End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +1113 -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: seed_code_multiple_samples_gpt_verification_scale_up_2K
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# seed_code_multiple_samples_gpt_verification_scale_up_2K
|
| 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: seed_code_multiple_samples_gpt_verification_scale_up_2K
|
|
|
|
| 16 |
|
| 17 |
# seed_code_multiple_samples_gpt_verification_scale_up_2K
|
| 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/seed_code_multiple_samples_gpt_verification_scale_up_2K dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.978930307941653,
|
| 3 |
+
"total_flos": 132192675135488.0,
|
| 4 |
+
"train_loss": 0.8684253560172187,
|
| 5 |
+
"train_runtime": 7585.4265,
|
| 6 |
+
"train_samples_per_second": 1.952,
|
| 7 |
+
"train_steps_per_second": 0.02
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.978930307941653,
|
| 3 |
+
"total_flos": 132192675135488.0,
|
| 4 |
+
"train_loss": 0.8684253560172187,
|
| 5 |
+
"train_runtime": 7585.4265,
|
| 6 |
+
"train_samples_per_second": 1.952,
|
| 7 |
+
"train_steps_per_second": 0.02
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.978930307941653,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 153,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.019448946515397084,
|
| 13 |
+
"grad_norm": 6.861098289489746,
|
| 14 |
+
"learning_rate": 6.25e-07,
|
| 15 |
+
"loss": 1.2627,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.03889789303079417,
|
| 20 |
+
"grad_norm": 6.737518310546875,
|
| 21 |
+
"learning_rate": 1.25e-06,
|
| 22 |
+
"loss": 1.2374,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.05834683954619125,
|
| 27 |
+
"grad_norm": 6.920078754425049,
|
| 28 |
+
"learning_rate": 1.8750000000000003e-06,
|
| 29 |
+
"loss": 1.2864,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.07779578606158834,
|
| 34 |
+
"grad_norm": 6.555400371551514,
|
| 35 |
+
"learning_rate": 2.5e-06,
|
| 36 |
+
"loss": 1.2097,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.09724473257698542,
|
| 41 |
+
"grad_norm": 6.175917625427246,
|
| 42 |
+
"learning_rate": 3.125e-06,
|
| 43 |
+
"loss": 1.1939,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.1166936790923825,
|
| 48 |
+
"grad_norm": 4.607879638671875,
|
| 49 |
+
"learning_rate": 3.7500000000000005e-06,
|
| 50 |
+
"loss": 1.1667,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.13614262560777957,
|
| 55 |
+
"grad_norm": 2.9558024406433105,
|
| 56 |
+
"learning_rate": 4.3750000000000005e-06,
|
| 57 |
+
"loss": 1.1707,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.15559157212317667,
|
| 62 |
+
"grad_norm": 2.6493217945098877,
|
| 63 |
+
"learning_rate": 5e-06,
|
| 64 |
+
"loss": 1.0802,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.17504051863857376,
|
| 69 |
+
"grad_norm": 4.4779953956604,
|
| 70 |
+
"learning_rate": 5.625e-06,
|
| 71 |
+
"loss": 1.1318,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.19448946515397084,
|
| 76 |
+
"grad_norm": 4.794122695922852,
|
| 77 |
+
"learning_rate": 6.25e-06,
|
| 78 |
+
"loss": 1.162,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.21393841166936792,
|
| 83 |
+
"grad_norm": 4.527707099914551,
|
| 84 |
+
"learning_rate": 6.875e-06,
|
| 85 |
+
"loss": 1.1654,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.233387358184765,
|
| 90 |
+
"grad_norm": 3.3236396312713623,
|
| 91 |
+
"learning_rate": 7.500000000000001e-06,
|
| 92 |
+
"loss": 1.0345,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.25283630470016205,
|
| 97 |
+
"grad_norm": 3.3806722164154053,
|
| 98 |
+
"learning_rate": 8.125000000000001e-06,
|
| 99 |
+
"loss": 1.0519,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.27228525121555913,
|
| 104 |
+
"grad_norm": 2.476033926010132,
|
| 105 |
+
"learning_rate": 8.750000000000001e-06,
|
| 106 |
+
"loss": 1.0189,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.2917341977309562,
|
| 111 |
+
"grad_norm": 2.0179576873779297,
|
| 112 |
+
"learning_rate": 9.375000000000001e-06,
|
| 113 |
+
"loss": 0.9914,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.31118314424635335,
|
| 118 |
+
"grad_norm": 1.9065077304840088,
|
| 119 |
+
"learning_rate": 1e-05,
|
| 120 |
+
"loss": 1.0208,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.33063209076175043,
|
| 125 |
+
"grad_norm": 1.8468468189239502,
|
| 126 |
+
"learning_rate": 9.998685442495921e-06,
|
| 127 |
+
"loss": 0.9893,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.3500810372771475,
|
| 132 |
+
"grad_norm": 1.5280859470367432,
|
| 133 |
+
"learning_rate": 9.994742461208251e-06,
|
| 134 |
+
"loss": 0.9482,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.3695299837925446,
|
| 139 |
+
"grad_norm": 1.369767665863037,
|
| 140 |
+
"learning_rate": 9.988173129447251e-06,
|
| 141 |
+
"loss": 0.9942,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.3889789303079417,
|
| 146 |
+
"grad_norm": 1.207467794418335,
|
| 147 |
+
"learning_rate": 9.978980901518663e-06,
|
| 148 |
+
"loss": 0.9676,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.40842787682333875,
|
| 153 |
+
"grad_norm": 1.4069736003875732,
|
| 154 |
+
"learning_rate": 9.96717061090737e-06,
|
| 155 |
+
"loss": 0.9322,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.42787682333873583,
|
| 160 |
+
"grad_norm": 1.1611406803131104,
|
| 161 |
+
"learning_rate": 9.95274846773583e-06,
|
| 162 |
+
"loss": 0.9786,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.4473257698541329,
|
| 167 |
+
"grad_norm": 1.1889172792434692,
|
| 168 |
+
"learning_rate": 9.935722055498655e-06,
|
| 169 |
+
"loss": 0.9256,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.46677471636953,
|
| 174 |
+
"grad_norm": 1.1732343435287476,
|
| 175 |
+
"learning_rate": 9.916100327075038e-06,
|
| 176 |
+
"loss": 0.8946,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.4862236628849271,
|
| 181 |
+
"grad_norm": 1.3214962482452393,
|
| 182 |
+
"learning_rate": 9.893893600021112e-06,
|
| 183 |
+
"loss": 0.9087,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.5056726094003241,
|
| 188 |
+
"grad_norm": 1.1180990934371948,
|
| 189 |
+
"learning_rate": 9.869113551144754e-06,
|
| 190 |
+
"loss": 0.9407,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.5251215559157212,
|
| 195 |
+
"grad_norm": 0.9630658626556396,
|
| 196 |
+
"learning_rate": 9.841773210365646e-06,
|
| 197 |
+
"loss": 0.9329,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.5445705024311183,
|
| 202 |
+
"grad_norm": 0.9198795557022095,
|
| 203 |
+
"learning_rate": 9.811886953863841e-06,
|
| 204 |
+
"loss": 0.9378,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.5640194489465153,
|
| 209 |
+
"grad_norm": 0.9277356266975403,
|
| 210 |
+
"learning_rate": 9.779470496520442e-06,
|
| 211 |
+
"loss": 0.9195,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.5834683954619124,
|
| 216 |
+
"grad_norm": 0.80616694688797,
|
| 217 |
+
"learning_rate": 9.744540883654348e-06,
|
| 218 |
+
"loss": 0.932,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.6029173419773096,
|
| 223 |
+
"grad_norm": 0.8931137323379517,
|
| 224 |
+
"learning_rate": 9.707116482059447e-06,
|
| 225 |
+
"loss": 0.9024,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.6223662884927067,
|
| 230 |
+
"grad_norm": 0.8059653043746948,
|
| 231 |
+
"learning_rate": 9.667216970346916e-06,
|
| 232 |
+
"loss": 0.9376,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.6418152350081038,
|
| 237 |
+
"grad_norm": 0.7000671625137329,
|
| 238 |
+
"learning_rate": 9.624863328597767e-06,
|
| 239 |
+
"loss": 0.8836,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.6612641815235009,
|
| 244 |
+
"grad_norm": 0.788222074508667,
|
| 245 |
+
"learning_rate": 9.580077827331038e-06,
|
| 246 |
+
"loss": 0.8801,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.6807131280388979,
|
| 251 |
+
"grad_norm": 0.960985004901886,
|
| 252 |
+
"learning_rate": 9.532884015793432e-06,
|
| 253 |
+
"loss": 0.8777,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.700162074554295,
|
| 258 |
+
"grad_norm": 0.9860551357269287,
|
| 259 |
+
"learning_rate": 9.48330670957659e-06,
|
| 260 |
+
"loss": 0.905,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.7196110210696921,
|
| 265 |
+
"grad_norm": 0.8046407699584961,
|
| 266 |
+
"learning_rate": 9.431371977568483e-06,
|
| 267 |
+
"loss": 0.9257,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.7390599675850892,
|
| 272 |
+
"grad_norm": 0.9749986529350281,
|
| 273 |
+
"learning_rate": 9.377107128245782e-06,
|
| 274 |
+
"loss": 0.9026,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.7585089141004863,
|
| 279 |
+
"grad_norm": 1.0727578401565552,
|
| 280 |
+
"learning_rate": 9.32054069531444e-06,
|
| 281 |
+
"loss": 0.9418,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.7779578606158833,
|
| 286 |
+
"grad_norm": 0.8145267963409424,
|
| 287 |
+
"learning_rate": 9.261702422706014e-06,
|
| 288 |
+
"loss": 0.906,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.7974068071312804,
|
| 293 |
+
"grad_norm": 0.8878953456878662,
|
| 294 |
+
"learning_rate": 9.200623248937619e-06,
|
| 295 |
+
"loss": 0.911,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.8168557536466775,
|
| 300 |
+
"grad_norm": 0.8581916689872742,
|
| 301 |
+
"learning_rate": 9.13733529084374e-06,
|
| 302 |
+
"loss": 0.8873,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.8363047001620746,
|
| 307 |
+
"grad_norm": 0.6927335858345032,
|
| 308 |
+
"learning_rate": 9.071871826688472e-06,
|
| 309 |
+
"loss": 0.8726,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.8557536466774717,
|
| 314 |
+
"grad_norm": 0.6785300970077515,
|
| 315 |
+
"learning_rate": 9.004267278667032e-06,
|
| 316 |
+
"loss": 0.9282,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.8752025931928687,
|
| 321 |
+
"grad_norm": 0.735817015171051,
|
| 322 |
+
"learning_rate": 8.934557194805787e-06,
|
| 323 |
+
"loss": 0.9498,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.8946515397082658,
|
| 328 |
+
"grad_norm": 0.6314980387687683,
|
| 329 |
+
"learning_rate": 8.862778230270276e-06,
|
| 330 |
+
"loss": 0.8851,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.9141004862236629,
|
| 335 |
+
"grad_norm": 0.6786671280860901,
|
| 336 |
+
"learning_rate": 8.788968128091084e-06,
|
| 337 |
+
"loss": 0.8834,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.93354943273906,
|
| 342 |
+
"grad_norm": 0.7222251892089844,
|
| 343 |
+
"learning_rate": 8.71316569931769e-06,
|
| 344 |
+
"loss": 0.8915,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.9529983792544571,
|
| 349 |
+
"grad_norm": 0.7341165542602539,
|
| 350 |
+
"learning_rate": 8.635410802610724e-06,
|
| 351 |
+
"loss": 0.8392,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.9724473257698542,
|
| 356 |
+
"grad_norm": 0.7214636206626892,
|
| 357 |
+
"learning_rate": 8.555744323283364e-06,
|
| 358 |
+
"loss": 0.8845,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.9918962722852512,
|
| 363 |
+
"grad_norm": 0.848508358001709,
|
| 364 |
+
"learning_rate": 8.474208151802898e-06,
|
| 365 |
+
"loss": 0.8581,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.012965964343598,
|
| 370 |
+
"grad_norm": 1.2223843336105347,
|
| 371 |
+
"learning_rate": 8.390845161763756e-06,
|
| 372 |
+
"loss": 1.4462,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 1.032414910858995,
|
| 377 |
+
"grad_norm": 0.6608096361160278,
|
| 378 |
+
"learning_rate": 8.305699187343586e-06,
|
| 379 |
+
"loss": 0.9298,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 1.0518638573743921,
|
| 384 |
+
"grad_norm": 0.7156009674072266,
|
| 385 |
+
"learning_rate": 8.218815000254233e-06,
|
| 386 |
+
"loss": 0.7472,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.0713128038897892,
|
| 391 |
+
"grad_norm": 0.7926570177078247,
|
| 392 |
+
"learning_rate": 8.130238286199747e-06,
|
| 393 |
+
"loss": 0.8235,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 1.0907617504051863,
|
| 398 |
+
"grad_norm": 0.8245845437049866,
|
| 399 |
+
"learning_rate": 8.04001562085379e-06,
|
| 400 |
+
"loss": 0.9211,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 1.1102106969205834,
|
| 405 |
+
"grad_norm": 0.6690172553062439,
|
| 406 |
+
"learning_rate": 7.948194445369065e-06,
|
| 407 |
+
"loss": 0.9178,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.1296596434359805,
|
| 412 |
+
"grad_norm": 0.8226907849311829,
|
| 413 |
+
"learning_rate": 7.85482304143168e-06,
|
| 414 |
+
"loss": 0.7913,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 1.1491085899513775,
|
| 419 |
+
"grad_norm": 0.9551813006401062,
|
| 420 |
+
"learning_rate": 7.759950505873523e-06,
|
| 421 |
+
"loss": 0.8701,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.1685575364667746,
|
| 426 |
+
"grad_norm": 0.6174091696739197,
|
| 427 |
+
"learning_rate": 7.66362672485601e-06,
|
| 428 |
+
"loss": 0.8091,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.1880064829821717,
|
| 433 |
+
"grad_norm": 0.8523845076560974,
|
| 434 |
+
"learning_rate": 7.565902347638806e-06,
|
| 435 |
+
"loss": 0.8805,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 1.2074554294975688,
|
| 440 |
+
"grad_norm": 0.6692298054695129,
|
| 441 |
+
"learning_rate": 7.466828759947271e-06,
|
| 442 |
+
"loss": 0.8076,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.2269043760129659,
|
| 447 |
+
"grad_norm": 0.6524062156677246,
|
| 448 |
+
"learning_rate": 7.366458056952668e-06,
|
| 449 |
+
"loss": 0.7676,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.246353322528363,
|
| 454 |
+
"grad_norm": 0.7085561752319336,
|
| 455 |
+
"learning_rate": 7.264843015879321e-06,
|
| 456 |
+
"loss": 0.9008,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 1.26580226904376,
|
| 461 |
+
"grad_norm": 0.6387475728988647,
|
| 462 |
+
"learning_rate": 7.162037068253141e-06,
|
| 463 |
+
"loss": 0.7623,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 1.2852512155591573,
|
| 468 |
+
"grad_norm": 0.6962757110595703,
|
| 469 |
+
"learning_rate": 7.058094271806091e-06,
|
| 470 |
+
"loss": 0.8989,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.3047001620745542,
|
| 475 |
+
"grad_norm": 0.6996948719024658,
|
| 476 |
+
"learning_rate": 6.953069282051397e-06,
|
| 477 |
+
"loss": 0.8975,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 1.3241491085899515,
|
| 482 |
+
"grad_norm": 0.6775169968605042,
|
| 483 |
+
"learning_rate": 6.84701732354442e-06,
|
| 484 |
+
"loss": 0.744,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 1.3435980551053484,
|
| 489 |
+
"grad_norm": 0.5788021087646484,
|
| 490 |
+
"learning_rate": 6.7399941608443096e-06,
|
| 491 |
+
"loss": 0.8693,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 1.3630470016207457,
|
| 496 |
+
"grad_norm": 0.797266960144043,
|
| 497 |
+
"learning_rate": 6.632056069191723e-06,
|
| 498 |
+
"loss": 0.8185,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 1.3824959481361425,
|
| 503 |
+
"grad_norm": 0.6203992366790771,
|
| 504 |
+
"learning_rate": 6.523259804918001e-06,
|
| 505 |
+
"loss": 0.8219,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.4019448946515398,
|
| 510 |
+
"grad_norm": 0.5873000621795654,
|
| 511 |
+
"learning_rate": 6.413662575601391e-06,
|
| 512 |
+
"loss": 0.8675,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.4213938411669367,
|
| 517 |
+
"grad_norm": 0.5779026746749878,
|
| 518 |
+
"learning_rate": 6.303322009985984e-06,
|
| 519 |
+
"loss": 0.8004,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 1.440842787682334,
|
| 524 |
+
"grad_norm": 0.7285134792327881,
|
| 525 |
+
"learning_rate": 6.1922961276791925e-06,
|
| 526 |
+
"loss": 0.8649,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.4602917341977308,
|
| 531 |
+
"grad_norm": 0.5539451837539673,
|
| 532 |
+
"learning_rate": 6.08064330864371e-06,
|
| 533 |
+
"loss": 0.7551,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.4797406807131281,
|
| 538 |
+
"grad_norm": 0.530315101146698,
|
| 539 |
+
"learning_rate": 5.968422262499983e-06,
|
| 540 |
+
"loss": 0.798,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.499189627228525,
|
| 545 |
+
"grad_norm": 0.6449223756790161,
|
| 546 |
+
"learning_rate": 5.85569199765534e-06,
|
| 547 |
+
"loss": 0.8498,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.5186385737439223,
|
| 552 |
+
"grad_norm": 0.5452909469604492,
|
| 553 |
+
"learning_rate": 5.7425117902760195e-06,
|
| 554 |
+
"loss": 0.7277,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.5380875202593192,
|
| 559 |
+
"grad_norm": 0.6189656853675842,
|
| 560 |
+
"learning_rate": 5.628941153118388e-06,
|
| 561 |
+
"loss": 0.8525,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.5575364667747165,
|
| 566 |
+
"grad_norm": 0.5398715734481812,
|
| 567 |
+
"learning_rate": 5.515039804235772e-06,
|
| 568 |
+
"loss": 0.7927,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.5769854132901133,
|
| 573 |
+
"grad_norm": 0.5609137415885925,
|
| 574 |
+
"learning_rate": 5.400867635577335e-06,
|
| 575 |
+
"loss": 0.8495,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.5964343598055106,
|
| 580 |
+
"grad_norm": 0.6827127933502197,
|
| 581 |
+
"learning_rate": 5.2864846814955e-06,
|
| 582 |
+
"loss": 0.7973,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 1.6158833063209075,
|
| 587 |
+
"grad_norm": 0.6233929395675659,
|
| 588 |
+
"learning_rate": 5.17195108717852e-06,
|
| 589 |
+
"loss": 0.8542,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.6353322528363048,
|
| 594 |
+
"grad_norm": 0.46808454394340515,
|
| 595 |
+
"learning_rate": 5.057327077024745e-06,
|
| 596 |
+
"loss": 0.7751,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.6547811993517016,
|
| 601 |
+
"grad_norm": 0.5673578381538391,
|
| 602 |
+
"learning_rate": 4.942672922975255e-06,
|
| 603 |
+
"loss": 0.7718,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.674230145867099,
|
| 608 |
+
"grad_norm": 0.6883957386016846,
|
| 609 |
+
"learning_rate": 4.82804891282148e-06,
|
| 610 |
+
"loss": 0.7642,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.6936790923824958,
|
| 615 |
+
"grad_norm": 0.6758309006690979,
|
| 616 |
+
"learning_rate": 4.713515318504501e-06,
|
| 617 |
+
"loss": 0.9642,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.7131280388978931,
|
| 622 |
+
"grad_norm": 0.4832862913608551,
|
| 623 |
+
"learning_rate": 4.599132364422666e-06,
|
| 624 |
+
"loss": 0.7228,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.73257698541329,
|
| 629 |
+
"grad_norm": 0.7116863131523132,
|
| 630 |
+
"learning_rate": 4.4849601957642295e-06,
|
| 631 |
+
"loss": 0.8748,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.7520259319286873,
|
| 636 |
+
"grad_norm": 0.5377712845802307,
|
| 637 |
+
"learning_rate": 4.371058846881614e-06,
|
| 638 |
+
"loss": 0.8228,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.7714748784440841,
|
| 643 |
+
"grad_norm": 0.49350258708000183,
|
| 644 |
+
"learning_rate": 4.257488209723981e-06,
|
| 645 |
+
"loss": 0.7398,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.7909238249594814,
|
| 650 |
+
"grad_norm": 0.5975490212440491,
|
| 651 |
+
"learning_rate": 4.1443080023446605e-06,
|
| 652 |
+
"loss": 0.8464,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.8103727714748783,
|
| 657 |
+
"grad_norm": 0.5417091846466064,
|
| 658 |
+
"learning_rate": 4.0315777375000185e-06,
|
| 659 |
+
"loss": 0.8294,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.8298217179902756,
|
| 664 |
+
"grad_norm": 0.5055018663406372,
|
| 665 |
+
"learning_rate": 3.9193566913562915e-06,
|
| 666 |
+
"loss": 0.7465,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.8492706645056725,
|
| 671 |
+
"grad_norm": 0.5458024144172668,
|
| 672 |
+
"learning_rate": 3.807703872320809e-06,
|
| 673 |
+
"loss": 0.8468,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.8687196110210698,
|
| 678 |
+
"grad_norm": 0.5673462748527527,
|
| 679 |
+
"learning_rate": 3.6966779900140193e-06,
|
| 680 |
+
"loss": 0.83,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.8881685575364666,
|
| 685 |
+
"grad_norm": 0.4504033625125885,
|
| 686 |
+
"learning_rate": 3.586337424398609e-06,
|
| 687 |
+
"loss": 0.8286,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.907617504051864,
|
| 692 |
+
"grad_norm": 0.5393473505973816,
|
| 693 |
+
"learning_rate": 3.4767401950820003e-06,
|
| 694 |
+
"loss": 0.7724,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 1.9270664505672608,
|
| 699 |
+
"grad_norm": 0.6027775406837463,
|
| 700 |
+
"learning_rate": 3.3679439308082777e-06,
|
| 701 |
+
"loss": 0.8476,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.946515397082658,
|
| 706 |
+
"grad_norm": 0.5444150567054749,
|
| 707 |
+
"learning_rate": 3.260005839155691e-06,
|
| 708 |
+
"loss": 0.7916,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.965964343598055,
|
| 713 |
+
"grad_norm": 0.5643745064735413,
|
| 714 |
+
"learning_rate": 3.152982676455581e-06,
|
| 715 |
+
"loss": 0.7754,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 1.9854132901134522,
|
| 720 |
+
"grad_norm": 0.6249105334281921,
|
| 721 |
+
"learning_rate": 3.046930717948604e-06,
|
| 722 |
+
"loss": 0.8918,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 2.006482982171799,
|
| 727 |
+
"grad_norm": 0.8598921895027161,
|
| 728 |
+
"learning_rate": 2.9419057281939106e-06,
|
| 729 |
+
"loss": 1.2974,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 2.025931928687196,
|
| 734 |
+
"grad_norm": 0.5371376276016235,
|
| 735 |
+
"learning_rate": 2.8379629317468604e-06,
|
| 736 |
+
"loss": 0.7535,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 2.0453808752025933,
|
| 741 |
+
"grad_norm": 0.5264458656311035,
|
| 742 |
+
"learning_rate": 2.7351569841206792e-06,
|
| 743 |
+
"loss": 0.7966,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 2.06482982171799,
|
| 748 |
+
"grad_norm": 0.537636399269104,
|
| 749 |
+
"learning_rate": 2.633541943047334e-06,
|
| 750 |
+
"loss": 0.8117,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 2.0842787682333874,
|
| 755 |
+
"grad_norm": 0.49134597182273865,
|
| 756 |
+
"learning_rate": 2.53317124005273e-06,
|
| 757 |
+
"loss": 0.8327,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 2.1037277147487843,
|
| 762 |
+
"grad_norm": 0.5109895467758179,
|
| 763 |
+
"learning_rate": 2.4340976523611957e-06,
|
| 764 |
+
"loss": 0.7766,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 2.1231766612641816,
|
| 769 |
+
"grad_norm": 0.5269736051559448,
|
| 770 |
+
"learning_rate": 2.3363732751439926e-06,
|
| 771 |
+
"loss": 0.7372,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 2.1426256077795784,
|
| 776 |
+
"grad_norm": 0.5074533820152283,
|
| 777 |
+
"learning_rate": 2.240049494126479e-06,
|
| 778 |
+
"loss": 0.7629,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 2.1620745542949757,
|
| 783 |
+
"grad_norm": 0.5118080973625183,
|
| 784 |
+
"learning_rate": 2.1451769585683196e-06,
|
| 785 |
+
"loss": 0.6913,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 2.1815235008103726,
|
| 790 |
+
"grad_norm": 0.5797163248062134,
|
| 791 |
+
"learning_rate": 2.0518055546309362e-06,
|
| 792 |
+
"loss": 0.8875,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 2.20097244732577,
|
| 797 |
+
"grad_norm": 0.5009273886680603,
|
| 798 |
+
"learning_rate": 1.9599843791462123e-06,
|
| 799 |
+
"loss": 0.8202,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 2.2204213938411668,
|
| 804 |
+
"grad_norm": 0.4513159394264221,
|
| 805 |
+
"learning_rate": 1.8697617138002545e-06,
|
| 806 |
+
"loss": 0.6574,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 2.239870340356564,
|
| 811 |
+
"grad_norm": 0.483067125082016,
|
| 812 |
+
"learning_rate": 1.7811849997457681e-06,
|
| 813 |
+
"loss": 0.766,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 2.259319286871961,
|
| 818 |
+
"grad_norm": 0.5190160274505615,
|
| 819 |
+
"learning_rate": 1.6943008126564164e-06,
|
| 820 |
+
"loss": 0.86,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 2.2787682333873582,
|
| 825 |
+
"grad_norm": 0.45720207691192627,
|
| 826 |
+
"learning_rate": 1.609154838236246e-06,
|
| 827 |
+
"loss": 0.7715,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 2.298217179902755,
|
| 832 |
+
"grad_norm": 0.46229684352874756,
|
| 833 |
+
"learning_rate": 1.5257918481971028e-06,
|
| 834 |
+
"loss": 0.7503,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 2.3176661264181524,
|
| 839 |
+
"grad_norm": 0.4342985153198242,
|
| 840 |
+
"learning_rate": 1.4442556767166371e-06,
|
| 841 |
+
"loss": 0.7868,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 2.3371150729335493,
|
| 846 |
+
"grad_norm": 0.4891180098056793,
|
| 847 |
+
"learning_rate": 1.3645891973892772e-06,
|
| 848 |
+
"loss": 0.7287,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 2.3565640194489466,
|
| 853 |
+
"grad_norm": 0.451238214969635,
|
| 854 |
+
"learning_rate": 1.2868343006823113e-06,
|
| 855 |
+
"loss": 0.7135,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 2.3760129659643434,
|
| 860 |
+
"grad_norm": 0.5156052112579346,
|
| 861 |
+
"learning_rate": 1.211031871908916e-06,
|
| 862 |
+
"loss": 0.8523,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 2.3954619124797407,
|
| 867 |
+
"grad_norm": 0.4339147210121155,
|
| 868 |
+
"learning_rate": 1.137221769729725e-06,
|
| 869 |
+
"loss": 0.7157,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 2.4149108589951376,
|
| 874 |
+
"grad_norm": 0.4493626356124878,
|
| 875 |
+
"learning_rate": 1.065442805194214e-06,
|
| 876 |
+
"loss": 0.8451,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 2.434359805510535,
|
| 881 |
+
"grad_norm": 0.4212321937084198,
|
| 882 |
+
"learning_rate": 9.957327213329687e-07,
|
| 883 |
+
"loss": 0.7459,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 2.4538087520259317,
|
| 888 |
+
"grad_norm": 0.49532240629196167,
|
| 889 |
+
"learning_rate": 9.281281733115288e-07,
|
| 890 |
+
"loss": 0.8074,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 2.473257698541329,
|
| 895 |
+
"grad_norm": 0.4537409543991089,
|
| 896 |
+
"learning_rate": 8.626647091562612e-07,
|
| 897 |
+
"loss": 0.7581,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 2.492706645056726,
|
| 902 |
+
"grad_norm": 0.4133566617965698,
|
| 903 |
+
"learning_rate": 7.993767510623834e-07,
|
| 904 |
+
"loss": 0.761,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 2.512155591572123,
|
| 909 |
+
"grad_norm": 0.47344374656677246,
|
| 910 |
+
"learning_rate": 7.382975772939866e-07,
|
| 911 |
+
"loss": 0.783,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 2.53160453808752,
|
| 916 |
+
"grad_norm": 0.4699486494064331,
|
| 917 |
+
"learning_rate": 6.794593046855613e-07,
|
| 918 |
+
"loss": 0.7739,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 2.5510534846029174,
|
| 923 |
+
"grad_norm": 0.4478330910205841,
|
| 924 |
+
"learning_rate": 6.228928717542205e-07,
|
| 925 |
+
"loss": 0.7713,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 2.5705024311183147,
|
| 930 |
+
"grad_norm": 0.43865975737571716,
|
| 931 |
+
"learning_rate": 5.686280224315189e-07,
|
| 932 |
+
"loss": 0.7643,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 2.5899513776337115,
|
| 937 |
+
"grad_norm": 0.45029687881469727,
|
| 938 |
+
"learning_rate": 5.166932904234101e-07,
|
| 939 |
+
"loss": 0.8228,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 2.6094003241491084,
|
| 944 |
+
"grad_norm": 0.43190592527389526,
|
| 945 |
+
"learning_rate": 4.671159842065698e-07,
|
| 946 |
+
"loss": 0.8042,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 2.6288492706645057,
|
| 951 |
+
"grad_norm": 0.4283352494239807,
|
| 952 |
+
"learning_rate": 4.199221726689634e-07,
|
| 953 |
+
"loss": 0.6469,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 2.648298217179903,
|
| 958 |
+
"grad_norm": 0.444757342338562,
|
| 959 |
+
"learning_rate": 3.751366714022342e-07,
|
| 960 |
+
"loss": 0.84,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 2.6677471636953,
|
| 965 |
+
"grad_norm": 0.4214431941509247,
|
| 966 |
+
"learning_rate": 3.3278302965308593e-07,
|
| 967 |
+
"loss": 0.8341,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 2.6871961102106967,
|
| 972 |
+
"grad_norm": 0.44082775712013245,
|
| 973 |
+
"learning_rate": 2.928835179405548e-07,
|
| 974 |
+
"loss": 0.7816,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 2.706645056726094,
|
| 979 |
+
"grad_norm": 0.4211124777793884,
|
| 980 |
+
"learning_rate": 2.5545911634565266e-07,
|
| 981 |
+
"loss": 0.7624,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 2.7260940032414913,
|
| 986 |
+
"grad_norm": 0.4169267416000366,
|
| 987 |
+
"learning_rate": 2.205295034795596e-07,
|
| 988 |
+
"loss": 0.7452,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 2.745542949756888,
|
| 993 |
+
"grad_norm": 0.4236930012702942,
|
| 994 |
+
"learning_rate": 1.881130461361591e-07,
|
| 995 |
+
"loss": 0.7443,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 2.764991896272285,
|
| 1000 |
+
"grad_norm": 0.4934384822845459,
|
| 1001 |
+
"learning_rate": 1.5822678963435479e-07,
|
| 1002 |
+
"loss": 0.8023,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 2.7844408427876823,
|
| 1007 |
+
"grad_norm": 0.43219056725502014,
|
| 1008 |
+
"learning_rate": 1.3088644885524637e-07,
|
| 1009 |
+
"loss": 0.7411,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 2.8038897893030796,
|
| 1014 |
+
"grad_norm": 0.4079039990901947,
|
| 1015 |
+
"learning_rate": 1.0610639997888917e-07,
|
| 1016 |
+
"loss": 0.742,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 2.8233387358184765,
|
| 1021 |
+
"grad_norm": 0.39644140005111694,
|
| 1022 |
+
"learning_rate": 8.38996729249636e-08,
|
| 1023 |
+
"loss": 0.7157,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 2.8427876823338734,
|
| 1028 |
+
"grad_norm": 0.4225790500640869,
|
| 1029 |
+
"learning_rate": 6.427794450134529e-08,
|
| 1030 |
+
"loss": 0.8331,
|
| 1031 |
+
"step": 146
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 2.8622366288492707,
|
| 1035 |
+
"grad_norm": 0.4538624882698059,
|
| 1036 |
+
"learning_rate": 4.72515322641709e-08,
|
| 1037 |
+
"loss": 0.9018,
|
| 1038 |
+
"step": 147
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 2.881685575364668,
|
| 1042 |
+
"grad_norm": 0.4045908451080322,
|
| 1043 |
+
"learning_rate": 3.282938909263122e-08,
|
| 1044 |
+
"loss": 0.6865,
|
| 1045 |
+
"step": 148
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 2.901134521880065,
|
| 1049 |
+
"grad_norm": 0.4469752609729767,
|
| 1050 |
+
"learning_rate": 2.101909848133743e-08,
|
| 1051 |
+
"loss": 0.7197,
|
| 1052 |
+
"step": 149
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 2.9205834683954617,
|
| 1056 |
+
"grad_norm": 0.520662248134613,
|
| 1057 |
+
"learning_rate": 1.1826870552749669e-08,
|
| 1058 |
+
"loss": 0.8062,
|
| 1059 |
+
"step": 150
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 2.940032414910859,
|
| 1063 |
+
"grad_norm": 0.42809349298477173,
|
| 1064 |
+
"learning_rate": 5.257538791749173e-09,
|
| 1065 |
+
"loss": 0.799,
|
| 1066 |
+
"step": 151
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 2.9594813614262563,
|
| 1070 |
+
"grad_norm": 0.4747503101825714,
|
| 1071 |
+
"learning_rate": 1.3145575040801605e-09,
|
| 1072 |
+
"loss": 0.8033,
|
| 1073 |
+
"step": 152
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 2.978930307941653,
|
| 1077 |
+
"grad_norm": 0.41074883937835693,
|
| 1078 |
+
"learning_rate": 0.0,
|
| 1079 |
+
"loss": 0.6416,
|
| 1080 |
+
"step": 153
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 2.978930307941653,
|
| 1084 |
+
"step": 153,
|
| 1085 |
+
"total_flos": 132192675135488.0,
|
| 1086 |
+
"train_loss": 0.8684253560172187,
|
| 1087 |
+
"train_runtime": 7585.4265,
|
| 1088 |
+
"train_samples_per_second": 1.952,
|
| 1089 |
+
"train_steps_per_second": 0.02
|
| 1090 |
+
}
|
| 1091 |
+
],
|
| 1092 |
+
"logging_steps": 1.0,
|
| 1093 |
+
"max_steps": 153,
|
| 1094 |
+
"num_input_tokens_seen": 0,
|
| 1095 |
+
"num_train_epochs": 3,
|
| 1096 |
+
"save_steps": 500,
|
| 1097 |
+
"stateful_callbacks": {
|
| 1098 |
+
"TrainerControl": {
|
| 1099 |
+
"args": {
|
| 1100 |
+
"should_epoch_stop": false,
|
| 1101 |
+
"should_evaluate": false,
|
| 1102 |
+
"should_log": false,
|
| 1103 |
+
"should_save": true,
|
| 1104 |
+
"should_training_stop": true
|
| 1105 |
+
},
|
| 1106 |
+
"attributes": {}
|
| 1107 |
+
}
|
| 1108 |
+
},
|
| 1109 |
+
"total_flos": 132192675135488.0,
|
| 1110 |
+
"train_batch_size": 1,
|
| 1111 |
+
"trial_name": null,
|
| 1112 |
+
"trial_params": null
|
| 1113 |
+
}
|
training_loss.png
ADDED
|