End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +1785 -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: qwen2-5_code_ablate_duplications_1
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# qwen2-5_code_ablate_duplications_1
|
| 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: qwen2-5_code_ablate_duplications_1
|
|
|
|
| 16 |
|
| 17 |
# qwen2-5_code_ablate_duplications_1
|
| 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/code_ablate_duplications_1 dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 210646484844544.0,
|
| 4 |
+
"train_loss": 0.6536134277960383,
|
| 5 |
+
"train_runtime": 3799.3108,
|
| 6 |
+
"train_samples_per_second": 6.269,
|
| 7 |
+
"train_steps_per_second": 0.066
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 210646484844544.0,
|
| 4 |
+
"train_loss": 0.6536134277960383,
|
| 5 |
+
"train_runtime": 3799.3108,
|
| 6 |
+
"train_samples_per_second": 6.269,
|
| 7 |
+
"train_steps_per_second": 0.066
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1785 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 249,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.012048192771084338,
|
| 13 |
+
"grad_norm": 6.947944879111486,
|
| 14 |
+
"learning_rate": 4.0000000000000003e-07,
|
| 15 |
+
"loss": 1.1152,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.024096385542168676,
|
| 20 |
+
"grad_norm": 6.551895316152613,
|
| 21 |
+
"learning_rate": 8.000000000000001e-07,
|
| 22 |
+
"loss": 1.0964,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03614457831325301,
|
| 27 |
+
"grad_norm": 6.846850714143195,
|
| 28 |
+
"learning_rate": 1.2000000000000002e-06,
|
| 29 |
+
"loss": 1.1132,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.04819277108433735,
|
| 34 |
+
"grad_norm": 6.73500827774856,
|
| 35 |
+
"learning_rate": 1.6000000000000001e-06,
|
| 36 |
+
"loss": 1.1177,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.060240963855421686,
|
| 41 |
+
"grad_norm": 6.486042838258102,
|
| 42 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 43 |
+
"loss": 1.1165,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.07228915662650602,
|
| 48 |
+
"grad_norm": 5.080164944992832,
|
| 49 |
+
"learning_rate": 2.4000000000000003e-06,
|
| 50 |
+
"loss": 1.0333,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.08433734939759036,
|
| 55 |
+
"grad_norm": 4.8162640470965545,
|
| 56 |
+
"learning_rate": 2.8000000000000003e-06,
|
| 57 |
+
"loss": 1.0607,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.0963855421686747,
|
| 62 |
+
"grad_norm": 2.9636266881255633,
|
| 63 |
+
"learning_rate": 3.2000000000000003e-06,
|
| 64 |
+
"loss": 0.995,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.10843373493975904,
|
| 69 |
+
"grad_norm": 2.9149441840060883,
|
| 70 |
+
"learning_rate": 3.6000000000000003e-06,
|
| 71 |
+
"loss": 0.9953,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.12048192771084337,
|
| 76 |
+
"grad_norm": 2.5104086655988858,
|
| 77 |
+
"learning_rate": 4.000000000000001e-06,
|
| 78 |
+
"loss": 0.9657,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.13253012048192772,
|
| 83 |
+
"grad_norm": 3.3748794057111042,
|
| 84 |
+
"learning_rate": 4.4e-06,
|
| 85 |
+
"loss": 0.9279,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.14457831325301204,
|
| 90 |
+
"grad_norm": 3.739579521016211,
|
| 91 |
+
"learning_rate": 4.800000000000001e-06,
|
| 92 |
+
"loss": 0.9651,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.1566265060240964,
|
| 97 |
+
"grad_norm": 3.3881771742497793,
|
| 98 |
+
"learning_rate": 5.2e-06,
|
| 99 |
+
"loss": 0.945,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.1686746987951807,
|
| 104 |
+
"grad_norm": 2.710732348285535,
|
| 105 |
+
"learning_rate": 5.600000000000001e-06,
|
| 106 |
+
"loss": 0.9118,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.18072289156626506,
|
| 111 |
+
"grad_norm": 2.5647590385181345,
|
| 112 |
+
"learning_rate": 6e-06,
|
| 113 |
+
"loss": 0.8692,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.1927710843373494,
|
| 118 |
+
"grad_norm": 2.4867313006793017,
|
| 119 |
+
"learning_rate": 6.4000000000000006e-06,
|
| 120 |
+
"loss": 0.8708,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.20481927710843373,
|
| 125 |
+
"grad_norm": 2.1051348582551803,
|
| 126 |
+
"learning_rate": 6.800000000000001e-06,
|
| 127 |
+
"loss": 0.8491,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.21686746987951808,
|
| 132 |
+
"grad_norm": 1.612401197421157,
|
| 133 |
+
"learning_rate": 7.2000000000000005e-06,
|
| 134 |
+
"loss": 0.8337,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.2289156626506024,
|
| 139 |
+
"grad_norm": 1.3293177079518312,
|
| 140 |
+
"learning_rate": 7.600000000000001e-06,
|
| 141 |
+
"loss": 0.835,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.24096385542168675,
|
| 146 |
+
"grad_norm": 1.5157822774844878,
|
| 147 |
+
"learning_rate": 8.000000000000001e-06,
|
| 148 |
+
"loss": 0.8007,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.25301204819277107,
|
| 153 |
+
"grad_norm": 1.737006171655161,
|
| 154 |
+
"learning_rate": 8.400000000000001e-06,
|
| 155 |
+
"loss": 0.8012,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.26506024096385544,
|
| 160 |
+
"grad_norm": 1.500594706792283,
|
| 161 |
+
"learning_rate": 8.8e-06,
|
| 162 |
+
"loss": 0.8001,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.27710843373493976,
|
| 167 |
+
"grad_norm": 1.1039643208102183,
|
| 168 |
+
"learning_rate": 9.200000000000002e-06,
|
| 169 |
+
"loss": 0.7822,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.2891566265060241,
|
| 174 |
+
"grad_norm": 1.0368896326465078,
|
| 175 |
+
"learning_rate": 9.600000000000001e-06,
|
| 176 |
+
"loss": 0.793,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.30120481927710846,
|
| 181 |
+
"grad_norm": 1.218355881230325,
|
| 182 |
+
"learning_rate": 1e-05,
|
| 183 |
+
"loss": 0.7781,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.3132530120481928,
|
| 188 |
+
"grad_norm": 1.038423389608468,
|
| 189 |
+
"learning_rate": 9.999508258797876e-06,
|
| 190 |
+
"loss": 0.7701,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.3253012048192771,
|
| 195 |
+
"grad_norm": 0.9316952575939548,
|
| 196 |
+
"learning_rate": 9.998033131915266e-06,
|
| 197 |
+
"loss": 0.7603,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.3373493975903614,
|
| 202 |
+
"grad_norm": 0.9000603093167511,
|
| 203 |
+
"learning_rate": 9.995574909504434e-06,
|
| 204 |
+
"loss": 0.741,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.3493975903614458,
|
| 209 |
+
"grad_norm": 0.930556207735138,
|
| 210 |
+
"learning_rate": 9.992134075089085e-06,
|
| 211 |
+
"loss": 0.7611,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.3614457831325301,
|
| 216 |
+
"grad_norm": 0.8969974980816755,
|
| 217 |
+
"learning_rate": 9.987711305469232e-06,
|
| 218 |
+
"loss": 0.7476,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.37349397590361444,
|
| 223 |
+
"grad_norm": 0.8890052593019384,
|
| 224 |
+
"learning_rate": 9.982307470588097e-06,
|
| 225 |
+
"loss": 0.7457,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.3855421686746988,
|
| 230 |
+
"grad_norm": 0.820863872004277,
|
| 231 |
+
"learning_rate": 9.975923633360985e-06,
|
| 232 |
+
"loss": 0.7755,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.39759036144578314,
|
| 237 |
+
"grad_norm": 0.9969711327635771,
|
| 238 |
+
"learning_rate": 9.968561049466214e-06,
|
| 239 |
+
"loss": 0.7392,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.40963855421686746,
|
| 244 |
+
"grad_norm": 0.7953930725873727,
|
| 245 |
+
"learning_rate": 9.960221167098124e-06,
|
| 246 |
+
"loss": 0.7249,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.42168674698795183,
|
| 251 |
+
"grad_norm": 0.8098618143284958,
|
| 252 |
+
"learning_rate": 9.950905626682229e-06,
|
| 253 |
+
"loss": 0.727,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.43373493975903615,
|
| 258 |
+
"grad_norm": 0.9495875679755755,
|
| 259 |
+
"learning_rate": 9.940616260552545e-06,
|
| 260 |
+
"loss": 0.7462,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.4457831325301205,
|
| 265 |
+
"grad_norm": 0.8278336434334101,
|
| 266 |
+
"learning_rate": 9.92935509259118e-06,
|
| 267 |
+
"loss": 0.7159,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.4578313253012048,
|
| 272 |
+
"grad_norm": 0.9212979365231454,
|
| 273 |
+
"learning_rate": 9.917124337830242e-06,
|
| 274 |
+
"loss": 0.7421,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.46987951807228917,
|
| 279 |
+
"grad_norm": 0.7883588253738649,
|
| 280 |
+
"learning_rate": 9.903926402016153e-06,
|
| 281 |
+
"loss": 0.7394,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.4819277108433735,
|
| 286 |
+
"grad_norm": 0.8135336025707903,
|
| 287 |
+
"learning_rate": 9.889763881136439e-06,
|
| 288 |
+
"loss": 0.7407,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.4939759036144578,
|
| 293 |
+
"grad_norm": 0.7284360537696872,
|
| 294 |
+
"learning_rate": 9.874639560909118e-06,
|
| 295 |
+
"loss": 0.723,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.5060240963855421,
|
| 300 |
+
"grad_norm": 0.6886889463442112,
|
| 301 |
+
"learning_rate": 9.858556416234755e-06,
|
| 302 |
+
"loss": 0.7055,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.5180722891566265,
|
| 307 |
+
"grad_norm": 0.7199574327858913,
|
| 308 |
+
"learning_rate": 9.841517610611309e-06,
|
| 309 |
+
"loss": 0.712,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.5301204819277109,
|
| 314 |
+
"grad_norm": 0.6147988317749675,
|
| 315 |
+
"learning_rate": 9.82352649551188e-06,
|
| 316 |
+
"loss": 0.7027,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.5421686746987951,
|
| 321 |
+
"grad_norm": 0.6882015749480584,
|
| 322 |
+
"learning_rate": 9.804586609725499e-06,
|
| 323 |
+
"loss": 0.7121,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.5542168674698795,
|
| 328 |
+
"grad_norm": 0.7280391155676497,
|
| 329 |
+
"learning_rate": 9.784701678661045e-06,
|
| 330 |
+
"loss": 0.716,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.5662650602409639,
|
| 335 |
+
"grad_norm": 0.7124213849751071,
|
| 336 |
+
"learning_rate": 9.763875613614482e-06,
|
| 337 |
+
"loss": 0.722,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.5783132530120482,
|
| 342 |
+
"grad_norm": 0.6593949739833803,
|
| 343 |
+
"learning_rate": 9.742112510999516e-06,
|
| 344 |
+
"loss": 0.7156,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.5903614457831325,
|
| 349 |
+
"grad_norm": 0.7348578544816223,
|
| 350 |
+
"learning_rate": 9.719416651541839e-06,
|
| 351 |
+
"loss": 0.7048,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.6024096385542169,
|
| 356 |
+
"grad_norm": 0.594788013806163,
|
| 357 |
+
"learning_rate": 9.69579249943714e-06,
|
| 358 |
+
"loss": 0.7199,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.6144578313253012,
|
| 363 |
+
"grad_norm": 0.7714227830284002,
|
| 364 |
+
"learning_rate": 9.671244701472999e-06,
|
| 365 |
+
"loss": 0.7161,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.6265060240963856,
|
| 370 |
+
"grad_norm": 0.7134932535970153,
|
| 371 |
+
"learning_rate": 9.645778086114892e-06,
|
| 372 |
+
"loss": 0.7172,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.6385542168674698,
|
| 377 |
+
"grad_norm": 0.6348354665227139,
|
| 378 |
+
"learning_rate": 9.619397662556434e-06,
|
| 379 |
+
"loss": 0.7122,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.6506024096385542,
|
| 384 |
+
"grad_norm": 0.6536014485282127,
|
| 385 |
+
"learning_rate": 9.592108619734107e-06,
|
| 386 |
+
"loss": 0.7228,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.6626506024096386,
|
| 391 |
+
"grad_norm": 0.6639976309067293,
|
| 392 |
+
"learning_rate": 9.563916325306595e-06,
|
| 393 |
+
"loss": 0.7039,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.6746987951807228,
|
| 398 |
+
"grad_norm": 0.6055507064587089,
|
| 399 |
+
"learning_rate": 9.534826324599002e-06,
|
| 400 |
+
"loss": 0.7009,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.6867469879518072,
|
| 405 |
+
"grad_norm": 0.7156208118389876,
|
| 406 |
+
"learning_rate": 9.504844339512096e-06,
|
| 407 |
+
"loss": 0.7112,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.6987951807228916,
|
| 412 |
+
"grad_norm": 0.6794191467333306,
|
| 413 |
+
"learning_rate": 9.473976267396831e-06,
|
| 414 |
+
"loss": 0.7054,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.7108433734939759,
|
| 419 |
+
"grad_norm": 0.6294077710372372,
|
| 420 |
+
"learning_rate": 9.442228179894362e-06,
|
| 421 |
+
"loss": 0.688,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.7228915662650602,
|
| 426 |
+
"grad_norm": 0.7964098018273663,
|
| 427 |
+
"learning_rate": 9.409606321741776e-06,
|
| 428 |
+
"loss": 0.7157,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.7349397590361446,
|
| 433 |
+
"grad_norm": 0.761322211412714,
|
| 434 |
+
"learning_rate": 9.376117109543769e-06,
|
| 435 |
+
"loss": 0.7015,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.7469879518072289,
|
| 440 |
+
"grad_norm": 0.6726658910004847,
|
| 441 |
+
"learning_rate": 9.341767130510529e-06,
|
| 442 |
+
"loss": 0.7093,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.7590361445783133,
|
| 447 |
+
"grad_norm": 0.7082226196205085,
|
| 448 |
+
"learning_rate": 9.306563141162046e-06,
|
| 449 |
+
"loss": 0.7068,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.7710843373493976,
|
| 454 |
+
"grad_norm": 0.7585930321127647,
|
| 455 |
+
"learning_rate": 9.270512065999139e-06,
|
| 456 |
+
"loss": 0.7223,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.7831325301204819,
|
| 461 |
+
"grad_norm": 0.6610590499726324,
|
| 462 |
+
"learning_rate": 9.233620996141421e-06,
|
| 463 |
+
"loss": 0.6997,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.7951807228915663,
|
| 468 |
+
"grad_norm": 0.6097126115460089,
|
| 469 |
+
"learning_rate": 9.195897187932513e-06,
|
| 470 |
+
"loss": 0.688,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.8072289156626506,
|
| 475 |
+
"grad_norm": 0.8193590896973392,
|
| 476 |
+
"learning_rate": 9.157348061512728e-06,
|
| 477 |
+
"loss": 0.6937,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.8192771084337349,
|
| 482 |
+
"grad_norm": 0.6636823955768107,
|
| 483 |
+
"learning_rate": 9.117981199359575e-06,
|
| 484 |
+
"loss": 0.7165,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.8313253012048193,
|
| 489 |
+
"grad_norm": 0.6320173996309013,
|
| 490 |
+
"learning_rate": 9.077804344796302e-06,
|
| 491 |
+
"loss": 0.7119,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.8433734939759037,
|
| 496 |
+
"grad_norm": 0.6144715713587066,
|
| 497 |
+
"learning_rate": 9.036825400468814e-06,
|
| 498 |
+
"loss": 0.6931,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.8554216867469879,
|
| 503 |
+
"grad_norm": 0.7395636253139917,
|
| 504 |
+
"learning_rate": 8.995052426791247e-06,
|
| 505 |
+
"loss": 0.6875,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.8674698795180723,
|
| 510 |
+
"grad_norm": 0.5930149191622746,
|
| 511 |
+
"learning_rate": 8.952493640360518e-06,
|
| 512 |
+
"loss": 0.6937,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.8795180722891566,
|
| 517 |
+
"grad_norm": 0.6740822123365926,
|
| 518 |
+
"learning_rate": 8.90915741234015e-06,
|
| 519 |
+
"loss": 0.6956,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.891566265060241,
|
| 524 |
+
"grad_norm": 0.6734900730110069,
|
| 525 |
+
"learning_rate": 8.865052266813686e-06,
|
| 526 |
+
"loss": 0.6908,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.9036144578313253,
|
| 531 |
+
"grad_norm": 0.6324954721691614,
|
| 532 |
+
"learning_rate": 8.820186879108038e-06,
|
| 533 |
+
"loss": 0.6879,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.9156626506024096,
|
| 538 |
+
"grad_norm": 0.5728199230507313,
|
| 539 |
+
"learning_rate": 8.77457007408708e-06,
|
| 540 |
+
"loss": 0.6805,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.927710843373494,
|
| 545 |
+
"grad_norm": 0.624518773096375,
|
| 546 |
+
"learning_rate": 8.728210824415829e-06,
|
| 547 |
+
"loss": 0.7028,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.9397590361445783,
|
| 552 |
+
"grad_norm": 0.71821618407165,
|
| 553 |
+
"learning_rate": 8.681118248795548e-06,
|
| 554 |
+
"loss": 0.7087,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.9518072289156626,
|
| 559 |
+
"grad_norm": 0.5810521850331176,
|
| 560 |
+
"learning_rate": 8.633301610170136e-06,
|
| 561 |
+
"loss": 0.6973,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.963855421686747,
|
| 566 |
+
"grad_norm": 0.520059051210702,
|
| 567 |
+
"learning_rate": 8.584770313904138e-06,
|
| 568 |
+
"loss": 0.6891,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.9759036144578314,
|
| 573 |
+
"grad_norm": 0.6165035125857066,
|
| 574 |
+
"learning_rate": 8.535533905932739e-06,
|
| 575 |
+
"loss": 0.6875,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.9879518072289156,
|
| 580 |
+
"grad_norm": 0.6827006515832174,
|
| 581 |
+
"learning_rate": 8.485602070884118e-06,
|
| 582 |
+
"loss": 0.7065,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 1.0,
|
| 587 |
+
"grad_norm": 0.6351337582735852,
|
| 588 |
+
"learning_rate": 8.43498463017451e-06,
|
| 589 |
+
"loss": 0.6899,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.0120481927710843,
|
| 594 |
+
"grad_norm": 0.6511788455271817,
|
| 595 |
+
"learning_rate": 8.383691540076372e-06,
|
| 596 |
+
"loss": 0.6301,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.0240963855421688,
|
| 601 |
+
"grad_norm": 0.5967211972196197,
|
| 602 |
+
"learning_rate": 8.331732889760021e-06,
|
| 603 |
+
"loss": 0.6374,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.036144578313253,
|
| 608 |
+
"grad_norm": 0.7092464449638426,
|
| 609 |
+
"learning_rate": 8.279118899309121e-06,
|
| 610 |
+
"loss": 0.6203,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.0481927710843373,
|
| 615 |
+
"grad_norm": 0.5845701177591752,
|
| 616 |
+
"learning_rate": 8.22585991771044e-06,
|
| 617 |
+
"loss": 0.6318,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.0602409638554218,
|
| 622 |
+
"grad_norm": 0.6002752317965907,
|
| 623 |
+
"learning_rate": 8.171966420818227e-06,
|
| 624 |
+
"loss": 0.6467,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.072289156626506,
|
| 629 |
+
"grad_norm": 0.6522220311834458,
|
| 630 |
+
"learning_rate": 8.117449009293668e-06,
|
| 631 |
+
"loss": 0.6356,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.0843373493975903,
|
| 636 |
+
"grad_norm": 0.6502822017099245,
|
| 637 |
+
"learning_rate": 8.062318406519751e-06,
|
| 638 |
+
"loss": 0.6139,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.0963855421686748,
|
| 643 |
+
"grad_norm": 0.6061197012036528,
|
| 644 |
+
"learning_rate": 8.00658545649203e-06,
|
| 645 |
+
"loss": 0.6323,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.108433734939759,
|
| 650 |
+
"grad_norm": 0.5887887451794878,
|
| 651 |
+
"learning_rate": 7.950261121685642e-06,
|
| 652 |
+
"loss": 0.6291,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.1204819277108433,
|
| 657 |
+
"grad_norm": 0.6612015091841277,
|
| 658 |
+
"learning_rate": 7.89335648089903e-06,
|
| 659 |
+
"loss": 0.6167,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.1325301204819278,
|
| 664 |
+
"grad_norm": 0.6883130497488364,
|
| 665 |
+
"learning_rate": 7.835882727074779e-06,
|
| 666 |
+
"loss": 0.6187,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.144578313253012,
|
| 671 |
+
"grad_norm": 0.6427426046369045,
|
| 672 |
+
"learning_rate": 7.777851165098012e-06,
|
| 673 |
+
"loss": 0.6475,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.1566265060240963,
|
| 678 |
+
"grad_norm": 0.5978708484682433,
|
| 679 |
+
"learning_rate": 7.719273209572745e-06,
|
| 680 |
+
"loss": 0.6252,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.1686746987951806,
|
| 685 |
+
"grad_norm": 0.5855601016209826,
|
| 686 |
+
"learning_rate": 7.660160382576683e-06,
|
| 687 |
+
"loss": 0.6135,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.180722891566265,
|
| 692 |
+
"grad_norm": 0.7492491277249468,
|
| 693 |
+
"learning_rate": 7.600524311394873e-06,
|
| 694 |
+
"loss": 0.6087,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 1.1927710843373494,
|
| 699 |
+
"grad_norm": 0.6627214296533939,
|
| 700 |
+
"learning_rate": 7.540376726232648e-06,
|
| 701 |
+
"loss": 0.6121,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.2048192771084336,
|
| 706 |
+
"grad_norm": 0.5450802132108117,
|
| 707 |
+
"learning_rate": 7.4797294579083405e-06,
|
| 708 |
+
"loss": 0.6247,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.216867469879518,
|
| 713 |
+
"grad_norm": 0.7526832546581198,
|
| 714 |
+
"learning_rate": 7.4185944355261996e-06,
|
| 715 |
+
"loss": 0.625,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 1.2289156626506024,
|
| 720 |
+
"grad_norm": 0.6518223670625207,
|
| 721 |
+
"learning_rate": 7.3569836841299905e-06,
|
| 722 |
+
"loss": 0.6274,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.2409638554216866,
|
| 727 |
+
"grad_norm": 0.5534033743461448,
|
| 728 |
+
"learning_rate": 7.294909322337689e-06,
|
| 729 |
+
"loss": 0.6266,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.2530120481927711,
|
| 734 |
+
"grad_norm": 0.592926258071772,
|
| 735 |
+
"learning_rate": 7.232383559957815e-06,
|
| 736 |
+
"loss": 0.6185,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.2650602409638554,
|
| 741 |
+
"grad_norm": 0.6375741825060003,
|
| 742 |
+
"learning_rate": 7.169418695587791e-06,
|
| 743 |
+
"loss": 0.6217,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.2771084337349397,
|
| 748 |
+
"grad_norm": 0.5055671631407958,
|
| 749 |
+
"learning_rate": 7.106027114194856e-06,
|
| 750 |
+
"loss": 0.6177,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.2891566265060241,
|
| 755 |
+
"grad_norm": 0.6595997797708595,
|
| 756 |
+
"learning_rate": 7.042221284679982e-06,
|
| 757 |
+
"loss": 0.6205,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.3012048192771084,
|
| 762 |
+
"grad_norm": 0.6162416361134196,
|
| 763 |
+
"learning_rate": 6.978013757425295e-06,
|
| 764 |
+
"loss": 0.6223,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.3132530120481927,
|
| 769 |
+
"grad_norm": 0.5370366676804204,
|
| 770 |
+
"learning_rate": 6.913417161825449e-06,
|
| 771 |
+
"loss": 0.5882,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 1.3253012048192772,
|
| 776 |
+
"grad_norm": 0.5399960489088714,
|
| 777 |
+
"learning_rate": 6.848444203803476e-06,
|
| 778 |
+
"loss": 0.6289,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.3373493975903614,
|
| 783 |
+
"grad_norm": 0.5674796084091516,
|
| 784 |
+
"learning_rate": 6.783107663311566e-06,
|
| 785 |
+
"loss": 0.6244,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.3493975903614457,
|
| 790 |
+
"grad_norm": 0.5404297036496657,
|
| 791 |
+
"learning_rate": 6.717420391817306e-06,
|
| 792 |
+
"loss": 0.6,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 1.3614457831325302,
|
| 797 |
+
"grad_norm": 0.6237792562306403,
|
| 798 |
+
"learning_rate": 6.651395309775837e-06,
|
| 799 |
+
"loss": 0.6159,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 1.3734939759036144,
|
| 804 |
+
"grad_norm": 0.5282878577502261,
|
| 805 |
+
"learning_rate": 6.585045404088442e-06,
|
| 806 |
+
"loss": 0.623,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.3855421686746987,
|
| 811 |
+
"grad_norm": 0.5981309403814754,
|
| 812 |
+
"learning_rate": 6.518383725548074e-06,
|
| 813 |
+
"loss": 0.6102,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 1.3975903614457832,
|
| 818 |
+
"grad_norm": 0.6058914291786243,
|
| 819 |
+
"learning_rate": 6.451423386272312e-06,
|
| 820 |
+
"loss": 0.6239,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 1.4096385542168675,
|
| 825 |
+
"grad_norm": 0.5850369846706815,
|
| 826 |
+
"learning_rate": 6.384177557124247e-06,
|
| 827 |
+
"loss": 0.6194,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 1.4216867469879517,
|
| 832 |
+
"grad_norm": 0.6752460747433573,
|
| 833 |
+
"learning_rate": 6.3166594651218235e-06,
|
| 834 |
+
"loss": 0.6253,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 1.4337349397590362,
|
| 839 |
+
"grad_norm": 0.5592890672490309,
|
| 840 |
+
"learning_rate": 6.248882390836135e-06,
|
| 841 |
+
"loss": 0.6407,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 1.4457831325301205,
|
| 846 |
+
"grad_norm": 0.5784407179794009,
|
| 847 |
+
"learning_rate": 6.180859665779173e-06,
|
| 848 |
+
"loss": 0.6126,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.4578313253012047,
|
| 853 |
+
"grad_norm": 0.6514449422611613,
|
| 854 |
+
"learning_rate": 6.112604669781572e-06,
|
| 855 |
+
"loss": 0.5998,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 1.4698795180722892,
|
| 860 |
+
"grad_norm": 0.5800025517248629,
|
| 861 |
+
"learning_rate": 6.04413082836085e-06,
|
| 862 |
+
"loss": 0.6232,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 1.4819277108433735,
|
| 867 |
+
"grad_norm": 0.6233783401088263,
|
| 868 |
+
"learning_rate": 5.975451610080643e-06,
|
| 869 |
+
"loss": 0.6125,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 1.4939759036144578,
|
| 874 |
+
"grad_norm": 0.5337119115433385,
|
| 875 |
+
"learning_rate": 5.906580523901493e-06,
|
| 876 |
+
"loss": 0.6231,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 1.5060240963855422,
|
| 881 |
+
"grad_norm": 0.5768923184837736,
|
| 882 |
+
"learning_rate": 5.837531116523683e-06,
|
| 883 |
+
"loss": 0.6225,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 1.5180722891566265,
|
| 888 |
+
"grad_norm": 0.5381113068629061,
|
| 889 |
+
"learning_rate": 5.768316969722651e-06,
|
| 890 |
+
"loss": 0.601,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 1.5301204819277108,
|
| 895 |
+
"grad_norm": 0.6056565356551226,
|
| 896 |
+
"learning_rate": 5.698951697677498e-06,
|
| 897 |
+
"loss": 0.6184,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 1.5421686746987953,
|
| 902 |
+
"grad_norm": 0.525624946737704,
|
| 903 |
+
"learning_rate": 5.629448944293128e-06,
|
| 904 |
+
"loss": 0.6014,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 1.5542168674698795,
|
| 909 |
+
"grad_norm": 0.5913097818886935,
|
| 910 |
+
"learning_rate": 5.559822380516539e-06,
|
| 911 |
+
"loss": 0.612,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 1.5662650602409638,
|
| 916 |
+
"grad_norm": 0.6465501317905712,
|
| 917 |
+
"learning_rate": 5.490085701647805e-06,
|
| 918 |
+
"loss": 0.6168,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 1.5783132530120483,
|
| 923 |
+
"grad_norm": 0.5768289213896209,
|
| 924 |
+
"learning_rate": 5.420252624646238e-06,
|
| 925 |
+
"loss": 0.611,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 1.5903614457831325,
|
| 930 |
+
"grad_norm": 0.6042174223931454,
|
| 931 |
+
"learning_rate": 5.350336885432337e-06,
|
| 932 |
+
"loss": 0.6131,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 1.6024096385542168,
|
| 937 |
+
"grad_norm": 0.6251689249617343,
|
| 938 |
+
"learning_rate": 5.2803522361859596e-06,
|
| 939 |
+
"loss": 0.6324,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.6144578313253013,
|
| 944 |
+
"grad_norm": 0.6236393687846856,
|
| 945 |
+
"learning_rate": 5.210312442641327e-06,
|
| 946 |
+
"loss": 0.6038,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 1.6265060240963856,
|
| 951 |
+
"grad_norm": 0.5691587883847324,
|
| 952 |
+
"learning_rate": 5.140231281379345e-06,
|
| 953 |
+
"loss": 0.6423,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 1.6385542168674698,
|
| 958 |
+
"grad_norm": 0.5322090688844037,
|
| 959 |
+
"learning_rate": 5.070122537117812e-06,
|
| 960 |
+
"loss": 0.6353,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 1.6506024096385543,
|
| 965 |
+
"grad_norm": 0.5383749289608458,
|
| 966 |
+
"learning_rate": 5e-06,
|
| 967 |
+
"loss": 0.6187,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 1.6626506024096386,
|
| 972 |
+
"grad_norm": 0.5162216016045197,
|
| 973 |
+
"learning_rate": 4.92987746288219e-06,
|
| 974 |
+
"loss": 0.6085,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 1.6746987951807228,
|
| 979 |
+
"grad_norm": 0.5584798604645789,
|
| 980 |
+
"learning_rate": 4.859768718620656e-06,
|
| 981 |
+
"loss": 0.6147,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 1.6867469879518073,
|
| 986 |
+
"grad_norm": 0.5162198601842644,
|
| 987 |
+
"learning_rate": 4.789687557358676e-06,
|
| 988 |
+
"loss": 0.6139,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 1.6987951807228916,
|
| 993 |
+
"grad_norm": 0.5697649494329119,
|
| 994 |
+
"learning_rate": 4.719647763814041e-06,
|
| 995 |
+
"loss": 0.6195,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 1.7108433734939759,
|
| 1000 |
+
"grad_norm": 0.511975229887655,
|
| 1001 |
+
"learning_rate": 4.649663114567663e-06,
|
| 1002 |
+
"loss": 0.6188,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 1.7228915662650603,
|
| 1007 |
+
"grad_norm": 0.5255171763725026,
|
| 1008 |
+
"learning_rate": 4.579747375353763e-06,
|
| 1009 |
+
"loss": 0.6218,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 1.7349397590361446,
|
| 1014 |
+
"grad_norm": 0.5524618942728109,
|
| 1015 |
+
"learning_rate": 4.509914298352197e-06,
|
| 1016 |
+
"loss": 0.6096,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 1.7469879518072289,
|
| 1021 |
+
"grad_norm": 0.5052514719235022,
|
| 1022 |
+
"learning_rate": 4.4401776194834615e-06,
|
| 1023 |
+
"loss": 0.6229,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 1.7590361445783134,
|
| 1028 |
+
"grad_norm": 0.5519602114427213,
|
| 1029 |
+
"learning_rate": 4.3705510557068746e-06,
|
| 1030 |
+
"loss": 0.6146,
|
| 1031 |
+
"step": 146
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 1.7710843373493976,
|
| 1035 |
+
"grad_norm": 0.5223041604156741,
|
| 1036 |
+
"learning_rate": 4.3010483023225045e-06,
|
| 1037 |
+
"loss": 0.6202,
|
| 1038 |
+
"step": 147
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 1.783132530120482,
|
| 1042 |
+
"grad_norm": 0.48632353132375417,
|
| 1043 |
+
"learning_rate": 4.231683030277349e-06,
|
| 1044 |
+
"loss": 0.6048,
|
| 1045 |
+
"step": 148
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 1.7951807228915664,
|
| 1049 |
+
"grad_norm": 0.5817221327934441,
|
| 1050 |
+
"learning_rate": 4.162468883476319e-06,
|
| 1051 |
+
"loss": 0.621,
|
| 1052 |
+
"step": 149
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 1.8072289156626506,
|
| 1056 |
+
"grad_norm": 0.5018230149071331,
|
| 1057 |
+
"learning_rate": 4.0934194760985095e-06,
|
| 1058 |
+
"loss": 0.5982,
|
| 1059 |
+
"step": 150
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 1.819277108433735,
|
| 1063 |
+
"grad_norm": 0.6010733865960758,
|
| 1064 |
+
"learning_rate": 4.02454838991936e-06,
|
| 1065 |
+
"loss": 0.6148,
|
| 1066 |
+
"step": 151
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 1.8313253012048194,
|
| 1070 |
+
"grad_norm": 0.5398862747771389,
|
| 1071 |
+
"learning_rate": 3.955869171639151e-06,
|
| 1072 |
+
"loss": 0.6239,
|
| 1073 |
+
"step": 152
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 1.8433734939759037,
|
| 1077 |
+
"grad_norm": 0.5294643193447254,
|
| 1078 |
+
"learning_rate": 3.887395330218429e-06,
|
| 1079 |
+
"loss": 0.6177,
|
| 1080 |
+
"step": 153
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 1.855421686746988,
|
| 1084 |
+
"grad_norm": 0.4808728735687609,
|
| 1085 |
+
"learning_rate": 3.81914033422083e-06,
|
| 1086 |
+
"loss": 0.5916,
|
| 1087 |
+
"step": 154
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 1.8674698795180724,
|
| 1091 |
+
"grad_norm": 0.5018762281121382,
|
| 1092 |
+
"learning_rate": 3.751117609163865e-06,
|
| 1093 |
+
"loss": 0.621,
|
| 1094 |
+
"step": 155
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 1.8795180722891565,
|
| 1098 |
+
"grad_norm": 0.544376505139809,
|
| 1099 |
+
"learning_rate": 3.683340534878176e-06,
|
| 1100 |
+
"loss": 0.6089,
|
| 1101 |
+
"step": 156
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 1.891566265060241,
|
| 1105 |
+
"grad_norm": 0.5054403811402102,
|
| 1106 |
+
"learning_rate": 3.6158224428757538e-06,
|
| 1107 |
+
"loss": 0.6221,
|
| 1108 |
+
"step": 157
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 1.9036144578313254,
|
| 1112 |
+
"grad_norm": 0.5468648536592757,
|
| 1113 |
+
"learning_rate": 3.5485766137276894e-06,
|
| 1114 |
+
"loss": 0.64,
|
| 1115 |
+
"step": 158
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 1.9156626506024095,
|
| 1119 |
+
"grad_norm": 0.53351231774059,
|
| 1120 |
+
"learning_rate": 3.4816162744519266e-06,
|
| 1121 |
+
"loss": 0.6076,
|
| 1122 |
+
"step": 159
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 1.927710843373494,
|
| 1126 |
+
"grad_norm": 0.5224911140859257,
|
| 1127 |
+
"learning_rate": 3.4149545959115604e-06,
|
| 1128 |
+
"loss": 0.6095,
|
| 1129 |
+
"step": 160
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.9397590361445785,
|
| 1133 |
+
"grad_norm": 0.4956768078646336,
|
| 1134 |
+
"learning_rate": 3.3486046902241663e-06,
|
| 1135 |
+
"loss": 0.6433,
|
| 1136 |
+
"step": 161
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 1.9518072289156625,
|
| 1140 |
+
"grad_norm": 0.5394838660039611,
|
| 1141 |
+
"learning_rate": 3.2825796081826943e-06,
|
| 1142 |
+
"loss": 0.5989,
|
| 1143 |
+
"step": 162
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 1.963855421686747,
|
| 1147 |
+
"grad_norm": 0.5882895452328137,
|
| 1148 |
+
"learning_rate": 3.216892336688435e-06,
|
| 1149 |
+
"loss": 0.6438,
|
| 1150 |
+
"step": 163
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 1.9759036144578315,
|
| 1154 |
+
"grad_norm": 0.5719005618760834,
|
| 1155 |
+
"learning_rate": 3.1515557961965254e-06,
|
| 1156 |
+
"loss": 0.5912,
|
| 1157 |
+
"step": 164
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.9879518072289155,
|
| 1161 |
+
"grad_norm": 0.5072127958299484,
|
| 1162 |
+
"learning_rate": 3.0865828381745515e-06,
|
| 1163 |
+
"loss": 0.5991,
|
| 1164 |
+
"step": 165
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 2.0,
|
| 1168 |
+
"grad_norm": 0.511444872643503,
|
| 1169 |
+
"learning_rate": 3.021986242574707e-06,
|
| 1170 |
+
"loss": 0.5906,
|
| 1171 |
+
"step": 166
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 2.0120481927710845,
|
| 1175 |
+
"grad_norm": 0.558646285679792,
|
| 1176 |
+
"learning_rate": 2.95777871532002e-06,
|
| 1177 |
+
"loss": 0.564,
|
| 1178 |
+
"step": 167
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 2.0240963855421685,
|
| 1182 |
+
"grad_norm": 0.4681676467833184,
|
| 1183 |
+
"learning_rate": 2.893972885805148e-06,
|
| 1184 |
+
"loss": 0.5602,
|
| 1185 |
+
"step": 168
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 2.036144578313253,
|
| 1189 |
+
"grad_norm": 0.5311210396221397,
|
| 1190 |
+
"learning_rate": 2.83058130441221e-06,
|
| 1191 |
+
"loss": 0.5653,
|
| 1192 |
+
"step": 169
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 2.0481927710843375,
|
| 1196 |
+
"grad_norm": 0.5134743590726569,
|
| 1197 |
+
"learning_rate": 2.7676164400421864e-06,
|
| 1198 |
+
"loss": 0.5694,
|
| 1199 |
+
"step": 170
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 2.0602409638554215,
|
| 1203 |
+
"grad_norm": 0.4783416685783163,
|
| 1204 |
+
"learning_rate": 2.705090677662311e-06,
|
| 1205 |
+
"loss": 0.5647,
|
| 1206 |
+
"step": 171
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 2.072289156626506,
|
| 1210 |
+
"grad_norm": 0.46340955591582167,
|
| 1211 |
+
"learning_rate": 2.6430163158700116e-06,
|
| 1212 |
+
"loss": 0.5637,
|
| 1213 |
+
"step": 172
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 2.0843373493975905,
|
| 1217 |
+
"grad_norm": 0.5060776877189238,
|
| 1218 |
+
"learning_rate": 2.5814055644738013e-06,
|
| 1219 |
+
"loss": 0.5711,
|
| 1220 |
+
"step": 173
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 2.0963855421686746,
|
| 1224 |
+
"grad_norm": 0.5097326865484699,
|
| 1225 |
+
"learning_rate": 2.520270542091663e-06,
|
| 1226 |
+
"loss": 0.5582,
|
| 1227 |
+
"step": 174
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 2.108433734939759,
|
| 1231 |
+
"grad_norm": 0.5092257252859715,
|
| 1232 |
+
"learning_rate": 2.4596232737673544e-06,
|
| 1233 |
+
"loss": 0.5554,
|
| 1234 |
+
"step": 175
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 2.1204819277108435,
|
| 1238 |
+
"grad_norm": 0.5197317924103939,
|
| 1239 |
+
"learning_rate": 2.3994756886051267e-06,
|
| 1240 |
+
"loss": 0.5792,
|
| 1241 |
+
"step": 176
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 2.1325301204819276,
|
| 1245 |
+
"grad_norm": 0.5510975774014351,
|
| 1246 |
+
"learning_rate": 2.339839617423318e-06,
|
| 1247 |
+
"loss": 0.5718,
|
| 1248 |
+
"step": 177
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 2.144578313253012,
|
| 1252 |
+
"grad_norm": 0.5446337856700941,
|
| 1253 |
+
"learning_rate": 2.280726790427258e-06,
|
| 1254 |
+
"loss": 0.5497,
|
| 1255 |
+
"step": 178
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 2.1566265060240966,
|
| 1259 |
+
"grad_norm": 0.5408576213489689,
|
| 1260 |
+
"learning_rate": 2.2221488349019903e-06,
|
| 1261 |
+
"loss": 0.5524,
|
| 1262 |
+
"step": 179
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 2.1686746987951806,
|
| 1266 |
+
"grad_norm": 0.5017965090675062,
|
| 1267 |
+
"learning_rate": 2.1641172729252206e-06,
|
| 1268 |
+
"loss": 0.5682,
|
| 1269 |
+
"step": 180
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 2.180722891566265,
|
| 1273 |
+
"grad_norm": 0.5141039319661626,
|
| 1274 |
+
"learning_rate": 2.1066435191009717e-06,
|
| 1275 |
+
"loss": 0.547,
|
| 1276 |
+
"step": 181
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 2.1927710843373496,
|
| 1280 |
+
"grad_norm": 0.5157721156590446,
|
| 1281 |
+
"learning_rate": 2.04973887831436e-06,
|
| 1282 |
+
"loss": 0.5709,
|
| 1283 |
+
"step": 182
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 2.2048192771084336,
|
| 1287 |
+
"grad_norm": 0.5870699701608006,
|
| 1288 |
+
"learning_rate": 1.9934145435079705e-06,
|
| 1289 |
+
"loss": 0.5447,
|
| 1290 |
+
"step": 183
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 2.216867469879518,
|
| 1294 |
+
"grad_norm": 0.6028935897052433,
|
| 1295 |
+
"learning_rate": 1.9376815934802496e-06,
|
| 1296 |
+
"loss": 0.5601,
|
| 1297 |
+
"step": 184
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 2.2289156626506026,
|
| 1301 |
+
"grad_norm": 0.4718903082783866,
|
| 1302 |
+
"learning_rate": 1.8825509907063328e-06,
|
| 1303 |
+
"loss": 0.5551,
|
| 1304 |
+
"step": 185
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 2.2409638554216866,
|
| 1308 |
+
"grad_norm": 0.5002810920888432,
|
| 1309 |
+
"learning_rate": 1.8280335791817733e-06,
|
| 1310 |
+
"loss": 0.5688,
|
| 1311 |
+
"step": 186
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 2.253012048192771,
|
| 1315 |
+
"grad_norm": 0.5294348388821193,
|
| 1316 |
+
"learning_rate": 1.7741400822895633e-06,
|
| 1317 |
+
"loss": 0.581,
|
| 1318 |
+
"step": 187
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 2.2650602409638556,
|
| 1322 |
+
"grad_norm": 0.5159109553291168,
|
| 1323 |
+
"learning_rate": 1.7208811006908798e-06,
|
| 1324 |
+
"loss": 0.5641,
|
| 1325 |
+
"step": 188
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 2.2771084337349397,
|
| 1329 |
+
"grad_norm": 0.47208482699892207,
|
| 1330 |
+
"learning_rate": 1.6682671102399806e-06,
|
| 1331 |
+
"loss": 0.5769,
|
| 1332 |
+
"step": 189
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 2.289156626506024,
|
| 1336 |
+
"grad_norm": 0.48487303053069875,
|
| 1337 |
+
"learning_rate": 1.6163084599236278e-06,
|
| 1338 |
+
"loss": 0.5682,
|
| 1339 |
+
"step": 190
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 2.3012048192771086,
|
| 1343 |
+
"grad_norm": 0.4569664582891425,
|
| 1344 |
+
"learning_rate": 1.5650153698254916e-06,
|
| 1345 |
+
"loss": 0.5803,
|
| 1346 |
+
"step": 191
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 2.3132530120481927,
|
| 1350 |
+
"grad_norm": 0.4695542073042292,
|
| 1351 |
+
"learning_rate": 1.514397929115884e-06,
|
| 1352 |
+
"loss": 0.5466,
|
| 1353 |
+
"step": 192
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 2.325301204819277,
|
| 1357 |
+
"grad_norm": 0.4883651576878005,
|
| 1358 |
+
"learning_rate": 1.4644660940672628e-06,
|
| 1359 |
+
"loss": 0.541,
|
| 1360 |
+
"step": 193
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 2.337349397590361,
|
| 1364 |
+
"grad_norm": 0.525384604033524,
|
| 1365 |
+
"learning_rate": 1.4152296860958641e-06,
|
| 1366 |
+
"loss": 0.5534,
|
| 1367 |
+
"step": 194
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 2.3493975903614457,
|
| 1371 |
+
"grad_norm": 0.4766107333921436,
|
| 1372 |
+
"learning_rate": 1.3666983898298659e-06,
|
| 1373 |
+
"loss": 0.5785,
|
| 1374 |
+
"step": 195
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 2.36144578313253,
|
| 1378 |
+
"grad_norm": 0.530501750758112,
|
| 1379 |
+
"learning_rate": 1.3188817512044544e-06,
|
| 1380 |
+
"loss": 0.5618,
|
| 1381 |
+
"step": 196
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 2.3734939759036147,
|
| 1385 |
+
"grad_norm": 0.41149448787680737,
|
| 1386 |
+
"learning_rate": 1.2717891755841722e-06,
|
| 1387 |
+
"loss": 0.5613,
|
| 1388 |
+
"step": 197
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 2.3855421686746987,
|
| 1392 |
+
"grad_norm": 0.47133376734164123,
|
| 1393 |
+
"learning_rate": 1.225429925912921e-06,
|
| 1394 |
+
"loss": 0.5456,
|
| 1395 |
+
"step": 198
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 2.397590361445783,
|
| 1399 |
+
"grad_norm": 0.44160978889629554,
|
| 1400 |
+
"learning_rate": 1.1798131208919628e-06,
|
| 1401 |
+
"loss": 0.5608,
|
| 1402 |
+
"step": 199
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 2.4096385542168672,
|
| 1406 |
+
"grad_norm": 0.4713207662270395,
|
| 1407 |
+
"learning_rate": 1.134947733186315e-06,
|
| 1408 |
+
"loss": 0.5671,
|
| 1409 |
+
"step": 200
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 2.4216867469879517,
|
| 1413 |
+
"grad_norm": 0.4735966149153215,
|
| 1414 |
+
"learning_rate": 1.0908425876598512e-06,
|
| 1415 |
+
"loss": 0.5562,
|
| 1416 |
+
"step": 201
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 2.433734939759036,
|
| 1420 |
+
"grad_norm": 0.4966573016169727,
|
| 1421 |
+
"learning_rate": 1.047506359639483e-06,
|
| 1422 |
+
"loss": 0.5622,
|
| 1423 |
+
"step": 202
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 2.4457831325301207,
|
| 1427 |
+
"grad_norm": 0.45702011307394225,
|
| 1428 |
+
"learning_rate": 1.004947573208756e-06,
|
| 1429 |
+
"loss": 0.5687,
|
| 1430 |
+
"step": 203
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 2.4578313253012047,
|
| 1434 |
+
"grad_norm": 0.4733539932472332,
|
| 1435 |
+
"learning_rate": 9.631745995311881e-07,
|
| 1436 |
+
"loss": 0.57,
|
| 1437 |
+
"step": 204
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 2.4698795180722892,
|
| 1441 |
+
"grad_norm": 0.42935877811723394,
|
| 1442 |
+
"learning_rate": 9.221956552036992e-07,
|
| 1443 |
+
"loss": 0.5688,
|
| 1444 |
+
"step": 205
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 2.4819277108433733,
|
| 1448 |
+
"grad_norm": 0.5401591357533175,
|
| 1449 |
+
"learning_rate": 8.820188006404268e-07,
|
| 1450 |
+
"loss": 0.5438,
|
| 1451 |
+
"step": 206
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 2.4939759036144578,
|
| 1455 |
+
"grad_norm": 0.48661222938058185,
|
| 1456 |
+
"learning_rate": 8.426519384872733e-07,
|
| 1457 |
+
"loss": 0.5878,
|
| 1458 |
+
"step": 207
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 2.5060240963855422,
|
| 1462 |
+
"grad_norm": 0.4665236617171864,
|
| 1463 |
+
"learning_rate": 8.041028120674894e-07,
|
| 1464 |
+
"loss": 0.5353,
|
| 1465 |
+
"step": 208
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 2.5180722891566267,
|
| 1469 |
+
"grad_norm": 0.4518632327746976,
|
| 1470 |
+
"learning_rate": 7.663790038585794e-07,
|
| 1471 |
+
"loss": 0.5614,
|
| 1472 |
+
"step": 209
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 2.5301204819277108,
|
| 1476 |
+
"grad_norm": 0.4721339046051855,
|
| 1477 |
+
"learning_rate": 7.294879340008632e-07,
|
| 1478 |
+
"loss": 0.567,
|
| 1479 |
+
"step": 210
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 2.5421686746987953,
|
| 1483 |
+
"grad_norm": 0.429139351792564,
|
| 1484 |
+
"learning_rate": 6.934368588379553e-07,
|
| 1485 |
+
"loss": 0.576,
|
| 1486 |
+
"step": 211
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 2.5542168674698793,
|
| 1490 |
+
"grad_norm": 0.5075035453973568,
|
| 1491 |
+
"learning_rate": 6.582328694894729e-07,
|
| 1492 |
+
"loss": 0.5703,
|
| 1493 |
+
"step": 212
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 2.566265060240964,
|
| 1497 |
+
"grad_norm": 0.4475281320044474,
|
| 1498 |
+
"learning_rate": 6.238828904562316e-07,
|
| 1499 |
+
"loss": 0.5631,
|
| 1500 |
+
"step": 213
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 2.5783132530120483,
|
| 1504 |
+
"grad_norm": 0.48913591285723984,
|
| 1505 |
+
"learning_rate": 5.903936782582253e-07,
|
| 1506 |
+
"loss": 0.5625,
|
| 1507 |
+
"step": 214
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 2.5903614457831328,
|
| 1511 |
+
"grad_norm": 0.45778937976857875,
|
| 1512 |
+
"learning_rate": 5.577718201056392e-07,
|
| 1513 |
+
"loss": 0.5504,
|
| 1514 |
+
"step": 215
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 2.602409638554217,
|
| 1518 |
+
"grad_norm": 0.4386055171062226,
|
| 1519 |
+
"learning_rate": 5.260237326031698e-07,
|
| 1520 |
+
"loss": 0.5566,
|
| 1521 |
+
"step": 216
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 2.6144578313253013,
|
| 1525 |
+
"grad_norm": 0.4455791135265807,
|
| 1526 |
+
"learning_rate": 4.951556604879049e-07,
|
| 1527 |
+
"loss": 0.5706,
|
| 1528 |
+
"step": 217
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 2.6265060240963853,
|
| 1532 |
+
"grad_norm": 0.45607445355118803,
|
| 1533 |
+
"learning_rate": 4.651736754009972e-07,
|
| 1534 |
+
"loss": 0.5484,
|
| 1535 |
+
"step": 218
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 2.63855421686747,
|
| 1539 |
+
"grad_norm": 0.4294752864219149,
|
| 1540 |
+
"learning_rate": 4.3608367469340553e-07,
|
| 1541 |
+
"loss": 0.5607,
|
| 1542 |
+
"step": 219
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 2.6506024096385543,
|
| 1546 |
+
"grad_norm": 0.4153517988579225,
|
| 1547 |
+
"learning_rate": 4.078913802658946e-07,
|
| 1548 |
+
"loss": 0.5679,
|
| 1549 |
+
"step": 220
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 2.662650602409639,
|
| 1553 |
+
"grad_norm": 0.43992411352059413,
|
| 1554 |
+
"learning_rate": 3.8060233744356634e-07,
|
| 1555 |
+
"loss": 0.5632,
|
| 1556 |
+
"step": 221
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 2.674698795180723,
|
| 1560 |
+
"grad_norm": 0.4753241876516238,
|
| 1561 |
+
"learning_rate": 3.542219138851094e-07,
|
| 1562 |
+
"loss": 0.5695,
|
| 1563 |
+
"step": 222
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 2.6867469879518073,
|
| 1567 |
+
"grad_norm": 0.4363375230009041,
|
| 1568 |
+
"learning_rate": 3.287552985270015e-07,
|
| 1569 |
+
"loss": 0.5578,
|
| 1570 |
+
"step": 223
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 2.6987951807228914,
|
| 1574 |
+
"grad_norm": 0.4939139048287021,
|
| 1575 |
+
"learning_rate": 3.0420750056286195e-07,
|
| 1576 |
+
"loss": 0.5525,
|
| 1577 |
+
"step": 224
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 2.710843373493976,
|
| 1581 |
+
"grad_norm": 0.4407433939031648,
|
| 1582 |
+
"learning_rate": 2.8058334845816214e-07,
|
| 1583 |
+
"loss": 0.5582,
|
| 1584 |
+
"step": 225
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 2.7228915662650603,
|
| 1588 |
+
"grad_norm": 0.4769224487486906,
|
| 1589 |
+
"learning_rate": 2.5788748900048676e-07,
|
| 1590 |
+
"loss": 0.563,
|
| 1591 |
+
"step": 226
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 2.734939759036145,
|
| 1595 |
+
"grad_norm": 0.45327939902074543,
|
| 1596 |
+
"learning_rate": 2.3612438638551837e-07,
|
| 1597 |
+
"loss": 0.5657,
|
| 1598 |
+
"step": 227
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 2.746987951807229,
|
| 1602 |
+
"grad_norm": 0.45824994236000044,
|
| 1603 |
+
"learning_rate": 2.152983213389559e-07,
|
| 1604 |
+
"loss": 0.5768,
|
| 1605 |
+
"step": 228
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 2.7590361445783134,
|
| 1609 |
+
"grad_norm": 0.41799106068990527,
|
| 1610 |
+
"learning_rate": 1.9541339027450256e-07,
|
| 1611 |
+
"loss": 0.5765,
|
| 1612 |
+
"step": 229
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 2.7710843373493974,
|
| 1616 |
+
"grad_norm": 0.44800928229406345,
|
| 1617 |
+
"learning_rate": 1.7647350448812105e-07,
|
| 1618 |
+
"loss": 0.5434,
|
| 1619 |
+
"step": 230
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 2.783132530120482,
|
| 1623 |
+
"grad_norm": 0.4786297933983056,
|
| 1624 |
+
"learning_rate": 1.5848238938869332e-07,
|
| 1625 |
+
"loss": 0.5644,
|
| 1626 |
+
"step": 231
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 2.7951807228915664,
|
| 1630 |
+
"grad_norm": 0.4495457623483388,
|
| 1631 |
+
"learning_rate": 1.4144358376524504e-07,
|
| 1632 |
+
"loss": 0.5711,
|
| 1633 |
+
"step": 232
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 2.807228915662651,
|
| 1637 |
+
"grad_norm": 0.4467368766784784,
|
| 1638 |
+
"learning_rate": 1.253604390908819e-07,
|
| 1639 |
+
"loss": 0.5747,
|
| 1640 |
+
"step": 233
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 2.819277108433735,
|
| 1644 |
+
"grad_norm": 0.42743637589347505,
|
| 1645 |
+
"learning_rate": 1.10236118863562e-07,
|
| 1646 |
+
"loss": 0.5741,
|
| 1647 |
+
"step": 234
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 2.8313253012048194,
|
| 1651 |
+
"grad_norm": 0.45971443043244103,
|
| 1652 |
+
"learning_rate": 9.607359798384785e-08,
|
| 1653 |
+
"loss": 0.5537,
|
| 1654 |
+
"step": 235
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 2.8433734939759034,
|
| 1658 |
+
"grad_norm": 0.45456136996123836,
|
| 1659 |
+
"learning_rate": 8.287566216975795e-08,
|
| 1660 |
+
"loss": 0.5436,
|
| 1661 |
+
"step": 236
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 2.855421686746988,
|
| 1665 |
+
"grad_norm": 0.45548000364213126,
|
| 1666 |
+
"learning_rate": 7.064490740882057e-08,
|
| 1667 |
+
"loss": 0.5481,
|
| 1668 |
+
"step": 237
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 2.8674698795180724,
|
| 1672 |
+
"grad_norm": 0.473130854594422,
|
| 1673 |
+
"learning_rate": 5.938373944745612e-08,
|
| 1674 |
+
"loss": 0.5745,
|
| 1675 |
+
"step": 238
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 2.8795180722891565,
|
| 1679 |
+
"grad_norm": 0.46051179937108094,
|
| 1680 |
+
"learning_rate": 4.909437331777178e-08,
|
| 1681 |
+
"loss": 0.569,
|
| 1682 |
+
"step": 239
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 2.891566265060241,
|
| 1686 |
+
"grad_norm": 0.44290071625137933,
|
| 1687 |
+
"learning_rate": 3.977883290187667e-08,
|
| 1688 |
+
"loss": 0.5433,
|
| 1689 |
+
"step": 240
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 2.9036144578313254,
|
| 1693 |
+
"grad_norm": 0.45323884161408806,
|
| 1694 |
+
"learning_rate": 3.143895053378698e-08,
|
| 1695 |
+
"loss": 0.5637,
|
| 1696 |
+
"step": 241
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 2.9156626506024095,
|
| 1700 |
+
"grad_norm": 0.42389164450454236,
|
| 1701 |
+
"learning_rate": 2.4076366639015914e-08,
|
| 1702 |
+
"loss": 0.5464,
|
| 1703 |
+
"step": 242
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 2.927710843373494,
|
| 1707 |
+
"grad_norm": 0.4695054217684337,
|
| 1708 |
+
"learning_rate": 1.769252941190458e-08,
|
| 1709 |
+
"loss": 0.5313,
|
| 1710 |
+
"step": 243
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 2.9397590361445785,
|
| 1714 |
+
"grad_norm": 0.4715323869865203,
|
| 1715 |
+
"learning_rate": 1.2288694530769862e-08,
|
| 1716 |
+
"loss": 0.5517,
|
| 1717 |
+
"step": 244
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 2.9518072289156625,
|
| 1721 |
+
"grad_norm": 0.45767533383001513,
|
| 1722 |
+
"learning_rate": 7.865924910916977e-09,
|
| 1723 |
+
"loss": 0.5535,
|
| 1724 |
+
"step": 245
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 2.963855421686747,
|
| 1728 |
+
"grad_norm": 0.45023688997317707,
|
| 1729 |
+
"learning_rate": 4.4250904955656095e-09,
|
| 1730 |
+
"loss": 0.5445,
|
| 1731 |
+
"step": 246
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 2.9759036144578315,
|
| 1735 |
+
"grad_norm": 0.4346661439099685,
|
| 1736 |
+
"learning_rate": 1.9668680847356735e-09,
|
| 1737 |
+
"loss": 0.5569,
|
| 1738 |
+
"step": 247
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 2.9879518072289155,
|
| 1742 |
+
"grad_norm": 0.4694101503195915,
|
| 1743 |
+
"learning_rate": 4.91741202124918e-10,
|
| 1744 |
+
"loss": 0.5643,
|
| 1745 |
+
"step": 248
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 3.0,
|
| 1749 |
+
"grad_norm": 0.44801681936473053,
|
| 1750 |
+
"learning_rate": 0.0,
|
| 1751 |
+
"loss": 0.5477,
|
| 1752 |
+
"step": 249
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 3.0,
|
| 1756 |
+
"step": 249,
|
| 1757 |
+
"total_flos": 210646484844544.0,
|
| 1758 |
+
"train_loss": 0.6536134277960383,
|
| 1759 |
+
"train_runtime": 3799.3108,
|
| 1760 |
+
"train_samples_per_second": 6.269,
|
| 1761 |
+
"train_steps_per_second": 0.066
|
| 1762 |
+
}
|
| 1763 |
+
],
|
| 1764 |
+
"logging_steps": 1,
|
| 1765 |
+
"max_steps": 249,
|
| 1766 |
+
"num_input_tokens_seen": 0,
|
| 1767 |
+
"num_train_epochs": 3,
|
| 1768 |
+
"save_steps": 500,
|
| 1769 |
+
"stateful_callbacks": {
|
| 1770 |
+
"TrainerControl": {
|
| 1771 |
+
"args": {
|
| 1772 |
+
"should_epoch_stop": false,
|
| 1773 |
+
"should_evaluate": false,
|
| 1774 |
+
"should_log": false,
|
| 1775 |
+
"should_save": true,
|
| 1776 |
+
"should_training_stop": true
|
| 1777 |
+
},
|
| 1778 |
+
"attributes": {}
|
| 1779 |
+
}
|
| 1780 |
+
},
|
| 1781 |
+
"total_flos": 210646484844544.0,
|
| 1782 |
+
"train_batch_size": 1,
|
| 1783 |
+
"trial_name": null,
|
| 1784 |
+
"trial_params": null
|
| 1785 |
+
}
|
training_loss.png
ADDED
|