End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +1302 -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: glaive_reasoning_300k
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# glaive_reasoning_300k
|
| 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: glaive_reasoning_300k
|
|
|
|
| 16 |
|
| 17 |
# glaive_reasoning_300k
|
| 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/glaive_reasoning_300k dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9690721649484537,
|
| 3 |
+
"total_flos": 4.323339643798946e+18,
|
| 4 |
+
"train_loss": 0.6483473062515259,
|
| 5 |
+
"train_runtime": 10930.2571,
|
| 6 |
+
"train_samples_per_second": 8.519,
|
| 7 |
+
"train_steps_per_second": 0.016
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9690721649484537,
|
| 3 |
+
"total_flos": 4.323339643798946e+18,
|
| 4 |
+
"train_loss": 0.6483473062515259,
|
| 5 |
+
"train_runtime": 10930.2571,
|
| 6 |
+
"train_samples_per_second": 8.519,
|
| 7 |
+
"train_steps_per_second": 0.016
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1302 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9690721649484537,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 180,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.016494845360824743,
|
| 13 |
+
"grad_norm": 6.510887010044826,
|
| 14 |
+
"learning_rate": 4.444444444444444e-06,
|
| 15 |
+
"loss": 1.1235,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.032989690721649485,
|
| 20 |
+
"grad_norm": 6.5268184982716475,
|
| 21 |
+
"learning_rate": 8.888888888888888e-06,
|
| 22 |
+
"loss": 1.1258,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.049484536082474224,
|
| 27 |
+
"grad_norm": 4.24927908625525,
|
| 28 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 29 |
+
"loss": 1.0563,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.06597938144329897,
|
| 34 |
+
"grad_norm": 2.816200291689023,
|
| 35 |
+
"learning_rate": 1.7777777777777777e-05,
|
| 36 |
+
"loss": 1.009,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.08247422680412371,
|
| 41 |
+
"grad_norm": 6.493905326694169,
|
| 42 |
+
"learning_rate": 2.2222222222222227e-05,
|
| 43 |
+
"loss": 1.013,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.09896907216494845,
|
| 48 |
+
"grad_norm": 7.726008627313003,
|
| 49 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 50 |
+
"loss": 1.0706,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.1154639175257732,
|
| 55 |
+
"grad_norm": 4.516493110783658,
|
| 56 |
+
"learning_rate": 3.111111111111112e-05,
|
| 57 |
+
"loss": 0.9695,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.13195876288659794,
|
| 62 |
+
"grad_norm": 4.640178402684917,
|
| 63 |
+
"learning_rate": 3.555555555555555e-05,
|
| 64 |
+
"loss": 0.9444,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.14845360824742268,
|
| 69 |
+
"grad_norm": 2.268866723993877,
|
| 70 |
+
"learning_rate": 4e-05,
|
| 71 |
+
"loss": 0.905,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.16494845360824742,
|
| 76 |
+
"grad_norm": 3.54868006526656,
|
| 77 |
+
"learning_rate": 4.444444444444445e-05,
|
| 78 |
+
"loss": 0.8855,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.18144329896907216,
|
| 83 |
+
"grad_norm": 2.702694507430541,
|
| 84 |
+
"learning_rate": 4.88888888888889e-05,
|
| 85 |
+
"loss": 0.8814,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.1979381443298969,
|
| 90 |
+
"grad_norm": 2.4163522339799424,
|
| 91 |
+
"learning_rate": 5.333333333333333e-05,
|
| 92 |
+
"loss": 0.8649,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.21443298969072164,
|
| 97 |
+
"grad_norm": 1.7906871535399842,
|
| 98 |
+
"learning_rate": 5.777777777777778e-05,
|
| 99 |
+
"loss": 0.8351,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.2309278350515464,
|
| 104 |
+
"grad_norm": 2.073156178645725,
|
| 105 |
+
"learning_rate": 6.222222222222223e-05,
|
| 106 |
+
"loss": 0.8352,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.24742268041237114,
|
| 111 |
+
"grad_norm": 4.016806278073859,
|
| 112 |
+
"learning_rate": 6.666666666666667e-05,
|
| 113 |
+
"loss": 0.8279,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.2639175257731959,
|
| 118 |
+
"grad_norm": 1.5493063583627422,
|
| 119 |
+
"learning_rate": 7.11111111111111e-05,
|
| 120 |
+
"loss": 0.8198,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.2804123711340206,
|
| 125 |
+
"grad_norm": 3.1170782607697487,
|
| 126 |
+
"learning_rate": 7.555555555555556e-05,
|
| 127 |
+
"loss": 0.8298,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.29690721649484536,
|
| 132 |
+
"grad_norm": 1.754906513968234,
|
| 133 |
+
"learning_rate": 8e-05,
|
| 134 |
+
"loss": 0.813,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.3134020618556701,
|
| 139 |
+
"grad_norm": 2.9900814711935846,
|
| 140 |
+
"learning_rate": 7.999247881794007e-05,
|
| 141 |
+
"loss": 0.8145,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.32989690721649484,
|
| 146 |
+
"grad_norm": 2.4128887550257256,
|
| 147 |
+
"learning_rate": 7.996991810016922e-05,
|
| 148 |
+
"loss": 0.8023,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.3463917525773196,
|
| 153 |
+
"grad_norm": 1.573430056889768,
|
| 154 |
+
"learning_rate": 7.993232633085074e-05,
|
| 155 |
+
"loss": 0.7798,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.3628865979381443,
|
| 160 |
+
"grad_norm": 1.7272127576229301,
|
| 161 |
+
"learning_rate": 7.987971764671168e-05,
|
| 162 |
+
"loss": 0.7822,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.37938144329896906,
|
| 167 |
+
"grad_norm": 2.4051614980913256,
|
| 168 |
+
"learning_rate": 7.981211183172663e-05,
|
| 169 |
+
"loss": 0.7858,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.3958762886597938,
|
| 174 |
+
"grad_norm": 1.2504967615335536,
|
| 175 |
+
"learning_rate": 7.972953430967773e-05,
|
| 176 |
+
"loss": 0.773,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.41237113402061853,
|
| 181 |
+
"grad_norm": 1.6023332952213127,
|
| 182 |
+
"learning_rate": 7.963201613459381e-05,
|
| 183 |
+
"loss": 0.7793,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.4288659793814433,
|
| 188 |
+
"grad_norm": 1.6124516785601999,
|
| 189 |
+
"learning_rate": 7.951959397907237e-05,
|
| 190 |
+
"loss": 0.7753,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.44536082474226807,
|
| 195 |
+
"grad_norm": 1.0172041366242313,
|
| 196 |
+
"learning_rate": 7.939231012048833e-05,
|
| 197 |
+
"loss": 0.7498,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.4618556701030928,
|
| 202 |
+
"grad_norm": 2.063022239192394,
|
| 203 |
+
"learning_rate": 7.925021242509539e-05,
|
| 204 |
+
"loss": 0.7668,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.47835051546391755,
|
| 209 |
+
"grad_norm": 1.203906865110656,
|
| 210 |
+
"learning_rate": 7.909335433002543e-05,
|
| 211 |
+
"loss": 0.7522,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.4948453608247423,
|
| 216 |
+
"grad_norm": 1.8963235208653197,
|
| 217 |
+
"learning_rate": 7.892179482319297e-05,
|
| 218 |
+
"loss": 0.7562,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.511340206185567,
|
| 223 |
+
"grad_norm": 1.4857136251084346,
|
| 224 |
+
"learning_rate": 7.873559842111225e-05,
|
| 225 |
+
"loss": 0.758,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.5278350515463918,
|
| 230 |
+
"grad_norm": 1.324299893798851,
|
| 231 |
+
"learning_rate": 7.853483514463521e-05,
|
| 232 |
+
"loss": 0.7392,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.5443298969072164,
|
| 237 |
+
"grad_norm": 1.1480502056057977,
|
| 238 |
+
"learning_rate": 7.831958049261956e-05,
|
| 239 |
+
"loss": 0.7363,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.5608247422680412,
|
| 244 |
+
"grad_norm": 1.0730578557805914,
|
| 245 |
+
"learning_rate": 7.808991541353662e-05,
|
| 246 |
+
"loss": 0.7244,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.5773195876288659,
|
| 251 |
+
"grad_norm": 1.2205423026753601,
|
| 252 |
+
"learning_rate": 7.784592627503004e-05,
|
| 253 |
+
"loss": 0.7307,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.5938144329896907,
|
| 258 |
+
"grad_norm": 1.1023928563893555,
|
| 259 |
+
"learning_rate": 7.758770483143634e-05,
|
| 260 |
+
"loss": 0.7178,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.6103092783505155,
|
| 265 |
+
"grad_norm": 1.2767578646872828,
|
| 266 |
+
"learning_rate": 7.731534818928004e-05,
|
| 267 |
+
"loss": 0.7173,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.6268041237113402,
|
| 272 |
+
"grad_norm": 1.682499530220273,
|
| 273 |
+
"learning_rate": 7.702895877075563e-05,
|
| 274 |
+
"loss": 0.733,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.643298969072165,
|
| 279 |
+
"grad_norm": 1.2445811359694992,
|
| 280 |
+
"learning_rate": 7.672864427521097e-05,
|
| 281 |
+
"loss": 0.708,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.6597938144329897,
|
| 286 |
+
"grad_norm": 0.923390898153776,
|
| 287 |
+
"learning_rate": 7.641451763864587e-05,
|
| 288 |
+
"loss": 0.7117,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.6762886597938145,
|
| 293 |
+
"grad_norm": 1.6810293301142893,
|
| 294 |
+
"learning_rate": 7.608669699124153e-05,
|
| 295 |
+
"loss": 0.7164,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.6927835051546392,
|
| 300 |
+
"grad_norm": 0.8665817723805724,
|
| 301 |
+
"learning_rate": 7.57453056129365e-05,
|
| 302 |
+
"loss": 0.7015,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.709278350515464,
|
| 307 |
+
"grad_norm": 1.38899095974282,
|
| 308 |
+
"learning_rate": 7.539047188706631e-05,
|
| 309 |
+
"loss": 0.7138,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.7257731958762886,
|
| 314 |
+
"grad_norm": 0.8370635723618396,
|
| 315 |
+
"learning_rate": 7.502232925208365e-05,
|
| 316 |
+
"loss": 0.6963,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.7422680412371134,
|
| 321 |
+
"grad_norm": 1.2109419876620096,
|
| 322 |
+
"learning_rate": 7.464101615137756e-05,
|
| 323 |
+
"loss": 0.6998,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.7587628865979381,
|
| 328 |
+
"grad_norm": 0.7345771754907713,
|
| 329 |
+
"learning_rate": 7.424667598121067e-05,
|
| 330 |
+
"loss": 0.6895,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.7752577319587629,
|
| 335 |
+
"grad_norm": 0.866583046558764,
|
| 336 |
+
"learning_rate": 7.383945703679365e-05,
|
| 337 |
+
"loss": 0.6853,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.7917525773195876,
|
| 342 |
+
"grad_norm": 0.954971416511012,
|
| 343 |
+
"learning_rate": 7.341951245651747e-05,
|
| 344 |
+
"loss": 0.6924,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.8082474226804124,
|
| 349 |
+
"grad_norm": 0.9698764503436211,
|
| 350 |
+
"learning_rate": 7.298700016436427e-05,
|
| 351 |
+
"loss": 0.692,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.8247422680412371,
|
| 356 |
+
"grad_norm": 1.144548805435363,
|
| 357 |
+
"learning_rate": 7.254208281051871e-05,
|
| 358 |
+
"loss": 0.6928,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.8412371134020619,
|
| 363 |
+
"grad_norm": 0.8399338717507018,
|
| 364 |
+
"learning_rate": 7.208492771020176e-05,
|
| 365 |
+
"loss": 0.685,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.8577319587628865,
|
| 370 |
+
"grad_norm": 0.8519348258795473,
|
| 371 |
+
"learning_rate": 7.161570678075038e-05,
|
| 372 |
+
"loss": 0.679,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.8742268041237113,
|
| 377 |
+
"grad_norm": 0.8682024621779066,
|
| 378 |
+
"learning_rate": 7.113459647696641e-05,
|
| 379 |
+
"loss": 0.6855,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.8907216494845361,
|
| 384 |
+
"grad_norm": 0.9687444841568461,
|
| 385 |
+
"learning_rate": 7.064177772475912e-05,
|
| 386 |
+
"loss": 0.679,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.9072164948453608,
|
| 391 |
+
"grad_norm": 1.3660815254644363,
|
| 392 |
+
"learning_rate": 7.013743585310642e-05,
|
| 393 |
+
"loss": 0.675,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.9237113402061856,
|
| 398 |
+
"grad_norm": 0.546131036326861,
|
| 399 |
+
"learning_rate": 6.96217605243602e-05,
|
| 400 |
+
"loss": 0.6711,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.9402061855670103,
|
| 405 |
+
"grad_norm": 1.1202176159006922,
|
| 406 |
+
"learning_rate": 6.909494566292195e-05,
|
| 407 |
+
"loss": 0.6688,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.9567010309278351,
|
| 412 |
+
"grad_norm": 1.2767701093146733,
|
| 413 |
+
"learning_rate": 6.855718938231597e-05,
|
| 414 |
+
"loss": 0.6707,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.9731958762886598,
|
| 419 |
+
"grad_norm": 0.5478022664863074,
|
| 420 |
+
"learning_rate": 6.800869391068674e-05,
|
| 421 |
+
"loss": 0.661,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.9896907216494846,
|
| 426 |
+
"grad_norm": 1.0121489489469924,
|
| 427 |
+
"learning_rate": 6.744966551474936e-05,
|
| 428 |
+
"loss": 0.6668,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.0061855670103093,
|
| 433 |
+
"grad_norm": 1.4780025517613948,
|
| 434 |
+
"learning_rate": 6.688031442222091e-05,
|
| 435 |
+
"loss": 0.9023,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 1.022680412371134,
|
| 440 |
+
"grad_norm": 0.8312783075179766,
|
| 441 |
+
"learning_rate": 6.630085474276256e-05,
|
| 442 |
+
"loss": 0.6324,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.0391752577319588,
|
| 447 |
+
"grad_norm": 0.8089531767122732,
|
| 448 |
+
"learning_rate": 6.571150438746157e-05,
|
| 449 |
+
"loss": 0.6264,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.0556701030927835,
|
| 454 |
+
"grad_norm": 0.5525157311375302,
|
| 455 |
+
"learning_rate": 6.511248498688396e-05,
|
| 456 |
+
"loss": 0.6245,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 1.0721649484536082,
|
| 461 |
+
"grad_norm": 0.6641634808727606,
|
| 462 |
+
"learning_rate": 6.450402180772811e-05,
|
| 463 |
+
"loss": 0.6239,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 1.088659793814433,
|
| 468 |
+
"grad_norm": 0.6945453989138148,
|
| 469 |
+
"learning_rate": 6.388634366811146e-05,
|
| 470 |
+
"loss": 0.6218,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.1051546391752578,
|
| 475 |
+
"grad_norm": 0.467762743943545,
|
| 476 |
+
"learning_rate": 6.325968285152107e-05,
|
| 477 |
+
"loss": 0.6191,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 1.1216494845360825,
|
| 482 |
+
"grad_norm": 0.5960377140822906,
|
| 483 |
+
"learning_rate": 6.262427501946155e-05,
|
| 484 |
+
"loss": 0.6196,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 1.1381443298969072,
|
| 489 |
+
"grad_norm": 0.6012136643477979,
|
| 490 |
+
"learning_rate": 6.198035912283225e-05,
|
| 491 |
+
"loss": 0.6156,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 1.1546391752577319,
|
| 496 |
+
"grad_norm": 0.3830555698329603,
|
| 497 |
+
"learning_rate": 6.132817731206766e-05,
|
| 498 |
+
"loss": 0.6164,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 1.1711340206185568,
|
| 503 |
+
"grad_norm": 0.5255708619248807,
|
| 504 |
+
"learning_rate": 6.0667974846074524e-05,
|
| 505 |
+
"loss": 0.6116,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.1876288659793814,
|
| 510 |
+
"grad_norm": 0.34124652573381775,
|
| 511 |
+
"learning_rate": 6.000000000000001e-05,
|
| 512 |
+
"loss": 0.6112,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.2041237113402061,
|
| 517 |
+
"grad_norm": 0.36719307010241353,
|
| 518 |
+
"learning_rate": 5.9324503971865545e-05,
|
| 519 |
+
"loss": 0.6087,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 1.220618556701031,
|
| 524 |
+
"grad_norm": 0.3744904944376666,
|
| 525 |
+
"learning_rate": 5.8641740788101566e-05,
|
| 526 |
+
"loss": 0.6178,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.2371134020618557,
|
| 531 |
+
"grad_norm": 0.40861995730924344,
|
| 532 |
+
"learning_rate": 5.79519672080185e-05,
|
| 533 |
+
"loss": 0.6078,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.2536082474226804,
|
| 538 |
+
"grad_norm": 0.4191817335171689,
|
| 539 |
+
"learning_rate": 5.7255442627250146e-05,
|
| 540 |
+
"loss": 0.6093,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.270103092783505,
|
| 545 |
+
"grad_norm": 0.4279620084135946,
|
| 546 |
+
"learning_rate": 5.6552428980205575e-05,
|
| 547 |
+
"loss": 0.6036,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.2865979381443298,
|
| 552 |
+
"grad_norm": 0.43387459801090117,
|
| 553 |
+
"learning_rate": 5.584319064156628e-05,
|
| 554 |
+
"loss": 0.6122,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.3030927835051547,
|
| 559 |
+
"grad_norm": 0.36347036101765934,
|
| 560 |
+
"learning_rate": 5.5127994326865706e-05,
|
| 561 |
+
"loss": 0.6095,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.3195876288659794,
|
| 566 |
+
"grad_norm": 0.4126765641672846,
|
| 567 |
+
"learning_rate": 5.440710899218842e-05,
|
| 568 |
+
"loss": 0.6066,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.3360824742268043,
|
| 573 |
+
"grad_norm": 0.4342669224320681,
|
| 574 |
+
"learning_rate": 5.368080573302676e-05,
|
| 575 |
+
"loss": 0.6049,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.352577319587629,
|
| 580 |
+
"grad_norm": 0.5247434320363652,
|
| 581 |
+
"learning_rate": 5.294935768233285e-05,
|
| 582 |
+
"loss": 0.6096,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 1.3690721649484536,
|
| 587 |
+
"grad_norm": 0.5346000474514714,
|
| 588 |
+
"learning_rate": 5.2213039907804535e-05,
|
| 589 |
+
"loss": 0.6103,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.3855670103092783,
|
| 594 |
+
"grad_norm": 0.4704610145658556,
|
| 595 |
+
"learning_rate": 5.1472129308443616e-05,
|
| 596 |
+
"loss": 0.6031,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.402061855670103,
|
| 601 |
+
"grad_norm": 0.39776693880011527,
|
| 602 |
+
"learning_rate": 5.07269045104255e-05,
|
| 603 |
+
"loss": 0.6037,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.418556701030928,
|
| 608 |
+
"grad_norm": 0.4551461417385109,
|
| 609 |
+
"learning_rate": 4.9977645762319255e-05,
|
| 610 |
+
"loss": 0.5964,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.4350515463917526,
|
| 615 |
+
"grad_norm": 0.49160111934260997,
|
| 616 |
+
"learning_rate": 4.922463482969761e-05,
|
| 617 |
+
"loss": 0.6041,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.4515463917525773,
|
| 622 |
+
"grad_norm": 0.4569400444284779,
|
| 623 |
+
"learning_rate": 4.846815488917644e-05,
|
| 624 |
+
"loss": 0.6038,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.4680412371134022,
|
| 629 |
+
"grad_norm": 0.37114067381878696,
|
| 630 |
+
"learning_rate": 4.7708490421923596e-05,
|
| 631 |
+
"loss": 0.6002,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.4845360824742269,
|
| 636 |
+
"grad_norm": 0.28286469224476896,
|
| 637 |
+
"learning_rate": 4.694592710667723e-05,
|
| 638 |
+
"loss": 0.5999,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.5010309278350515,
|
| 643 |
+
"grad_norm": 0.2544980684276211,
|
| 644 |
+
"learning_rate": 4.618075171231363e-05,
|
| 645 |
+
"loss": 0.5975,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.5175257731958762,
|
| 650 |
+
"grad_norm": 0.3294943971867536,
|
| 651 |
+
"learning_rate": 4.541325199000525e-05,
|
| 652 |
+
"loss": 0.6029,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.534020618556701,
|
| 657 |
+
"grad_norm": 0.41072515728050296,
|
| 658 |
+
"learning_rate": 4.464371656500921e-05,
|
| 659 |
+
"loss": 0.5921,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.5505154639175258,
|
| 664 |
+
"grad_norm": 0.35351679633113386,
|
| 665 |
+
"learning_rate": 4.387243482812717e-05,
|
| 666 |
+
"loss": 0.5949,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.5670103092783505,
|
| 671 |
+
"grad_norm": 0.26711294822182974,
|
| 672 |
+
"learning_rate": 4.309969682687724e-05,
|
| 673 |
+
"loss": 0.5994,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.5835051546391754,
|
| 678 |
+
"grad_norm": 0.32816659581517543,
|
| 679 |
+
"learning_rate": 4.2325793156419035e-05,
|
| 680 |
+
"loss": 0.5932,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.6,
|
| 685 |
+
"grad_norm": 0.3504348660738673,
|
| 686 |
+
"learning_rate": 4.155101485027268e-05,
|
| 687 |
+
"loss": 0.5987,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.6164948453608248,
|
| 692 |
+
"grad_norm": 0.31517917046437344,
|
| 693 |
+
"learning_rate": 4.077565327087298e-05,
|
| 694 |
+
"loss": 0.5971,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 1.6329896907216495,
|
| 699 |
+
"grad_norm": 0.2535047071826055,
|
| 700 |
+
"learning_rate": 4e-05,
|
| 701 |
+
"loss": 0.5948,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.6494845360824741,
|
| 706 |
+
"grad_norm": 0.2375012914581539,
|
| 707 |
+
"learning_rate": 3.9224346729127034e-05,
|
| 708 |
+
"loss": 0.5949,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.6659793814432988,
|
| 713 |
+
"grad_norm": 0.2623717476380207,
|
| 714 |
+
"learning_rate": 3.844898514972733e-05,
|
| 715 |
+
"loss": 0.5947,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 1.6824742268041237,
|
| 720 |
+
"grad_norm": 0.2512637608509031,
|
| 721 |
+
"learning_rate": 3.767420684358097e-05,
|
| 722 |
+
"loss": 0.5988,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.6989690721649484,
|
| 727 |
+
"grad_norm": 0.18029355738972075,
|
| 728 |
+
"learning_rate": 3.690030317312277e-05,
|
| 729 |
+
"loss": 0.5927,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.7154639175257733,
|
| 734 |
+
"grad_norm": 0.20901651442289526,
|
| 735 |
+
"learning_rate": 3.612756517187284e-05,
|
| 736 |
+
"loss": 0.5963,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.731958762886598,
|
| 741 |
+
"grad_norm": 0.23100136098283308,
|
| 742 |
+
"learning_rate": 3.535628343499079e-05,
|
| 743 |
+
"loss": 0.5957,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.7484536082474227,
|
| 748 |
+
"grad_norm": 0.18935083808209807,
|
| 749 |
+
"learning_rate": 3.458674800999477e-05,
|
| 750 |
+
"loss": 0.5926,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.7649484536082474,
|
| 755 |
+
"grad_norm": 0.16393645527535064,
|
| 756 |
+
"learning_rate": 3.3819248287686386e-05,
|
| 757 |
+
"loss": 0.5949,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.781443298969072,
|
| 762 |
+
"grad_norm": 0.190745251922808,
|
| 763 |
+
"learning_rate": 3.305407289332279e-05,
|
| 764 |
+
"loss": 0.5891,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.797938144329897,
|
| 769 |
+
"grad_norm": 0.16188706039772582,
|
| 770 |
+
"learning_rate": 3.229150957807641e-05,
|
| 771 |
+
"loss": 0.5892,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 1.8144329896907216,
|
| 776 |
+
"grad_norm": 0.18778980243793414,
|
| 777 |
+
"learning_rate": 3.153184511082359e-05,
|
| 778 |
+
"loss": 0.592,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.8309278350515465,
|
| 783 |
+
"grad_norm": 0.16922028732307035,
|
| 784 |
+
"learning_rate": 3.07753651703024e-05,
|
| 785 |
+
"loss": 0.5926,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.8474226804123712,
|
| 790 |
+
"grad_norm": 0.2075008066134838,
|
| 791 |
+
"learning_rate": 3.0022354237680752e-05,
|
| 792 |
+
"loss": 0.5915,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 1.863917525773196,
|
| 797 |
+
"grad_norm": 0.15945271606226596,
|
| 798 |
+
"learning_rate": 2.9273095489574502e-05,
|
| 799 |
+
"loss": 0.5917,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 1.8804123711340206,
|
| 804 |
+
"grad_norm": 0.20924714994332358,
|
| 805 |
+
"learning_rate": 2.8527870691556404e-05,
|
| 806 |
+
"loss": 0.589,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.8969072164948453,
|
| 811 |
+
"grad_norm": 0.15413768093132926,
|
| 812 |
+
"learning_rate": 2.778696009219548e-05,
|
| 813 |
+
"loss": 0.5895,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 1.91340206185567,
|
| 818 |
+
"grad_norm": 0.17340241637334963,
|
| 819 |
+
"learning_rate": 2.7050642317667164e-05,
|
| 820 |
+
"loss": 0.5908,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 1.9298969072164949,
|
| 825 |
+
"grad_norm": 0.13700935671950965,
|
| 826 |
+
"learning_rate": 2.6319194266973256e-05,
|
| 827 |
+
"loss": 0.5881,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 1.9463917525773196,
|
| 832 |
+
"grad_norm": 0.16121450857357886,
|
| 833 |
+
"learning_rate": 2.5592891007811594e-05,
|
| 834 |
+
"loss": 0.5856,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 1.9628865979381445,
|
| 839 |
+
"grad_norm": 0.13760640745884387,
|
| 840 |
+
"learning_rate": 2.4872005673134307e-05,
|
| 841 |
+
"loss": 0.5888,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 1.9793814432989691,
|
| 846 |
+
"grad_norm": 0.136153453631026,
|
| 847 |
+
"learning_rate": 2.4156809358433728e-05,
|
| 848 |
+
"loss": 0.5866,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.9958762886597938,
|
| 853 |
+
"grad_norm": 0.1740518146800063,
|
| 854 |
+
"learning_rate": 2.3447571019794438e-05,
|
| 855 |
+
"loss": 0.7221,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 2.0123711340206185,
|
| 860 |
+
"grad_norm": 0.1913924294175378,
|
| 861 |
+
"learning_rate": 2.274455737274987e-05,
|
| 862 |
+
"loss": 0.649,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 2.028865979381443,
|
| 867 |
+
"grad_norm": 0.16283149279005063,
|
| 868 |
+
"learning_rate": 2.2048032791981515e-05,
|
| 869 |
+
"loss": 0.5525,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 2.045360824742268,
|
| 874 |
+
"grad_norm": 0.14595606592277305,
|
| 875 |
+
"learning_rate": 2.135825921189846e-05,
|
| 876 |
+
"loss": 0.5518,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 2.0618556701030926,
|
| 881 |
+
"grad_norm": 0.17091723837273506,
|
| 882 |
+
"learning_rate": 2.067549602813446e-05,
|
| 883 |
+
"loss": 0.5537,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 2.0783505154639177,
|
| 888 |
+
"grad_norm": 0.1472669016069401,
|
| 889 |
+
"learning_rate": 2.0000000000000012e-05,
|
| 890 |
+
"loss": 0.5468,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 2.0948453608247424,
|
| 895 |
+
"grad_norm": 0.1383718741274944,
|
| 896 |
+
"learning_rate": 1.9332025153925486e-05,
|
| 897 |
+
"loss": 0.554,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 2.111340206185567,
|
| 902 |
+
"grad_norm": 0.1449682321168763,
|
| 903 |
+
"learning_rate": 1.867182268793236e-05,
|
| 904 |
+
"loss": 0.5481,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 2.1278350515463917,
|
| 909 |
+
"grad_norm": 0.14268562258623765,
|
| 910 |
+
"learning_rate": 1.8019640877167763e-05,
|
| 911 |
+
"loss": 0.551,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 2.1443298969072164,
|
| 916 |
+
"grad_norm": 0.14398336699894976,
|
| 917 |
+
"learning_rate": 1.7375724980538465e-05,
|
| 918 |
+
"loss": 0.5485,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 2.160824742268041,
|
| 923 |
+
"grad_norm": 0.13632304217235544,
|
| 924 |
+
"learning_rate": 1.6740317148478932e-05,
|
| 925 |
+
"loss": 0.5513,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 2.177319587628866,
|
| 930 |
+
"grad_norm": 0.13802596151410262,
|
| 931 |
+
"learning_rate": 1.6113656331888563e-05,
|
| 932 |
+
"loss": 0.546,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 2.193814432989691,
|
| 937 |
+
"grad_norm": 0.1367651968028799,
|
| 938 |
+
"learning_rate": 1.5495978192271887e-05,
|
| 939 |
+
"loss": 0.5507,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 2.2103092783505156,
|
| 944 |
+
"grad_norm": 0.14319896957050066,
|
| 945 |
+
"learning_rate": 1.4887515013116067e-05,
|
| 946 |
+
"loss": 0.5474,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 2.2268041237113403,
|
| 951 |
+
"grad_norm": 0.13563813749833395,
|
| 952 |
+
"learning_rate": 1.4288495612538427e-05,
|
| 953 |
+
"loss": 0.5466,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 2.243298969072165,
|
| 958 |
+
"grad_norm": 0.13299637580848364,
|
| 959 |
+
"learning_rate": 1.369914525723746e-05,
|
| 960 |
+
"loss": 0.5546,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 2.2597938144329897,
|
| 965 |
+
"grad_norm": 0.12840209113989406,
|
| 966 |
+
"learning_rate": 1.3119685577779105e-05,
|
| 967 |
+
"loss": 0.5443,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 2.2762886597938143,
|
| 972 |
+
"grad_norm": 0.12810536536017894,
|
| 973 |
+
"learning_rate": 1.2550334485250661e-05,
|
| 974 |
+
"loss": 0.5499,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 2.292783505154639,
|
| 979 |
+
"grad_norm": 0.11355419047013178,
|
| 980 |
+
"learning_rate": 1.1991306089313261e-05,
|
| 981 |
+
"loss": 0.5479,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 2.3092783505154637,
|
| 986 |
+
"grad_norm": 0.1295630499886211,
|
| 987 |
+
"learning_rate": 1.1442810617684046e-05,
|
| 988 |
+
"loss": 0.5489,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 2.325773195876289,
|
| 993 |
+
"grad_norm": 0.1221697199562323,
|
| 994 |
+
"learning_rate": 1.0905054337078051e-05,
|
| 995 |
+
"loss": 0.5499,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 2.3422680412371135,
|
| 1000 |
+
"grad_norm": 0.10736730884852848,
|
| 1001 |
+
"learning_rate": 1.0378239475639823e-05,
|
| 1002 |
+
"loss": 0.5469,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 2.358762886597938,
|
| 1007 |
+
"grad_norm": 0.11911805451017765,
|
| 1008 |
+
"learning_rate": 9.862564146893571e-06,
|
| 1009 |
+
"loss": 0.5533,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 2.375257731958763,
|
| 1014 |
+
"grad_norm": 0.10719682452107784,
|
| 1015 |
+
"learning_rate": 9.358222275240884e-06,
|
| 1016 |
+
"loss": 0.5492,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 2.3917525773195876,
|
| 1021 |
+
"grad_norm": 0.1062158910238879,
|
| 1022 |
+
"learning_rate": 8.8654035230336e-06,
|
| 1023 |
+
"loss": 0.549,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 2.4082474226804123,
|
| 1028 |
+
"grad_norm": 0.10542623562823075,
|
| 1029 |
+
"learning_rate": 8.384293219249633e-06,
|
| 1030 |
+
"loss": 0.5472,
|
| 1031 |
+
"step": 146
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 2.424742268041237,
|
| 1035 |
+
"grad_norm": 0.10737625408939123,
|
| 1036 |
+
"learning_rate": 7.915072289798247e-06,
|
| 1037 |
+
"loss": 0.5439,
|
| 1038 |
+
"step": 147
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 2.441237113402062,
|
| 1042 |
+
"grad_norm": 0.113365548855691,
|
| 1043 |
+
"learning_rate": 7.457917189481301e-06,
|
| 1044 |
+
"loss": 0.5465,
|
| 1045 |
+
"step": 148
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 2.4577319587628867,
|
| 1049 |
+
"grad_norm": 0.09803128955615437,
|
| 1050 |
+
"learning_rate": 7.0129998356357295e-06,
|
| 1051 |
+
"loss": 0.5454,
|
| 1052 |
+
"step": 149
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 2.4742268041237114,
|
| 1056 |
+
"grad_norm": 0.10740236378002757,
|
| 1057 |
+
"learning_rate": 6.58048754348255e-06,
|
| 1058 |
+
"loss": 0.5532,
|
| 1059 |
+
"step": 150
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 2.490721649484536,
|
| 1063 |
+
"grad_norm": 0.10615779921255894,
|
| 1064 |
+
"learning_rate": 6.160542963206357e-06,
|
| 1065 |
+
"loss": 0.5462,
|
| 1066 |
+
"step": 151
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 2.507216494845361,
|
| 1070 |
+
"grad_norm": 0.10941467555755459,
|
| 1071 |
+
"learning_rate": 5.753324018789346e-06,
|
| 1072 |
+
"loss": 0.5467,
|
| 1073 |
+
"step": 152
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 2.5237113402061855,
|
| 1077 |
+
"grad_norm": 0.09824679682670868,
|
| 1078 |
+
"learning_rate": 5.358983848622452e-06,
|
| 1079 |
+
"loss": 0.5464,
|
| 1080 |
+
"step": 153
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 2.54020618556701,
|
| 1084 |
+
"grad_norm": 0.09719860472925167,
|
| 1085 |
+
"learning_rate": 4.97767074791637e-06,
|
| 1086 |
+
"loss": 0.5437,
|
| 1087 |
+
"step": 154
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 2.556701030927835,
|
| 1091 |
+
"grad_norm": 0.09683396959072503,
|
| 1092 |
+
"learning_rate": 4.609528112933688e-06,
|
| 1093 |
+
"loss": 0.5477,
|
| 1094 |
+
"step": 155
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 2.5731958762886595,
|
| 1098 |
+
"grad_norm": 0.09836422675496619,
|
| 1099 |
+
"learning_rate": 4.254694387063514e-06,
|
| 1100 |
+
"loss": 0.5469,
|
| 1101 |
+
"step": 156
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 2.5896907216494847,
|
| 1105 |
+
"grad_norm": 0.0995681618956925,
|
| 1106 |
+
"learning_rate": 3.913303008758491e-06,
|
| 1107 |
+
"loss": 0.5482,
|
| 1108 |
+
"step": 157
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 2.6061855670103093,
|
| 1112 |
+
"grad_norm": 0.09559938988699572,
|
| 1113 |
+
"learning_rate": 3.585482361354138e-06,
|
| 1114 |
+
"loss": 0.5463,
|
| 1115 |
+
"step": 158
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 2.622680412371134,
|
| 1119 |
+
"grad_norm": 0.09220251838124616,
|
| 1120 |
+
"learning_rate": 3.2713557247890447e-06,
|
| 1121 |
+
"loss": 0.549,
|
| 1122 |
+
"step": 159
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 2.6391752577319587,
|
| 1126 |
+
"grad_norm": 0.09182371190140297,
|
| 1127 |
+
"learning_rate": 2.9710412292443868e-06,
|
| 1128 |
+
"loss": 0.5447,
|
| 1129 |
+
"step": 160
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 2.6556701030927834,
|
| 1133 |
+
"grad_norm": 0.09285117312965371,
|
| 1134 |
+
"learning_rate": 2.6846518107199782e-06,
|
| 1135 |
+
"loss": 0.5499,
|
| 1136 |
+
"step": 161
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 2.6721649484536085,
|
| 1140 |
+
"grad_norm": 0.08888916031023086,
|
| 1141 |
+
"learning_rate": 2.4122951685636674e-06,
|
| 1142 |
+
"loss": 0.5476,
|
| 1143 |
+
"step": 162
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 2.688659793814433,
|
| 1147 |
+
"grad_norm": 0.09108536955799308,
|
| 1148 |
+
"learning_rate": 2.1540737249699893e-06,
|
| 1149 |
+
"loss": 0.5468,
|
| 1150 |
+
"step": 163
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 2.705154639175258,
|
| 1154 |
+
"grad_norm": 0.09161991297859239,
|
| 1155 |
+
"learning_rate": 1.9100845864633875e-06,
|
| 1156 |
+
"loss": 0.5447,
|
| 1157 |
+
"step": 164
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 2.7216494845360826,
|
| 1161 |
+
"grad_norm": 0.08993683350116187,
|
| 1162 |
+
"learning_rate": 1.6804195073804442e-06,
|
| 1163 |
+
"loss": 0.547,
|
| 1164 |
+
"step": 165
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 2.7381443298969073,
|
| 1168 |
+
"grad_norm": 0.08768348095869663,
|
| 1169 |
+
"learning_rate": 1.4651648553647869e-06,
|
| 1170 |
+
"loss": 0.548,
|
| 1171 |
+
"step": 166
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 2.754639175257732,
|
| 1175 |
+
"grad_norm": 0.08908278856482474,
|
| 1176 |
+
"learning_rate": 1.2644015788877684e-06,
|
| 1177 |
+
"loss": 0.5424,
|
| 1178 |
+
"step": 167
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 2.7711340206185566,
|
| 1182 |
+
"grad_norm": 0.08772182232275079,
|
| 1183 |
+
"learning_rate": 1.0782051768070477e-06,
|
| 1184 |
+
"loss": 0.5426,
|
| 1185 |
+
"step": 168
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 2.7876288659793813,
|
| 1189 |
+
"grad_norm": 0.09014271400131238,
|
| 1190 |
+
"learning_rate": 9.066456699745774e-07,
|
| 1191 |
+
"loss": 0.5423,
|
| 1192 |
+
"step": 169
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 2.804123711340206,
|
| 1196 |
+
"grad_norm": 0.08846808941818018,
|
| 1197 |
+
"learning_rate": 7.497875749046124e-07,
|
| 1198 |
+
"loss": 0.5491,
|
| 1199 |
+
"step": 170
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 2.8206185567010307,
|
| 1203 |
+
"grad_norm": 0.09003919031348395,
|
| 1204 |
+
"learning_rate": 6.076898795116792e-07,
|
| 1205 |
+
"loss": 0.5466,
|
| 1206 |
+
"step": 171
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 2.837113402061856,
|
| 1210 |
+
"grad_norm": 0.0860255355801196,
|
| 1211 |
+
"learning_rate": 4.804060209276396e-07,
|
| 1212 |
+
"loss": 0.5481,
|
| 1213 |
+
"step": 172
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 2.8536082474226805,
|
| 1217 |
+
"grad_norm": 0.0863084170468407,
|
| 1218 |
+
"learning_rate": 3.679838654061874e-07,
|
| 1219 |
+
"loss": 0.5466,
|
| 1220 |
+
"step": 173
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 2.870103092783505,
|
| 1224 |
+
"grad_norm": 0.08494132877549186,
|
| 1225 |
+
"learning_rate": 2.704656903222791e-07,
|
| 1226 |
+
"loss": 0.5481,
|
| 1227 |
+
"step": 174
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 2.88659793814433,
|
| 1231 |
+
"grad_norm": 0.08696339412244179,
|
| 1232 |
+
"learning_rate": 1.8788816827336686e-07,
|
| 1233 |
+
"loss": 0.5488,
|
| 1234 |
+
"step": 175
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 2.9030927835051545,
|
| 1238 |
+
"grad_norm": 0.08479502393635585,
|
| 1239 |
+
"learning_rate": 1.2028235328831906e-07,
|
| 1240 |
+
"loss": 0.5457,
|
| 1241 |
+
"step": 176
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 2.9195876288659792,
|
| 1245 |
+
"grad_norm": 0.08544111428797167,
|
| 1246 |
+
"learning_rate": 6.767366914927298e-08,
|
| 1247 |
+
"loss": 0.5482,
|
| 1248 |
+
"step": 177
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 2.9360824742268044,
|
| 1252 |
+
"grad_norm": 0.08423838312148532,
|
| 1253 |
+
"learning_rate": 3.0081899830798345e-08,
|
| 1254 |
+
"loss": 0.5468,
|
| 1255 |
+
"step": 178
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 2.952577319587629,
|
| 1259 |
+
"grad_norm": 0.08547740551858984,
|
| 1260 |
+
"learning_rate": 7.521182059946342e-09,
|
| 1261 |
+
"loss": 0.5457,
|
| 1262 |
+
"step": 179
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 2.9690721649484537,
|
| 1266 |
+
"grad_norm": 0.08570261529447104,
|
| 1267 |
+
"learning_rate": 0.0,
|
| 1268 |
+
"loss": 0.5454,
|
| 1269 |
+
"step": 180
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 2.9690721649484537,
|
| 1273 |
+
"step": 180,
|
| 1274 |
+
"total_flos": 4.323339643798946e+18,
|
| 1275 |
+
"train_loss": 0.6483473062515259,
|
| 1276 |
+
"train_runtime": 10930.2571,
|
| 1277 |
+
"train_samples_per_second": 8.519,
|
| 1278 |
+
"train_steps_per_second": 0.016
|
| 1279 |
+
}
|
| 1280 |
+
],
|
| 1281 |
+
"logging_steps": 1.0,
|
| 1282 |
+
"max_steps": 180,
|
| 1283 |
+
"num_input_tokens_seen": 0,
|
| 1284 |
+
"num_train_epochs": 3,
|
| 1285 |
+
"save_steps": 500,
|
| 1286 |
+
"stateful_callbacks": {
|
| 1287 |
+
"TrainerControl": {
|
| 1288 |
+
"args": {
|
| 1289 |
+
"should_epoch_stop": false,
|
| 1290 |
+
"should_evaluate": false,
|
| 1291 |
+
"should_log": false,
|
| 1292 |
+
"should_save": true,
|
| 1293 |
+
"should_training_stop": true
|
| 1294 |
+
},
|
| 1295 |
+
"attributes": {}
|
| 1296 |
+
}
|
| 1297 |
+
},
|
| 1298 |
+
"total_flos": 4.323339643798946e+18,
|
| 1299 |
+
"train_batch_size": 1,
|
| 1300 |
+
"trial_name": null,
|
| 1301 |
+
"trial_params": null
|
| 1302 |
+
}
|
training_loss.png
ADDED
|