End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +2387 -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: fig1_math_openr1
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# fig1_math_openr1
|
| 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: fig1_math_openr1
|
|
|
|
| 16 |
|
| 17 |
# fig1_math_openr1
|
| 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/fig1_math_openr1 dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.990689013035381,
|
| 3 |
+
"total_flos": 8.620546826447094e+18,
|
| 4 |
+
"train_loss": 0.380745083004681,
|
| 5 |
+
"train_runtime": 51129.1279,
|
| 6 |
+
"train_samples_per_second": 3.36,
|
| 7 |
+
"train_steps_per_second": 0.007
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.990689013035381,
|
| 3 |
+
"total_flos": 8.620546826447094e+18,
|
| 4 |
+
"train_loss": 0.380745083004681,
|
| 5 |
+
"train_runtime": 51129.1279,
|
| 6 |
+
"train_samples_per_second": 3.36,
|
| 7 |
+
"train_steps_per_second": 0.007
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2387 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.990689013035381,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 335,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0148975791433892,
|
| 13 |
+
"grad_norm": 5.950184932951318,
|
| 14 |
+
"learning_rate": 2.3529411764705885e-06,
|
| 15 |
+
"loss": 0.7975,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0297951582867784,
|
| 20 |
+
"grad_norm": 5.889999633747208,
|
| 21 |
+
"learning_rate": 4.705882352941177e-06,
|
| 22 |
+
"loss": 0.7918,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.0446927374301676,
|
| 27 |
+
"grad_norm": 5.479080731430823,
|
| 28 |
+
"learning_rate": 7.058823529411766e-06,
|
| 29 |
+
"loss": 0.7842,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0595903165735568,
|
| 34 |
+
"grad_norm": 4.072102472920601,
|
| 35 |
+
"learning_rate": 9.411764705882354e-06,
|
| 36 |
+
"loss": 0.7305,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.074487895716946,
|
| 41 |
+
"grad_norm": 2.0993469862660445,
|
| 42 |
+
"learning_rate": 1.1764705882352942e-05,
|
| 43 |
+
"loss": 0.6919,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.0893854748603352,
|
| 48 |
+
"grad_norm": 5.471012079326577,
|
| 49 |
+
"learning_rate": 1.4117647058823532e-05,
|
| 50 |
+
"loss": 0.7321,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.1042830540037244,
|
| 55 |
+
"grad_norm": 7.497778887994976,
|
| 56 |
+
"learning_rate": 1.647058823529412e-05,
|
| 57 |
+
"loss": 0.7089,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.1191806331471136,
|
| 62 |
+
"grad_norm": 7.744362603097892,
|
| 63 |
+
"learning_rate": 1.8823529411764708e-05,
|
| 64 |
+
"loss": 0.7259,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.1340782122905028,
|
| 69 |
+
"grad_norm": 4.336088431882978,
|
| 70 |
+
"learning_rate": 2.1176470588235296e-05,
|
| 71 |
+
"loss": 0.6722,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.148975791433892,
|
| 76 |
+
"grad_norm": 3.1425590071036407,
|
| 77 |
+
"learning_rate": 2.3529411764705884e-05,
|
| 78 |
+
"loss": 0.6323,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.16387337057728119,
|
| 83 |
+
"grad_norm": 2.293080261987849,
|
| 84 |
+
"learning_rate": 2.5882352941176475e-05,
|
| 85 |
+
"loss": 0.6058,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.1787709497206704,
|
| 90 |
+
"grad_norm": 1.5511769350436764,
|
| 91 |
+
"learning_rate": 2.8235294117647063e-05,
|
| 92 |
+
"loss": 0.5911,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.19366852886405958,
|
| 97 |
+
"grad_norm": 1.43403410737388,
|
| 98 |
+
"learning_rate": 3.0588235294117644e-05,
|
| 99 |
+
"loss": 0.5715,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.2085661080074488,
|
| 104 |
+
"grad_norm": 1.0282624052041764,
|
| 105 |
+
"learning_rate": 3.294117647058824e-05,
|
| 106 |
+
"loss": 0.5482,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.22346368715083798,
|
| 111 |
+
"grad_norm": 22.401057880346002,
|
| 112 |
+
"learning_rate": 3.529411764705883e-05,
|
| 113 |
+
"loss": 0.6398,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.2383612662942272,
|
| 118 |
+
"grad_norm": 4.036215605056668,
|
| 119 |
+
"learning_rate": 3.7647058823529415e-05,
|
| 120 |
+
"loss": 0.5932,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.2532588454376164,
|
| 125 |
+
"grad_norm": 2.1089398812874904,
|
| 126 |
+
"learning_rate": 4e-05,
|
| 127 |
+
"loss": 0.5449,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.2681564245810056,
|
| 132 |
+
"grad_norm": 1.8917019656777936,
|
| 133 |
+
"learning_rate": 4.235294117647059e-05,
|
| 134 |
+
"loss": 0.545,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.28305400372439476,
|
| 139 |
+
"grad_norm": 1.9916573775756592,
|
| 140 |
+
"learning_rate": 4.470588235294118e-05,
|
| 141 |
+
"loss": 0.5414,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.297951582867784,
|
| 146 |
+
"grad_norm": 1.8920562076710838,
|
| 147 |
+
"learning_rate": 4.705882352941177e-05,
|
| 148 |
+
"loss": 0.5407,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.3128491620111732,
|
| 153 |
+
"grad_norm": 1.0243631917296254,
|
| 154 |
+
"learning_rate": 4.941176470588236e-05,
|
| 155 |
+
"loss": 0.5197,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.32774674115456237,
|
| 160 |
+
"grad_norm": 1.8353601120734953,
|
| 161 |
+
"learning_rate": 5.176470588235295e-05,
|
| 162 |
+
"loss": 0.5242,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.3426443202979516,
|
| 167 |
+
"grad_norm": 1.0556187539851671,
|
| 168 |
+
"learning_rate": 5.411764705882354e-05,
|
| 169 |
+
"loss": 0.5115,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.3575418994413408,
|
| 174 |
+
"grad_norm": 1.6827786939863305,
|
| 175 |
+
"learning_rate": 5.6470588235294126e-05,
|
| 176 |
+
"loss": 0.5057,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.37243947858473,
|
| 181 |
+
"grad_norm": 1.3016042554320595,
|
| 182 |
+
"learning_rate": 5.8823529411764714e-05,
|
| 183 |
+
"loss": 0.5114,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.38733705772811916,
|
| 188 |
+
"grad_norm": 1.2977216399034888,
|
| 189 |
+
"learning_rate": 6.117647058823529e-05,
|
| 190 |
+
"loss": 0.4991,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.4022346368715084,
|
| 195 |
+
"grad_norm": 1.223225396686375,
|
| 196 |
+
"learning_rate": 6.352941176470589e-05,
|
| 197 |
+
"loss": 0.4941,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.4171322160148976,
|
| 202 |
+
"grad_norm": 0.9631867501185041,
|
| 203 |
+
"learning_rate": 6.588235294117648e-05,
|
| 204 |
+
"loss": 0.4906,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.43202979515828677,
|
| 209 |
+
"grad_norm": 1.2189198129233703,
|
| 210 |
+
"learning_rate": 6.823529411764707e-05,
|
| 211 |
+
"loss": 0.4913,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.44692737430167595,
|
| 216 |
+
"grad_norm": 0.7374132716188752,
|
| 217 |
+
"learning_rate": 7.058823529411765e-05,
|
| 218 |
+
"loss": 0.4785,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.4618249534450652,
|
| 223 |
+
"grad_norm": 4.329279729767168,
|
| 224 |
+
"learning_rate": 7.294117647058824e-05,
|
| 225 |
+
"loss": 0.4855,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.4767225325884544,
|
| 230 |
+
"grad_norm": 1.9935350979555255,
|
| 231 |
+
"learning_rate": 7.529411764705883e-05,
|
| 232 |
+
"loss": 0.5068,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.49162011173184356,
|
| 237 |
+
"grad_norm": 1.0099023827824438,
|
| 238 |
+
"learning_rate": 7.764705882352942e-05,
|
| 239 |
+
"loss": 0.4878,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.5065176908752328,
|
| 244 |
+
"grad_norm": 1.453165427026921,
|
| 245 |
+
"learning_rate": 8e-05,
|
| 246 |
+
"loss": 0.4887,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.521415270018622,
|
| 251 |
+
"grad_norm": 1.0681365388503938,
|
| 252 |
+
"learning_rate": 7.999782132320701e-05,
|
| 253 |
+
"loss": 0.4792,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.5363128491620112,
|
| 258 |
+
"grad_norm": 1.2991278121605818,
|
| 259 |
+
"learning_rate": 7.999128553015966e-05,
|
| 260 |
+
"loss": 0.4746,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.5512104283054003,
|
| 265 |
+
"grad_norm": 0.9705929073068399,
|
| 266 |
+
"learning_rate": 7.998039333282696e-05,
|
| 267 |
+
"loss": 0.47,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.5661080074487895,
|
| 272 |
+
"grad_norm": 1.288262936234187,
|
| 273 |
+
"learning_rate": 7.996514591773782e-05,
|
| 274 |
+
"loss": 0.4758,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.5810055865921788,
|
| 279 |
+
"grad_norm": 0.6816553781708893,
|
| 280 |
+
"learning_rate": 7.99455449458517e-05,
|
| 281 |
+
"loss": 0.4627,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.595903165735568,
|
| 286 |
+
"grad_norm": 0.9231036421804909,
|
| 287 |
+
"learning_rate": 7.992159255237773e-05,
|
| 288 |
+
"loss": 0.4691,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.6108007448789572,
|
| 293 |
+
"grad_norm": 1.1402552499674083,
|
| 294 |
+
"learning_rate": 7.989329134654207e-05,
|
| 295 |
+
"loss": 0.4638,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.6256983240223464,
|
| 300 |
+
"grad_norm": 0.7253677973155603,
|
| 301 |
+
"learning_rate": 7.986064441130378e-05,
|
| 302 |
+
"loss": 0.4593,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.6405959031657356,
|
| 307 |
+
"grad_norm": 1.1918043936517428,
|
| 308 |
+
"learning_rate": 7.982365530301885e-05,
|
| 309 |
+
"loss": 0.4624,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.6554934823091247,
|
| 314 |
+
"grad_norm": 1.0659452922693904,
|
| 315 |
+
"learning_rate": 7.978232805105288e-05,
|
| 316 |
+
"loss": 0.4514,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.6703910614525139,
|
| 321 |
+
"grad_norm": 0.9974435758912656,
|
| 322 |
+
"learning_rate": 7.97366671573421e-05,
|
| 323 |
+
"loss": 0.4495,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.6852886405959032,
|
| 328 |
+
"grad_norm": 0.741244345164511,
|
| 329 |
+
"learning_rate": 7.968667759590298e-05,
|
| 330 |
+
"loss": 0.4498,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.7001862197392924,
|
| 335 |
+
"grad_norm": 0.700212224489924,
|
| 336 |
+
"learning_rate": 7.96323648122904e-05,
|
| 337 |
+
"loss": 0.4496,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.7150837988826816,
|
| 342 |
+
"grad_norm": 0.6861544024192645,
|
| 343 |
+
"learning_rate": 7.957373472300442e-05,
|
| 344 |
+
"loss": 0.4425,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.7299813780260708,
|
| 349 |
+
"grad_norm": 0.9097284558328156,
|
| 350 |
+
"learning_rate": 7.951079371484578e-05,
|
| 351 |
+
"loss": 0.4435,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.74487895716946,
|
| 356 |
+
"grad_norm": 0.8086828171768753,
|
| 357 |
+
"learning_rate": 7.944354864422016e-05,
|
| 358 |
+
"loss": 0.4427,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.7597765363128491,
|
| 363 |
+
"grad_norm": 0.7336340975598995,
|
| 364 |
+
"learning_rate": 7.937200683639133e-05,
|
| 365 |
+
"loss": 0.4418,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.7746741154562383,
|
| 370 |
+
"grad_norm": 0.709266378863673,
|
| 371 |
+
"learning_rate": 7.929617608468308e-05,
|
| 372 |
+
"loss": 0.4413,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.7895716945996276,
|
| 377 |
+
"grad_norm": 0.6997957286653358,
|
| 378 |
+
"learning_rate": 7.921606464963037e-05,
|
| 379 |
+
"loss": 0.4343,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.8044692737430168,
|
| 384 |
+
"grad_norm": 0.6312526710744601,
|
| 385 |
+
"learning_rate": 7.913168125807943e-05,
|
| 386 |
+
"loss": 0.4357,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.819366852886406,
|
| 391 |
+
"grad_norm": 0.8682993581299321,
|
| 392 |
+
"learning_rate": 7.90430351022371e-05,
|
| 393 |
+
"loss": 0.4256,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.8342644320297952,
|
| 398 |
+
"grad_norm": 1.0211685354189273,
|
| 399 |
+
"learning_rate": 7.895013583866949e-05,
|
| 400 |
+
"loss": 0.4383,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.8491620111731844,
|
| 405 |
+
"grad_norm": 0.5942703334288042,
|
| 406 |
+
"learning_rate": 7.88529935872501e-05,
|
| 407 |
+
"loss": 0.4266,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.8640595903165735,
|
| 412 |
+
"grad_norm": 0.4905469818523975,
|
| 413 |
+
"learning_rate": 7.875161893005736e-05,
|
| 414 |
+
"loss": 0.4275,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.8789571694599627,
|
| 419 |
+
"grad_norm": 0.713524523381961,
|
| 420 |
+
"learning_rate": 7.864602291022193e-05,
|
| 421 |
+
"loss": 0.425,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.8938547486033519,
|
| 426 |
+
"grad_norm": 0.7215883306108987,
|
| 427 |
+
"learning_rate": 7.85362170307237e-05,
|
| 428 |
+
"loss": 0.4296,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.9087523277467412,
|
| 433 |
+
"grad_norm": 0.5476669418552049,
|
| 434 |
+
"learning_rate": 7.842221325313873e-05,
|
| 435 |
+
"loss": 0.4264,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.9236499068901304,
|
| 440 |
+
"grad_norm": 0.5026608565405364,
|
| 441 |
+
"learning_rate": 7.830402399633624e-05,
|
| 442 |
+
"loss": 0.4279,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.9385474860335196,
|
| 447 |
+
"grad_norm": 0.43642895836746987,
|
| 448 |
+
"learning_rate": 7.818166213512581e-05,
|
| 449 |
+
"loss": 0.4231,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.9534450651769087,
|
| 454 |
+
"grad_norm": 0.5516886415086357,
|
| 455 |
+
"learning_rate": 7.805514099885479e-05,
|
| 456 |
+
"loss": 0.4286,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.9683426443202979,
|
| 461 |
+
"grad_norm": 0.6202502097645083,
|
| 462 |
+
"learning_rate": 7.792447436995634e-05,
|
| 463 |
+
"loss": 0.4238,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.9832402234636871,
|
| 468 |
+
"grad_norm": 0.8483095514593049,
|
| 469 |
+
"learning_rate": 7.778967648244807e-05,
|
| 470 |
+
"loss": 0.4251,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.9981378026070763,
|
| 475 |
+
"grad_norm": 0.9010008832838037,
|
| 476 |
+
"learning_rate": 7.765076202038145e-05,
|
| 477 |
+
"loss": 0.4227,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 1.0130353817504656,
|
| 482 |
+
"grad_norm": 1.1210899234881495,
|
| 483 |
+
"learning_rate": 7.750774611624222e-05,
|
| 484 |
+
"loss": 0.7678,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 1.0279329608938548,
|
| 489 |
+
"grad_norm": 1.4294187108260912,
|
| 490 |
+
"learning_rate": 7.736064434930193e-05,
|
| 491 |
+
"loss": 0.4298,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 1.042830540037244,
|
| 496 |
+
"grad_norm": 0.5162696432741285,
|
| 497 |
+
"learning_rate": 7.720947274392087e-05,
|
| 498 |
+
"loss": 0.4051,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 1.0577281191806331,
|
| 503 |
+
"grad_norm": 1.2710462444765749,
|
| 504 |
+
"learning_rate": 7.705424776780249e-05,
|
| 505 |
+
"loss": 0.4149,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.0726256983240223,
|
| 510 |
+
"grad_norm": 0.7995934416533542,
|
| 511 |
+
"learning_rate": 7.689498633019941e-05,
|
| 512 |
+
"loss": 0.4007,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.0875232774674115,
|
| 517 |
+
"grad_norm": 0.880390966869298,
|
| 518 |
+
"learning_rate": 7.673170578007157e-05,
|
| 519 |
+
"loss": 0.4116,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 1.1024208566108007,
|
| 524 |
+
"grad_norm": 0.7628454204466086,
|
| 525 |
+
"learning_rate": 7.656442390419622e-05,
|
| 526 |
+
"loss": 0.4008,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.1173184357541899,
|
| 531 |
+
"grad_norm": 0.5370866632430045,
|
| 532 |
+
"learning_rate": 7.63931589252304e-05,
|
| 533 |
+
"loss": 0.3935,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.132216014897579,
|
| 538 |
+
"grad_norm": 0.6503753033899171,
|
| 539 |
+
"learning_rate": 7.621792949972588e-05,
|
| 540 |
+
"loss": 0.3983,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.1471135940409685,
|
| 545 |
+
"grad_norm": 0.483185187236749,
|
| 546 |
+
"learning_rate": 7.603875471609677e-05,
|
| 547 |
+
"loss": 0.4092,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.1620111731843576,
|
| 552 |
+
"grad_norm": 0.5469246081737635,
|
| 553 |
+
"learning_rate": 7.585565409254025e-05,
|
| 554 |
+
"loss": 0.3988,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.1769087523277468,
|
| 559 |
+
"grad_norm": 0.3809737733256841,
|
| 560 |
+
"learning_rate": 7.566864757491027e-05,
|
| 561 |
+
"loss": 0.4049,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.191806331471136,
|
| 566 |
+
"grad_norm": 0.4978345458094043,
|
| 567 |
+
"learning_rate": 7.547775553454485e-05,
|
| 568 |
+
"loss": 0.3991,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.2067039106145252,
|
| 573 |
+
"grad_norm": 0.3419277603644534,
|
| 574 |
+
"learning_rate": 7.528299876604689e-05,
|
| 575 |
+
"loss": 0.4015,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.2216014897579144,
|
| 580 |
+
"grad_norm": 0.3978591421270835,
|
| 581 |
+
"learning_rate": 7.508439848501899e-05,
|
| 582 |
+
"loss": 0.3948,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 1.2364990689013036,
|
| 587 |
+
"grad_norm": 0.3215672869140669,
|
| 588 |
+
"learning_rate": 7.488197632575232e-05,
|
| 589 |
+
"loss": 0.3946,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.2513966480446927,
|
| 594 |
+
"grad_norm": 0.2805092237683431,
|
| 595 |
+
"learning_rate": 7.467575433886989e-05,
|
| 596 |
+
"loss": 0.3925,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.266294227188082,
|
| 601 |
+
"grad_norm": 0.29668081700935095,
|
| 602 |
+
"learning_rate": 7.44657549889246e-05,
|
| 603 |
+
"loss": 0.3944,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.2811918063314711,
|
| 608 |
+
"grad_norm": 0.32093150433950507,
|
| 609 |
+
"learning_rate": 7.425200115195193e-05,
|
| 610 |
+
"loss": 0.395,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.2960893854748603,
|
| 615 |
+
"grad_norm": 0.3114671727422004,
|
| 616 |
+
"learning_rate": 7.403451611297808e-05,
|
| 617 |
+
"loss": 0.3896,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.3109869646182495,
|
| 622 |
+
"grad_norm": 0.2621069849515514,
|
| 623 |
+
"learning_rate": 7.381332356348343e-05,
|
| 624 |
+
"loss": 0.3972,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.3258845437616387,
|
| 629 |
+
"grad_norm": 0.35041652635951187,
|
| 630 |
+
"learning_rate": 7.358844759882168e-05,
|
| 631 |
+
"loss": 0.3947,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.3407821229050279,
|
| 636 |
+
"grad_norm": 0.35165133417817274,
|
| 637 |
+
"learning_rate": 7.335991271559512e-05,
|
| 638 |
+
"loss": 0.3924,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.355679702048417,
|
| 643 |
+
"grad_norm": 0.3622625923423102,
|
| 644 |
+
"learning_rate": 7.312774380898608e-05,
|
| 645 |
+
"loss": 0.3802,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.3705772811918062,
|
| 650 |
+
"grad_norm": 0.34568371596915276,
|
| 651 |
+
"learning_rate": 7.289196617004499e-05,
|
| 652 |
+
"loss": 0.3921,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.3854748603351954,
|
| 657 |
+
"grad_norm": 0.36106236048997714,
|
| 658 |
+
"learning_rate": 7.265260548293535e-05,
|
| 659 |
+
"loss": 0.3852,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.4003724394785848,
|
| 664 |
+
"grad_norm": 0.3591694116875136,
|
| 665 |
+
"learning_rate": 7.24096878221359e-05,
|
| 666 |
+
"loss": 0.3864,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.415270018621974,
|
| 671 |
+
"grad_norm": 0.4611887631357433,
|
| 672 |
+
"learning_rate": 7.216323964960013e-05,
|
| 673 |
+
"loss": 0.3917,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.4301675977653632,
|
| 678 |
+
"grad_norm": 0.5900177988285087,
|
| 679 |
+
"learning_rate": 7.191328781187374e-05,
|
| 680 |
+
"loss": 0.3889,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.4450651769087524,
|
| 685 |
+
"grad_norm": 0.6476785738427469,
|
| 686 |
+
"learning_rate": 7.165985953717017e-05,
|
| 687 |
+
"loss": 0.3976,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.4599627560521415,
|
| 692 |
+
"grad_norm": 0.5959898548929913,
|
| 693 |
+
"learning_rate": 7.140298243240444e-05,
|
| 694 |
+
"loss": 0.3991,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 1.4748603351955307,
|
| 699 |
+
"grad_norm": 0.45154508108061203,
|
| 700 |
+
"learning_rate": 7.114268448018589e-05,
|
| 701 |
+
"loss": 0.395,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.48975791433892,
|
| 706 |
+
"grad_norm": 0.41405552449106015,
|
| 707 |
+
"learning_rate": 7.087899403576992e-05,
|
| 708 |
+
"loss": 0.3904,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.504655493482309,
|
| 713 |
+
"grad_norm": 0.550596726311639,
|
| 714 |
+
"learning_rate": 7.06119398239691e-05,
|
| 715 |
+
"loss": 0.3809,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 1.5195530726256983,
|
| 720 |
+
"grad_norm": 0.6087570876386633,
|
| 721 |
+
"learning_rate": 7.034155093602413e-05,
|
| 722 |
+
"loss": 0.3962,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.5344506517690877,
|
| 727 |
+
"grad_norm": 0.533129391668596,
|
| 728 |
+
"learning_rate": 7.006785682643479e-05,
|
| 729 |
+
"loss": 0.3976,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.5493482309124769,
|
| 734 |
+
"grad_norm": 0.43458513735835697,
|
| 735 |
+
"learning_rate": 6.979088730975128e-05,
|
| 736 |
+
"loss": 0.3917,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.564245810055866,
|
| 741 |
+
"grad_norm": 0.3518341619336429,
|
| 742 |
+
"learning_rate": 6.951067255732655e-05,
|
| 743 |
+
"loss": 0.3858,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.5791433891992552,
|
| 748 |
+
"grad_norm": 0.40015247854184544,
|
| 749 |
+
"learning_rate": 6.92272430940295e-05,
|
| 750 |
+
"loss": 0.3864,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.5940409683426444,
|
| 755 |
+
"grad_norm": 0.3910716089734902,
|
| 756 |
+
"learning_rate": 6.894062979491987e-05,
|
| 757 |
+
"loss": 0.3883,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.6089385474860336,
|
| 762 |
+
"grad_norm": 0.35066296337841696,
|
| 763 |
+
"learning_rate": 6.865086388188476e-05,
|
| 764 |
+
"loss": 0.386,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.6238361266294228,
|
| 769 |
+
"grad_norm": 0.3072713840073755,
|
| 770 |
+
"learning_rate": 6.835797692023774e-05,
|
| 771 |
+
"loss": 0.39,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 1.638733705772812,
|
| 776 |
+
"grad_norm": 0.3550143349129471,
|
| 777 |
+
"learning_rate": 6.806200081528008e-05,
|
| 778 |
+
"loss": 0.3872,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.6536312849162011,
|
| 783 |
+
"grad_norm": 0.37053547013887106,
|
| 784 |
+
"learning_rate": 6.776296780882537e-05,
|
| 785 |
+
"loss": 0.3813,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.6685288640595903,
|
| 790 |
+
"grad_norm": 0.24071852433891697,
|
| 791 |
+
"learning_rate": 6.746091047568716e-05,
|
| 792 |
+
"loss": 0.3812,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 1.6834264432029795,
|
| 797 |
+
"grad_norm": 0.3042807960699796,
|
| 798 |
+
"learning_rate": 6.715586172013054e-05,
|
| 799 |
+
"loss": 0.3835,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 1.6983240223463687,
|
| 804 |
+
"grad_norm": 0.3538152445413312,
|
| 805 |
+
"learning_rate": 6.684785477228777e-05,
|
| 806 |
+
"loss": 0.3813,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.7132216014897579,
|
| 811 |
+
"grad_norm": 0.24086260757195502,
|
| 812 |
+
"learning_rate": 6.653692318453831e-05,
|
| 813 |
+
"loss": 0.3852,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 1.728119180633147,
|
| 818 |
+
"grad_norm": 0.3025847544952239,
|
| 819 |
+
"learning_rate": 6.622310082785384e-05,
|
| 820 |
+
"loss": 0.3913,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 1.7430167597765363,
|
| 825 |
+
"grad_norm": 0.31641711838551906,
|
| 826 |
+
"learning_rate": 6.590642188810869e-05,
|
| 827 |
+
"loss": 0.3827,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 1.7579143389199254,
|
| 832 |
+
"grad_norm": 0.2688168797114581,
|
| 833 |
+
"learning_rate": 6.558692086235565e-05,
|
| 834 |
+
"loss": 0.3744,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 1.7728119180633146,
|
| 839 |
+
"grad_norm": 0.2984297462672916,
|
| 840 |
+
"learning_rate": 6.526463255506828e-05,
|
| 841 |
+
"loss": 0.3811,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 1.7877094972067038,
|
| 846 |
+
"grad_norm": 0.30746963837396896,
|
| 847 |
+
"learning_rate": 6.493959207434934e-05,
|
| 848 |
+
"loss": 0.3758,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.802607076350093,
|
| 853 |
+
"grad_norm": 0.3230084067714464,
|
| 854 |
+
"learning_rate": 6.461183482810646e-05,
|
| 855 |
+
"loss": 0.3853,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 1.8175046554934822,
|
| 860 |
+
"grad_norm": 0.4000243849303593,
|
| 861 |
+
"learning_rate": 6.42813965201949e-05,
|
| 862 |
+
"loss": 0.3882,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 1.8324022346368714,
|
| 867 |
+
"grad_norm": 0.4288088964712755,
|
| 868 |
+
"learning_rate": 6.394831314652835e-05,
|
| 869 |
+
"loss": 0.3858,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 1.8472998137802608,
|
| 874 |
+
"grad_norm": 0.5085831972309272,
|
| 875 |
+
"learning_rate": 6.361262099115761e-05,
|
| 876 |
+
"loss": 0.3856,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 1.86219739292365,
|
| 881 |
+
"grad_norm": 0.6105698024621092,
|
| 882 |
+
"learning_rate": 6.327435662231812e-05,
|
| 883 |
+
"loss": 0.3849,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 1.8770949720670391,
|
| 888 |
+
"grad_norm": 0.5824359200910605,
|
| 889 |
+
"learning_rate": 6.293355688844637e-05,
|
| 890 |
+
"loss": 0.3866,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 1.8919925512104283,
|
| 895 |
+
"grad_norm": 0.44326416200929236,
|
| 896 |
+
"learning_rate": 6.259025891416594e-05,
|
| 897 |
+
"loss": 0.3737,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 1.9068901303538175,
|
| 902 |
+
"grad_norm": 0.3430006009849836,
|
| 903 |
+
"learning_rate": 6.224450009624332e-05,
|
| 904 |
+
"loss": 0.3741,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 1.9217877094972067,
|
| 909 |
+
"grad_norm": 0.3048045239289814,
|
| 910 |
+
"learning_rate": 6.18963180995141e-05,
|
| 911 |
+
"loss": 0.3767,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 1.9366852886405959,
|
| 916 |
+
"grad_norm": 0.3664037873157842,
|
| 917 |
+
"learning_rate": 6.154575085278012e-05,
|
| 918 |
+
"loss": 0.3857,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 1.9515828677839853,
|
| 923 |
+
"grad_norm": 0.3595451501590318,
|
| 924 |
+
"learning_rate": 6.119283654467761e-05,
|
| 925 |
+
"loss": 0.3806,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 1.9664804469273744,
|
| 930 |
+
"grad_norm": 0.3076574382248462,
|
| 931 |
+
"learning_rate": 6.083761361951722e-05,
|
| 932 |
+
"loss": 0.3802,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 1.9813780260707636,
|
| 937 |
+
"grad_norm": 0.25896414972948856,
|
| 938 |
+
"learning_rate": 6.048012077309612e-05,
|
| 939 |
+
"loss": 0.3773,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.9962756052141528,
|
| 944 |
+
"grad_norm": 0.2438114619698701,
|
| 945 |
+
"learning_rate": 6.01203969484827e-05,
|
| 946 |
+
"loss": 0.3832,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 2.011173184357542,
|
| 951 |
+
"grad_norm": 0.4880986651628094,
|
| 952 |
+
"learning_rate": 5.975848133177442e-05,
|
| 953 |
+
"loss": 0.7025,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 2.026070763500931,
|
| 958 |
+
"grad_norm": 0.7683631863694373,
|
| 959 |
+
"learning_rate": 5.939441334782901e-05,
|
| 960 |
+
"loss": 0.3581,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 2.0409683426443204,
|
| 965 |
+
"grad_norm": 1.0088180311972472,
|
| 966 |
+
"learning_rate": 5.9028232655969866e-05,
|
| 967 |
+
"loss": 0.3662,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 2.0558659217877095,
|
| 972 |
+
"grad_norm": 0.8036028379230191,
|
| 973 |
+
"learning_rate": 5.865997914566577e-05,
|
| 974 |
+
"loss": 0.3606,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 2.0707635009310987,
|
| 979 |
+
"grad_norm": 0.6488117999773151,
|
| 980 |
+
"learning_rate": 5.8289692932185546e-05,
|
| 981 |
+
"loss": 0.3619,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 2.085661080074488,
|
| 986 |
+
"grad_norm": 0.6603945376014646,
|
| 987 |
+
"learning_rate": 5.791741435222821e-05,
|
| 988 |
+
"loss": 0.3613,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 2.100558659217877,
|
| 993 |
+
"grad_norm": 0.6137565370101866,
|
| 994 |
+
"learning_rate": 5.7543183959528886e-05,
|
| 995 |
+
"loss": 0.3523,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 2.1154562383612663,
|
| 1000 |
+
"grad_norm": 0.6393236118969376,
|
| 1001 |
+
"learning_rate": 5.716704252044116e-05,
|
| 1002 |
+
"loss": 0.3543,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 2.1303538175046555,
|
| 1007 |
+
"grad_norm": 0.37602818408299177,
|
| 1008 |
+
"learning_rate": 5.678903100949625e-05,
|
| 1009 |
+
"loss": 0.3564,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 2.1452513966480447,
|
| 1014 |
+
"grad_norm": 0.4873243740997193,
|
| 1015 |
+
"learning_rate": 5.640919060493948e-05,
|
| 1016 |
+
"loss": 0.3547,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 2.160148975791434,
|
| 1021 |
+
"grad_norm": 0.399733374633036,
|
| 1022 |
+
"learning_rate": 5.602756268424457e-05,
|
| 1023 |
+
"loss": 0.3521,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 2.175046554934823,
|
| 1028 |
+
"grad_norm": 0.38098879738078906,
|
| 1029 |
+
"learning_rate": 5.564418881960624e-05,
|
| 1030 |
+
"loss": 0.3525,
|
| 1031 |
+
"step": 146
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 2.189944134078212,
|
| 1035 |
+
"grad_norm": 0.3112584196059825,
|
| 1036 |
+
"learning_rate": 5.5259110773411596e-05,
|
| 1037 |
+
"loss": 0.3578,
|
| 1038 |
+
"step": 147
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 2.2048417132216014,
|
| 1042 |
+
"grad_norm": 0.33974576612810525,
|
| 1043 |
+
"learning_rate": 5.487237049369075e-05,
|
| 1044 |
+
"loss": 0.3485,
|
| 1045 |
+
"step": 148
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 2.2197392923649906,
|
| 1049 |
+
"grad_norm": 0.31599699558663985,
|
| 1050 |
+
"learning_rate": 5.448401010954733e-05,
|
| 1051 |
+
"loss": 0.3482,
|
| 1052 |
+
"step": 149
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 2.2346368715083798,
|
| 1056 |
+
"grad_norm": 0.23588411232355225,
|
| 1057 |
+
"learning_rate": 5.4094071926569146e-05,
|
| 1058 |
+
"loss": 0.3465,
|
| 1059 |
+
"step": 150
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 2.249534450651769,
|
| 1063 |
+
"grad_norm": 0.259141065976224,
|
| 1064 |
+
"learning_rate": 5.370259842221972e-05,
|
| 1065 |
+
"loss": 0.3574,
|
| 1066 |
+
"step": 151
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 2.264432029795158,
|
| 1070 |
+
"grad_norm": 0.2948627119507419,
|
| 1071 |
+
"learning_rate": 5.330963224121096e-05,
|
| 1072 |
+
"loss": 0.356,
|
| 1073 |
+
"step": 152
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 2.2793296089385473,
|
| 1077 |
+
"grad_norm": 0.2398464878022089,
|
| 1078 |
+
"learning_rate": 5.291521619085785e-05,
|
| 1079 |
+
"loss": 0.3536,
|
| 1080 |
+
"step": 153
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 2.294227188081937,
|
| 1084 |
+
"grad_norm": 0.2554013267182894,
|
| 1085 |
+
"learning_rate": 5.251939323641516e-05,
|
| 1086 |
+
"loss": 0.3494,
|
| 1087 |
+
"step": 154
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 2.3091247672253257,
|
| 1091 |
+
"grad_norm": 0.2781655892263444,
|
| 1092 |
+
"learning_rate": 5.212220649639715e-05,
|
| 1093 |
+
"loss": 0.3511,
|
| 1094 |
+
"step": 155
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 2.3240223463687153,
|
| 1098 |
+
"grad_norm": 0.22065610655196213,
|
| 1099 |
+
"learning_rate": 5.172369923788046e-05,
|
| 1100 |
+
"loss": 0.3589,
|
| 1101 |
+
"step": 156
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 2.338919925512104,
|
| 1105 |
+
"grad_norm": 0.2632172433601213,
|
| 1106 |
+
"learning_rate": 5.132391487179088e-05,
|
| 1107 |
+
"loss": 0.3537,
|
| 1108 |
+
"step": 157
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 2.3538175046554937,
|
| 1112 |
+
"grad_norm": 0.18801127961637412,
|
| 1113 |
+
"learning_rate": 5.092289694817446e-05,
|
| 1114 |
+
"loss": 0.3483,
|
| 1115 |
+
"step": 158
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 2.368715083798883,
|
| 1119 |
+
"grad_norm": 0.2368052254172045,
|
| 1120 |
+
"learning_rate": 5.052068915145336e-05,
|
| 1121 |
+
"loss": 0.3571,
|
| 1122 |
+
"step": 159
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 2.383612662942272,
|
| 1126 |
+
"grad_norm": 0.23655539210427956,
|
| 1127 |
+
"learning_rate": 5.011733529566723e-05,
|
| 1128 |
+
"loss": 0.3446,
|
| 1129 |
+
"step": 160
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 2.398510242085661,
|
| 1133 |
+
"grad_norm": 0.2138112386109768,
|
| 1134 |
+
"learning_rate": 4.971287931970033e-05,
|
| 1135 |
+
"loss": 0.3482,
|
| 1136 |
+
"step": 161
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 2.4134078212290504,
|
| 1140 |
+
"grad_norm": 0.23467262592443583,
|
| 1141 |
+
"learning_rate": 4.9307365282495075e-05,
|
| 1142 |
+
"loss": 0.3473,
|
| 1143 |
+
"step": 162
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 2.4283054003724396,
|
| 1147 |
+
"grad_norm": 0.1804084648863834,
|
| 1148 |
+
"learning_rate": 4.890083735825258e-05,
|
| 1149 |
+
"loss": 0.3531,
|
| 1150 |
+
"step": 163
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 2.4432029795158288,
|
| 1154 |
+
"grad_norm": 0.22285709273589918,
|
| 1155 |
+
"learning_rate": 4.849333983162056e-05,
|
| 1156 |
+
"loss": 0.3516,
|
| 1157 |
+
"step": 164
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 2.458100558659218,
|
| 1161 |
+
"grad_norm": 0.14828204605953096,
|
| 1162 |
+
"learning_rate": 4.808491709286921e-05,
|
| 1163 |
+
"loss": 0.356,
|
| 1164 |
+
"step": 165
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 2.472998137802607,
|
| 1168 |
+
"grad_norm": 0.1797938362516586,
|
| 1169 |
+
"learning_rate": 4.76756136330557e-05,
|
| 1170 |
+
"loss": 0.3491,
|
| 1171 |
+
"step": 166
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 2.4878957169459963,
|
| 1175 |
+
"grad_norm": 0.15466564418943565,
|
| 1176 |
+
"learning_rate": 4.726547403917746e-05,
|
| 1177 |
+
"loss": 0.3435,
|
| 1178 |
+
"step": 167
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 2.5027932960893855,
|
| 1182 |
+
"grad_norm": 0.1866313977972178,
|
| 1183 |
+
"learning_rate": 4.685454298931527e-05,
|
| 1184 |
+
"loss": 0.3506,
|
| 1185 |
+
"step": 168
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 2.5176908752327747,
|
| 1189 |
+
"grad_norm": 0.15144628774380284,
|
| 1190 |
+
"learning_rate": 4.6442865247766203e-05,
|
| 1191 |
+
"loss": 0.3547,
|
| 1192 |
+
"step": 169
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 2.532588454376164,
|
| 1196 |
+
"grad_norm": 0.17455463171543423,
|
| 1197 |
+
"learning_rate": 4.603048566016735e-05,
|
| 1198 |
+
"loss": 0.3486,
|
| 1199 |
+
"step": 170
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 2.547486033519553,
|
| 1203 |
+
"grad_norm": 0.17359950511666877,
|
| 1204 |
+
"learning_rate": 4.5617449148610584e-05,
|
| 1205 |
+
"loss": 0.3483,
|
| 1206 |
+
"step": 171
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 2.5623836126629422,
|
| 1210 |
+
"grad_norm": 0.16169017429437474,
|
| 1211 |
+
"learning_rate": 4.520380070674902e-05,
|
| 1212 |
+
"loss": 0.3477,
|
| 1213 |
+
"step": 172
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 2.5772811918063314,
|
| 1217 |
+
"grad_norm": 0.17061911155312887,
|
| 1218 |
+
"learning_rate": 4.478958539489569e-05,
|
| 1219 |
+
"loss": 0.3571,
|
| 1220 |
+
"step": 173
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 2.5921787709497206,
|
| 1224 |
+
"grad_norm": 0.16695037154209072,
|
| 1225 |
+
"learning_rate": 4.437484833511499e-05,
|
| 1226 |
+
"loss": 0.3522,
|
| 1227 |
+
"step": 174
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 2.60707635009311,
|
| 1231 |
+
"grad_norm": 0.15955082753766311,
|
| 1232 |
+
"learning_rate": 4.395963470630723e-05,
|
| 1233 |
+
"loss": 0.3413,
|
| 1234 |
+
"step": 175
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 2.621973929236499,
|
| 1238 |
+
"grad_norm": 0.1573403347105783,
|
| 1239 |
+
"learning_rate": 4.3543989739287326e-05,
|
| 1240 |
+
"loss": 0.3477,
|
| 1241 |
+
"step": 176
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 2.636871508379888,
|
| 1245 |
+
"grad_norm": 0.14729071549065167,
|
| 1246 |
+
"learning_rate": 4.312795871185742e-05,
|
| 1247 |
+
"loss": 0.3483,
|
| 1248 |
+
"step": 177
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 2.6517690875232773,
|
| 1252 |
+
"grad_norm": 0.1625891228202278,
|
| 1253 |
+
"learning_rate": 4.2711586943874774e-05,
|
| 1254 |
+
"loss": 0.3452,
|
| 1255 |
+
"step": 178
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 2.6666666666666665,
|
| 1259 |
+
"grad_norm": 0.15062427849577625,
|
| 1260 |
+
"learning_rate": 4.2294919792314794e-05,
|
| 1261 |
+
"loss": 0.3488,
|
| 1262 |
+
"step": 179
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 2.6815642458100557,
|
| 1266 |
+
"grad_norm": 0.14387393723407899,
|
| 1267 |
+
"learning_rate": 4.1878002646330144e-05,
|
| 1268 |
+
"loss": 0.3524,
|
| 1269 |
+
"step": 180
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 2.6964618249534453,
|
| 1273 |
+
"grad_norm": 0.14777699560280422,
|
| 1274 |
+
"learning_rate": 4.1460880922306367e-05,
|
| 1275 |
+
"loss": 0.3458,
|
| 1276 |
+
"step": 181
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 2.711359404096834,
|
| 1280 |
+
"grad_norm": 0.1590574368277688,
|
| 1281 |
+
"learning_rate": 4.1043600058914436e-05,
|
| 1282 |
+
"loss": 0.3479,
|
| 1283 |
+
"step": 182
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 2.7262569832402237,
|
| 1287 |
+
"grad_norm": 0.1285624178683975,
|
| 1288 |
+
"learning_rate": 4.0626205512161034e-05,
|
| 1289 |
+
"loss": 0.3503,
|
| 1290 |
+
"step": 183
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 2.7411545623836124,
|
| 1294 |
+
"grad_norm": 0.14369454205895854,
|
| 1295 |
+
"learning_rate": 4.020874275043679e-05,
|
| 1296 |
+
"loss": 0.346,
|
| 1297 |
+
"step": 184
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 2.756052141527002,
|
| 1301 |
+
"grad_norm": 0.12193167492676163,
|
| 1302 |
+
"learning_rate": 3.979125724956324e-05,
|
| 1303 |
+
"loss": 0.3506,
|
| 1304 |
+
"step": 185
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 2.770949720670391,
|
| 1308 |
+
"grad_norm": 0.1326021753158276,
|
| 1309 |
+
"learning_rate": 3.937379448783898e-05,
|
| 1310 |
+
"loss": 0.3502,
|
| 1311 |
+
"step": 186
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 2.7858472998137804,
|
| 1315 |
+
"grad_norm": 0.12810706794198765,
|
| 1316 |
+
"learning_rate": 3.895639994108558e-05,
|
| 1317 |
+
"loss": 0.3541,
|
| 1318 |
+
"step": 187
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 2.8007448789571696,
|
| 1322 |
+
"grad_norm": 0.12656208043359207,
|
| 1323 |
+
"learning_rate": 3.853911907769365e-05,
|
| 1324 |
+
"loss": 0.3497,
|
| 1325 |
+
"step": 188
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 2.815642458100559,
|
| 1329 |
+
"grad_norm": 0.11404167595412021,
|
| 1330 |
+
"learning_rate": 3.812199735366986e-05,
|
| 1331 |
+
"loss": 0.3473,
|
| 1332 |
+
"step": 189
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 2.830540037243948,
|
| 1336 |
+
"grad_norm": 0.13878407632584827,
|
| 1337 |
+
"learning_rate": 3.770508020768522e-05,
|
| 1338 |
+
"loss": 0.3489,
|
| 1339 |
+
"step": 190
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 2.845437616387337,
|
| 1343 |
+
"grad_norm": 0.12311309579828897,
|
| 1344 |
+
"learning_rate": 3.728841305612524e-05,
|
| 1345 |
+
"loss": 0.3464,
|
| 1346 |
+
"step": 191
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 2.8603351955307263,
|
| 1350 |
+
"grad_norm": 0.13332912284616857,
|
| 1351 |
+
"learning_rate": 3.687204128814259e-05,
|
| 1352 |
+
"loss": 0.3428,
|
| 1353 |
+
"step": 192
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 2.8752327746741155,
|
| 1357 |
+
"grad_norm": 0.1384361081760211,
|
| 1358 |
+
"learning_rate": 3.645601026071269e-05,
|
| 1359 |
+
"loss": 0.3505,
|
| 1360 |
+
"step": 193
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 2.8901303538175047,
|
| 1364 |
+
"grad_norm": 0.13736333082695462,
|
| 1365 |
+
"learning_rate": 3.604036529369277e-05,
|
| 1366 |
+
"loss": 0.347,
|
| 1367 |
+
"step": 194
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 2.905027932960894,
|
| 1371 |
+
"grad_norm": 0.11583463546593212,
|
| 1372 |
+
"learning_rate": 3.5625151664885036e-05,
|
| 1373 |
+
"loss": 0.3461,
|
| 1374 |
+
"step": 195
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 2.919925512104283,
|
| 1378 |
+
"grad_norm": 0.12889980341532484,
|
| 1379 |
+
"learning_rate": 3.5210414605104314e-05,
|
| 1380 |
+
"loss": 0.3428,
|
| 1381 |
+
"step": 196
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 2.9348230912476723,
|
| 1385 |
+
"grad_norm": 0.11316852370701413,
|
| 1386 |
+
"learning_rate": 3.4796199293250987e-05,
|
| 1387 |
+
"loss": 0.3479,
|
| 1388 |
+
"step": 197
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 2.9497206703910615,
|
| 1392 |
+
"grad_norm": 0.11454972761265435,
|
| 1393 |
+
"learning_rate": 3.438255085138943e-05,
|
| 1394 |
+
"loss": 0.3464,
|
| 1395 |
+
"step": 198
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 2.9646182495344506,
|
| 1399 |
+
"grad_norm": 0.13041453651138907,
|
| 1400 |
+
"learning_rate": 3.396951433983266e-05,
|
| 1401 |
+
"loss": 0.3458,
|
| 1402 |
+
"step": 199
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 2.97951582867784,
|
| 1406 |
+
"grad_norm": 0.12148037255351198,
|
| 1407 |
+
"learning_rate": 3.355713475223382e-05,
|
| 1408 |
+
"loss": 0.3463,
|
| 1409 |
+
"step": 200
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 2.994413407821229,
|
| 1413 |
+
"grad_norm": 0.1255719642211306,
|
| 1414 |
+
"learning_rate": 3.314545701068475e-05,
|
| 1415 |
+
"loss": 0.3491,
|
| 1416 |
+
"step": 201
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 3.009310986964618,
|
| 1420 |
+
"grad_norm": 0.3022359318173022,
|
| 1421 |
+
"learning_rate": 3.2734525960822545e-05,
|
| 1422 |
+
"loss": 0.6352,
|
| 1423 |
+
"step": 202
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 3.0242085661080074,
|
| 1427 |
+
"grad_norm": 0.24062134731666432,
|
| 1428 |
+
"learning_rate": 3.232438636694431e-05,
|
| 1429 |
+
"loss": 0.3224,
|
| 1430 |
+
"step": 203
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 3.0391061452513966,
|
| 1434 |
+
"grad_norm": 0.18412193702307067,
|
| 1435 |
+
"learning_rate": 3.191508290713079e-05,
|
| 1436 |
+
"loss": 0.3206,
|
| 1437 |
+
"step": 204
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 3.0540037243947857,
|
| 1441 |
+
"grad_norm": 0.20860348558828723,
|
| 1442 |
+
"learning_rate": 3.150666016837947e-05,
|
| 1443 |
+
"loss": 0.3264,
|
| 1444 |
+
"step": 205
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 3.068901303538175,
|
| 1448 |
+
"grad_norm": 0.20845238316157091,
|
| 1449 |
+
"learning_rate": 3.109916264174743e-05,
|
| 1450 |
+
"loss": 0.327,
|
| 1451 |
+
"step": 206
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 3.083798882681564,
|
| 1455 |
+
"grad_norm": 0.20010239080813352,
|
| 1456 |
+
"learning_rate": 3.069263471750493e-05,
|
| 1457 |
+
"loss": 0.3223,
|
| 1458 |
+
"step": 207
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 3.0986964618249533,
|
| 1462 |
+
"grad_norm": 0.18760823228422985,
|
| 1463 |
+
"learning_rate": 3.0287120680299677e-05,
|
| 1464 |
+
"loss": 0.3238,
|
| 1465 |
+
"step": 208
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 3.1135940409683425,
|
| 1469 |
+
"grad_norm": 0.21319162553294677,
|
| 1470 |
+
"learning_rate": 2.988266470433277e-05,
|
| 1471 |
+
"loss": 0.3249,
|
| 1472 |
+
"step": 209
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 3.1284916201117317,
|
| 1476 |
+
"grad_norm": 0.17329474811121787,
|
| 1477 |
+
"learning_rate": 2.9479310848546644e-05,
|
| 1478 |
+
"loss": 0.3243,
|
| 1479 |
+
"step": 210
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 3.143389199255121,
|
| 1483 |
+
"grad_norm": 0.20404750548823786,
|
| 1484 |
+
"learning_rate": 2.9077103051825567e-05,
|
| 1485 |
+
"loss": 0.3203,
|
| 1486 |
+
"step": 211
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 3.1582867783985105,
|
| 1490 |
+
"grad_norm": 0.17940098271660299,
|
| 1491 |
+
"learning_rate": 2.8676085128209133e-05,
|
| 1492 |
+
"loss": 0.3237,
|
| 1493 |
+
"step": 212
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 3.1731843575418996,
|
| 1497 |
+
"grad_norm": 0.16237217554172287,
|
| 1498 |
+
"learning_rate": 2.8276300762119553e-05,
|
| 1499 |
+
"loss": 0.3196,
|
| 1500 |
+
"step": 213
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 3.188081936685289,
|
| 1504 |
+
"grad_norm": 0.15801986044567953,
|
| 1505 |
+
"learning_rate": 2.787779350360286e-05,
|
| 1506 |
+
"loss": 0.3196,
|
| 1507 |
+
"step": 214
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 3.202979515828678,
|
| 1511 |
+
"grad_norm": 0.1485056929542617,
|
| 1512 |
+
"learning_rate": 2.748060676358484e-05,
|
| 1513 |
+
"loss": 0.3192,
|
| 1514 |
+
"step": 215
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 3.217877094972067,
|
| 1518 |
+
"grad_norm": 0.15223329100287147,
|
| 1519 |
+
"learning_rate": 2.7084783809142164e-05,
|
| 1520 |
+
"loss": 0.3192,
|
| 1521 |
+
"step": 216
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 3.2327746741154564,
|
| 1525 |
+
"grad_norm": 0.13836533584306443,
|
| 1526 |
+
"learning_rate": 2.6690367758789046e-05,
|
| 1527 |
+
"loss": 0.328,
|
| 1528 |
+
"step": 217
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 3.2476722532588456,
|
| 1532 |
+
"grad_norm": 0.1351886559378493,
|
| 1533 |
+
"learning_rate": 2.6297401577780295e-05,
|
| 1534 |
+
"loss": 0.322,
|
| 1535 |
+
"step": 218
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 3.2625698324022347,
|
| 1539 |
+
"grad_norm": 0.12857547848905795,
|
| 1540 |
+
"learning_rate": 2.5905928073430854e-05,
|
| 1541 |
+
"loss": 0.319,
|
| 1542 |
+
"step": 219
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 3.277467411545624,
|
| 1546 |
+
"grad_norm": 0.1274395295470198,
|
| 1547 |
+
"learning_rate": 2.5515989890452674e-05,
|
| 1548 |
+
"loss": 0.3237,
|
| 1549 |
+
"step": 220
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 3.292364990689013,
|
| 1553 |
+
"grad_norm": 0.11899376687857942,
|
| 1554 |
+
"learning_rate": 2.5127629506309264e-05,
|
| 1555 |
+
"loss": 0.3205,
|
| 1556 |
+
"step": 221
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 3.3072625698324023,
|
| 1560 |
+
"grad_norm": 0.1304655308172865,
|
| 1561 |
+
"learning_rate": 2.474088922658842e-05,
|
| 1562 |
+
"loss": 0.3188,
|
| 1563 |
+
"step": 222
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 3.3221601489757915,
|
| 1567 |
+
"grad_norm": 0.11611090203712811,
|
| 1568 |
+
"learning_rate": 2.4355811180393767e-05,
|
| 1569 |
+
"loss": 0.3195,
|
| 1570 |
+
"step": 223
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 3.3370577281191807,
|
| 1574 |
+
"grad_norm": 0.11604416368224107,
|
| 1575 |
+
"learning_rate": 2.397243731575543e-05,
|
| 1576 |
+
"loss": 0.3201,
|
| 1577 |
+
"step": 224
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 3.35195530726257,
|
| 1581 |
+
"grad_norm": 0.11134670769841407,
|
| 1582 |
+
"learning_rate": 2.359080939506052e-05,
|
| 1583 |
+
"loss": 0.32,
|
| 1584 |
+
"step": 225
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 3.366852886405959,
|
| 1588 |
+
"grad_norm": 0.10870133266703798,
|
| 1589 |
+
"learning_rate": 2.3210968990503755e-05,
|
| 1590 |
+
"loss": 0.3208,
|
| 1591 |
+
"step": 226
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 3.381750465549348,
|
| 1595 |
+
"grad_norm": 0.1110502941686079,
|
| 1596 |
+
"learning_rate": 2.2832957479558866e-05,
|
| 1597 |
+
"loss": 0.317,
|
| 1598 |
+
"step": 227
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 3.3966480446927374,
|
| 1602 |
+
"grad_norm": 0.10438158313371027,
|
| 1603 |
+
"learning_rate": 2.245681604047114e-05,
|
| 1604 |
+
"loss": 0.3179,
|
| 1605 |
+
"step": 228
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 3.4115456238361266,
|
| 1609 |
+
"grad_norm": 0.10282665897445756,
|
| 1610 |
+
"learning_rate": 2.2082585647771807e-05,
|
| 1611 |
+
"loss": 0.3228,
|
| 1612 |
+
"step": 229
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 3.4264432029795158,
|
| 1616 |
+
"grad_norm": 0.10672800838711503,
|
| 1617 |
+
"learning_rate": 2.171030706781446e-05,
|
| 1618 |
+
"loss": 0.3222,
|
| 1619 |
+
"step": 230
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 3.441340782122905,
|
| 1623 |
+
"grad_norm": 0.09786842543478856,
|
| 1624 |
+
"learning_rate": 2.1340020854334246e-05,
|
| 1625 |
+
"loss": 0.3181,
|
| 1626 |
+
"step": 231
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 3.456238361266294,
|
| 1630 |
+
"grad_norm": 0.10404230481342372,
|
| 1631 |
+
"learning_rate": 2.0971767344030144e-05,
|
| 1632 |
+
"loss": 0.3225,
|
| 1633 |
+
"step": 232
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 3.4711359404096833,
|
| 1637 |
+
"grad_norm": 0.10712648472255477,
|
| 1638 |
+
"learning_rate": 2.0605586652170998e-05,
|
| 1639 |
+
"loss": 0.321,
|
| 1640 |
+
"step": 233
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 3.4860335195530725,
|
| 1644 |
+
"grad_norm": 0.1044874161797147,
|
| 1645 |
+
"learning_rate": 2.0241518668225595e-05,
|
| 1646 |
+
"loss": 0.3252,
|
| 1647 |
+
"step": 234
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 3.5009310986964617,
|
| 1651 |
+
"grad_norm": 0.10451587153618398,
|
| 1652 |
+
"learning_rate": 1.98796030515173e-05,
|
| 1653 |
+
"loss": 0.3173,
|
| 1654 |
+
"step": 235
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 3.515828677839851,
|
| 1658 |
+
"grad_norm": 0.09831156843059215,
|
| 1659 |
+
"learning_rate": 1.9519879226903903e-05,
|
| 1660 |
+
"loss": 0.3188,
|
| 1661 |
+
"step": 236
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 3.5307262569832405,
|
| 1665 |
+
"grad_norm": 0.09438833971964583,
|
| 1666 |
+
"learning_rate": 1.9162386380482795e-05,
|
| 1667 |
+
"loss": 0.3174,
|
| 1668 |
+
"step": 237
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 3.5456238361266292,
|
| 1672 |
+
"grad_norm": 0.10433270782878293,
|
| 1673 |
+
"learning_rate": 1.88071634553224e-05,
|
| 1674 |
+
"loss": 0.3219,
|
| 1675 |
+
"step": 238
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 3.560521415270019,
|
| 1679 |
+
"grad_norm": 0.09292286071725575,
|
| 1680 |
+
"learning_rate": 1.845424914721988e-05,
|
| 1681 |
+
"loss": 0.3252,
|
| 1682 |
+
"step": 239
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 3.5754189944134076,
|
| 1686 |
+
"grad_norm": 0.09413410282284697,
|
| 1687 |
+
"learning_rate": 1.81036819004859e-05,
|
| 1688 |
+
"loss": 0.3163,
|
| 1689 |
+
"step": 240
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 3.5903165735567972,
|
| 1693 |
+
"grad_norm": 0.10158989698055416,
|
| 1694 |
+
"learning_rate": 1.7755499903756704e-05,
|
| 1695 |
+
"loss": 0.3259,
|
| 1696 |
+
"step": 241
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 3.605214152700186,
|
| 1700 |
+
"grad_norm": 0.09464740249041373,
|
| 1701 |
+
"learning_rate": 1.7409741085834066e-05,
|
| 1702 |
+
"loss": 0.3191,
|
| 1703 |
+
"step": 242
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 3.6201117318435756,
|
| 1707 |
+
"grad_norm": 0.10726107957817572,
|
| 1708 |
+
"learning_rate": 1.7066443111553627e-05,
|
| 1709 |
+
"loss": 0.3211,
|
| 1710 |
+
"step": 243
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 3.635009310986965,
|
| 1714 |
+
"grad_norm": 0.08917870235234628,
|
| 1715 |
+
"learning_rate": 1.6725643377681893e-05,
|
| 1716 |
+
"loss": 0.3225,
|
| 1717 |
+
"step": 244
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 3.649906890130354,
|
| 1721 |
+
"grad_norm": 0.10677910900640168,
|
| 1722 |
+
"learning_rate": 1.638737900884239e-05,
|
| 1723 |
+
"loss": 0.3214,
|
| 1724 |
+
"step": 245
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 3.664804469273743,
|
| 1728 |
+
"grad_norm": 0.09774898119089985,
|
| 1729 |
+
"learning_rate": 1.6051686853471667e-05,
|
| 1730 |
+
"loss": 0.3252,
|
| 1731 |
+
"step": 246
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 3.6797020484171323,
|
| 1735 |
+
"grad_norm": 0.08773810545171451,
|
| 1736 |
+
"learning_rate": 1.5718603479805113e-05,
|
| 1737 |
+
"loss": 0.3235,
|
| 1738 |
+
"step": 247
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 3.6945996275605215,
|
| 1742 |
+
"grad_norm": 0.10111349625699705,
|
| 1743 |
+
"learning_rate": 1.538816517189356e-05,
|
| 1744 |
+
"loss": 0.3228,
|
| 1745 |
+
"step": 248
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 3.7094972067039107,
|
| 1749 |
+
"grad_norm": 0.09592458935558433,
|
| 1750 |
+
"learning_rate": 1.5060407925650662e-05,
|
| 1751 |
+
"loss": 0.3234,
|
| 1752 |
+
"step": 249
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 3.7243947858473,
|
| 1756 |
+
"grad_norm": 0.08715032888076826,
|
| 1757 |
+
"learning_rate": 1.4735367444931722e-05,
|
| 1758 |
+
"loss": 0.3192,
|
| 1759 |
+
"step": 250
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 3.739292364990689,
|
| 1763 |
+
"grad_norm": 0.09053851330147095,
|
| 1764 |
+
"learning_rate": 1.4413079137644358e-05,
|
| 1765 |
+
"loss": 0.3162,
|
| 1766 |
+
"step": 251
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 3.7541899441340782,
|
| 1770 |
+
"grad_norm": 0.10377676484499614,
|
| 1771 |
+
"learning_rate": 1.4093578111891333e-05,
|
| 1772 |
+
"loss": 0.3189,
|
| 1773 |
+
"step": 252
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 3.7690875232774674,
|
| 1777 |
+
"grad_norm": 0.08949080189520761,
|
| 1778 |
+
"learning_rate": 1.377689917214617e-05,
|
| 1779 |
+
"loss": 0.3258,
|
| 1780 |
+
"step": 253
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 3.7839851024208566,
|
| 1784 |
+
"grad_norm": 0.09258472675428549,
|
| 1785 |
+
"learning_rate": 1.3463076815461703e-05,
|
| 1786 |
+
"loss": 0.3195,
|
| 1787 |
+
"step": 254
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 3.798882681564246,
|
| 1791 |
+
"grad_norm": 0.0951200280500826,
|
| 1792 |
+
"learning_rate": 1.3152145227712221e-05,
|
| 1793 |
+
"loss": 0.314,
|
| 1794 |
+
"step": 255
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 3.813780260707635,
|
| 1798 |
+
"grad_norm": 0.09226678982549726,
|
| 1799 |
+
"learning_rate": 1.284413827986946e-05,
|
| 1800 |
+
"loss": 0.3255,
|
| 1801 |
+
"step": 256
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 3.828677839851024,
|
| 1805 |
+
"grad_norm": 0.08915216421489361,
|
| 1806 |
+
"learning_rate": 1.2539089524312855e-05,
|
| 1807 |
+
"loss": 0.3261,
|
| 1808 |
+
"step": 257
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 3.8435754189944134,
|
| 1812 |
+
"grad_norm": 0.0925569123285621,
|
| 1813 |
+
"learning_rate": 1.2237032191174642e-05,
|
| 1814 |
+
"loss": 0.3202,
|
| 1815 |
+
"step": 258
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 3.8584729981378025,
|
| 1819 |
+
"grad_norm": 0.08684065982720417,
|
| 1820 |
+
"learning_rate": 1.1937999184719926e-05,
|
| 1821 |
+
"loss": 0.3212,
|
| 1822 |
+
"step": 259
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 3.8733705772811917,
|
| 1826 |
+
"grad_norm": 0.08765050211323365,
|
| 1827 |
+
"learning_rate": 1.1642023079762281e-05,
|
| 1828 |
+
"loss": 0.319,
|
| 1829 |
+
"step": 260
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 3.888268156424581,
|
| 1833 |
+
"grad_norm": 0.08724442004118642,
|
| 1834 |
+
"learning_rate": 1.1349136118115242e-05,
|
| 1835 |
+
"loss": 0.3154,
|
| 1836 |
+
"step": 261
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 3.90316573556797,
|
| 1840 |
+
"grad_norm": 0.08586178309454286,
|
| 1841 |
+
"learning_rate": 1.1059370205080157e-05,
|
| 1842 |
+
"loss": 0.3226,
|
| 1843 |
+
"step": 262
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 3.9180633147113593,
|
| 1847 |
+
"grad_norm": 0.08501873030376662,
|
| 1848 |
+
"learning_rate": 1.07727569059705e-05,
|
| 1849 |
+
"loss": 0.3229,
|
| 1850 |
+
"step": 263
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 3.9329608938547485,
|
| 1854 |
+
"grad_norm": 0.09206134247645327,
|
| 1855 |
+
"learning_rate": 1.0489327442673459e-05,
|
| 1856 |
+
"loss": 0.3227,
|
| 1857 |
+
"step": 264
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 3.9478584729981376,
|
| 1861 |
+
"grad_norm": 0.08410101453326498,
|
| 1862 |
+
"learning_rate": 1.0209112690248726e-05,
|
| 1863 |
+
"loss": 0.3177,
|
| 1864 |
+
"step": 265
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 3.9627560521415273,
|
| 1868 |
+
"grad_norm": 0.08821111302237976,
|
| 1869 |
+
"learning_rate": 9.932143173565225e-06,
|
| 1870 |
+
"loss": 0.3227,
|
| 1871 |
+
"step": 266
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 3.977653631284916,
|
| 1875 |
+
"grad_norm": 0.08616646529797505,
|
| 1876 |
+
"learning_rate": 9.658449063975875e-06,
|
| 1877 |
+
"loss": 0.3216,
|
| 1878 |
+
"step": 267
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 3.9925512104283056,
|
| 1882 |
+
"grad_norm": 0.0885838583519875,
|
| 1883 |
+
"learning_rate": 9.388060176030907e-06,
|
| 1884 |
+
"loss": 0.3226,
|
| 1885 |
+
"step": 268
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 4.007448789571694,
|
| 1889 |
+
"grad_norm": 0.22436110155064673,
|
| 1890 |
+
"learning_rate": 9.12100596423009e-06,
|
| 1891 |
+
"loss": 0.577,
|
| 1892 |
+
"step": 269
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 4.022346368715084,
|
| 1896 |
+
"grad_norm": 0.11607630428391699,
|
| 1897 |
+
"learning_rate": 8.857315519814111e-06,
|
| 1898 |
+
"loss": 0.306,
|
| 1899 |
+
"step": 270
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 4.037243947858473,
|
| 1903 |
+
"grad_norm": 0.11774451222490284,
|
| 1904 |
+
"learning_rate": 8.597017567595562e-06,
|
| 1905 |
+
"loss": 0.3064,
|
| 1906 |
+
"step": 271
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 4.052141527001862,
|
| 1910 |
+
"grad_norm": 0.09907950082186576,
|
| 1911 |
+
"learning_rate": 8.34014046282984e-06,
|
| 1912 |
+
"loss": 0.302,
|
| 1913 |
+
"step": 272
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 4.067039106145251,
|
| 1917 |
+
"grad_norm": 0.10570787971335635,
|
| 1918 |
+
"learning_rate": 8.086712188126263e-06,
|
| 1919 |
+
"loss": 0.3021,
|
| 1920 |
+
"step": 273
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 4.081936685288641,
|
| 1924 |
+
"grad_norm": 0.10877019752281963,
|
| 1925 |
+
"learning_rate": 7.836760350399881e-06,
|
| 1926 |
+
"loss": 0.2992,
|
| 1927 |
+
"step": 274
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 4.0968342644320295,
|
| 1931 |
+
"grad_norm": 0.1173773952444213,
|
| 1932 |
+
"learning_rate": 7.5903121778641096e-06,
|
| 1933 |
+
"loss": 0.3077,
|
| 1934 |
+
"step": 275
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 4.111731843575419,
|
| 1938 |
+
"grad_norm": 0.10898666220477518,
|
| 1939 |
+
"learning_rate": 7.347394517064663e-06,
|
| 1940 |
+
"loss": 0.3068,
|
| 1941 |
+
"step": 276
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 4.126629422718808,
|
| 1945 |
+
"grad_norm": 0.09803810087456757,
|
| 1946 |
+
"learning_rate": 7.108033829955028e-06,
|
| 1947 |
+
"loss": 0.3077,
|
| 1948 |
+
"step": 277
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 4.1415270018621975,
|
| 1952 |
+
"grad_norm": 0.09446749801813671,
|
| 1953 |
+
"learning_rate": 6.87225619101394e-06,
|
| 1954 |
+
"loss": 0.3061,
|
| 1955 |
+
"step": 278
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 4.156424581005586,
|
| 1959 |
+
"grad_norm": 0.0951410747387855,
|
| 1960 |
+
"learning_rate": 6.640087284404888e-06,
|
| 1961 |
+
"loss": 0.3054,
|
| 1962 |
+
"step": 279
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 4.171322160148976,
|
| 1966 |
+
"grad_norm": 0.10491597814630026,
|
| 1967 |
+
"learning_rate": 6.411552401178327e-06,
|
| 1968 |
+
"loss": 0.3098,
|
| 1969 |
+
"step": 280
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 4.186219739292365,
|
| 1973 |
+
"grad_norm": 0.09593380058395089,
|
| 1974 |
+
"learning_rate": 6.186676436516581e-06,
|
| 1975 |
+
"loss": 0.3008,
|
| 1976 |
+
"step": 281
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 4.201117318435754,
|
| 1980 |
+
"grad_norm": 0.09551371288826128,
|
| 1981 |
+
"learning_rate": 5.965483887021934e-06,
|
| 1982 |
+
"loss": 0.3087,
|
| 1983 |
+
"step": 282
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 4.216014897579143,
|
| 1987 |
+
"grad_norm": 0.0895153508605015,
|
| 1988 |
+
"learning_rate": 5.747998848048091e-06,
|
| 1989 |
+
"loss": 0.3091,
|
| 1990 |
+
"step": 283
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 4.230912476722533,
|
| 1994 |
+
"grad_norm": 0.09197880309307534,
|
| 1995 |
+
"learning_rate": 5.534245011075414e-06,
|
| 1996 |
+
"loss": 0.298,
|
| 1997 |
+
"step": 284
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 4.245810055865922,
|
| 2001 |
+
"grad_norm": 0.08575532851271551,
|
| 2002 |
+
"learning_rate": 5.3242456611301095e-06,
|
| 2003 |
+
"loss": 0.3,
|
| 2004 |
+
"step": 285
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 4.260707635009311,
|
| 2008 |
+
"grad_norm": 0.08276481700085347,
|
| 2009 |
+
"learning_rate": 5.118023674247692e-06,
|
| 2010 |
+
"loss": 0.2984,
|
| 2011 |
+
"step": 286
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 4.275605214152701,
|
| 2015 |
+
"grad_norm": 0.08713205903583655,
|
| 2016 |
+
"learning_rate": 4.915601514981024e-06,
|
| 2017 |
+
"loss": 0.3078,
|
| 2018 |
+
"step": 287
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 4.290502793296089,
|
| 2022 |
+
"grad_norm": 0.08363731970724225,
|
| 2023 |
+
"learning_rate": 4.717001233953116e-06,
|
| 2024 |
+
"loss": 0.2987,
|
| 2025 |
+
"step": 288
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 4.305400372439479,
|
| 2029 |
+
"grad_norm": 0.08529607146039025,
|
| 2030 |
+
"learning_rate": 4.522244465455154e-06,
|
| 2031 |
+
"loss": 0.3038,
|
| 2032 |
+
"step": 289
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 4.320297951582868,
|
| 2036 |
+
"grad_norm": 0.08215569802598276,
|
| 2037 |
+
"learning_rate": 4.33135242508973e-06,
|
| 2038 |
+
"loss": 0.3043,
|
| 2039 |
+
"step": 290
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 4.335195530726257,
|
| 2043 |
+
"grad_norm": 0.08149200923150887,
|
| 2044 |
+
"learning_rate": 4.144345907459753e-06,
|
| 2045 |
+
"loss": 0.3013,
|
| 2046 |
+
"step": 291
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 4.350093109869646,
|
| 2050 |
+
"grad_norm": 0.08086624632566386,
|
| 2051 |
+
"learning_rate": 3.961245283903239e-06,
|
| 2052 |
+
"loss": 0.308,
|
| 2053 |
+
"step": 292
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 4.364990689013036,
|
| 2057 |
+
"grad_norm": 0.07896402407099593,
|
| 2058 |
+
"learning_rate": 3.7820705002741353e-06,
|
| 2059 |
+
"loss": 0.3052,
|
| 2060 |
+
"step": 293
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 4.379888268156424,
|
| 2064 |
+
"grad_norm": 0.08231952485165063,
|
| 2065 |
+
"learning_rate": 3.6068410747696112e-06,
|
| 2066 |
+
"loss": 0.3002,
|
| 2067 |
+
"step": 294
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 4.394785847299814,
|
| 2071 |
+
"grad_norm": 0.07789166320140198,
|
| 2072 |
+
"learning_rate": 3.435576095803792e-06,
|
| 2073 |
+
"loss": 0.3021,
|
| 2074 |
+
"step": 295
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 4.409683426443203,
|
| 2078 |
+
"grad_norm": 0.07892696916845467,
|
| 2079 |
+
"learning_rate": 3.268294219928434e-06,
|
| 2080 |
+
"loss": 0.3046,
|
| 2081 |
+
"step": 296
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 4.424581005586592,
|
| 2085 |
+
"grad_norm": 0.07646811095500806,
|
| 2086 |
+
"learning_rate": 3.1050136698005963e-06,
|
| 2087 |
+
"loss": 0.3025,
|
| 2088 |
+
"step": 297
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 4.439478584729981,
|
| 2092 |
+
"grad_norm": 0.07957607014767461,
|
| 2093 |
+
"learning_rate": 2.9457522321975253e-06,
|
| 2094 |
+
"loss": 0.3079,
|
| 2095 |
+
"step": 298
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 4.454376163873371,
|
| 2099 |
+
"grad_norm": 0.08390752993938617,
|
| 2100 |
+
"learning_rate": 2.790527256079134e-06,
|
| 2101 |
+
"loss": 0.3066,
|
| 2102 |
+
"step": 299
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 4.4692737430167595,
|
| 2106 |
+
"grad_norm": 0.07541814294925331,
|
| 2107 |
+
"learning_rate": 2.6393556506980834e-06,
|
| 2108 |
+
"loss": 0.3071,
|
| 2109 |
+
"step": 300
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 4.484171322160149,
|
| 2113 |
+
"grad_norm": 0.0714738276840467,
|
| 2114 |
+
"learning_rate": 2.4922538837577916e-06,
|
| 2115 |
+
"loss": 0.3078,
|
| 2116 |
+
"step": 301
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 4.499068901303538,
|
| 2120 |
+
"grad_norm": 0.0729695749304457,
|
| 2121 |
+
"learning_rate": 2.349237979618555e-06,
|
| 2122 |
+
"loss": 0.3112,
|
| 2123 |
+
"step": 302
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 4.5139664804469275,
|
| 2127 |
+
"grad_norm": 0.10108195097380965,
|
| 2128 |
+
"learning_rate": 2.2103235175519355e-06,
|
| 2129 |
+
"loss": 0.3052,
|
| 2130 |
+
"step": 303
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 4.528864059590316,
|
| 2134 |
+
"grad_norm": 0.07138906578544997,
|
| 2135 |
+
"learning_rate": 2.0755256300436687e-06,
|
| 2136 |
+
"loss": 0.3014,
|
| 2137 |
+
"step": 304
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 4.543761638733706,
|
| 2141 |
+
"grad_norm": 0.07356056598380585,
|
| 2142 |
+
"learning_rate": 1.944859001145223e-06,
|
| 2143 |
+
"loss": 0.3065,
|
| 2144 |
+
"step": 305
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 4.558659217877095,
|
| 2148 |
+
"grad_norm": 0.07516469607423958,
|
| 2149 |
+
"learning_rate": 1.8183378648741979e-06,
|
| 2150 |
+
"loss": 0.3049,
|
| 2151 |
+
"step": 306
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 4.573556797020484,
|
| 2155 |
+
"grad_norm": 0.07371825538928153,
|
| 2156 |
+
"learning_rate": 1.6959760036637662e-06,
|
| 2157 |
+
"loss": 0.304,
|
| 2158 |
+
"step": 307
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 4.588454376163874,
|
| 2162 |
+
"grad_norm": 0.07502909475594224,
|
| 2163 |
+
"learning_rate": 1.5777867468612874e-06,
|
| 2164 |
+
"loss": 0.3011,
|
| 2165 |
+
"step": 308
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 4.603351955307263,
|
| 2169 |
+
"grad_norm": 0.07352157905066296,
|
| 2170 |
+
"learning_rate": 1.4637829692763128e-06,
|
| 2171 |
+
"loss": 0.3029,
|
| 2172 |
+
"step": 309
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 4.618249534450651,
|
| 2176 |
+
"grad_norm": 0.07644054766848495,
|
| 2177 |
+
"learning_rate": 1.353977089778078e-06,
|
| 2178 |
+
"loss": 0.3046,
|
| 2179 |
+
"step": 310
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 4.633147113594041,
|
| 2183 |
+
"grad_norm": 0.07171131988386027,
|
| 2184 |
+
"learning_rate": 1.2483810699426458e-06,
|
| 2185 |
+
"loss": 0.3068,
|
| 2186 |
+
"step": 311
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 4.648044692737431,
|
| 2190 |
+
"grad_norm": 0.07057850167398541,
|
| 2191 |
+
"learning_rate": 1.1470064127499091e-06,
|
| 2192 |
+
"loss": 0.3064,
|
| 2193 |
+
"step": 312
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 4.662942271880819,
|
| 2197 |
+
"grad_norm": 0.07626745016001804,
|
| 2198 |
+
"learning_rate": 1.0498641613305182e-06,
|
| 2199 |
+
"loss": 0.3007,
|
| 2200 |
+
"step": 313
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 4.677839851024208,
|
| 2204 |
+
"grad_norm": 0.0693829644961785,
|
| 2205 |
+
"learning_rate": 9.569648977629176e-07,
|
| 2206 |
+
"loss": 0.3049,
|
| 2207 |
+
"step": 314
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 4.692737430167598,
|
| 2211 |
+
"grad_norm": 0.0674761214613311,
|
| 2212 |
+
"learning_rate": 8.683187419205797e-07,
|
| 2213 |
+
"loss": 0.3013,
|
| 2214 |
+
"step": 315
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 4.707635009310987,
|
| 2218 |
+
"grad_norm": 0.06823222699165288,
|
| 2219 |
+
"learning_rate": 7.839353503696379e-07,
|
| 2220 |
+
"loss": 0.3071,
|
| 2221 |
+
"step": 316
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 4.722532588454376,
|
| 2225 |
+
"grad_norm": 0.06859479836699696,
|
| 2226 |
+
"learning_rate": 7.038239153169324e-07,
|
| 2227 |
+
"loss": 0.301,
|
| 2228 |
+
"step": 317
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 4.737430167597766,
|
| 2232 |
+
"grad_norm": 0.07031736775350605,
|
| 2233 |
+
"learning_rate": 6.279931636086912e-07,
|
| 2234 |
+
"loss": 0.3086,
|
| 2235 |
+
"step": 318
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 4.752327746741154,
|
| 2239 |
+
"grad_norm": 0.06915744071480374,
|
| 2240 |
+
"learning_rate": 5.564513557798501e-07,
|
| 2241 |
+
"loss": 0.3048,
|
| 2242 |
+
"step": 319
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 4.767225325884544,
|
| 2246 |
+
"grad_norm": 0.06815891873681693,
|
| 2247 |
+
"learning_rate": 4.892062851542356e-07,
|
| 2248 |
+
"loss": 0.309,
|
| 2249 |
+
"step": 320
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 4.782122905027933,
|
| 2253 |
+
"grad_norm": 0.06935050248754245,
|
| 2254 |
+
"learning_rate": 4.2626527699558996e-07,
|
| 2255 |
+
"loss": 0.3018,
|
| 2256 |
+
"step": 321
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 4.797020484171322,
|
| 2260 |
+
"grad_norm": 0.06784753003557113,
|
| 2261 |
+
"learning_rate": 3.6763518770960517e-07,
|
| 2262 |
+
"loss": 0.3051,
|
| 2263 |
+
"step": 322
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 4.811918063314711,
|
| 2267 |
+
"grad_norm": 0.06808652827602746,
|
| 2268 |
+
"learning_rate": 3.133224040970273e-07,
|
| 2269 |
+
"loss": 0.3071,
|
| 2270 |
+
"step": 323
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 4.826815642458101,
|
| 2274 |
+
"grad_norm": 0.07121784851648261,
|
| 2275 |
+
"learning_rate": 2.6333284265790627e-07,
|
| 2276 |
+
"loss": 0.3047,
|
| 2277 |
+
"step": 324
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 4.8417132216014895,
|
| 2281 |
+
"grad_norm": 0.06700344502725675,
|
| 2282 |
+
"learning_rate": 2.1767194894712462e-07,
|
| 2283 |
+
"loss": 0.305,
|
| 2284 |
+
"step": 325
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 4.856610800744879,
|
| 2288 |
+
"grad_norm": 0.06927419764551407,
|
| 2289 |
+
"learning_rate": 1.763446969811522e-07,
|
| 2290 |
+
"loss": 0.306,
|
| 2291 |
+
"step": 326
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 4.871508379888268,
|
| 2295 |
+
"grad_norm": 0.06947638763948212,
|
| 2296 |
+
"learning_rate": 1.3935558869622168e-07,
|
| 2297 |
+
"loss": 0.3042,
|
| 2298 |
+
"step": 327
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 4.8864059590316575,
|
| 2302 |
+
"grad_norm": 0.06866693792434822,
|
| 2303 |
+
"learning_rate": 1.0670865345793425e-07,
|
| 2304 |
+
"loss": 0.3094,
|
| 2305 |
+
"step": 328
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 4.901303538175046,
|
| 2309 |
+
"grad_norm": 0.06859589228192586,
|
| 2310 |
+
"learning_rate": 7.840744762229069e-08,
|
| 2311 |
+
"loss": 0.3054,
|
| 2312 |
+
"step": 329
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 4.916201117318436,
|
| 2316 |
+
"grad_norm": 0.06927380611470749,
|
| 2317 |
+
"learning_rate": 5.445505414831242e-08,
|
| 2318 |
+
"loss": 0.3054,
|
| 2319 |
+
"step": 330
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 4.931098696461825,
|
| 2323 |
+
"grad_norm": 0.06680927663742126,
|
| 2324 |
+
"learning_rate": 3.485408226218567e-08,
|
| 2325 |
+
"loss": 0.2998,
|
| 2326 |
+
"step": 331
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 4.945996275605214,
|
| 2330 |
+
"grad_norm": 0.06773777244031369,
|
| 2331 |
+
"learning_rate": 1.960666717304438e-08,
|
| 2332 |
+
"loss": 0.3058,
|
| 2333 |
+
"step": 332
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 4.960893854748603,
|
| 2337 |
+
"grad_norm": 0.06864556914107234,
|
| 2338 |
+
"learning_rate": 8.714469840351848e-09,
|
| 2339 |
+
"loss": 0.2984,
|
| 2340 |
+
"step": 333
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 4.975791433891993,
|
| 2344 |
+
"grad_norm": 0.0678647360547641,
|
| 2345 |
+
"learning_rate": 2.178676792996548e-09,
|
| 2346 |
+
"loss": 0.3051,
|
| 2347 |
+
"step": 334
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 4.990689013035381,
|
| 2351 |
+
"grad_norm": 0.06662103871858636,
|
| 2352 |
+
"learning_rate": 0.0,
|
| 2353 |
+
"loss": 0.2973,
|
| 2354 |
+
"step": 335
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 4.990689013035381,
|
| 2358 |
+
"step": 335,
|
| 2359 |
+
"total_flos": 8.620546826447094e+18,
|
| 2360 |
+
"train_loss": 0.380745083004681,
|
| 2361 |
+
"train_runtime": 51129.1279,
|
| 2362 |
+
"train_samples_per_second": 3.36,
|
| 2363 |
+
"train_steps_per_second": 0.007
|
| 2364 |
+
}
|
| 2365 |
+
],
|
| 2366 |
+
"logging_steps": 1.0,
|
| 2367 |
+
"max_steps": 335,
|
| 2368 |
+
"num_input_tokens_seen": 0,
|
| 2369 |
+
"num_train_epochs": 5,
|
| 2370 |
+
"save_steps": 500,
|
| 2371 |
+
"stateful_callbacks": {
|
| 2372 |
+
"TrainerControl": {
|
| 2373 |
+
"args": {
|
| 2374 |
+
"should_epoch_stop": false,
|
| 2375 |
+
"should_evaluate": false,
|
| 2376 |
+
"should_log": false,
|
| 2377 |
+
"should_save": true,
|
| 2378 |
+
"should_training_stop": true
|
| 2379 |
+
},
|
| 2380 |
+
"attributes": {}
|
| 2381 |
+
}
|
| 2382 |
+
},
|
| 2383 |
+
"total_flos": 8.620546826447094e+18,
|
| 2384 |
+
"train_batch_size": 1,
|
| 2385 |
+
"trial_name": null,
|
| 2386 |
+
"trial_params": null
|
| 2387 |
+
}
|
training_loss.png
ADDED
|