End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +1372 -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: openthoughts2_science
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# openthoughts2_science
|
| 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: openthoughts2_science
|
|
|
|
| 16 |
|
| 17 |
# openthoughts2_science
|
| 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/openthoughts2_science dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.948051948051948,
|
| 3 |
+
"total_flos": 1.8291450201715507e+17,
|
| 4 |
+
"train_loss": 0.4666951280283301,
|
| 5 |
+
"train_runtime": 4594.7358,
|
| 6 |
+
"train_samples_per_second": 5.357,
|
| 7 |
+
"train_steps_per_second": 0.041
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.948051948051948,
|
| 3 |
+
"total_flos": 1.8291450201715507e+17,
|
| 4 |
+
"train_loss": 0.4666951280283301,
|
| 5 |
+
"train_runtime": 4594.7358,
|
| 6 |
+
"train_samples_per_second": 5.357,
|
| 7 |
+
"train_steps_per_second": 0.041
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1372 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.948051948051948,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 190,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.025974025974025976,
|
| 13 |
+
"grad_norm": 7.932461880382458,
|
| 14 |
+
"learning_rate": 2.105263157894737e-06,
|
| 15 |
+
"loss": 1.3022,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.05194805194805195,
|
| 20 |
+
"grad_norm": 7.914768259228103,
|
| 21 |
+
"learning_rate": 4.210526315789474e-06,
|
| 22 |
+
"loss": 1.2794,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.07792207792207792,
|
| 27 |
+
"grad_norm": 7.484077281744907,
|
| 28 |
+
"learning_rate": 6.31578947368421e-06,
|
| 29 |
+
"loss": 1.2625,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.1038961038961039,
|
| 34 |
+
"grad_norm": 5.714449349246834,
|
| 35 |
+
"learning_rate": 8.421052631578948e-06,
|
| 36 |
+
"loss": 1.2443,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.12987012987012986,
|
| 41 |
+
"grad_norm": 3.1210181292904724,
|
| 42 |
+
"learning_rate": 1.0526315789473684e-05,
|
| 43 |
+
"loss": 1.1532,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.15584415584415584,
|
| 48 |
+
"grad_norm": 5.253391384757655,
|
| 49 |
+
"learning_rate": 1.263157894736842e-05,
|
| 50 |
+
"loss": 1.0944,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.18181818181818182,
|
| 55 |
+
"grad_norm": 5.463591834581839,
|
| 56 |
+
"learning_rate": 1.4736842105263159e-05,
|
| 57 |
+
"loss": 1.1138,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.2077922077922078,
|
| 62 |
+
"grad_norm": 7.387714938198011,
|
| 63 |
+
"learning_rate": 1.6842105263157896e-05,
|
| 64 |
+
"loss": 1.1008,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.23376623376623376,
|
| 69 |
+
"grad_norm": 6.205307398999116,
|
| 70 |
+
"learning_rate": 1.894736842105263e-05,
|
| 71 |
+
"loss": 1.0759,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.2597402597402597,
|
| 76 |
+
"grad_norm": 4.626405073408399,
|
| 77 |
+
"learning_rate": 2.105263157894737e-05,
|
| 78 |
+
"loss": 1.0411,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.2857142857142857,
|
| 83 |
+
"grad_norm": 3.5062975875923623,
|
| 84 |
+
"learning_rate": 2.3157894736842107e-05,
|
| 85 |
+
"loss": 0.9892,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.3116883116883117,
|
| 90 |
+
"grad_norm": 3.095922849196239,
|
| 91 |
+
"learning_rate": 2.526315789473684e-05,
|
| 92 |
+
"loss": 0.981,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.33766233766233766,
|
| 97 |
+
"grad_norm": 2.620362610628679,
|
| 98 |
+
"learning_rate": 2.7368421052631583e-05,
|
| 99 |
+
"loss": 0.9321,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.36363636363636365,
|
| 104 |
+
"grad_norm": 2.095917606876017,
|
| 105 |
+
"learning_rate": 2.9473684210526317e-05,
|
| 106 |
+
"loss": 0.9431,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.38961038961038963,
|
| 111 |
+
"grad_norm": 1.6957008846140307,
|
| 112 |
+
"learning_rate": 3.157894736842106e-05,
|
| 113 |
+
"loss": 0.937,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.4155844155844156,
|
| 118 |
+
"grad_norm": 1.7112898298596606,
|
| 119 |
+
"learning_rate": 3.368421052631579e-05,
|
| 120 |
+
"loss": 0.9237,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.44155844155844154,
|
| 125 |
+
"grad_norm": 1.7675227036340526,
|
| 126 |
+
"learning_rate": 3.578947368421053e-05,
|
| 127 |
+
"loss": 0.913,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.4675324675324675,
|
| 132 |
+
"grad_norm": 1.6383266641991525,
|
| 133 |
+
"learning_rate": 3.789473684210526e-05,
|
| 134 |
+
"loss": 0.9288,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.4935064935064935,
|
| 139 |
+
"grad_norm": 1.294665470376389,
|
| 140 |
+
"learning_rate": 4e-05,
|
| 141 |
+
"loss": 0.9351,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.5194805194805194,
|
| 146 |
+
"grad_norm": 1.604347276742893,
|
| 147 |
+
"learning_rate": 3.999662483266646e-05,
|
| 148 |
+
"loss": 0.8908,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.5454545454545454,
|
| 153 |
+
"grad_norm": 1.4355986610502338,
|
| 154 |
+
"learning_rate": 3.9986500469841275e-05,
|
| 155 |
+
"loss": 0.9129,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.5714285714285714,
|
| 160 |
+
"grad_norm": 630.6282393505426,
|
| 161 |
+
"learning_rate": 3.996963032866633e-05,
|
| 162 |
+
"loss": 1.137,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.5974025974025974,
|
| 167 |
+
"grad_norm": 64.18229097051045,
|
| 168 |
+
"learning_rate": 3.994602010309655e-05,
|
| 169 |
+
"loss": 0.9911,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.6233766233766234,
|
| 174 |
+
"grad_norm": 3.1233891543931755,
|
| 175 |
+
"learning_rate": 3.991567776197815e-05,
|
| 176 |
+
"loss": 0.9639,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.6493506493506493,
|
| 181 |
+
"grad_norm": 2.077319867927905,
|
| 182 |
+
"learning_rate": 3.9878613546358996e-05,
|
| 183 |
+
"loss": 0.9394,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.6753246753246753,
|
| 188 |
+
"grad_norm": 6.491527923131102,
|
| 189 |
+
"learning_rate": 3.983483996603205e-05,
|
| 190 |
+
"loss": 0.8881,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.7012987012987013,
|
| 195 |
+
"grad_norm": 39.42852606734072,
|
| 196 |
+
"learning_rate": 3.978437179531316e-05,
|
| 197 |
+
"loss": 0.9145,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.7272727272727273,
|
| 202 |
+
"grad_norm": 3.4103842126583013,
|
| 203 |
+
"learning_rate": 3.972722606805445e-05,
|
| 204 |
+
"loss": 0.9565,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.7532467532467533,
|
| 209 |
+
"grad_norm": 2.603677290738666,
|
| 210 |
+
"learning_rate": 3.9663422071895103e-05,
|
| 211 |
+
"loss": 0.9527,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.7792207792207793,
|
| 216 |
+
"grad_norm": 1.5693962270477466,
|
| 217 |
+
"learning_rate": 3.959298134175148e-05,
|
| 218 |
+
"loss": 0.9261,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.8051948051948052,
|
| 223 |
+
"grad_norm": 1.9966129861478277,
|
| 224 |
+
"learning_rate": 3.9515927652548714e-05,
|
| 225 |
+
"loss": 0.8946,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.8311688311688312,
|
| 230 |
+
"grad_norm": 2.6605968358600744,
|
| 231 |
+
"learning_rate": 3.943228701119628e-05,
|
| 232 |
+
"loss": 0.9076,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.8571428571428571,
|
| 237 |
+
"grad_norm": 2.1460676505845138,
|
| 238 |
+
"learning_rate": 3.934208764781022e-05,
|
| 239 |
+
"loss": 0.8956,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.8831168831168831,
|
| 244 |
+
"grad_norm": 1.5905762959039638,
|
| 245 |
+
"learning_rate": 3.924536000618501e-05,
|
| 246 |
+
"loss": 0.8986,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.9090909090909091,
|
| 251 |
+
"grad_norm": 1.53645783721347,
|
| 252 |
+
"learning_rate": 3.9142136733518285e-05,
|
| 253 |
+
"loss": 0.8862,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.935064935064935,
|
| 258 |
+
"grad_norm": 1.68321757769248,
|
| 259 |
+
"learning_rate": 3.903245266939184e-05,
|
| 260 |
+
"loss": 0.9017,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.961038961038961,
|
| 265 |
+
"grad_norm": 1.30815074965975,
|
| 266 |
+
"learning_rate": 3.8916344834012695e-05,
|
| 267 |
+
"loss": 0.8698,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.987012987012987,
|
| 272 |
+
"grad_norm": 1.165747960130663,
|
| 273 |
+
"learning_rate": 3.879385241571817e-05,
|
| 274 |
+
"loss": 0.8618,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.0162337662337662,
|
| 279 |
+
"grad_norm": 1.182349191382658,
|
| 280 |
+
"learning_rate": 3.866501675774914e-05,
|
| 281 |
+
"loss": 0.7754,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.0422077922077921,
|
| 286 |
+
"grad_norm": 1.1769523292955406,
|
| 287 |
+
"learning_rate": 3.8529881344296037e-05,
|
| 288 |
+
"loss": 0.7007,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.0681818181818181,
|
| 293 |
+
"grad_norm": 1.0627768684949523,
|
| 294 |
+
"learning_rate": 3.8388491785822154e-05,
|
| 295 |
+
"loss": 0.6888,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.094155844155844,
|
| 300 |
+
"grad_norm": 1.0474113890412635,
|
| 301 |
+
"learning_rate": 3.8240895803669415e-05,
|
| 302 |
+
"loss": 0.666,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.12012987012987,
|
| 307 |
+
"grad_norm": 1.1513266436057166,
|
| 308 |
+
"learning_rate": 3.808714321395155e-05,
|
| 309 |
+
"loss": 0.6711,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.146103896103896,
|
| 314 |
+
"grad_norm": 1.0575614450294766,
|
| 315 |
+
"learning_rate": 3.792728591074041e-05,
|
| 316 |
+
"loss": 0.6675,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.172077922077922,
|
| 321 |
+
"grad_norm": 1.0417037432847753,
|
| 322 |
+
"learning_rate": 3.776137784855076e-05,
|
| 323 |
+
"loss": 0.6505,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.198051948051948,
|
| 328 |
+
"grad_norm": 1.0718429071818538,
|
| 329 |
+
"learning_rate": 3.758947502412978e-05,
|
| 330 |
+
"loss": 0.6398,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.224025974025974,
|
| 335 |
+
"grad_norm": 1.035859051149055,
|
| 336 |
+
"learning_rate": 3.741163545755725e-05,
|
| 337 |
+
"loss": 0.6344,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.25,
|
| 342 |
+
"grad_norm": 1.2059393425085077,
|
| 343 |
+
"learning_rate": 3.722791917266273e-05,
|
| 344 |
+
"loss": 0.6576,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.275974025974026,
|
| 349 |
+
"grad_norm": 0.8647464266057819,
|
| 350 |
+
"learning_rate": 3.703838817676654e-05,
|
| 351 |
+
"loss": 0.634,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.301948051948052,
|
| 356 |
+
"grad_norm": 0.9794755119362144,
|
| 357 |
+
"learning_rate": 3.684310643975132e-05,
|
| 358 |
+
"loss": 0.6587,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.327922077922078,
|
| 363 |
+
"grad_norm": 0.8945933571618422,
|
| 364 |
+
"learning_rate": 3.6642139872471006e-05,
|
| 365 |
+
"loss": 0.6489,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.353896103896104,
|
| 370 |
+
"grad_norm": 0.7218628490321455,
|
| 371 |
+
"learning_rate": 3.64355563045049e-05,
|
| 372 |
+
"loss": 0.6499,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 1.37987012987013,
|
| 377 |
+
"grad_norm": 0.9164999911062107,
|
| 378 |
+
"learning_rate": 3.622342546126405e-05,
|
| 379 |
+
"loss": 0.6396,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 1.405844155844156,
|
| 384 |
+
"grad_norm": 0.8475563662080481,
|
| 385 |
+
"learning_rate": 3.600581894045768e-05,
|
| 386 |
+
"loss": 0.6728,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.4318181818181819,
|
| 391 |
+
"grad_norm": 0.9702631527667891,
|
| 392 |
+
"learning_rate": 3.578281018792788e-05,
|
| 393 |
+
"loss": 0.6644,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 1.4577922077922079,
|
| 398 |
+
"grad_norm": 0.9538702840059207,
|
| 399 |
+
"learning_rate": 3.555447447286028e-05,
|
| 400 |
+
"loss": 0.643,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 1.4837662337662338,
|
| 405 |
+
"grad_norm": 0.8910634080576203,
|
| 406 |
+
"learning_rate": 3.532088886237956e-05,
|
| 407 |
+
"loss": 0.6628,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.5097402597402598,
|
| 412 |
+
"grad_norm": 0.9694684889310542,
|
| 413 |
+
"learning_rate": 3.508213219553793e-05,
|
| 414 |
+
"loss": 0.6267,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 1.5357142857142856,
|
| 419 |
+
"grad_norm": 0.7645363444588047,
|
| 420 |
+
"learning_rate": 3.483828505670563e-05,
|
| 421 |
+
"loss": 0.6621,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.5616883116883118,
|
| 426 |
+
"grad_norm": 1.0003412015299207,
|
| 427 |
+
"learning_rate": 3.458942974837242e-05,
|
| 428 |
+
"loss": 0.6523,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.5876623376623376,
|
| 433 |
+
"grad_norm": 0.9130736095702605,
|
| 434 |
+
"learning_rate": 3.433565026336903e-05,
|
| 435 |
+
"loss": 0.6607,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 1.6136363636363638,
|
| 440 |
+
"grad_norm": 0.9845762925311329,
|
| 441 |
+
"learning_rate": 3.4077032256518236e-05,
|
| 442 |
+
"loss": 0.6396,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.6396103896103895,
|
| 447 |
+
"grad_norm": 0.8116185410937748,
|
| 448 |
+
"learning_rate": 3.381366301572489e-05,
|
| 449 |
+
"loss": 0.6413,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.6655844155844157,
|
| 454 |
+
"grad_norm": 0.86437358110291,
|
| 455 |
+
"learning_rate": 3.354563143251483e-05,
|
| 456 |
+
"loss": 0.6711,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 1.6915584415584415,
|
| 461 |
+
"grad_norm": 0.8420048228007022,
|
| 462 |
+
"learning_rate": 3.327302797203243e-05,
|
| 463 |
+
"loss": 0.6604,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 1.7175324675324677,
|
| 468 |
+
"grad_norm": 0.7816899345223021,
|
| 469 |
+
"learning_rate": 3.29959446425072e-05,
|
| 470 |
+
"loss": 0.651,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.7435064935064934,
|
| 475 |
+
"grad_norm": 0.9303056765525075,
|
| 476 |
+
"learning_rate": 3.2714474964199365e-05,
|
| 477 |
+
"loss": 0.6289,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 1.7694805194805194,
|
| 482 |
+
"grad_norm": 0.7805801403650556,
|
| 483 |
+
"learning_rate": 3.24287139378353e-05,
|
| 484 |
+
"loss": 0.6411,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 1.7954545454545454,
|
| 489 |
+
"grad_norm": 0.753331126461648,
|
| 490 |
+
"learning_rate": 3.213875801254314e-05,
|
| 491 |
+
"loss": 0.6646,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 1.8214285714285714,
|
| 496 |
+
"grad_norm": 0.7358002312013492,
|
| 497 |
+
"learning_rate": 3.1844705053299606e-05,
|
| 498 |
+
"loss": 0.6293,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 1.8474025974025974,
|
| 503 |
+
"grad_norm": 0.8070564650099749,
|
| 504 |
+
"learning_rate": 3.154665430789893e-05,
|
| 505 |
+
"loss": 0.6596,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.8733766233766234,
|
| 510 |
+
"grad_norm": 0.7226075974955157,
|
| 511 |
+
"learning_rate": 3.1244706373455084e-05,
|
| 512 |
+
"loss": 0.667,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.8993506493506493,
|
| 517 |
+
"grad_norm": 0.7791333934794239,
|
| 518 |
+
"learning_rate": 3.093896316244855e-05,
|
| 519 |
+
"loss": 0.6465,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 1.9253246753246753,
|
| 524 |
+
"grad_norm": 0.7754676549638453,
|
| 525 |
+
"learning_rate": 3.062952786832912e-05,
|
| 526 |
+
"loss": 0.6554,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.9512987012987013,
|
| 531 |
+
"grad_norm": 0.6557877212038498,
|
| 532 |
+
"learning_rate": 3.0316504930686485e-05,
|
| 533 |
+
"loss": 0.6566,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.9772727272727273,
|
| 538 |
+
"grad_norm": 0.8194426729485009,
|
| 539 |
+
"learning_rate": 3.0000000000000004e-05,
|
| 540 |
+
"loss": 0.6627,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 2.0064935064935066,
|
| 545 |
+
"grad_norm": 0.7334083955009458,
|
| 546 |
+
"learning_rate": 2.9680119901979984e-05,
|
| 547 |
+
"loss": 0.6111,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 2.0324675324675323,
|
| 552 |
+
"grad_norm": 1.1895868881255909,
|
| 553 |
+
"learning_rate": 2.935697260151216e-05,
|
| 554 |
+
"loss": 0.3871,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 2.0584415584415585,
|
| 559 |
+
"grad_norm": 0.9604279263135902,
|
| 560 |
+
"learning_rate": 2.903066716621779e-05,
|
| 561 |
+
"loss": 0.4077,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 2.0844155844155843,
|
| 566 |
+
"grad_norm": 1.1393762686141848,
|
| 567 |
+
"learning_rate": 2.8701313729641467e-05,
|
| 568 |
+
"loss": 0.3866,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 2.1103896103896105,
|
| 573 |
+
"grad_norm": 0.7106851428516716,
|
| 574 |
+
"learning_rate": 2.8369023454079223e-05,
|
| 575 |
+
"loss": 0.3825,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 2.1363636363636362,
|
| 580 |
+
"grad_norm": 0.8224703275776866,
|
| 581 |
+
"learning_rate": 2.8033908493059394e-05,
|
| 582 |
+
"loss": 0.3714,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 2.1623376623376624,
|
| 587 |
+
"grad_norm": 0.6836375654772662,
|
| 588 |
+
"learning_rate": 2.7696081953488917e-05,
|
| 589 |
+
"loss": 0.3888,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 2.188311688311688,
|
| 594 |
+
"grad_norm": 0.7313622114325852,
|
| 595 |
+
"learning_rate": 2.735565785747787e-05,
|
| 596 |
+
"loss": 0.3642,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 2.2142857142857144,
|
| 601 |
+
"grad_norm": 0.6822815355692488,
|
| 602 |
+
"learning_rate": 2.7012751103855092e-05,
|
| 603 |
+
"loss": 0.3783,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 2.24025974025974,
|
| 608 |
+
"grad_norm": 0.6553172875405961,
|
| 609 |
+
"learning_rate": 2.6667477429387915e-05,
|
| 610 |
+
"loss": 0.3754,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 2.2662337662337664,
|
| 615 |
+
"grad_norm": 0.6074920244076911,
|
| 616 |
+
"learning_rate": 2.6319953369719057e-05,
|
| 617 |
+
"loss": 0.3473,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 2.292207792207792,
|
| 622 |
+
"grad_norm": 0.6021128235097986,
|
| 623 |
+
"learning_rate": 2.5970296220033894e-05,
|
| 624 |
+
"loss": 0.3471,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 2.3181818181818183,
|
| 629 |
+
"grad_norm": 0.6940589972604451,
|
| 630 |
+
"learning_rate": 2.5618623995471394e-05,
|
| 631 |
+
"loss": 0.3837,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 2.344155844155844,
|
| 636 |
+
"grad_norm": 0.6033654970817208,
|
| 637 |
+
"learning_rate": 2.5265055391291986e-05,
|
| 638 |
+
"loss": 0.3528,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 2.3701298701298703,
|
| 643 |
+
"grad_norm": 0.6333023948866248,
|
| 644 |
+
"learning_rate": 2.4909709742815986e-05,
|
| 645 |
+
"loss": 0.3649,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 2.396103896103896,
|
| 650 |
+
"grad_norm": 0.6001340560802214,
|
| 651 |
+
"learning_rate": 2.4552706985145873e-05,
|
| 652 |
+
"loss": 0.3669,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 2.4220779220779223,
|
| 657 |
+
"grad_norm": 0.6197546210826222,
|
| 658 |
+
"learning_rate": 2.4194167612686208e-05,
|
| 659 |
+
"loss": 0.3532,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 2.448051948051948,
|
| 664 |
+
"grad_norm": 0.565080044721377,
|
| 665 |
+
"learning_rate": 2.3834212638474773e-05,
|
| 666 |
+
"loss": 0.3657,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 2.474025974025974,
|
| 671 |
+
"grad_norm": 0.5902739460347666,
|
| 672 |
+
"learning_rate": 2.3472963553338614e-05,
|
| 673 |
+
"loss": 0.3621,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 2.5,
|
| 678 |
+
"grad_norm": 0.5749686649380882,
|
| 679 |
+
"learning_rate": 2.3110542284888866e-05,
|
| 680 |
+
"loss": 0.3467,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 2.525974025974026,
|
| 685 |
+
"grad_norm": 0.5450163127235501,
|
| 686 |
+
"learning_rate": 2.2747071156368166e-05,
|
| 687 |
+
"loss": 0.3624,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 2.551948051948052,
|
| 692 |
+
"grad_norm": 0.6232436601785027,
|
| 693 |
+
"learning_rate": 2.2382672845364474e-05,
|
| 694 |
+
"loss": 0.3564,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 2.5779220779220777,
|
| 699 |
+
"grad_norm": 0.5515744279861114,
|
| 700 |
+
"learning_rate": 2.201747034240537e-05,
|
| 701 |
+
"loss": 0.3658,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 2.603896103896104,
|
| 706 |
+
"grad_norm": 0.5362907375585828,
|
| 707 |
+
"learning_rate": 2.165158690944665e-05,
|
| 708 |
+
"loss": 0.3473,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 2.62987012987013,
|
| 713 |
+
"grad_norm": 0.6161976462395182,
|
| 714 |
+
"learning_rate": 2.1285146038269406e-05,
|
| 715 |
+
"loss": 0.3416,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 2.655844155844156,
|
| 720 |
+
"grad_norm": 0.5199919758117065,
|
| 721 |
+
"learning_rate": 2.091827140879944e-05,
|
| 722 |
+
"loss": 0.3448,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 2.6818181818181817,
|
| 727 |
+
"grad_norm": 0.5858886775846843,
|
| 728 |
+
"learning_rate": 2.0551086847363245e-05,
|
| 729 |
+
"loss": 0.3433,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 2.707792207792208,
|
| 734 |
+
"grad_norm": 0.5676263304852041,
|
| 735 |
+
"learning_rate": 2.0183716284894533e-05,
|
| 736 |
+
"loss": 0.3467,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 2.7337662337662336,
|
| 741 |
+
"grad_norm": 0.5586462671917939,
|
| 742 |
+
"learning_rate": 1.9816283715105474e-05,
|
| 743 |
+
"loss": 0.3482,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 2.75974025974026,
|
| 748 |
+
"grad_norm": 0.6276307789744222,
|
| 749 |
+
"learning_rate": 1.9448913152636765e-05,
|
| 750 |
+
"loss": 0.3545,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 2.7857142857142856,
|
| 755 |
+
"grad_norm": 0.5484342032145305,
|
| 756 |
+
"learning_rate": 1.9081728591200565e-05,
|
| 757 |
+
"loss": 0.3666,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 2.811688311688312,
|
| 762 |
+
"grad_norm": 0.5688020278596353,
|
| 763 |
+
"learning_rate": 1.87148539617306e-05,
|
| 764 |
+
"loss": 0.344,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 2.8376623376623376,
|
| 769 |
+
"grad_norm": 0.539614144085222,
|
| 770 |
+
"learning_rate": 1.8348413090553356e-05,
|
| 771 |
+
"loss": 0.3387,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 2.8636363636363638,
|
| 776 |
+
"grad_norm": 0.5698805550812537,
|
| 777 |
+
"learning_rate": 1.7982529657594637e-05,
|
| 778 |
+
"loss": 0.3604,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 2.8896103896103895,
|
| 783 |
+
"grad_norm": 0.5212709930299778,
|
| 784 |
+
"learning_rate": 1.761732715463553e-05,
|
| 785 |
+
"loss": 0.3363,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 2.9155844155844157,
|
| 790 |
+
"grad_norm": 0.5284822211250491,
|
| 791 |
+
"learning_rate": 1.7252928843631838e-05,
|
| 792 |
+
"loss": 0.3546,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 2.9415584415584415,
|
| 797 |
+
"grad_norm": 0.5401001882166652,
|
| 798 |
+
"learning_rate": 1.6889457715111144e-05,
|
| 799 |
+
"loss": 0.3486,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 2.9675324675324677,
|
| 804 |
+
"grad_norm": 0.5229863215386347,
|
| 805 |
+
"learning_rate": 1.6527036446661396e-05,
|
| 806 |
+
"loss": 0.3352,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 2.9935064935064934,
|
| 811 |
+
"grad_norm": 0.5347563548020706,
|
| 812 |
+
"learning_rate": 1.6165787361525237e-05,
|
| 813 |
+
"loss": 0.3593,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 3.022727272727273,
|
| 818 |
+
"grad_norm": 0.672978181037337,
|
| 819 |
+
"learning_rate": 1.5805832387313795e-05,
|
| 820 |
+
"loss": 0.2407,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 3.0487012987012987,
|
| 825 |
+
"grad_norm": 0.679162551176236,
|
| 826 |
+
"learning_rate": 1.544729301485414e-05,
|
| 827 |
+
"loss": 0.1911,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 3.074675324675325,
|
| 832 |
+
"grad_norm": 0.48652138994921784,
|
| 833 |
+
"learning_rate": 1.5090290257184019e-05,
|
| 834 |
+
"loss": 0.1896,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 3.1006493506493507,
|
| 839 |
+
"grad_norm": 0.5783075834024586,
|
| 840 |
+
"learning_rate": 1.4734944608708022e-05,
|
| 841 |
+
"loss": 0.2093,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 3.1266233766233764,
|
| 846 |
+
"grad_norm": 0.8020276248905834,
|
| 847 |
+
"learning_rate": 1.4381376004528616e-05,
|
| 848 |
+
"loss": 0.2057,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 3.1525974025974026,
|
| 853 |
+
"grad_norm": 0.667374545311432,
|
| 854 |
+
"learning_rate": 1.4029703779966116e-05,
|
| 855 |
+
"loss": 0.1884,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 3.1785714285714284,
|
| 860 |
+
"grad_norm": 0.5056105500696159,
|
| 861 |
+
"learning_rate": 1.3680046630280952e-05,
|
| 862 |
+
"loss": 0.1977,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 3.2045454545454546,
|
| 867 |
+
"grad_norm": 0.49060521809385876,
|
| 868 |
+
"learning_rate": 1.3332522570612097e-05,
|
| 869 |
+
"loss": 0.1891,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 3.2305194805194803,
|
| 874 |
+
"grad_norm": 0.5481519220939601,
|
| 875 |
+
"learning_rate": 1.2987248896144915e-05,
|
| 876 |
+
"loss": 0.1912,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 3.2564935064935066,
|
| 881 |
+
"grad_norm": 0.5257555666517691,
|
| 882 |
+
"learning_rate": 1.2644342142522142e-05,
|
| 883 |
+
"loss": 0.1982,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 3.2824675324675323,
|
| 888 |
+
"grad_norm": 0.48753413095850306,
|
| 889 |
+
"learning_rate": 1.230391804651109e-05,
|
| 890 |
+
"loss": 0.1825,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 3.3084415584415585,
|
| 895 |
+
"grad_norm": 0.4612445791577537,
|
| 896 |
+
"learning_rate": 1.1966091506940616e-05,
|
| 897 |
+
"loss": 0.1963,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 3.3344155844155843,
|
| 902 |
+
"grad_norm": 0.44552190602064307,
|
| 903 |
+
"learning_rate": 1.1630976545920777e-05,
|
| 904 |
+
"loss": 0.1706,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 3.3603896103896105,
|
| 909 |
+
"grad_norm": 0.48659675686631854,
|
| 910 |
+
"learning_rate": 1.1298686270358542e-05,
|
| 911 |
+
"loss": 0.1913,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 3.3863636363636362,
|
| 916 |
+
"grad_norm": 0.4764396048263091,
|
| 917 |
+
"learning_rate": 1.0969332833782217e-05,
|
| 918 |
+
"loss": 0.1671,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 3.4123376623376624,
|
| 923 |
+
"grad_norm": 0.4740155487267979,
|
| 924 |
+
"learning_rate": 1.0643027398487848e-05,
|
| 925 |
+
"loss": 0.1854,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 3.438311688311688,
|
| 930 |
+
"grad_norm": 0.4551923057514232,
|
| 931 |
+
"learning_rate": 1.031988009802003e-05,
|
| 932 |
+
"loss": 0.1709,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 3.4642857142857144,
|
| 937 |
+
"grad_norm": 0.43070005789183097,
|
| 938 |
+
"learning_rate": 1.0000000000000006e-05,
|
| 939 |
+
"loss": 0.1975,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 3.49025974025974,
|
| 944 |
+
"grad_norm": 0.383014073709059,
|
| 945 |
+
"learning_rate": 9.683495069313527e-06,
|
| 946 |
+
"loss": 0.1787,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 3.5162337662337664,
|
| 951 |
+
"grad_norm": 0.4286879659999333,
|
| 952 |
+
"learning_rate": 9.370472131670887e-06,
|
| 953 |
+
"loss": 0.1979,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 3.542207792207792,
|
| 958 |
+
"grad_norm": 0.41592759389422845,
|
| 959 |
+
"learning_rate": 9.061036837551467e-06,
|
| 960 |
+
"loss": 0.1672,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 3.5681818181818183,
|
| 965 |
+
"grad_norm": 0.4101654305939979,
|
| 966 |
+
"learning_rate": 8.755293626544921e-06,
|
| 967 |
+
"loss": 0.1578,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 3.594155844155844,
|
| 972 |
+
"grad_norm": 0.41025853609303076,
|
| 973 |
+
"learning_rate": 8.453345692101076e-06,
|
| 974 |
+
"loss": 0.1732,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 3.62012987012987,
|
| 979 |
+
"grad_norm": 0.4099487747185865,
|
| 980 |
+
"learning_rate": 8.155294946700402e-06,
|
| 981 |
+
"loss": 0.1868,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 3.646103896103896,
|
| 986 |
+
"grad_norm": 0.39174988018880874,
|
| 987 |
+
"learning_rate": 7.861241987456869e-06,
|
| 988 |
+
"loss": 0.1921,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 3.6720779220779223,
|
| 993 |
+
"grad_norm": 0.3960964308201075,
|
| 994 |
+
"learning_rate": 7.571286062164709e-06,
|
| 995 |
+
"loss": 0.1902,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 3.698051948051948,
|
| 1000 |
+
"grad_norm": 0.41695917345370964,
|
| 1001 |
+
"learning_rate": 7.285525035800645e-06,
|
| 1002 |
+
"loss": 0.1885,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 3.724025974025974,
|
| 1007 |
+
"grad_norm": 0.3946638754267475,
|
| 1008 |
+
"learning_rate": 7.0040553574928115e-06,
|
| 1009 |
+
"loss": 0.1646,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 3.75,
|
| 1014 |
+
"grad_norm": 0.3843896631591302,
|
| 1015 |
+
"learning_rate": 6.7269720279675755e-06,
|
| 1016 |
+
"loss": 0.1769,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 3.775974025974026,
|
| 1021 |
+
"grad_norm": 0.39754823944143786,
|
| 1022 |
+
"learning_rate": 6.4543685674851834e-06,
|
| 1023 |
+
"loss": 0.1927,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 3.801948051948052,
|
| 1028 |
+
"grad_norm": 0.39430307748603793,
|
| 1029 |
+
"learning_rate": 6.1863369842751145e-06,
|
| 1030 |
+
"loss": 0.1835,
|
| 1031 |
+
"step": 146
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 3.8279220779220777,
|
| 1035 |
+
"grad_norm": 0.3925790082334243,
|
| 1036 |
+
"learning_rate": 5.922967743481773e-06,
|
| 1037 |
+
"loss": 0.1912,
|
| 1038 |
+
"step": 147
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 3.853896103896104,
|
| 1042 |
+
"grad_norm": 0.4061383035436692,
|
| 1043 |
+
"learning_rate": 5.664349736630979e-06,
|
| 1044 |
+
"loss": 0.1688,
|
| 1045 |
+
"step": 148
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 3.87987012987013,
|
| 1049 |
+
"grad_norm": 0.3887498420237992,
|
| 1050 |
+
"learning_rate": 5.410570251627587e-06,
|
| 1051 |
+
"loss": 0.202,
|
| 1052 |
+
"step": 149
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 3.905844155844156,
|
| 1056 |
+
"grad_norm": 0.38629968407857657,
|
| 1057 |
+
"learning_rate": 5.161714943294372e-06,
|
| 1058 |
+
"loss": 0.1841,
|
| 1059 |
+
"step": 150
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 3.9318181818181817,
|
| 1063 |
+
"grad_norm": 0.38720595837879046,
|
| 1064 |
+
"learning_rate": 4.917867804462077e-06,
|
| 1065 |
+
"loss": 0.1819,
|
| 1066 |
+
"step": 151
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 3.957792207792208,
|
| 1070 |
+
"grad_norm": 0.38121444486474165,
|
| 1071 |
+
"learning_rate": 4.679111137620442e-06,
|
| 1072 |
+
"loss": 0.187,
|
| 1073 |
+
"step": 152
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 3.9837662337662336,
|
| 1077 |
+
"grad_norm": 0.3830372856152854,
|
| 1078 |
+
"learning_rate": 4.445525527139725e-06,
|
| 1079 |
+
"loss": 0.187,
|
| 1080 |
+
"step": 153
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 4.012987012987013,
|
| 1084 |
+
"grad_norm": 0.3791401299823691,
|
| 1085 |
+
"learning_rate": 4.217189812072131e-06,
|
| 1086 |
+
"loss": 0.1686,
|
| 1087 |
+
"step": 154
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 4.038961038961039,
|
| 1091 |
+
"grad_norm": 0.4148718569874963,
|
| 1092 |
+
"learning_rate": 3.994181059542321e-06,
|
| 1093 |
+
"loss": 0.1176,
|
| 1094 |
+
"step": 155
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 4.064935064935065,
|
| 1098 |
+
"grad_norm": 0.35673107519822433,
|
| 1099 |
+
"learning_rate": 3.7765745387359574e-06,
|
| 1100 |
+
"loss": 0.1154,
|
| 1101 |
+
"step": 156
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 4.090909090909091,
|
| 1105 |
+
"grad_norm": 0.3402341389305598,
|
| 1106 |
+
"learning_rate": 3.564443695495099e-06,
|
| 1107 |
+
"loss": 0.1369,
|
| 1108 |
+
"step": 157
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 4.116883116883117,
|
| 1112 |
+
"grad_norm": 0.33628395582708454,
|
| 1113 |
+
"learning_rate": 3.357860127529e-06,
|
| 1114 |
+
"loss": 0.1167,
|
| 1115 |
+
"step": 158
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 4.142857142857143,
|
| 1119 |
+
"grad_norm": 0.30102455569288517,
|
| 1120 |
+
"learning_rate": 3.156893560248688e-06,
|
| 1121 |
+
"loss": 0.1242,
|
| 1122 |
+
"step": 159
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 4.1688311688311686,
|
| 1126 |
+
"grad_norm": 0.2771068438895251,
|
| 1127 |
+
"learning_rate": 2.9616118232334613e-06,
|
| 1128 |
+
"loss": 0.1187,
|
| 1129 |
+
"step": 160
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 4.194805194805195,
|
| 1133 |
+
"grad_norm": 0.294541202996176,
|
| 1134 |
+
"learning_rate": 2.7720808273372823e-06,
|
| 1135 |
+
"loss": 0.1143,
|
| 1136 |
+
"step": 161
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 4.220779220779221,
|
| 1140 |
+
"grad_norm": 0.3243600487046826,
|
| 1141 |
+
"learning_rate": 2.588364542442754e-06,
|
| 1142 |
+
"loss": 0.1267,
|
| 1143 |
+
"step": 162
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 4.246753246753247,
|
| 1147 |
+
"grad_norm": 0.3313486959659834,
|
| 1148 |
+
"learning_rate": 2.410524975870221e-06,
|
| 1149 |
+
"loss": 0.127,
|
| 1150 |
+
"step": 163
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 4.2727272727272725,
|
| 1154 |
+
"grad_norm": 0.35233311448800625,
|
| 1155 |
+
"learning_rate": 2.2386221514492502e-06,
|
| 1156 |
+
"loss": 0.132,
|
| 1157 |
+
"step": 164
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 4.298701298701299,
|
| 1161 |
+
"grad_norm": 0.34772021499799033,
|
| 1162 |
+
"learning_rate": 2.0727140892595998e-06,
|
| 1163 |
+
"loss": 0.1249,
|
| 1164 |
+
"step": 165
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 4.324675324675325,
|
| 1168 |
+
"grad_norm": 0.31722684001225576,
|
| 1169 |
+
"learning_rate": 1.9128567860484516e-06,
|
| 1170 |
+
"loss": 0.1297,
|
| 1171 |
+
"step": 166
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 4.35064935064935,
|
| 1175 |
+
"grad_norm": 0.31190729931884087,
|
| 1176 |
+
"learning_rate": 1.759104196330592e-06,
|
| 1177 |
+
"loss": 0.1163,
|
| 1178 |
+
"step": 167
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 4.376623376623376,
|
| 1182 |
+
"grad_norm": 0.29649306847713347,
|
| 1183 |
+
"learning_rate": 1.6115082141778459e-06,
|
| 1184 |
+
"loss": 0.1219,
|
| 1185 |
+
"step": 168
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 4.402597402597403,
|
| 1189 |
+
"grad_norm": 0.28001769998158305,
|
| 1190 |
+
"learning_rate": 1.4701186557039648e-06,
|
| 1191 |
+
"loss": 0.1096,
|
| 1192 |
+
"step": 169
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 4.428571428571429,
|
| 1196 |
+
"grad_norm": 0.2810796360606971,
|
| 1197 |
+
"learning_rate": 1.334983242250858e-06,
|
| 1198 |
+
"loss": 0.1097,
|
| 1199 |
+
"step": 170
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 4.454545454545454,
|
| 1203 |
+
"grad_norm": 0.2833719049954468,
|
| 1204 |
+
"learning_rate": 1.2061475842818337e-06,
|
| 1205 |
+
"loss": 0.1279,
|
| 1206 |
+
"step": 171
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 4.48051948051948,
|
| 1210 |
+
"grad_norm": 0.2634347576438535,
|
| 1211 |
+
"learning_rate": 1.0836551659873073e-06,
|
| 1212 |
+
"loss": 0.123,
|
| 1213 |
+
"step": 172
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 4.5064935064935066,
|
| 1217 |
+
"grad_norm": 0.2792887436301362,
|
| 1218 |
+
"learning_rate": 9.67547330608165e-07,
|
| 1219 |
+
"loss": 0.1189,
|
| 1220 |
+
"step": 173
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 4.532467532467533,
|
| 1224 |
+
"grad_norm": 0.2615347102434456,
|
| 1225 |
+
"learning_rate": 8.578632664817177e-07,
|
| 1226 |
+
"loss": 0.1249,
|
| 1227 |
+
"step": 174
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 4.558441558441558,
|
| 1231 |
+
"grad_norm": 0.2723001428445289,
|
| 1232 |
+
"learning_rate": 7.546399938149918e-07,
|
| 1233 |
+
"loss": 0.1137,
|
| 1234 |
+
"step": 175
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 4.584415584415584,
|
| 1238 |
+
"grad_norm": 0.2612744190545831,
|
| 1239 |
+
"learning_rate": 6.579123521897867e-07,
|
| 1240 |
+
"loss": 0.1015,
|
| 1241 |
+
"step": 176
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 4.6103896103896105,
|
| 1245 |
+
"grad_norm": 0.2689642699590416,
|
| 1246 |
+
"learning_rate": 5.677129888037236e-07,
|
| 1247 |
+
"loss": 0.1126,
|
| 1248 |
+
"step": 177
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 4.636363636363637,
|
| 1252 |
+
"grad_norm": 0.269452974192897,
|
| 1253 |
+
"learning_rate": 4.840723474512876e-07,
|
| 1254 |
+
"loss": 0.123,
|
| 1255 |
+
"step": 178
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 4.662337662337662,
|
| 1259 |
+
"grad_norm": 0.26461030349016573,
|
| 1260 |
+
"learning_rate": 4.070186582485214e-07,
|
| 1261 |
+
"loss": 0.1227,
|
| 1262 |
+
"step": 179
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 4.688311688311688,
|
| 1266 |
+
"grad_norm": 0.26195993538778606,
|
| 1267 |
+
"learning_rate": 3.3657792810489975e-07,
|
| 1268 |
+
"loss": 0.1265,
|
| 1269 |
+
"step": 180
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 4.714285714285714,
|
| 1273 |
+
"grad_norm": 0.2629718231282119,
|
| 1274 |
+
"learning_rate": 2.7277393194555357e-07,
|
| 1275 |
+
"loss": 0.0993,
|
| 1276 |
+
"step": 181
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 4.740259740259741,
|
| 1280 |
+
"grad_norm": 0.2748041688236983,
|
| 1281 |
+
"learning_rate": 2.1562820468684187e-07,
|
| 1282 |
+
"loss": 0.1271,
|
| 1283 |
+
"step": 182
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 4.766233766233766,
|
| 1287 |
+
"grad_norm": 0.28368676223609396,
|
| 1288 |
+
"learning_rate": 1.6516003396795489e-07,
|
| 1289 |
+
"loss": 0.132,
|
| 1290 |
+
"step": 183
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 4.792207792207792,
|
| 1294 |
+
"grad_norm": 0.2691168035289099,
|
| 1295 |
+
"learning_rate": 1.2138645364101032e-07,
|
| 1296 |
+
"loss": 0.099,
|
| 1297 |
+
"step": 184
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 4.818181818181818,
|
| 1301 |
+
"grad_norm": 0.26074215375130616,
|
| 1302 |
+
"learning_rate": 8.432223802185002e-08,
|
| 1303 |
+
"loss": 0.1111,
|
| 1304 |
+
"step": 185
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 4.8441558441558445,
|
| 1308 |
+
"grad_norm": 0.27028450763035056,
|
| 1309 |
+
"learning_rate": 5.3979896903453287e-08,
|
| 1310 |
+
"loss": 0.1229,
|
| 1311 |
+
"step": 186
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 4.87012987012987,
|
| 1315 |
+
"grad_norm": 0.27411525111121277,
|
| 1316 |
+
"learning_rate": 3.036967133367652e-08,
|
| 1317 |
+
"loss": 0.1303,
|
| 1318 |
+
"step": 187
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 4.896103896103896,
|
| 1322 |
+
"grad_norm": 0.25069357083928406,
|
| 1323 |
+
"learning_rate": 1.349953015872707e-08,
|
| 1324 |
+
"loss": 0.1212,
|
| 1325 |
+
"step": 188
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 4.922077922077922,
|
| 1329 |
+
"grad_norm": 0.2630680904345287,
|
| 1330 |
+
"learning_rate": 3.3751673335458147e-09,
|
| 1331 |
+
"loss": 0.1268,
|
| 1332 |
+
"step": 189
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 4.948051948051948,
|
| 1336 |
+
"grad_norm": 0.2705412617221253,
|
| 1337 |
+
"learning_rate": 0.0,
|
| 1338 |
+
"loss": 0.1421,
|
| 1339 |
+
"step": 190
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 4.948051948051948,
|
| 1343 |
+
"step": 190,
|
| 1344 |
+
"total_flos": 1.8291450201715507e+17,
|
| 1345 |
+
"train_loss": 0.4666951280283301,
|
| 1346 |
+
"train_runtime": 4594.7358,
|
| 1347 |
+
"train_samples_per_second": 5.357,
|
| 1348 |
+
"train_steps_per_second": 0.041
|
| 1349 |
+
}
|
| 1350 |
+
],
|
| 1351 |
+
"logging_steps": 1,
|
| 1352 |
+
"max_steps": 190,
|
| 1353 |
+
"num_input_tokens_seen": 0,
|
| 1354 |
+
"num_train_epochs": 5,
|
| 1355 |
+
"save_steps": 500,
|
| 1356 |
+
"stateful_callbacks": {
|
| 1357 |
+
"TrainerControl": {
|
| 1358 |
+
"args": {
|
| 1359 |
+
"should_epoch_stop": false,
|
| 1360 |
+
"should_evaluate": false,
|
| 1361 |
+
"should_log": false,
|
| 1362 |
+
"should_save": true,
|
| 1363 |
+
"should_training_stop": true
|
| 1364 |
+
},
|
| 1365 |
+
"attributes": {}
|
| 1366 |
+
}
|
| 1367 |
+
},
|
| 1368 |
+
"total_flos": 1.8291450201715507e+17,
|
| 1369 |
+
"train_batch_size": 1,
|
| 1370 |
+
"trial_name": null,
|
| 1371 |
+
"trial_params": null
|
| 1372 |
+
}
|
training_loss.png
ADDED
|