End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +2702 -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: stack_code_longest_science_longest
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# stack_code_longest_science_longest
|
| 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: stack_code_longest_science_longest
|
|
|
|
| 16 |
|
| 17 |
# stack_code_longest_science_longest
|
| 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/stack_code_longest_science_longest dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.975629569455727,
|
| 3 |
+
"total_flos": 9.790538054727893e+18,
|
| 4 |
+
"train_loss": 0.17350224256515503,
|
| 5 |
+
"train_runtime": 16013.9297,
|
| 6 |
+
"train_samples_per_second": 12.293,
|
| 7 |
+
"train_steps_per_second": 0.024
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.975629569455727,
|
| 3 |
+
"total_flos": 9.790538054727893e+18,
|
| 4 |
+
"train_loss": 0.17350224256515503,
|
| 5 |
+
"train_runtime": 16013.9297,
|
| 6 |
+
"train_samples_per_second": 12.293,
|
| 7 |
+
"train_steps_per_second": 0.024
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2702 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.975629569455727,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 380,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.012997562956945572,
|
| 13 |
+
"grad_norm": 6.099751379930322,
|
| 14 |
+
"learning_rate": 2.105263157894737e-06,
|
| 15 |
+
"loss": 1.0219,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.025995125913891144,
|
| 20 |
+
"grad_norm": 6.068929688233013,
|
| 21 |
+
"learning_rate": 4.210526315789474e-06,
|
| 22 |
+
"loss": 1.0148,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03899268887083672,
|
| 27 |
+
"grad_norm": 5.607482856386817,
|
| 28 |
+
"learning_rate": 6.31578947368421e-06,
|
| 29 |
+
"loss": 0.9978,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.05199025182778229,
|
| 34 |
+
"grad_norm": 4.0344324115028956,
|
| 35 |
+
"learning_rate": 8.421052631578948e-06,
|
| 36 |
+
"loss": 0.9695,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.06498781478472786,
|
| 41 |
+
"grad_norm": 2.3652828088294218,
|
| 42 |
+
"learning_rate": 1.0526315789473684e-05,
|
| 43 |
+
"loss": 0.9321,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.07798537774167344,
|
| 48 |
+
"grad_norm": 4.801199261631304,
|
| 49 |
+
"learning_rate": 1.263157894736842e-05,
|
| 50 |
+
"loss": 0.9538,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.09098294069861901,
|
| 55 |
+
"grad_norm": 4.831210221526376,
|
| 56 |
+
"learning_rate": 1.4736842105263159e-05,
|
| 57 |
+
"loss": 0.9455,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.10398050365556458,
|
| 62 |
+
"grad_norm": 5.705571120150557,
|
| 63 |
+
"learning_rate": 1.6842105263157896e-05,
|
| 64 |
+
"loss": 0.9346,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.11697806661251016,
|
| 69 |
+
"grad_norm": 4.118034247132142,
|
| 70 |
+
"learning_rate": 1.894736842105263e-05,
|
| 71 |
+
"loss": 0.9103,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.12997562956945571,
|
| 76 |
+
"grad_norm": 2.7464416924594333,
|
| 77 |
+
"learning_rate": 2.105263157894737e-05,
|
| 78 |
+
"loss": 0.8666,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.1429731925264013,
|
| 83 |
+
"grad_norm": 1.8112884281407549,
|
| 84 |
+
"learning_rate": 2.3157894736842107e-05,
|
| 85 |
+
"loss": 0.8288,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.15597075548334688,
|
| 90 |
+
"grad_norm": 1.6168217780438021,
|
| 91 |
+
"learning_rate": 2.526315789473684e-05,
|
| 92 |
+
"loss": 0.8095,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.16896831844029245,
|
| 97 |
+
"grad_norm": 1.0800910213719421,
|
| 98 |
+
"learning_rate": 2.7368421052631583e-05,
|
| 99 |
+
"loss": 0.7876,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.18196588139723802,
|
| 104 |
+
"grad_norm": 1.273865117132841,
|
| 105 |
+
"learning_rate": 2.9473684210526317e-05,
|
| 106 |
+
"loss": 0.7801,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.19496344435418358,
|
| 111 |
+
"grad_norm": 1.4101116134429739,
|
| 112 |
+
"learning_rate": 3.157894736842106e-05,
|
| 113 |
+
"loss": 0.7769,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.20796100731112915,
|
| 118 |
+
"grad_norm": 1.3300011416464073,
|
| 119 |
+
"learning_rate": 3.368421052631579e-05,
|
| 120 |
+
"loss": 0.7705,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.22095857026807472,
|
| 125 |
+
"grad_norm": 1.2303404991910958,
|
| 126 |
+
"learning_rate": 3.578947368421053e-05,
|
| 127 |
+
"loss": 0.7457,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.23395613322502032,
|
| 132 |
+
"grad_norm": 1.2600947996998637,
|
| 133 |
+
"learning_rate": 3.789473684210526e-05,
|
| 134 |
+
"loss": 0.7414,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.2469536961819659,
|
| 139 |
+
"grad_norm": 0.9415351295551974,
|
| 140 |
+
"learning_rate": 4e-05,
|
| 141 |
+
"loss": 0.731,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.25995125913891143,
|
| 146 |
+
"grad_norm": 1.6378942120476991,
|
| 147 |
+
"learning_rate": 4.210526315789474e-05,
|
| 148 |
+
"loss": 0.7402,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.272948822095857,
|
| 153 |
+
"grad_norm": 1.452156312513347,
|
| 154 |
+
"learning_rate": 4.421052631578948e-05,
|
| 155 |
+
"loss": 0.7293,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.2859463850528026,
|
| 160 |
+
"grad_norm": 1.1024110144705295,
|
| 161 |
+
"learning_rate": 4.6315789473684214e-05,
|
| 162 |
+
"loss": 0.7143,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.29894394800974816,
|
| 167 |
+
"grad_norm": 1.9887153689227788,
|
| 168 |
+
"learning_rate": 4.842105263157895e-05,
|
| 169 |
+
"loss": 0.7255,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.31194151096669376,
|
| 174 |
+
"grad_norm": 1.1903531007119599,
|
| 175 |
+
"learning_rate": 5.052631578947368e-05,
|
| 176 |
+
"loss": 0.7177,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.3249390739236393,
|
| 181 |
+
"grad_norm": 1.9904927095675595,
|
| 182 |
+
"learning_rate": 5.263157894736843e-05,
|
| 183 |
+
"loss": 0.7215,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.3379366368805849,
|
| 188 |
+
"grad_norm": 1.6681859777545944,
|
| 189 |
+
"learning_rate": 5.4736842105263165e-05,
|
| 190 |
+
"loss": 0.7009,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.35093419983753044,
|
| 195 |
+
"grad_norm": 1.6209941695574477,
|
| 196 |
+
"learning_rate": 5.68421052631579e-05,
|
| 197 |
+
"loss": 0.7052,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.36393176279447603,
|
| 202 |
+
"grad_norm": 1.98849797370751,
|
| 203 |
+
"learning_rate": 5.8947368421052634e-05,
|
| 204 |
+
"loss": 0.7004,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.37692932575142163,
|
| 209 |
+
"grad_norm": 1.12064775343047,
|
| 210 |
+
"learning_rate": 6.105263157894738e-05,
|
| 211 |
+
"loss": 0.6898,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.38992688870836717,
|
| 216 |
+
"grad_norm": 2.2171415848887475,
|
| 217 |
+
"learning_rate": 6.315789473684212e-05,
|
| 218 |
+
"loss": 0.6866,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.40292445166531277,
|
| 223 |
+
"grad_norm": 1.5015021280904342,
|
| 224 |
+
"learning_rate": 6.526315789473685e-05,
|
| 225 |
+
"loss": 0.6899,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.4159220146222583,
|
| 230 |
+
"grad_norm": 2.1943095640217583,
|
| 231 |
+
"learning_rate": 6.736842105263159e-05,
|
| 232 |
+
"loss": 0.6852,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.4289195775792039,
|
| 237 |
+
"grad_norm": 1.7052014979491807,
|
| 238 |
+
"learning_rate": 6.947368421052632e-05,
|
| 239 |
+
"loss": 0.6898,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.44191714053614944,
|
| 244 |
+
"grad_norm": 1.4787351390255603,
|
| 245 |
+
"learning_rate": 7.157894736842105e-05,
|
| 246 |
+
"loss": 0.6812,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.45491470349309504,
|
| 251 |
+
"grad_norm": 1.1982328674577414,
|
| 252 |
+
"learning_rate": 7.368421052631579e-05,
|
| 253 |
+
"loss": 0.6827,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.46791226645004064,
|
| 258 |
+
"grad_norm": 2.055421861681658,
|
| 259 |
+
"learning_rate": 7.578947368421052e-05,
|
| 260 |
+
"loss": 0.6747,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.4809098294069862,
|
| 265 |
+
"grad_norm": 1.3504861459840583,
|
| 266 |
+
"learning_rate": 7.789473684210527e-05,
|
| 267 |
+
"loss": 0.6697,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.4939073923639318,
|
| 272 |
+
"grad_norm": 1.9872016361599776,
|
| 273 |
+
"learning_rate": 8e-05,
|
| 274 |
+
"loss": 0.6748,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.5069049553208773,
|
| 279 |
+
"grad_norm": 1.9190088069026263,
|
| 280 |
+
"learning_rate": 7.99983123807325e-05,
|
| 281 |
+
"loss": 0.6721,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.5199025182778229,
|
| 286 |
+
"grad_norm": 1.265154939225945,
|
| 287 |
+
"learning_rate": 7.999324966533291e-05,
|
| 288 |
+
"loss": 0.6603,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.5329000812347685,
|
| 293 |
+
"grad_norm": 3.2164002414551978,
|
| 294 |
+
"learning_rate": 7.998481228099806e-05,
|
| 295 |
+
"loss": 0.6723,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.545897644191714,
|
| 300 |
+
"grad_norm": 2.571438671486186,
|
| 301 |
+
"learning_rate": 7.997300093968255e-05,
|
| 302 |
+
"loss": 0.6806,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.5588952071486596,
|
| 307 |
+
"grad_norm": 1.8156950022852132,
|
| 308 |
+
"learning_rate": 7.995781663803876e-05,
|
| 309 |
+
"loss": 0.6635,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.5718927701056052,
|
| 314 |
+
"grad_norm": 1.3254069741419403,
|
| 315 |
+
"learning_rate": 7.993926065733265e-05,
|
| 316 |
+
"loss": 0.6637,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.5848903330625508,
|
| 321 |
+
"grad_norm": 0.9530737655919242,
|
| 322 |
+
"learning_rate": 7.991733456333579e-05,
|
| 323 |
+
"loss": 0.6636,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.5978878960194963,
|
| 328 |
+
"grad_norm": 1.3664556141065045,
|
| 329 |
+
"learning_rate": 7.98920402061931e-05,
|
| 330 |
+
"loss": 0.6616,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.6108854589764419,
|
| 335 |
+
"grad_norm": 1.2839159067727302,
|
| 336 |
+
"learning_rate": 7.98633797202668e-05,
|
| 337 |
+
"loss": 0.6656,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.6238830219333875,
|
| 342 |
+
"grad_norm": 1.1439614314511357,
|
| 343 |
+
"learning_rate": 7.98313555239563e-05,
|
| 344 |
+
"loss": 0.6639,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.6368805848903331,
|
| 349 |
+
"grad_norm": 1.8097099672517978,
|
| 350 |
+
"learning_rate": 7.979597031949415e-05,
|
| 351 |
+
"loss": 0.6788,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.6498781478472786,
|
| 356 |
+
"grad_norm": 1.0800803816613773,
|
| 357 |
+
"learning_rate": 7.975722709271799e-05,
|
| 358 |
+
"loss": 0.6578,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.6628757108042242,
|
| 363 |
+
"grad_norm": 2.014427030879868,
|
| 364 |
+
"learning_rate": 7.97151291128186e-05,
|
| 365 |
+
"loss": 0.664,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.6758732737611698,
|
| 370 |
+
"grad_norm": 1.5251902643366386,
|
| 371 |
+
"learning_rate": 7.96696799320641e-05,
|
| 372 |
+
"loss": 0.6617,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.6888708367181153,
|
| 377 |
+
"grad_norm": 1.4609799533681953,
|
| 378 |
+
"learning_rate": 7.962088338550013e-05,
|
| 379 |
+
"loss": 0.6544,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.7018683996750609,
|
| 384 |
+
"grad_norm": 1.2857979651137834,
|
| 385 |
+
"learning_rate": 7.956874359062632e-05,
|
| 386 |
+
"loss": 0.6563,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.7148659626320065,
|
| 391 |
+
"grad_norm": 1.167851324111819,
|
| 392 |
+
"learning_rate": 7.951326494704878e-05,
|
| 393 |
+
"loss": 0.6432,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.7278635255889521,
|
| 398 |
+
"grad_norm": 0.923367616793914,
|
| 399 |
+
"learning_rate": 7.94544521361089e-05,
|
| 400 |
+
"loss": 0.6458,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.7408610885458976,
|
| 405 |
+
"grad_norm": 1.2536213795566458,
|
| 406 |
+
"learning_rate": 7.939231012048833e-05,
|
| 407 |
+
"loss": 0.6483,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.7538586515028433,
|
| 412 |
+
"grad_norm": 1.2119787729723712,
|
| 413 |
+
"learning_rate": 7.932684414379021e-05,
|
| 414 |
+
"loss": 0.6461,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.7668562144597888,
|
| 419 |
+
"grad_norm": 0.7624960645952309,
|
| 420 |
+
"learning_rate": 7.925805973009672e-05,
|
| 421 |
+
"loss": 0.6347,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.7798537774167343,
|
| 426 |
+
"grad_norm": 0.9917480604742027,
|
| 427 |
+
"learning_rate": 7.918596268350296e-05,
|
| 428 |
+
"loss": 0.639,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.7928513403736799,
|
| 433 |
+
"grad_norm": 1.3671397849973843,
|
| 434 |
+
"learning_rate": 7.911055908762718e-05,
|
| 435 |
+
"loss": 0.6416,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.8058489033306255,
|
| 440 |
+
"grad_norm": 0.7823232773420852,
|
| 441 |
+
"learning_rate": 7.903185530509743e-05,
|
| 442 |
+
"loss": 0.633,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.8188464662875711,
|
| 447 |
+
"grad_norm": 0.8711197066128451,
|
| 448 |
+
"learning_rate": 7.894985797701472e-05,
|
| 449 |
+
"loss": 0.6348,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.8318440292445166,
|
| 454 |
+
"grad_norm": 1.0138573543907548,
|
| 455 |
+
"learning_rate": 7.886457402239256e-05,
|
| 456 |
+
"loss": 0.6317,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.8448415922014623,
|
| 461 |
+
"grad_norm": 1.328902077693916,
|
| 462 |
+
"learning_rate": 7.877601063757323e-05,
|
| 463 |
+
"loss": 0.641,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.8578391551584078,
|
| 468 |
+
"grad_norm": 0.8975115888522265,
|
| 469 |
+
"learning_rate": 7.868417529562043e-05,
|
| 470 |
+
"loss": 0.6225,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.8708367181153533,
|
| 475 |
+
"grad_norm": 0.9433279422872343,
|
| 476 |
+
"learning_rate": 7.858907574568882e-05,
|
| 477 |
+
"loss": 0.6318,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.8838342810722989,
|
| 482 |
+
"grad_norm": 0.9051780877745009,
|
| 483 |
+
"learning_rate": 7.849072001237001e-05,
|
| 484 |
+
"loss": 0.623,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.8968318440292445,
|
| 489 |
+
"grad_norm": 1.1238293364288126,
|
| 490 |
+
"learning_rate": 7.838911639501557e-05,
|
| 491 |
+
"loss": 0.6197,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.9098294069861901,
|
| 496 |
+
"grad_norm": 0.9616875737950008,
|
| 497 |
+
"learning_rate": 7.828427346703657e-05,
|
| 498 |
+
"loss": 0.6151,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.9228269699431356,
|
| 503 |
+
"grad_norm": 0.7925602555435675,
|
| 504 |
+
"learning_rate": 7.81762000751803e-05,
|
| 505 |
+
"loss": 0.6204,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.9358245329000813,
|
| 510 |
+
"grad_norm": 0.8202368746016689,
|
| 511 |
+
"learning_rate": 7.806490533878368e-05,
|
| 512 |
+
"loss": 0.6206,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.9488220958570268,
|
| 517 |
+
"grad_norm": 0.7281381020297469,
|
| 518 |
+
"learning_rate": 7.795039864900378e-05,
|
| 519 |
+
"loss": 0.6145,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.9618196588139724,
|
| 524 |
+
"grad_norm": 0.951203457585769,
|
| 525 |
+
"learning_rate": 7.783268966802539e-05,
|
| 526 |
+
"loss": 0.6271,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.974817221770918,
|
| 531 |
+
"grad_norm": 1.079648600019301,
|
| 532 |
+
"learning_rate": 7.771178832824573e-05,
|
| 533 |
+
"loss": 0.6142,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.9878147847278635,
|
| 538 |
+
"grad_norm": 0.7728669124672748,
|
| 539 |
+
"learning_rate": 7.758770483143634e-05,
|
| 540 |
+
"loss": 0.6123,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.0024370430544274,
|
| 545 |
+
"grad_norm": 0.9574347690194315,
|
| 546 |
+
"learning_rate": 7.74604496478822e-05,
|
| 547 |
+
"loss": 0.615,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.0154346060113728,
|
| 552 |
+
"grad_norm": 1.0135972450552604,
|
| 553 |
+
"learning_rate": 7.733003351549829e-05,
|
| 554 |
+
"loss": 0.5888,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.0284321689683185,
|
| 559 |
+
"grad_norm": 1.1758211244717183,
|
| 560 |
+
"learning_rate": 7.719646743892352e-05,
|
| 561 |
+
"loss": 0.5932,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.0414297319252641,
|
| 566 |
+
"grad_norm": 1.0448938050043781,
|
| 567 |
+
"learning_rate": 7.705976268859207e-05,
|
| 568 |
+
"loss": 0.5934,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.0544272948822095,
|
| 573 |
+
"grad_norm": 0.9104488344215643,
|
| 574 |
+
"learning_rate": 7.691993079978252e-05,
|
| 575 |
+
"loss": 0.5815,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.0674248578391552,
|
| 580 |
+
"grad_norm": 0.7412780882809253,
|
| 581 |
+
"learning_rate": 7.677698357164431e-05,
|
| 582 |
+
"loss": 0.5752,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 1.0804224207961006,
|
| 587 |
+
"grad_norm": 0.7417024796170562,
|
| 588 |
+
"learning_rate": 7.663093306620231e-05,
|
| 589 |
+
"loss": 0.5792,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.0934199837530463,
|
| 594 |
+
"grad_norm": 0.7190010808453768,
|
| 595 |
+
"learning_rate": 7.648179160733883e-05,
|
| 596 |
+
"loss": 0.5753,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.106417546709992,
|
| 601 |
+
"grad_norm": 0.7427027225824168,
|
| 602 |
+
"learning_rate": 7.632957177975387e-05,
|
| 603 |
+
"loss": 0.5777,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.1194151096669374,
|
| 608 |
+
"grad_norm": 0.9295269491982405,
|
| 609 |
+
"learning_rate": 7.61742864279031e-05,
|
| 610 |
+
"loss": 0.5834,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.132412672623883,
|
| 615 |
+
"grad_norm": 0.9634417055121992,
|
| 616 |
+
"learning_rate": 7.601594865491414e-05,
|
| 617 |
+
"loss": 0.5742,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.1454102355808287,
|
| 622 |
+
"grad_norm": 0.9476309894224839,
|
| 623 |
+
"learning_rate": 7.585457182148081e-05,
|
| 624 |
+
"loss": 0.5784,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.158407798537774,
|
| 629 |
+
"grad_norm": 0.9101385250862156,
|
| 630 |
+
"learning_rate": 7.569016954473577e-05,
|
| 631 |
+
"loss": 0.5826,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.1714053614947197,
|
| 636 |
+
"grad_norm": 0.9143144480170803,
|
| 637 |
+
"learning_rate": 7.552275569710152e-05,
|
| 638 |
+
"loss": 0.5852,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.1844029244516654,
|
| 643 |
+
"grad_norm": 0.6885600525748597,
|
| 644 |
+
"learning_rate": 7.535234440511979e-05,
|
| 645 |
+
"loss": 0.5763,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.1974004874086108,
|
| 650 |
+
"grad_norm": 0.5214486371121746,
|
| 651 |
+
"learning_rate": 7.517895004825956e-05,
|
| 652 |
+
"loss": 0.5787,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.2103980503655565,
|
| 657 |
+
"grad_norm": 0.758408482295764,
|
| 658 |
+
"learning_rate": 7.500258725770375e-05,
|
| 659 |
+
"loss": 0.5746,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.2233956133225021,
|
| 664 |
+
"grad_norm": 0.7125338265833929,
|
| 665 |
+
"learning_rate": 7.48232709151145e-05,
|
| 666 |
+
"loss": 0.5703,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.2363931762794476,
|
| 671 |
+
"grad_norm": 0.6377296028835163,
|
| 672 |
+
"learning_rate": 7.464101615137756e-05,
|
| 673 |
+
"loss": 0.579,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.2493907392363932,
|
| 678 |
+
"grad_norm": 0.5870416970514215,
|
| 679 |
+
"learning_rate": 7.445583834532546e-05,
|
| 680 |
+
"loss": 0.5637,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.2623883021933389,
|
| 685 |
+
"grad_norm": 0.4860633167448116,
|
| 686 |
+
"learning_rate": 7.426775312243986e-05,
|
| 687 |
+
"loss": 0.5756,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.2753858651502843,
|
| 692 |
+
"grad_norm": 0.5083572483496955,
|
| 693 |
+
"learning_rate": 7.407677635353308e-05,
|
| 694 |
+
"loss": 0.5734,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 1.28838342810723,
|
| 699 |
+
"grad_norm": 0.5305435155519614,
|
| 700 |
+
"learning_rate": 7.388292415340888e-05,
|
| 701 |
+
"loss": 0.5682,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.3013809910641756,
|
| 706 |
+
"grad_norm": 0.4176759940201937,
|
| 707 |
+
"learning_rate": 7.368621287950264e-05,
|
| 708 |
+
"loss": 0.5643,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.314378554021121,
|
| 713 |
+
"grad_norm": 0.4583116745957642,
|
| 714 |
+
"learning_rate": 7.348665913050115e-05,
|
| 715 |
+
"loss": 0.5602,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 1.3273761169780667,
|
| 720 |
+
"grad_norm": 0.5426624427041704,
|
| 721 |
+
"learning_rate": 7.328427974494201e-05,
|
| 722 |
+
"loss": 0.5672,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.340373679935012,
|
| 727 |
+
"grad_norm": 0.4189086182858418,
|
| 728 |
+
"learning_rate": 7.307909179979274e-05,
|
| 729 |
+
"loss": 0.5648,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.3533712428919578,
|
| 734 |
+
"grad_norm": 0.39949243757403974,
|
| 735 |
+
"learning_rate": 7.28711126090098e-05,
|
| 736 |
+
"loss": 0.566,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.3663688058489034,
|
| 741 |
+
"grad_norm": 0.43131027290320334,
|
| 742 |
+
"learning_rate": 7.266035972207773e-05,
|
| 743 |
+
"loss": 0.5571,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.3793663688058488,
|
| 748 |
+
"grad_norm": 0.40582965588538134,
|
| 749 |
+
"learning_rate": 7.24468509225281e-05,
|
| 750 |
+
"loss": 0.5693,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.3923639317627945,
|
| 755 |
+
"grad_norm": 0.4761372341291519,
|
| 756 |
+
"learning_rate": 7.223060422643914e-05,
|
| 757 |
+
"loss": 0.5686,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.40536149471974,
|
| 762 |
+
"grad_norm": 0.5727339140771481,
|
| 763 |
+
"learning_rate": 7.201163788091536e-05,
|
| 764 |
+
"loss": 0.5678,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.4183590576766856,
|
| 769 |
+
"grad_norm": 0.7085163969661245,
|
| 770 |
+
"learning_rate": 7.178997036254799e-05,
|
| 771 |
+
"loss": 0.5683,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 1.4313566206336312,
|
| 776 |
+
"grad_norm": 0.80819559722067,
|
| 777 |
+
"learning_rate": 7.156562037585576e-05,
|
| 778 |
+
"loss": 0.5665,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.4443541835905767,
|
| 783 |
+
"grad_norm": 0.793253904366816,
|
| 784 |
+
"learning_rate": 7.133860685170665e-05,
|
| 785 |
+
"loss": 0.5745,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.4573517465475223,
|
| 790 |
+
"grad_norm": 0.7256059178824779,
|
| 791 |
+
"learning_rate": 7.110894894572056e-05,
|
| 792 |
+
"loss": 0.5645,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 1.470349309504468,
|
| 797 |
+
"grad_norm": 0.5014971965016265,
|
| 798 |
+
"learning_rate": 7.087666603665284e-05,
|
| 799 |
+
"loss": 0.5606,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 1.4833468724614134,
|
| 804 |
+
"grad_norm": 0.43914912895871583,
|
| 805 |
+
"learning_rate": 7.064177772475912e-05,
|
| 806 |
+
"loss": 0.5674,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.496344435418359,
|
| 811 |
+
"grad_norm": 0.4961335507396086,
|
| 812 |
+
"learning_rate": 7.040430383014146e-05,
|
| 813 |
+
"loss": 0.5655,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 1.5093419983753047,
|
| 818 |
+
"grad_norm": 0.5185842695541142,
|
| 819 |
+
"learning_rate": 7.016426439107586e-05,
|
| 820 |
+
"loss": 0.5653,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 1.5223395613322501,
|
| 825 |
+
"grad_norm": 0.37245930997617116,
|
| 826 |
+
"learning_rate": 6.992167966232143e-05,
|
| 827 |
+
"loss": 0.5567,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 1.5353371242891958,
|
| 832 |
+
"grad_norm": 0.5310947508784376,
|
| 833 |
+
"learning_rate": 6.967657011341126e-05,
|
| 834 |
+
"loss": 0.575,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 1.5483346872461414,
|
| 839 |
+
"grad_norm": 0.7628101414612303,
|
| 840 |
+
"learning_rate": 6.942895642692527e-05,
|
| 841 |
+
"loss": 0.5624,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 1.5613322502030869,
|
| 846 |
+
"grad_norm": 0.7910046561291942,
|
| 847 |
+
"learning_rate": 6.917885949674483e-05,
|
| 848 |
+
"loss": 0.5667,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.5743298131600325,
|
| 853 |
+
"grad_norm": 0.7246609366699134,
|
| 854 |
+
"learning_rate": 6.892630042628988e-05,
|
| 855 |
+
"loss": 0.557,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 1.5873273761169782,
|
| 860 |
+
"grad_norm": 0.6852631021753094,
|
| 861 |
+
"learning_rate": 6.867130052673806e-05,
|
| 862 |
+
"loss": 0.5638,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 1.6003249390739236,
|
| 867 |
+
"grad_norm": 0.6947100326982237,
|
| 868 |
+
"learning_rate": 6.841388131522656e-05,
|
| 869 |
+
"loss": 0.5626,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 1.6133225020308692,
|
| 874 |
+
"grad_norm": 0.5891017692387462,
|
| 875 |
+
"learning_rate": 6.815406451303647e-05,
|
| 876 |
+
"loss": 0.5632,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 1.626320064987815,
|
| 881 |
+
"grad_norm": 0.44282420651875987,
|
| 882 |
+
"learning_rate": 6.789187204375981e-05,
|
| 883 |
+
"loss": 0.5643,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 1.6393176279447603,
|
| 888 |
+
"grad_norm": 0.3540188196234301,
|
| 889 |
+
"learning_rate": 6.762732603144978e-05,
|
| 890 |
+
"loss": 0.5611,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 1.652315190901706,
|
| 895 |
+
"grad_norm": 0.38606767224591043,
|
| 896 |
+
"learning_rate": 6.736044879875373e-05,
|
| 897 |
+
"loss": 0.5548,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 1.6653127538586516,
|
| 902 |
+
"grad_norm": 0.4847276958422751,
|
| 903 |
+
"learning_rate": 6.709126286502965e-05,
|
| 904 |
+
"loss": 0.5634,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 1.678310316815597,
|
| 909 |
+
"grad_norm": 0.48098159010027874,
|
| 910 |
+
"learning_rate": 6.681979094444596e-05,
|
| 911 |
+
"loss": 0.558,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 1.6913078797725425,
|
| 916 |
+
"grad_norm": 0.35223251057931265,
|
| 917 |
+
"learning_rate": 6.654605594406486e-05,
|
| 918 |
+
"loss": 0.5584,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 1.7043054427294884,
|
| 923 |
+
"grad_norm": 0.3582278064607583,
|
| 924 |
+
"learning_rate": 6.627008096190938e-05,
|
| 925 |
+
"loss": 0.5581,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 1.7173030056864338,
|
| 930 |
+
"grad_norm": 0.4148482135356544,
|
| 931 |
+
"learning_rate": 6.59918892850144e-05,
|
| 932 |
+
"loss": 0.5604,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 1.7303005686433792,
|
| 937 |
+
"grad_norm": 0.5160390925469622,
|
| 938 |
+
"learning_rate": 6.571150438746157e-05,
|
| 939 |
+
"loss": 0.5578,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.743298131600325,
|
| 944 |
+
"grad_norm": 0.6691571622471794,
|
| 945 |
+
"learning_rate": 6.542894992839873e-05,
|
| 946 |
+
"loss": 0.5521,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 1.7562956945572705,
|
| 951 |
+
"grad_norm": 0.7398206439178091,
|
| 952 |
+
"learning_rate": 6.514424975004329e-05,
|
| 953 |
+
"loss": 0.5559,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 1.769293257514216,
|
| 958 |
+
"grad_norm": 0.6904604759405913,
|
| 959 |
+
"learning_rate": 6.48574278756706e-05,
|
| 960 |
+
"loss": 0.556,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 1.7822908204711616,
|
| 965 |
+
"grad_norm": 0.5927997707542059,
|
| 966 |
+
"learning_rate": 6.456850850758673e-05,
|
| 967 |
+
"loss": 0.5511,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 1.7952883834281073,
|
| 972 |
+
"grad_norm": 0.598576202040419,
|
| 973 |
+
"learning_rate": 6.427751602508628e-05,
|
| 974 |
+
"loss": 0.5517,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 1.8082859463850527,
|
| 979 |
+
"grad_norm": 0.5752299054086354,
|
| 980 |
+
"learning_rate": 6.398447498239527e-05,
|
| 981 |
+
"loss": 0.5603,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 1.8212835093419983,
|
| 986 |
+
"grad_norm": 0.47947265005962353,
|
| 987 |
+
"learning_rate": 6.368941010659921e-05,
|
| 988 |
+
"loss": 0.5583,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 1.834281072298944,
|
| 993 |
+
"grad_norm": 0.3589925554258543,
|
| 994 |
+
"learning_rate": 6.339234629555655e-05,
|
| 995 |
+
"loss": 0.5566,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 1.8472786352558894,
|
| 1000 |
+
"grad_norm": 0.3418394937521007,
|
| 1001 |
+
"learning_rate": 6.309330861579786e-05,
|
| 1002 |
+
"loss": 0.5592,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 1.860276198212835,
|
| 1007 |
+
"grad_norm": 0.4539321991211633,
|
| 1008 |
+
"learning_rate": 6.279232230041065e-05,
|
| 1009 |
+
"loss": 0.5544,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 1.8732737611697807,
|
| 1014 |
+
"grad_norm": 0.44216438200356556,
|
| 1015 |
+
"learning_rate": 6.248941274691017e-05,
|
| 1016 |
+
"loss": 0.5519,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 1.8862713241267262,
|
| 1021 |
+
"grad_norm": 0.3237161862715092,
|
| 1022 |
+
"learning_rate": 6.218460551509636e-05,
|
| 1023 |
+
"loss": 0.5471,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 1.8992688870836718,
|
| 1028 |
+
"grad_norm": 0.3051484675988478,
|
| 1029 |
+
"learning_rate": 6.18779263248971e-05,
|
| 1030 |
+
"loss": 0.5551,
|
| 1031 |
+
"step": 146
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 1.9122664500406175,
|
| 1035 |
+
"grad_norm": 0.459140656732003,
|
| 1036 |
+
"learning_rate": 6.156940105419785e-05,
|
| 1037 |
+
"loss": 0.5491,
|
| 1038 |
+
"step": 147
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 1.925264012997563,
|
| 1042 |
+
"grad_norm": 0.5335980534072164,
|
| 1043 |
+
"learning_rate": 6.125905573665824e-05,
|
| 1044 |
+
"loss": 0.5515,
|
| 1045 |
+
"step": 148
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 1.9382615759545085,
|
| 1049 |
+
"grad_norm": 0.4199748973939331,
|
| 1050 |
+
"learning_rate": 6.094691655951512e-05,
|
| 1051 |
+
"loss": 0.554,
|
| 1052 |
+
"step": 149
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 1.9512591389114542,
|
| 1056 |
+
"grad_norm": 0.37821939152611067,
|
| 1057 |
+
"learning_rate": 6.063300986137297e-05,
|
| 1058 |
+
"loss": 0.5515,
|
| 1059 |
+
"step": 150
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 1.9642567018683996,
|
| 1063 |
+
"grad_norm": 0.4525799105101174,
|
| 1064 |
+
"learning_rate": 6.0317362129981375e-05,
|
| 1065 |
+
"loss": 0.5514,
|
| 1066 |
+
"step": 151
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 1.9772542648253453,
|
| 1070 |
+
"grad_norm": 0.4866209265488796,
|
| 1071 |
+
"learning_rate": 6.000000000000001e-05,
|
| 1072 |
+
"loss": 0.5557,
|
| 1073 |
+
"step": 152
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 1.990251827782291,
|
| 1077 |
+
"grad_norm": 0.4881518290915675,
|
| 1078 |
+
"learning_rate": 5.968095025075114e-05,
|
| 1079 |
+
"loss": 0.5581,
|
| 1080 |
+
"step": 153
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 2.0048740861088548,
|
| 1084 |
+
"grad_norm": 0.3855836959947548,
|
| 1085 |
+
"learning_rate": 5.936023980395997e-05,
|
| 1086 |
+
"loss": 0.5411,
|
| 1087 |
+
"step": 154
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 2.0178716490658,
|
| 1091 |
+
"grad_norm": 0.3731193378171015,
|
| 1092 |
+
"learning_rate": 5.903789572148295e-05,
|
| 1093 |
+
"loss": 0.5115,
|
| 1094 |
+
"step": 155
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 2.0308692120227456,
|
| 1098 |
+
"grad_norm": 0.4760587483033507,
|
| 1099 |
+
"learning_rate": 5.871394520302432e-05,
|
| 1100 |
+
"loss": 0.5036,
|
| 1101 |
+
"step": 156
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 2.0438667749796915,
|
| 1105 |
+
"grad_norm": 0.5788173180313999,
|
| 1106 |
+
"learning_rate": 5.838841558384091e-05,
|
| 1107 |
+
"loss": 0.5023,
|
| 1108 |
+
"step": 157
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 2.056864337936637,
|
| 1112 |
+
"grad_norm": 0.610294677890403,
|
| 1113 |
+
"learning_rate": 5.806133433243558e-05,
|
| 1114 |
+
"loss": 0.5115,
|
| 1115 |
+
"step": 158
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 2.0698619008935824,
|
| 1119 |
+
"grad_norm": 0.5785376971559186,
|
| 1120 |
+
"learning_rate": 5.7732729048239444e-05,
|
| 1121 |
+
"loss": 0.5059,
|
| 1122 |
+
"step": 159
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 2.0828594638505282,
|
| 1126 |
+
"grad_norm": 0.6361199902732823,
|
| 1127 |
+
"learning_rate": 5.740262745928293e-05,
|
| 1128 |
+
"loss": 0.5094,
|
| 1129 |
+
"step": 160
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 2.0958570268074737,
|
| 1133 |
+
"grad_norm": 0.7055783417389399,
|
| 1134 |
+
"learning_rate": 5.707105741985615e-05,
|
| 1135 |
+
"loss": 0.5099,
|
| 1136 |
+
"step": 161
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 2.108854589764419,
|
| 1140 |
+
"grad_norm": 0.7551674489031295,
|
| 1141 |
+
"learning_rate": 5.673804690815845e-05,
|
| 1142 |
+
"loss": 0.5115,
|
| 1143 |
+
"step": 162
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 2.121852152721365,
|
| 1147 |
+
"grad_norm": 0.7239995903013289,
|
| 1148 |
+
"learning_rate": 5.6403624023937614e-05,
|
| 1149 |
+
"loss": 0.5031,
|
| 1150 |
+
"step": 163
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 2.1348497156783104,
|
| 1154 |
+
"grad_norm": 0.509463011523919,
|
| 1155 |
+
"learning_rate": 5.606781698611879e-05,
|
| 1156 |
+
"loss": 0.5021,
|
| 1157 |
+
"step": 164
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 2.147847278635256,
|
| 1161 |
+
"grad_norm": 0.4210575883324648,
|
| 1162 |
+
"learning_rate": 5.573065413042333e-05,
|
| 1163 |
+
"loss": 0.5053,
|
| 1164 |
+
"step": 165
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 2.1608448415922012,
|
| 1168 |
+
"grad_norm": 0.5009273026595834,
|
| 1169 |
+
"learning_rate": 5.5392163906977835e-05,
|
| 1170 |
+
"loss": 0.507,
|
| 1171 |
+
"step": 166
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 2.173842404549147,
|
| 1175 |
+
"grad_norm": 0.47375681034352735,
|
| 1176 |
+
"learning_rate": 5.505237487791343e-05,
|
| 1177 |
+
"loss": 0.5042,
|
| 1178 |
+
"step": 167
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 2.1868399675060926,
|
| 1182 |
+
"grad_norm": 0.37667913409010934,
|
| 1183 |
+
"learning_rate": 5.471131571495574e-05,
|
| 1184 |
+
"loss": 0.5006,
|
| 1185 |
+
"step": 168
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 2.199837530463038,
|
| 1189 |
+
"grad_norm": 0.292819297582803,
|
| 1190 |
+
"learning_rate": 5.4369015197005506e-05,
|
| 1191 |
+
"loss": 0.5102,
|
| 1192 |
+
"step": 169
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 2.212835093419984,
|
| 1196 |
+
"grad_norm": 0.4148005226049645,
|
| 1197 |
+
"learning_rate": 5.4025502207710184e-05,
|
| 1198 |
+
"loss": 0.5061,
|
| 1199 |
+
"step": 170
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 2.2258326563769293,
|
| 1203 |
+
"grad_norm": 0.34689504337022264,
|
| 1204 |
+
"learning_rate": 5.368080573302676e-05,
|
| 1205 |
+
"loss": 0.5016,
|
| 1206 |
+
"step": 171
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 2.2388302193338747,
|
| 1210 |
+
"grad_norm": 0.3094307656424445,
|
| 1211 |
+
"learning_rate": 5.333495485877583e-05,
|
| 1212 |
+
"loss": 0.5014,
|
| 1213 |
+
"step": 172
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 2.2518277822908206,
|
| 1217 |
+
"grad_norm": 0.3739855090857637,
|
| 1218 |
+
"learning_rate": 5.298797876818735e-05,
|
| 1219 |
+
"loss": 0.501,
|
| 1220 |
+
"step": 173
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 2.264825345247766,
|
| 1224 |
+
"grad_norm": 0.3427237300205951,
|
| 1225 |
+
"learning_rate": 5.263990673943811e-05,
|
| 1226 |
+
"loss": 0.5022,
|
| 1227 |
+
"step": 174
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 2.2778229082047114,
|
| 1231 |
+
"grad_norm": 0.2853871717746141,
|
| 1232 |
+
"learning_rate": 5.229076814318122e-05,
|
| 1233 |
+
"loss": 0.5024,
|
| 1234 |
+
"step": 175
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 2.2908204711616573,
|
| 1238 |
+
"grad_norm": 0.30137576187728127,
|
| 1239 |
+
"learning_rate": 5.194059244006779e-05,
|
| 1240 |
+
"loss": 0.4956,
|
| 1241 |
+
"step": 176
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 2.3038180341186028,
|
| 1245 |
+
"grad_norm": 0.34898425966594765,
|
| 1246 |
+
"learning_rate": 5.158940917826099e-05,
|
| 1247 |
+
"loss": 0.5048,
|
| 1248 |
+
"step": 177
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 2.316815597075548,
|
| 1252 |
+
"grad_norm": 0.3375764565690276,
|
| 1253 |
+
"learning_rate": 5.123724799094279e-05,
|
| 1254 |
+
"loss": 0.4971,
|
| 1255 |
+
"step": 178
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 2.329813160032494,
|
| 1259 |
+
"grad_norm": 0.3526352081558193,
|
| 1260 |
+
"learning_rate": 5.088413859381341e-05,
|
| 1261 |
+
"loss": 0.4953,
|
| 1262 |
+
"step": 179
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 2.3428107229894395,
|
| 1266 |
+
"grad_norm": 0.2669067122173656,
|
| 1267 |
+
"learning_rate": 5.053011078258397e-05,
|
| 1268 |
+
"loss": 0.4988,
|
| 1269 |
+
"step": 180
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 2.355808285946385,
|
| 1273 |
+
"grad_norm": 0.2634804890652626,
|
| 1274 |
+
"learning_rate": 5.017519443046226e-05,
|
| 1275 |
+
"loss": 0.5062,
|
| 1276 |
+
"step": 181
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 2.368805848903331,
|
| 1280 |
+
"grad_norm": 0.3884943325282365,
|
| 1281 |
+
"learning_rate": 4.981941948563197e-05,
|
| 1282 |
+
"loss": 0.4947,
|
| 1283 |
+
"step": 182
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 2.381803411860276,
|
| 1287 |
+
"grad_norm": 0.30824639305661866,
|
| 1288 |
+
"learning_rate": 4.94628159687257e-05,
|
| 1289 |
+
"loss": 0.4959,
|
| 1290 |
+
"step": 183
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 2.3948009748172217,
|
| 1294 |
+
"grad_norm": 0.2779177232068281,
|
| 1295 |
+
"learning_rate": 4.9105413970291747e-05,
|
| 1296 |
+
"loss": 0.5004,
|
| 1297 |
+
"step": 184
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 2.4077985377741675,
|
| 1301 |
+
"grad_norm": 0.2542309798243027,
|
| 1302 |
+
"learning_rate": 4.874724364825504e-05,
|
| 1303 |
+
"loss": 0.5059,
|
| 1304 |
+
"step": 185
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 2.420796100731113,
|
| 1308 |
+
"grad_norm": 0.2377609454443894,
|
| 1309 |
+
"learning_rate": 4.8388335225372416e-05,
|
| 1310 |
+
"loss": 0.5047,
|
| 1311 |
+
"step": 186
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 2.4337936636880584,
|
| 1315 |
+
"grad_norm": 0.2783658709624058,
|
| 1316 |
+
"learning_rate": 4.802871898668237e-05,
|
| 1317 |
+
"loss": 0.5019,
|
| 1318 |
+
"step": 187
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 2.4467912266450043,
|
| 1322 |
+
"grad_norm": 0.212526701822668,
|
| 1323 |
+
"learning_rate": 4.7668425276949546e-05,
|
| 1324 |
+
"loss": 0.5055,
|
| 1325 |
+
"step": 188
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 2.4597887896019497,
|
| 1329 |
+
"grad_norm": 0.23513126552745808,
|
| 1330 |
+
"learning_rate": 4.730748449810429e-05,
|
| 1331 |
+
"loss": 0.4955,
|
| 1332 |
+
"step": 189
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 2.472786352558895,
|
| 1336 |
+
"grad_norm": 0.24679411263913667,
|
| 1337 |
+
"learning_rate": 4.694592710667723e-05,
|
| 1338 |
+
"loss": 0.4954,
|
| 1339 |
+
"step": 190
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 2.4857839155158405,
|
| 1343 |
+
"grad_norm": 0.24566735026281666,
|
| 1344 |
+
"learning_rate": 4.658378361122936e-05,
|
| 1345 |
+
"loss": 0.4991,
|
| 1346 |
+
"step": 191
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 2.4987814784727864,
|
| 1350 |
+
"grad_norm": 0.18986094039099186,
|
| 1351 |
+
"learning_rate": 4.622108456977773e-05,
|
| 1352 |
+
"loss": 0.5029,
|
| 1353 |
+
"step": 192
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 2.511779041429732,
|
| 1357 |
+
"grad_norm": 0.23326957776437438,
|
| 1358 |
+
"learning_rate": 4.585786058721687e-05,
|
| 1359 |
+
"loss": 0.4995,
|
| 1360 |
+
"step": 193
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 2.5247766043866777,
|
| 1364 |
+
"grad_norm": 0.3107226298797518,
|
| 1365 |
+
"learning_rate": 4.549414231273633e-05,
|
| 1366 |
+
"loss": 0.5026,
|
| 1367 |
+
"step": 194
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 2.537774167343623,
|
| 1371 |
+
"grad_norm": 0.22719154064847447,
|
| 1372 |
+
"learning_rate": 4.512996043723453e-05,
|
| 1373 |
+
"loss": 0.5016,
|
| 1374 |
+
"step": 195
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 2.5507717303005686,
|
| 1378 |
+
"grad_norm": 0.1833290747151392,
|
| 1379 |
+
"learning_rate": 4.476534569072895e-05,
|
| 1380 |
+
"loss": 0.5015,
|
| 1381 |
+
"step": 196
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 2.563769293257514,
|
| 1385 |
+
"grad_norm": 0.18170499366430282,
|
| 1386 |
+
"learning_rate": 4.440032883976318e-05,
|
| 1387 |
+
"loss": 0.4987,
|
| 1388 |
+
"step": 197
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 2.57676685621446,
|
| 1392 |
+
"grad_norm": 0.22937959483532433,
|
| 1393 |
+
"learning_rate": 4.403494068481074e-05,
|
| 1394 |
+
"loss": 0.497,
|
| 1395 |
+
"step": 198
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 2.5897644191714053,
|
| 1399 |
+
"grad_norm": 0.20103120503973224,
|
| 1400 |
+
"learning_rate": 4.3669212057676145e-05,
|
| 1401 |
+
"loss": 0.5039,
|
| 1402 |
+
"step": 199
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 2.602761982128351,
|
| 1406 |
+
"grad_norm": 0.19185288266242695,
|
| 1407 |
+
"learning_rate": 4.33031738188933e-05,
|
| 1408 |
+
"loss": 0.494,
|
| 1409 |
+
"step": 200
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 2.6157595450852966,
|
| 1413 |
+
"grad_norm": 0.17010477360475862,
|
| 1414 |
+
"learning_rate": 4.293685685512142e-05,
|
| 1415 |
+
"loss": 0.4983,
|
| 1416 |
+
"step": 201
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 2.628757108042242,
|
| 1420 |
+
"grad_norm": 0.22826164302714383,
|
| 1421 |
+
"learning_rate": 4.257029207653881e-05,
|
| 1422 |
+
"loss": 0.4973,
|
| 1423 |
+
"step": 202
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 2.6417546709991875,
|
| 1427 |
+
"grad_norm": 0.1999552754693765,
|
| 1428 |
+
"learning_rate": 4.220351041423462e-05,
|
| 1429 |
+
"loss": 0.4965,
|
| 1430 |
+
"step": 203
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 2.6547522339561334,
|
| 1434 |
+
"grad_norm": 0.16313332181232204,
|
| 1435 |
+
"learning_rate": 4.183654281759888e-05,
|
| 1436 |
+
"loss": 0.5064,
|
| 1437 |
+
"step": 204
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 2.667749796913079,
|
| 1441 |
+
"grad_norm": 0.2067882657675044,
|
| 1442 |
+
"learning_rate": 4.1469420251710905e-05,
|
| 1443 |
+
"loss": 0.5006,
|
| 1444 |
+
"step": 205
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 2.680747359870024,
|
| 1448 |
+
"grad_norm": 0.19027529910668617,
|
| 1449 |
+
"learning_rate": 4.110217369472649e-05,
|
| 1450 |
+
"loss": 0.505,
|
| 1451 |
+
"step": 206
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 2.69374492282697,
|
| 1455 |
+
"grad_norm": 0.2032049934064908,
|
| 1456 |
+
"learning_rate": 4.07348341352639e-05,
|
| 1457 |
+
"loss": 0.4931,
|
| 1458 |
+
"step": 207
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 2.7067424857839155,
|
| 1462 |
+
"grad_norm": 0.16941618101686762,
|
| 1463 |
+
"learning_rate": 4.0367432569789065e-05,
|
| 1464 |
+
"loss": 0.4932,
|
| 1465 |
+
"step": 208
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 2.719740048740861,
|
| 1469 |
+
"grad_norm": 0.17079677319469672,
|
| 1470 |
+
"learning_rate": 4e-05,
|
| 1471 |
+
"loss": 0.4903,
|
| 1472 |
+
"step": 209
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 2.732737611697807,
|
| 1476 |
+
"grad_norm": 0.19810836153539363,
|
| 1477 |
+
"learning_rate": 3.963256743021095e-05,
|
| 1478 |
+
"loss": 0.4938,
|
| 1479 |
+
"step": 210
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 2.7457351746547523,
|
| 1483 |
+
"grad_norm": 0.16838352156942718,
|
| 1484 |
+
"learning_rate": 3.92651658647361e-05,
|
| 1485 |
+
"loss": 0.4932,
|
| 1486 |
+
"step": 211
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 2.7587327376116977,
|
| 1490 |
+
"grad_norm": 0.19393287722628685,
|
| 1491 |
+
"learning_rate": 3.889782630527353e-05,
|
| 1492 |
+
"loss": 0.501,
|
| 1493 |
+
"step": 212
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 2.7717303005686436,
|
| 1497 |
+
"grad_norm": 0.2322999523417372,
|
| 1498 |
+
"learning_rate": 3.853057974828911e-05,
|
| 1499 |
+
"loss": 0.5028,
|
| 1500 |
+
"step": 213
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 2.784727863525589,
|
| 1504 |
+
"grad_norm": 0.17963554890231898,
|
| 1505 |
+
"learning_rate": 3.816345718240113e-05,
|
| 1506 |
+
"loss": 0.4966,
|
| 1507 |
+
"step": 214
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 2.7977254264825344,
|
| 1511 |
+
"grad_norm": 0.17972346659387642,
|
| 1512 |
+
"learning_rate": 3.779648958576538e-05,
|
| 1513 |
+
"loss": 0.4971,
|
| 1514 |
+
"step": 215
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 2.81072298943948,
|
| 1518 |
+
"grad_norm": 0.18567150272224223,
|
| 1519 |
+
"learning_rate": 3.74297079234612e-05,
|
| 1520 |
+
"loss": 0.5,
|
| 1521 |
+
"step": 216
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 2.8237205523964257,
|
| 1525 |
+
"grad_norm": 0.13962164511716743,
|
| 1526 |
+
"learning_rate": 3.706314314487859e-05,
|
| 1527 |
+
"loss": 0.5029,
|
| 1528 |
+
"step": 217
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 2.836718115353371,
|
| 1532 |
+
"grad_norm": 0.15495008282651787,
|
| 1533 |
+
"learning_rate": 3.669682618110671e-05,
|
| 1534 |
+
"loss": 0.4963,
|
| 1535 |
+
"step": 218
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 2.849715678310317,
|
| 1539 |
+
"grad_norm": 0.14169366024663888,
|
| 1540 |
+
"learning_rate": 3.6330787942323855e-05,
|
| 1541 |
+
"loss": 0.4975,
|
| 1542 |
+
"step": 219
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 2.8627132412672625,
|
| 1546 |
+
"grad_norm": 0.17858977296408154,
|
| 1547 |
+
"learning_rate": 3.5965059315189274e-05,
|
| 1548 |
+
"loss": 0.5001,
|
| 1549 |
+
"step": 220
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 2.875710804224208,
|
| 1553 |
+
"grad_norm": 0.16013806431323374,
|
| 1554 |
+
"learning_rate": 3.559967116023683e-05,
|
| 1555 |
+
"loss": 0.5015,
|
| 1556 |
+
"step": 221
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 2.8887083671811533,
|
| 1560 |
+
"grad_norm": 0.17965163443416698,
|
| 1561 |
+
"learning_rate": 3.523465430927106e-05,
|
| 1562 |
+
"loss": 0.4978,
|
| 1563 |
+
"step": 222
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 2.901705930138099,
|
| 1567 |
+
"grad_norm": 0.180187277461439,
|
| 1568 |
+
"learning_rate": 3.4870039562765475e-05,
|
| 1569 |
+
"loss": 0.4974,
|
| 1570 |
+
"step": 223
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 2.9147034930950446,
|
| 1574 |
+
"grad_norm": 0.1838861258279284,
|
| 1575 |
+
"learning_rate": 3.4505857687263675e-05,
|
| 1576 |
+
"loss": 0.4921,
|
| 1577 |
+
"step": 224
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 2.9277010560519905,
|
| 1581 |
+
"grad_norm": 0.18286519398138992,
|
| 1582 |
+
"learning_rate": 3.414213941278314e-05,
|
| 1583 |
+
"loss": 0.5012,
|
| 1584 |
+
"step": 225
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 2.940698619008936,
|
| 1588 |
+
"grad_norm": 0.1574518878317098,
|
| 1589 |
+
"learning_rate": 3.377891543022229e-05,
|
| 1590 |
+
"loss": 0.4967,
|
| 1591 |
+
"step": 226
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 2.9536961819658814,
|
| 1595 |
+
"grad_norm": 0.18504753095964077,
|
| 1596 |
+
"learning_rate": 3.341621638877064e-05,
|
| 1597 |
+
"loss": 0.5026,
|
| 1598 |
+
"step": 227
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 2.966693744922827,
|
| 1602 |
+
"grad_norm": 0.1576894962337943,
|
| 1603 |
+
"learning_rate": 3.305407289332279e-05,
|
| 1604 |
+
"loss": 0.4944,
|
| 1605 |
+
"step": 228
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 2.9796913078797727,
|
| 1609 |
+
"grad_norm": 0.1467985899864142,
|
| 1610 |
+
"learning_rate": 3.269251550189573e-05,
|
| 1611 |
+
"loss": 0.4954,
|
| 1612 |
+
"step": 229
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 2.992688870836718,
|
| 1616 |
+
"grad_norm": 0.1515755081778688,
|
| 1617 |
+
"learning_rate": 3.2331574723050474e-05,
|
| 1618 |
+
"loss": 0.5042,
|
| 1619 |
+
"step": 230
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 3.0389926888708367,
|
| 1623 |
+
"grad_norm": 0.2765548168210541,
|
| 1624 |
+
"learning_rate": 3.197128101331764e-05,
|
| 1625 |
+
"loss": 0.4549,
|
| 1626 |
+
"step": 231
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 3.051990251827782,
|
| 1630 |
+
"grad_norm": 0.19466505214102667,
|
| 1631 |
+
"learning_rate": 3.161166477462759e-05,
|
| 1632 |
+
"loss": 0.4548,
|
| 1633 |
+
"step": 232
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 3.064987814784728,
|
| 1637 |
+
"grad_norm": 0.2880161957309376,
|
| 1638 |
+
"learning_rate": 3.125275635174497e-05,
|
| 1639 |
+
"loss": 0.4582,
|
| 1640 |
+
"step": 233
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 3.0779853777416735,
|
| 1644 |
+
"grad_norm": 0.23822280817514718,
|
| 1645 |
+
"learning_rate": 3.089458602970828e-05,
|
| 1646 |
+
"loss": 0.453,
|
| 1647 |
+
"step": 234
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 3.090982940698619,
|
| 1651 |
+
"grad_norm": 0.25800133083185917,
|
| 1652 |
+
"learning_rate": 3.0537184031274306e-05,
|
| 1653 |
+
"loss": 0.4547,
|
| 1654 |
+
"step": 235
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 3.1039805036555648,
|
| 1658 |
+
"grad_norm": 0.2384112705824712,
|
| 1659 |
+
"learning_rate": 3.0180580514368037e-05,
|
| 1660 |
+
"loss": 0.4586,
|
| 1661 |
+
"step": 236
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 3.11697806661251,
|
| 1665 |
+
"grad_norm": 0.24369875451596973,
|
| 1666 |
+
"learning_rate": 2.9824805569537747e-05,
|
| 1667 |
+
"loss": 0.4551,
|
| 1668 |
+
"step": 237
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 3.1299756295694556,
|
| 1672 |
+
"grad_norm": 0.24117461954872021,
|
| 1673 |
+
"learning_rate": 2.9469889217416045e-05,
|
| 1674 |
+
"loss": 0.4526,
|
| 1675 |
+
"step": 238
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 3.1429731925264015,
|
| 1679 |
+
"grad_norm": 0.20788905500839922,
|
| 1680 |
+
"learning_rate": 2.9115861406186593e-05,
|
| 1681 |
+
"loss": 0.4543,
|
| 1682 |
+
"step": 239
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 3.155970755483347,
|
| 1686 |
+
"grad_norm": 0.20899161474751476,
|
| 1687 |
+
"learning_rate": 2.8762752009057232e-05,
|
| 1688 |
+
"loss": 0.4523,
|
| 1689 |
+
"step": 240
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 3.1689683184402924,
|
| 1693 |
+
"grad_norm": 0.21136922172757902,
|
| 1694 |
+
"learning_rate": 2.841059082173902e-05,
|
| 1695 |
+
"loss": 0.4551,
|
| 1696 |
+
"step": 241
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 3.181965881397238,
|
| 1700 |
+
"grad_norm": 0.20064139424506391,
|
| 1701 |
+
"learning_rate": 2.805940755993223e-05,
|
| 1702 |
+
"loss": 0.4522,
|
| 1703 |
+
"step": 242
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 3.1949634443541837,
|
| 1707 |
+
"grad_norm": 0.18215269955576766,
|
| 1708 |
+
"learning_rate": 2.770923185681878e-05,
|
| 1709 |
+
"loss": 0.4543,
|
| 1710 |
+
"step": 243
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 3.207961007311129,
|
| 1714 |
+
"grad_norm": 0.20092168632579746,
|
| 1715 |
+
"learning_rate": 2.7360093260561904e-05,
|
| 1716 |
+
"loss": 0.4547,
|
| 1717 |
+
"step": 244
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 3.2209585702680745,
|
| 1721 |
+
"grad_norm": 0.15760927431037322,
|
| 1722 |
+
"learning_rate": 2.7012021231812666e-05,
|
| 1723 |
+
"loss": 0.4485,
|
| 1724 |
+
"step": 245
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 3.2339561332250204,
|
| 1728 |
+
"grad_norm": 0.1905855267036173,
|
| 1729 |
+
"learning_rate": 2.6665045141224193e-05,
|
| 1730 |
+
"loss": 0.4514,
|
| 1731 |
+
"step": 246
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 3.246953696181966,
|
| 1735 |
+
"grad_norm": 0.15059676552502058,
|
| 1736 |
+
"learning_rate": 2.6319194266973256e-05,
|
| 1737 |
+
"loss": 0.4587,
|
| 1738 |
+
"step": 247
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 3.2599512591389113,
|
| 1742 |
+
"grad_norm": 0.18536963620839997,
|
| 1743 |
+
"learning_rate": 2.597449779228983e-05,
|
| 1744 |
+
"loss": 0.4534,
|
| 1745 |
+
"step": 248
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 3.272948822095857,
|
| 1749 |
+
"grad_norm": 0.17274276141163067,
|
| 1750 |
+
"learning_rate": 2.563098480299451e-05,
|
| 1751 |
+
"loss": 0.457,
|
| 1752 |
+
"step": 249
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 3.2859463850528026,
|
| 1756 |
+
"grad_norm": 0.1562543243595631,
|
| 1757 |
+
"learning_rate": 2.5288684285044283e-05,
|
| 1758 |
+
"loss": 0.4549,
|
| 1759 |
+
"step": 250
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 3.298943948009748,
|
| 1763 |
+
"grad_norm": 0.17358175772296236,
|
| 1764 |
+
"learning_rate": 2.4947625122086585e-05,
|
| 1765 |
+
"loss": 0.4548,
|
| 1766 |
+
"step": 251
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 3.311941510966694,
|
| 1770 |
+
"grad_norm": 0.17184079642105152,
|
| 1771 |
+
"learning_rate": 2.460783609302218e-05,
|
| 1772 |
+
"loss": 0.4521,
|
| 1773 |
+
"step": 252
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 3.3249390739236393,
|
| 1777 |
+
"grad_norm": 0.16030118314009942,
|
| 1778 |
+
"learning_rate": 2.4269345869576676e-05,
|
| 1779 |
+
"loss": 0.4469,
|
| 1780 |
+
"step": 253
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 3.3379366368805847,
|
| 1784 |
+
"grad_norm": 0.16681227025456086,
|
| 1785 |
+
"learning_rate": 2.393218301388123e-05,
|
| 1786 |
+
"loss": 0.4532,
|
| 1787 |
+
"step": 254
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 3.3509341998375306,
|
| 1791 |
+
"grad_norm": 0.13889802201519397,
|
| 1792 |
+
"learning_rate": 2.35963759760624e-05,
|
| 1793 |
+
"loss": 0.4524,
|
| 1794 |
+
"step": 255
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 3.363931762794476,
|
| 1798 |
+
"grad_norm": 0.15349090525146497,
|
| 1799 |
+
"learning_rate": 2.3261953091841553e-05,
|
| 1800 |
+
"loss": 0.4546,
|
| 1801 |
+
"step": 256
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 3.3769293257514215,
|
| 1805 |
+
"grad_norm": 0.13644110770797446,
|
| 1806 |
+
"learning_rate": 2.2928942580143855e-05,
|
| 1807 |
+
"loss": 0.4526,
|
| 1808 |
+
"step": 257
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 3.3899268887083673,
|
| 1812 |
+
"grad_norm": 0.1490492694969517,
|
| 1813 |
+
"learning_rate": 2.2597372540717083e-05,
|
| 1814 |
+
"loss": 0.4568,
|
| 1815 |
+
"step": 258
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 3.4029244516653128,
|
| 1819 |
+
"grad_norm": 0.14894023043131757,
|
| 1820 |
+
"learning_rate": 2.226727095176057e-05,
|
| 1821 |
+
"loss": 0.4588,
|
| 1822 |
+
"step": 259
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 3.415922014622258,
|
| 1826 |
+
"grad_norm": 0.14995590721137517,
|
| 1827 |
+
"learning_rate": 2.1938665667564435e-05,
|
| 1828 |
+
"loss": 0.4507,
|
| 1829 |
+
"step": 260
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 3.428919577579204,
|
| 1833 |
+
"grad_norm": 0.14184790166599112,
|
| 1834 |
+
"learning_rate": 2.1611584416159106e-05,
|
| 1835 |
+
"loss": 0.4496,
|
| 1836 |
+
"step": 261
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 3.4419171405361495,
|
| 1840 |
+
"grad_norm": 0.13481813074778676,
|
| 1841 |
+
"learning_rate": 2.1286054796975696e-05,
|
| 1842 |
+
"loss": 0.4541,
|
| 1843 |
+
"step": 262
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 3.454914703493095,
|
| 1847 |
+
"grad_norm": 0.12999426318312995,
|
| 1848 |
+
"learning_rate": 2.096210427851706e-05,
|
| 1849 |
+
"loss": 0.4544,
|
| 1850 |
+
"step": 263
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 3.467912266450041,
|
| 1854 |
+
"grad_norm": 0.13239806186780637,
|
| 1855 |
+
"learning_rate": 2.063976019604006e-05,
|
| 1856 |
+
"loss": 0.451,
|
| 1857 |
+
"step": 264
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 3.4809098294069862,
|
| 1861 |
+
"grad_norm": 0.1271255029835273,
|
| 1862 |
+
"learning_rate": 2.0319049749248876e-05,
|
| 1863 |
+
"loss": 0.4487,
|
| 1864 |
+
"step": 265
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 3.4939073923639317,
|
| 1868 |
+
"grad_norm": 0.13303879175543112,
|
| 1869 |
+
"learning_rate": 2.0000000000000012e-05,
|
| 1870 |
+
"loss": 0.4522,
|
| 1871 |
+
"step": 266
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 3.506904955320877,
|
| 1875 |
+
"grad_norm": 0.12772791682528986,
|
| 1876 |
+
"learning_rate": 1.9682637870018638e-05,
|
| 1877 |
+
"loss": 0.4486,
|
| 1878 |
+
"step": 267
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 3.519902518277823,
|
| 1882 |
+
"grad_norm": 0.13368037803272537,
|
| 1883 |
+
"learning_rate": 1.9366990138627054e-05,
|
| 1884 |
+
"loss": 0.4556,
|
| 1885 |
+
"step": 268
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 3.5329000812347684,
|
| 1889 |
+
"grad_norm": 0.12998443969153295,
|
| 1890 |
+
"learning_rate": 1.9053083440484887e-05,
|
| 1891 |
+
"loss": 0.4573,
|
| 1892 |
+
"step": 269
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 3.5458976441917143,
|
| 1896 |
+
"grad_norm": 0.1299143292827015,
|
| 1897 |
+
"learning_rate": 1.8740944263341773e-05,
|
| 1898 |
+
"loss": 0.4496,
|
| 1899 |
+
"step": 270
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 3.5588952071486597,
|
| 1903 |
+
"grad_norm": 0.13501723708928842,
|
| 1904 |
+
"learning_rate": 1.8430598945802156e-05,
|
| 1905 |
+
"loss": 0.4529,
|
| 1906 |
+
"step": 271
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 3.571892770105605,
|
| 1910 |
+
"grad_norm": 0.1392141581263843,
|
| 1911 |
+
"learning_rate": 1.8122073675102935e-05,
|
| 1912 |
+
"loss": 0.4606,
|
| 1913 |
+
"step": 272
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 3.5848903330625506,
|
| 1917 |
+
"grad_norm": 0.13279583183929072,
|
| 1918 |
+
"learning_rate": 1.781539448490365e-05,
|
| 1919 |
+
"loss": 0.4559,
|
| 1920 |
+
"step": 273
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 3.5978878960194964,
|
| 1924 |
+
"grad_norm": 0.13802766481193707,
|
| 1925 |
+
"learning_rate": 1.7510587253089842e-05,
|
| 1926 |
+
"loss": 0.4525,
|
| 1927 |
+
"step": 274
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 3.610885458976442,
|
| 1931 |
+
"grad_norm": 0.1335727117344679,
|
| 1932 |
+
"learning_rate": 1.7207677699589355e-05,
|
| 1933 |
+
"loss": 0.4529,
|
| 1934 |
+
"step": 275
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 3.6238830219333877,
|
| 1938 |
+
"grad_norm": 0.12489253393946519,
|
| 1939 |
+
"learning_rate": 1.690669138420215e-05,
|
| 1940 |
+
"loss": 0.4582,
|
| 1941 |
+
"step": 276
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 3.636880584890333,
|
| 1945 |
+
"grad_norm": 0.1413569401198253,
|
| 1946 |
+
"learning_rate": 1.6607653704443457e-05,
|
| 1947 |
+
"loss": 0.4559,
|
| 1948 |
+
"step": 277
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 3.6498781478472786,
|
| 1952 |
+
"grad_norm": 0.11828655169190146,
|
| 1953 |
+
"learning_rate": 1.6310589893400804e-05,
|
| 1954 |
+
"loss": 0.4518,
|
| 1955 |
+
"step": 278
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 3.662875710804224,
|
| 1959 |
+
"grad_norm": 0.12039871469350676,
|
| 1960 |
+
"learning_rate": 1.601552501760473e-05,
|
| 1961 |
+
"loss": 0.4513,
|
| 1962 |
+
"step": 279
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 3.67587327376117,
|
| 1966 |
+
"grad_norm": 0.10972016559298864,
|
| 1967 |
+
"learning_rate": 1.5722483974913737e-05,
|
| 1968 |
+
"loss": 0.4585,
|
| 1969 |
+
"step": 280
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 3.6888708367181153,
|
| 1973 |
+
"grad_norm": 0.11605815211359002,
|
| 1974 |
+
"learning_rate": 1.5431491492413288e-05,
|
| 1975 |
+
"loss": 0.4548,
|
| 1976 |
+
"step": 281
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 3.7018683996750608,
|
| 1980 |
+
"grad_norm": 0.11113738686213914,
|
| 1981 |
+
"learning_rate": 1.5142572124329418e-05,
|
| 1982 |
+
"loss": 0.456,
|
| 1983 |
+
"step": 282
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 3.7148659626320066,
|
| 1987 |
+
"grad_norm": 0.11801948433211017,
|
| 1988 |
+
"learning_rate": 1.4855750249956718e-05,
|
| 1989 |
+
"loss": 0.4567,
|
| 1990 |
+
"step": 283
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 3.727863525588952,
|
| 1994 |
+
"grad_norm": 0.11508267709388358,
|
| 1995 |
+
"learning_rate": 1.457105007160129e-05,
|
| 1996 |
+
"loss": 0.4567,
|
| 1997 |
+
"step": 284
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 3.7408610885458975,
|
| 2001 |
+
"grad_norm": 0.11951109036290335,
|
| 2002 |
+
"learning_rate": 1.4288495612538427e-05,
|
| 2003 |
+
"loss": 0.4543,
|
| 2004 |
+
"step": 285
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 3.7538586515028434,
|
| 2008 |
+
"grad_norm": 0.11609444931011924,
|
| 2009 |
+
"learning_rate": 1.4008110714985623e-05,
|
| 2010 |
+
"loss": 0.457,
|
| 2011 |
+
"step": 286
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 3.766856214459789,
|
| 2015 |
+
"grad_norm": 0.12161842365979787,
|
| 2016 |
+
"learning_rate": 1.3729919038090627e-05,
|
| 2017 |
+
"loss": 0.4574,
|
| 2018 |
+
"step": 287
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 3.7798537774167342,
|
| 2022 |
+
"grad_norm": 0.12517775168843562,
|
| 2023 |
+
"learning_rate": 1.3453944055935151e-05,
|
| 2024 |
+
"loss": 0.4547,
|
| 2025 |
+
"step": 288
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 3.79285134037368,
|
| 2029 |
+
"grad_norm": 0.11520911340042557,
|
| 2030 |
+
"learning_rate": 1.3180209055554043e-05,
|
| 2031 |
+
"loss": 0.4513,
|
| 2032 |
+
"step": 289
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 3.8058489033306255,
|
| 2036 |
+
"grad_norm": 0.11815010738675953,
|
| 2037 |
+
"learning_rate": 1.2908737134970367e-05,
|
| 2038 |
+
"loss": 0.443,
|
| 2039 |
+
"step": 290
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 3.818846466287571,
|
| 2043 |
+
"grad_norm": 0.1162507897952791,
|
| 2044 |
+
"learning_rate": 1.2639551201246278e-05,
|
| 2045 |
+
"loss": 0.4516,
|
| 2046 |
+
"step": 291
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 3.8318440292445164,
|
| 2050 |
+
"grad_norm": 0.11366641746047221,
|
| 2051 |
+
"learning_rate": 1.2372673968550229e-05,
|
| 2052 |
+
"loss": 0.4547,
|
| 2053 |
+
"step": 292
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 3.8448415922014623,
|
| 2057 |
+
"grad_norm": 0.13504962259021788,
|
| 2058 |
+
"learning_rate": 1.2108127956240186e-05,
|
| 2059 |
+
"loss": 0.4455,
|
| 2060 |
+
"step": 293
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 3.8578391551584077,
|
| 2064 |
+
"grad_norm": 0.11026952373517614,
|
| 2065 |
+
"learning_rate": 1.1845935486963546e-05,
|
| 2066 |
+
"loss": 0.4525,
|
| 2067 |
+
"step": 294
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 3.8708367181153536,
|
| 2071 |
+
"grad_norm": 0.10668225682868658,
|
| 2072 |
+
"learning_rate": 1.158611868477344e-05,
|
| 2073 |
+
"loss": 0.4566,
|
| 2074 |
+
"step": 295
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 3.883834281072299,
|
| 2078 |
+
"grad_norm": 0.1354540165594788,
|
| 2079 |
+
"learning_rate": 1.1328699473261957e-05,
|
| 2080 |
+
"loss": 0.4472,
|
| 2081 |
+
"step": 296
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 3.8968318440292444,
|
| 2085 |
+
"grad_norm": 0.10921111595164792,
|
| 2086 |
+
"learning_rate": 1.107369957371013e-05,
|
| 2087 |
+
"loss": 0.4473,
|
| 2088 |
+
"step": 297
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 3.90982940698619,
|
| 2092 |
+
"grad_norm": 0.10437459191229037,
|
| 2093 |
+
"learning_rate": 1.0821140503255174e-05,
|
| 2094 |
+
"loss": 0.4539,
|
| 2095 |
+
"step": 298
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 3.9228269699431357,
|
| 2099 |
+
"grad_norm": 0.11124834426391973,
|
| 2100 |
+
"learning_rate": 1.0571043573074737e-05,
|
| 2101 |
+
"loss": 0.4524,
|
| 2102 |
+
"step": 299
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 3.935824532900081,
|
| 2106 |
+
"grad_norm": 0.11103073467741553,
|
| 2107 |
+
"learning_rate": 1.0323429886588743e-05,
|
| 2108 |
+
"loss": 0.4551,
|
| 2109 |
+
"step": 300
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 3.948822095857027,
|
| 2113 |
+
"grad_norm": 0.0996775517579157,
|
| 2114 |
+
"learning_rate": 1.0078320337678584e-05,
|
| 2115 |
+
"loss": 0.4542,
|
| 2116 |
+
"step": 301
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 3.9618196588139725,
|
| 2120 |
+
"grad_norm": 0.10553906139080531,
|
| 2121 |
+
"learning_rate": 9.835735608924155e-06,
|
| 2122 |
+
"loss": 0.4559,
|
| 2123 |
+
"step": 302
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 3.974817221770918,
|
| 2127 |
+
"grad_norm": 0.11276985701526075,
|
| 2128 |
+
"learning_rate": 9.595696169858542e-06,
|
| 2129 |
+
"loss": 0.4556,
|
| 2130 |
+
"step": 303
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 3.9878147847278633,
|
| 2134 |
+
"grad_norm": 0.10020067885290669,
|
| 2135 |
+
"learning_rate": 9.358222275240884e-06,
|
| 2136 |
+
"loss": 0.452,
|
| 2137 |
+
"step": 304
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 4.000812347684809,
|
| 2141 |
+
"grad_norm": 0.1015888198294778,
|
| 2142 |
+
"learning_rate": 9.123333963347166e-06,
|
| 2143 |
+
"loss": 0.4523,
|
| 2144 |
+
"step": 305
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 4.013809910641755,
|
| 2148 |
+
"grad_norm": 0.19346874584833063,
|
| 2149 |
+
"learning_rate": 8.89105105427945e-06,
|
| 2150 |
+
"loss": 0.4304,
|
| 2151 |
+
"step": 306
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 4.0268074735987005,
|
| 2155 |
+
"grad_norm": 0.1492042453109882,
|
| 2156 |
+
"learning_rate": 8.661393148293355e-06,
|
| 2157 |
+
"loss": 0.4184,
|
| 2158 |
+
"step": 307
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 4.039805036555646,
|
| 2162 |
+
"grad_norm": 0.11128451836895309,
|
| 2163 |
+
"learning_rate": 8.434379624144261e-06,
|
| 2164 |
+
"loss": 0.4272,
|
| 2165 |
+
"step": 308
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 4.052802599512591,
|
| 2169 |
+
"grad_norm": 0.15566082975695297,
|
| 2170 |
+
"learning_rate": 8.210029637452016e-06,
|
| 2171 |
+
"loss": 0.4291,
|
| 2172 |
+
"step": 309
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 4.065800162469537,
|
| 2176 |
+
"grad_norm": 0.18015489370960358,
|
| 2177 |
+
"learning_rate": 7.988362119084642e-06,
|
| 2178 |
+
"loss": 0.43,
|
| 2179 |
+
"step": 310
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 4.078797725426482,
|
| 2183 |
+
"grad_norm": 0.16617077404145308,
|
| 2184 |
+
"learning_rate": 7.769395773560874e-06,
|
| 2185 |
+
"loss": 0.4245,
|
| 2186 |
+
"step": 311
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 4.0917952883834285,
|
| 2190 |
+
"grad_norm": 0.12915804996415034,
|
| 2191 |
+
"learning_rate": 7.553149077471915e-06,
|
| 2192 |
+
"loss": 0.4205,
|
| 2193 |
+
"step": 312
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 4.104792851340374,
|
| 2197 |
+
"grad_norm": 0.12694294053103128,
|
| 2198 |
+
"learning_rate": 7.3396402779222845e-06,
|
| 2199 |
+
"loss": 0.4281,
|
| 2200 |
+
"step": 313
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 4.117790414297319,
|
| 2204 |
+
"grad_norm": 0.14590711745883797,
|
| 2205 |
+
"learning_rate": 7.128887390990198e-06,
|
| 2206 |
+
"loss": 0.4361,
|
| 2207 |
+
"step": 314
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 4.130787977254265,
|
| 2211 |
+
"grad_norm": 0.13808851249499354,
|
| 2212 |
+
"learning_rate": 6.9209082002072725e-06,
|
| 2213 |
+
"loss": 0.4215,
|
| 2214 |
+
"step": 315
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 4.14378554021121,
|
| 2218 |
+
"grad_norm": 0.129695250623056,
|
| 2219 |
+
"learning_rate": 6.715720255058e-06,
|
| 2220 |
+
"loss": 0.4252,
|
| 2221 |
+
"step": 316
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 4.156783103168156,
|
| 2225 |
+
"grad_norm": 0.11617214795717144,
|
| 2226 |
+
"learning_rate": 6.513340869498859e-06,
|
| 2227 |
+
"loss": 0.4251,
|
| 2228 |
+
"step": 317
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 4.169780666125101,
|
| 2232 |
+
"grad_norm": 0.12511546150804922,
|
| 2233 |
+
"learning_rate": 6.313787120497376e-06,
|
| 2234 |
+
"loss": 0.4223,
|
| 2235 |
+
"step": 318
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 4.182778229082047,
|
| 2239 |
+
"grad_norm": 0.11917710079150087,
|
| 2240 |
+
"learning_rate": 6.117075846591123e-06,
|
| 2241 |
+
"loss": 0.4259,
|
| 2242 |
+
"step": 319
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 4.195775792038993,
|
| 2246 |
+
"grad_norm": 0.11982991360751519,
|
| 2247 |
+
"learning_rate": 5.923223646466923e-06,
|
| 2248 |
+
"loss": 0.4267,
|
| 2249 |
+
"step": 320
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 4.208773354995938,
|
| 2253 |
+
"grad_norm": 0.11087809076543045,
|
| 2254 |
+
"learning_rate": 5.732246877560146e-06,
|
| 2255 |
+
"loss": 0.4237,
|
| 2256 |
+
"step": 321
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 4.221770917952884,
|
| 2260 |
+
"grad_norm": 0.11037591637224678,
|
| 2261 |
+
"learning_rate": 5.5441616546745646e-06,
|
| 2262 |
+
"loss": 0.4253,
|
| 2263 |
+
"step": 322
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 4.234768480909829,
|
| 2267 |
+
"grad_norm": 0.11290723637234998,
|
| 2268 |
+
"learning_rate": 5.358983848622452e-06,
|
| 2269 |
+
"loss": 0.4272,
|
| 2270 |
+
"step": 323
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 4.247766043866775,
|
| 2274 |
+
"grad_norm": 0.11769455319020229,
|
| 2275 |
+
"learning_rate": 5.176729084885508e-06,
|
| 2276 |
+
"loss": 0.4234,
|
| 2277 |
+
"step": 324
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 4.260763606823721,
|
| 2281 |
+
"grad_norm": 0.11385474199844745,
|
| 2282 |
+
"learning_rate": 4.99741274229625e-06,
|
| 2283 |
+
"loss": 0.4323,
|
| 2284 |
+
"step": 325
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 4.273761169780666,
|
| 2288 |
+
"grad_norm": 0.10749198484614475,
|
| 2289 |
+
"learning_rate": 4.821049951740442e-06,
|
| 2290 |
+
"loss": 0.4295,
|
| 2291 |
+
"step": 326
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 4.286758732737612,
|
| 2295 |
+
"grad_norm": 0.10566297009015177,
|
| 2296 |
+
"learning_rate": 4.647655594880225e-06,
|
| 2297 |
+
"loss": 0.4254,
|
| 2298 |
+
"step": 327
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 4.299756295694557,
|
| 2302 |
+
"grad_norm": 0.10419068782938447,
|
| 2303 |
+
"learning_rate": 4.4772443028985004e-06,
|
| 2304 |
+
"loss": 0.4252,
|
| 2305 |
+
"step": 328
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 4.312753858651503,
|
| 2309 |
+
"grad_norm": 0.10950077630402558,
|
| 2310 |
+
"learning_rate": 4.3098304552642385e-06,
|
| 2311 |
+
"loss": 0.4242,
|
| 2312 |
+
"step": 329
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 4.325751421608448,
|
| 2316 |
+
"grad_norm": 0.1100371440360915,
|
| 2317 |
+
"learning_rate": 4.1454281785191995e-06,
|
| 2318 |
+
"loss": 0.4197,
|
| 2319 |
+
"step": 330
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 4.338748984565394,
|
| 2323 |
+
"grad_norm": 0.10391792774677544,
|
| 2324 |
+
"learning_rate": 3.984051345085855e-06,
|
| 2325 |
+
"loss": 0.4258,
|
| 2326 |
+
"step": 331
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 4.35174654752234,
|
| 2330 |
+
"grad_norm": 0.09904939283103152,
|
| 2331 |
+
"learning_rate": 3.825713572096903e-06,
|
| 2332 |
+
"loss": 0.4184,
|
| 2333 |
+
"step": 332
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 4.364744110479285,
|
| 2337 |
+
"grad_norm": 0.10192004321049586,
|
| 2338 |
+
"learning_rate": 3.6704282202461515e-06,
|
| 2339 |
+
"loss": 0.4281,
|
| 2340 |
+
"step": 333
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 4.377741673436231,
|
| 2344 |
+
"grad_norm": 0.09890117596157007,
|
| 2345 |
+
"learning_rate": 3.518208392661184e-06,
|
| 2346 |
+
"loss": 0.4197,
|
| 2347 |
+
"step": 334
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 4.390739236393176,
|
| 2351 |
+
"grad_norm": 0.09792268745311886,
|
| 2352 |
+
"learning_rate": 3.3690669337977e-06,
|
| 2353 |
+
"loss": 0.4265,
|
| 2354 |
+
"step": 335
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 4.4037367993501215,
|
| 2358 |
+
"grad_norm": 0.09563298489182019,
|
| 2359 |
+
"learning_rate": 3.2230164283556918e-06,
|
| 2360 |
+
"loss": 0.4251,
|
| 2361 |
+
"step": 336
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 4.416734362307068,
|
| 2365 |
+
"grad_norm": 0.09937136144673961,
|
| 2366 |
+
"learning_rate": 3.080069200217497e-06,
|
| 2367 |
+
"loss": 0.4345,
|
| 2368 |
+
"step": 337
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 4.429731925264013,
|
| 2372 |
+
"grad_norm": 0.09928349883535201,
|
| 2373 |
+
"learning_rate": 2.9402373114079295e-06,
|
| 2374 |
+
"loss": 0.4285,
|
| 2375 |
+
"step": 338
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 4.442729488220959,
|
| 2379 |
+
"grad_norm": 0.09247546072284324,
|
| 2380 |
+
"learning_rate": 2.803532561076492e-06,
|
| 2381 |
+
"loss": 0.4273,
|
| 2382 |
+
"step": 339
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 4.455727051177904,
|
| 2386 |
+
"grad_norm": 0.09749820385703685,
|
| 2387 |
+
"learning_rate": 2.669966484501716e-06,
|
| 2388 |
+
"loss": 0.4269,
|
| 2389 |
+
"step": 340
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 4.46872461413485,
|
| 2393 |
+
"grad_norm": 0.09646403701008398,
|
| 2394 |
+
"learning_rate": 2.5395503521178143e-06,
|
| 2395 |
+
"loss": 0.4308,
|
| 2396 |
+
"step": 341
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 4.481722177091795,
|
| 2400 |
+
"grad_norm": 0.0936333573004958,
|
| 2401 |
+
"learning_rate": 2.4122951685636674e-06,
|
| 2402 |
+
"loss": 0.4224,
|
| 2403 |
+
"step": 342
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 4.49471974004874,
|
| 2407 |
+
"grad_norm": 0.09222486151634639,
|
| 2408 |
+
"learning_rate": 2.2882116717542634e-06,
|
| 2409 |
+
"loss": 0.4228,
|
| 2410 |
+
"step": 343
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 4.507717303005687,
|
| 2414 |
+
"grad_norm": 0.0937700330761675,
|
| 2415 |
+
"learning_rate": 2.1673103319746146e-06,
|
| 2416 |
+
"loss": 0.4251,
|
| 2417 |
+
"step": 344
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 4.520714865962632,
|
| 2421 |
+
"grad_norm": 0.09523262003402952,
|
| 2422 |
+
"learning_rate": 2.049601350996233e-06,
|
| 2423 |
+
"loss": 0.425,
|
| 2424 |
+
"step": 345
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 4.533712428919578,
|
| 2428 |
+
"grad_norm": 0.09580115361604435,
|
| 2429 |
+
"learning_rate": 1.93509466121633e-06,
|
| 2430 |
+
"loss": 0.4278,
|
| 2431 |
+
"step": 346
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 4.546709991876523,
|
| 2435 |
+
"grad_norm": 0.09551827606861985,
|
| 2436 |
+
"learning_rate": 1.8237999248197002e-06,
|
| 2437 |
+
"loss": 0.4277,
|
| 2438 |
+
"step": 347
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 4.5597075548334685,
|
| 2442 |
+
"grad_norm": 0.09398206095795404,
|
| 2443 |
+
"learning_rate": 1.7157265329634354e-06,
|
| 2444 |
+
"loss": 0.4296,
|
| 2445 |
+
"step": 348
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 4.572705117790415,
|
| 2449 |
+
"grad_norm": 0.09186446471518088,
|
| 2450 |
+
"learning_rate": 1.6108836049844434e-06,
|
| 2451 |
+
"loss": 0.4254,
|
| 2452 |
+
"step": 349
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 4.58570268074736,
|
| 2456 |
+
"grad_norm": 0.09291207003002876,
|
| 2457 |
+
"learning_rate": 1.5092799876299835e-06,
|
| 2458 |
+
"loss": 0.4228,
|
| 2459 |
+
"step": 350
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 4.598700243704306,
|
| 2463 |
+
"grad_norm": 0.09321080065504848,
|
| 2464 |
+
"learning_rate": 1.4109242543111834e-06,
|
| 2465 |
+
"loss": 0.4224,
|
| 2466 |
+
"step": 351
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 4.611697806661251,
|
| 2470 |
+
"grad_norm": 0.09820369207399382,
|
| 2471 |
+
"learning_rate": 1.3158247043795735e-06,
|
| 2472 |
+
"loss": 0.425,
|
| 2473 |
+
"step": 352
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 4.6246953696181965,
|
| 2477 |
+
"grad_norm": 0.09483780290747863,
|
| 2478 |
+
"learning_rate": 1.2239893624267852e-06,
|
| 2479 |
+
"loss": 0.4248,
|
| 2480 |
+
"step": 353
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 4.637692932575142,
|
| 2484 |
+
"grad_norm": 0.09731358909691826,
|
| 2485 |
+
"learning_rate": 1.1354259776074472e-06,
|
| 2486 |
+
"loss": 0.4235,
|
| 2487 |
+
"step": 354
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 4.650690495532087,
|
| 2491 |
+
"grad_norm": 0.0904965273633941,
|
| 2492 |
+
"learning_rate": 1.050142022985292e-06,
|
| 2493 |
+
"loss": 0.4181,
|
| 2494 |
+
"step": 355
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 4.663688058489034,
|
| 2498 |
+
"grad_norm": 0.08967404436562013,
|
| 2499 |
+
"learning_rate": 9.681446949025752e-07,
|
| 2500 |
+
"loss": 0.4294,
|
| 2501 |
+
"step": 356
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 4.676685621445979,
|
| 2505 |
+
"grad_norm": 0.09202959723546777,
|
| 2506 |
+
"learning_rate": 8.89440912372832e-07,
|
| 2507 |
+
"loss": 0.4223,
|
| 2508 |
+
"step": 357
|
| 2509 |
+
},
|
| 2510 |
+
{
|
| 2511 |
+
"epoch": 4.6896831844029245,
|
| 2512 |
+
"grad_norm": 0.0934294923741134,
|
| 2513 |
+
"learning_rate": 8.140373164970428e-07,
|
| 2514 |
+
"loss": 0.4254,
|
| 2515 |
+
"step": 358
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 4.70268074735987,
|
| 2519 |
+
"grad_norm": 0.09277475785552658,
|
| 2520 |
+
"learning_rate": 7.419402699032852e-07,
|
| 2521 |
+
"loss": 0.4264,
|
| 2522 |
+
"step": 359
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 4.715678310316815,
|
| 2526 |
+
"grad_norm": 0.0963901158463573,
|
| 2527 |
+
"learning_rate": 6.731558562097995e-07,
|
| 2528 |
+
"loss": 0.4244,
|
| 2529 |
+
"step": 360
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 4.728675873273761,
|
| 2533 |
+
"grad_norm": 0.08814663638316801,
|
| 2534 |
+
"learning_rate": 6.076898795116792e-07,
|
| 2535 |
+
"loss": 0.4191,
|
| 2536 |
+
"step": 361
|
| 2537 |
+
},
|
| 2538 |
+
{
|
| 2539 |
+
"epoch": 4.741673436230707,
|
| 2540 |
+
"grad_norm": 0.08994523311851658,
|
| 2541 |
+
"learning_rate": 5.455478638911071e-07,
|
| 2542 |
+
"loss": 0.4287,
|
| 2543 |
+
"step": 362
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 4.754670999187653,
|
| 2547 |
+
"grad_norm": 0.08992860659969752,
|
| 2548 |
+
"learning_rate": 4.867350529512261e-07,
|
| 2549 |
+
"loss": 0.4243,
|
| 2550 |
+
"step": 363
|
| 2551 |
+
},
|
| 2552 |
+
{
|
| 2553 |
+
"epoch": 4.767668562144598,
|
| 2554 |
+
"grad_norm": 0.08903822534894691,
|
| 2555 |
+
"learning_rate": 4.3125640937368373e-07,
|
| 2556 |
+
"loss": 0.4254,
|
| 2557 |
+
"step": 364
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 4.780666125101543,
|
| 2561 |
+
"grad_norm": 0.09037872867259723,
|
| 2562 |
+
"learning_rate": 3.791166144998704e-07,
|
| 2563 |
+
"loss": 0.4237,
|
| 2564 |
+
"step": 365
|
| 2565 |
+
},
|
| 2566 |
+
{
|
| 2567 |
+
"epoch": 4.793663688058489,
|
| 2568 |
+
"grad_norm": 0.08849981605290622,
|
| 2569 |
+
"learning_rate": 3.3032006793590977e-07,
|
| 2570 |
+
"loss": 0.4256,
|
| 2571 |
+
"step": 366
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 4.806661251015434,
|
| 2575 |
+
"grad_norm": 0.08939190625410524,
|
| 2576 |
+
"learning_rate": 2.848708871814054e-07,
|
| 2577 |
+
"loss": 0.432,
|
| 2578 |
+
"step": 367
|
| 2579 |
+
},
|
| 2580 |
+
{
|
| 2581 |
+
"epoch": 4.81965881397238,
|
| 2582 |
+
"grad_norm": 0.08978512061239115,
|
| 2583 |
+
"learning_rate": 2.4277290728202063e-07,
|
| 2584 |
+
"loss": 0.431,
|
| 2585 |
+
"step": 368
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 4.832656376929326,
|
| 2589 |
+
"grad_norm": 0.08749342151530978,
|
| 2590 |
+
"learning_rate": 2.040296805058528e-07,
|
| 2591 |
+
"loss": 0.4282,
|
| 2592 |
+
"step": 369
|
| 2593 |
+
},
|
| 2594 |
+
{
|
| 2595 |
+
"epoch": 4.8456539398862715,
|
| 2596 |
+
"grad_norm": 0.09394237513340908,
|
| 2597 |
+
"learning_rate": 1.6864447604370004e-07,
|
| 2598 |
+
"loss": 0.4175,
|
| 2599 |
+
"step": 370
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 4.858651502843217,
|
| 2603 |
+
"grad_norm": 0.0881034945018527,
|
| 2604 |
+
"learning_rate": 1.3662027973320614e-07,
|
| 2605 |
+
"loss": 0.4225,
|
| 2606 |
+
"step": 371
|
| 2607 |
+
},
|
| 2608 |
+
{
|
| 2609 |
+
"epoch": 4.871649065800162,
|
| 2610 |
+
"grad_norm": 0.08852561609870382,
|
| 2611 |
+
"learning_rate": 1.0795979380690657e-07,
|
| 2612 |
+
"loss": 0.4227,
|
| 2613 |
+
"step": 372
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 4.884646628757108,
|
| 2617 |
+
"grad_norm": 0.0911620154787333,
|
| 2618 |
+
"learning_rate": 8.266543666421544e-08,
|
| 2619 |
+
"loss": 0.429,
|
| 2620 |
+
"step": 373
|
| 2621 |
+
},
|
| 2622 |
+
{
|
| 2623 |
+
"epoch": 4.897644191714054,
|
| 2624 |
+
"grad_norm": 0.08685734979527214,
|
| 2625 |
+
"learning_rate": 6.073934266735303e-08,
|
| 2626 |
+
"loss": 0.4251,
|
| 2627 |
+
"step": 374
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 4.9106417546709995,
|
| 2631 |
+
"grad_norm": 0.08736267011789721,
|
| 2632 |
+
"learning_rate": 4.218336196125439e-08,
|
| 2633 |
+
"loss": 0.4222,
|
| 2634 |
+
"step": 375
|
| 2635 |
+
},
|
| 2636 |
+
{
|
| 2637 |
+
"epoch": 4.923639317627945,
|
| 2638 |
+
"grad_norm": 0.0888955083475754,
|
| 2639 |
+
"learning_rate": 2.699906031745414e-08,
|
| 2640 |
+
"loss": 0.4263,
|
| 2641 |
+
"step": 376
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 4.93663688058489,
|
| 2645 |
+
"grad_norm": 0.08888998189271619,
|
| 2646 |
+
"learning_rate": 1.5187719001943378e-08,
|
| 2647 |
+
"loss": 0.429,
|
| 2648 |
+
"step": 377
|
| 2649 |
+
},
|
| 2650 |
+
{
|
| 2651 |
+
"epoch": 4.949634443541836,
|
| 2652 |
+
"grad_norm": 0.08806089423257202,
|
| 2653 |
+
"learning_rate": 6.750334667091629e-09,
|
| 2654 |
+
"loss": 0.4241,
|
| 2655 |
+
"step": 378
|
| 2656 |
+
},
|
| 2657 |
+
{
|
| 2658 |
+
"epoch": 4.962632006498781,
|
| 2659 |
+
"grad_norm": 0.0864294126107438,
|
| 2660 |
+
"learning_rate": 1.6876192675052695e-09,
|
| 2661 |
+
"loss": 0.4205,
|
| 2662 |
+
"step": 379
|
| 2663 |
+
},
|
| 2664 |
+
{
|
| 2665 |
+
"epoch": 4.975629569455727,
|
| 2666 |
+
"grad_norm": 0.0892424352366353,
|
| 2667 |
+
"learning_rate": 0.0,
|
| 2668 |
+
"loss": 0.4228,
|
| 2669 |
+
"step": 380
|
| 2670 |
+
},
|
| 2671 |
+
{
|
| 2672 |
+
"epoch": 4.975629569455727,
|
| 2673 |
+
"step": 380,
|
| 2674 |
+
"total_flos": 9.790538054727893e+18,
|
| 2675 |
+
"train_loss": 0.17350224256515503,
|
| 2676 |
+
"train_runtime": 16013.9297,
|
| 2677 |
+
"train_samples_per_second": 12.293,
|
| 2678 |
+
"train_steps_per_second": 0.024
|
| 2679 |
+
}
|
| 2680 |
+
],
|
| 2681 |
+
"logging_steps": 1,
|
| 2682 |
+
"max_steps": 380,
|
| 2683 |
+
"num_input_tokens_seen": 0,
|
| 2684 |
+
"num_train_epochs": 5,
|
| 2685 |
+
"save_steps": 500,
|
| 2686 |
+
"stateful_callbacks": {
|
| 2687 |
+
"TrainerControl": {
|
| 2688 |
+
"args": {
|
| 2689 |
+
"should_epoch_stop": false,
|
| 2690 |
+
"should_evaluate": false,
|
| 2691 |
+
"should_log": false,
|
| 2692 |
+
"should_save": true,
|
| 2693 |
+
"should_training_stop": true
|
| 2694 |
+
},
|
| 2695 |
+
"attributes": {}
|
| 2696 |
+
}
|
| 2697 |
+
},
|
| 2698 |
+
"total_flos": 9.790538054727893e+18,
|
| 2699 |
+
"train_batch_size": 1,
|
| 2700 |
+
"trial_name": null,
|
| 2701 |
+
"trial_params": null
|
| 2702 |
+
}
|
training_loss.png
ADDED
|