End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +1057 -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: no_pipeline_science_100k
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# no_pipeline_science_100k
|
| 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: no_pipeline_science_100k
|
|
|
|
| 16 |
|
| 17 |
# no_pipeline_science_100k
|
| 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/no_pipeline_science_100k dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.937369519832985,
|
| 3 |
+
"total_flos": 3.738141667979428e+18,
|
| 4 |
+
"train_loss": 0.2130410626016814,
|
| 5 |
+
"train_runtime": 6079.0514,
|
| 6 |
+
"train_samples_per_second": 12.591,
|
| 7 |
+
"train_steps_per_second": 0.024
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.937369519832985,
|
| 3 |
+
"total_flos": 3.738141667979428e+18,
|
| 4 |
+
"train_loss": 0.2130410626016814,
|
| 5 |
+
"train_runtime": 6079.0514,
|
| 6 |
+
"train_samples_per_second": 12.591,
|
| 7 |
+
"train_steps_per_second": 0.024
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1057 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.937369519832985,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 145,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.033402922755741124,
|
| 13 |
+
"grad_norm": 7.154098089649519,
|
| 14 |
+
"learning_rate": 5.333333333333334e-06,
|
| 15 |
+
"loss": 1.2049,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.06680584551148225,
|
| 20 |
+
"grad_norm": 7.224671814367719,
|
| 21 |
+
"learning_rate": 1.0666666666666667e-05,
|
| 22 |
+
"loss": 1.2046,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.10020876826722339,
|
| 27 |
+
"grad_norm": 5.112010906482035,
|
| 28 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 29 |
+
"loss": 1.1276,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.1336116910229645,
|
| 34 |
+
"grad_norm": 5.240191362417293,
|
| 35 |
+
"learning_rate": 2.1333333333333335e-05,
|
| 36 |
+
"loss": 1.0958,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.16701461377870563,
|
| 41 |
+
"grad_norm": 4.398708169023894,
|
| 42 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 43 |
+
"loss": 1.0242,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.20041753653444677,
|
| 48 |
+
"grad_norm": 4.9473080352678895,
|
| 49 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 50 |
+
"loss": 1.0277,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.23382045929018788,
|
| 55 |
+
"grad_norm": 3.8837845230573835,
|
| 56 |
+
"learning_rate": 3.733333333333334e-05,
|
| 57 |
+
"loss": 0.9755,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.267223382045929,
|
| 62 |
+
"grad_norm": 2.957475416120971,
|
| 63 |
+
"learning_rate": 4.266666666666667e-05,
|
| 64 |
+
"loss": 0.9334,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.30062630480167013,
|
| 69 |
+
"grad_norm": 2.187999537773017,
|
| 70 |
+
"learning_rate": 4.8e-05,
|
| 71 |
+
"loss": 0.9211,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.33402922755741127,
|
| 76 |
+
"grad_norm": 2.3155958654718614,
|
| 77 |
+
"learning_rate": 5.333333333333333e-05,
|
| 78 |
+
"loss": 0.8983,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.3674321503131524,
|
| 83 |
+
"grad_norm": 2.8444701447464436,
|
| 84 |
+
"learning_rate": 5.8666666666666665e-05,
|
| 85 |
+
"loss": 0.8975,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.40083507306889354,
|
| 90 |
+
"grad_norm": 3.0982586639870213,
|
| 91 |
+
"learning_rate": 6.400000000000001e-05,
|
| 92 |
+
"loss": 0.8856,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.4342379958246347,
|
| 97 |
+
"grad_norm": 1.8874954111166966,
|
| 98 |
+
"learning_rate": 6.933333333333334e-05,
|
| 99 |
+
"loss": 0.872,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.46764091858037576,
|
| 104 |
+
"grad_norm": 3.038189077699479,
|
| 105 |
+
"learning_rate": 7.466666666666667e-05,
|
| 106 |
+
"loss": 0.8892,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.5010438413361169,
|
| 111 |
+
"grad_norm": 1.7381979961116139,
|
| 112 |
+
"learning_rate": 8e-05,
|
| 113 |
+
"loss": 0.8535,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.534446764091858,
|
| 118 |
+
"grad_norm": 2188.323143153608,
|
| 119 |
+
"learning_rate": 7.998832056320773e-05,
|
| 120 |
+
"loss": 1.0923,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.5678496868475992,
|
| 125 |
+
"grad_norm": 5.568753243553315,
|
| 126 |
+
"learning_rate": 7.995328907329308e-05,
|
| 127 |
+
"loss": 0.9433,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.6012526096033403,
|
| 132 |
+
"grad_norm": 3.003707178203899,
|
| 133 |
+
"learning_rate": 7.989492598765966e-05,
|
| 134 |
+
"loss": 0.8783,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.6346555323590815,
|
| 139 |
+
"grad_norm": 3.3787729580945367,
|
| 140 |
+
"learning_rate": 7.981326538870596e-05,
|
| 141 |
+
"loss": 0.8657,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.6680584551148225,
|
| 146 |
+
"grad_norm": 3.0096085489081923,
|
| 147 |
+
"learning_rate": 7.970835496392216e-05,
|
| 148 |
+
"loss": 0.8705,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.7014613778705637,
|
| 153 |
+
"grad_norm": 2.2251853165136186,
|
| 154 |
+
"learning_rate": 7.958025597804205e-05,
|
| 155 |
+
"loss": 0.8591,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.7348643006263048,
|
| 160 |
+
"grad_norm": 1.393655838420696,
|
| 161 |
+
"learning_rate": 7.942904323726604e-05,
|
| 162 |
+
"loss": 0.8202,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.7682672233820459,
|
| 167 |
+
"grad_norm": 1.709595774468825,
|
| 168 |
+
"learning_rate": 7.925480504557654e-05,
|
| 169 |
+
"loss": 0.8239,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.8016701461377871,
|
| 174 |
+
"grad_norm": 1.04923819217978,
|
| 175 |
+
"learning_rate": 7.90576431531709e-05,
|
| 176 |
+
"loss": 0.8236,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.8350730688935282,
|
| 181 |
+
"grad_norm": 1.4676306786694173,
|
| 182 |
+
"learning_rate": 7.883767269704209e-05,
|
| 183 |
+
"loss": 0.8083,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.8684759916492694,
|
| 188 |
+
"grad_norm": 417.78005391043996,
|
| 189 |
+
"learning_rate": 7.859502213374207e-05,
|
| 190 |
+
"loss": 1.1719,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.9018789144050104,
|
| 195 |
+
"grad_norm": 12.203128331470229,
|
| 196 |
+
"learning_rate": 7.832983316436666e-05,
|
| 197 |
+
"loss": 0.8597,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.9352818371607515,
|
| 202 |
+
"grad_norm": 4.957392164656034,
|
| 203 |
+
"learning_rate": 7.804226065180615e-05,
|
| 204 |
+
"loss": 0.9382,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.9686847599164927,
|
| 209 |
+
"grad_norm": 10.61998316626802,
|
| 210 |
+
"learning_rate": 7.773247253030973e-05,
|
| 211 |
+
"loss": 0.9939,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.0083507306889352,
|
| 216 |
+
"grad_norm": 54.87377316789775,
|
| 217 |
+
"learning_rate": 7.740064970741661e-05,
|
| 218 |
+
"loss": 0.8724,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.0417536534446765,
|
| 223 |
+
"grad_norm": 88.85368950052036,
|
| 224 |
+
"learning_rate": 7.704698595831107e-05,
|
| 225 |
+
"loss": 0.9805,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.0751565762004176,
|
| 230 |
+
"grad_norm": 12.07917493536492,
|
| 231 |
+
"learning_rate": 7.667168781266331e-05,
|
| 232 |
+
"loss": 0.9689,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.1085594989561587,
|
| 237 |
+
"grad_norm": 30.730151095536375,
|
| 238 |
+
"learning_rate": 7.627497443402182e-05,
|
| 239 |
+
"loss": 1.0908,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.1419624217118998,
|
| 244 |
+
"grad_norm": 4.303465706734318,
|
| 245 |
+
"learning_rate": 7.585707749182816e-05,
|
| 246 |
+
"loss": 0.8883,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 1.1753653444676408,
|
| 251 |
+
"grad_norm": 1.3597826636785535,
|
| 252 |
+
"learning_rate": 7.541824102612839e-05,
|
| 253 |
+
"loss": 0.8376,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.2087682672233822,
|
| 258 |
+
"grad_norm": 2.028071696746282,
|
| 259 |
+
"learning_rate": 7.495872130506072e-05,
|
| 260 |
+
"loss": 0.8018,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.2421711899791232,
|
| 265 |
+
"grad_norm": 1.5668710744698326,
|
| 266 |
+
"learning_rate": 7.447878667520198e-05,
|
| 267 |
+
"loss": 0.7901,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.2755741127348643,
|
| 272 |
+
"grad_norm": 0.9166659557892114,
|
| 273 |
+
"learning_rate": 7.397871740486085e-05,
|
| 274 |
+
"loss": 0.7699,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.3089770354906054,
|
| 279 |
+
"grad_norm": 8.207728871032339,
|
| 280 |
+
"learning_rate": 7.345880552040907e-05,
|
| 281 |
+
"loss": 0.7735,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.3423799582463465,
|
| 286 |
+
"grad_norm": 2.508524585534657,
|
| 287 |
+
"learning_rate": 7.291935463574626e-05,
|
| 288 |
+
"loss": 0.8447,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.3757828810020878,
|
| 293 |
+
"grad_norm": 1.364586902470756,
|
| 294 |
+
"learning_rate": 7.236067977499791e-05,
|
| 295 |
+
"loss": 0.7856,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.4091858037578289,
|
| 300 |
+
"grad_norm": 1.8720653087352772,
|
| 301 |
+
"learning_rate": 7.178310718855018e-05,
|
| 302 |
+
"loss": 0.7829,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.44258872651357,
|
| 307 |
+
"grad_norm": 1.8178558573775088,
|
| 308 |
+
"learning_rate": 7.11869741625289e-05,
|
| 309 |
+
"loss": 0.7737,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.475991649269311,
|
| 314 |
+
"grad_norm": 1.6638629849138615,
|
| 315 |
+
"learning_rate": 7.057262882183393e-05,
|
| 316 |
+
"loss": 0.7737,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.5093945720250521,
|
| 321 |
+
"grad_norm": 1.1958951695778888,
|
| 322 |
+
"learning_rate": 6.994042992684406e-05,
|
| 323 |
+
"loss": 0.7499,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.5427974947807934,
|
| 328 |
+
"grad_norm": 1.1237749762548175,
|
| 329 |
+
"learning_rate": 6.929074666391095e-05,
|
| 330 |
+
"loss": 0.7457,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.5762004175365343,
|
| 335 |
+
"grad_norm": 0.9523363043794499,
|
| 336 |
+
"learning_rate": 6.862395842976484e-05,
|
| 337 |
+
"loss": 0.7449,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.6096033402922756,
|
| 342 |
+
"grad_norm": 0.7794493625394828,
|
| 343 |
+
"learning_rate": 6.79404546099575e-05,
|
| 344 |
+
"loss": 0.7471,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.6430062630480167,
|
| 349 |
+
"grad_norm": 2.1007938107258224,
|
| 350 |
+
"learning_rate": 6.724063435147189e-05,
|
| 351 |
+
"loss": 0.738,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.6764091858037578,
|
| 356 |
+
"grad_norm": 0.8397590052899939,
|
| 357 |
+
"learning_rate": 6.652490632963182e-05,
|
| 358 |
+
"loss": 0.7366,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.709812108559499,
|
| 363 |
+
"grad_norm": 1.5244169148841136,
|
| 364 |
+
"learning_rate": 6.579368850944683e-05,
|
| 365 |
+
"loss": 0.7518,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.7432150313152401,
|
| 370 |
+
"grad_norm": 0.97500410064134,
|
| 371 |
+
"learning_rate": 6.504740790153255e-05,
|
| 372 |
+
"loss": 0.7365,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 1.7766179540709812,
|
| 377 |
+
"grad_norm": 1.833109071141926,
|
| 378 |
+
"learning_rate": 6.428650031274845e-05,
|
| 379 |
+
"loss": 0.7327,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 1.8100208768267223,
|
| 384 |
+
"grad_norm": 1.4707510085946327,
|
| 385 |
+
"learning_rate": 6.351141009169893e-05,
|
| 386 |
+
"loss": 0.7227,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.8434237995824634,
|
| 391 |
+
"grad_norm": 1.2363917202252765,
|
| 392 |
+
"learning_rate": 6.272258986924624e-05,
|
| 393 |
+
"loss": 0.7405,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 1.8768267223382047,
|
| 398 |
+
"grad_norm": 1.0298920741813498,
|
| 399 |
+
"learning_rate": 6.192050029418682e-05,
|
| 400 |
+
"loss": 0.7241,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 1.9102296450939458,
|
| 405 |
+
"grad_norm": 0.9097363351471279,
|
| 406 |
+
"learning_rate": 6.110560976424531e-05,
|
| 407 |
+
"loss": 0.7167,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.9436325678496869,
|
| 412 |
+
"grad_norm": 0.8471695952793523,
|
| 413 |
+
"learning_rate": 6.027839415254362e-05,
|
| 414 |
+
"loss": 0.7181,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 1.977035490605428,
|
| 419 |
+
"grad_norm": 0.6602662698524506,
|
| 420 |
+
"learning_rate": 5.943933652970424e-05,
|
| 421 |
+
"loss": 0.7088,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 2.0167014613778704,
|
| 426 |
+
"grad_norm": 0.624041177687339,
|
| 427 |
+
"learning_rate": 5.858892688175075e-05,
|
| 428 |
+
"loss": 0.6922,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 2.0501043841336117,
|
| 433 |
+
"grad_norm": 0.731560229530671,
|
| 434 |
+
"learning_rate": 5.772766182396966e-05,
|
| 435 |
+
"loss": 0.6655,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 2.083507306889353,
|
| 440 |
+
"grad_norm": 0.5160825456760252,
|
| 441 |
+
"learning_rate": 5.685604431090117e-05,
|
| 442 |
+
"loss": 0.6624,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 2.116910229645094,
|
| 447 |
+
"grad_norm": 0.6466642583190281,
|
| 448 |
+
"learning_rate": 5.597458334262782e-05,
|
| 449 |
+
"loss": 0.6474,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 2.150313152400835,
|
| 454 |
+
"grad_norm": 0.6905839273768964,
|
| 455 |
+
"learning_rate": 5.508379366753282e-05,
|
| 456 |
+
"loss": 0.6512,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 2.183716075156576,
|
| 461 |
+
"grad_norm": 0.3760316450742919,
|
| 462 |
+
"learning_rate": 5.4184195481701425e-05,
|
| 463 |
+
"loss": 0.6523,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.2171189979123174,
|
| 468 |
+
"grad_norm": 0.606234562718693,
|
| 469 |
+
"learning_rate": 5.3276314125141144e-05,
|
| 470 |
+
"loss": 0.6487,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 2.2505219206680582,
|
| 475 |
+
"grad_norm": 0.44809718292050676,
|
| 476 |
+
"learning_rate": 5.23606797749979e-05,
|
| 477 |
+
"loss": 0.649,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 2.2839248434237995,
|
| 482 |
+
"grad_norm": 0.40244410097202155,
|
| 483 |
+
"learning_rate": 5.1437827135947566e-05,
|
| 484 |
+
"loss": 0.6468,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 2.317327766179541,
|
| 489 |
+
"grad_norm": 0.359719180741915,
|
| 490 |
+
"learning_rate": 5.050829512794348e-05,
|
| 491 |
+
"loss": 0.6409,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 2.3507306889352817,
|
| 496 |
+
"grad_norm": 0.40415638024369727,
|
| 497 |
+
"learning_rate": 4.9572626571502316e-05,
|
| 498 |
+
"loss": 0.639,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 2.384133611691023,
|
| 503 |
+
"grad_norm": 0.3340843503248373,
|
| 504 |
+
"learning_rate": 4.8631367870712254e-05,
|
| 505 |
+
"loss": 0.6326,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 2.4175365344467643,
|
| 510 |
+
"grad_norm": 0.3262882595570267,
|
| 511 |
+
"learning_rate": 4.768506869414834e-05,
|
| 512 |
+
"loss": 0.6298,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 2.450939457202505,
|
| 517 |
+
"grad_norm": 0.3253891492249243,
|
| 518 |
+
"learning_rate": 4.6734281653881536e-05,
|
| 519 |
+
"loss": 0.6326,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 2.4843423799582465,
|
| 524 |
+
"grad_norm": 0.35311540573233735,
|
| 525 |
+
"learning_rate": 4.577956198276886e-05,
|
| 526 |
+
"loss": 0.6291,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 2.5177453027139873,
|
| 531 |
+
"grad_norm": 0.3440383701499157,
|
| 532 |
+
"learning_rate": 4.4821467210212924e-05,
|
| 533 |
+
"loss": 0.6332,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 2.5511482254697286,
|
| 538 |
+
"grad_norm": 0.30978369513311105,
|
| 539 |
+
"learning_rate": 4.386055683658061e-05,
|
| 540 |
+
"loss": 0.6408,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 2.5845511482254695,
|
| 545 |
+
"grad_norm": 0.3823149004105222,
|
| 546 |
+
"learning_rate": 4.2897392006470503e-05,
|
| 547 |
+
"loss": 0.6246,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 2.617954070981211,
|
| 552 |
+
"grad_norm": 0.2810880790539587,
|
| 553 |
+
"learning_rate": 4.1932535181020286e-05,
|
| 554 |
+
"loss": 0.6293,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 2.651356993736952,
|
| 559 |
+
"grad_norm": 0.2835535239751324,
|
| 560 |
+
"learning_rate": 4.096654980944529e-05,
|
| 561 |
+
"loss": 0.6252,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 2.684759916492693,
|
| 566 |
+
"grad_norm": 0.336833154001104,
|
| 567 |
+
"learning_rate": 4e-05,
|
| 568 |
+
"loss": 0.6305,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 2.7181628392484343,
|
| 573 |
+
"grad_norm": 0.23274589850456745,
|
| 574 |
+
"learning_rate": 3.903345019055472e-05,
|
| 575 |
+
"loss": 0.6298,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 2.7515657620041756,
|
| 580 |
+
"grad_norm": 0.2420684628004819,
|
| 581 |
+
"learning_rate": 3.806746481897973e-05,
|
| 582 |
+
"loss": 0.6241,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 2.7849686847599164,
|
| 587 |
+
"grad_norm": 0.23622928619950834,
|
| 588 |
+
"learning_rate": 3.710260799352951e-05,
|
| 589 |
+
"loss": 0.6167,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 2.8183716075156577,
|
| 594 |
+
"grad_norm": 0.21286687906297902,
|
| 595 |
+
"learning_rate": 3.6139443163419394e-05,
|
| 596 |
+
"loss": 0.6268,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 2.8517745302713986,
|
| 601 |
+
"grad_norm": 0.20113400910479923,
|
| 602 |
+
"learning_rate": 3.517853278978708e-05,
|
| 603 |
+
"loss": 0.622,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 2.88517745302714,
|
| 608 |
+
"grad_norm": 0.19296938971649688,
|
| 609 |
+
"learning_rate": 3.422043801723116e-05,
|
| 610 |
+
"loss": 0.6167,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 2.9185803757828808,
|
| 615 |
+
"grad_norm": 0.17640926051127553,
|
| 616 |
+
"learning_rate": 3.3265718346118464e-05,
|
| 617 |
+
"loss": 0.6251,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 2.951983298538622,
|
| 622 |
+
"grad_norm": 0.17760201524918323,
|
| 623 |
+
"learning_rate": 3.231493130585167e-05,
|
| 624 |
+
"loss": 0.6195,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 2.9853862212943634,
|
| 629 |
+
"grad_norm": 0.18267169419590248,
|
| 630 |
+
"learning_rate": 3.136863212928776e-05,
|
| 631 |
+
"loss": 0.6214,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 3.1002087682672235,
|
| 636 |
+
"grad_norm": 0.2479134339023779,
|
| 637 |
+
"learning_rate": 3.0427373428497704e-05,
|
| 638 |
+
"loss": 0.5792,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 3.1336116910229643,
|
| 643 |
+
"grad_norm": 0.17829804990091588,
|
| 644 |
+
"learning_rate": 2.9491704872056525e-05,
|
| 645 |
+
"loss": 0.571,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 3.1670146137787056,
|
| 650 |
+
"grad_norm": 0.2102957726786887,
|
| 651 |
+
"learning_rate": 2.8562172864052437e-05,
|
| 652 |
+
"loss": 0.5665,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 3.200417536534447,
|
| 657 |
+
"grad_norm": 0.18138996143773695,
|
| 658 |
+
"learning_rate": 2.7639320225002108e-05,
|
| 659 |
+
"loss": 0.5734,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 3.233820459290188,
|
| 664 |
+
"grad_norm": 0.18231114685106467,
|
| 665 |
+
"learning_rate": 2.6723685874858873e-05,
|
| 666 |
+
"loss": 0.5665,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 3.267223382045929,
|
| 671 |
+
"grad_norm": 0.1891068826294468,
|
| 672 |
+
"learning_rate": 2.5815804518298575e-05,
|
| 673 |
+
"loss": 0.5649,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 3.30062630480167,
|
| 678 |
+
"grad_norm": 0.1449193634467542,
|
| 679 |
+
"learning_rate": 2.4916206332467184e-05,
|
| 680 |
+
"loss": 0.5626,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 3.3340292275574113,
|
| 685 |
+
"grad_norm": 0.17521384625415576,
|
| 686 |
+
"learning_rate": 2.4025416657372186e-05,
|
| 687 |
+
"loss": 0.5672,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 3.3674321503131526,
|
| 692 |
+
"grad_norm": 0.17060274829594732,
|
| 693 |
+
"learning_rate": 2.3143955689098844e-05,
|
| 694 |
+
"loss": 0.5701,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 3.4008350730688934,
|
| 699 |
+
"grad_norm": 0.16427792254004098,
|
| 700 |
+
"learning_rate": 2.2272338176030354e-05,
|
| 701 |
+
"loss": 0.5648,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 3.4342379958246347,
|
| 706 |
+
"grad_norm": 0.16851785214921267,
|
| 707 |
+
"learning_rate": 2.141107311824926e-05,
|
| 708 |
+
"loss": 0.5637,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 3.4676409185803756,
|
| 713 |
+
"grad_norm": 0.1647295715319099,
|
| 714 |
+
"learning_rate": 2.056066347029576e-05,
|
| 715 |
+
"loss": 0.5698,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 3.501043841336117,
|
| 720 |
+
"grad_norm": 0.14383360405355872,
|
| 721 |
+
"learning_rate": 1.9721605847456397e-05,
|
| 722 |
+
"loss": 0.5678,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 3.534446764091858,
|
| 727 |
+
"grad_norm": 0.16369393007489977,
|
| 728 |
+
"learning_rate": 1.8894390235754686e-05,
|
| 729 |
+
"loss": 0.5687,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 3.567849686847599,
|
| 734 |
+
"grad_norm": 0.1484533364671656,
|
| 735 |
+
"learning_rate": 1.807949970581321e-05,
|
| 736 |
+
"loss": 0.5612,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 3.6012526096033404,
|
| 741 |
+
"grad_norm": 0.13327395767499348,
|
| 742 |
+
"learning_rate": 1.7277410130753775e-05,
|
| 743 |
+
"loss": 0.5621,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 3.6346555323590817,
|
| 748 |
+
"grad_norm": 0.14483989970799924,
|
| 749 |
+
"learning_rate": 1.648858990830108e-05,
|
| 750 |
+
"loss": 0.5602,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 3.6680584551148225,
|
| 755 |
+
"grad_norm": 0.11501467177953302,
|
| 756 |
+
"learning_rate": 1.5713499687251554e-05,
|
| 757 |
+
"loss": 0.5625,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 3.701461377870564,
|
| 762 |
+
"grad_norm": 0.12471522633663724,
|
| 763 |
+
"learning_rate": 1.4952592098467453e-05,
|
| 764 |
+
"loss": 0.5566,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 3.7348643006263047,
|
| 769 |
+
"grad_norm": 0.12841415317626956,
|
| 770 |
+
"learning_rate": 1.4206311490553187e-05,
|
| 771 |
+
"loss": 0.5563,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 3.768267223382046,
|
| 776 |
+
"grad_norm": 0.13024977809323665,
|
| 777 |
+
"learning_rate": 1.3475093670368202e-05,
|
| 778 |
+
"loss": 0.5642,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 3.801670146137787,
|
| 783 |
+
"grad_norm": 0.12141142140280577,
|
| 784 |
+
"learning_rate": 1.275936564852811e-05,
|
| 785 |
+
"loss": 0.5619,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 3.835073068893528,
|
| 790 |
+
"grad_norm": 0.1189681977822036,
|
| 791 |
+
"learning_rate": 1.2059545390042526e-05,
|
| 792 |
+
"loss": 0.5627,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 3.8684759916492695,
|
| 797 |
+
"grad_norm": 0.11637565722872692,
|
| 798 |
+
"learning_rate": 1.1376041570235162e-05,
|
| 799 |
+
"loss": 0.5597,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 3.9018789144050103,
|
| 804 |
+
"grad_norm": 0.11126444342562675,
|
| 805 |
+
"learning_rate": 1.070925333608907e-05,
|
| 806 |
+
"loss": 0.5646,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 3.9352818371607516,
|
| 811 |
+
"grad_norm": 0.11144727795080511,
|
| 812 |
+
"learning_rate": 1.0059570073155953e-05,
|
| 813 |
+
"loss": 0.5663,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 3.968684759916493,
|
| 818 |
+
"grad_norm": 0.11568625785765184,
|
| 819 |
+
"learning_rate": 9.427371178166065e-06,
|
| 820 |
+
"loss": 0.5628,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 4.002087682672234,
|
| 825 |
+
"grad_norm": 0.1172051146855964,
|
| 826 |
+
"learning_rate": 8.81302583747111e-06,
|
| 827 |
+
"loss": 0.5657,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 4.035490605427975,
|
| 832 |
+
"grad_norm": 0.1386962246589997,
|
| 833 |
+
"learning_rate": 8.216892811449834e-06,
|
| 834 |
+
"loss": 0.5431,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 4.068893528183716,
|
| 839 |
+
"grad_norm": 0.12227065820674828,
|
| 840 |
+
"learning_rate": 7.639320225002106e-06,
|
| 841 |
+
"loss": 0.5386,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 4.102296450939457,
|
| 846 |
+
"grad_norm": 0.11676189189940173,
|
| 847 |
+
"learning_rate": 7.080645364253747e-06,
|
| 848 |
+
"loss": 0.5341,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 4.135699373695198,
|
| 853 |
+
"grad_norm": 0.1086671391408473,
|
| 854 |
+
"learning_rate": 6.541194479590931e-06,
|
| 855 |
+
"loss": 0.5472,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 4.16910229645094,
|
| 860 |
+
"grad_norm": 0.11780635228612878,
|
| 861 |
+
"learning_rate": 6.021282595139167e-06,
|
| 862 |
+
"loss": 0.5376,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 4.202505219206681,
|
| 867 |
+
"grad_norm": 0.11122819389457546,
|
| 868 |
+
"learning_rate": 5.521213324798029e-06,
|
| 869 |
+
"loss": 0.5405,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 4.235908141962422,
|
| 874 |
+
"grad_norm": 0.11302950909483094,
|
| 875 |
+
"learning_rate": 5.0412786949392845e-06,
|
| 876 |
+
"loss": 0.5389,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 4.2693110647181625,
|
| 881 |
+
"grad_norm": 0.10897006989347469,
|
| 882 |
+
"learning_rate": 4.581758973871609e-06,
|
| 883 |
+
"loss": 0.5443,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 4.302713987473904,
|
| 888 |
+
"grad_norm": 0.10317913683812792,
|
| 889 |
+
"learning_rate": 4.142922508171849e-06,
|
| 890 |
+
"loss": 0.5363,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 4.336116910229645,
|
| 895 |
+
"grad_norm": 0.10003486708202455,
|
| 896 |
+
"learning_rate": 3.7250255659781844e-06,
|
| 897 |
+
"loss": 0.5364,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 4.369519832985386,
|
| 902 |
+
"grad_norm": 0.1071731871255614,
|
| 903 |
+
"learning_rate": 3.3283121873367043e-06,
|
| 904 |
+
"loss": 0.5432,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 4.402922755741128,
|
| 909 |
+
"grad_norm": 0.10539727253992291,
|
| 910 |
+
"learning_rate": 2.9530140416889465e-06,
|
| 911 |
+
"loss": 0.5373,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 4.4363256784968685,
|
| 916 |
+
"grad_norm": 0.09606764766200912,
|
| 917 |
+
"learning_rate": 2.5993502925834115e-06,
|
| 918 |
+
"loss": 0.5333,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 4.469728601252609,
|
| 923 |
+
"grad_norm": 0.09219554498498256,
|
| 924 |
+
"learning_rate": 2.2675274696902737e-06,
|
| 925 |
+
"loss": 0.5315,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 4.503131524008351,
|
| 930 |
+
"grad_norm": 0.08960509523269163,
|
| 931 |
+
"learning_rate": 1.957739348193859e-06,
|
| 932 |
+
"loss": 0.5334,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 4.536534446764092,
|
| 937 |
+
"grad_norm": 0.09160224849384657,
|
| 938 |
+
"learning_rate": 1.670166835633351e-06,
|
| 939 |
+
"loss": 0.5384,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 4.569937369519833,
|
| 944 |
+
"grad_norm": 0.08852713488345453,
|
| 945 |
+
"learning_rate": 1.4049778662579462e-06,
|
| 946 |
+
"loss": 0.53,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 4.603340292275574,
|
| 951 |
+
"grad_norm": 0.09132315616256415,
|
| 952 |
+
"learning_rate": 1.1623273029579195e-06,
|
| 953 |
+
"loss": 0.538,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 4.6367432150313155,
|
| 958 |
+
"grad_norm": 0.09194633813127549,
|
| 959 |
+
"learning_rate": 9.423568468291156e-07,
|
| 960 |
+
"loss": 0.541,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 4.670146137787056,
|
| 965 |
+
"grad_norm": 0.09237238332398756,
|
| 966 |
+
"learning_rate": 7.451949544234627e-07,
|
| 967 |
+
"loss": 0.5379,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 4.703549060542797,
|
| 972 |
+
"grad_norm": 0.08974432368849375,
|
| 973 |
+
"learning_rate": 5.709567627339674e-07,
|
| 974 |
+
"loss": 0.5443,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 4.736951983298539,
|
| 979 |
+
"grad_norm": 0.09013165116820136,
|
| 980 |
+
"learning_rate": 4.1974402195795514e-07,
|
| 981 |
+
"loss": 0.535,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 4.77035490605428,
|
| 986 |
+
"grad_norm": 0.09022158123863006,
|
| 987 |
+
"learning_rate": 2.916450360778411e-07,
|
| 988 |
+
"loss": 0.5333,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 4.803757828810021,
|
| 993 |
+
"grad_norm": 0.08981410735542258,
|
| 994 |
+
"learning_rate": 1.867346112940549e-07,
|
| 995 |
+
"loss": 0.5462,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 4.8371607515657615,
|
| 1000 |
+
"grad_norm": 0.09141559902413697,
|
| 1001 |
+
"learning_rate": 1.0507401234035819e-07,
|
| 1002 |
+
"loss": 0.5377,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 4.870563674321503,
|
| 1007 |
+
"grad_norm": 0.08951832053531815,
|
| 1008 |
+
"learning_rate": 4.6710926706934336e-08,
|
| 1009 |
+
"loss": 0.5305,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 4.903966597077244,
|
| 1014 |
+
"grad_norm": 0.08926873218925392,
|
| 1015 |
+
"learning_rate": 1.1679436792282339e-08,
|
| 1016 |
+
"loss": 0.54,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 4.937369519832985,
|
| 1021 |
+
"grad_norm": 0.08723888890212035,
|
| 1022 |
+
"learning_rate": 0.0,
|
| 1023 |
+
"loss": 0.54,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 4.937369519832985,
|
| 1028 |
+
"step": 145,
|
| 1029 |
+
"total_flos": 3.738141667979428e+18,
|
| 1030 |
+
"train_loss": 0.2130410626016814,
|
| 1031 |
+
"train_runtime": 6079.0514,
|
| 1032 |
+
"train_samples_per_second": 12.591,
|
| 1033 |
+
"train_steps_per_second": 0.024
|
| 1034 |
+
}
|
| 1035 |
+
],
|
| 1036 |
+
"logging_steps": 1,
|
| 1037 |
+
"max_steps": 145,
|
| 1038 |
+
"num_input_tokens_seen": 0,
|
| 1039 |
+
"num_train_epochs": 5,
|
| 1040 |
+
"save_steps": 500,
|
| 1041 |
+
"stateful_callbacks": {
|
| 1042 |
+
"TrainerControl": {
|
| 1043 |
+
"args": {
|
| 1044 |
+
"should_epoch_stop": false,
|
| 1045 |
+
"should_evaluate": false,
|
| 1046 |
+
"should_log": false,
|
| 1047 |
+
"should_save": true,
|
| 1048 |
+
"should_training_stop": true
|
| 1049 |
+
},
|
| 1050 |
+
"attributes": {}
|
| 1051 |
+
}
|
| 1052 |
+
},
|
| 1053 |
+
"total_flos": 3.738141667979428e+18,
|
| 1054 |
+
"train_batch_size": 1,
|
| 1055 |
+
"trial_name": null,
|
| 1056 |
+
"trial_params": null
|
| 1057 |
+
}
|
training_loss.png
ADDED
|