End of training
Browse files- README.md +2 -1
- all_results.json +5 -9
- train_results.json +5 -5
- trainer_state.json +1532 -30
- 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: llama3-1_8b_4o_annotated_math
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# llama3-1_8b_4o_annotated_math
|
| 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: llama3-1_8b_4o_annotated_math
|
|
|
|
| 16 |
|
| 17 |
# llama3-1_8b_4o_annotated_math
|
| 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/4o_annotated_math dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
CHANGED
|
@@ -1,12 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
-
"
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
"
|
| 7 |
-
"
|
| 8 |
-
"train_loss": 0.5236397902170817,
|
| 9 |
-
"train_runtime": 518.9737,
|
| 10 |
-
"train_samples_per_second": 13.475,
|
| 11 |
-
"train_steps_per_second": 0.029
|
| 12 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
+
"total_flos": 45867016224768.0,
|
| 4 |
+
"train_loss": 0.2807643291748822,
|
| 5 |
+
"train_runtime": 547.5472,
|
| 6 |
+
"train_samples_per_second": 37.92,
|
| 7 |
+
"train_steps_per_second": 0.4
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
+
"total_flos": 45867016224768.0,
|
| 4 |
+
"train_loss": 0.2807643291748822,
|
| 5 |
+
"train_runtime": 547.5472,
|
| 6 |
+
"train_samples_per_second": 37.92,
|
| 7 |
+
"train_steps_per_second": 0.4
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -3,54 +3,1556 @@
|
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 3.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
-
"epoch":
|
| 13 |
-
"
|
| 14 |
-
"
|
| 15 |
-
"
|
| 16 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
"step": 5
|
| 18 |
},
|
| 19 |
{
|
| 20 |
-
"epoch":
|
| 21 |
-
"grad_norm":
|
| 22 |
-
"learning_rate":
|
| 23 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
"step": 10
|
| 25 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
{
|
| 27 |
"epoch": 2.0,
|
| 28 |
-
"
|
| 29 |
-
"
|
| 30 |
-
"
|
| 31 |
-
"
|
| 32 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 3.0,
|
| 36 |
-
"
|
| 37 |
-
"
|
| 38 |
-
"
|
| 39 |
-
"
|
| 40 |
-
"step": 15
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"epoch": 3.0,
|
| 44 |
-
"step":
|
| 45 |
-
"total_flos":
|
| 46 |
-
"train_loss": 0.
|
| 47 |
-
"train_runtime":
|
| 48 |
-
"train_samples_per_second":
|
| 49 |
-
"train_steps_per_second": 0.
|
| 50 |
}
|
| 51 |
],
|
| 52 |
-
"logging_steps":
|
| 53 |
-
"max_steps":
|
| 54 |
"num_input_tokens_seen": 0,
|
| 55 |
"num_train_epochs": 3,
|
| 56 |
"save_steps": 500,
|
|
@@ -66,8 +1568,8 @@
|
|
| 66 |
"attributes": {}
|
| 67 |
}
|
| 68 |
},
|
| 69 |
-
"total_flos":
|
| 70 |
-
"train_batch_size":
|
| 71 |
"trial_name": null,
|
| 72 |
"trial_params": null
|
| 73 |
}
|
|
|
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 3.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 219,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.0136986301369863,
|
| 13 |
+
"grad_norm": 3.7877831881292834,
|
| 14 |
+
"learning_rate": 4.5454545454545457e-07,
|
| 15 |
+
"loss": 0.472,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0273972602739726,
|
| 20 |
+
"grad_norm": 4.130214622110189,
|
| 21 |
+
"learning_rate": 9.090909090909091e-07,
|
| 22 |
+
"loss": 0.4526,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.0410958904109589,
|
| 27 |
+
"grad_norm": 3.8247534821935094,
|
| 28 |
+
"learning_rate": 1.3636363636363636e-06,
|
| 29 |
+
"loss": 0.4436,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0547945205479452,
|
| 34 |
+
"grad_norm": 3.8662923348917535,
|
| 35 |
+
"learning_rate": 1.8181818181818183e-06,
|
| 36 |
+
"loss": 0.494,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.0684931506849315,
|
| 41 |
+
"grad_norm": 3.563387846978886,
|
| 42 |
+
"learning_rate": 2.2727272727272728e-06,
|
| 43 |
+
"loss": 0.4486,
|
| 44 |
"step": 5
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.0821917808219178,
|
| 48 |
+
"grad_norm": 2.5747863718119715,
|
| 49 |
+
"learning_rate": 2.7272727272727272e-06,
|
| 50 |
+
"loss": 0.418,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.0958904109589041,
|
| 55 |
+
"grad_norm": 2.655505984347451,
|
| 56 |
+
"learning_rate": 3.181818181818182e-06,
|
| 57 |
+
"loss": 0.4354,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.1095890410958904,
|
| 62 |
+
"grad_norm": 2.072138367597328,
|
| 63 |
+
"learning_rate": 3.6363636363636366e-06,
|
| 64 |
+
"loss": 0.4127,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.1232876712328767,
|
| 69 |
+
"grad_norm": 1.961206195469995,
|
| 70 |
+
"learning_rate": 4.0909090909090915e-06,
|
| 71 |
+
"loss": 0.387,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.136986301369863,
|
| 76 |
+
"grad_norm": 1.4884526330840524,
|
| 77 |
+
"learning_rate": 4.5454545454545455e-06,
|
| 78 |
+
"loss": 0.414,
|
| 79 |
"step": 10
|
| 80 |
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.1506849315068493,
|
| 83 |
+
"grad_norm": 1.5986375806144255,
|
| 84 |
+
"learning_rate": 5e-06,
|
| 85 |
+
"loss": 0.4015,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.1643835616438356,
|
| 90 |
+
"grad_norm": 1.2500780248731937,
|
| 91 |
+
"learning_rate": 5.4545454545454545e-06,
|
| 92 |
+
"loss": 0.3787,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.1780821917808219,
|
| 97 |
+
"grad_norm": 1.1255699225061293,
|
| 98 |
+
"learning_rate": 5.90909090909091e-06,
|
| 99 |
+
"loss": 0.3654,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.1917808219178082,
|
| 104 |
+
"grad_norm": 1.3780264614281572,
|
| 105 |
+
"learning_rate": 6.363636363636364e-06,
|
| 106 |
+
"loss": 0.3886,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.2054794520547945,
|
| 111 |
+
"grad_norm": 1.662621715972107,
|
| 112 |
+
"learning_rate": 6.818181818181818e-06,
|
| 113 |
+
"loss": 0.368,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.2191780821917808,
|
| 118 |
+
"grad_norm": 1.4540202113644316,
|
| 119 |
+
"learning_rate": 7.272727272727273e-06,
|
| 120 |
+
"loss": 0.3584,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.2328767123287671,
|
| 125 |
+
"grad_norm": 1.2750666233659884,
|
| 126 |
+
"learning_rate": 7.727272727272727e-06,
|
| 127 |
+
"loss": 0.3403,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.2465753424657534,
|
| 132 |
+
"grad_norm": 1.2010950321245533,
|
| 133 |
+
"learning_rate": 8.181818181818183e-06,
|
| 134 |
+
"loss": 0.3206,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.2602739726027397,
|
| 139 |
+
"grad_norm": 0.9366449404857862,
|
| 140 |
+
"learning_rate": 8.636363636363637e-06,
|
| 141 |
+
"loss": 0.3002,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.273972602739726,
|
| 146 |
+
"grad_norm": 0.8235569541259258,
|
| 147 |
+
"learning_rate": 9.090909090909091e-06,
|
| 148 |
+
"loss": 0.3244,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.2876712328767123,
|
| 153 |
+
"grad_norm": 0.9490140777574348,
|
| 154 |
+
"learning_rate": 9.545454545454547e-06,
|
| 155 |
+
"loss": 0.3761,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.3013698630136986,
|
| 160 |
+
"grad_norm": 0.860686135666645,
|
| 161 |
+
"learning_rate": 1e-05,
|
| 162 |
+
"loss": 0.3035,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.3150684931506849,
|
| 167 |
+
"grad_norm": 1.0246441607822483,
|
| 168 |
+
"learning_rate": 9.999364232830053e-06,
|
| 169 |
+
"loss": 0.3365,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.3287671232876712,
|
| 174 |
+
"grad_norm": 0.8261477706641936,
|
| 175 |
+
"learning_rate": 9.997457093000165e-06,
|
| 176 |
+
"loss": 0.3114,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.3424657534246575,
|
| 181 |
+
"grad_norm": 0.7678914540657628,
|
| 182 |
+
"learning_rate": 9.994279065509094e-06,
|
| 183 |
+
"loss": 0.3489,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.3561643835616438,
|
| 188 |
+
"grad_norm": 0.8460367890612149,
|
| 189 |
+
"learning_rate": 9.989830958551058e-06,
|
| 190 |
+
"loss": 0.3447,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.3698630136986301,
|
| 195 |
+
"grad_norm": 0.8258388717644197,
|
| 196 |
+
"learning_rate": 9.984113903310206e-06,
|
| 197 |
+
"loss": 0.3154,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.3835616438356164,
|
| 202 |
+
"grad_norm": 0.7839964948766741,
|
| 203 |
+
"learning_rate": 9.977129353672951e-06,
|
| 204 |
+
"loss": 0.3445,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.3972602739726027,
|
| 209 |
+
"grad_norm": 0.6689832051270882,
|
| 210 |
+
"learning_rate": 9.968879085858234e-06,
|
| 211 |
+
"loss": 0.3465,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.410958904109589,
|
| 216 |
+
"grad_norm": 0.6963372804685805,
|
| 217 |
+
"learning_rate": 9.959365197965824e-06,
|
| 218 |
+
"loss": 0.3273,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.4246575342465753,
|
| 223 |
+
"grad_norm": 0.6765532716442401,
|
| 224 |
+
"learning_rate": 9.948590109442755e-06,
|
| 225 |
+
"loss": 0.3304,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.4383561643835616,
|
| 230 |
+
"grad_norm": 0.8399760611721238,
|
| 231 |
+
"learning_rate": 9.936556560468037e-06,
|
| 232 |
+
"loss": 0.3329,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.4520547945205479,
|
| 237 |
+
"grad_norm": 0.667707505156549,
|
| 238 |
+
"learning_rate": 9.923267611255824e-06,
|
| 239 |
+
"loss": 0.3268,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.4657534246575342,
|
| 244 |
+
"grad_norm": 0.6960781324564396,
|
| 245 |
+
"learning_rate": 9.908726641277167e-06,
|
| 246 |
+
"loss": 0.3683,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.4794520547945205,
|
| 251 |
+
"grad_norm": 0.7038989733011621,
|
| 252 |
+
"learning_rate": 9.8929373484006e-06,
|
| 253 |
+
"loss": 0.3313,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.4931506849315068,
|
| 258 |
+
"grad_norm": 0.7625951560605625,
|
| 259 |
+
"learning_rate": 9.875903747951742e-06,
|
| 260 |
+
"loss": 0.3306,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.5068493150684932,
|
| 265 |
+
"grad_norm": 0.7666008793193901,
|
| 266 |
+
"learning_rate": 9.857630171692175e-06,
|
| 267 |
+
"loss": 0.3117,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.5205479452054794,
|
| 272 |
+
"grad_norm": 0.7091615846675945,
|
| 273 |
+
"learning_rate": 9.83812126671784e-06,
|
| 274 |
+
"loss": 0.3357,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.5342465753424658,
|
| 279 |
+
"grad_norm": 0.7444795431133784,
|
| 280 |
+
"learning_rate": 9.81738199427726e-06,
|
| 281 |
+
"loss": 0.3769,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.547945205479452,
|
| 286 |
+
"grad_norm": 0.7735033443112485,
|
| 287 |
+
"learning_rate": 9.795417628509857e-06,
|
| 288 |
+
"loss": 0.3469,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.5616438356164384,
|
| 293 |
+
"grad_norm": 0.6413429464736542,
|
| 294 |
+
"learning_rate": 9.772233755104695e-06,
|
| 295 |
+
"loss": 0.3305,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.5753424657534246,
|
| 300 |
+
"grad_norm": 0.659915390024641,
|
| 301 |
+
"learning_rate": 9.747836269880005e-06,
|
| 302 |
+
"loss": 0.3312,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.589041095890411,
|
| 307 |
+
"grad_norm": 0.6973050902366138,
|
| 308 |
+
"learning_rate": 9.722231377283841e-06,
|
| 309 |
+
"loss": 0.3713,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.6027397260273972,
|
| 314 |
+
"grad_norm": 0.6281599009291579,
|
| 315 |
+
"learning_rate": 9.695425588816248e-06,
|
| 316 |
+
"loss": 0.3817,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.6164383561643836,
|
| 321 |
+
"grad_norm": 0.6960334137766047,
|
| 322 |
+
"learning_rate": 9.667425721373333e-06,
|
| 323 |
+
"loss": 0.3504,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.6301369863013698,
|
| 328 |
+
"grad_norm": 0.6495158710619351,
|
| 329 |
+
"learning_rate": 9.638238895513687e-06,
|
| 330 |
+
"loss": 0.3246,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.6438356164383562,
|
| 335 |
+
"grad_norm": 0.5950872060309309,
|
| 336 |
+
"learning_rate": 9.607872533647584e-06,
|
| 337 |
+
"loss": 0.3301,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.6575342465753424,
|
| 342 |
+
"grad_norm": 0.6507041877121674,
|
| 343 |
+
"learning_rate": 9.5763343581494e-06,
|
| 344 |
+
"loss": 0.3264,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.6712328767123288,
|
| 349 |
+
"grad_norm": 0.7289638460609872,
|
| 350 |
+
"learning_rate": 9.543632389393767e-06,
|
| 351 |
+
"loss": 0.315,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.684931506849315,
|
| 356 |
+
"grad_norm": 0.6880639519415185,
|
| 357 |
+
"learning_rate": 9.50977494371594e-06,
|
| 358 |
+
"loss": 0.3348,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.6986301369863014,
|
| 363 |
+
"grad_norm": 0.679491769853036,
|
| 364 |
+
"learning_rate": 9.474770631296882e-06,
|
| 365 |
+
"loss": 0.3885,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.7123287671232876,
|
| 370 |
+
"grad_norm": 0.8010838765285704,
|
| 371 |
+
"learning_rate": 9.438628353973654e-06,
|
| 372 |
+
"loss": 0.351,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.726027397260274,
|
| 377 |
+
"grad_norm": 0.6491781621767001,
|
| 378 |
+
"learning_rate": 9.4013573029756e-06,
|
| 379 |
+
"loss": 0.2853,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.7397260273972602,
|
| 384 |
+
"grad_norm": 0.7176326214293206,
|
| 385 |
+
"learning_rate": 9.36296695658697e-06,
|
| 386 |
+
"loss": 0.3421,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.7534246575342466,
|
| 391 |
+
"grad_norm": 0.6041528656416243,
|
| 392 |
+
"learning_rate": 9.323467077736513e-06,
|
| 393 |
+
"loss": 0.3127,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.7671232876712328,
|
| 398 |
+
"grad_norm": 0.7187788626962461,
|
| 399 |
+
"learning_rate": 9.282867711514703e-06,
|
| 400 |
+
"loss": 0.3773,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.7808219178082192,
|
| 405 |
+
"grad_norm": 0.6231054950105221,
|
| 406 |
+
"learning_rate": 9.241179182619207e-06,
|
| 407 |
+
"loss": 0.2957,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.7945205479452054,
|
| 412 |
+
"grad_norm": 0.6008267630763687,
|
| 413 |
+
"learning_rate": 9.19841209272924e-06,
|
| 414 |
+
"loss": 0.3309,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.8082191780821918,
|
| 419 |
+
"grad_norm": 0.560136479324393,
|
| 420 |
+
"learning_rate": 9.154577317809483e-06,
|
| 421 |
+
"loss": 0.3175,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.821917808219178,
|
| 426 |
+
"grad_norm": 0.5585141155467109,
|
| 427 |
+
"learning_rate": 9.109686005344258e-06,
|
| 428 |
+
"loss": 0.3083,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.8356164383561644,
|
| 433 |
+
"grad_norm": 0.5697927188870517,
|
| 434 |
+
"learning_rate": 9.063749571502633e-06,
|
| 435 |
+
"loss": 0.326,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.8493150684931506,
|
| 440 |
+
"grad_norm": 0.6255449947186281,
|
| 441 |
+
"learning_rate": 9.016779698235227e-06,
|
| 442 |
+
"loss": 0.3308,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.863013698630137,
|
| 447 |
+
"grad_norm": 0.6723459386216729,
|
| 448 |
+
"learning_rate": 8.9687883303034e-06,
|
| 449 |
+
"loss": 0.3217,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.8767123287671232,
|
| 454 |
+
"grad_norm": 0.5750639576833132,
|
| 455 |
+
"learning_rate": 8.919787672241619e-06,
|
| 456 |
+
"loss": 0.292,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.8904109589041096,
|
| 461 |
+
"grad_norm": 0.5992326031899223,
|
| 462 |
+
"learning_rate": 8.869790185253766e-06,
|
| 463 |
+
"loss": 0.3156,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.9041095890410958,
|
| 468 |
+
"grad_norm": 0.6283658662032029,
|
| 469 |
+
"learning_rate": 8.818808584044163e-06,
|
| 470 |
+
"loss": 0.3835,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.9178082191780822,
|
| 475 |
+
"grad_norm": 0.6371243664450067,
|
| 476 |
+
"learning_rate": 8.76685583358414e-06,
|
| 477 |
+
"loss": 0.3118,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.9315068493150684,
|
| 482 |
+
"grad_norm": 0.5620578408048604,
|
| 483 |
+
"learning_rate": 8.713945145814948e-06,
|
| 484 |
+
"loss": 0.2837,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.9452054794520548,
|
| 489 |
+
"grad_norm": 0.5950148577440809,
|
| 490 |
+
"learning_rate": 8.660089976287875e-06,
|
| 491 |
+
"loss": 0.3545,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.958904109589041,
|
| 496 |
+
"grad_norm": 0.5835125820960362,
|
| 497 |
+
"learning_rate": 8.60530402074241e-06,
|
| 498 |
+
"loss": 0.347,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.9726027397260274,
|
| 503 |
+
"grad_norm": 0.622127618589228,
|
| 504 |
+
"learning_rate": 8.549601211623316e-06,
|
| 505 |
+
"loss": 0.3328,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.9863013698630136,
|
| 510 |
+
"grad_norm": 0.5405205685392995,
|
| 511 |
+
"learning_rate": 8.492995714537519e-06,
|
| 512 |
+
"loss": 0.317,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.0,
|
| 517 |
+
"grad_norm": 0.677897499227197,
|
| 518 |
+
"learning_rate": 8.43550192465169e-06,
|
| 519 |
+
"loss": 0.3426,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 1.0136986301369864,
|
| 524 |
+
"grad_norm": 0.6208082237697633,
|
| 525 |
+
"learning_rate": 8.377134463031468e-06,
|
| 526 |
+
"loss": 0.2593,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.0273972602739727,
|
| 531 |
+
"grad_norm": 0.5162418454739198,
|
| 532 |
+
"learning_rate": 8.317908172923207e-06,
|
| 533 |
+
"loss": 0.2759,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.0410958904109588,
|
| 538 |
+
"grad_norm": 0.5656793029599352,
|
| 539 |
+
"learning_rate": 8.257838115979244e-06,
|
| 540 |
+
"loss": 0.3252,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.0547945205479452,
|
| 545 |
+
"grad_norm": 0.5513584658381595,
|
| 546 |
+
"learning_rate": 8.196939568427624e-06,
|
| 547 |
+
"loss": 0.2972,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.0684931506849316,
|
| 552 |
+
"grad_norm": 0.5327973468535152,
|
| 553 |
+
"learning_rate": 8.135228017187238e-06,
|
| 554 |
+
"loss": 0.2969,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.0821917808219177,
|
| 559 |
+
"grad_norm": 0.5731699767134483,
|
| 560 |
+
"learning_rate": 8.0727191559294e-06,
|
| 561 |
+
"loss": 0.2835,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.095890410958904,
|
| 566 |
+
"grad_norm": 0.5596080529256069,
|
| 567 |
+
"learning_rate": 8.009428881086836e-06,
|
| 568 |
+
"loss": 0.3078,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.1095890410958904,
|
| 573 |
+
"grad_norm": 0.5638954322443812,
|
| 574 |
+
"learning_rate": 7.945373287811116e-06,
|
| 575 |
+
"loss": 0.2332,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.1232876712328768,
|
| 580 |
+
"grad_norm": 0.5129998785020614,
|
| 581 |
+
"learning_rate": 7.880568665879542e-06,
|
| 582 |
+
"loss": 0.2494,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 1.1369863013698631,
|
| 587 |
+
"grad_norm": 0.5820798550577473,
|
| 588 |
+
"learning_rate": 7.81503149555255e-06,
|
| 589 |
+
"loss": 0.3014,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.1506849315068493,
|
| 594 |
+
"grad_norm": 0.5860949437859232,
|
| 595 |
+
"learning_rate": 7.748778443382658e-06,
|
| 596 |
+
"loss": 0.2684,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.1643835616438356,
|
| 601 |
+
"grad_norm": 0.563363854418844,
|
| 602 |
+
"learning_rate": 7.68182635797606e-06,
|
| 603 |
+
"loss": 0.2688,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.178082191780822,
|
| 608 |
+
"grad_norm": 0.5724895638568498,
|
| 609 |
+
"learning_rate": 7.6141922657079045e-06,
|
| 610 |
+
"loss": 0.2822,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.191780821917808,
|
| 615 |
+
"grad_norm": 0.5509356742221773,
|
| 616 |
+
"learning_rate": 7.545893366392358e-06,
|
| 617 |
+
"loss": 0.2939,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.2054794520547945,
|
| 622 |
+
"grad_norm": 0.5363319816988867,
|
| 623 |
+
"learning_rate": 7.476947028908595e-06,
|
| 624 |
+
"loss": 0.2571,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.2191780821917808,
|
| 629 |
+
"grad_norm": 0.5057649104760942,
|
| 630 |
+
"learning_rate": 7.407370786783757e-06,
|
| 631 |
+
"loss": 0.2285,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.2328767123287672,
|
| 636 |
+
"grad_norm": 0.5436043669187894,
|
| 637 |
+
"learning_rate": 7.33718233373407e-06,
|
| 638 |
+
"loss": 0.2908,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.2465753424657535,
|
| 643 |
+
"grad_norm": 0.5447149924954856,
|
| 644 |
+
"learning_rate": 7.266399519165193e-06,
|
| 645 |
+
"loss": 0.2572,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.2602739726027397,
|
| 650 |
+
"grad_norm": 0.5187716905978955,
|
| 651 |
+
"learning_rate": 7.195040343633006e-06,
|
| 652 |
+
"loss": 0.2675,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.273972602739726,
|
| 657 |
+
"grad_norm": 0.5595936637649671,
|
| 658 |
+
"learning_rate": 7.123122954265942e-06,
|
| 659 |
+
"loss": 0.278,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.2876712328767124,
|
| 664 |
+
"grad_norm": 0.5261591293424116,
|
| 665 |
+
"learning_rate": 7.050665640150045e-06,
|
| 666 |
+
"loss": 0.2649,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.3013698630136985,
|
| 671 |
+
"grad_norm": 0.5270715295341053,
|
| 672 |
+
"learning_rate": 6.977686827677926e-06,
|
| 673 |
+
"loss": 0.275,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.3150684931506849,
|
| 678 |
+
"grad_norm": 0.556369323261503,
|
| 679 |
+
"learning_rate": 6.904205075862816e-06,
|
| 680 |
+
"loss": 0.2633,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.3287671232876712,
|
| 685 |
+
"grad_norm": 0.5555674767813581,
|
| 686 |
+
"learning_rate": 6.830239071618874e-06,
|
| 687 |
+
"loss": 0.2421,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.3424657534246576,
|
| 692 |
+
"grad_norm": 0.535436439367427,
|
| 693 |
+
"learning_rate": 6.755807625008974e-06,
|
| 694 |
+
"loss": 0.2533,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 1.356164383561644,
|
| 699 |
+
"grad_norm": 0.5814891791046758,
|
| 700 |
+
"learning_rate": 6.680929664461184e-06,
|
| 701 |
+
"loss": 0.2923,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.36986301369863,
|
| 706 |
+
"grad_norm": 0.6144450850540146,
|
| 707 |
+
"learning_rate": 6.6056242319551315e-06,
|
| 708 |
+
"loss": 0.2928,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.3835616438356164,
|
| 713 |
+
"grad_norm": 0.5902751077265254,
|
| 714 |
+
"learning_rate": 6.529910478179499e-06,
|
| 715 |
+
"loss": 0.3264,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 1.3972602739726028,
|
| 720 |
+
"grad_norm": 0.5175445081068616,
|
| 721 |
+
"learning_rate": 6.45380765766187e-06,
|
| 722 |
+
"loss": 0.258,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.410958904109589,
|
| 727 |
+
"grad_norm": 0.5809094017457281,
|
| 728 |
+
"learning_rate": 6.377335123872177e-06,
|
| 729 |
+
"loss": 0.2556,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.4246575342465753,
|
| 734 |
+
"grad_norm": 0.5442606015258069,
|
| 735 |
+
"learning_rate": 6.300512324300975e-06,
|
| 736 |
+
"loss": 0.2864,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.4383561643835616,
|
| 741 |
+
"grad_norm": 0.5727394997266216,
|
| 742 |
+
"learning_rate": 6.223358795513812e-06,
|
| 743 |
+
"loss": 0.2552,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.452054794520548,
|
| 748 |
+
"grad_norm": 0.5300673079637859,
|
| 749 |
+
"learning_rate": 6.145894158182945e-06,
|
| 750 |
+
"loss": 0.245,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.4657534246575343,
|
| 755 |
+
"grad_norm": 0.545463299232601,
|
| 756 |
+
"learning_rate": 6.0681381120976745e-06,
|
| 757 |
+
"loss": 0.2753,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.4794520547945205,
|
| 762 |
+
"grad_norm": 0.5377711308930468,
|
| 763 |
+
"learning_rate": 5.990110431154549e-06,
|
| 764 |
+
"loss": 0.2808,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.4931506849315068,
|
| 769 |
+
"grad_norm": 0.5533928789823335,
|
| 770 |
+
"learning_rate": 5.9118309583287205e-06,
|
| 771 |
+
"loss": 0.2591,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 1.5068493150684932,
|
| 776 |
+
"grad_norm": 0.5266036701592406,
|
| 777 |
+
"learning_rate": 5.8333196006277536e-06,
|
| 778 |
+
"loss": 0.3354,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.5205479452054793,
|
| 783 |
+
"grad_norm": 0.5912384789495004,
|
| 784 |
+
"learning_rate": 5.754596324029125e-06,
|
| 785 |
+
"loss": 0.2526,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.5342465753424657,
|
| 790 |
+
"grad_norm": 0.541721412221213,
|
| 791 |
+
"learning_rate": 5.675681148402743e-06,
|
| 792 |
+
"loss": 0.2537,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 1.547945205479452,
|
| 797 |
+
"grad_norm": 0.5658927714711918,
|
| 798 |
+
"learning_rate": 5.596594142419759e-06,
|
| 799 |
+
"loss": 0.3343,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 1.5616438356164384,
|
| 804 |
+
"grad_norm": 0.5284050054712385,
|
| 805 |
+
"learning_rate": 5.517355418448961e-06,
|
| 806 |
+
"loss": 0.2454,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.5753424657534247,
|
| 811 |
+
"grad_norm": 0.5254831524550178,
|
| 812 |
+
"learning_rate": 5.437985127442065e-06,
|
| 813 |
+
"loss": 0.2782,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 1.589041095890411,
|
| 818 |
+
"grad_norm": 0.529102854689219,
|
| 819 |
+
"learning_rate": 5.3585034538091885e-06,
|
| 820 |
+
"loss": 0.2633,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 1.6027397260273972,
|
| 825 |
+
"grad_norm": 0.5342738860253239,
|
| 826 |
+
"learning_rate": 5.278930610285813e-06,
|
| 827 |
+
"loss": 0.2261,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 1.6164383561643836,
|
| 832 |
+
"grad_norm": 0.5137694315107021,
|
| 833 |
+
"learning_rate": 5.199286832792553e-06,
|
| 834 |
+
"loss": 0.2315,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 1.6301369863013697,
|
| 839 |
+
"grad_norm": 0.519478951814081,
|
| 840 |
+
"learning_rate": 5.119592375289015e-06,
|
| 841 |
+
"loss": 0.295,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 1.643835616438356,
|
| 846 |
+
"grad_norm": 0.5512666805902274,
|
| 847 |
+
"learning_rate": 5.039867504623084e-06,
|
| 848 |
+
"loss": 0.2276,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.6575342465753424,
|
| 853 |
+
"grad_norm": 0.5119337064403229,
|
| 854 |
+
"learning_rate": 4.960132495376919e-06,
|
| 855 |
+
"loss": 0.276,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 1.6712328767123288,
|
| 860 |
+
"grad_norm": 0.5685662217269354,
|
| 861 |
+
"learning_rate": 4.880407624710986e-06,
|
| 862 |
+
"loss": 0.2886,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 1.6849315068493151,
|
| 867 |
+
"grad_norm": 0.5585276705083959,
|
| 868 |
+
"learning_rate": 4.800713167207449e-06,
|
| 869 |
+
"loss": 0.2911,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 1.6986301369863015,
|
| 874 |
+
"grad_norm": 0.5544086931950164,
|
| 875 |
+
"learning_rate": 4.721069389714188e-06,
|
| 876 |
+
"loss": 0.2931,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 1.7123287671232876,
|
| 881 |
+
"grad_norm": 0.5183703372212171,
|
| 882 |
+
"learning_rate": 4.641496546190813e-06,
|
| 883 |
+
"loss": 0.2429,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 1.726027397260274,
|
| 888 |
+
"grad_norm": 0.5501662699279504,
|
| 889 |
+
"learning_rate": 4.562014872557936e-06,
|
| 890 |
+
"loss": 0.2898,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 1.7397260273972601,
|
| 895 |
+
"grad_norm": 0.5935691455739288,
|
| 896 |
+
"learning_rate": 4.48264458155104e-06,
|
| 897 |
+
"loss": 0.2853,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 1.7534246575342465,
|
| 902 |
+
"grad_norm": 0.47705900931285083,
|
| 903 |
+
"learning_rate": 4.403405857580243e-06,
|
| 904 |
+
"loss": 0.2457,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 1.7671232876712328,
|
| 909 |
+
"grad_norm": 0.5302361811027393,
|
| 910 |
+
"learning_rate": 4.3243188515972575e-06,
|
| 911 |
+
"loss": 0.282,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 1.7808219178082192,
|
| 916 |
+
"grad_norm": 0.5207725400711429,
|
| 917 |
+
"learning_rate": 4.245403675970877e-06,
|
| 918 |
+
"loss": 0.2653,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 1.7945205479452055,
|
| 923 |
+
"grad_norm": 0.5171045408832986,
|
| 924 |
+
"learning_rate": 4.166680399372248e-06,
|
| 925 |
+
"loss": 0.2535,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 1.808219178082192,
|
| 930 |
+
"grad_norm": 0.5446445460257779,
|
| 931 |
+
"learning_rate": 4.08816904167128e-06,
|
| 932 |
+
"loss": 0.2786,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 1.821917808219178,
|
| 937 |
+
"grad_norm": 0.5644383885565699,
|
| 938 |
+
"learning_rate": 4.009889568845453e-06,
|
| 939 |
+
"loss": 0.2588,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.8356164383561644,
|
| 944 |
+
"grad_norm": 0.54866666314673,
|
| 945 |
+
"learning_rate": 3.9318618879023255e-06,
|
| 946 |
+
"loss": 0.276,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 1.8493150684931505,
|
| 951 |
+
"grad_norm": 0.5331494721217096,
|
| 952 |
+
"learning_rate": 3.854105841817056e-06,
|
| 953 |
+
"loss": 0.2486,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 1.8630136986301369,
|
| 958 |
+
"grad_norm": 0.6183550187762842,
|
| 959 |
+
"learning_rate": 3.776641204486191e-06,
|
| 960 |
+
"loss": 0.3044,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 1.8767123287671232,
|
| 965 |
+
"grad_norm": 0.6460508272689064,
|
| 966 |
+
"learning_rate": 3.699487675699027e-06,
|
| 967 |
+
"loss": 0.2668,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 1.8904109589041096,
|
| 972 |
+
"grad_norm": 0.5288849383910833,
|
| 973 |
+
"learning_rate": 3.6226648761278238e-06,
|
| 974 |
+
"loss": 0.263,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 1.904109589041096,
|
| 979 |
+
"grad_norm": 0.5520634423352098,
|
| 980 |
+
"learning_rate": 3.5461923423381313e-06,
|
| 981 |
+
"loss": 0.2641,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 1.9178082191780823,
|
| 986 |
+
"grad_norm": 0.5469755940931316,
|
| 987 |
+
"learning_rate": 3.4700895218205026e-06,
|
| 988 |
+
"loss": 0.2841,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 1.9315068493150684,
|
| 993 |
+
"grad_norm": 0.5873481478129947,
|
| 994 |
+
"learning_rate": 3.3943757680448697e-06,
|
| 995 |
+
"loss": 0.2793,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 1.9452054794520548,
|
| 1000 |
+
"grad_norm": 0.5416971398564479,
|
| 1001 |
+
"learning_rate": 3.3190703355388165e-06,
|
| 1002 |
+
"loss": 0.2646,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 1.958904109589041,
|
| 1007 |
+
"grad_norm": 0.5420206676528927,
|
| 1008 |
+
"learning_rate": 3.244192374991027e-06,
|
| 1009 |
+
"loss": 0.2544,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 1.9726027397260273,
|
| 1014 |
+
"grad_norm": 0.535688446995686,
|
| 1015 |
+
"learning_rate": 3.169760928381127e-06,
|
| 1016 |
+
"loss": 0.2838,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 1.9863013698630136,
|
| 1021 |
+
"grad_norm": 0.5758663260506761,
|
| 1022 |
+
"learning_rate": 3.0957949241371845e-06,
|
| 1023 |
+
"loss": 0.2582,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
{
|
| 1027 |
"epoch": 2.0,
|
| 1028 |
+
"grad_norm": 0.5423112459351196,
|
| 1029 |
+
"learning_rate": 3.0223131723220756e-06,
|
| 1030 |
+
"loss": 0.2092,
|
| 1031 |
+
"step": 146
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 2.0136986301369864,
|
| 1035 |
+
"grad_norm": 0.5748656765471171,
|
| 1036 |
+
"learning_rate": 2.949334359849957e-06,
|
| 1037 |
+
"loss": 0.2165,
|
| 1038 |
+
"step": 147
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 2.0273972602739727,
|
| 1042 |
+
"grad_norm": 0.5812711248684536,
|
| 1043 |
+
"learning_rate": 2.876877045734058e-06,
|
| 1044 |
+
"loss": 0.2247,
|
| 1045 |
+
"step": 148
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 2.041095890410959,
|
| 1049 |
+
"grad_norm": 0.5108152620715224,
|
| 1050 |
+
"learning_rate": 2.8049596563669936e-06,
|
| 1051 |
+
"loss": 0.1997,
|
| 1052 |
+
"step": 149
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 2.0547945205479454,
|
| 1056 |
+
"grad_norm": 0.5319905935091304,
|
| 1057 |
+
"learning_rate": 2.7336004808348094e-06,
|
| 1058 |
+
"loss": 0.2302,
|
| 1059 |
+
"step": 150
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 2.0684931506849313,
|
| 1063 |
+
"grad_norm": 0.4977057243011831,
|
| 1064 |
+
"learning_rate": 2.662817666265932e-06,
|
| 1065 |
+
"loss": 0.2337,
|
| 1066 |
+
"step": 151
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 2.0821917808219177,
|
| 1070 |
+
"grad_norm": 0.49966208843602644,
|
| 1071 |
+
"learning_rate": 2.5926292132162432e-06,
|
| 1072 |
+
"loss": 0.2303,
|
| 1073 |
+
"step": 152
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 2.095890410958904,
|
| 1077 |
+
"grad_norm": 0.5291383837159909,
|
| 1078 |
+
"learning_rate": 2.5230529710914074e-06,
|
| 1079 |
+
"loss": 0.2373,
|
| 1080 |
+
"step": 153
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 2.1095890410958904,
|
| 1084 |
+
"grad_norm": 0.5212335952508754,
|
| 1085 |
+
"learning_rate": 2.4541066336076434e-06,
|
| 1086 |
+
"loss": 0.1983,
|
| 1087 |
+
"step": 154
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 2.1232876712328768,
|
| 1091 |
+
"grad_norm": 0.6468598665123299,
|
| 1092 |
+
"learning_rate": 2.385807734292097e-06,
|
| 1093 |
+
"loss": 0.3069,
|
| 1094 |
+
"step": 155
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 2.136986301369863,
|
| 1098 |
+
"grad_norm": 0.5154051184203585,
|
| 1099 |
+
"learning_rate": 2.318173642023939e-06,
|
| 1100 |
+
"loss": 0.2487,
|
| 1101 |
+
"step": 156
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 2.1506849315068495,
|
| 1105 |
+
"grad_norm": 0.5710904036349707,
|
| 1106 |
+
"learning_rate": 2.251221556617344e-06,
|
| 1107 |
+
"loss": 0.2513,
|
| 1108 |
+
"step": 157
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 2.1643835616438354,
|
| 1112 |
+
"grad_norm": 0.5522744399817583,
|
| 1113 |
+
"learning_rate": 2.184968504447453e-06,
|
| 1114 |
+
"loss": 0.2337,
|
| 1115 |
+
"step": 158
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 2.1780821917808217,
|
| 1119 |
+
"grad_norm": 0.504662185035172,
|
| 1120 |
+
"learning_rate": 2.11943133412046e-06,
|
| 1121 |
+
"loss": 0.1819,
|
| 1122 |
+
"step": 159
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 2.191780821917808,
|
| 1126 |
+
"grad_norm": 0.5284658788057356,
|
| 1127 |
+
"learning_rate": 2.0546267121888863e-06,
|
| 1128 |
+
"loss": 0.2157,
|
| 1129 |
+
"step": 160
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 2.2054794520547945,
|
| 1133 |
+
"grad_norm": 0.6006401896732142,
|
| 1134 |
+
"learning_rate": 1.990571118913166e-06,
|
| 1135 |
+
"loss": 0.2337,
|
| 1136 |
+
"step": 161
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 2.219178082191781,
|
| 1140 |
+
"grad_norm": 0.5574674320975703,
|
| 1141 |
+
"learning_rate": 1.9272808440706024e-06,
|
| 1142 |
+
"loss": 0.2319,
|
| 1143 |
+
"step": 162
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 2.232876712328767,
|
| 1147 |
+
"grad_norm": 0.531100925481991,
|
| 1148 |
+
"learning_rate": 1.864771982812763e-06,
|
| 1149 |
+
"loss": 0.2067,
|
| 1150 |
+
"step": 163
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 2.2465753424657535,
|
| 1154 |
+
"grad_norm": 0.48950862001219997,
|
| 1155 |
+
"learning_rate": 1.8030604315723765e-06,
|
| 1156 |
+
"loss": 0.1983,
|
| 1157 |
+
"step": 164
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 2.26027397260274,
|
| 1161 |
+
"grad_norm": 0.5378366125563677,
|
| 1162 |
+
"learning_rate": 1.7421618840207576e-06,
|
| 1163 |
+
"loss": 0.2062,
|
| 1164 |
+
"step": 165
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 2.2739726027397262,
|
| 1168 |
+
"grad_norm": 0.5696491800713778,
|
| 1169 |
+
"learning_rate": 1.682091827076796e-06,
|
| 1170 |
+
"loss": 0.2391,
|
| 1171 |
+
"step": 166
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 2.287671232876712,
|
| 1175 |
+
"grad_norm": 0.5697069187287241,
|
| 1176 |
+
"learning_rate": 1.6228655369685342e-06,
|
| 1177 |
+
"loss": 0.2615,
|
| 1178 |
+
"step": 167
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 2.3013698630136985,
|
| 1182 |
+
"grad_norm": 0.5218858820665893,
|
| 1183 |
+
"learning_rate": 1.5644980753483109e-06,
|
| 1184 |
+
"loss": 0.2346,
|
| 1185 |
+
"step": 168
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 2.315068493150685,
|
| 1189 |
+
"grad_norm": 0.5161376628326411,
|
| 1190 |
+
"learning_rate": 1.5070042854624833e-06,
|
| 1191 |
+
"loss": 0.2281,
|
| 1192 |
+
"step": 169
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 2.328767123287671,
|
| 1196 |
+
"grad_norm": 0.5545958003378002,
|
| 1197 |
+
"learning_rate": 1.4503987883766857e-06,
|
| 1198 |
+
"loss": 0.2411,
|
| 1199 |
+
"step": 170
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 2.3424657534246576,
|
| 1203 |
+
"grad_norm": 0.537439441326481,
|
| 1204 |
+
"learning_rate": 1.3946959792575915e-06,
|
| 1205 |
+
"loss": 0.214,
|
| 1206 |
+
"step": 171
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 2.356164383561644,
|
| 1210 |
+
"grad_norm": 0.5139230513757913,
|
| 1211 |
+
"learning_rate": 1.3399100237121266e-06,
|
| 1212 |
+
"loss": 0.1733,
|
| 1213 |
+
"step": 172
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 2.3698630136986303,
|
| 1217 |
+
"grad_norm": 0.4887244916875088,
|
| 1218 |
+
"learning_rate": 1.2860548541850542e-06,
|
| 1219 |
+
"loss": 0.191,
|
| 1220 |
+
"step": 173
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 2.383561643835616,
|
| 1224 |
+
"grad_norm": 0.5390739819968635,
|
| 1225 |
+
"learning_rate": 1.233144166415861e-06,
|
| 1226 |
+
"loss": 0.2372,
|
| 1227 |
+
"step": 174
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 2.3972602739726026,
|
| 1231 |
+
"grad_norm": 0.48410838913562393,
|
| 1232 |
+
"learning_rate": 1.1811914159558374e-06,
|
| 1233 |
+
"loss": 0.187,
|
| 1234 |
+
"step": 175
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 2.410958904109589,
|
| 1238 |
+
"grad_norm": 0.5135693972833678,
|
| 1239 |
+
"learning_rate": 1.1302098147462348e-06,
|
| 1240 |
+
"loss": 0.2357,
|
| 1241 |
+
"step": 176
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 2.4246575342465753,
|
| 1245 |
+
"grad_norm": 0.5373615943185261,
|
| 1246 |
+
"learning_rate": 1.080212327758382e-06,
|
| 1247 |
+
"loss": 0.2322,
|
| 1248 |
+
"step": 177
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 2.4383561643835616,
|
| 1252 |
+
"grad_norm": 0.5158850004818074,
|
| 1253 |
+
"learning_rate": 1.0312116696966012e-06,
|
| 1254 |
+
"loss": 0.1893,
|
| 1255 |
+
"step": 178
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 2.452054794520548,
|
| 1259 |
+
"grad_norm": 0.5519073855595148,
|
| 1260 |
+
"learning_rate": 9.832203017647746e-07,
|
| 1261 |
+
"loss": 0.2097,
|
| 1262 |
+
"step": 179
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 2.4657534246575343,
|
| 1266 |
+
"grad_norm": 0.5017085918962575,
|
| 1267 |
+
"learning_rate": 9.362504284973683e-07,
|
| 1268 |
+
"loss": 0.187,
|
| 1269 |
+
"step": 180
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 2.4794520547945207,
|
| 1273 |
+
"grad_norm": 0.5130783119417842,
|
| 1274 |
+
"learning_rate": 8.903139946557437e-07,
|
| 1275 |
+
"loss": 0.2157,
|
| 1276 |
+
"step": 181
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 2.493150684931507,
|
| 1280 |
+
"grad_norm": 0.5389267286866157,
|
| 1281 |
+
"learning_rate": 8.454226821905171e-07,
|
| 1282 |
+
"loss": 0.2315,
|
| 1283 |
+
"step": 182
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 2.506849315068493,
|
| 1287 |
+
"grad_norm": 0.5233789862184065,
|
| 1288 |
+
"learning_rate": 8.015879072707611e-07,
|
| 1289 |
+
"loss": 0.2128,
|
| 1290 |
+
"step": 183
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 2.5205479452054793,
|
| 1294 |
+
"grad_norm": 0.4994050322522943,
|
| 1295 |
+
"learning_rate": 7.588208173807943e-07,
|
| 1296 |
+
"loss": 0.21,
|
| 1297 |
+
"step": 184
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 2.5342465753424657,
|
| 1301 |
+
"grad_norm": 0.5679474653520452,
|
| 1302 |
+
"learning_rate": 7.171322884852988e-07,
|
| 1303 |
+
"loss": 0.227,
|
| 1304 |
+
"step": 185
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 2.547945205479452,
|
| 1308 |
+
"grad_norm": 0.4901253211724444,
|
| 1309 |
+
"learning_rate": 6.765329222634892e-07,
|
| 1310 |
+
"loss": 0.2004,
|
| 1311 |
+
"step": 186
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 2.5616438356164384,
|
| 1315 |
+
"grad_norm": 0.5344019882677575,
|
| 1316 |
+
"learning_rate": 6.370330434130317e-07,
|
| 1317 |
+
"loss": 0.2319,
|
| 1318 |
+
"step": 187
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 2.5753424657534247,
|
| 1322 |
+
"grad_norm": 0.5477249705653034,
|
| 1323 |
+
"learning_rate": 5.986426970244009e-07,
|
| 1324 |
+
"loss": 0.242,
|
| 1325 |
+
"step": 188
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 2.589041095890411,
|
| 1329 |
+
"grad_norm": 0.45770911123213665,
|
| 1330 |
+
"learning_rate": 5.613716460263485e-07,
|
| 1331 |
+
"loss": 0.1823,
|
| 1332 |
+
"step": 189
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 2.602739726027397,
|
| 1336 |
+
"grad_norm": 0.5352703597126046,
|
| 1337 |
+
"learning_rate": 5.252293687031196e-07,
|
| 1338 |
+
"loss": 0.2112,
|
| 1339 |
+
"step": 190
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 2.616438356164384,
|
| 1343 |
+
"grad_norm": 0.4950710305983482,
|
| 1344 |
+
"learning_rate": 4.902250562840622e-07,
|
| 1345 |
+
"loss": 0.2016,
|
| 1346 |
+
"step": 191
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 2.6301369863013697,
|
| 1350 |
+
"grad_norm": 0.5471496379803641,
|
| 1351 |
+
"learning_rate": 4.5636761060623314e-07,
|
| 1352 |
+
"loss": 0.2507,
|
| 1353 |
+
"step": 192
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 2.643835616438356,
|
| 1357 |
+
"grad_norm": 0.5241424656059378,
|
| 1358 |
+
"learning_rate": 4.2366564185060134e-07,
|
| 1359 |
+
"loss": 0.2042,
|
| 1360 |
+
"step": 193
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 2.6575342465753424,
|
| 1364 |
+
"grad_norm": 0.5367033886521897,
|
| 1365 |
+
"learning_rate": 3.921274663524183e-07,
|
| 1366 |
+
"loss": 0.2087,
|
| 1367 |
+
"step": 194
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 2.671232876712329,
|
| 1371 |
+
"grad_norm": 0.539959003498879,
|
| 1372 |
+
"learning_rate": 3.61761104486314e-07,
|
| 1373 |
+
"loss": 0.2578,
|
| 1374 |
+
"step": 195
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 2.684931506849315,
|
| 1378 |
+
"grad_norm": 0.5370864788515491,
|
| 1379 |
+
"learning_rate": 3.3257427862666894e-07,
|
| 1380 |
+
"loss": 0.2471,
|
| 1381 |
+
"step": 196
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 2.6986301369863015,
|
| 1385 |
+
"grad_norm": 0.5382409255829738,
|
| 1386 |
+
"learning_rate": 3.045744111837529e-07,
|
| 1387 |
+
"loss": 0.2304,
|
| 1388 |
+
"step": 197
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 2.712328767123288,
|
| 1392 |
+
"grad_norm": 0.4874312382394395,
|
| 1393 |
+
"learning_rate": 2.777686227161591e-07,
|
| 1394 |
+
"loss": 0.1633,
|
| 1395 |
+
"step": 198
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 2.7260273972602738,
|
| 1399 |
+
"grad_norm": 0.48530434650570287,
|
| 1400 |
+
"learning_rate": 2.5216373011999697e-07,
|
| 1401 |
+
"loss": 0.2266,
|
| 1402 |
+
"step": 199
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 2.73972602739726,
|
| 1406 |
+
"grad_norm": 0.516529966832154,
|
| 1407 |
+
"learning_rate": 2.2776624489530664e-07,
|
| 1408 |
+
"loss": 0.234,
|
| 1409 |
+
"step": 200
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 2.7534246575342465,
|
| 1413 |
+
"grad_norm": 0.49198285843124256,
|
| 1414 |
+
"learning_rate": 2.0458237149014347e-07,
|
| 1415 |
+
"loss": 0.2286,
|
| 1416 |
+
"step": 201
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 2.767123287671233,
|
| 1420 |
+
"grad_norm": 0.5628930578689073,
|
| 1421 |
+
"learning_rate": 1.8261800572274001e-07,
|
| 1422 |
+
"loss": 0.2296,
|
| 1423 |
+
"step": 202
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 2.780821917808219,
|
| 1427 |
+
"grad_norm": 0.5128850573323045,
|
| 1428 |
+
"learning_rate": 1.6187873328216142e-07,
|
| 1429 |
+
"loss": 0.2116,
|
| 1430 |
+
"step": 203
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 2.7945205479452055,
|
| 1434 |
+
"grad_norm": 0.5257141185804697,
|
| 1435 |
+
"learning_rate": 1.4236982830782676e-07,
|
| 1436 |
+
"loss": 0.2032,
|
| 1437 |
+
"step": 204
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 2.808219178082192,
|
| 1441 |
+
"grad_norm": 0.530326476668592,
|
| 1442 |
+
"learning_rate": 1.2409625204825802e-07,
|
| 1443 |
+
"loss": 0.2345,
|
| 1444 |
+
"step": 205
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 2.821917808219178,
|
| 1448 |
+
"grad_norm": 0.4878232959939308,
|
| 1449 |
+
"learning_rate": 1.0706265159939944e-07,
|
| 1450 |
+
"loss": 0.19,
|
| 1451 |
+
"step": 206
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 2.8356164383561646,
|
| 1455 |
+
"grad_norm": 0.48868333300275113,
|
| 1456 |
+
"learning_rate": 9.12733587228326e-08,
|
| 1457 |
+
"loss": 0.1803,
|
| 1458 |
+
"step": 207
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 2.8493150684931505,
|
| 1462 |
+
"grad_norm": 0.5072984875795505,
|
| 1463 |
+
"learning_rate": 7.673238874417676e-08,
|
| 1464 |
+
"loss": 0.1956,
|
| 1465 |
+
"step": 208
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 2.863013698630137,
|
| 1469 |
+
"grad_norm": 0.5212480182362544,
|
| 1470 |
+
"learning_rate": 6.344343953196386e-08,
|
| 1471 |
+
"loss": 0.2221,
|
| 1472 |
+
"step": 209
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 2.8767123287671232,
|
| 1476 |
+
"grad_norm": 0.5420925850203508,
|
| 1477 |
+
"learning_rate": 5.1409890557246876e-08,
|
| 1478 |
+
"loss": 0.2437,
|
| 1479 |
+
"step": 210
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 2.8904109589041096,
|
| 1483 |
+
"grad_norm": 0.5344487774832275,
|
| 1484 |
+
"learning_rate": 4.063480203417625e-08,
|
| 1485 |
+
"loss": 0.2314,
|
| 1486 |
+
"step": 211
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 2.904109589041096,
|
| 1490 |
+
"grad_norm": 0.4959162109141275,
|
| 1491 |
+
"learning_rate": 3.1120914141766214e-08,
|
| 1492 |
+
"loss": 0.249,
|
| 1493 |
+
"step": 212
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 2.9178082191780823,
|
| 1497 |
+
"grad_norm": 0.497324311904558,
|
| 1498 |
+
"learning_rate": 2.287064632705005e-08,
|
| 1499 |
+
"loss": 0.2131,
|
| 1500 |
+
"step": 213
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 2.9315068493150687,
|
| 1504 |
+
"grad_norm": 0.5118131436420149,
|
| 1505 |
+
"learning_rate": 1.588609668979446e-08,
|
| 1506 |
+
"loss": 0.2178,
|
| 1507 |
+
"step": 214
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 2.9452054794520546,
|
| 1511 |
+
"grad_norm": 0.4960404282762548,
|
| 1512 |
+
"learning_rate": 1.016904144894304e-08,
|
| 1513 |
+
"loss": 0.2207,
|
| 1514 |
+
"step": 215
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 2.958904109589041,
|
| 1518 |
+
"grad_norm": 0.5644673659667615,
|
| 1519 |
+
"learning_rate": 5.720934490907604e-09,
|
| 1520 |
+
"loss": 0.2142,
|
| 1521 |
+
"step": 216
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 2.9726027397260273,
|
| 1525 |
+
"grad_norm": 0.48284047194050117,
|
| 1526 |
+
"learning_rate": 2.542906999836725e-09,
|
| 1527 |
+
"loss": 0.2298,
|
| 1528 |
+
"step": 217
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 2.9863013698630136,
|
| 1532 |
+
"grad_norm": 0.5051550042171722,
|
| 1533 |
+
"learning_rate": 6.357671699486201e-10,
|
| 1534 |
+
"loss": 0.2056,
|
| 1535 |
+
"step": 218
|
| 1536 |
},
|
| 1537 |
{
|
| 1538 |
"epoch": 3.0,
|
| 1539 |
+
"grad_norm": 0.500169473170659,
|
| 1540 |
+
"learning_rate": 0.0,
|
| 1541 |
+
"loss": 0.1987,
|
| 1542 |
+
"step": 219
|
|
|
|
| 1543 |
},
|
| 1544 |
{
|
| 1545 |
"epoch": 3.0,
|
| 1546 |
+
"step": 219,
|
| 1547 |
+
"total_flos": 45867016224768.0,
|
| 1548 |
+
"train_loss": 0.2807643291748822,
|
| 1549 |
+
"train_runtime": 547.5472,
|
| 1550 |
+
"train_samples_per_second": 37.92,
|
| 1551 |
+
"train_steps_per_second": 0.4
|
| 1552 |
}
|
| 1553 |
],
|
| 1554 |
+
"logging_steps": 1,
|
| 1555 |
+
"max_steps": 219,
|
| 1556 |
"num_input_tokens_seen": 0,
|
| 1557 |
"num_train_epochs": 3,
|
| 1558 |
"save_steps": 500,
|
|
|
|
| 1568 |
"attributes": {}
|
| 1569 |
}
|
| 1570 |
},
|
| 1571 |
+
"total_flos": 45867016224768.0,
|
| 1572 |
+
"train_batch_size": 3,
|
| 1573 |
"trial_name": null,
|
| 1574 |
"trial_params": null
|
| 1575 |
}
|
training_loss.png
CHANGED
|
|