End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +1323 -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: Light-R1-SFTData
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# Light-R1-SFTData
|
| 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: Light-R1-SFTData
|
|
|
|
| 16 |
|
| 17 |
# Light-R1-SFTData
|
| 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 qihoo360/Light-R1-SFTData dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9786802030456854,
|
| 3 |
+
"total_flos": 4.709134058959929e+18,
|
| 4 |
+
"train_loss": 0.42409751356625164,
|
| 5 |
+
"train_runtime": 40618.2962,
|
| 6 |
+
"train_samples_per_second": 2.327,
|
| 7 |
+
"train_steps_per_second": 0.005
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9786802030456854,
|
| 3 |
+
"total_flos": 4.709134058959929e+18,
|
| 4 |
+
"train_loss": 0.42409751356625164,
|
| 5 |
+
"train_runtime": 40618.2962,
|
| 6 |
+
"train_samples_per_second": 2.327,
|
| 7 |
+
"train_steps_per_second": 0.005
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1323 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9786802030456854,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 183,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.016243654822335026,
|
| 13 |
+
"grad_norm": 5.861148280465038,
|
| 14 |
+
"learning_rate": 4.210526315789474e-06,
|
| 15 |
+
"loss": 0.7971,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.03248730964467005,
|
| 20 |
+
"grad_norm": 5.903622852368125,
|
| 21 |
+
"learning_rate": 8.421052631578948e-06,
|
| 22 |
+
"loss": 0.8013,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.048730964467005075,
|
| 27 |
+
"grad_norm": 4.414814742973429,
|
| 28 |
+
"learning_rate": 1.263157894736842e-05,
|
| 29 |
+
"loss": 0.7483,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0649746192893401,
|
| 34 |
+
"grad_norm": 2.1084544285026685,
|
| 35 |
+
"learning_rate": 1.6842105263157896e-05,
|
| 36 |
+
"loss": 0.696,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.08121827411167512,
|
| 41 |
+
"grad_norm": 5.670885486524175,
|
| 42 |
+
"learning_rate": 2.105263157894737e-05,
|
| 43 |
+
"loss": 0.7237,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.09746192893401015,
|
| 48 |
+
"grad_norm": 10.09125086973651,
|
| 49 |
+
"learning_rate": 2.526315789473684e-05,
|
| 50 |
+
"loss": 0.7683,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.11370558375634518,
|
| 55 |
+
"grad_norm": 6.783333688153429,
|
| 56 |
+
"learning_rate": 2.9473684210526317e-05,
|
| 57 |
+
"loss": 0.7212,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.1299492385786802,
|
| 62 |
+
"grad_norm": 4.468625434130326,
|
| 63 |
+
"learning_rate": 3.368421052631579e-05,
|
| 64 |
+
"loss": 0.6675,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.14619289340101524,
|
| 69 |
+
"grad_norm": 2.839936985092543,
|
| 70 |
+
"learning_rate": 3.789473684210526e-05,
|
| 71 |
+
"loss": 0.6339,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.16243654822335024,
|
| 76 |
+
"grad_norm": 2.13780637268824,
|
| 77 |
+
"learning_rate": 4.210526315789474e-05,
|
| 78 |
+
"loss": 0.6086,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.17868020304568527,
|
| 83 |
+
"grad_norm": 1.5941717672571045,
|
| 84 |
+
"learning_rate": 4.6315789473684214e-05,
|
| 85 |
+
"loss": 0.5825,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.1949238578680203,
|
| 90 |
+
"grad_norm": 1.6168928558054896,
|
| 91 |
+
"learning_rate": 5.052631578947368e-05,
|
| 92 |
+
"loss": 0.5701,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.21116751269035533,
|
| 97 |
+
"grad_norm": 2.2327738877787646,
|
| 98 |
+
"learning_rate": 5.4736842105263165e-05,
|
| 99 |
+
"loss": 0.5649,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.22741116751269036,
|
| 104 |
+
"grad_norm": 1.922360650495667,
|
| 105 |
+
"learning_rate": 5.8947368421052634e-05,
|
| 106 |
+
"loss": 0.5556,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.2436548223350254,
|
| 111 |
+
"grad_norm": 1.5360747043737273,
|
| 112 |
+
"learning_rate": 6.315789473684212e-05,
|
| 113 |
+
"loss": 0.5472,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.2598984771573604,
|
| 118 |
+
"grad_norm": 1.6023781510033264,
|
| 119 |
+
"learning_rate": 6.736842105263159e-05,
|
| 120 |
+
"loss": 0.5383,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.27614213197969545,
|
| 125 |
+
"grad_norm": 1.4948570507713637,
|
| 126 |
+
"learning_rate": 7.157894736842105e-05,
|
| 127 |
+
"loss": 0.5259,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.2923857868020305,
|
| 132 |
+
"grad_norm": 1.6235378104579135,
|
| 133 |
+
"learning_rate": 7.578947368421052e-05,
|
| 134 |
+
"loss": 0.5215,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.3086294416243655,
|
| 139 |
+
"grad_norm": 1.49280941435323,
|
| 140 |
+
"learning_rate": 8e-05,
|
| 141 |
+
"loss": 0.5219,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.3248730964467005,
|
| 146 |
+
"grad_norm": 1.52673025515821,
|
| 147 |
+
"learning_rate": 7.999266113727178e-05,
|
| 148 |
+
"loss": 0.5159,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.3411167512690355,
|
| 153 |
+
"grad_norm": 2.0944356574595644,
|
| 154 |
+
"learning_rate": 7.99706472420324e-05,
|
| 155 |
+
"loss": 0.5082,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.35736040609137054,
|
| 160 |
+
"grad_norm": 1.1426245341381593,
|
| 161 |
+
"learning_rate": 7.993396639212965e-05,
|
| 162 |
+
"loss": 0.5065,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.37360406091370557,
|
| 167 |
+
"grad_norm": 2.027227172313339,
|
| 168 |
+
"learning_rate": 7.988263204734962e-05,
|
| 169 |
+
"loss": 0.5082,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.3898477157360406,
|
| 174 |
+
"grad_norm": 1.2244497820900966,
|
| 175 |
+
"learning_rate": 7.98166630444778e-05,
|
| 176 |
+
"loss": 0.5009,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.40609137055837563,
|
| 181 |
+
"grad_norm": 1.6772440184784814,
|
| 182 |
+
"learning_rate": 7.973608359038701e-05,
|
| 183 |
+
"loss": 0.4935,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.42233502538071066,
|
| 188 |
+
"grad_norm": 1.3035902371007322,
|
| 189 |
+
"learning_rate": 7.964092325315485e-05,
|
| 190 |
+
"loss": 0.4869,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.4385786802030457,
|
| 195 |
+
"grad_norm": 1.3526293786861174,
|
| 196 |
+
"learning_rate": 7.953121695121395e-05,
|
| 197 |
+
"loss": 0.492,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.4548223350253807,
|
| 202 |
+
"grad_norm": 1.425792402521663,
|
| 203 |
+
"learning_rate": 7.94070049405388e-05,
|
| 204 |
+
"loss": 0.4773,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.47106598984771575,
|
| 209 |
+
"grad_norm": 1.0589770114481525,
|
| 210 |
+
"learning_rate": 7.926833279987421e-05,
|
| 211 |
+
"loss": 0.4869,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.4873096446700508,
|
| 216 |
+
"grad_norm": 1.0852485944575374,
|
| 217 |
+
"learning_rate": 7.911525141401037e-05,
|
| 218 |
+
"loss": 0.4752,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.5035532994923858,
|
| 223 |
+
"grad_norm": 1.1576752537494561,
|
| 224 |
+
"learning_rate": 7.894781695511117e-05,
|
| 225 |
+
"loss": 0.4811,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.5197969543147208,
|
| 230 |
+
"grad_norm": 2.0538631486502723,
|
| 231 |
+
"learning_rate": 7.876609086210207e-05,
|
| 232 |
+
"loss": 0.4832,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.5360406091370559,
|
| 237 |
+
"grad_norm": 1.1528883813172177,
|
| 238 |
+
"learning_rate": 7.857013981812564e-05,
|
| 239 |
+
"loss": 0.4706,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.5522842639593909,
|
| 244 |
+
"grad_norm": 1.6961278477225181,
|
| 245 |
+
"learning_rate": 7.836003572607253e-05,
|
| 246 |
+
"loss": 0.4933,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.5685279187817259,
|
| 251 |
+
"grad_norm": 1.338921085872361,
|
| 252 |
+
"learning_rate": 7.813585568219723e-05,
|
| 253 |
+
"loss": 0.4735,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.584771573604061,
|
| 258 |
+
"grad_norm": 1.2911770652190075,
|
| 259 |
+
"learning_rate": 7.789768194782818e-05,
|
| 260 |
+
"loss": 0.4795,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.601015228426396,
|
| 265 |
+
"grad_norm": 1.1735059474903817,
|
| 266 |
+
"learning_rate": 7.764560191918247e-05,
|
| 267 |
+
"loss": 0.4739,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.617258883248731,
|
| 272 |
+
"grad_norm": 1.0123782894306088,
|
| 273 |
+
"learning_rate": 7.737970809529645e-05,
|
| 274 |
+
"loss": 0.4665,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.6335025380710659,
|
| 279 |
+
"grad_norm": 0.9595374983763921,
|
| 280 |
+
"learning_rate": 7.71000980440838e-05,
|
| 281 |
+
"loss": 0.4616,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.649746192893401,
|
| 286 |
+
"grad_norm": 1.0251669587395573,
|
| 287 |
+
"learning_rate": 7.680687436653367e-05,
|
| 288 |
+
"loss": 0.4578,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.665989847715736,
|
| 293 |
+
"grad_norm": 0.8481767848175804,
|
| 294 |
+
"learning_rate": 7.650014465906201e-05,
|
| 295 |
+
"loss": 0.4532,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.682233502538071,
|
| 300 |
+
"grad_norm": 1.1450293435840186,
|
| 301 |
+
"learning_rate": 7.618002147402967e-05,
|
| 302 |
+
"loss": 0.4504,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.698477157360406,
|
| 307 |
+
"grad_norm": 0.7376186540483177,
|
| 308 |
+
"learning_rate": 7.584662227844223e-05,
|
| 309 |
+
"loss": 0.4514,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.7147208121827411,
|
| 314 |
+
"grad_norm": 1.002643345794404,
|
| 315 |
+
"learning_rate": 7.550006941084619e-05,
|
| 316 |
+
"loss": 0.4531,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.7309644670050761,
|
| 321 |
+
"grad_norm": 1.2178757607184856,
|
| 322 |
+
"learning_rate": 7.51404900364377e-05,
|
| 323 |
+
"loss": 0.441,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.7472081218274111,
|
| 328 |
+
"grad_norm": 0.8379800700247181,
|
| 329 |
+
"learning_rate": 7.476801610040021e-05,
|
| 330 |
+
"loss": 0.4404,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.7634517766497462,
|
| 335 |
+
"grad_norm": 0.7565253428528901,
|
| 336 |
+
"learning_rate": 7.438278427948805e-05,
|
| 337 |
+
"loss": 0.4382,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.7796954314720812,
|
| 342 |
+
"grad_norm": 0.6727947399441317,
|
| 343 |
+
"learning_rate": 7.398493593187383e-05,
|
| 344 |
+
"loss": 0.4373,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.7959390862944162,
|
| 349 |
+
"grad_norm": 0.876356454587121,
|
| 350 |
+
"learning_rate": 7.357461704527802e-05,
|
| 351 |
+
"loss": 0.4373,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.8121827411167513,
|
| 356 |
+
"grad_norm": 1.0412780327861013,
|
| 357 |
+
"learning_rate": 7.315197818339979e-05,
|
| 358 |
+
"loss": 0.4406,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.8284263959390863,
|
| 363 |
+
"grad_norm": 1.2604470089396205,
|
| 364 |
+
"learning_rate": 7.271717443066871e-05,
|
| 365 |
+
"loss": 0.4344,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.8446700507614213,
|
| 370 |
+
"grad_norm": 1.004867279026282,
|
| 371 |
+
"learning_rate": 7.227036533533753e-05,
|
| 372 |
+
"loss": 0.433,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.8609137055837564,
|
| 377 |
+
"grad_norm": 0.8563093497070937,
|
| 378 |
+
"learning_rate": 7.181171485093706e-05,
|
| 379 |
+
"loss": 0.4304,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.8771573604060914,
|
| 384 |
+
"grad_norm": 0.5671831882105272,
|
| 385 |
+
"learning_rate": 7.134139127611457e-05,
|
| 386 |
+
"loss": 0.4221,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.8934010152284264,
|
| 391 |
+
"grad_norm": 0.5655405062857799,
|
| 392 |
+
"learning_rate": 7.085956719287773e-05,
|
| 393 |
+
"loss": 0.4288,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.9096446700507614,
|
| 398 |
+
"grad_norm": 0.6227846963328939,
|
| 399 |
+
"learning_rate": 7.036641940326682e-05,
|
| 400 |
+
"loss": 0.4271,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.9258883248730965,
|
| 405 |
+
"grad_norm": 0.7242656258268864,
|
| 406 |
+
"learning_rate": 6.986212886447851e-05,
|
| 407 |
+
"loss": 0.4313,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.9421319796954315,
|
| 412 |
+
"grad_norm": 0.7433411082090003,
|
| 413 |
+
"learning_rate": 6.934688062246474e-05,
|
| 414 |
+
"loss": 0.4218,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.9583756345177665,
|
| 419 |
+
"grad_norm": 0.8720528869263957,
|
| 420 |
+
"learning_rate": 6.882086374403148e-05,
|
| 421 |
+
"loss": 0.4348,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.9746192893401016,
|
| 426 |
+
"grad_norm": 0.9990535700111963,
|
| 427 |
+
"learning_rate": 6.828427124746191e-05,
|
| 428 |
+
"loss": 0.4272,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.9908629441624366,
|
| 433 |
+
"grad_norm": 1.015667186765777,
|
| 434 |
+
"learning_rate": 6.773730003168967e-05,
|
| 435 |
+
"loss": 0.4279,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 1.0101522842639594,
|
| 440 |
+
"grad_norm": 2.3437756145181603,
|
| 441 |
+
"learning_rate": 6.718015080404824e-05,
|
| 442 |
+
"loss": 0.691,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.0263959390862945,
|
| 447 |
+
"grad_norm": 0.7192408099739781,
|
| 448 |
+
"learning_rate": 6.661302800662261e-05,
|
| 449 |
+
"loss": 0.4051,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.0426395939086295,
|
| 454 |
+
"grad_norm": 0.8432945110635002,
|
| 455 |
+
"learning_rate": 6.603613974123086e-05,
|
| 456 |
+
"loss": 0.4116,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 1.0588832487309645,
|
| 461 |
+
"grad_norm": 1.2726135726974086,
|
| 462 |
+
"learning_rate": 6.54496976930624e-05,
|
| 463 |
+
"loss": 0.4076,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 1.0751269035532995,
|
| 468 |
+
"grad_norm": 1.0079271087443598,
|
| 469 |
+
"learning_rate": 6.485391705300173e-05,
|
| 470 |
+
"loss": 0.4069,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.0913705583756346,
|
| 475 |
+
"grad_norm": 1.1533020481630858,
|
| 476 |
+
"learning_rate": 6.424901643866553e-05,
|
| 477 |
+
"loss": 0.4011,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 1.1076142131979696,
|
| 482 |
+
"grad_norm": 1.0026635744570633,
|
| 483 |
+
"learning_rate": 6.363521781418243e-05,
|
| 484 |
+
"loss": 0.4033,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 1.1238578680203046,
|
| 489 |
+
"grad_norm": 0.9231770673079176,
|
| 490 |
+
"learning_rate": 6.301274640874483e-05,
|
| 491 |
+
"loss": 0.4032,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 1.1401015228426397,
|
| 496 |
+
"grad_norm": 0.8692546537652855,
|
| 497 |
+
"learning_rate": 6.238183063396257e-05,
|
| 498 |
+
"loss": 0.397,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 1.1563451776649747,
|
| 503 |
+
"grad_norm": 0.9442686170156996,
|
| 504 |
+
"learning_rate": 6.174270200004885e-05,
|
| 505 |
+
"loss": 0.3919,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.1725888324873097,
|
| 510 |
+
"grad_norm": 0.9040277727758386,
|
| 511 |
+
"learning_rate": 6.109559503086918e-05,
|
| 512 |
+
"loss": 0.4003,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.1888324873096447,
|
| 517 |
+
"grad_norm": 1.124693266326007,
|
| 518 |
+
"learning_rate": 6.044074717788442e-05,
|
| 519 |
+
"loss": 0.3989,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 1.2050761421319798,
|
| 524 |
+
"grad_norm": 0.7075238799261049,
|
| 525 |
+
"learning_rate": 5.9778398733019614e-05,
|
| 526 |
+
"loss": 0.3908,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.2213197969543148,
|
| 531 |
+
"grad_norm": 0.7559974740351498,
|
| 532 |
+
"learning_rate": 5.910879274049052e-05,
|
| 533 |
+
"loss": 0.3987,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.2375634517766498,
|
| 538 |
+
"grad_norm": 0.8753481648950223,
|
| 539 |
+
"learning_rate": 5.84321749076202e-05,
|
| 540 |
+
"loss": 0.4045,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.2538071065989849,
|
| 545 |
+
"grad_norm": 0.8249863395981523,
|
| 546 |
+
"learning_rate": 5.7748793514678394e-05,
|
| 547 |
+
"loss": 0.4017,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.2700507614213197,
|
| 552 |
+
"grad_norm": 0.8834530813481759,
|
| 553 |
+
"learning_rate": 5.705889932377679e-05,
|
| 554 |
+
"loss": 0.3972,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.286294416243655,
|
| 559 |
+
"grad_norm": 0.5321200318731625,
|
| 560 |
+
"learning_rate": 5.636274548685361e-05,
|
| 561 |
+
"loss": 0.4009,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.3025380710659897,
|
| 566 |
+
"grad_norm": 0.6712989019156405,
|
| 567 |
+
"learning_rate": 5.566058745278117e-05,
|
| 568 |
+
"loss": 0.39,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.318781725888325,
|
| 573 |
+
"grad_norm": 0.5440707965852146,
|
| 574 |
+
"learning_rate": 5.4952682873630755e-05,
|
| 575 |
+
"loss": 0.3979,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.3350253807106598,
|
| 580 |
+
"grad_norm": 0.6907333140636629,
|
| 581 |
+
"learning_rate": 5.4239291510128936e-05,
|
| 582 |
+
"loss": 0.3974,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 1.351269035532995,
|
| 587 |
+
"grad_norm": 0.7093211514864298,
|
| 588 |
+
"learning_rate": 5.352067513634011e-05,
|
| 589 |
+
"loss": 0.395,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.3675126903553299,
|
| 594 |
+
"grad_norm": 0.5197383653605123,
|
| 595 |
+
"learning_rate": 5.279709744361036e-05,
|
| 596 |
+
"loss": 0.3917,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.383756345177665,
|
| 601 |
+
"grad_norm": 0.4873841137171276,
|
| 602 |
+
"learning_rate": 5.20688239438077e-05,
|
| 603 |
+
"loss": 0.3897,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.4,
|
| 608 |
+
"grad_norm": 0.7772345510903597,
|
| 609 |
+
"learning_rate": 5.133612187189429e-05,
|
| 610 |
+
"loss": 0.3958,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.4162436548223352,
|
| 615 |
+
"grad_norm": 0.6568207816645832,
|
| 616 |
+
"learning_rate": 5.059926008786648e-05,
|
| 617 |
+
"loss": 0.3885,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.43248730964467,
|
| 622 |
+
"grad_norm": 0.6865987314717193,
|
| 623 |
+
"learning_rate": 4.985850897809838e-05,
|
| 624 |
+
"loss": 0.3913,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.448730964467005,
|
| 629 |
+
"grad_norm": 0.6754318415370026,
|
| 630 |
+
"learning_rate": 4.911414035612551e-05,
|
| 631 |
+
"loss": 0.3897,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.46497461928934,
|
| 636 |
+
"grad_norm": 0.5510166556882232,
|
| 637 |
+
"learning_rate": 4.836642736290468e-05,
|
| 638 |
+
"loss": 0.3863,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.481218274111675,
|
| 643 |
+
"grad_norm": 0.4218642671019698,
|
| 644 |
+
"learning_rate": 4.761564436658674e-05,
|
| 645 |
+
"loss": 0.3905,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.49746192893401,
|
| 650 |
+
"grad_norm": 0.33249291138365206,
|
| 651 |
+
"learning_rate": 4.686206686183914e-05,
|
| 652 |
+
"loss": 0.3842,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.5137055837563453,
|
| 657 |
+
"grad_norm": 0.36240839911771244,
|
| 658 |
+
"learning_rate": 4.610597136875498e-05,
|
| 659 |
+
"loss": 0.3849,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.5299492385786801,
|
| 664 |
+
"grad_norm": 0.4075634735970758,
|
| 665 |
+
"learning_rate": 4.534763533138594e-05,
|
| 666 |
+
"loss": 0.382,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.5461928934010152,
|
| 671 |
+
"grad_norm": 0.4020419111096129,
|
| 672 |
+
"learning_rate": 4.458733701593603e-05,
|
| 673 |
+
"loss": 0.3902,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.5624365482233502,
|
| 678 |
+
"grad_norm": 0.4162126818044518,
|
| 679 |
+
"learning_rate": 4.3825355408653694e-05,
|
| 680 |
+
"loss": 0.3865,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.5786802030456852,
|
| 685 |
+
"grad_norm": 0.3250125445127836,
|
| 686 |
+
"learning_rate": 4.306197011345984e-05,
|
| 687 |
+
"loss": 0.3927,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.5949238578680203,
|
| 692 |
+
"grad_norm": 0.37873273335865215,
|
| 693 |
+
"learning_rate": 4.229746124934894e-05,
|
| 694 |
+
"loss": 0.3897,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 1.6111675126903553,
|
| 699 |
+
"grad_norm": 0.26283572176655795,
|
| 700 |
+
"learning_rate": 4.153210934760142e-05,
|
| 701 |
+
"loss": 0.3898,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.6274111675126903,
|
| 706 |
+
"grad_norm": 0.3697844911122642,
|
| 707 |
+
"learning_rate": 4.0766195248844574e-05,
|
| 708 |
+
"loss": 0.3915,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.6436548223350254,
|
| 713 |
+
"grad_norm": 0.4192576770954174,
|
| 714 |
+
"learning_rate": 4e-05,
|
| 715 |
+
"loss": 0.3938,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 1.6598984771573604,
|
| 720 |
+
"grad_norm": 0.24580117390367293,
|
| 721 |
+
"learning_rate": 3.923380475115544e-05,
|
| 722 |
+
"loss": 0.3837,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.6761421319796954,
|
| 727 |
+
"grad_norm": 0.35508418766154465,
|
| 728 |
+
"learning_rate": 3.846789065239859e-05,
|
| 729 |
+
"loss": 0.3866,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.6923857868020304,
|
| 734 |
+
"grad_norm": 0.3642394227261978,
|
| 735 |
+
"learning_rate": 3.770253875065107e-05,
|
| 736 |
+
"loss": 0.3879,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.7086294416243655,
|
| 741 |
+
"grad_norm": 0.23721046069527885,
|
| 742 |
+
"learning_rate": 3.6938029886540174e-05,
|
| 743 |
+
"loss": 0.386,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.7248730964467005,
|
| 748 |
+
"grad_norm": 0.3182396199511866,
|
| 749 |
+
"learning_rate": 3.617464459134631e-05,
|
| 750 |
+
"loss": 0.382,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.7411167512690355,
|
| 755 |
+
"grad_norm": 0.23591223152132948,
|
| 756 |
+
"learning_rate": 3.541266298406399e-05,
|
| 757 |
+
"loss": 0.3837,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.7573604060913706,
|
| 762 |
+
"grad_norm": 0.3103657704912103,
|
| 763 |
+
"learning_rate": 3.4652364668614065e-05,
|
| 764 |
+
"loss": 0.385,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.7736040609137056,
|
| 769 |
+
"grad_norm": 0.23604167874137535,
|
| 770 |
+
"learning_rate": 3.3894028631245017e-05,
|
| 771 |
+
"loss": 0.388,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 1.7898477157360406,
|
| 776 |
+
"grad_norm": 0.2123461071124295,
|
| 777 |
+
"learning_rate": 3.313793313816087e-05,
|
| 778 |
+
"loss": 0.3873,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.8060913705583757,
|
| 783 |
+
"grad_norm": 0.2159520420107397,
|
| 784 |
+
"learning_rate": 3.238435563341326e-05,
|
| 785 |
+
"loss": 0.3837,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.8223350253807107,
|
| 790 |
+
"grad_norm": 0.22146736675422216,
|
| 791 |
+
"learning_rate": 3.163357263709534e-05,
|
| 792 |
+
"loss": 0.3819,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 1.8385786802030457,
|
| 797 |
+
"grad_norm": 0.17002552231432885,
|
| 798 |
+
"learning_rate": 3.088585964387451e-05,
|
| 799 |
+
"loss": 0.3768,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 1.8548223350253807,
|
| 804 |
+
"grad_norm": 0.24119956983584898,
|
| 805 |
+
"learning_rate": 3.0141491021901644e-05,
|
| 806 |
+
"loss": 0.3839,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.8710659898477158,
|
| 811 |
+
"grad_norm": 0.2013830370445654,
|
| 812 |
+
"learning_rate": 2.9400739912133543e-05,
|
| 813 |
+
"loss": 0.3797,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 1.8873096446700508,
|
| 818 |
+
"grad_norm": 0.18674898588211797,
|
| 819 |
+
"learning_rate": 2.866387812810572e-05,
|
| 820 |
+
"loss": 0.3823,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 1.9035532994923858,
|
| 825 |
+
"grad_norm": 0.26548717082542594,
|
| 826 |
+
"learning_rate": 2.793117605619231e-05,
|
| 827 |
+
"loss": 0.378,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 1.9197969543147209,
|
| 832 |
+
"grad_norm": 0.2002277680016461,
|
| 833 |
+
"learning_rate": 2.7202902556389647e-05,
|
| 834 |
+
"loss": 0.3814,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 1.936040609137056,
|
| 839 |
+
"grad_norm": 0.15827356517250973,
|
| 840 |
+
"learning_rate": 2.6479324863659897e-05,
|
| 841 |
+
"loss": 0.3721,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 1.952284263959391,
|
| 846 |
+
"grad_norm": 0.1653044744580572,
|
| 847 |
+
"learning_rate": 2.5760708489871077e-05,
|
| 848 |
+
"loss": 0.3854,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.9685279187817257,
|
| 853 |
+
"grad_norm": 0.16729489813208265,
|
| 854 |
+
"learning_rate": 2.504731712636925e-05,
|
| 855 |
+
"loss": 0.3784,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 1.984771573604061,
|
| 860 |
+
"grad_norm": 0.16164016444282092,
|
| 861 |
+
"learning_rate": 2.4339412547218845e-05,
|
| 862 |
+
"loss": 0.3809,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 2.0040609137055836,
|
| 867 |
+
"grad_norm": 0.28163111232184695,
|
| 868 |
+
"learning_rate": 2.3637254513146406e-05,
|
| 869 |
+
"loss": 0.606,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 2.020304568527919,
|
| 874 |
+
"grad_norm": 0.1925240063892539,
|
| 875 |
+
"learning_rate": 2.294110067622321e-05,
|
| 876 |
+
"loss": 0.3647,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 2.0365482233502537,
|
| 881 |
+
"grad_norm": 0.20226990255325633,
|
| 882 |
+
"learning_rate": 2.225120648532161e-05,
|
| 883 |
+
"loss": 0.3608,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 2.052791878172589,
|
| 888 |
+
"grad_norm": 0.16740913026001164,
|
| 889 |
+
"learning_rate": 2.1567825092379807e-05,
|
| 890 |
+
"loss": 0.3614,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 2.0690355329949237,
|
| 895 |
+
"grad_norm": 0.25083361243306157,
|
| 896 |
+
"learning_rate": 2.089120725950948e-05,
|
| 897 |
+
"loss": 0.3682,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 2.085279187817259,
|
| 902 |
+
"grad_norm": 0.19080011782710088,
|
| 903 |
+
"learning_rate": 2.0221601266980383e-05,
|
| 904 |
+
"loss": 0.3548,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 2.1015228426395938,
|
| 909 |
+
"grad_norm": 0.2188934640616483,
|
| 910 |
+
"learning_rate": 1.955925282211558e-05,
|
| 911 |
+
"loss": 0.3552,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 2.117766497461929,
|
| 916 |
+
"grad_norm": 0.2172533644259959,
|
| 917 |
+
"learning_rate": 1.890440496913083e-05,
|
| 918 |
+
"loss": 0.3641,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 2.134010152284264,
|
| 923 |
+
"grad_norm": 0.1707808407927364,
|
| 924 |
+
"learning_rate": 1.825729799995116e-05,
|
| 925 |
+
"loss": 0.3641,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 2.150253807106599,
|
| 930 |
+
"grad_norm": 0.1946400955168161,
|
| 931 |
+
"learning_rate": 1.761816936603744e-05,
|
| 932 |
+
"loss": 0.3618,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 2.166497461928934,
|
| 937 |
+
"grad_norm": 0.14159881045312211,
|
| 938 |
+
"learning_rate": 1.6987253591255178e-05,
|
| 939 |
+
"loss": 0.3546,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 2.182741116751269,
|
| 944 |
+
"grad_norm": 0.1881834295592266,
|
| 945 |
+
"learning_rate": 1.6364782185817592e-05,
|
| 946 |
+
"loss": 0.3549,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 2.198984771573604,
|
| 951 |
+
"grad_norm": 0.15289061814224608,
|
| 952 |
+
"learning_rate": 1.5750983561334493e-05,
|
| 953 |
+
"loss": 0.3586,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 2.215228426395939,
|
| 958 |
+
"grad_norm": 0.15911195051937885,
|
| 959 |
+
"learning_rate": 1.5146082946998286e-05,
|
| 960 |
+
"loss": 0.3559,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 2.231472081218274,
|
| 965 |
+
"grad_norm": 0.19045813298325232,
|
| 966 |
+
"learning_rate": 1.4550302306937619e-05,
|
| 967 |
+
"loss": 0.3639,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 2.2477157360406093,
|
| 972 |
+
"grad_norm": 0.15335108480289958,
|
| 973 |
+
"learning_rate": 1.396386025876916e-05,
|
| 974 |
+
"loss": 0.355,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 2.263959390862944,
|
| 979 |
+
"grad_norm": 0.16446774618332,
|
| 980 |
+
"learning_rate": 1.338697199337739e-05,
|
| 981 |
+
"loss": 0.3549,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 2.2802030456852793,
|
| 986 |
+
"grad_norm": 0.15106141305507895,
|
| 987 |
+
"learning_rate": 1.2819849195951778e-05,
|
| 988 |
+
"loss": 0.3586,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 2.296446700507614,
|
| 993 |
+
"grad_norm": 0.13993724665364407,
|
| 994 |
+
"learning_rate": 1.2262699968310336e-05,
|
| 995 |
+
"loss": 0.3604,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 2.3126903553299494,
|
| 1000 |
+
"grad_norm": 0.1363435862641145,
|
| 1001 |
+
"learning_rate": 1.1715728752538103e-05,
|
| 1002 |
+
"loss": 0.3551,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 2.328934010152284,
|
| 1007 |
+
"grad_norm": 0.1339274080889315,
|
| 1008 |
+
"learning_rate": 1.1179136255968523e-05,
|
| 1009 |
+
"loss": 0.3563,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 2.3451776649746194,
|
| 1014 |
+
"grad_norm": 0.12185082172688805,
|
| 1015 |
+
"learning_rate": 1.065311937753526e-05,
|
| 1016 |
+
"loss": 0.359,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 2.3614213197969542,
|
| 1021 |
+
"grad_norm": 0.1321809457616183,
|
| 1022 |
+
"learning_rate": 1.0137871135521493e-05,
|
| 1023 |
+
"loss": 0.3548,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 2.3776649746192895,
|
| 1028 |
+
"grad_norm": 0.13050325616691505,
|
| 1029 |
+
"learning_rate": 9.633580596733179e-06,
|
| 1030 |
+
"loss": 0.3523,
|
| 1031 |
+
"step": 146
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 2.3939086294416243,
|
| 1035 |
+
"grad_norm": 0.11130286495660592,
|
| 1036 |
+
"learning_rate": 9.140432807122282e-06,
|
| 1037 |
+
"loss": 0.359,
|
| 1038 |
+
"step": 147
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 2.4101522842639596,
|
| 1042 |
+
"grad_norm": 0.10084069337286101,
|
| 1043 |
+
"learning_rate": 8.658608723885433e-06,
|
| 1044 |
+
"loss": 0.3518,
|
| 1045 |
+
"step": 148
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 2.4263959390862944,
|
| 1049 |
+
"grad_norm": 0.10103011757244325,
|
| 1050 |
+
"learning_rate": 8.18828514906294e-06,
|
| 1051 |
+
"loss": 0.3535,
|
| 1052 |
+
"step": 149
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 2.4426395939086296,
|
| 1056 |
+
"grad_norm": 0.09880519324295578,
|
| 1057 |
+
"learning_rate": 7.729634664662469e-06,
|
| 1058 |
+
"loss": 0.3534,
|
| 1059 |
+
"step": 150
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 2.4588832487309644,
|
| 1063 |
+
"grad_norm": 0.10471446375611543,
|
| 1064 |
+
"learning_rate": 7.282825569331296e-06,
|
| 1065 |
+
"loss": 0.3596,
|
| 1066 |
+
"step": 151
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 2.4751269035532997,
|
| 1070 |
+
"grad_norm": 0.10882725576899555,
|
| 1071 |
+
"learning_rate": 6.848021816600221e-06,
|
| 1072 |
+
"loss": 0.361,
|
| 1073 |
+
"step": 152
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 2.4913705583756345,
|
| 1077 |
+
"grad_norm": 0.09782268685408212,
|
| 1078 |
+
"learning_rate": 6.425382954722002e-06,
|
| 1079 |
+
"loss": 0.3614,
|
| 1080 |
+
"step": 153
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 2.5076142131979697,
|
| 1084 |
+
"grad_norm": 0.10430688918677015,
|
| 1085 |
+
"learning_rate": 6.015064068126188e-06,
|
| 1086 |
+
"loss": 0.3575,
|
| 1087 |
+
"step": 154
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 2.5238578680203045,
|
| 1091 |
+
"grad_norm": 0.1172067268082759,
|
| 1092 |
+
"learning_rate": 5.617215720511962e-06,
|
| 1093 |
+
"loss": 0.351,
|
| 1094 |
+
"step": 155
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 2.5401015228426393,
|
| 1098 |
+
"grad_norm": 0.09574414741627191,
|
| 1099 |
+
"learning_rate": 5.231983899599798e-06,
|
| 1100 |
+
"loss": 0.3543,
|
| 1101 |
+
"step": 156
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 2.5563451776649746,
|
| 1105 |
+
"grad_norm": 0.09746185929647122,
|
| 1106 |
+
"learning_rate": 4.859509963562313e-06,
|
| 1107 |
+
"loss": 0.3646,
|
| 1108 |
+
"step": 157
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 2.57258883248731,
|
| 1112 |
+
"grad_norm": 0.10144569993947126,
|
| 1113 |
+
"learning_rate": 4.4999305891538294e-06,
|
| 1114 |
+
"loss": 0.3546,
|
| 1115 |
+
"step": 158
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 2.5888324873096447,
|
| 1119 |
+
"grad_norm": 0.09770560240880942,
|
| 1120 |
+
"learning_rate": 4.153377721557781e-06,
|
| 1121 |
+
"loss": 0.3579,
|
| 1122 |
+
"step": 159
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 2.6050761421319795,
|
| 1126 |
+
"grad_norm": 0.09280446790594858,
|
| 1127 |
+
"learning_rate": 3.819978525970336e-06,
|
| 1128 |
+
"loss": 0.3565,
|
| 1129 |
+
"step": 160
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 2.6213197969543147,
|
| 1133 |
+
"grad_norm": 0.08692751824611722,
|
| 1134 |
+
"learning_rate": 3.499855340938001e-06,
|
| 1135 |
+
"loss": 0.3553,
|
| 1136 |
+
"step": 161
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 2.63756345177665,
|
| 1140 |
+
"grad_norm": 0.10842712708563858,
|
| 1141 |
+
"learning_rate": 3.19312563346633e-06,
|
| 1142 |
+
"loss": 0.3545,
|
| 1143 |
+
"step": 162
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 2.6538071065989848,
|
| 1147 |
+
"grad_norm": 0.09032134534631381,
|
| 1148 |
+
"learning_rate": 2.8999019559162156e-06,
|
| 1149 |
+
"loss": 0.3552,
|
| 1150 |
+
"step": 163
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 2.6700507614213196,
|
| 1154 |
+
"grad_norm": 0.09027568441791341,
|
| 1155 |
+
"learning_rate": 2.6202919047035604e-06,
|
| 1156 |
+
"loss": 0.3468,
|
| 1157 |
+
"step": 164
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 2.686294416243655,
|
| 1161 |
+
"grad_norm": 0.08414383492724592,
|
| 1162 |
+
"learning_rate": 2.3543980808175393e-06,
|
| 1163 |
+
"loss": 0.3562,
|
| 1164 |
+
"step": 165
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 2.70253807106599,
|
| 1168 |
+
"grad_norm": 0.07832242786610931,
|
| 1169 |
+
"learning_rate": 2.10231805217183e-06,
|
| 1170 |
+
"loss": 0.3556,
|
| 1171 |
+
"step": 166
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 2.718781725888325,
|
| 1175 |
+
"grad_norm": 0.08668215141175065,
|
| 1176 |
+
"learning_rate": 1.8641443178027784e-06,
|
| 1177 |
+
"loss": 0.354,
|
| 1178 |
+
"step": 167
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 2.7350253807106597,
|
| 1182 |
+
"grad_norm": 0.09642452144914332,
|
| 1183 |
+
"learning_rate": 1.6399642739274791e-06,
|
| 1184 |
+
"loss": 0.3534,
|
| 1185 |
+
"step": 168
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 2.751269035532995,
|
| 1189 |
+
"grad_norm": 0.08397615302565715,
|
| 1190 |
+
"learning_rate": 1.4298601818743607e-06,
|
| 1191 |
+
"loss": 0.3585,
|
| 1192 |
+
"step": 169
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 2.76751269035533,
|
| 1196 |
+
"grad_norm": 0.0868453744624661,
|
| 1197 |
+
"learning_rate": 1.233909137897924e-06,
|
| 1198 |
+
"loss": 0.3632,
|
| 1199 |
+
"step": 170
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 2.783756345177665,
|
| 1203 |
+
"grad_norm": 0.085225634007902,
|
| 1204 |
+
"learning_rate": 1.0521830448888414e-06,
|
| 1205 |
+
"loss": 0.3581,
|
| 1206 |
+
"step": 171
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 2.8,
|
| 1210 |
+
"grad_norm": 0.08094902436979953,
|
| 1211 |
+
"learning_rate": 8.847485859896365e-07,
|
| 1212 |
+
"loss": 0.3502,
|
| 1213 |
+
"step": 172
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 2.816243654822335,
|
| 1217 |
+
"grad_norm": 0.08165676150513626,
|
| 1218 |
+
"learning_rate": 7.31667200125803e-07,
|
| 1219 |
+
"loss": 0.3567,
|
| 1220 |
+
"step": 173
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 2.8324873096446703,
|
| 1224 |
+
"grad_norm": 0.08289385702790433,
|
| 1225 |
+
"learning_rate": 5.929950594612032e-07,
|
| 1226 |
+
"loss": 0.3554,
|
| 1227 |
+
"step": 174
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 2.848730964467005,
|
| 1231 |
+
"grad_norm": 0.07955035485502655,
|
| 1232 |
+
"learning_rate": 4.687830487860634e-07,
|
| 1233 |
+
"loss": 0.3563,
|
| 1234 |
+
"step": 175
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 2.86497461928934,
|
| 1238 |
+
"grad_norm": 0.07869020841570933,
|
| 1239 |
+
"learning_rate": 3.590767468451528e-07,
|
| 1240 |
+
"loss": 0.3505,
|
| 1241 |
+
"step": 176
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 2.881218274111675,
|
| 1245 |
+
"grad_norm": 0.08319077707558656,
|
| 1246 |
+
"learning_rate": 2.639164096129987e-07,
|
| 1247 |
+
"loss": 0.3541,
|
| 1248 |
+
"step": 177
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 2.89746192893401,
|
| 1252 |
+
"grad_norm": 0.07867342327367309,
|
| 1253 |
+
"learning_rate": 1.833369555222042e-07,
|
| 1254 |
+
"loss": 0.356,
|
| 1255 |
+
"step": 178
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 2.9137055837563453,
|
| 1259 |
+
"grad_norm": 0.07940276764093634,
|
| 1260 |
+
"learning_rate": 1.1736795265038237e-07,
|
| 1261 |
+
"loss": 0.3602,
|
| 1262 |
+
"step": 179
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 2.92994923857868,
|
| 1266 |
+
"grad_norm": 0.08102239091967386,
|
| 1267 |
+
"learning_rate": 6.603360787035495e-08,
|
| 1268 |
+
"loss": 0.3592,
|
| 1269 |
+
"step": 180
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 2.9461928934010153,
|
| 1273 |
+
"grad_norm": 0.07325271521654589,
|
| 1274 |
+
"learning_rate": 2.9352757967600064e-08,
|
| 1275 |
+
"loss": 0.3495,
|
| 1276 |
+
"step": 181
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 2.96243654822335,
|
| 1280 |
+
"grad_norm": 0.07584071622767746,
|
| 1281 |
+
"learning_rate": 7.338862728225593e-09,
|
| 1282 |
+
"loss": 0.3571,
|
| 1283 |
+
"step": 182
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 2.9786802030456854,
|
| 1287 |
+
"grad_norm": 0.07924817576453998,
|
| 1288 |
+
"learning_rate": 0.0,
|
| 1289 |
+
"loss": 0.3592,
|
| 1290 |
+
"step": 183
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 2.9786802030456854,
|
| 1294 |
+
"step": 183,
|
| 1295 |
+
"total_flos": 4.709134058959929e+18,
|
| 1296 |
+
"train_loss": 0.42409751356625164,
|
| 1297 |
+
"train_runtime": 40618.2962,
|
| 1298 |
+
"train_samples_per_second": 2.327,
|
| 1299 |
+
"train_steps_per_second": 0.005
|
| 1300 |
+
}
|
| 1301 |
+
],
|
| 1302 |
+
"logging_steps": 1.0,
|
| 1303 |
+
"max_steps": 183,
|
| 1304 |
+
"num_input_tokens_seen": 0,
|
| 1305 |
+
"num_train_epochs": 3,
|
| 1306 |
+
"save_steps": 500,
|
| 1307 |
+
"stateful_callbacks": {
|
| 1308 |
+
"TrainerControl": {
|
| 1309 |
+
"args": {
|
| 1310 |
+
"should_epoch_stop": false,
|
| 1311 |
+
"should_evaluate": false,
|
| 1312 |
+
"should_log": false,
|
| 1313 |
+
"should_save": true,
|
| 1314 |
+
"should_training_stop": true
|
| 1315 |
+
},
|
| 1316 |
+
"attributes": {}
|
| 1317 |
+
}
|
| 1318 |
+
},
|
| 1319 |
+
"total_flos": 4.709134058959929e+18,
|
| 1320 |
+
"train_batch_size": 1,
|
| 1321 |
+
"trial_name": null,
|
| 1322 |
+
"trial_params": null
|
| 1323 |
+
}
|
training_loss.png
ADDED
|