End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +1092 -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: 316_globalbatchsize32_lr2e5_epochs15
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# 316_globalbatchsize32_lr2e5_epochs15
|
| 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: 316_globalbatchsize32_lr2e5_epochs15
|
|
|
|
| 16 |
|
| 17 |
# 316_globalbatchsize32_lr2e5_epochs15
|
| 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/openthoughts_316 dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 15.0,
|
| 3 |
+
"total_flos": 8.481547119440691e+16,
|
| 4 |
+
"train_loss": 0.1808963591993476,
|
| 5 |
+
"train_runtime": 6243.0048,
|
| 6 |
+
"train_samples_per_second": 0.759,
|
| 7 |
+
"train_steps_per_second": 0.024
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 15.0,
|
| 3 |
+
"total_flos": 8.481547119440691e+16,
|
| 4 |
+
"train_loss": 0.1808963591993476,
|
| 5 |
+
"train_runtime": 6243.0048,
|
| 6 |
+
"train_samples_per_second": 0.759,
|
| 7 |
+
"train_steps_per_second": 0.024
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1092 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 15.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 150,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.1,
|
| 13 |
+
"grad_norm": 5.456483190001166,
|
| 14 |
+
"learning_rate": 1.3333333333333334e-06,
|
| 15 |
+
"loss": 0.8054,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.2,
|
| 20 |
+
"grad_norm": 5.759462172287989,
|
| 21 |
+
"learning_rate": 2.666666666666667e-06,
|
| 22 |
+
"loss": 0.8566,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.3,
|
| 27 |
+
"grad_norm": 5.647493114157845,
|
| 28 |
+
"learning_rate": 4.000000000000001e-06,
|
| 29 |
+
"loss": 0.8604,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.4,
|
| 34 |
+
"grad_norm": 5.062774089894794,
|
| 35 |
+
"learning_rate": 5.333333333333334e-06,
|
| 36 |
+
"loss": 0.8926,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.5,
|
| 41 |
+
"grad_norm": 2.742178622247567,
|
| 42 |
+
"learning_rate": 6.666666666666667e-06,
|
| 43 |
+
"loss": 0.8096,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.6,
|
| 48 |
+
"grad_norm": 2.094214554696164,
|
| 49 |
+
"learning_rate": 8.000000000000001e-06,
|
| 50 |
+
"loss": 0.8214,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.7,
|
| 55 |
+
"grad_norm": 4.578250564308243,
|
| 56 |
+
"learning_rate": 9.333333333333334e-06,
|
| 57 |
+
"loss": 0.8371,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.8,
|
| 62 |
+
"grad_norm": 4.914224760901885,
|
| 63 |
+
"learning_rate": 1.0666666666666667e-05,
|
| 64 |
+
"loss": 0.8386,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.9,
|
| 69 |
+
"grad_norm": 5.104636711377158,
|
| 70 |
+
"learning_rate": 1.2e-05,
|
| 71 |
+
"loss": 0.768,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 1.0,
|
| 76 |
+
"grad_norm": 4.741500054760724,
|
| 77 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 78 |
+
"loss": 0.7601,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 1.1,
|
| 83 |
+
"grad_norm": 3.0673965583798566,
|
| 84 |
+
"learning_rate": 1.4666666666666666e-05,
|
| 85 |
+
"loss": 0.6711,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.2,
|
| 90 |
+
"grad_norm": 2.3130829408950597,
|
| 91 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 92 |
+
"loss": 0.6996,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.3,
|
| 97 |
+
"grad_norm": 2.4521476942644096,
|
| 98 |
+
"learning_rate": 1.7333333333333336e-05,
|
| 99 |
+
"loss": 0.6883,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.4,
|
| 104 |
+
"grad_norm": 2.060188555365567,
|
| 105 |
+
"learning_rate": 1.866666666666667e-05,
|
| 106 |
+
"loss": 0.6712,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.5,
|
| 111 |
+
"grad_norm": 1.5880322665772053,
|
| 112 |
+
"learning_rate": 2e-05,
|
| 113 |
+
"loss": 0.6361,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.6,
|
| 118 |
+
"grad_norm": 1.5065788447188164,
|
| 119 |
+
"learning_rate": 1.999729241179462e-05,
|
| 120 |
+
"loss": 0.6229,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.7,
|
| 125 |
+
"grad_norm": 1.846665331936718,
|
| 126 |
+
"learning_rate": 1.998917111338525e-05,
|
| 127 |
+
"loss": 0.6138,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.8,
|
| 132 |
+
"grad_norm": 1.397736554007089,
|
| 133 |
+
"learning_rate": 1.9975640502598243e-05,
|
| 134 |
+
"loss": 0.6224,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.9,
|
| 139 |
+
"grad_norm": 1.250044207797159,
|
| 140 |
+
"learning_rate": 1.9956707906498046e-05,
|
| 141 |
+
"loss": 0.5978,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 2.0,
|
| 146 |
+
"grad_norm": 1.1978733008887823,
|
| 147 |
+
"learning_rate": 1.9932383577419432e-05,
|
| 148 |
+
"loss": 0.5691,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 2.1,
|
| 153 |
+
"grad_norm": 1.3616776529906953,
|
| 154 |
+
"learning_rate": 1.9902680687415704e-05,
|
| 155 |
+
"loss": 0.5554,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 2.2,
|
| 160 |
+
"grad_norm": 1.097602231035553,
|
| 161 |
+
"learning_rate": 1.9867615321125796e-05,
|
| 162 |
+
"loss": 0.5255,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 2.3,
|
| 167 |
+
"grad_norm": 1.0111196181375406,
|
| 168 |
+
"learning_rate": 1.9827206467064133e-05,
|
| 169 |
+
"loss": 0.4776,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.4,
|
| 174 |
+
"grad_norm": 0.9955327255126635,
|
| 175 |
+
"learning_rate": 1.9781476007338058e-05,
|
| 176 |
+
"loss": 0.4818,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 2.5,
|
| 181 |
+
"grad_norm": 0.9140689471373215,
|
| 182 |
+
"learning_rate": 1.973044870579824e-05,
|
| 183 |
+
"loss": 0.4888,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 2.6,
|
| 188 |
+
"grad_norm": 0.8950005541922588,
|
| 189 |
+
"learning_rate": 1.967415219462864e-05,
|
| 190 |
+
"loss": 0.4678,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 2.7,
|
| 195 |
+
"grad_norm": 0.9264924413390109,
|
| 196 |
+
"learning_rate": 1.961261695938319e-05,
|
| 197 |
+
"loss": 0.4916,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 2.8,
|
| 202 |
+
"grad_norm": 0.9016767081799504,
|
| 203 |
+
"learning_rate": 1.954587632247732e-05,
|
| 204 |
+
"loss": 0.4914,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 2.9,
|
| 209 |
+
"grad_norm": 0.8711206171973317,
|
| 210 |
+
"learning_rate": 1.9473966425143292e-05,
|
| 211 |
+
"loss": 0.4279,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 3.0,
|
| 216 |
+
"grad_norm": 0.965284052630944,
|
| 217 |
+
"learning_rate": 1.9396926207859085e-05,
|
| 218 |
+
"loss": 0.4769,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 3.1,
|
| 223 |
+
"grad_norm": 0.8710629657905165,
|
| 224 |
+
"learning_rate": 1.9314797389261426e-05,
|
| 225 |
+
"loss": 0.3557,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 3.2,
|
| 230 |
+
"grad_norm": 0.7829249544686165,
|
| 231 |
+
"learning_rate": 1.9227624443554425e-05,
|
| 232 |
+
"loss": 0.3159,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 3.3,
|
| 237 |
+
"grad_norm": 1.1372489228974627,
|
| 238 |
+
"learning_rate": 1.913545457642601e-05,
|
| 239 |
+
"loss": 0.3496,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 3.4,
|
| 244 |
+
"grad_norm": 0.8970662832168831,
|
| 245 |
+
"learning_rate": 1.9038337699485207e-05,
|
| 246 |
+
"loss": 0.3805,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 3.5,
|
| 251 |
+
"grad_norm": 1.0612014407477506,
|
| 252 |
+
"learning_rate": 1.8936326403234125e-05,
|
| 253 |
+
"loss": 0.3481,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 3.6,
|
| 258 |
+
"grad_norm": 0.8370235615255618,
|
| 259 |
+
"learning_rate": 1.8829475928589272e-05,
|
| 260 |
+
"loss": 0.3333,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 3.7,
|
| 265 |
+
"grad_norm": 1.128753299885166,
|
| 266 |
+
"learning_rate": 1.8717844136967626e-05,
|
| 267 |
+
"loss": 0.3398,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 3.8,
|
| 272 |
+
"grad_norm": 1.0163020931362265,
|
| 273 |
+
"learning_rate": 1.860149147895366e-05,
|
| 274 |
+
"loss": 0.3192,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 3.9,
|
| 279 |
+
"grad_norm": 0.7411794509431812,
|
| 280 |
+
"learning_rate": 1.848048096156426e-05,
|
| 281 |
+
"loss": 0.2694,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 4.0,
|
| 286 |
+
"grad_norm": 0.9250164203908562,
|
| 287 |
+
"learning_rate": 1.8354878114129368e-05,
|
| 288 |
+
"loss": 0.2863,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 4.1,
|
| 293 |
+
"grad_norm": 0.8417377767403931,
|
| 294 |
+
"learning_rate": 1.8224750952806626e-05,
|
| 295 |
+
"loss": 0.2318,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 4.2,
|
| 300 |
+
"grad_norm": 0.8880509994076226,
|
| 301 |
+
"learning_rate": 1.8090169943749477e-05,
|
| 302 |
+
"loss": 0.2463,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 4.3,
|
| 307 |
+
"grad_norm": 0.8319508153001826,
|
| 308 |
+
"learning_rate": 1.795120796494848e-05,
|
| 309 |
+
"loss": 0.2142,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 4.4,
|
| 314 |
+
"grad_norm": 0.9069642204701174,
|
| 315 |
+
"learning_rate": 1.7807940266766595e-05,
|
| 316 |
+
"loss": 0.1861,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 4.5,
|
| 321 |
+
"grad_norm": 0.886648766459474,
|
| 322 |
+
"learning_rate": 1.766044443118978e-05,
|
| 323 |
+
"loss": 0.1981,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 4.6,
|
| 328 |
+
"grad_norm": 0.7878272604729076,
|
| 329 |
+
"learning_rate": 1.7508800329814993e-05,
|
| 330 |
+
"loss": 0.1927,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 4.7,
|
| 335 |
+
"grad_norm": 0.859960892022644,
|
| 336 |
+
"learning_rate": 1.735309008059829e-05,
|
| 337 |
+
"loss": 0.2185,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 4.8,
|
| 342 |
+
"grad_norm": 0.8198360072603958,
|
| 343 |
+
"learning_rate": 1.7193398003386514e-05,
|
| 344 |
+
"loss": 0.1932,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 4.9,
|
| 349 |
+
"grad_norm": 0.8197303574303446,
|
| 350 |
+
"learning_rate": 1.702981057425662e-05,
|
| 351 |
+
"loss": 0.1896,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 5.0,
|
| 356 |
+
"grad_norm": 0.7095776631735655,
|
| 357 |
+
"learning_rate": 1.686241637868734e-05,
|
| 358 |
+
"loss": 0.1808,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 5.1,
|
| 363 |
+
"grad_norm": 0.782000326482277,
|
| 364 |
+
"learning_rate": 1.6691306063588583e-05,
|
| 365 |
+
"loss": 0.1546,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 5.2,
|
| 370 |
+
"grad_norm": 0.757071977981014,
|
| 371 |
+
"learning_rate": 1.6516572288214555e-05,
|
| 372 |
+
"loss": 0.1219,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 5.3,
|
| 377 |
+
"grad_norm": 0.7489429204163558,
|
| 378 |
+
"learning_rate": 1.63383096739871e-05,
|
| 379 |
+
"loss": 0.1047,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 5.4,
|
| 384 |
+
"grad_norm": 0.7352612139748114,
|
| 385 |
+
"learning_rate": 1.6156614753256583e-05,
|
| 386 |
+
"loss": 0.1179,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 5.5,
|
| 391 |
+
"grad_norm": 0.7350662711218962,
|
| 392 |
+
"learning_rate": 1.5971585917027864e-05,
|
| 393 |
+
"loss": 0.1137,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 5.6,
|
| 398 |
+
"grad_norm": 0.7039275993910796,
|
| 399 |
+
"learning_rate": 1.5783323361679865e-05,
|
| 400 |
+
"loss": 0.1172,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 5.7,
|
| 405 |
+
"grad_norm": 0.6910516646490666,
|
| 406 |
+
"learning_rate": 1.5591929034707468e-05,
|
| 407 |
+
"loss": 0.1024,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 5.8,
|
| 412 |
+
"grad_norm": 0.7236787235958125,
|
| 413 |
+
"learning_rate": 1.539750657951513e-05,
|
| 414 |
+
"loss": 0.0989,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 5.9,
|
| 419 |
+
"grad_norm": 0.6420220198866008,
|
| 420 |
+
"learning_rate": 1.5200161279292154e-05,
|
| 421 |
+
"loss": 0.1241,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 6.0,
|
| 426 |
+
"grad_norm": 0.6203363523773471,
|
| 427 |
+
"learning_rate": 1.5000000000000002e-05,
|
| 428 |
+
"loss": 0.0817,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 6.1,
|
| 433 |
+
"grad_norm": 0.6104409465029903,
|
| 434 |
+
"learning_rate": 1.4797131132502464e-05,
|
| 435 |
+
"loss": 0.0601,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 6.2,
|
| 440 |
+
"grad_norm": 0.5844775253639324,
|
| 441 |
+
"learning_rate": 1.4591664533870118e-05,
|
| 442 |
+
"loss": 0.0627,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 6.3,
|
| 447 |
+
"grad_norm": 0.5069649786509103,
|
| 448 |
+
"learning_rate": 1.4383711467890776e-05,
|
| 449 |
+
"loss": 0.0587,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 6.4,
|
| 454 |
+
"grad_norm": 0.8916378878545967,
|
| 455 |
+
"learning_rate": 1.417338454481818e-05,
|
| 456 |
+
"loss": 0.0836,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 6.5,
|
| 461 |
+
"grad_norm": 0.6085732114627656,
|
| 462 |
+
"learning_rate": 1.396079766039157e-05,
|
| 463 |
+
"loss": 0.0444,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 6.6,
|
| 468 |
+
"grad_norm": 0.8766545204586843,
|
| 469 |
+
"learning_rate": 1.3746065934159123e-05,
|
| 470 |
+
"loss": 0.0671,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 6.7,
|
| 475 |
+
"grad_norm": 0.5289923674586601,
|
| 476 |
+
"learning_rate": 1.3529305647138689e-05,
|
| 477 |
+
"loss": 0.0544,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 6.8,
|
| 482 |
+
"grad_norm": 0.5631884598314233,
|
| 483 |
+
"learning_rate": 1.3310634178849583e-05,
|
| 484 |
+
"loss": 0.0532,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 6.9,
|
| 489 |
+
"grad_norm": 0.5869614627369972,
|
| 490 |
+
"learning_rate": 1.3090169943749475e-05,
|
| 491 |
+
"loss": 0.0594,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 7.0,
|
| 496 |
+
"grad_norm": 0.49999369328894544,
|
| 497 |
+
"learning_rate": 1.2868032327110904e-05,
|
| 498 |
+
"loss": 0.0547,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 7.1,
|
| 503 |
+
"grad_norm": 0.443457075418473,
|
| 504 |
+
"learning_rate": 1.2644341620372025e-05,
|
| 505 |
+
"loss": 0.0329,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 7.2,
|
| 510 |
+
"grad_norm": 0.4438435027066986,
|
| 511 |
+
"learning_rate": 1.2419218955996677e-05,
|
| 512 |
+
"loss": 0.0284,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 7.3,
|
| 517 |
+
"grad_norm": 0.4800778119424111,
|
| 518 |
+
"learning_rate": 1.2192786241879033e-05,
|
| 519 |
+
"loss": 0.0404,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 7.4,
|
| 524 |
+
"grad_norm": 0.4379474529157175,
|
| 525 |
+
"learning_rate": 1.1965166095328302e-05,
|
| 526 |
+
"loss": 0.0225,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 7.5,
|
| 531 |
+
"grad_norm": 0.4429369566894146,
|
| 532 |
+
"learning_rate": 1.1736481776669307e-05,
|
| 533 |
+
"loss": 0.0223,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 7.6,
|
| 538 |
+
"grad_norm": 0.40432933172297614,
|
| 539 |
+
"learning_rate": 1.1506857122494832e-05,
|
| 540 |
+
"loss": 0.0244,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 7.7,
|
| 545 |
+
"grad_norm": 0.48073981290705153,
|
| 546 |
+
"learning_rate": 1.127641647860595e-05,
|
| 547 |
+
"loss": 0.0319,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 7.8,
|
| 552 |
+
"grad_norm": 0.5001498731871603,
|
| 553 |
+
"learning_rate": 1.1045284632676535e-05,
|
| 554 |
+
"loss": 0.0307,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 7.9,
|
| 559 |
+
"grad_norm": 0.3920879064027223,
|
| 560 |
+
"learning_rate": 1.0813586746678584e-05,
|
| 561 |
+
"loss": 0.0254,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 8.0,
|
| 566 |
+
"grad_norm": 0.4091992943404657,
|
| 567 |
+
"learning_rate": 1.0581448289104759e-05,
|
| 568 |
+
"loss": 0.0259,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 8.1,
|
| 573 |
+
"grad_norm": 0.24591634835172133,
|
| 574 |
+
"learning_rate": 1.0348994967025012e-05,
|
| 575 |
+
"loss": 0.0129,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 8.2,
|
| 580 |
+
"grad_norm": 0.27732329015357815,
|
| 581 |
+
"learning_rate": 1.0116352658013973e-05,
|
| 582 |
+
"loss": 0.0118,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 8.3,
|
| 587 |
+
"grad_norm": 0.2737809179611153,
|
| 588 |
+
"learning_rate": 9.883647341986032e-06,
|
| 589 |
+
"loss": 0.0125,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 8.4,
|
| 594 |
+
"grad_norm": 0.30306810527445566,
|
| 595 |
+
"learning_rate": 9.651005032974994e-06,
|
| 596 |
+
"loss": 0.0154,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 8.5,
|
| 601 |
+
"grad_norm": 0.30379855260514727,
|
| 602 |
+
"learning_rate": 9.418551710895243e-06,
|
| 603 |
+
"loss": 0.0118,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 8.6,
|
| 608 |
+
"grad_norm": 0.4811355659404676,
|
| 609 |
+
"learning_rate": 9.18641325332142e-06,
|
| 610 |
+
"loss": 0.0155,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 8.7,
|
| 615 |
+
"grad_norm": 0.37455252522236027,
|
| 616 |
+
"learning_rate": 8.954715367323468e-06,
|
| 617 |
+
"loss": 0.0109,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 8.8,
|
| 622 |
+
"grad_norm": 0.3382983231236897,
|
| 623 |
+
"learning_rate": 8.723583521394054e-06,
|
| 624 |
+
"loss": 0.0152,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 8.9,
|
| 629 |
+
"grad_norm": 0.3297109614209282,
|
| 630 |
+
"learning_rate": 8.49314287750517e-06,
|
| 631 |
+
"loss": 0.0119,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 9.0,
|
| 636 |
+
"grad_norm": 0.3116900824217769,
|
| 637 |
+
"learning_rate": 8.263518223330698e-06,
|
| 638 |
+
"loss": 0.0099,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 9.1,
|
| 643 |
+
"grad_norm": 0.2048883072228153,
|
| 644 |
+
"learning_rate": 8.034833904671698e-06,
|
| 645 |
+
"loss": 0.0068,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 9.2,
|
| 650 |
+
"grad_norm": 0.16372430312031436,
|
| 651 |
+
"learning_rate": 7.807213758120965e-06,
|
| 652 |
+
"loss": 0.0046,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 9.3,
|
| 657 |
+
"grad_norm": 0.17126616465729205,
|
| 658 |
+
"learning_rate": 7.580781044003324e-06,
|
| 659 |
+
"loss": 0.0045,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 9.4,
|
| 664 |
+
"grad_norm": 0.17140249123203252,
|
| 665 |
+
"learning_rate": 7.355658379627981e-06,
|
| 666 |
+
"loss": 0.0054,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 9.5,
|
| 671 |
+
"grad_norm": 0.21145963284827615,
|
| 672 |
+
"learning_rate": 7.131967672889101e-06,
|
| 673 |
+
"loss": 0.0064,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 9.6,
|
| 678 |
+
"grad_norm": 0.16836913651183916,
|
| 679 |
+
"learning_rate": 6.909830056250527e-06,
|
| 680 |
+
"loss": 0.0038,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 9.7,
|
| 685 |
+
"grad_norm": 0.18115546955306835,
|
| 686 |
+
"learning_rate": 6.689365821150421e-06,
|
| 687 |
+
"loss": 0.0052,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 9.8,
|
| 692 |
+
"grad_norm": 0.2577468160241198,
|
| 693 |
+
"learning_rate": 6.4706943528613135e-06,
|
| 694 |
+
"loss": 0.0056,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 9.9,
|
| 699 |
+
"grad_norm": 0.19659235565523647,
|
| 700 |
+
"learning_rate": 6.25393406584088e-06,
|
| 701 |
+
"loss": 0.0042,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 10.0,
|
| 706 |
+
"grad_norm": 0.23535354069396494,
|
| 707 |
+
"learning_rate": 6.039202339608432e-06,
|
| 708 |
+
"loss": 0.0043,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 10.1,
|
| 713 |
+
"grad_norm": 0.08757863007098991,
|
| 714 |
+
"learning_rate": 5.8266154551818225e-06,
|
| 715 |
+
"loss": 0.0022,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 10.2,
|
| 720 |
+
"grad_norm": 0.11715962745878235,
|
| 721 |
+
"learning_rate": 5.616288532109225e-06,
|
| 722 |
+
"loss": 0.0022,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 10.3,
|
| 727 |
+
"grad_norm": 0.12361827660694866,
|
| 728 |
+
"learning_rate": 5.4083354661298816e-06,
|
| 729 |
+
"loss": 0.002,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 10.4,
|
| 734 |
+
"grad_norm": 0.13828988254954486,
|
| 735 |
+
"learning_rate": 5.202868867497542e-06,
|
| 736 |
+
"loss": 0.0025,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 10.5,
|
| 741 |
+
"grad_norm": 0.1215485981095267,
|
| 742 |
+
"learning_rate": 5.000000000000003e-06,
|
| 743 |
+
"loss": 0.002,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 10.6,
|
| 748 |
+
"grad_norm": 0.10696031651620225,
|
| 749 |
+
"learning_rate": 4.799838720707847e-06,
|
| 750 |
+
"loss": 0.0024,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 10.7,
|
| 755 |
+
"grad_norm": 0.11537485121928975,
|
| 756 |
+
"learning_rate": 4.6024934204848745e-06,
|
| 757 |
+
"loss": 0.0019,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 10.8,
|
| 762 |
+
"grad_norm": 0.11477645379676313,
|
| 763 |
+
"learning_rate": 4.408070965292534e-06,
|
| 764 |
+
"loss": 0.0023,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 10.9,
|
| 769 |
+
"grad_norm": 0.09407959791293473,
|
| 770 |
+
"learning_rate": 4.216676638320135e-06,
|
| 771 |
+
"loss": 0.0017,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 11.0,
|
| 776 |
+
"grad_norm": 0.10539572481392215,
|
| 777 |
+
"learning_rate": 4.028414082972141e-06,
|
| 778 |
+
"loss": 0.0022,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 11.1,
|
| 783 |
+
"grad_norm": 0.04526592878878114,
|
| 784 |
+
"learning_rate": 3.8433852467434175e-06,
|
| 785 |
+
"loss": 0.0013,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 11.2,
|
| 790 |
+
"grad_norm": 0.04747157304079231,
|
| 791 |
+
"learning_rate": 3.661690326012897e-06,
|
| 792 |
+
"loss": 0.0012,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 11.3,
|
| 797 |
+
"grad_norm": 0.05989856905170414,
|
| 798 |
+
"learning_rate": 3.483427711785449e-06,
|
| 799 |
+
"loss": 0.0014,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 11.4,
|
| 804 |
+
"grad_norm": 0.07405131299600318,
|
| 805 |
+
"learning_rate": 3.308693936411421e-06,
|
| 806 |
+
"loss": 0.0012,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 11.5,
|
| 811 |
+
"grad_norm": 0.036105812123230004,
|
| 812 |
+
"learning_rate": 3.1375836213126653e-06,
|
| 813 |
+
"loss": 0.0012,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 11.6,
|
| 818 |
+
"grad_norm": 0.04336874203309867,
|
| 819 |
+
"learning_rate": 2.970189425743383e-06,
|
| 820 |
+
"loss": 0.0015,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 11.7,
|
| 825 |
+
"grad_norm": 0.03911723515161731,
|
| 826 |
+
"learning_rate": 2.8066019966134907e-06,
|
| 827 |
+
"loss": 0.0014,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 11.8,
|
| 832 |
+
"grad_norm": 0.06319472371081573,
|
| 833 |
+
"learning_rate": 2.6469099194017144e-06,
|
| 834 |
+
"loss": 0.0013,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 11.9,
|
| 839 |
+
"grad_norm": 0.06203490181593157,
|
| 840 |
+
"learning_rate": 2.4911996701850083e-06,
|
| 841 |
+
"loss": 0.0012,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 12.0,
|
| 846 |
+
"grad_norm": 0.038461603051341636,
|
| 847 |
+
"learning_rate": 2.339555568810221e-06,
|
| 848 |
+
"loss": 0.0011,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 12.1,
|
| 853 |
+
"grad_norm": 0.03151892994828768,
|
| 854 |
+
"learning_rate": 2.192059733233408e-06,
|
| 855 |
+
"loss": 0.0011,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 12.2,
|
| 860 |
+
"grad_norm": 0.026069986960984427,
|
| 861 |
+
"learning_rate": 2.048792035051521e-06,
|
| 862 |
+
"loss": 0.001,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 12.3,
|
| 867 |
+
"grad_norm": 0.029353134476379206,
|
| 868 |
+
"learning_rate": 1.9098300562505266e-06,
|
| 869 |
+
"loss": 0.0011,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 12.4,
|
| 874 |
+
"grad_norm": 0.026449026260907393,
|
| 875 |
+
"learning_rate": 1.7752490471933769e-06,
|
| 876 |
+
"loss": 0.001,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 12.5,
|
| 881 |
+
"grad_norm": 0.024494407561961196,
|
| 882 |
+
"learning_rate": 1.6451218858706374e-06,
|
| 883 |
+
"loss": 0.001,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 12.6,
|
| 888 |
+
"grad_norm": 0.02435497987035409,
|
| 889 |
+
"learning_rate": 1.5195190384357405e-06,
|
| 890 |
+
"loss": 0.0009,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 12.7,
|
| 895 |
+
"grad_norm": 0.026479892781776853,
|
| 896 |
+
"learning_rate": 1.3985085210463479e-06,
|
| 897 |
+
"loss": 0.0008,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 12.8,
|
| 902 |
+
"grad_norm": 0.02103523842744242,
|
| 903 |
+
"learning_rate": 1.282155863032377e-06,
|
| 904 |
+
"loss": 0.0009,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 12.9,
|
| 909 |
+
"grad_norm": 0.026913938950377716,
|
| 910 |
+
"learning_rate": 1.1705240714107301e-06,
|
| 911 |
+
"loss": 0.0008,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 13.0,
|
| 916 |
+
"grad_norm": 0.021497261239699632,
|
| 917 |
+
"learning_rate": 1.0636735967658785e-06,
|
| 918 |
+
"loss": 0.0009,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 13.1,
|
| 923 |
+
"grad_norm": 0.01744937560052008,
|
| 924 |
+
"learning_rate": 9.616623005147952e-07,
|
| 925 |
+
"loss": 0.0008,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 13.2,
|
| 930 |
+
"grad_norm": 0.022830147389962408,
|
| 931 |
+
"learning_rate": 8.645454235739903e-07,
|
| 932 |
+
"loss": 0.001,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 13.3,
|
| 937 |
+
"grad_norm": 0.018549892449922493,
|
| 938 |
+
"learning_rate": 7.723755564455771e-07,
|
| 939 |
+
"loss": 0.0008,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 13.4,
|
| 944 |
+
"grad_norm": 0.018499963246780587,
|
| 945 |
+
"learning_rate": 6.852026107385756e-07,
|
| 946 |
+
"loss": 0.0007,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 13.5,
|
| 951 |
+
"grad_norm": 0.020186180806129512,
|
| 952 |
+
"learning_rate": 6.030737921409169e-07,
|
| 953 |
+
"loss": 0.0008,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 13.6,
|
| 958 |
+
"grad_norm": 0.02160863937701566,
|
| 959 |
+
"learning_rate": 5.26033574856708e-07,
|
| 960 |
+
"loss": 0.0008,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 13.7,
|
| 965 |
+
"grad_norm": 0.021380770597770406,
|
| 966 |
+
"learning_rate": 4.5412367752268094e-07,
|
| 967 |
+
"loss": 0.0009,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 13.8,
|
| 972 |
+
"grad_norm": 0.017139391436868278,
|
| 973 |
+
"learning_rate": 3.8738304061681107e-07,
|
| 974 |
+
"loss": 0.0008,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 13.9,
|
| 979 |
+
"grad_norm": 0.015543842724841007,
|
| 980 |
+
"learning_rate": 3.2584780537136206e-07,
|
| 981 |
+
"loss": 0.0006,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 14.0,
|
| 986 |
+
"grad_norm": 0.023669058624946445,
|
| 987 |
+
"learning_rate": 2.6955129420176193e-07,
|
| 988 |
+
"loss": 0.0008,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 14.1,
|
| 993 |
+
"grad_norm": 0.017273400705971477,
|
| 994 |
+
"learning_rate": 2.1852399266194312e-07,
|
| 995 |
+
"loss": 0.0007,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 14.2,
|
| 1000 |
+
"grad_norm": 0.017728316737897203,
|
| 1001 |
+
"learning_rate": 1.7279353293586765e-07,
|
| 1002 |
+
"loss": 0.0008,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 14.3,
|
| 1007 |
+
"grad_norm": 0.019827798313299654,
|
| 1008 |
+
"learning_rate": 1.323846788742078e-07,
|
| 1009 |
+
"loss": 0.0009,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 14.4,
|
| 1014 |
+
"grad_norm": 0.016917306292850116,
|
| 1015 |
+
"learning_rate": 9.731931258429638e-08,
|
| 1016 |
+
"loss": 0.0007,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 14.5,
|
| 1021 |
+
"grad_norm": 0.01653817553682287,
|
| 1022 |
+
"learning_rate": 6.761642258056977e-08,
|
| 1023 |
+
"loss": 0.0007,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 14.6,
|
| 1028 |
+
"grad_norm": 0.03480683137636861,
|
| 1029 |
+
"learning_rate": 4.329209350195651e-08,
|
| 1030 |
+
"loss": 0.0007,
|
| 1031 |
+
"step": 146
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 14.7,
|
| 1035 |
+
"grad_norm": 0.020559555488437672,
|
| 1036 |
+
"learning_rate": 2.4359497401758026e-08,
|
| 1037 |
+
"loss": 0.001,
|
| 1038 |
+
"step": 147
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 14.8,
|
| 1042 |
+
"grad_norm": 0.018105533298564763,
|
| 1043 |
+
"learning_rate": 1.0828886614754342e-08,
|
| 1044 |
+
"loss": 0.0008,
|
| 1045 |
+
"step": 148
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 14.9,
|
| 1049 |
+
"grad_norm": 0.019042313810839078,
|
| 1050 |
+
"learning_rate": 2.7075882053828605e-09,
|
| 1051 |
+
"loss": 0.0008,
|
| 1052 |
+
"step": 149
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 15.0,
|
| 1056 |
+
"grad_norm": 0.018967228362383,
|
| 1057 |
+
"learning_rate": 0.0,
|
| 1058 |
+
"loss": 0.0008,
|
| 1059 |
+
"step": 150
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 15.0,
|
| 1063 |
+
"step": 150,
|
| 1064 |
+
"total_flos": 8.481547119440691e+16,
|
| 1065 |
+
"train_loss": 0.1808963591993476,
|
| 1066 |
+
"train_runtime": 6243.0048,
|
| 1067 |
+
"train_samples_per_second": 0.759,
|
| 1068 |
+
"train_steps_per_second": 0.024
|
| 1069 |
+
}
|
| 1070 |
+
],
|
| 1071 |
+
"logging_steps": 1.0,
|
| 1072 |
+
"max_steps": 150,
|
| 1073 |
+
"num_input_tokens_seen": 0,
|
| 1074 |
+
"num_train_epochs": 15,
|
| 1075 |
+
"save_steps": 500,
|
| 1076 |
+
"stateful_callbacks": {
|
| 1077 |
+
"TrainerControl": {
|
| 1078 |
+
"args": {
|
| 1079 |
+
"should_epoch_stop": false,
|
| 1080 |
+
"should_evaluate": false,
|
| 1081 |
+
"should_log": false,
|
| 1082 |
+
"should_save": true,
|
| 1083 |
+
"should_training_stop": true
|
| 1084 |
+
},
|
| 1085 |
+
"attributes": {}
|
| 1086 |
+
}
|
| 1087 |
+
},
|
| 1088 |
+
"total_flos": 8.481547119440691e+16,
|
| 1089 |
+
"train_batch_size": 1,
|
| 1090 |
+
"trial_name": null,
|
| 1091 |
+
"trial_params": null
|
| 1092 |
+
}
|
training_loss.png
ADDED
|