End of training
Browse files- README.md +2 -1
- all_results.json +12 -0
- eval_results.json +7 -0
- train_results.json +8 -0
- trainer_state.json +1095 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: apache-2.0
|
|
| 4 |
base_model: mistralai/Mistral-7B-v0.3
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: mistral_7b_0-3_oh-dcft-v3.1-gpt-4o-mini
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# mistral_7b_0-3_oh-dcft-v3.1-gpt-4o-mini
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 0.5735
|
| 21 |
|
|
|
|
| 4 |
base_model: mistralai/Mistral-7B-v0.3
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: mistral_7b_0-3_oh-dcft-v3.1-gpt-4o-mini
|
|
|
|
| 16 |
|
| 17 |
# mistral_7b_0-3_oh-dcft-v3.1-gpt-4o-mini
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on the mlfoundations-dev/oh-dcft-v3.1-gpt-4o-mini dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.5735
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 0.5735070705413818,
|
| 4 |
+
"eval_runtime": 50.9717,
|
| 5 |
+
"eval_samples_per_second": 258.928,
|
| 6 |
+
"eval_steps_per_second": 1.02,
|
| 7 |
+
"total_flos": 2462304750796800.0,
|
| 8 |
+
"train_loss": 0.48433749789283387,
|
| 9 |
+
"train_runtime": 9163.976,
|
| 10 |
+
"train_samples_per_second": 82.091,
|
| 11 |
+
"train_steps_per_second": 0.16
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 0.5735070705413818,
|
| 4 |
+
"eval_runtime": 50.9717,
|
| 5 |
+
"eval_samples_per_second": 258.928,
|
| 6 |
+
"eval_steps_per_second": 1.02
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 2462304750796800.0,
|
| 4 |
+
"train_loss": 0.48433749789283387,
|
| 5 |
+
"train_runtime": 9163.976,
|
| 6 |
+
"train_samples_per_second": 82.091,
|
| 7 |
+
"train_steps_per_second": 0.16
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1095 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1470,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02040816326530612,
|
| 13 |
+
"grad_norm": 7.778071589344308,
|
| 14 |
+
"learning_rate": 6.756756756756758e-07,
|
| 15 |
+
"loss": 0.8354,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.04081632653061224,
|
| 20 |
+
"grad_norm": 3.0197649197148544,
|
| 21 |
+
"learning_rate": 1.3513513513513515e-06,
|
| 22 |
+
"loss": 0.736,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.061224489795918366,
|
| 27 |
+
"grad_norm": 1.6185593920539272,
|
| 28 |
+
"learning_rate": 2.0270270270270273e-06,
|
| 29 |
+
"loss": 0.6712,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.08163265306122448,
|
| 34 |
+
"grad_norm": 1.5428582304546115,
|
| 35 |
+
"learning_rate": 2.702702702702703e-06,
|
| 36 |
+
"loss": 0.6315,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.10204081632653061,
|
| 41 |
+
"grad_norm": 1.7211785189281783,
|
| 42 |
+
"learning_rate": 3.3783783783783788e-06,
|
| 43 |
+
"loss": 0.6102,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.12244897959183673,
|
| 48 |
+
"grad_norm": 2.559107572127415,
|
| 49 |
+
"learning_rate": 4.0540540540540545e-06,
|
| 50 |
+
"loss": 0.6067,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.14285714285714285,
|
| 55 |
+
"grad_norm": 2.314900289599986,
|
| 56 |
+
"learning_rate": 4.72972972972973e-06,
|
| 57 |
+
"loss": 0.5976,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.16326530612244897,
|
| 62 |
+
"grad_norm": 1.585557769101424,
|
| 63 |
+
"learning_rate": 4.999794894487084e-06,
|
| 64 |
+
"loss": 0.6048,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.1836734693877551,
|
| 69 |
+
"grad_norm": 1.746887510895138,
|
| 70 |
+
"learning_rate": 4.998541607324267e-06,
|
| 71 |
+
"loss": 0.5888,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.20408163265306123,
|
| 76 |
+
"grad_norm": 3.353300338752779,
|
| 77 |
+
"learning_rate": 4.996149614425655e-06,
|
| 78 |
+
"loss": 0.5946,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.22448979591836735,
|
| 83 |
+
"grad_norm": 2.8435118056608255,
|
| 84 |
+
"learning_rate": 4.992620127143546e-06,
|
| 85 |
+
"loss": 0.5859,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.24489795918367346,
|
| 90 |
+
"grad_norm": 2.100533655111189,
|
| 91 |
+
"learning_rate": 4.987954932879781e-06,
|
| 92 |
+
"loss": 0.5875,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.2653061224489796,
|
| 97 |
+
"grad_norm": 2.3315284939616605,
|
| 98 |
+
"learning_rate": 4.982156394180578e-06,
|
| 99 |
+
"loss": 0.5787,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.2857142857142857,
|
| 104 |
+
"grad_norm": 2.239136455760216,
|
| 105 |
+
"learning_rate": 4.975227447540084e-06,
|
| 106 |
+
"loss": 0.5844,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.30612244897959184,
|
| 111 |
+
"grad_norm": 2.129725342439742,
|
| 112 |
+
"learning_rate": 4.967171601913286e-06,
|
| 113 |
+
"loss": 0.5777,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.32653061224489793,
|
| 118 |
+
"grad_norm": 2.5819786560128186,
|
| 119 |
+
"learning_rate": 4.957992936939001e-06,
|
| 120 |
+
"loss": 0.585,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.3469387755102041,
|
| 125 |
+
"grad_norm": 1.7001590677192884,
|
| 126 |
+
"learning_rate": 4.947696100873868e-06,
|
| 127 |
+
"loss": 0.5773,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.3673469387755102,
|
| 132 |
+
"grad_norm": 1.7263599397345204,
|
| 133 |
+
"learning_rate": 4.936286308238376e-06,
|
| 134 |
+
"loss": 0.5824,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.3877551020408163,
|
| 139 |
+
"grad_norm": 1.8366911838390632,
|
| 140 |
+
"learning_rate": 4.923769337176137e-06,
|
| 141 |
+
"loss": 0.5791,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.40816326530612246,
|
| 146 |
+
"grad_norm": 1.3905029741864174,
|
| 147 |
+
"learning_rate": 4.910151526527711e-06,
|
| 148 |
+
"loss": 0.5767,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.42857142857142855,
|
| 153 |
+
"grad_norm": 1.148322568291514,
|
| 154 |
+
"learning_rate": 4.895439772620496e-06,
|
| 155 |
+
"loss": 0.5728,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.4489795918367347,
|
| 160 |
+
"grad_norm": 1.6127960821049323,
|
| 161 |
+
"learning_rate": 4.879641525776294e-06,
|
| 162 |
+
"loss": 0.5784,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.46938775510204084,
|
| 167 |
+
"grad_norm": 1.291452047677863,
|
| 168 |
+
"learning_rate": 4.8627647865383185e-06,
|
| 169 |
+
"loss": 0.5755,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.4897959183673469,
|
| 174 |
+
"grad_norm": 1.2840139593689956,
|
| 175 |
+
"learning_rate": 4.844818101619563e-06,
|
| 176 |
+
"loss": 0.574,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.5102040816326531,
|
| 181 |
+
"grad_norm": 1.8038609241857482,
|
| 182 |
+
"learning_rate": 4.825810559574577e-06,
|
| 183 |
+
"loss": 0.5709,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.5306122448979592,
|
| 188 |
+
"grad_norm": 1.4347005717657924,
|
| 189 |
+
"learning_rate": 4.805751786196844e-06,
|
| 190 |
+
"loss": 0.5657,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.5510204081632653,
|
| 195 |
+
"grad_norm": 1.193365239502765,
|
| 196 |
+
"learning_rate": 4.784651939644088e-06,
|
| 197 |
+
"loss": 0.5702,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.5714285714285714,
|
| 202 |
+
"grad_norm": 1.7823342346005195,
|
| 203 |
+
"learning_rate": 4.762521705293985e-06,
|
| 204 |
+
"loss": 0.566,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.5918367346938775,
|
| 209 |
+
"grad_norm": 1.2403759513997483,
|
| 210 |
+
"learning_rate": 4.739372290332876e-06,
|
| 211 |
+
"loss": 0.5668,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.6122448979591837,
|
| 216 |
+
"grad_norm": 1.863444933423126,
|
| 217 |
+
"learning_rate": 4.715215418080228e-06,
|
| 218 |
+
"loss": 0.5671,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.6326530612244898,
|
| 223 |
+
"grad_norm": 1.4221353274898374,
|
| 224 |
+
"learning_rate": 4.690063322051714e-06,
|
| 225 |
+
"loss": 0.5718,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.6530612244897959,
|
| 230 |
+
"grad_norm": 1.6811648872628475,
|
| 231 |
+
"learning_rate": 4.6639287397639175e-06,
|
| 232 |
+
"loss": 0.5632,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.673469387755102,
|
| 237 |
+
"grad_norm": 1.4152595096160547,
|
| 238 |
+
"learning_rate": 4.636824906283807e-06,
|
| 239 |
+
"loss": 0.562,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.6938775510204082,
|
| 244 |
+
"grad_norm": 1.4843724359941501,
|
| 245 |
+
"learning_rate": 4.608765547526235e-06,
|
| 246 |
+
"loss": 0.5599,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.7142857142857143,
|
| 251 |
+
"grad_norm": 1.4557344773873018,
|
| 252 |
+
"learning_rate": 4.5797648733028665e-06,
|
| 253 |
+
"loss": 0.5614,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.7346938775510204,
|
| 258 |
+
"grad_norm": 1.2086032121032202,
|
| 259 |
+
"learning_rate": 4.54983757012605e-06,
|
| 260 |
+
"loss": 0.5634,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.7551020408163265,
|
| 265 |
+
"grad_norm": 1.2423711642376856,
|
| 266 |
+
"learning_rate": 4.518998793771276e-06,
|
| 267 |
+
"loss": 0.5615,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.7755102040816326,
|
| 272 |
+
"grad_norm": 1.2875724524685657,
|
| 273 |
+
"learning_rate": 4.487264161601997e-06,
|
| 274 |
+
"loss": 0.5514,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.7959183673469388,
|
| 279 |
+
"grad_norm": 1.1225946056234728,
|
| 280 |
+
"learning_rate": 4.454649744660687e-06,
|
| 281 |
+
"loss": 0.5647,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.8163265306122449,
|
| 286 |
+
"grad_norm": 1.2503911438284534,
|
| 287 |
+
"learning_rate": 4.4211720595301474e-06,
|
| 288 |
+
"loss": 0.5551,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.8367346938775511,
|
| 293 |
+
"grad_norm": 1.2909414765131615,
|
| 294 |
+
"learning_rate": 4.386848059969186e-06,
|
| 295 |
+
"loss": 0.5492,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.8571428571428571,
|
| 300 |
+
"grad_norm": 1.3184301150941293,
|
| 301 |
+
"learning_rate": 4.351695128326899e-06,
|
| 302 |
+
"loss": 0.5449,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.8775510204081632,
|
| 307 |
+
"grad_norm": 1.2586947786363358,
|
| 308 |
+
"learning_rate": 4.315731066739907e-06,
|
| 309 |
+
"loss": 0.5555,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.8979591836734694,
|
| 314 |
+
"grad_norm": 1.4262738599752862,
|
| 315 |
+
"learning_rate": 4.278974088117002e-06,
|
| 316 |
+
"loss": 0.5543,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.9183673469387755,
|
| 321 |
+
"grad_norm": 1.4446508113688332,
|
| 322 |
+
"learning_rate": 4.241442806915776e-06,
|
| 323 |
+
"loss": 0.5493,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.9387755102040817,
|
| 328 |
+
"grad_norm": 1.298816139110553,
|
| 329 |
+
"learning_rate": 4.203156229715885e-06,
|
| 330 |
+
"loss": 0.5562,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.9591836734693877,
|
| 335 |
+
"grad_norm": 1.2637066502227081,
|
| 336 |
+
"learning_rate": 4.164133745593752e-06,
|
| 337 |
+
"loss": 0.5502,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.9795918367346939,
|
| 342 |
+
"grad_norm": 1.0561664250294849,
|
| 343 |
+
"learning_rate": 4.1243951163035515e-06,
|
| 344 |
+
"loss": 0.5524,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.0,
|
| 349 |
+
"grad_norm": 1.068711582818471,
|
| 350 |
+
"learning_rate": 4.083960466269468e-06,
|
| 351 |
+
"loss": 0.5482,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.0,
|
| 356 |
+
"eval_loss": 0.5568229556083679,
|
| 357 |
+
"eval_runtime": 44.6985,
|
| 358 |
+
"eval_samples_per_second": 295.267,
|
| 359 |
+
"eval_steps_per_second": 1.163,
|
| 360 |
+
"step": 490
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.0204081632653061,
|
| 364 |
+
"grad_norm": 1.6967871170326598,
|
| 365 |
+
"learning_rate": 4.042850272394296e-06,
|
| 366 |
+
"loss": 0.4815,
|
| 367 |
+
"step": 500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.0408163265306123,
|
| 371 |
+
"grad_norm": 1.329681106394839,
|
| 372 |
+
"learning_rate": 4.001085353689527e-06,
|
| 373 |
+
"loss": 0.4746,
|
| 374 |
+
"step": 510
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.0612244897959184,
|
| 378 |
+
"grad_norm": 1.1249203575095268,
|
| 379 |
+
"learning_rate": 3.958686860732198e-06,
|
| 380 |
+
"loss": 0.4712,
|
| 381 |
+
"step": 520
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.0816326530612246,
|
| 385 |
+
"grad_norm": 1.7553226916997662,
|
| 386 |
+
"learning_rate": 3.915676264953819e-06,
|
| 387 |
+
"loss": 0.473,
|
| 388 |
+
"step": 530
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.1020408163265305,
|
| 392 |
+
"grad_norm": 1.814402186020549,
|
| 393 |
+
"learning_rate": 3.8720753477668174e-06,
|
| 394 |
+
"loss": 0.4728,
|
| 395 |
+
"step": 540
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.1224489795918366,
|
| 399 |
+
"grad_norm": 1.780073335115998,
|
| 400 |
+
"learning_rate": 3.8279061895340065e-06,
|
| 401 |
+
"loss": 0.4715,
|
| 402 |
+
"step": 550
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.1428571428571428,
|
| 406 |
+
"grad_norm": 1.8264269071746542,
|
| 407 |
+
"learning_rate": 3.783191158386649e-06,
|
| 408 |
+
"loss": 0.4703,
|
| 409 |
+
"step": 560
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.163265306122449,
|
| 413 |
+
"grad_norm": 1.4978817218835796,
|
| 414 |
+
"learning_rate": 3.7379528988968004e-06,
|
| 415 |
+
"loss": 0.4738,
|
| 416 |
+
"step": 570
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.183673469387755,
|
| 420 |
+
"grad_norm": 1.4615376013915895,
|
| 421 |
+
"learning_rate": 3.6922143206096463e-06,
|
| 422 |
+
"loss": 0.4719,
|
| 423 |
+
"step": 580
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.2040816326530612,
|
| 427 |
+
"grad_norm": 1.8203771196800125,
|
| 428 |
+
"learning_rate": 3.645998586441664e-06,
|
| 429 |
+
"loss": 0.4722,
|
| 430 |
+
"step": 590
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.2244897959183674,
|
| 434 |
+
"grad_norm": 1.7300255308447494,
|
| 435 |
+
"learning_rate": 3.5993291009504583e-06,
|
| 436 |
+
"loss": 0.4743,
|
| 437 |
+
"step": 600
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.2448979591836735,
|
| 441 |
+
"grad_norm": 1.5452609367603438,
|
| 442 |
+
"learning_rate": 3.5522294984822414e-06,
|
| 443 |
+
"loss": 0.4742,
|
| 444 |
+
"step": 610
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.2653061224489797,
|
| 448 |
+
"grad_norm": 1.4110906025605625,
|
| 449 |
+
"learning_rate": 3.504723631202927e-06,
|
| 450 |
+
"loss": 0.478,
|
| 451 |
+
"step": 620
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.2857142857142856,
|
| 455 |
+
"grad_norm": 1.2668133255763068,
|
| 456 |
+
"learning_rate": 3.4568355570189293e-06,
|
| 457 |
+
"loss": 0.4758,
|
| 458 |
+
"step": 630
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.306122448979592,
|
| 462 |
+
"grad_norm": 1.1536880529657885,
|
| 463 |
+
"learning_rate": 3.4085895273937616e-06,
|
| 464 |
+
"loss": 0.4725,
|
| 465 |
+
"step": 640
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.3265306122448979,
|
| 469 |
+
"grad_norm": 1.2378783567029548,
|
| 470 |
+
"learning_rate": 3.3600099750666186e-06,
|
| 471 |
+
"loss": 0.4682,
|
| 472 |
+
"step": 650
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.346938775510204,
|
| 476 |
+
"grad_norm": 1.3094029659983764,
|
| 477 |
+
"learning_rate": 3.3111215016791615e-06,
|
| 478 |
+
"loss": 0.48,
|
| 479 |
+
"step": 660
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.3673469387755102,
|
| 483 |
+
"grad_norm": 1.413780733952238,
|
| 484 |
+
"learning_rate": 3.2619488653167524e-06,
|
| 485 |
+
"loss": 0.4776,
|
| 486 |
+
"step": 670
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.3877551020408163,
|
| 490 |
+
"grad_norm": 1.1451278058611685,
|
| 491 |
+
"learning_rate": 3.2125169679704816e-06,
|
| 492 |
+
"loss": 0.4777,
|
| 493 |
+
"step": 680
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.4081632653061225,
|
| 497 |
+
"grad_norm": 1.168070145148228,
|
| 498 |
+
"learning_rate": 3.1628508429263055e-06,
|
| 499 |
+
"loss": 0.4756,
|
| 500 |
+
"step": 690
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.4285714285714286,
|
| 504 |
+
"grad_norm": 1.1109475835139078,
|
| 505 |
+
"learning_rate": 3.112975642087696e-06,
|
| 506 |
+
"loss": 0.4727,
|
| 507 |
+
"step": 700
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.4489795918367347,
|
| 511 |
+
"grad_norm": 1.2678867479201292,
|
| 512 |
+
"learning_rate": 3.0629166232382244e-06,
|
| 513 |
+
"loss": 0.4776,
|
| 514 |
+
"step": 710
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.469387755102041,
|
| 518 |
+
"grad_norm": 1.1561029802658416,
|
| 519 |
+
"learning_rate": 3.012699137250523e-06,
|
| 520 |
+
"loss": 0.4738,
|
| 521 |
+
"step": 720
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.489795918367347,
|
| 525 |
+
"grad_norm": 1.1313128254815696,
|
| 526 |
+
"learning_rate": 2.962348615248099e-06,
|
| 527 |
+
"loss": 0.4797,
|
| 528 |
+
"step": 730
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.510204081632653,
|
| 532 |
+
"grad_norm": 1.2587718327059303,
|
| 533 |
+
"learning_rate": 2.9118905557265194e-06,
|
| 534 |
+
"loss": 0.4735,
|
| 535 |
+
"step": 740
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.5306122448979593,
|
| 539 |
+
"grad_norm": 1.1013738197897254,
|
| 540 |
+
"learning_rate": 2.861350511640466e-06,
|
| 541 |
+
"loss": 0.475,
|
| 542 |
+
"step": 750
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.5510204081632653,
|
| 546 |
+
"grad_norm": 1.1227769485684345,
|
| 547 |
+
"learning_rate": 2.81075407746322e-06,
|
| 548 |
+
"loss": 0.4749,
|
| 549 |
+
"step": 760
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.5714285714285714,
|
| 553 |
+
"grad_norm": 1.0818370734100442,
|
| 554 |
+
"learning_rate": 2.760126876225113e-06,
|
| 555 |
+
"loss": 0.4753,
|
| 556 |
+
"step": 770
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.5918367346938775,
|
| 560 |
+
"grad_norm": 1.0587953555625602,
|
| 561 |
+
"learning_rate": 2.7094945465375237e-06,
|
| 562 |
+
"loss": 0.47,
|
| 563 |
+
"step": 780
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.6122448979591837,
|
| 567 |
+
"grad_norm": 1.1618625324803182,
|
| 568 |
+
"learning_rate": 2.6588827296089765e-06,
|
| 569 |
+
"loss": 0.4746,
|
| 570 |
+
"step": 790
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.6326530612244898,
|
| 574 |
+
"grad_norm": 1.2352446476841303,
|
| 575 |
+
"learning_rate": 2.608317056259933e-06,
|
| 576 |
+
"loss": 0.4733,
|
| 577 |
+
"step": 800
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.6530612244897958,
|
| 581 |
+
"grad_norm": 1.0937135850117063,
|
| 582 |
+
"learning_rate": 2.557823133942836e-06,
|
| 583 |
+
"loss": 0.4793,
|
| 584 |
+
"step": 810
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.6734693877551021,
|
| 588 |
+
"grad_norm": 1.126671194089832,
|
| 589 |
+
"learning_rate": 2.507426533773994e-06,
|
| 590 |
+
"loss": 0.4709,
|
| 591 |
+
"step": 820
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.693877551020408,
|
| 595 |
+
"grad_norm": 1.1253283659142022,
|
| 596 |
+
"learning_rate": 2.4571527775838637e-06,
|
| 597 |
+
"loss": 0.4741,
|
| 598 |
+
"step": 830
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.7142857142857144,
|
| 602 |
+
"grad_norm": 1.1309032305899065,
|
| 603 |
+
"learning_rate": 2.407027324992293e-06,
|
| 604 |
+
"loss": 0.4735,
|
| 605 |
+
"step": 840
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.7346938775510203,
|
| 609 |
+
"grad_norm": 1.1311416180631535,
|
| 610 |
+
"learning_rate": 2.357075560515267e-06,
|
| 611 |
+
"loss": 0.4742,
|
| 612 |
+
"step": 850
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.7551020408163265,
|
| 616 |
+
"grad_norm": 1.0615765131524626,
|
| 617 |
+
"learning_rate": 2.3073227807096903e-06,
|
| 618 |
+
"loss": 0.4764,
|
| 619 |
+
"step": 860
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.7755102040816326,
|
| 623 |
+
"grad_norm": 1.1511014505350845,
|
| 624 |
+
"learning_rate": 2.2577941813627137e-06,
|
| 625 |
+
"loss": 0.4675,
|
| 626 |
+
"step": 870
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.7959183673469388,
|
| 630 |
+
"grad_norm": 1.1577030186189212,
|
| 631 |
+
"learning_rate": 2.2085148447320886e-06,
|
| 632 |
+
"loss": 0.4762,
|
| 633 |
+
"step": 880
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.816326530612245,
|
| 637 |
+
"grad_norm": 1.0977519312106587,
|
| 638 |
+
"learning_rate": 2.1595097268440215e-06,
|
| 639 |
+
"loss": 0.4728,
|
| 640 |
+
"step": 890
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.836734693877551,
|
| 644 |
+
"grad_norm": 1.1107484368711582,
|
| 645 |
+
"learning_rate": 2.110803644854949e-06,
|
| 646 |
+
"loss": 0.472,
|
| 647 |
+
"step": 900
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.8571428571428572,
|
| 651 |
+
"grad_norm": 1.1592418760463674,
|
| 652 |
+
"learning_rate": 2.062421264483641e-06,
|
| 653 |
+
"loss": 0.4715,
|
| 654 |
+
"step": 910
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.8775510204081631,
|
| 658 |
+
"grad_norm": 1.0540592699686717,
|
| 659 |
+
"learning_rate": 2.0143870875199952e-06,
|
| 660 |
+
"loss": 0.4732,
|
| 661 |
+
"step": 920
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.8979591836734695,
|
| 665 |
+
"grad_norm": 1.1457616506688253,
|
| 666 |
+
"learning_rate": 1.9667254394168497e-06,
|
| 667 |
+
"loss": 0.4726,
|
| 668 |
+
"step": 930
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.9183673469387754,
|
| 672 |
+
"grad_norm": 1.0508307850745724,
|
| 673 |
+
"learning_rate": 1.9194604569710933e-06,
|
| 674 |
+
"loss": 0.4682,
|
| 675 |
+
"step": 940
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.9387755102040818,
|
| 679 |
+
"grad_norm": 1.0174568043397745,
|
| 680 |
+
"learning_rate": 1.8726160761003172e-06,
|
| 681 |
+
"loss": 0.4714,
|
| 682 |
+
"step": 950
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.9591836734693877,
|
| 686 |
+
"grad_norm": 1.1472581629373104,
|
| 687 |
+
"learning_rate": 1.8262160197211954e-06,
|
| 688 |
+
"loss": 0.4694,
|
| 689 |
+
"step": 960
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.9795918367346939,
|
| 693 |
+
"grad_norm": 1.1908224015497966,
|
| 694 |
+
"learning_rate": 1.780283785735729e-06,
|
| 695 |
+
"loss": 0.4734,
|
| 696 |
+
"step": 970
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 2.0,
|
| 700 |
+
"grad_norm": 1.2121370436582353,
|
| 701 |
+
"learning_rate": 1.734842635131455e-06,
|
| 702 |
+
"loss": 0.4704,
|
| 703 |
+
"step": 980
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 2.0,
|
| 707 |
+
"eval_loss": 0.5511366724967957,
|
| 708 |
+
"eval_runtime": 52.0352,
|
| 709 |
+
"eval_samples_per_second": 253.636,
|
| 710 |
+
"eval_steps_per_second": 0.999,
|
| 711 |
+
"step": 980
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 2.020408163265306,
|
| 715 |
+
"grad_norm": 1.8051946996767576,
|
| 716 |
+
"learning_rate": 1.689915580201614e-06,
|
| 717 |
+
"loss": 0.3994,
|
| 718 |
+
"step": 990
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 2.0408163265306123,
|
| 722 |
+
"grad_norm": 1.1478153392823722,
|
| 723 |
+
"learning_rate": 1.6455253728912765e-06,
|
| 724 |
+
"loss": 0.4039,
|
| 725 |
+
"step": 1000
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 2.061224489795918,
|
| 729 |
+
"grad_norm": 1.1584353460539132,
|
| 730 |
+
"learning_rate": 1.6016944932753123e-06,
|
| 731 |
+
"loss": 0.3966,
|
| 732 |
+
"step": 1010
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 2.0816326530612246,
|
| 736 |
+
"grad_norm": 1.116691322240523,
|
| 737 |
+
"learning_rate": 1.558445138174033e-06,
|
| 738 |
+
"loss": 0.3956,
|
| 739 |
+
"step": 1020
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 2.1020408163265305,
|
| 743 |
+
"grad_norm": 1.2064468569146183,
|
| 744 |
+
"learning_rate": 1.5157992099122896e-06,
|
| 745 |
+
"loss": 0.3993,
|
| 746 |
+
"step": 1030
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 2.122448979591837,
|
| 750 |
+
"grad_norm": 1.139941688958116,
|
| 751 |
+
"learning_rate": 1.4737783052277017e-06,
|
| 752 |
+
"loss": 0.3961,
|
| 753 |
+
"step": 1040
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 2.142857142857143,
|
| 757 |
+
"grad_norm": 1.0807209086306862,
|
| 758 |
+
"learning_rate": 1.432403704333643e-06,
|
| 759 |
+
"loss": 0.3947,
|
| 760 |
+
"step": 1050
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 2.163265306122449,
|
| 764 |
+
"grad_norm": 1.2684450483524876,
|
| 765 |
+
"learning_rate": 1.3916963601425293e-06,
|
| 766 |
+
"loss": 0.3969,
|
| 767 |
+
"step": 1060
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 2.183673469387755,
|
| 771 |
+
"grad_norm": 1.1513016140487604,
|
| 772 |
+
"learning_rate": 1.3516768876548404e-06,
|
| 773 |
+
"loss": 0.393,
|
| 774 |
+
"step": 1070
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 2.204081632653061,
|
| 778 |
+
"grad_norm": 1.1528208336686618,
|
| 779 |
+
"learning_rate": 1.3123655535192873e-06,
|
| 780 |
+
"loss": 0.3951,
|
| 781 |
+
"step": 1080
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 2.2244897959183674,
|
| 785 |
+
"grad_norm": 1.114096425157638,
|
| 786 |
+
"learning_rate": 1.2737822657693763e-06,
|
| 787 |
+
"loss": 0.3979,
|
| 788 |
+
"step": 1090
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 2.2448979591836733,
|
| 792 |
+
"grad_norm": 1.137857862533777,
|
| 793 |
+
"learning_rate": 1.235946563741594e-06,
|
| 794 |
+
"loss": 0.3997,
|
| 795 |
+
"step": 1100
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 2.2653061224489797,
|
| 799 |
+
"grad_norm": 1.1835334812821745,
|
| 800 |
+
"learning_rate": 1.1988776081802975e-06,
|
| 801 |
+
"loss": 0.3899,
|
| 802 |
+
"step": 1110
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 2.2857142857142856,
|
| 806 |
+
"grad_norm": 1.1680694095477702,
|
| 807 |
+
"learning_rate": 1.1625941715343404e-06,
|
| 808 |
+
"loss": 0.3966,
|
| 809 |
+
"step": 1120
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 2.306122448979592,
|
| 813 |
+
"grad_norm": 1.1446186179544782,
|
| 814 |
+
"learning_rate": 1.1271146284503326e-06,
|
| 815 |
+
"loss": 0.396,
|
| 816 |
+
"step": 1130
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 2.326530612244898,
|
| 820 |
+
"grad_norm": 1.11805038713306,
|
| 821 |
+
"learning_rate": 1.0924569464673593e-06,
|
| 822 |
+
"loss": 0.3904,
|
| 823 |
+
"step": 1140
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 2.3469387755102042,
|
| 827 |
+
"grad_norm": 1.1390452730330538,
|
| 828 |
+
"learning_rate": 1.0586386769178644e-06,
|
| 829 |
+
"loss": 0.3975,
|
| 830 |
+
"step": 1150
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 2.36734693877551,
|
| 834 |
+
"grad_norm": 1.1201370952508136,
|
| 835 |
+
"learning_rate": 1.0256769460393087e-06,
|
| 836 |
+
"loss": 0.3967,
|
| 837 |
+
"step": 1160
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 2.387755102040816,
|
| 841 |
+
"grad_norm": 1.1392432124449605,
|
| 842 |
+
"learning_rate": 9.935884463011108e-07,
|
| 843 |
+
"loss": 0.3996,
|
| 844 |
+
"step": 1170
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 2.4081632653061225,
|
| 848 |
+
"grad_norm": 1.2588827341992963,
|
| 849 |
+
"learning_rate": 9.623894279512455e-07,
|
| 850 |
+
"loss": 0.396,
|
| 851 |
+
"step": 1180
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 2.4285714285714284,
|
| 855 |
+
"grad_norm": 1.077230551463912,
|
| 856 |
+
"learning_rate": 9.320956907868051e-07,
|
| 857 |
+
"loss": 0.3937,
|
| 858 |
+
"step": 1190
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 2.4489795918367347,
|
| 862 |
+
"grad_norm": 1.11076242811804,
|
| 863 |
+
"learning_rate": 9.027225761526653e-07,
|
| 864 |
+
"loss": 0.3952,
|
| 865 |
+
"step": 1200
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 2.4693877551020407,
|
| 869 |
+
"grad_norm": 1.09876781476475,
|
| 870 |
+
"learning_rate": 8.742849591723315e-07,
|
| 871 |
+
"loss": 0.3959,
|
| 872 |
+
"step": 1210
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 2.489795918367347,
|
| 876 |
+
"grad_norm": 1.147140927511145,
|
| 877 |
+
"learning_rate": 8.467972412148767e-07,
|
| 878 |
+
"loss": 0.398,
|
| 879 |
+
"step": 1220
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 2.510204081632653,
|
| 883 |
+
"grad_norm": 1.1822473270970597,
|
| 884 |
+
"learning_rate": 8.202733426018117e-07,
|
| 885 |
+
"loss": 0.3964,
|
| 886 |
+
"step": 1230
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 2.5306122448979593,
|
| 890 |
+
"grad_norm": 1.13658360907236,
|
| 891 |
+
"learning_rate": 7.947266955575562e-07,
|
| 892 |
+
"loss": 0.3927,
|
| 893 |
+
"step": 1240
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 2.5510204081632653,
|
| 897 |
+
"grad_norm": 1.161600360604373,
|
| 898 |
+
"learning_rate": 7.701702374070962e-07,
|
| 899 |
+
"loss": 0.395,
|
| 900 |
+
"step": 1250
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 2.571428571428571,
|
| 904 |
+
"grad_norm": 1.1360953648560599,
|
| 905 |
+
"learning_rate": 7.466164040242694e-07,
|
| 906 |
+
"loss": 0.393,
|
| 907 |
+
"step": 1260
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 2.5918367346938775,
|
| 911 |
+
"grad_norm": 1.0871899727126686,
|
| 912 |
+
"learning_rate": 7.24077123533992e-07,
|
| 913 |
+
"loss": 0.3954,
|
| 914 |
+
"step": 1270
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 2.612244897959184,
|
| 918 |
+
"grad_norm": 1.1448805596871288,
|
| 919 |
+
"learning_rate": 7.025638102716238e-07,
|
| 920 |
+
"loss": 0.3956,
|
| 921 |
+
"step": 1280
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 2.63265306122449,
|
| 925 |
+
"grad_norm": 1.15756019184531,
|
| 926 |
+
"learning_rate": 6.820873590025216e-07,
|
| 927 |
+
"loss": 0.3976,
|
| 928 |
+
"step": 1290
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 2.6530612244897958,
|
| 932 |
+
"grad_norm": 1.1241749432401325,
|
| 933 |
+
"learning_rate": 6.626581394047174e-07,
|
| 934 |
+
"loss": 0.3984,
|
| 935 |
+
"step": 1300
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 2.673469387755102,
|
| 939 |
+
"grad_norm": 1.0729517449985635,
|
| 940 |
+
"learning_rate": 6.442859908175084e-07,
|
| 941 |
+
"loss": 0.3959,
|
| 942 |
+
"step": 1310
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 2.693877551020408,
|
| 946 |
+
"grad_norm": 1.1503013647826037,
|
| 947 |
+
"learning_rate": 6.269802172586215e-07,
|
| 948 |
+
"loss": 0.397,
|
| 949 |
+
"step": 1320
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 2.7142857142857144,
|
| 953 |
+
"grad_norm": 1.0665491356834242,
|
| 954 |
+
"learning_rate": 6.107495827124764e-07,
|
| 955 |
+
"loss": 0.39,
|
| 956 |
+
"step": 1330
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 2.7346938775510203,
|
| 960 |
+
"grad_norm": 1.0915048516830226,
|
| 961 |
+
"learning_rate": 5.956023066919313e-07,
|
| 962 |
+
"loss": 0.3959,
|
| 963 |
+
"step": 1340
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 2.7551020408163263,
|
| 967 |
+
"grad_norm": 1.109246892499863,
|
| 968 |
+
"learning_rate": 5.815460600757599e-07,
|
| 969 |
+
"loss": 0.3959,
|
| 970 |
+
"step": 1350
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 2.7755102040816326,
|
| 974 |
+
"grad_norm": 1.0721604859361742,
|
| 975 |
+
"learning_rate": 5.685879612239649e-07,
|
| 976 |
+
"loss": 0.3966,
|
| 977 |
+
"step": 1360
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 2.795918367346939,
|
| 981 |
+
"grad_norm": 1.099826021414002,
|
| 982 |
+
"learning_rate": 5.567345723729062e-07,
|
| 983 |
+
"loss": 0.3981,
|
| 984 |
+
"step": 1370
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 2.816326530612245,
|
| 988 |
+
"grad_norm": 1.1271135580966902,
|
| 989 |
+
"learning_rate": 5.459918963120477e-07,
|
| 990 |
+
"loss": 0.3958,
|
| 991 |
+
"step": 1380
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 2.836734693877551,
|
| 995 |
+
"grad_norm": 1.1076320060744895,
|
| 996 |
+
"learning_rate": 5.363653733440328e-07,
|
| 997 |
+
"loss": 0.3937,
|
| 998 |
+
"step": 1390
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 2.857142857142857,
|
| 1002 |
+
"grad_norm": 1.2274793148430172,
|
| 1003 |
+
"learning_rate": 5.278598785296044e-07,
|
| 1004 |
+
"loss": 0.3955,
|
| 1005 |
+
"step": 1400
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 2.877551020408163,
|
| 1009 |
+
"grad_norm": 1.118998176569128,
|
| 1010 |
+
"learning_rate": 5.2047971921878e-07,
|
| 1011 |
+
"loss": 0.3935,
|
| 1012 |
+
"step": 1410
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 2.8979591836734695,
|
| 1016 |
+
"grad_norm": 1.0904203190313753,
|
| 1017 |
+
"learning_rate": 5.142286328695235e-07,
|
| 1018 |
+
"loss": 0.3991,
|
| 1019 |
+
"step": 1420
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 2.9183673469387754,
|
| 1023 |
+
"grad_norm": 1.09693683808665,
|
| 1024 |
+
"learning_rate": 5.091097851550239e-07,
|
| 1025 |
+
"loss": 0.3984,
|
| 1026 |
+
"step": 1430
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 2.938775510204082,
|
| 1030 |
+
"grad_norm": 1.136997659277711,
|
| 1031 |
+
"learning_rate": 5.051257683605363e-07,
|
| 1032 |
+
"loss": 0.3977,
|
| 1033 |
+
"step": 1440
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 2.9591836734693877,
|
| 1037 |
+
"grad_norm": 1.1088368453362634,
|
| 1038 |
+
"learning_rate": 5.022786000705963e-07,
|
| 1039 |
+
"loss": 0.3948,
|
| 1040 |
+
"step": 1450
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 2.979591836734694,
|
| 1044 |
+
"grad_norm": 1.0739107650188835,
|
| 1045 |
+
"learning_rate": 5.005697221472769e-07,
|
| 1046 |
+
"loss": 0.3949,
|
| 1047 |
+
"step": 1460
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 3.0,
|
| 1051 |
+
"grad_norm": 1.116205224878417,
|
| 1052 |
+
"learning_rate": 5e-07,
|
| 1053 |
+
"loss": 0.3994,
|
| 1054 |
+
"step": 1470
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 3.0,
|
| 1058 |
+
"eval_loss": 0.5735070705413818,
|
| 1059 |
+
"eval_runtime": 51.0398,
|
| 1060 |
+
"eval_samples_per_second": 258.583,
|
| 1061 |
+
"eval_steps_per_second": 1.019,
|
| 1062 |
+
"step": 1470
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 3.0,
|
| 1066 |
+
"step": 1470,
|
| 1067 |
+
"total_flos": 2462304750796800.0,
|
| 1068 |
+
"train_loss": 0.48433749789283387,
|
| 1069 |
+
"train_runtime": 9163.976,
|
| 1070 |
+
"train_samples_per_second": 82.091,
|
| 1071 |
+
"train_steps_per_second": 0.16
|
| 1072 |
+
}
|
| 1073 |
+
],
|
| 1074 |
+
"logging_steps": 10,
|
| 1075 |
+
"max_steps": 1470,
|
| 1076 |
+
"num_input_tokens_seen": 0,
|
| 1077 |
+
"num_train_epochs": 3,
|
| 1078 |
+
"save_steps": 500,
|
| 1079 |
+
"stateful_callbacks": {
|
| 1080 |
+
"TrainerControl": {
|
| 1081 |
+
"args": {
|
| 1082 |
+
"should_epoch_stop": false,
|
| 1083 |
+
"should_evaluate": false,
|
| 1084 |
+
"should_log": false,
|
| 1085 |
+
"should_save": true,
|
| 1086 |
+
"should_training_stop": true
|
| 1087 |
+
},
|
| 1088 |
+
"attributes": {}
|
| 1089 |
+
}
|
| 1090 |
+
},
|
| 1091 |
+
"total_flos": 2462304750796800.0,
|
| 1092 |
+
"train_batch_size": 16,
|
| 1093 |
+
"trial_name": null,
|
| 1094 |
+
"trial_params": null
|
| 1095 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|