End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +2226 -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: mix_base_code_math_t_0
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# mix_base_code_math_t_0
|
| 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: mix_base_code_math_t_0
|
|
|
|
| 16 |
|
| 17 |
# mix_base_code_math_t_0
|
| 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/mix_base_code_math_t_0 dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9952,
|
| 3 |
+
"total_flos": 312970832904192.0,
|
| 4 |
+
"train_loss": 0.610789420035405,
|
| 5 |
+
"train_runtime": 29538.0563,
|
| 6 |
+
"train_samples_per_second": 1.016,
|
| 7 |
+
"train_steps_per_second": 0.011
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9952,
|
| 3 |
+
"total_flos": 312970832904192.0,
|
| 4 |
+
"train_loss": 0.610789420035405,
|
| 5 |
+
"train_runtime": 29538.0563,
|
| 6 |
+
"train_samples_per_second": 1.016,
|
| 7 |
+
"train_steps_per_second": 0.011
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2226 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9952,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 312,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0096,
|
| 13 |
+
"grad_norm": 6.292316913604736,
|
| 14 |
+
"learning_rate": 3.125e-07,
|
| 15 |
+
"loss": 1.0104,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0192,
|
| 20 |
+
"grad_norm": 6.1730875968933105,
|
| 21 |
+
"learning_rate": 6.25e-07,
|
| 22 |
+
"loss": 1.0026,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.0288,
|
| 27 |
+
"grad_norm": 6.434154033660889,
|
| 28 |
+
"learning_rate": 9.375000000000001e-07,
|
| 29 |
+
"loss": 1.0329,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0384,
|
| 34 |
+
"grad_norm": 6.069917678833008,
|
| 35 |
+
"learning_rate": 1.25e-06,
|
| 36 |
+
"loss": 0.9934,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.048,
|
| 41 |
+
"grad_norm": 5.826951503753662,
|
| 42 |
+
"learning_rate": 1.5625e-06,
|
| 43 |
+
"loss": 0.9941,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.0576,
|
| 48 |
+
"grad_norm": 5.749411582946777,
|
| 49 |
+
"learning_rate": 1.8750000000000003e-06,
|
| 50 |
+
"loss": 0.9974,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.0672,
|
| 55 |
+
"grad_norm": 4.575586318969727,
|
| 56 |
+
"learning_rate": 2.1875000000000002e-06,
|
| 57 |
+
"loss": 0.9291,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.0768,
|
| 62 |
+
"grad_norm": 4.361931800842285,
|
| 63 |
+
"learning_rate": 2.5e-06,
|
| 64 |
+
"loss": 0.9198,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.0864,
|
| 69 |
+
"grad_norm": 2.572038412094116,
|
| 70 |
+
"learning_rate": 2.8125e-06,
|
| 71 |
+
"loss": 0.9106,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.096,
|
| 76 |
+
"grad_norm": 2.4609551429748535,
|
| 77 |
+
"learning_rate": 3.125e-06,
|
| 78 |
+
"loss": 0.9226,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.1056,
|
| 83 |
+
"grad_norm": 2.093930959701538,
|
| 84 |
+
"learning_rate": 3.4375e-06,
|
| 85 |
+
"loss": 0.8899,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.1152,
|
| 90 |
+
"grad_norm": 3.553408622741699,
|
| 91 |
+
"learning_rate": 3.7500000000000005e-06,
|
| 92 |
+
"loss": 0.9156,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.1248,
|
| 97 |
+
"grad_norm": 3.967522621154785,
|
| 98 |
+
"learning_rate": 4.0625000000000005e-06,
|
| 99 |
+
"loss": 0.8831,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.1344,
|
| 104 |
+
"grad_norm": 3.7353246212005615,
|
| 105 |
+
"learning_rate": 4.3750000000000005e-06,
|
| 106 |
+
"loss": 0.8756,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.144,
|
| 111 |
+
"grad_norm": 3.722759962081909,
|
| 112 |
+
"learning_rate": 4.6875000000000004e-06,
|
| 113 |
+
"loss": 0.8935,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.1536,
|
| 118 |
+
"grad_norm": 2.4490113258361816,
|
| 119 |
+
"learning_rate": 5e-06,
|
| 120 |
+
"loss": 0.8094,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.1632,
|
| 125 |
+
"grad_norm": 2.2576043605804443,
|
| 126 |
+
"learning_rate": 5.3125e-06,
|
| 127 |
+
"loss": 0.8232,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.1728,
|
| 132 |
+
"grad_norm": 2.022249460220337,
|
| 133 |
+
"learning_rate": 5.625e-06,
|
| 134 |
+
"loss": 0.8152,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.1824,
|
| 139 |
+
"grad_norm": 1.6432116031646729,
|
| 140 |
+
"learning_rate": 5.9375e-06,
|
| 141 |
+
"loss": 0.8131,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.192,
|
| 146 |
+
"grad_norm": 1.428215742111206,
|
| 147 |
+
"learning_rate": 6.25e-06,
|
| 148 |
+
"loss": 0.7559,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.2016,
|
| 153 |
+
"grad_norm": 1.2886855602264404,
|
| 154 |
+
"learning_rate": 6.5625e-06,
|
| 155 |
+
"loss": 0.7587,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.2112,
|
| 160 |
+
"grad_norm": 1.229178786277771,
|
| 161 |
+
"learning_rate": 6.875e-06,
|
| 162 |
+
"loss": 0.779,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.2208,
|
| 167 |
+
"grad_norm": 1.1774561405181885,
|
| 168 |
+
"learning_rate": 7.1875e-06,
|
| 169 |
+
"loss": 0.7286,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.2304,
|
| 174 |
+
"grad_norm": 1.279067039489746,
|
| 175 |
+
"learning_rate": 7.500000000000001e-06,
|
| 176 |
+
"loss": 0.768,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.24,
|
| 181 |
+
"grad_norm": 0.9670516848564148,
|
| 182 |
+
"learning_rate": 7.8125e-06,
|
| 183 |
+
"loss": 0.7009,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.2496,
|
| 188 |
+
"grad_norm": 1.081884503364563,
|
| 189 |
+
"learning_rate": 8.125000000000001e-06,
|
| 190 |
+
"loss": 0.7441,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.2592,
|
| 195 |
+
"grad_norm": 1.046007752418518,
|
| 196 |
+
"learning_rate": 8.4375e-06,
|
| 197 |
+
"loss": 0.7463,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.2688,
|
| 202 |
+
"grad_norm": 0.8546833395957947,
|
| 203 |
+
"learning_rate": 8.750000000000001e-06,
|
| 204 |
+
"loss": 0.6999,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.2784,
|
| 209 |
+
"grad_norm": 0.8875015377998352,
|
| 210 |
+
"learning_rate": 9.0625e-06,
|
| 211 |
+
"loss": 0.7203,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.288,
|
| 216 |
+
"grad_norm": 0.899333119392395,
|
| 217 |
+
"learning_rate": 9.375000000000001e-06,
|
| 218 |
+
"loss": 0.725,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.2976,
|
| 223 |
+
"grad_norm": 0.9151673316955566,
|
| 224 |
+
"learning_rate": 9.6875e-06,
|
| 225 |
+
"loss": 0.7323,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.3072,
|
| 230 |
+
"grad_norm": 0.7202209830284119,
|
| 231 |
+
"learning_rate": 1e-05,
|
| 232 |
+
"loss": 0.7081,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.3168,
|
| 237 |
+
"grad_norm": 0.8347250819206238,
|
| 238 |
+
"learning_rate": 9.999685283773504e-06,
|
| 239 |
+
"loss": 0.702,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.3264,
|
| 244 |
+
"grad_norm": 0.7798133492469788,
|
| 245 |
+
"learning_rate": 9.998741174712534e-06,
|
| 246 |
+
"loss": 0.679,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.336,
|
| 251 |
+
"grad_norm": 0.8034778833389282,
|
| 252 |
+
"learning_rate": 9.997167791667668e-06,
|
| 253 |
+
"loss": 0.7096,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.3456,
|
| 258 |
+
"grad_norm": 0.7123808860778809,
|
| 259 |
+
"learning_rate": 9.994965332706574e-06,
|
| 260 |
+
"loss": 0.6878,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.3552,
|
| 265 |
+
"grad_norm": 0.8426344990730286,
|
| 266 |
+
"learning_rate": 9.992134075089085e-06,
|
| 267 |
+
"loss": 0.7157,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.3648,
|
| 272 |
+
"grad_norm": 0.6954659819602966,
|
| 273 |
+
"learning_rate": 9.98867437523228e-06,
|
| 274 |
+
"loss": 0.709,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.3744,
|
| 279 |
+
"grad_norm": 0.8144009709358215,
|
| 280 |
+
"learning_rate": 9.984586668665641e-06,
|
| 281 |
+
"loss": 0.6934,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.384,
|
| 286 |
+
"grad_norm": 0.6534774303436279,
|
| 287 |
+
"learning_rate": 9.979871469976197e-06,
|
| 288 |
+
"loss": 0.6694,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.3936,
|
| 293 |
+
"grad_norm": 0.792493999004364,
|
| 294 |
+
"learning_rate": 9.974529372743762e-06,
|
| 295 |
+
"loss": 0.6651,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.4032,
|
| 300 |
+
"grad_norm": 0.7658901810646057,
|
| 301 |
+
"learning_rate": 9.968561049466214e-06,
|
| 302 |
+
"loss": 0.6625,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.4128,
|
| 307 |
+
"grad_norm": 0.5957349538803101,
|
| 308 |
+
"learning_rate": 9.961967251474823e-06,
|
| 309 |
+
"loss": 0.6556,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.4224,
|
| 314 |
+
"grad_norm": 0.6661067605018616,
|
| 315 |
+
"learning_rate": 9.954748808839675e-06,
|
| 316 |
+
"loss": 0.6638,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.432,
|
| 321 |
+
"grad_norm": 0.6937732100486755,
|
| 322 |
+
"learning_rate": 9.946906630265184e-06,
|
| 323 |
+
"loss": 0.6636,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.4416,
|
| 328 |
+
"grad_norm": 0.6557593941688538,
|
| 329 |
+
"learning_rate": 9.938441702975689e-06,
|
| 330 |
+
"loss": 0.6641,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.4512,
|
| 335 |
+
"grad_norm": 0.7512499094009399,
|
| 336 |
+
"learning_rate": 9.92935509259118e-06,
|
| 337 |
+
"loss": 0.6812,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.4608,
|
| 342 |
+
"grad_norm": 0.626158595085144,
|
| 343 |
+
"learning_rate": 9.91964794299315e-06,
|
| 344 |
+
"loss": 0.6607,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.4704,
|
| 349 |
+
"grad_norm": 0.5737528204917908,
|
| 350 |
+
"learning_rate": 9.909321476180594e-06,
|
| 351 |
+
"loss": 0.695,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.48,
|
| 356 |
+
"grad_norm": 0.6223921775817871,
|
| 357 |
+
"learning_rate": 9.898376992116179e-06,
|
| 358 |
+
"loss": 0.6679,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.4896,
|
| 363 |
+
"grad_norm": 0.6310274600982666,
|
| 364 |
+
"learning_rate": 9.886815868562596e-06,
|
| 365 |
+
"loss": 0.6666,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.4992,
|
| 370 |
+
"grad_norm": 0.7005355954170227,
|
| 371 |
+
"learning_rate": 9.874639560909118e-06,
|
| 372 |
+
"loss": 0.6745,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.5088,
|
| 377 |
+
"grad_norm": 0.6608271598815918,
|
| 378 |
+
"learning_rate": 9.861849601988384e-06,
|
| 379 |
+
"loss": 0.6894,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.5184,
|
| 384 |
+
"grad_norm": 0.6414551734924316,
|
| 385 |
+
"learning_rate": 9.848447601883436e-06,
|
| 386 |
+
"loss": 0.6771,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.528,
|
| 391 |
+
"grad_norm": 0.7467500567436218,
|
| 392 |
+
"learning_rate": 9.834435247725032e-06,
|
| 393 |
+
"loss": 0.6468,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.5376,
|
| 398 |
+
"grad_norm": 0.5815238952636719,
|
| 399 |
+
"learning_rate": 9.819814303479268e-06,
|
| 400 |
+
"loss": 0.6622,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.5472,
|
| 405 |
+
"grad_norm": 0.6850916147232056,
|
| 406 |
+
"learning_rate": 9.804586609725499e-06,
|
| 407 |
+
"loss": 0.623,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.5568,
|
| 412 |
+
"grad_norm": 0.67253178358078,
|
| 413 |
+
"learning_rate": 9.788754083424654e-06,
|
| 414 |
+
"loss": 0.6524,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.5664,
|
| 419 |
+
"grad_norm": 0.6569348573684692,
|
| 420 |
+
"learning_rate": 9.772318717677905e-06,
|
| 421 |
+
"loss": 0.6649,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.576,
|
| 426 |
+
"grad_norm": 0.7703596949577332,
|
| 427 |
+
"learning_rate": 9.755282581475769e-06,
|
| 428 |
+
"loss": 0.6653,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.5856,
|
| 433 |
+
"grad_norm": 0.5406990647315979,
|
| 434 |
+
"learning_rate": 9.737647819437645e-06,
|
| 435 |
+
"loss": 0.664,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.5952,
|
| 440 |
+
"grad_norm": 0.6827347278594971,
|
| 441 |
+
"learning_rate": 9.719416651541839e-06,
|
| 442 |
+
"loss": 0.6854,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.6048,
|
| 447 |
+
"grad_norm": 0.6011564135551453,
|
| 448 |
+
"learning_rate": 9.700591372846096e-06,
|
| 449 |
+
"loss": 0.6595,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.6144,
|
| 454 |
+
"grad_norm": 0.6541777849197388,
|
| 455 |
+
"learning_rate": 9.681174353198687e-06,
|
| 456 |
+
"loss": 0.6764,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.624,
|
| 461 |
+
"grad_norm": 0.6818787455558777,
|
| 462 |
+
"learning_rate": 9.661168036940071e-06,
|
| 463 |
+
"loss": 0.6201,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.6336,
|
| 468 |
+
"grad_norm": 0.6184643507003784,
|
| 469 |
+
"learning_rate": 9.640574942595195e-06,
|
| 470 |
+
"loss": 0.6488,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.6432,
|
| 475 |
+
"grad_norm": 0.6250948309898376,
|
| 476 |
+
"learning_rate": 9.619397662556434e-06,
|
| 477 |
+
"loss": 0.6462,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.6528,
|
| 482 |
+
"grad_norm": 0.6833012104034424,
|
| 483 |
+
"learning_rate": 9.597638862757255e-06,
|
| 484 |
+
"loss": 0.6527,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.6624,
|
| 489 |
+
"grad_norm": 0.5511516332626343,
|
| 490 |
+
"learning_rate": 9.5753012823366e-06,
|
| 491 |
+
"loss": 0.6502,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.672,
|
| 496 |
+
"grad_norm": 0.7079241275787354,
|
| 497 |
+
"learning_rate": 9.552387733294081e-06,
|
| 498 |
+
"loss": 0.6747,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.6816,
|
| 503 |
+
"grad_norm": 0.637936532497406,
|
| 504 |
+
"learning_rate": 9.528901100135971e-06,
|
| 505 |
+
"loss": 0.669,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.6912,
|
| 510 |
+
"grad_norm": 0.6084673404693604,
|
| 511 |
+
"learning_rate": 9.504844339512096e-06,
|
| 512 |
+
"loss": 0.6397,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.7008,
|
| 517 |
+
"grad_norm": 0.6382216811180115,
|
| 518 |
+
"learning_rate": 9.480220479843627e-06,
|
| 519 |
+
"loss": 0.6775,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.7104,
|
| 524 |
+
"grad_norm": 0.5169996023178101,
|
| 525 |
+
"learning_rate": 9.45503262094184e-06,
|
| 526 |
+
"loss": 0.6424,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.72,
|
| 531 |
+
"grad_norm": 0.6096466779708862,
|
| 532 |
+
"learning_rate": 9.4292839336179e-06,
|
| 533 |
+
"loss": 0.642,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.7296,
|
| 538 |
+
"grad_norm": 0.5510257482528687,
|
| 539 |
+
"learning_rate": 9.40297765928369e-06,
|
| 540 |
+
"loss": 0.6335,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.7392,
|
| 545 |
+
"grad_norm": 0.5844236612319946,
|
| 546 |
+
"learning_rate": 9.376117109543769e-06,
|
| 547 |
+
"loss": 0.6247,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.7488,
|
| 552 |
+
"grad_norm": 0.5517457127571106,
|
| 553 |
+
"learning_rate": 9.348705665778479e-06,
|
| 554 |
+
"loss": 0.6216,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.7584,
|
| 559 |
+
"grad_norm": 0.5716204047203064,
|
| 560 |
+
"learning_rate": 9.320746778718274e-06,
|
| 561 |
+
"loss": 0.6496,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.768,
|
| 566 |
+
"grad_norm": 0.5770816206932068,
|
| 567 |
+
"learning_rate": 9.292243968009332e-06,
|
| 568 |
+
"loss": 0.6431,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.7776,
|
| 573 |
+
"grad_norm": 0.5499193668365479,
|
| 574 |
+
"learning_rate": 9.263200821770462e-06,
|
| 575 |
+
"loss": 0.6548,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.7872,
|
| 580 |
+
"grad_norm": 0.6924810409545898,
|
| 581 |
+
"learning_rate": 9.233620996141421e-06,
|
| 582 |
+
"loss": 0.6227,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.7968,
|
| 587 |
+
"grad_norm": 0.5241541862487793,
|
| 588 |
+
"learning_rate": 9.203508214822652e-06,
|
| 589 |
+
"loss": 0.6568,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.8064,
|
| 594 |
+
"grad_norm": 0.6041975617408752,
|
| 595 |
+
"learning_rate": 9.172866268606514e-06,
|
| 596 |
+
"loss": 0.6451,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.816,
|
| 601 |
+
"grad_norm": 0.6413403749465942,
|
| 602 |
+
"learning_rate": 9.141699014900084e-06,
|
| 603 |
+
"loss": 0.6489,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.8256,
|
| 608 |
+
"grad_norm": 0.5075194835662842,
|
| 609 |
+
"learning_rate": 9.110010377239552e-06,
|
| 610 |
+
"loss": 0.6278,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.8352,
|
| 615 |
+
"grad_norm": 0.6670998334884644,
|
| 616 |
+
"learning_rate": 9.077804344796302e-06,
|
| 617 |
+
"loss": 0.6798,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.8448,
|
| 622 |
+
"grad_norm": 0.5765168070793152,
|
| 623 |
+
"learning_rate": 9.045084971874738e-06,
|
| 624 |
+
"loss": 0.6451,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.8544,
|
| 629 |
+
"grad_norm": 0.555912435054779,
|
| 630 |
+
"learning_rate": 9.011856377401891e-06,
|
| 631 |
+
"loss": 0.6401,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.864,
|
| 636 |
+
"grad_norm": 0.5889183878898621,
|
| 637 |
+
"learning_rate": 8.978122744408905e-06,
|
| 638 |
+
"loss": 0.6513,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.8736,
|
| 643 |
+
"grad_norm": 0.558150053024292,
|
| 644 |
+
"learning_rate": 8.943888319504456e-06,
|
| 645 |
+
"loss": 0.6286,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.8832,
|
| 650 |
+
"grad_norm": 0.6536504626274109,
|
| 651 |
+
"learning_rate": 8.90915741234015e-06,
|
| 652 |
+
"loss": 0.6396,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.8928,
|
| 657 |
+
"grad_norm": 0.6340594291687012,
|
| 658 |
+
"learning_rate": 8.873934395068006e-06,
|
| 659 |
+
"loss": 0.6436,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.9024,
|
| 664 |
+
"grad_norm": 0.7267080545425415,
|
| 665 |
+
"learning_rate": 8.838223701790057e-06,
|
| 666 |
+
"loss": 0.6352,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.912,
|
| 671 |
+
"grad_norm": 0.5870280265808105,
|
| 672 |
+
"learning_rate": 8.802029828000157e-06,
|
| 673 |
+
"loss": 0.6036,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.9216,
|
| 678 |
+
"grad_norm": 0.6412261128425598,
|
| 679 |
+
"learning_rate": 8.765357330018056e-06,
|
| 680 |
+
"loss": 0.6242,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.9312,
|
| 685 |
+
"grad_norm": 0.6203837394714355,
|
| 686 |
+
"learning_rate": 8.728210824415829e-06,
|
| 687 |
+
"loss": 0.6363,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.9408,
|
| 692 |
+
"grad_norm": 0.6868276000022888,
|
| 693 |
+
"learning_rate": 8.690594987436705e-06,
|
| 694 |
+
"loss": 0.6171,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.9504,
|
| 699 |
+
"grad_norm": 0.5638834238052368,
|
| 700 |
+
"learning_rate": 8.652514554406388e-06,
|
| 701 |
+
"loss": 0.635,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.96,
|
| 706 |
+
"grad_norm": 0.69553542137146,
|
| 707 |
+
"learning_rate": 8.613974319136959e-06,
|
| 708 |
+
"loss": 0.6527,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.9696,
|
| 713 |
+
"grad_norm": 0.5303117036819458,
|
| 714 |
+
"learning_rate": 8.574979133323378e-06,
|
| 715 |
+
"loss": 0.6403,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.9792,
|
| 720 |
+
"grad_norm": 0.6957817673683167,
|
| 721 |
+
"learning_rate": 8.535533905932739e-06,
|
| 722 |
+
"loss": 0.6295,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.9888,
|
| 727 |
+
"grad_norm": 0.6576924324035645,
|
| 728 |
+
"learning_rate": 8.495643602586287e-06,
|
| 729 |
+
"loss": 0.6362,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.9984,
|
| 734 |
+
"grad_norm": 0.6190880537033081,
|
| 735 |
+
"learning_rate": 8.455313244934324e-06,
|
| 736 |
+
"loss": 0.6343,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.008,
|
| 741 |
+
"grad_norm": 1.2567451000213623,
|
| 742 |
+
"learning_rate": 8.414547910024035e-06,
|
| 743 |
+
"loss": 1.0639,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.0176,
|
| 748 |
+
"grad_norm": 0.5477228164672852,
|
| 749 |
+
"learning_rate": 8.373352729660373e-06,
|
| 750 |
+
"loss": 0.546,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.0272,
|
| 755 |
+
"grad_norm": 0.569487452507019,
|
| 756 |
+
"learning_rate": 8.331732889760021e-06,
|
| 757 |
+
"loss": 0.5735,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.0368,
|
| 762 |
+
"grad_norm": 0.6835495233535767,
|
| 763 |
+
"learning_rate": 8.289693629698564e-06,
|
| 764 |
+
"loss": 0.6376,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.0464,
|
| 769 |
+
"grad_norm": 0.5983431339263916,
|
| 770 |
+
"learning_rate": 8.247240241650918e-06,
|
| 771 |
+
"loss": 0.6078,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 1.056,
|
| 776 |
+
"grad_norm": 0.6319621801376343,
|
| 777 |
+
"learning_rate": 8.204378069925121e-06,
|
| 778 |
+
"loss": 0.591,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.0656,
|
| 783 |
+
"grad_norm": 0.6427493691444397,
|
| 784 |
+
"learning_rate": 8.16111251028955e-06,
|
| 785 |
+
"loss": 0.5695,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.0752,
|
| 790 |
+
"grad_norm": 0.5300183892250061,
|
| 791 |
+
"learning_rate": 8.117449009293668e-06,
|
| 792 |
+
"loss": 0.5742,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 1.0848,
|
| 797 |
+
"grad_norm": 0.5667701959609985,
|
| 798 |
+
"learning_rate": 8.073393063582386e-06,
|
| 799 |
+
"loss": 0.5429,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 1.0944,
|
| 804 |
+
"grad_norm": 0.6527385711669922,
|
| 805 |
+
"learning_rate": 8.0289502192041e-06,
|
| 806 |
+
"loss": 0.5633,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.104,
|
| 811 |
+
"grad_norm": 0.6647496819496155,
|
| 812 |
+
"learning_rate": 7.984126070912519e-06,
|
| 813 |
+
"loss": 0.6611,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 1.1136,
|
| 818 |
+
"grad_norm": 0.47675877809524536,
|
| 819 |
+
"learning_rate": 7.938926261462366e-06,
|
| 820 |
+
"loss": 0.5287,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 1.1232,
|
| 825 |
+
"grad_norm": 0.738347589969635,
|
| 826 |
+
"learning_rate": 7.89335648089903e-06,
|
| 827 |
+
"loss": 0.6157,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 1.1328,
|
| 832 |
+
"grad_norm": 0.57480788230896,
|
| 833 |
+
"learning_rate": 7.84742246584226e-06,
|
| 834 |
+
"loss": 0.5565,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 1.1424,
|
| 839 |
+
"grad_norm": 0.5129834413528442,
|
| 840 |
+
"learning_rate": 7.801129998764014e-06,
|
| 841 |
+
"loss": 0.5546,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 1.152,
|
| 846 |
+
"grad_norm": 0.7716547250747681,
|
| 847 |
+
"learning_rate": 7.754484907260513e-06,
|
| 848 |
+
"loss": 0.6147,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.1616,
|
| 853 |
+
"grad_norm": 0.545978307723999,
|
| 854 |
+
"learning_rate": 7.70749306331863e-06,
|
| 855 |
+
"loss": 0.5565,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 1.1712,
|
| 860 |
+
"grad_norm": 0.5517440438270569,
|
| 861 |
+
"learning_rate": 7.660160382576683e-06,
|
| 862 |
+
"loss": 0.608,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 1.1808,
|
| 867 |
+
"grad_norm": 0.6543371081352234,
|
| 868 |
+
"learning_rate": 7.612492823579744e-06,
|
| 869 |
+
"loss": 0.5766,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 1.1904,
|
| 874 |
+
"grad_norm": 0.5610912442207336,
|
| 875 |
+
"learning_rate": 7.564496387029532e-06,
|
| 876 |
+
"loss": 0.5889,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 1.2,
|
| 881 |
+
"grad_norm": 0.725592315196991,
|
| 882 |
+
"learning_rate": 7.516177115029002e-06,
|
| 883 |
+
"loss": 0.576,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 1.2096,
|
| 888 |
+
"grad_norm": 0.5460718870162964,
|
| 889 |
+
"learning_rate": 7.467541090321735e-06,
|
| 890 |
+
"loss": 0.5926,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 1.2192,
|
| 895 |
+
"grad_norm": 0.587978720664978,
|
| 896 |
+
"learning_rate": 7.4185944355261996e-06,
|
| 897 |
+
"loss": 0.544,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 1.2288000000000001,
|
| 902 |
+
"grad_norm": 0.5988969802856445,
|
| 903 |
+
"learning_rate": 7.369343312364994e-06,
|
| 904 |
+
"loss": 0.5996,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 1.2384,
|
| 909 |
+
"grad_norm": 0.5384567379951477,
|
| 910 |
+
"learning_rate": 7.319793920889171e-06,
|
| 911 |
+
"loss": 0.5328,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 1.248,
|
| 916 |
+
"grad_norm": 0.6369662880897522,
|
| 917 |
+
"learning_rate": 7.269952498697734e-06,
|
| 918 |
+
"loss": 0.5878,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 1.2576,
|
| 923 |
+
"grad_norm": 0.5659148097038269,
|
| 924 |
+
"learning_rate": 7.219825320152411e-06,
|
| 925 |
+
"loss": 0.6203,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 1.2671999999999999,
|
| 930 |
+
"grad_norm": 0.5150180459022522,
|
| 931 |
+
"learning_rate": 7.169418695587791e-06,
|
| 932 |
+
"loss": 0.4977,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 1.2768,
|
| 937 |
+
"grad_norm": 0.6585394740104675,
|
| 938 |
+
"learning_rate": 7.118738970516944e-06,
|
| 939 |
+
"loss": 0.6233,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.2864,
|
| 944 |
+
"grad_norm": 0.49442875385284424,
|
| 945 |
+
"learning_rate": 7.067792524832604e-06,
|
| 946 |
+
"loss": 0.5462,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 1.296,
|
| 951 |
+
"grad_norm": 0.5812093019485474,
|
| 952 |
+
"learning_rate": 7.016585772004026e-06,
|
| 953 |
+
"loss": 0.6037,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 1.3056,
|
| 958 |
+
"grad_norm": 0.6433523297309875,
|
| 959 |
+
"learning_rate": 6.965125158269619e-06,
|
| 960 |
+
"loss": 0.6334,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 1.3152,
|
| 965 |
+
"grad_norm": 0.5826403498649597,
|
| 966 |
+
"learning_rate": 6.913417161825449e-06,
|
| 967 |
+
"loss": 0.5644,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 1.3248,
|
| 972 |
+
"grad_norm": 0.492260605096817,
|
| 973 |
+
"learning_rate": 6.8614682920097265e-06,
|
| 974 |
+
"loss": 0.5566,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 1.3344,
|
| 979 |
+
"grad_norm": 0.5302029848098755,
|
| 980 |
+
"learning_rate": 6.809285088483361e-06,
|
| 981 |
+
"loss": 0.576,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 1.3439999999999999,
|
| 986 |
+
"grad_norm": 0.5525418519973755,
|
| 987 |
+
"learning_rate": 6.7568741204067145e-06,
|
| 988 |
+
"loss": 0.5355,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 1.3536000000000001,
|
| 993 |
+
"grad_norm": 0.5225656628608704,
|
| 994 |
+
"learning_rate": 6.704241985612625e-06,
|
| 995 |
+
"loss": 0.5751,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 1.3632,
|
| 1000 |
+
"grad_norm": 0.4587990939617157,
|
| 1001 |
+
"learning_rate": 6.651395309775837e-06,
|
| 1002 |
+
"loss": 0.5381,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 1.3728,
|
| 1007 |
+
"grad_norm": 0.579556941986084,
|
| 1008 |
+
"learning_rate": 6.598340745578908e-06,
|
| 1009 |
+
"loss": 0.6322,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 1.3824,
|
| 1014 |
+
"grad_norm": 0.5754554271697998,
|
| 1015 |
+
"learning_rate": 6.545084971874738e-06,
|
| 1016 |
+
"loss": 0.575,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 1.392,
|
| 1021 |
+
"grad_norm": 0.5633704662322998,
|
| 1022 |
+
"learning_rate": 6.491634692845781e-06,
|
| 1023 |
+
"loss": 0.6123,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 1.4016,
|
| 1028 |
+
"grad_norm": 0.4322211742401123,
|
| 1029 |
+
"learning_rate": 6.437996637160086e-06,
|
| 1030 |
+
"loss": 0.5378,
|
| 1031 |
+
"step": 146
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 1.4112,
|
| 1035 |
+
"grad_norm": 0.5670461058616638,
|
| 1036 |
+
"learning_rate": 6.384177557124247e-06,
|
| 1037 |
+
"loss": 0.6098,
|
| 1038 |
+
"step": 147
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 1.4208,
|
| 1042 |
+
"grad_norm": 0.501027524471283,
|
| 1043 |
+
"learning_rate": 6.330184227833376e-06,
|
| 1044 |
+
"loss": 0.5874,
|
| 1045 |
+
"step": 148
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 1.4304000000000001,
|
| 1049 |
+
"grad_norm": 0.44575896859169006,
|
| 1050 |
+
"learning_rate": 6.276023446318214e-06,
|
| 1051 |
+
"loss": 0.5889,
|
| 1052 |
+
"step": 149
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 1.44,
|
| 1056 |
+
"grad_norm": 0.48979705572128296,
|
| 1057 |
+
"learning_rate": 6.2217020306894705e-06,
|
| 1058 |
+
"loss": 0.5575,
|
| 1059 |
+
"step": 150
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 1.4496,
|
| 1063 |
+
"grad_norm": 0.5052200555801392,
|
| 1064 |
+
"learning_rate": 6.1672268192795285e-06,
|
| 1065 |
+
"loss": 0.551,
|
| 1066 |
+
"step": 151
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 1.4592,
|
| 1070 |
+
"grad_norm": 0.4936927855014801,
|
| 1071 |
+
"learning_rate": 6.112604669781572e-06,
|
| 1072 |
+
"loss": 0.5616,
|
| 1073 |
+
"step": 152
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 1.4687999999999999,
|
| 1077 |
+
"grad_norm": 0.4863929748535156,
|
| 1078 |
+
"learning_rate": 6.057842458386315e-06,
|
| 1079 |
+
"loss": 0.6105,
|
| 1080 |
+
"step": 153
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 1.4784,
|
| 1084 |
+
"grad_norm": 0.4865013659000397,
|
| 1085 |
+
"learning_rate": 6.002947078916365e-06,
|
| 1086 |
+
"loss": 0.5389,
|
| 1087 |
+
"step": 154
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 1.488,
|
| 1091 |
+
"grad_norm": 0.5264416933059692,
|
| 1092 |
+
"learning_rate": 5.947925441958393e-06,
|
| 1093 |
+
"loss": 0.5851,
|
| 1094 |
+
"step": 155
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 1.4976,
|
| 1098 |
+
"grad_norm": 0.4394872784614563,
|
| 1099 |
+
"learning_rate": 5.892784473993184e-06,
|
| 1100 |
+
"loss": 0.5623,
|
| 1101 |
+
"step": 156
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 1.5072,
|
| 1105 |
+
"grad_norm": 0.5211396813392639,
|
| 1106 |
+
"learning_rate": 5.837531116523683e-06,
|
| 1107 |
+
"loss": 0.6225,
|
| 1108 |
+
"step": 157
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 1.5168,
|
| 1112 |
+
"grad_norm": 0.4977400302886963,
|
| 1113 |
+
"learning_rate": 5.782172325201155e-06,
|
| 1114 |
+
"loss": 0.5915,
|
| 1115 |
+
"step": 158
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 1.5264,
|
| 1119 |
+
"grad_norm": 0.4418800175189972,
|
| 1120 |
+
"learning_rate": 5.726715068949564e-06,
|
| 1121 |
+
"loss": 0.4918,
|
| 1122 |
+
"step": 159
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 1.536,
|
| 1126 |
+
"grad_norm": 0.5426927208900452,
|
| 1127 |
+
"learning_rate": 5.671166329088278e-06,
|
| 1128 |
+
"loss": 0.6375,
|
| 1129 |
+
"step": 160
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.5455999999999999,
|
| 1133 |
+
"grad_norm": 0.4744737446308136,
|
| 1134 |
+
"learning_rate": 5.615533098453215e-06,
|
| 1135 |
+
"loss": 0.6084,
|
| 1136 |
+
"step": 161
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 1.5552000000000001,
|
| 1140 |
+
"grad_norm": 0.4746991991996765,
|
| 1141 |
+
"learning_rate": 5.559822380516539e-06,
|
| 1142 |
+
"loss": 0.5142,
|
| 1143 |
+
"step": 162
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 1.5648,
|
| 1147 |
+
"grad_norm": 0.4827795624732971,
|
| 1148 |
+
"learning_rate": 5.504041188505022e-06,
|
| 1149 |
+
"loss": 0.5769,
|
| 1150 |
+
"step": 163
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 1.5744,
|
| 1154 |
+
"grad_norm": 0.468890905380249,
|
| 1155 |
+
"learning_rate": 5.448196544517168e-06,
|
| 1156 |
+
"loss": 0.5877,
|
| 1157 |
+
"step": 164
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.584,
|
| 1161 |
+
"grad_norm": 0.48452773690223694,
|
| 1162 |
+
"learning_rate": 5.392295478639226e-06,
|
| 1163 |
+
"loss": 0.5833,
|
| 1164 |
+
"step": 165
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 1.5936,
|
| 1168 |
+
"grad_norm": 0.5015302896499634,
|
| 1169 |
+
"learning_rate": 5.336345028060199e-06,
|
| 1170 |
+
"loss": 0.6116,
|
| 1171 |
+
"step": 166
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 1.6032,
|
| 1175 |
+
"grad_norm": 0.43964874744415283,
|
| 1176 |
+
"learning_rate": 5.2803522361859596e-06,
|
| 1177 |
+
"loss": 0.5582,
|
| 1178 |
+
"step": 167
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 1.6128,
|
| 1182 |
+
"grad_norm": 0.4486831724643707,
|
| 1183 |
+
"learning_rate": 5.224324151752575e-06,
|
| 1184 |
+
"loss": 0.5489,
|
| 1185 |
+
"step": 168
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 1.6223999999999998,
|
| 1189 |
+
"grad_norm": 0.47891250252723694,
|
| 1190 |
+
"learning_rate": 5.168267827938971e-06,
|
| 1191 |
+
"loss": 0.5648,
|
| 1192 |
+
"step": 169
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 1.6320000000000001,
|
| 1196 |
+
"grad_norm": 0.4622023105621338,
|
| 1197 |
+
"learning_rate": 5.112190321479026e-06,
|
| 1198 |
+
"loss": 0.5918,
|
| 1199 |
+
"step": 170
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 1.6416,
|
| 1203 |
+
"grad_norm": 0.5129140615463257,
|
| 1204 |
+
"learning_rate": 5.05609869177323e-06,
|
| 1205 |
+
"loss": 0.6332,
|
| 1206 |
+
"step": 171
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 1.6512,
|
| 1210 |
+
"grad_norm": 0.4973113536834717,
|
| 1211 |
+
"learning_rate": 5e-06,
|
| 1212 |
+
"loss": 0.5124,
|
| 1213 |
+
"step": 172
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 1.6608,
|
| 1217 |
+
"grad_norm": 0.4771605134010315,
|
| 1218 |
+
"learning_rate": 4.943901308226771e-06,
|
| 1219 |
+
"loss": 0.6114,
|
| 1220 |
+
"step": 173
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 1.6703999999999999,
|
| 1224 |
+
"grad_norm": 0.45923885703086853,
|
| 1225 |
+
"learning_rate": 4.887809678520976e-06,
|
| 1226 |
+
"loss": 0.5534,
|
| 1227 |
+
"step": 174
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 1.6800000000000002,
|
| 1231 |
+
"grad_norm": 0.5138639211654663,
|
| 1232 |
+
"learning_rate": 4.831732172061032e-06,
|
| 1233 |
+
"loss": 0.5472,
|
| 1234 |
+
"step": 175
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 1.6896,
|
| 1238 |
+
"grad_norm": 0.49369630217552185,
|
| 1239 |
+
"learning_rate": 4.775675848247427e-06,
|
| 1240 |
+
"loss": 0.6085,
|
| 1241 |
+
"step": 176
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 1.6992,
|
| 1245 |
+
"grad_norm": 0.48870953917503357,
|
| 1246 |
+
"learning_rate": 4.719647763814041e-06,
|
| 1247 |
+
"loss": 0.5798,
|
| 1248 |
+
"step": 177
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 1.7088,
|
| 1252 |
+
"grad_norm": 0.4958065152168274,
|
| 1253 |
+
"learning_rate": 4.663654971939802e-06,
|
| 1254 |
+
"loss": 0.5883,
|
| 1255 |
+
"step": 178
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 1.7184,
|
| 1259 |
+
"grad_norm": 0.49560844898223877,
|
| 1260 |
+
"learning_rate": 4.6077045213607765e-06,
|
| 1261 |
+
"loss": 0.5757,
|
| 1262 |
+
"step": 179
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 1.728,
|
| 1266 |
+
"grad_norm": 0.4331684112548828,
|
| 1267 |
+
"learning_rate": 4.551803455482833e-06,
|
| 1268 |
+
"loss": 0.5657,
|
| 1269 |
+
"step": 180
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.7376,
|
| 1273 |
+
"grad_norm": 0.5511804223060608,
|
| 1274 |
+
"learning_rate": 4.4959588114949785e-06,
|
| 1275 |
+
"loss": 0.6329,
|
| 1276 |
+
"step": 181
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 1.7471999999999999,
|
| 1280 |
+
"grad_norm": 0.48789289593696594,
|
| 1281 |
+
"learning_rate": 4.4401776194834615e-06,
|
| 1282 |
+
"loss": 0.5785,
|
| 1283 |
+
"step": 182
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 1.7568000000000001,
|
| 1287 |
+
"grad_norm": 0.4831961691379547,
|
| 1288 |
+
"learning_rate": 4.384466901546786e-06,
|
| 1289 |
+
"loss": 0.581,
|
| 1290 |
+
"step": 183
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 1.7664,
|
| 1294 |
+
"grad_norm": 0.45741593837738037,
|
| 1295 |
+
"learning_rate": 4.3288336709117246e-06,
|
| 1296 |
+
"loss": 0.5404,
|
| 1297 |
+
"step": 184
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 1.776,
|
| 1301 |
+
"grad_norm": 0.4758993685245514,
|
| 1302 |
+
"learning_rate": 4.273284931050438e-06,
|
| 1303 |
+
"loss": 0.5718,
|
| 1304 |
+
"step": 185
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 1.7856,
|
| 1308 |
+
"grad_norm": 0.4522536098957062,
|
| 1309 |
+
"learning_rate": 4.217827674798845e-06,
|
| 1310 |
+
"loss": 0.5726,
|
| 1311 |
+
"step": 186
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 1.7952,
|
| 1315 |
+
"grad_norm": 0.5672460794448853,
|
| 1316 |
+
"learning_rate": 4.162468883476319e-06,
|
| 1317 |
+
"loss": 0.6464,
|
| 1318 |
+
"step": 187
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 1.8048,
|
| 1322 |
+
"grad_norm": 0.4288261830806732,
|
| 1323 |
+
"learning_rate": 4.107215526006818e-06,
|
| 1324 |
+
"loss": 0.5412,
|
| 1325 |
+
"step": 188
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 1.8144,
|
| 1329 |
+
"grad_norm": 0.4769589900970459,
|
| 1330 |
+
"learning_rate": 4.052074558041608e-06,
|
| 1331 |
+
"loss": 0.6142,
|
| 1332 |
+
"step": 189
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 1.8239999999999998,
|
| 1336 |
+
"grad_norm": 0.5145401954650879,
|
| 1337 |
+
"learning_rate": 3.997052921083637e-06,
|
| 1338 |
+
"loss": 0.5725,
|
| 1339 |
+
"step": 190
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 1.8336000000000001,
|
| 1343 |
+
"grad_norm": 0.46486806869506836,
|
| 1344 |
+
"learning_rate": 3.9421575416136866e-06,
|
| 1345 |
+
"loss": 0.621,
|
| 1346 |
+
"step": 191
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 1.8432,
|
| 1350 |
+
"grad_norm": 0.42144760489463806,
|
| 1351 |
+
"learning_rate": 3.887395330218429e-06,
|
| 1352 |
+
"loss": 0.4962,
|
| 1353 |
+
"step": 192
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 1.8528,
|
| 1357 |
+
"grad_norm": 0.5083242654800415,
|
| 1358 |
+
"learning_rate": 3.832773180720475e-06,
|
| 1359 |
+
"loss": 0.6506,
|
| 1360 |
+
"step": 193
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 1.8624,
|
| 1364 |
+
"grad_norm": 0.4573202431201935,
|
| 1365 |
+
"learning_rate": 3.778297969310529e-06,
|
| 1366 |
+
"loss": 0.5586,
|
| 1367 |
+
"step": 194
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 1.8719999999999999,
|
| 1371 |
+
"grad_norm": 0.4502522647380829,
|
| 1372 |
+
"learning_rate": 3.723976553681787e-06,
|
| 1373 |
+
"loss": 0.5363,
|
| 1374 |
+
"step": 195
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 1.8816000000000002,
|
| 1378 |
+
"grad_norm": 0.42463284730911255,
|
| 1379 |
+
"learning_rate": 3.669815772166625e-06,
|
| 1380 |
+
"loss": 0.6078,
|
| 1381 |
+
"step": 196
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 1.8912,
|
| 1385 |
+
"grad_norm": 0.4534298777580261,
|
| 1386 |
+
"learning_rate": 3.6158224428757538e-06,
|
| 1387 |
+
"loss": 0.5645,
|
| 1388 |
+
"step": 197
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 1.9008,
|
| 1392 |
+
"grad_norm": 0.4633239507675171,
|
| 1393 |
+
"learning_rate": 3.562003362839914e-06,
|
| 1394 |
+
"loss": 0.5657,
|
| 1395 |
+
"step": 198
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 1.9104,
|
| 1399 |
+
"grad_norm": 0.4833671450614929,
|
| 1400 |
+
"learning_rate": 3.50836530715422e-06,
|
| 1401 |
+
"loss": 0.5732,
|
| 1402 |
+
"step": 199
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 1.92,
|
| 1406 |
+
"grad_norm": 0.511324942111969,
|
| 1407 |
+
"learning_rate": 3.4549150281252635e-06,
|
| 1408 |
+
"loss": 0.6541,
|
| 1409 |
+
"step": 200
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 1.9296,
|
| 1413 |
+
"grad_norm": 0.41902709007263184,
|
| 1414 |
+
"learning_rate": 3.4016592544210937e-06,
|
| 1415 |
+
"loss": 0.5181,
|
| 1416 |
+
"step": 201
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 1.9392,
|
| 1420 |
+
"grad_norm": 0.49513956904411316,
|
| 1421 |
+
"learning_rate": 3.3486046902241663e-06,
|
| 1422 |
+
"loss": 0.594,
|
| 1423 |
+
"step": 202
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 1.9487999999999999,
|
| 1427 |
+
"grad_norm": 0.4521034359931946,
|
| 1428 |
+
"learning_rate": 3.295758014387375e-06,
|
| 1429 |
+
"loss": 0.5428,
|
| 1430 |
+
"step": 203
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 1.9584000000000001,
|
| 1434 |
+
"grad_norm": 0.48090317845344543,
|
| 1435 |
+
"learning_rate": 3.2431258795932863e-06,
|
| 1436 |
+
"loss": 0.5857,
|
| 1437 |
+
"step": 204
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 1.968,
|
| 1441 |
+
"grad_norm": 0.42190292477607727,
|
| 1442 |
+
"learning_rate": 3.1907149115166403e-06,
|
| 1443 |
+
"loss": 0.5711,
|
| 1444 |
+
"step": 205
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 1.9776,
|
| 1448 |
+
"grad_norm": 0.5230044722557068,
|
| 1449 |
+
"learning_rate": 3.1385317079902743e-06,
|
| 1450 |
+
"loss": 0.5769,
|
| 1451 |
+
"step": 206
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 1.9872,
|
| 1455 |
+
"grad_norm": 0.47211894392967224,
|
| 1456 |
+
"learning_rate": 3.0865828381745515e-06,
|
| 1457 |
+
"loss": 0.596,
|
| 1458 |
+
"step": 207
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 1.9968,
|
| 1462 |
+
"grad_norm": 0.4404360353946686,
|
| 1463 |
+
"learning_rate": 3.0348748417303826e-06,
|
| 1464 |
+
"loss": 0.5447,
|
| 1465 |
+
"step": 208
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 2.0064,
|
| 1469 |
+
"grad_norm": 1.2754789590835571,
|
| 1470 |
+
"learning_rate": 2.9834142279959754e-06,
|
| 1471 |
+
"loss": 1.0076,
|
| 1472 |
+
"step": 209
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 2.016,
|
| 1476 |
+
"grad_norm": 0.445046067237854,
|
| 1477 |
+
"learning_rate": 2.932207475167398e-06,
|
| 1478 |
+
"loss": 0.5325,
|
| 1479 |
+
"step": 210
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 2.0256,
|
| 1483 |
+
"grad_norm": 0.5322118401527405,
|
| 1484 |
+
"learning_rate": 2.8812610294830568e-06,
|
| 1485 |
+
"loss": 0.5812,
|
| 1486 |
+
"step": 211
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 2.0352,
|
| 1490 |
+
"grad_norm": 0.5101974606513977,
|
| 1491 |
+
"learning_rate": 2.83058130441221e-06,
|
| 1492 |
+
"loss": 0.5126,
|
| 1493 |
+
"step": 212
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 2.0448,
|
| 1497 |
+
"grad_norm": 0.469745397567749,
|
| 1498 |
+
"learning_rate": 2.7801746798475905e-06,
|
| 1499 |
+
"loss": 0.5893,
|
| 1500 |
+
"step": 213
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 2.0544,
|
| 1504 |
+
"grad_norm": 0.47024786472320557,
|
| 1505 |
+
"learning_rate": 2.7300475013022666e-06,
|
| 1506 |
+
"loss": 0.5568,
|
| 1507 |
+
"step": 214
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 2.064,
|
| 1511 |
+
"grad_norm": 0.49212148785591125,
|
| 1512 |
+
"learning_rate": 2.6802060791108304e-06,
|
| 1513 |
+
"loss": 0.5738,
|
| 1514 |
+
"step": 215
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 2.0736,
|
| 1518 |
+
"grad_norm": 0.4421893060207367,
|
| 1519 |
+
"learning_rate": 2.6306566876350072e-06,
|
| 1520 |
+
"loss": 0.4556,
|
| 1521 |
+
"step": 216
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 2.0832,
|
| 1525 |
+
"grad_norm": 0.47675591707229614,
|
| 1526 |
+
"learning_rate": 2.5814055644738013e-06,
|
| 1527 |
+
"loss": 0.5503,
|
| 1528 |
+
"step": 217
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 2.0928,
|
| 1532 |
+
"grad_norm": 0.40364202857017517,
|
| 1533 |
+
"learning_rate": 2.532458909678266e-06,
|
| 1534 |
+
"loss": 0.507,
|
| 1535 |
+
"step": 218
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 2.1024,
|
| 1539 |
+
"grad_norm": 0.49315252900123596,
|
| 1540 |
+
"learning_rate": 2.483822884971e-06,
|
| 1541 |
+
"loss": 0.5551,
|
| 1542 |
+
"step": 219
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 2.112,
|
| 1546 |
+
"grad_norm": 0.4763312339782715,
|
| 1547 |
+
"learning_rate": 2.43550361297047e-06,
|
| 1548 |
+
"loss": 0.5125,
|
| 1549 |
+
"step": 220
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 2.1216,
|
| 1553 |
+
"grad_norm": 0.4296324551105499,
|
| 1554 |
+
"learning_rate": 2.387507176420256e-06,
|
| 1555 |
+
"loss": 0.5489,
|
| 1556 |
+
"step": 221
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 2.1312,
|
| 1560 |
+
"grad_norm": 0.4918951690196991,
|
| 1561 |
+
"learning_rate": 2.339839617423318e-06,
|
| 1562 |
+
"loss": 0.5195,
|
| 1563 |
+
"step": 222
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 2.1408,
|
| 1567 |
+
"grad_norm": 0.4372878670692444,
|
| 1568 |
+
"learning_rate": 2.2925069366813718e-06,
|
| 1569 |
+
"loss": 0.5181,
|
| 1570 |
+
"step": 223
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 2.1504,
|
| 1574 |
+
"grad_norm": 0.4088146686553955,
|
| 1575 |
+
"learning_rate": 2.245515092739488e-06,
|
| 1576 |
+
"loss": 0.5357,
|
| 1577 |
+
"step": 224
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 2.16,
|
| 1581 |
+
"grad_norm": 0.43566828966140747,
|
| 1582 |
+
"learning_rate": 2.1988700012359865e-06,
|
| 1583 |
+
"loss": 0.5389,
|
| 1584 |
+
"step": 225
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 2.1696,
|
| 1588 |
+
"grad_norm": 0.4104842245578766,
|
| 1589 |
+
"learning_rate": 2.1525775341577404e-06,
|
| 1590 |
+
"loss": 0.4976,
|
| 1591 |
+
"step": 226
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 2.1792,
|
| 1595 |
+
"grad_norm": 0.41833817958831787,
|
| 1596 |
+
"learning_rate": 2.1066435191009717e-06,
|
| 1597 |
+
"loss": 0.5311,
|
| 1598 |
+
"step": 227
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 2.1888,
|
| 1602 |
+
"grad_norm": 0.40475812554359436,
|
| 1603 |
+
"learning_rate": 2.061073738537635e-06,
|
| 1604 |
+
"loss": 0.5153,
|
| 1605 |
+
"step": 228
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 2.1984,
|
| 1609 |
+
"grad_norm": 0.4294889271259308,
|
| 1610 |
+
"learning_rate": 2.0158739290874822e-06,
|
| 1611 |
+
"loss": 0.5571,
|
| 1612 |
+
"step": 229
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 2.208,
|
| 1616 |
+
"grad_norm": 0.49284547567367554,
|
| 1617 |
+
"learning_rate": 1.971049780795901e-06,
|
| 1618 |
+
"loss": 0.5989,
|
| 1619 |
+
"step": 230
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 2.2176,
|
| 1623 |
+
"grad_norm": 0.3920767307281494,
|
| 1624 |
+
"learning_rate": 1.9266069364176144e-06,
|
| 1625 |
+
"loss": 0.4818,
|
| 1626 |
+
"step": 231
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 2.2272,
|
| 1630 |
+
"grad_norm": 0.4156140089035034,
|
| 1631 |
+
"learning_rate": 1.8825509907063328e-06,
|
| 1632 |
+
"loss": 0.5287,
|
| 1633 |
+
"step": 232
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 2.2368,
|
| 1637 |
+
"grad_norm": 0.4189988672733307,
|
| 1638 |
+
"learning_rate": 1.838887489710452e-06,
|
| 1639 |
+
"loss": 0.5527,
|
| 1640 |
+
"step": 233
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 2.2464,
|
| 1644 |
+
"grad_norm": 0.4066447913646698,
|
| 1645 |
+
"learning_rate": 1.7956219300748796e-06,
|
| 1646 |
+
"loss": 0.4751,
|
| 1647 |
+
"step": 234
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 2.2560000000000002,
|
| 1651 |
+
"grad_norm": 0.394909143447876,
|
| 1652 |
+
"learning_rate": 1.7527597583490825e-06,
|
| 1653 |
+
"loss": 0.5778,
|
| 1654 |
+
"step": 235
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 2.2656,
|
| 1658 |
+
"grad_norm": 0.4090768098831177,
|
| 1659 |
+
"learning_rate": 1.7103063703014372e-06,
|
| 1660 |
+
"loss": 0.5591,
|
| 1661 |
+
"step": 236
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 2.2752,
|
| 1665 |
+
"grad_norm": 0.6263449788093567,
|
| 1666 |
+
"learning_rate": 1.6682671102399806e-06,
|
| 1667 |
+
"loss": 0.5066,
|
| 1668 |
+
"step": 237
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 2.2848,
|
| 1672 |
+
"grad_norm": 0.42953482270240784,
|
| 1673 |
+
"learning_rate": 1.6266472703396286e-06,
|
| 1674 |
+
"loss": 0.5288,
|
| 1675 |
+
"step": 238
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 2.2944,
|
| 1679 |
+
"grad_norm": 0.3976917266845703,
|
| 1680 |
+
"learning_rate": 1.5854520899759656e-06,
|
| 1681 |
+
"loss": 0.5317,
|
| 1682 |
+
"step": 239
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 2.304,
|
| 1686 |
+
"grad_norm": 0.41823217272758484,
|
| 1687 |
+
"learning_rate": 1.544686755065677e-06,
|
| 1688 |
+
"loss": 0.5226,
|
| 1689 |
+
"step": 240
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 2.3136,
|
| 1693 |
+
"grad_norm": 0.42223042249679565,
|
| 1694 |
+
"learning_rate": 1.5043563974137132e-06,
|
| 1695 |
+
"loss": 0.5536,
|
| 1696 |
+
"step": 241
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 2.3232,
|
| 1700 |
+
"grad_norm": 0.42981192469596863,
|
| 1701 |
+
"learning_rate": 1.4644660940672628e-06,
|
| 1702 |
+
"loss": 0.5563,
|
| 1703 |
+
"step": 242
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 2.3327999999999998,
|
| 1707 |
+
"grad_norm": 0.35931915044784546,
|
| 1708 |
+
"learning_rate": 1.4250208666766235e-06,
|
| 1709 |
+
"loss": 0.4857,
|
| 1710 |
+
"step": 243
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 2.3424,
|
| 1714 |
+
"grad_norm": 0.38428106904029846,
|
| 1715 |
+
"learning_rate": 1.3860256808630429e-06,
|
| 1716 |
+
"loss": 0.4783,
|
| 1717 |
+
"step": 244
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 2.352,
|
| 1721 |
+
"grad_norm": 0.4292716085910797,
|
| 1722 |
+
"learning_rate": 1.3474854455936126e-06,
|
| 1723 |
+
"loss": 0.5553,
|
| 1724 |
+
"step": 245
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 2.3616,
|
| 1728 |
+
"grad_norm": 0.4062524437904358,
|
| 1729 |
+
"learning_rate": 1.3094050125632973e-06,
|
| 1730 |
+
"loss": 0.5389,
|
| 1731 |
+
"step": 246
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 2.3712,
|
| 1735 |
+
"grad_norm": 0.3885515630245209,
|
| 1736 |
+
"learning_rate": 1.2717891755841722e-06,
|
| 1737 |
+
"loss": 0.4804,
|
| 1738 |
+
"step": 247
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 2.3808,
|
| 1742 |
+
"grad_norm": 0.4065932035446167,
|
| 1743 |
+
"learning_rate": 1.234642669981946e-06,
|
| 1744 |
+
"loss": 0.5717,
|
| 1745 |
+
"step": 248
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 2.3904,
|
| 1749 |
+
"grad_norm": 0.38877761363983154,
|
| 1750 |
+
"learning_rate": 1.1979701719998454e-06,
|
| 1751 |
+
"loss": 0.5226,
|
| 1752 |
+
"step": 249
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 2.4,
|
| 1756 |
+
"grad_norm": 0.40351080894470215,
|
| 1757 |
+
"learning_rate": 1.1617762982099446e-06,
|
| 1758 |
+
"loss": 0.5395,
|
| 1759 |
+
"step": 250
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 2.4096,
|
| 1763 |
+
"grad_norm": 0.37985244393348694,
|
| 1764 |
+
"learning_rate": 1.1260656049319957e-06,
|
| 1765 |
+
"loss": 0.509,
|
| 1766 |
+
"step": 251
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 2.4192,
|
| 1770 |
+
"grad_norm": 0.43029841780662537,
|
| 1771 |
+
"learning_rate": 1.0908425876598512e-06,
|
| 1772 |
+
"loss": 0.5682,
|
| 1773 |
+
"step": 252
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 2.4288,
|
| 1777 |
+
"grad_norm": 0.40593045949935913,
|
| 1778 |
+
"learning_rate": 1.0561116804955451e-06,
|
| 1779 |
+
"loss": 0.5389,
|
| 1780 |
+
"step": 253
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 2.4384,
|
| 1784 |
+
"grad_norm": 0.36474233865737915,
|
| 1785 |
+
"learning_rate": 1.0218772555910955e-06,
|
| 1786 |
+
"loss": 0.4982,
|
| 1787 |
+
"step": 254
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 2.448,
|
| 1791 |
+
"grad_norm": 0.4089374840259552,
|
| 1792 |
+
"learning_rate": 9.881436225981107e-07,
|
| 1793 |
+
"loss": 0.5787,
|
| 1794 |
+
"step": 255
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 2.4576000000000002,
|
| 1798 |
+
"grad_norm": 0.36549311876296997,
|
| 1799 |
+
"learning_rate": 9.549150281252633e-07,
|
| 1800 |
+
"loss": 0.4473,
|
| 1801 |
+
"step": 256
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 2.4672,
|
| 1805 |
+
"grad_norm": 0.41079387068748474,
|
| 1806 |
+
"learning_rate": 9.221956552036992e-07,
|
| 1807 |
+
"loss": 0.5655,
|
| 1808 |
+
"step": 257
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 2.4768,
|
| 1812 |
+
"grad_norm": 0.4164627194404602,
|
| 1813 |
+
"learning_rate": 8.899896227604509e-07,
|
| 1814 |
+
"loss": 0.5304,
|
| 1815 |
+
"step": 258
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 2.4864,
|
| 1819 |
+
"grad_norm": 0.42988118529319763,
|
| 1820 |
+
"learning_rate": 8.58300985099918e-07,
|
| 1821 |
+
"loss": 0.5282,
|
| 1822 |
+
"step": 259
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 2.496,
|
| 1826 |
+
"grad_norm": 0.4137679934501648,
|
| 1827 |
+
"learning_rate": 8.271337313934869e-07,
|
| 1828 |
+
"loss": 0.5628,
|
| 1829 |
+
"step": 260
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 2.5056000000000003,
|
| 1833 |
+
"grad_norm": 0.3814125657081604,
|
| 1834 |
+
"learning_rate": 7.964917851773496e-07,
|
| 1835 |
+
"loss": 0.5245,
|
| 1836 |
+
"step": 261
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 2.5152,
|
| 1840 |
+
"grad_norm": 0.38825955986976624,
|
| 1841 |
+
"learning_rate": 7.663790038585794e-07,
|
| 1842 |
+
"loss": 0.4994,
|
| 1843 |
+
"step": 262
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 2.5248,
|
| 1847 |
+
"grad_norm": 0.4235158860683441,
|
| 1848 |
+
"learning_rate": 7.367991782295392e-07,
|
| 1849 |
+
"loss": 0.5233,
|
| 1850 |
+
"step": 263
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 2.5343999999999998,
|
| 1854 |
+
"grad_norm": 0.4122079908847809,
|
| 1855 |
+
"learning_rate": 7.077560319906696e-07,
|
| 1856 |
+
"loss": 0.5305,
|
| 1857 |
+
"step": 264
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 2.544,
|
| 1861 |
+
"grad_norm": 0.38463661074638367,
|
| 1862 |
+
"learning_rate": 6.792532212817271e-07,
|
| 1863 |
+
"loss": 0.5075,
|
| 1864 |
+
"step": 265
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 2.5536,
|
| 1868 |
+
"grad_norm": 0.46616417169570923,
|
| 1869 |
+
"learning_rate": 6.512943342215234e-07,
|
| 1870 |
+
"loss": 0.5858,
|
| 1871 |
+
"step": 266
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 2.5632,
|
| 1875 |
+
"grad_norm": 0.3797391653060913,
|
| 1876 |
+
"learning_rate": 6.238828904562316e-07,
|
| 1877 |
+
"loss": 0.5053,
|
| 1878 |
+
"step": 267
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 2.5728,
|
| 1882 |
+
"grad_norm": 0.40550941228866577,
|
| 1883 |
+
"learning_rate": 5.9702234071631e-07,
|
| 1884 |
+
"loss": 0.5295,
|
| 1885 |
+
"step": 268
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 2.5824,
|
| 1889 |
+
"grad_norm": 0.3795751929283142,
|
| 1890 |
+
"learning_rate": 5.707160663821009e-07,
|
| 1891 |
+
"loss": 0.5053,
|
| 1892 |
+
"step": 269
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 2.592,
|
| 1896 |
+
"grad_norm": 0.38254594802856445,
|
| 1897 |
+
"learning_rate": 5.449673790581611e-07,
|
| 1898 |
+
"loss": 0.5196,
|
| 1899 |
+
"step": 270
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 2.6016,
|
| 1903 |
+
"grad_norm": 0.4230276644229889,
|
| 1904 |
+
"learning_rate": 5.197795201563744e-07,
|
| 1905 |
+
"loss": 0.5181,
|
| 1906 |
+
"step": 271
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 2.6112,
|
| 1910 |
+
"grad_norm": 0.39369747042655945,
|
| 1911 |
+
"learning_rate": 4.951556604879049e-07,
|
| 1912 |
+
"loss": 0.5888,
|
| 1913 |
+
"step": 272
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 2.6208,
|
| 1917 |
+
"grad_norm": 0.3621313273906708,
|
| 1918 |
+
"learning_rate": 4.710988998640298e-07,
|
| 1919 |
+
"loss": 0.5424,
|
| 1920 |
+
"step": 273
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 2.6304,
|
| 1924 |
+
"grad_norm": 0.3762126564979553,
|
| 1925 |
+
"learning_rate": 4.4761226670592074e-07,
|
| 1926 |
+
"loss": 0.5004,
|
| 1927 |
+
"step": 274
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 2.64,
|
| 1931 |
+
"grad_norm": 0.3839513957500458,
|
| 1932 |
+
"learning_rate": 4.2469871766340096e-07,
|
| 1933 |
+
"loss": 0.5305,
|
| 1934 |
+
"step": 275
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 2.6496,
|
| 1938 |
+
"grad_norm": 0.40465694665908813,
|
| 1939 |
+
"learning_rate": 4.0236113724274716e-07,
|
| 1940 |
+
"loss": 0.5355,
|
| 1941 |
+
"step": 276
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 2.6592000000000002,
|
| 1945 |
+
"grad_norm": 0.41210877895355225,
|
| 1946 |
+
"learning_rate": 3.8060233744356634e-07,
|
| 1947 |
+
"loss": 0.5671,
|
| 1948 |
+
"step": 277
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 2.6688,
|
| 1952 |
+
"grad_norm": 0.3980127274990082,
|
| 1953 |
+
"learning_rate": 3.5942505740480583e-07,
|
| 1954 |
+
"loss": 0.5108,
|
| 1955 |
+
"step": 278
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 2.6784,
|
| 1959 |
+
"grad_norm": 0.4046895503997803,
|
| 1960 |
+
"learning_rate": 3.3883196305992906e-07,
|
| 1961 |
+
"loss": 0.5229,
|
| 1962 |
+
"step": 279
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 2.6879999999999997,
|
| 1966 |
+
"grad_norm": 0.38082319498062134,
|
| 1967 |
+
"learning_rate": 3.18825646801314e-07,
|
| 1968 |
+
"loss": 0.5244,
|
| 1969 |
+
"step": 280
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 2.6976,
|
| 1973 |
+
"grad_norm": 0.4220086336135864,
|
| 1974 |
+
"learning_rate": 2.9940862715390483e-07,
|
| 1975 |
+
"loss": 0.5123,
|
| 1976 |
+
"step": 281
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 2.7072000000000003,
|
| 1980 |
+
"grad_norm": 0.4062383472919464,
|
| 1981 |
+
"learning_rate": 2.8058334845816214e-07,
|
| 1982 |
+
"loss": 0.5092,
|
| 1983 |
+
"step": 282
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 2.7168,
|
| 1987 |
+
"grad_norm": 0.386997252702713,
|
| 1988 |
+
"learning_rate": 2.6235218056235633e-07,
|
| 1989 |
+
"loss": 0.5442,
|
| 1990 |
+
"step": 283
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 2.7264,
|
| 1994 |
+
"grad_norm": 0.39148667454719543,
|
| 1995 |
+
"learning_rate": 2.447174185242324e-07,
|
| 1996 |
+
"loss": 0.5711,
|
| 1997 |
+
"step": 284
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 2.7359999999999998,
|
| 2001 |
+
"grad_norm": 0.37360548973083496,
|
| 2002 |
+
"learning_rate": 2.276812823220964e-07,
|
| 2003 |
+
"loss": 0.5,
|
| 2004 |
+
"step": 285
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 2.7456,
|
| 2008 |
+
"grad_norm": 0.39551421999931335,
|
| 2009 |
+
"learning_rate": 2.1124591657534776e-07,
|
| 2010 |
+
"loss": 0.5256,
|
| 2011 |
+
"step": 286
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 2.7552,
|
| 2015 |
+
"grad_norm": 0.3795803487300873,
|
| 2016 |
+
"learning_rate": 1.9541339027450256e-07,
|
| 2017 |
+
"loss": 0.5371,
|
| 2018 |
+
"step": 287
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 2.7648,
|
| 2022 |
+
"grad_norm": 0.3761843740940094,
|
| 2023 |
+
"learning_rate": 1.801856965207338e-07,
|
| 2024 |
+
"loss": 0.5725,
|
| 2025 |
+
"step": 288
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 2.7744,
|
| 2029 |
+
"grad_norm": 0.3336462676525116,
|
| 2030 |
+
"learning_rate": 1.6556475227496816e-07,
|
| 2031 |
+
"loss": 0.4762,
|
| 2032 |
+
"step": 289
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 2.784,
|
| 2036 |
+
"grad_norm": 0.3762846887111664,
|
| 2037 |
+
"learning_rate": 1.5155239811656562e-07,
|
| 2038 |
+
"loss": 0.5404,
|
| 2039 |
+
"step": 290
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 2.7936,
|
| 2043 |
+
"grad_norm": 0.3734802305698395,
|
| 2044 |
+
"learning_rate": 1.3815039801161723e-07,
|
| 2045 |
+
"loss": 0.5515,
|
| 2046 |
+
"step": 291
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 2.8032,
|
| 2050 |
+
"grad_norm": 0.3967645466327667,
|
| 2051 |
+
"learning_rate": 1.253604390908819e-07,
|
| 2052 |
+
"loss": 0.5259,
|
| 2053 |
+
"step": 292
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 2.8128,
|
| 2057 |
+
"grad_norm": 0.3874190151691437,
|
| 2058 |
+
"learning_rate": 1.1318413143740436e-07,
|
| 2059 |
+
"loss": 0.5366,
|
| 2060 |
+
"step": 293
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 2.8224,
|
| 2064 |
+
"grad_norm": 0.36908280849456787,
|
| 2065 |
+
"learning_rate": 1.0162300788382263e-07,
|
| 2066 |
+
"loss": 0.5674,
|
| 2067 |
+
"step": 294
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 2.832,
|
| 2071 |
+
"grad_norm": 0.34430015087127686,
|
| 2072 |
+
"learning_rate": 9.0678523819408e-08,
|
| 2073 |
+
"loss": 0.4563,
|
| 2074 |
+
"step": 295
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 2.8416,
|
| 2078 |
+
"grad_norm": 0.4032260775566101,
|
| 2079 |
+
"learning_rate": 8.035205700685167e-08,
|
| 2080 |
+
"loss": 0.5201,
|
| 2081 |
+
"step": 296
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 2.8512,
|
| 2085 |
+
"grad_norm": 0.385893315076828,
|
| 2086 |
+
"learning_rate": 7.064490740882057e-08,
|
| 2087 |
+
"loss": 0.574,
|
| 2088 |
+
"step": 297
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 2.8608000000000002,
|
| 2092 |
+
"grad_norm": 0.3859463930130005,
|
| 2093 |
+
"learning_rate": 6.15582970243117e-08,
|
| 2094 |
+
"loss": 0.5587,
|
| 2095 |
+
"step": 298
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 2.8704,
|
| 2099 |
+
"grad_norm": 0.35366320610046387,
|
| 2100 |
+
"learning_rate": 5.3093369734816824e-08,
|
| 2101 |
+
"loss": 0.4771,
|
| 2102 |
+
"step": 299
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 2.88,
|
| 2106 |
+
"grad_norm": 0.35460808873176575,
|
| 2107 |
+
"learning_rate": 4.52511911603265e-08,
|
| 2108 |
+
"loss": 0.5471,
|
| 2109 |
+
"step": 300
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 2.8895999999999997,
|
| 2113 |
+
"grad_norm": 0.36865419149398804,
|
| 2114 |
+
"learning_rate": 3.8032748525179684e-08,
|
| 2115 |
+
"loss": 0.5279,
|
| 2116 |
+
"step": 301
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 2.8992,
|
| 2120 |
+
"grad_norm": 0.39643099904060364,
|
| 2121 |
+
"learning_rate": 3.143895053378698e-08,
|
| 2122 |
+
"loss": 0.5488,
|
| 2123 |
+
"step": 302
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 2.9088000000000003,
|
| 2127 |
+
"grad_norm": 0.3732302486896515,
|
| 2128 |
+
"learning_rate": 2.547062725623828e-08,
|
| 2129 |
+
"loss": 0.5458,
|
| 2130 |
+
"step": 303
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 2.9184,
|
| 2134 |
+
"grad_norm": 0.34452953934669495,
|
| 2135 |
+
"learning_rate": 2.012853002380466e-08,
|
| 2136 |
+
"loss": 0.4718,
|
| 2137 |
+
"step": 304
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 2.928,
|
| 2141 |
+
"grad_norm": 0.3710247278213501,
|
| 2142 |
+
"learning_rate": 1.541333133436018e-08,
|
| 2143 |
+
"loss": 0.552,
|
| 2144 |
+
"step": 305
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 2.9375999999999998,
|
| 2148 |
+
"grad_norm": 0.3867627680301666,
|
| 2149 |
+
"learning_rate": 1.132562476771959e-08,
|
| 2150 |
+
"loss": 0.5287,
|
| 2151 |
+
"step": 306
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 2.9472,
|
| 2155 |
+
"grad_norm": 0.36105963587760925,
|
| 2156 |
+
"learning_rate": 7.865924910916977e-09,
|
| 2157 |
+
"loss": 0.4764,
|
| 2158 |
+
"step": 307
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 2.9568,
|
| 2162 |
+
"grad_norm": 0.42076411843299866,
|
| 2163 |
+
"learning_rate": 5.034667293427053e-09,
|
| 2164 |
+
"loss": 0.5559,
|
| 2165 |
+
"step": 308
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 2.9664,
|
| 2169 |
+
"grad_norm": 0.34399110078811646,
|
| 2170 |
+
"learning_rate": 2.8322083323334417e-09,
|
| 2171 |
+
"loss": 0.4897,
|
| 2172 |
+
"step": 309
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 2.976,
|
| 2176 |
+
"grad_norm": 0.36756882071495056,
|
| 2177 |
+
"learning_rate": 1.2588252874673469e-09,
|
| 2178 |
+
"loss": 0.5773,
|
| 2179 |
+
"step": 310
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 2.9856,
|
| 2183 |
+
"grad_norm": 0.3748956024646759,
|
| 2184 |
+
"learning_rate": 3.147162264971471e-10,
|
| 2185 |
+
"loss": 0.5365,
|
| 2186 |
+
"step": 311
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 2.9952,
|
| 2190 |
+
"grad_norm": 0.3594142496585846,
|
| 2191 |
+
"learning_rate": 0.0,
|
| 2192 |
+
"loss": 0.5758,
|
| 2193 |
+
"step": 312
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 2.9952,
|
| 2197 |
+
"step": 312,
|
| 2198 |
+
"total_flos": 312970832904192.0,
|
| 2199 |
+
"train_loss": 0.610789420035405,
|
| 2200 |
+
"train_runtime": 29538.0563,
|
| 2201 |
+
"train_samples_per_second": 1.016,
|
| 2202 |
+
"train_steps_per_second": 0.011
|
| 2203 |
+
}
|
| 2204 |
+
],
|
| 2205 |
+
"logging_steps": 1.0,
|
| 2206 |
+
"max_steps": 312,
|
| 2207 |
+
"num_input_tokens_seen": 0,
|
| 2208 |
+
"num_train_epochs": 3,
|
| 2209 |
+
"save_steps": 500,
|
| 2210 |
+
"stateful_callbacks": {
|
| 2211 |
+
"TrainerControl": {
|
| 2212 |
+
"args": {
|
| 2213 |
+
"should_epoch_stop": false,
|
| 2214 |
+
"should_evaluate": false,
|
| 2215 |
+
"should_log": false,
|
| 2216 |
+
"should_save": true,
|
| 2217 |
+
"should_training_stop": true
|
| 2218 |
+
},
|
| 2219 |
+
"attributes": {}
|
| 2220 |
+
}
|
| 2221 |
+
},
|
| 2222 |
+
"total_flos": 312970832904192.0,
|
| 2223 |
+
"train_batch_size": 1,
|
| 2224 |
+
"trial_name": null,
|
| 2225 |
+
"trial_params": null
|
| 2226 |
+
}
|
training_loss.png
ADDED
|