,
|
| 260 |
+
"loss": 0.8481,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.592,
|
| 265 |
+
"grad_norm": 0.7017203569412231,
|
| 266 |
+
"learning_rate": 9.71607857430419e-06,
|
| 267 |
+
"loss": 0.7968,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.608,
|
| 272 |
+
"grad_norm": 0.5962669849395752,
|
| 273 |
+
"learning_rate": 9.68400114044064e-06,
|
| 274 |
+
"loss": 0.802,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.624,
|
| 279 |
+
"grad_norm": 0.6717164516448975,
|
| 280 |
+
"learning_rate": 9.650266139975474e-06,
|
| 281 |
+
"loss": 0.7948,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.64,
|
| 286 |
+
"grad_norm": 0.6035948395729065,
|
| 287 |
+
"learning_rate": 9.614885510995047e-06,
|
| 288 |
+
"loss": 0.8319,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.656,
|
| 293 |
+
"grad_norm": 0.5939772725105286,
|
| 294 |
+
"learning_rate": 9.577871773938013e-06,
|
| 295 |
+
"loss": 0.7678,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.672,
|
| 300 |
+
"grad_norm": 0.4986055791378021,
|
| 301 |
+
"learning_rate": 9.539238027164618e-06,
|
| 302 |
+
"loss": 0.6981,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.688,
|
| 307 |
+
"grad_norm": 0.6004526615142822,
|
| 308 |
+
"learning_rate": 9.498997942321484e-06,
|
| 309 |
+
"loss": 0.821,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.704,
|
| 314 |
+
"grad_norm": 0.5085128545761108,
|
| 315 |
+
"learning_rate": 9.457165759503492e-06,
|
| 316 |
+
"loss": 0.793,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.72,
|
| 321 |
+
"grad_norm": 0.5946983098983765,
|
| 322 |
+
"learning_rate": 9.413756282214538e-06,
|
| 323 |
+
"loss": 0.8268,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.736,
|
| 328 |
+
"grad_norm": 0.5231062173843384,
|
| 329 |
+
"learning_rate": 9.368784872128877e-06,
|
| 330 |
+
"loss": 0.787,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.752,
|
| 335 |
+
"grad_norm": 0.5451761484146118,
|
| 336 |
+
"learning_rate": 9.322267443654974e-06,
|
| 337 |
+
"loss": 0.8682,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.768,
|
| 342 |
+
"grad_norm": 0.5007831454277039,
|
| 343 |
+
"learning_rate": 9.274220458303727e-06,
|
| 344 |
+
"loss": 0.727,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.784,
|
| 349 |
+
"grad_norm": 0.49679020047187805,
|
| 350 |
+
"learning_rate": 9.224660918863104e-06,
|
| 351 |
+
"loss": 0.8356,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.8,
|
| 356 |
+
"grad_norm": 0.5376884341239929,
|
| 357 |
+
"learning_rate": 9.173606363381218e-06,
|
| 358 |
+
"loss": 0.7961,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.816,
|
| 363 |
+
"grad_norm": 0.512400209903717,
|
| 364 |
+
"learning_rate": 9.121074858959997e-06,
|
| 365 |
+
"loss": 0.7562,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.832,
|
| 370 |
+
"grad_norm": 0.5244386792182922,
|
| 371 |
+
"learning_rate": 9.067084995361623e-06,
|
| 372 |
+
"loss": 0.7479,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.848,
|
| 377 |
+
"grad_norm": 0.6458032727241516,
|
| 378 |
+
"learning_rate": 9.011655878430018e-06,
|
| 379 |
+
"loss": 0.8041,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.864,
|
| 384 |
+
"grad_norm": 0.5464228391647339,
|
| 385 |
+
"learning_rate": 8.954807123329703e-06,
|
| 386 |
+
"loss": 0.7755,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.88,
|
| 391 |
+
"grad_norm": 0.4465423822402954,
|
| 392 |
+
"learning_rate": 8.896558847604414e-06,
|
| 393 |
+
"loss": 0.7301,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.896,
|
| 398 |
+
"grad_norm": 0.5520794987678528,
|
| 399 |
+
"learning_rate": 8.836931664057935e-06,
|
| 400 |
+
"loss": 0.8006,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.912,
|
| 405 |
+
"grad_norm": 0.5246075987815857,
|
| 406 |
+
"learning_rate": 8.775946673459682e-06,
|
| 407 |
+
"loss": 0.7755,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.928,
|
| 412 |
+
"grad_norm": 0.5505017638206482,
|
| 413 |
+
"learning_rate": 8.713625457077585e-06,
|
| 414 |
+
"loss": 0.7278,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.944,
|
| 419 |
+
"grad_norm": 0.44412118196487427,
|
| 420 |
+
"learning_rate": 8.64999006904096e-06,
|
| 421 |
+
"loss": 0.7849,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.96,
|
| 426 |
+
"grad_norm": 0.6552417874336243,
|
| 427 |
+
"learning_rate": 8.585063028536015e-06,
|
| 428 |
+
"loss": 0.7567,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.976,
|
| 433 |
+
"grad_norm": 0.5109571814537048,
|
| 434 |
+
"learning_rate": 8.518867311836808e-06,
|
| 435 |
+
"loss": 0.8015,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.992,
|
| 440 |
+
"grad_norm": 0.50904780626297,
|
| 441 |
+
"learning_rate": 8.451426344174433e-06,
|
| 442 |
+
"loss": 0.8244,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.008,
|
| 447 |
+
"grad_norm": 0.7810150980949402,
|
| 448 |
+
"learning_rate": 8.382763991447344e-06,
|
| 449 |
+
"loss": 1.1297,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.024,
|
| 454 |
+
"grad_norm": 0.7078925371170044,
|
| 455 |
+
"learning_rate": 8.312904551775731e-06,
|
| 456 |
+
"loss": 0.6906,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 1.04,
|
| 461 |
+
"grad_norm": 0.5447573661804199,
|
| 462 |
+
"learning_rate": 8.241872746902934e-06,
|
| 463 |
+
"loss": 0.7177,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 1.056,
|
| 468 |
+
"grad_norm": 0.6897069215774536,
|
| 469 |
+
"learning_rate": 8.16969371344696e-06,
|
| 470 |
+
"loss": 0.7934,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.072,
|
| 475 |
+
"grad_norm": 0.5533248782157898,
|
| 476 |
+
"learning_rate": 8.096392994005177e-06,
|
| 477 |
+
"loss": 0.7176,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 1.088,
|
| 482 |
+
"grad_norm": 0.46568524837493896,
|
| 483 |
+
"learning_rate": 8.021996528115335e-06,
|
| 484 |
+
"loss": 0.7277,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 1.104,
|
| 489 |
+
"grad_norm": 0.6250821352005005,
|
| 490 |
+
"learning_rate": 7.946530643076138e-06,
|
| 491 |
+
"loss": 0.7373,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 1.12,
|
| 496 |
+
"grad_norm": 0.5421143770217896,
|
| 497 |
+
"learning_rate": 7.870022044630569e-06,
|
| 498 |
+
"loss": 0.7057,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 1.1360000000000001,
|
| 503 |
+
"grad_norm": 0.6077035665512085,
|
| 504 |
+
"learning_rate": 7.792497807515317e-06,
|
| 505 |
+
"loss": 0.7334,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.152,
|
| 510 |
+
"grad_norm": 0.6327843070030212,
|
| 511 |
+
"learning_rate": 7.713985365879607e-06,
|
| 512 |
+
"loss": 0.7679,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.168,
|
| 517 |
+
"grad_norm": 0.49813559651374817,
|
| 518 |
+
"learning_rate": 7.63451250357685e-06,
|
| 519 |
+
"loss": 0.7183,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 1.184,
|
| 524 |
+
"grad_norm": 0.6324042081832886,
|
| 525 |
+
"learning_rate": 7.55410734433254e-06,
|
| 526 |
+
"loss": 0.7163,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.2,
|
| 531 |
+
"grad_norm": 0.5511308908462524,
|
| 532 |
+
"learning_rate": 7.472798341791877e-06,
|
| 533 |
+
"loss": 0.8224,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.216,
|
| 538 |
+
"grad_norm": 0.5071510672569275,
|
| 539 |
+
"learning_rate": 7.390614269450633e-06,
|
| 540 |
+
"loss": 0.748,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.232,
|
| 545 |
+
"grad_norm": 0.6148613691329956,
|
| 546 |
+
"learning_rate": 7.3075842104728445e-06,
|
| 547 |
+
"loss": 0.798,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.248,
|
| 552 |
+
"grad_norm": 0.519557535648346,
|
| 553 |
+
"learning_rate": 7.223737547398898e-06,
|
| 554 |
+
"loss": 0.7786,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.264,
|
| 559 |
+
"grad_norm": 0.48721715807914734,
|
| 560 |
+
"learning_rate": 7.139103951747694e-06,
|
| 561 |
+
"loss": 0.7259,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.28,
|
| 566 |
+
"grad_norm": 0.5514334440231323,
|
| 567 |
+
"learning_rate": 7.053713373516538e-06,
|
| 568 |
+
"loss": 0.7555,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.296,
|
| 573 |
+
"grad_norm": 0.48266488313674927,
|
| 574 |
+
"learning_rate": 6.9675960305824785e-06,
|
| 575 |
+
"loss": 0.7324,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.312,
|
| 580 |
+
"grad_norm": 0.5061817169189453,
|
| 581 |
+
"learning_rate": 6.880782398008862e-06,
|
| 582 |
+
"loss": 0.6775,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 1.328,
|
| 587 |
+
"grad_norm": 0.6087468862533569,
|
| 588 |
+
"learning_rate": 6.7933031972608644e-06,
|
| 589 |
+
"loss": 0.8298,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.3439999999999999,
|
| 594 |
+
"grad_norm": 0.39912983775138855,
|
| 595 |
+
"learning_rate": 6.70518938533383e-06,
|
| 596 |
+
"loss": 0.6214,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.3599999999999999,
|
| 601 |
+
"grad_norm": 0.707404613494873,
|
| 602 |
+
"learning_rate": 6.61647214379826e-06,
|
| 603 |
+
"loss": 0.8824,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.376,
|
| 608 |
+
"grad_norm": 0.49149787425994873,
|
| 609 |
+
"learning_rate": 6.527182867765333e-06,
|
| 610 |
+
"loss": 0.7861,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.392,
|
| 615 |
+
"grad_norm": 0.3921094834804535,
|
| 616 |
+
"learning_rate": 6.437353154776848e-06,
|
| 617 |
+
"loss": 0.5916,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.408,
|
| 622 |
+
"grad_norm": 0.6061850786209106,
|
| 623 |
+
"learning_rate": 6.3470147936235485e-06,
|
| 624 |
+
"loss": 0.7394,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.424,
|
| 629 |
+
"grad_norm": 0.5723496079444885,
|
| 630 |
+
"learning_rate": 6.256199753095745e-06,
|
| 631 |
+
"loss": 0.7603,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.44,
|
| 636 |
+
"grad_norm": 0.5121960639953613,
|
| 637 |
+
"learning_rate": 6.164940170670266e-06,
|
| 638 |
+
"loss": 0.783,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.456,
|
| 643 |
+
"grad_norm": 0.48070028424263,
|
| 644 |
+
"learning_rate": 6.073268341137694e-06,
|
| 645 |
+
"loss": 0.6773,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.472,
|
| 650 |
+
"grad_norm": 0.5026914477348328,
|
| 651 |
+
"learning_rate": 5.98121670517393e-06,
|
| 652 |
+
"loss": 0.6969,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.488,
|
| 657 |
+
"grad_norm": 0.6264543533325195,
|
| 658 |
+
"learning_rate": 5.8888178378601565e-06,
|
| 659 |
+
"loss": 0.7354,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.504,
|
| 664 |
+
"grad_norm": 0.5623913407325745,
|
| 665 |
+
"learning_rate": 5.796104437155213e-06,
|
| 666 |
+
"loss": 0.6885,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.52,
|
| 671 |
+
"grad_norm": 0.5678471326828003,
|
| 672 |
+
"learning_rate": 5.703109312324493e-06,
|
| 673 |
+
"loss": 0.791,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.536,
|
| 678 |
+
"grad_norm": 0.5602116584777832,
|
| 679 |
+
"learning_rate": 5.609865372329461e-06,
|
| 680 |
+
"loss": 0.8243,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.552,
|
| 685 |
+
"grad_norm": 0.5252257585525513,
|
| 686 |
+
"learning_rate": 5.516405614181883e-06,
|
| 687 |
+
"loss": 0.7718,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.568,
|
| 692 |
+
"grad_norm": 0.5818773508071899,
|
| 693 |
+
"learning_rate": 5.4227631112668955e-06,
|
| 694 |
+
"loss": 0.6252,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 1.584,
|
| 699 |
+
"grad_norm": 0.5256779193878174,
|
| 700 |
+
"learning_rate": 5.328971001639054e-06,
|
| 701 |
+
"loss": 0.7551,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.6,
|
| 706 |
+
"grad_norm": 0.473935604095459,
|
| 707 |
+
"learning_rate": 5.235062476295488e-06,
|
| 708 |
+
"loss": 0.8162,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.616,
|
| 713 |
+
"grad_norm": 0.4878559708595276,
|
| 714 |
+
"learning_rate": 5.141070767430331e-06,
|
| 715 |
+
"loss": 0.6622,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 1.6320000000000001,
|
| 720 |
+
"grad_norm": 0.5742131471633911,
|
| 721 |
+
"learning_rate": 5.047029136674563e-06,
|
| 722 |
+
"loss": 0.8376,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.6480000000000001,
|
| 727 |
+
"grad_norm": 0.4893825054168701,
|
| 728 |
+
"learning_rate": 4.95297086332544e-06,
|
| 729 |
+
"loss": 0.7099,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.6640000000000001,
|
| 734 |
+
"grad_norm": 0.4951648712158203,
|
| 735 |
+
"learning_rate": 4.858929232569671e-06,
|
| 736 |
+
"loss": 0.8082,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.6800000000000002,
|
| 741 |
+
"grad_norm": 0.45592811703681946,
|
| 742 |
+
"learning_rate": 4.7649375237045135e-06,
|
| 743 |
+
"loss": 0.7456,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.696,
|
| 748 |
+
"grad_norm": 0.51396244764328,
|
| 749 |
+
"learning_rate": 4.671028998360947e-06,
|
| 750 |
+
"loss": 0.7856,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.712,
|
| 755 |
+
"grad_norm": 0.4982396066188812,
|
| 756 |
+
"learning_rate": 4.5772368887331044e-06,
|
| 757 |
+
"loss": 0.7818,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.728,
|
| 762 |
+
"grad_norm": 0.4770466089248657,
|
| 763 |
+
"learning_rate": 4.483594385818119e-06,
|
| 764 |
+
"loss": 0.7014,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.744,
|
| 769 |
+
"grad_norm": 0.4669516086578369,
|
| 770 |
+
"learning_rate": 4.39013462767054e-06,
|
| 771 |
+
"loss": 0.702,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 1.76,
|
| 776 |
+
"grad_norm": 0.4871979355812073,
|
| 777 |
+
"learning_rate": 4.29689068767551e-06,
|
| 778 |
+
"loss": 0.6881,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.776,
|
| 783 |
+
"grad_norm": 0.5842928886413574,
|
| 784 |
+
"learning_rate": 4.203895562844789e-06,
|
| 785 |
+
"loss": 0.8086,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.792,
|
| 790 |
+
"grad_norm": 0.5212162733078003,
|
| 791 |
+
"learning_rate": 4.111182162139844e-06,
|
| 792 |
+
"loss": 0.8712,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 1.808,
|
| 797 |
+
"grad_norm": 0.5059789419174194,
|
| 798 |
+
"learning_rate": 4.018783294826071e-06,
|
| 799 |
+
"loss": 0.6912,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 1.8239999999999998,
|
| 804 |
+
"grad_norm": 0.5188186168670654,
|
| 805 |
+
"learning_rate": 3.926731658862307e-06,
|
| 806 |
+
"loss": 0.8044,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.8399999999999999,
|
| 811 |
+
"grad_norm": 0.4948703646659851,
|
| 812 |
+
"learning_rate": 3.8350598293297345e-06,
|
| 813 |
+
"loss": 0.6886,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 1.8559999999999999,
|
| 818 |
+
"grad_norm": 0.43077465891838074,
|
| 819 |
+
"learning_rate": 3.7438002469042567e-06,
|
| 820 |
+
"loss": 0.6942,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 1.8719999999999999,
|
| 825 |
+
"grad_norm": 0.4874947965145111,
|
| 826 |
+
"learning_rate": 3.652985206376455e-06,
|
| 827 |
+
"loss": 0.7744,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 1.888,
|
| 832 |
+
"grad_norm": 0.4097570478916168,
|
| 833 |
+
"learning_rate": 3.5626468452231534e-06,
|
| 834 |
+
"loss": 0.7281,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 1.904,
|
| 839 |
+
"grad_norm": 0.45681607723236084,
|
| 840 |
+
"learning_rate": 3.472817132234669e-06,
|
| 841 |
+
"loss": 0.7454,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 1.92,
|
| 846 |
+
"grad_norm": 0.4318609833717346,
|
| 847 |
+
"learning_rate": 3.3835278562017405e-06,
|
| 848 |
+
"loss": 0.8402,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.936,
|
| 853 |
+
"grad_norm": 0.4432387053966522,
|
| 854 |
+
"learning_rate": 3.29481061466617e-06,
|
| 855 |
+
"loss": 0.7245,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 1.952,
|
| 860 |
+
"grad_norm": 0.43325987458229065,
|
| 861 |
+
"learning_rate": 3.2066968027391377e-06,
|
| 862 |
+
"loss": 0.7821,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 1.968,
|
| 867 |
+
"grad_norm": 0.41319578886032104,
|
| 868 |
+
"learning_rate": 3.119217601991139e-06,
|
| 869 |
+
"loss": 0.7493,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 1.984,
|
| 874 |
+
"grad_norm": 0.4166939854621887,
|
| 875 |
+
"learning_rate": 3.032403969417523e-06,
|
| 876 |
+
"loss": 0.6969,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 2.0,
|
| 881 |
+
"grad_norm": 0.6539634466171265,
|
| 882 |
+
"learning_rate": 2.946286626483463e-06,
|
| 883 |
+
"loss": 0.9684,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 2.016,
|
| 888 |
+
"grad_norm": 0.49411338567733765,
|
| 889 |
+
"learning_rate": 2.8608960482523058e-06,
|
| 890 |
+
"loss": 0.7107,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 2.032,
|
| 895 |
+
"grad_norm": 0.44227027893066406,
|
| 896 |
+
"learning_rate": 2.776262452601104e-06,
|
| 897 |
+
"loss": 0.7462,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 2.048,
|
| 902 |
+
"grad_norm": 0.4018813371658325,
|
| 903 |
+
"learning_rate": 2.6924157895271563e-06,
|
| 904 |
+
"loss": 0.6588,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 2.064,
|
| 909 |
+
"grad_norm": 0.435094952583313,
|
| 910 |
+
"learning_rate": 2.6093857305493666e-06,
|
| 911 |
+
"loss": 0.7366,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 2.08,
|
| 916 |
+
"grad_norm": 0.5179253816604614,
|
| 917 |
+
"learning_rate": 2.5272016582081236e-06,
|
| 918 |
+
"loss": 0.634,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 2.096,
|
| 923 |
+
"grad_norm": 0.4748607575893402,
|
| 924 |
+
"learning_rate": 2.445892655667462e-06,
|
| 925 |
+
"loss": 0.7273,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 2.112,
|
| 930 |
+
"grad_norm": 0.40352708101272583,
|
| 931 |
+
"learning_rate": 2.365487496423152e-06,
|
| 932 |
+
"loss": 0.7158,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 2.128,
|
| 937 |
+
"grad_norm": 0.4192029535770416,
|
| 938 |
+
"learning_rate": 2.2860146341203936e-06,
|
| 939 |
+
"loss": 0.674,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 2.144,
|
| 944 |
+
"grad_norm": 0.45303046703338623,
|
| 945 |
+
"learning_rate": 2.207502192484685e-06,
|
| 946 |
+
"loss": 0.7368,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 2.16,
|
| 951 |
+
"grad_norm": 0.4972662329673767,
|
| 952 |
+
"learning_rate": 2.1299779553694323e-06,
|
| 953 |
+
"loss": 0.7117,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 2.176,
|
| 958 |
+
"grad_norm": 0.45653873682022095,
|
| 959 |
+
"learning_rate": 2.053469356923865e-06,
|
| 960 |
+
"loss": 0.6312,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 2.192,
|
| 965 |
+
"grad_norm": 0.4445890188217163,
|
| 966 |
+
"learning_rate": 1.9780034718846653e-06,
|
| 967 |
+
"loss": 0.7096,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 2.208,
|
| 972 |
+
"grad_norm": 0.49326151609420776,
|
| 973 |
+
"learning_rate": 1.9036070059948253e-06,
|
| 974 |
+
"loss": 0.6783,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 2.224,
|
| 979 |
+
"grad_norm": 0.43406474590301514,
|
| 980 |
+
"learning_rate": 1.8303062865530407e-06,
|
| 981 |
+
"loss": 0.7526,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 2.24,
|
| 986 |
+
"grad_norm": 0.4142819046974182,
|
| 987 |
+
"learning_rate": 1.7581272530970666e-06,
|
| 988 |
+
"loss": 0.7312,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 2.2560000000000002,
|
| 993 |
+
"grad_norm": 0.4054710566997528,
|
| 994 |
+
"learning_rate": 1.6870954482242707e-06,
|
| 995 |
+
"loss": 0.6695,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 2.2720000000000002,
|
| 1000 |
+
"grad_norm": 0.42124947905540466,
|
| 1001 |
+
"learning_rate": 1.6172360085526567e-06,
|
| 1002 |
+
"loss": 0.6941,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 2.288,
|
| 1007 |
+
"grad_norm": 0.42006680369377136,
|
| 1008 |
+
"learning_rate": 1.54857365582557e-06,
|
| 1009 |
+
"loss": 0.6693,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 2.304,
|
| 1014 |
+
"grad_norm": 0.39132973551750183,
|
| 1015 |
+
"learning_rate": 1.4811326881631937e-06,
|
| 1016 |
+
"loss": 0.6711,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 2.32,
|
| 1021 |
+
"grad_norm": 0.3638474941253662,
|
| 1022 |
+
"learning_rate": 1.4149369714639856e-06,
|
| 1023 |
+
"loss": 0.7054,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 2.336,
|
| 1028 |
+
"grad_norm": 0.39572256803512573,
|
| 1029 |
+
"learning_rate": 1.3500099309590397e-06,
|
| 1030 |
+
"loss": 0.625,
|
| 1031 |
+
"step": 146
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 2.352,
|
| 1035 |
+
"grad_norm": 0.4146718680858612,
|
| 1036 |
+
"learning_rate": 1.2863745429224145e-06,
|
| 1037 |
+
"loss": 0.6545,
|
| 1038 |
+
"step": 147
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 2.368,
|
| 1042 |
+
"grad_norm": 0.42824339866638184,
|
| 1043 |
+
"learning_rate": 1.22405332654032e-06,
|
| 1044 |
+
"loss": 0.7246,
|
| 1045 |
+
"step": 148
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 2.384,
|
| 1049 |
+
"grad_norm": 0.3978138566017151,
|
| 1050 |
+
"learning_rate": 1.1630683359420653e-06,
|
| 1051 |
+
"loss": 0.7389,
|
| 1052 |
+
"step": 149
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 2.4,
|
| 1056 |
+
"grad_norm": 0.35629239678382874,
|
| 1057 |
+
"learning_rate": 1.103441152395588e-06,
|
| 1058 |
+
"loss": 0.6475,
|
| 1059 |
+
"step": 150
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 2.416,
|
| 1063 |
+
"grad_norm": 0.36607304215431213,
|
| 1064 |
+
"learning_rate": 1.045192876670298e-06,
|
| 1065 |
+
"loss": 0.7146,
|
| 1066 |
+
"step": 151
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 2.432,
|
| 1070 |
+
"grad_norm": 0.37903138995170593,
|
| 1071 |
+
"learning_rate": 9.883441215699824e-07,
|
| 1072 |
+
"loss": 0.724,
|
| 1073 |
+
"step": 152
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 2.448,
|
| 1077 |
+
"grad_norm": 0.4119018316268921,
|
| 1078 |
+
"learning_rate": 9.329150046383773e-07,
|
| 1079 |
+
"loss": 0.6687,
|
| 1080 |
+
"step": 153
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 2.464,
|
| 1084 |
+
"grad_norm": 0.3879659175872803,
|
| 1085 |
+
"learning_rate": 8.789251410400024e-07,
|
| 1086 |
+
"loss": 0.7853,
|
| 1087 |
+
"step": 154
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 2.48,
|
| 1091 |
+
"grad_norm": 0.410463809967041,
|
| 1092 |
+
"learning_rate": 8.263936366187825e-07,
|
| 1093 |
+
"loss": 0.7102,
|
| 1094 |
+
"step": 155
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 2.496,
|
| 1098 |
+
"grad_norm": 0.4049909710884094,
|
| 1099 |
+
"learning_rate": 7.753390811368972e-07,
|
| 1100 |
+
"loss": 0.7436,
|
| 1101 |
+
"step": 156
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 2.512,
|
| 1105 |
+
"grad_norm": 0.36085453629493713,
|
| 1106 |
+
"learning_rate": 7.257795416962754e-07,
|
| 1107 |
+
"loss": 0.684,
|
| 1108 |
+
"step": 157
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 2.528,
|
| 1112 |
+
"grad_norm": 0.43106627464294434,
|
| 1113 |
+
"learning_rate": 6.777325563450282e-07,
|
| 1114 |
+
"loss": 0.6822,
|
| 1115 |
+
"step": 158
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 2.544,
|
| 1119 |
+
"grad_norm": 0.3700436055660248,
|
| 1120 |
+
"learning_rate": 6.312151278711237e-07,
|
| 1121 |
+
"loss": 0.706,
|
| 1122 |
+
"step": 159
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 2.56,
|
| 1126 |
+
"grad_norm": 0.38907262682914734,
|
| 1127 |
+
"learning_rate": 5.862437177854629e-07,
|
| 1128 |
+
"loss": 0.7186,
|
| 1129 |
+
"step": 160
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 2.576,
|
| 1133 |
+
"grad_norm": 0.3614966869354248,
|
| 1134 |
+
"learning_rate": 5.428342404965076e-07,
|
| 1135 |
+
"loss": 0.7398,
|
| 1136 |
+
"step": 161
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 2.592,
|
| 1140 |
+
"grad_norm": 0.3803021311759949,
|
| 1141 |
+
"learning_rate": 5.010020576785174e-07,
|
| 1142 |
+
"loss": 0.6833,
|
| 1143 |
+
"step": 162
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 2.608,
|
| 1147 |
+
"grad_norm": 0.38011065125465393,
|
| 1148 |
+
"learning_rate": 4.607619728353818e-07,
|
| 1149 |
+
"loss": 0.6949,
|
| 1150 |
+
"step": 163
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 2.624,
|
| 1154 |
+
"grad_norm": 0.3799115717411041,
|
| 1155 |
+
"learning_rate": 4.221282260619891e-07,
|
| 1156 |
+
"loss": 0.6992,
|
| 1157 |
+
"step": 164
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 2.64,
|
| 1161 |
+
"grad_norm": 0.38610032200813293,
|
| 1162 |
+
"learning_rate": 3.851144890049535e-07,
|
| 1163 |
+
"loss": 0.7146,
|
| 1164 |
+
"step": 165
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 2.656,
|
| 1168 |
+
"grad_norm": 0.39044347405433655,
|
| 1169 |
+
"learning_rate": 3.497338600245254e-07,
|
| 1170 |
+
"loss": 0.6423,
|
| 1171 |
+
"step": 166
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 2.672,
|
| 1175 |
+
"grad_norm": 0.3409990668296814,
|
| 1176 |
+
"learning_rate": 3.159988595593616e-07,
|
| 1177 |
+
"loss": 0.6919,
|
| 1178 |
+
"step": 167
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 2.6879999999999997,
|
| 1182 |
+
"grad_norm": 0.37552517652511597,
|
| 1183 |
+
"learning_rate": 2.839214256958106e-07,
|
| 1184 |
+
"loss": 0.7524,
|
| 1185 |
+
"step": 168
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 2.7039999999999997,
|
| 1189 |
+
"grad_norm": 0.4066920280456543,
|
| 1190 |
+
"learning_rate": 2.5351290994328703e-07,
|
| 1191 |
+
"loss": 0.7457,
|
| 1192 |
+
"step": 169
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 2.7199999999999998,
|
| 1196 |
+
"grad_norm": 0.39518383145332336,
|
| 1197 |
+
"learning_rate": 2.2478407321721295e-07,
|
| 1198 |
+
"loss": 0.747,
|
| 1199 |
+
"step": 170
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 2.7359999999999998,
|
| 1203 |
+
"grad_norm": 0.3754367530345917,
|
| 1204 |
+
"learning_rate": 1.9774508203096843e-07,
|
| 1205 |
+
"loss": 0.7235,
|
| 1206 |
+
"step": 171
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 2.752,
|
| 1210 |
+
"grad_norm": 0.338599294424057,
|
| 1211 |
+
"learning_rate": 1.7240550489817652e-07,
|
| 1212 |
+
"loss": 0.6887,
|
| 1213 |
+
"step": 172
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 2.768,
|
| 1217 |
+
"grad_norm": 0.37499845027923584,
|
| 1218 |
+
"learning_rate": 1.4877430894662037e-07,
|
| 1219 |
+
"loss": 0.7928,
|
| 1220 |
+
"step": 173
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 2.784,
|
| 1224 |
+
"grad_norm": 0.3994706869125366,
|
| 1225 |
+
"learning_rate": 1.268598567449647e-07,
|
| 1226 |
+
"loss": 0.7622,
|
| 1227 |
+
"step": 174
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 2.8,
|
| 1231 |
+
"grad_norm": 0.3536545932292938,
|
| 1232 |
+
"learning_rate": 1.0666990334342708e-07,
|
| 1233 |
+
"loss": 0.716,
|
| 1234 |
+
"step": 175
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 2.816,
|
| 1238 |
+
"grad_norm": 0.3440304100513458,
|
| 1239 |
+
"learning_rate": 8.821159352943142e-08,
|
| 1240 |
+
"loss": 0.6963,
|
| 1241 |
+
"step": 176
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 2.832,
|
| 1245 |
+
"grad_norm": 0.37041378021240234,
|
| 1246 |
+
"learning_rate": 7.149145929922607e-08,
|
| 1247 |
+
"loss": 0.6921,
|
| 1248 |
+
"step": 177
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 2.848,
|
| 1252 |
+
"grad_norm": 0.3808996379375458,
|
| 1253 |
+
"learning_rate": 5.651541754634726e-08,
|
| 1254 |
+
"loss": 0.7491,
|
| 1255 |
+
"step": 178
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 2.864,
|
| 1259 |
+
"grad_norm": 0.3579948842525482,
|
| 1260 |
+
"learning_rate": 4.328876796776071e-08,
|
| 1261 |
+
"loss": 0.6694,
|
| 1262 |
+
"step": 179
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 2.88,
|
| 1266 |
+
"grad_norm": 0.3801659047603607,
|
| 1267 |
+
"learning_rate": 3.181619118841517e-08,
|
| 1268 |
+
"loss": 0.7126,
|
| 1269 |
+
"step": 180
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 2.896,
|
| 1273 |
+
"grad_norm": 0.36324548721313477,
|
| 1274 |
+
"learning_rate": 2.210174710486679e-08,
|
| 1275 |
+
"loss": 0.6724,
|
| 1276 |
+
"step": 181
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 2.912,
|
| 1280 |
+
"grad_norm": 0.37609073519706726,
|
| 1281 |
+
"learning_rate": 1.4148873448573408e-08,
|
| 1282 |
+
"loss": 0.7101,
|
| 1283 |
+
"step": 182
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 2.928,
|
| 1287 |
+
"grad_norm": 0.3577752113342285,
|
| 1288 |
+
"learning_rate": 7.96038456935322e-09,
|
| 1289 |
+
"loss": 0.7491,
|
| 1290 |
+
"step": 183
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 2.944,
|
| 1294 |
+
"grad_norm": 0.33213570713996887,
|
| 1295 |
+
"learning_rate": 3.538470439448105e-09,
|
| 1296 |
+
"loss": 0.7011,
|
| 1297 |
+
"step": 184
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 2.96,
|
| 1301 |
+
"grad_norm": 0.38149145245552063,
|
| 1302 |
+
"learning_rate": 8.846958785418969e-10,
|
| 1303 |
+
"loss": 0.7158,
|
| 1304 |
+
"step": 185
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 2.976,
|
| 1308 |
+
"grad_norm": 0.3634936511516571,
|
| 1309 |
+
"learning_rate": 0.0,
|
| 1310 |
+
"loss": 0.7134,
|
| 1311 |
+
"step": 186
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 2.976,
|
| 1315 |
+
"step": 186,
|
| 1316 |
+
"total_flos": 174730160373760.0,
|
| 1317 |
+
"train_loss": 0.7767894777559465,
|
| 1318 |
+
"train_runtime": 9646.7578,
|
| 1319 |
+
"train_samples_per_second": 1.866,
|
| 1320 |
+
"train_steps_per_second": 0.019
|
| 1321 |
+
}
|
| 1322 |
+
],
|
| 1323 |
+
"logging_steps": 1.0,
|
| 1324 |
+
"max_steps": 186,
|
| 1325 |
+
"num_input_tokens_seen": 0,
|
| 1326 |
+
"num_train_epochs": 3,
|
| 1327 |
+
"save_steps": 500,
|
| 1328 |
+
"stateful_callbacks": {
|
| 1329 |
+
"TrainerControl": {
|
| 1330 |
+
"args": {
|
| 1331 |
+
"should_epoch_stop": false,
|
| 1332 |
+
"should_evaluate": false,
|
| 1333 |
+
"should_log": false,
|
| 1334 |
+
"should_save": true,
|
| 1335 |
+
"should_training_stop": true
|
| 1336 |
+
},
|
| 1337 |
+
"attributes": {}
|
| 1338 |
+
}
|
| 1339 |
+
},
|
| 1340 |
+
"total_flos": 174730160373760.0,
|
| 1341 |
+
"train_batch_size": 1,
|
| 1342 |
+
"trial_name": null,
|
| 1343 |
+
"trial_params": null
|
| 1344 |
+
}
|
training_loss.png
ADDED
|