End of training
Browse files- README.md +7 -7
- all_results.json +16 -0
- eval_results.json +11 -0
- train_results.json +8 -0
- trainer_state.json +926 -0
README.md
CHANGED
|
@@ -26,16 +26,16 @@ model-index:
|
|
| 26 |
metrics:
|
| 27 |
- name: Accuracy
|
| 28 |
type: accuracy
|
| 29 |
-
value: 0
|
| 30 |
- name: Precision
|
| 31 |
type: precision
|
| 32 |
-
value: 0
|
| 33 |
- name: Recall
|
| 34 |
type: recall
|
| 35 |
value: 1.0
|
| 36 |
- name: F1
|
| 37 |
type: f1
|
| 38 |
-
value: 0
|
| 39 |
---
|
| 40 |
|
| 41 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -45,11 +45,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 45 |
|
| 46 |
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
|
| 47 |
It achieves the following results on the evaluation set:
|
| 48 |
-
- Loss: 0.
|
| 49 |
-
- Accuracy: 0
|
| 50 |
-
- Precision: 0
|
| 51 |
- Recall: 1.0
|
| 52 |
-
- F1: 0
|
| 53 |
|
| 54 |
## Model description
|
| 55 |
|
|
|
|
| 26 |
metrics:
|
| 27 |
- name: Accuracy
|
| 28 |
type: accuracy
|
| 29 |
+
value: 1.0
|
| 30 |
- name: Precision
|
| 31 |
type: precision
|
| 32 |
+
value: 1.0
|
| 33 |
- name: Recall
|
| 34 |
type: recall
|
| 35 |
value: 1.0
|
| 36 |
- name: F1
|
| 37 |
type: f1
|
| 38 |
+
value: 1.0
|
| 39 |
---
|
| 40 |
|
| 41 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 45 |
|
| 46 |
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
|
| 47 |
It achieves the following results on the evaluation set:
|
| 48 |
+
- Loss: 0.0072
|
| 49 |
+
- Accuracy: 1.0
|
| 50 |
+
- Precision: 1.0
|
| 51 |
- Recall: 1.0
|
| 52 |
+
- F1: 1.0
|
| 53 |
|
| 54 |
## Model description
|
| 55 |
|
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"eval_accuracy": 1.0,
|
| 4 |
+
"eval_f1": 1.0,
|
| 5 |
+
"eval_loss": 0.00724475271999836,
|
| 6 |
+
"eval_precision": 1.0,
|
| 7 |
+
"eval_recall": 1.0,
|
| 8 |
+
"eval_runtime": 0.6251,
|
| 9 |
+
"eval_samples_per_second": 519.879,
|
| 10 |
+
"eval_steps_per_second": 17.596,
|
| 11 |
+
"total_flos": 1.4530811161131418e+18,
|
| 12 |
+
"train_loss": 0.0580909106111073,
|
| 13 |
+
"train_runtime": 291.8902,
|
| 14 |
+
"train_samples_per_second": 200.281,
|
| 15 |
+
"train_steps_per_second": 1.576
|
| 16 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"eval_accuracy": 1.0,
|
| 4 |
+
"eval_f1": 1.0,
|
| 5 |
+
"eval_loss": 0.00724475271999836,
|
| 6 |
+
"eval_precision": 1.0,
|
| 7 |
+
"eval_recall": 1.0,
|
| 8 |
+
"eval_runtime": 0.6251,
|
| 9 |
+
"eval_samples_per_second": 519.879,
|
| 10 |
+
"eval_steps_per_second": 17.596
|
| 11 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"total_flos": 1.4530811161131418e+18,
|
| 4 |
+
"train_loss": 0.0580909106111073,
|
| 5 |
+
"train_runtime": 291.8902,
|
| 6 |
+
"train_samples_per_second": 200.281,
|
| 7 |
+
"train_steps_per_second": 1.576
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,926 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.0,
|
| 3 |
+
"best_model_checkpoint": "bridalMakeupClassifier_binary/checkpoint-414",
|
| 4 |
+
"epoch": 20.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 460,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.21739130434782608,
|
| 13 |
+
"grad_norm": 7.482993125915527,
|
| 14 |
+
"learning_rate": 5.4347826086956525e-06,
|
| 15 |
+
"loss": 0.7413,
|
| 16 |
+
"step": 5
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.43478260869565216,
|
| 20 |
+
"grad_norm": 5.045105934143066,
|
| 21 |
+
"learning_rate": 1.0869565217391305e-05,
|
| 22 |
+
"loss": 0.6285,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.6521739130434783,
|
| 27 |
+
"grad_norm": 3.057001829147339,
|
| 28 |
+
"learning_rate": 1.630434782608696e-05,
|
| 29 |
+
"loss": 0.4579,
|
| 30 |
+
"step": 15
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.8695652173913043,
|
| 34 |
+
"grad_norm": 2.394951581954956,
|
| 35 |
+
"learning_rate": 2.173913043478261e-05,
|
| 36 |
+
"loss": 0.2966,
|
| 37 |
+
"step": 20
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 1.0,
|
| 41 |
+
"eval_accuracy": 0.9661538461538461,
|
| 42 |
+
"eval_f1": 0.9378531073446328,
|
| 43 |
+
"eval_loss": 0.12898202240467072,
|
| 44 |
+
"eval_precision": 0.9431818181818182,
|
| 45 |
+
"eval_recall": 0.9325842696629213,
|
| 46 |
+
"eval_runtime": 0.6116,
|
| 47 |
+
"eval_samples_per_second": 531.418,
|
| 48 |
+
"eval_steps_per_second": 17.986,
|
| 49 |
+
"step": 23
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 1.0869565217391304,
|
| 53 |
+
"grad_norm": 2.818490982055664,
|
| 54 |
+
"learning_rate": 2.7173913043478262e-05,
|
| 55 |
+
"loss": 0.1788,
|
| 56 |
+
"step": 25
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.3043478260869565,
|
| 60 |
+
"grad_norm": 2.19661545753479,
|
| 61 |
+
"learning_rate": 3.260869565217392e-05,
|
| 62 |
+
"loss": 0.1157,
|
| 63 |
+
"step": 30
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 1.5217391304347827,
|
| 67 |
+
"grad_norm": 1.980846643447876,
|
| 68 |
+
"learning_rate": 3.804347826086957e-05,
|
| 69 |
+
"loss": 0.077,
|
| 70 |
+
"step": 35
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 1.7391304347826086,
|
| 74 |
+
"grad_norm": 1.7503933906555176,
|
| 75 |
+
"learning_rate": 4.347826086956522e-05,
|
| 76 |
+
"loss": 0.076,
|
| 77 |
+
"step": 40
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 1.9565217391304348,
|
| 81 |
+
"grad_norm": 4.313005447387695,
|
| 82 |
+
"learning_rate": 4.891304347826087e-05,
|
| 83 |
+
"loss": 0.1233,
|
| 84 |
+
"step": 45
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 2.0,
|
| 88 |
+
"eval_accuracy": 0.9876923076923076,
|
| 89 |
+
"eval_f1": 0.9777777777777779,
|
| 90 |
+
"eval_loss": 0.04074087738990784,
|
| 91 |
+
"eval_precision": 0.967032967032967,
|
| 92 |
+
"eval_recall": 0.9887640449438202,
|
| 93 |
+
"eval_runtime": 0.614,
|
| 94 |
+
"eval_samples_per_second": 529.309,
|
| 95 |
+
"eval_steps_per_second": 17.915,
|
| 96 |
+
"step": 46
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 2.1739130434782608,
|
| 100 |
+
"grad_norm": 2.5787644386291504,
|
| 101 |
+
"learning_rate": 4.9516908212560386e-05,
|
| 102 |
+
"loss": 0.0834,
|
| 103 |
+
"step": 50
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 2.391304347826087,
|
| 107 |
+
"grad_norm": 2.1645395755767822,
|
| 108 |
+
"learning_rate": 4.891304347826087e-05,
|
| 109 |
+
"loss": 0.0538,
|
| 110 |
+
"step": 55
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 2.608695652173913,
|
| 114 |
+
"grad_norm": 2.0289194583892822,
|
| 115 |
+
"learning_rate": 4.830917874396135e-05,
|
| 116 |
+
"loss": 0.0749,
|
| 117 |
+
"step": 60
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 2.8260869565217392,
|
| 121 |
+
"grad_norm": 1.7418752908706665,
|
| 122 |
+
"learning_rate": 4.770531400966184e-05,
|
| 123 |
+
"loss": 0.0469,
|
| 124 |
+
"step": 65
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 3.0,
|
| 128 |
+
"eval_accuracy": 0.9815384615384616,
|
| 129 |
+
"eval_f1": 0.967391304347826,
|
| 130 |
+
"eval_loss": 0.059426549822092056,
|
| 131 |
+
"eval_precision": 0.9368421052631579,
|
| 132 |
+
"eval_recall": 1.0,
|
| 133 |
+
"eval_runtime": 0.6222,
|
| 134 |
+
"eval_samples_per_second": 522.372,
|
| 135 |
+
"eval_steps_per_second": 17.68,
|
| 136 |
+
"step": 69
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 3.0434782608695654,
|
| 140 |
+
"grad_norm": 4.78839635848999,
|
| 141 |
+
"learning_rate": 4.710144927536232e-05,
|
| 142 |
+
"loss": 0.0729,
|
| 143 |
+
"step": 70
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 3.260869565217391,
|
| 147 |
+
"grad_norm": 2.100724697113037,
|
| 148 |
+
"learning_rate": 4.64975845410628e-05,
|
| 149 |
+
"loss": 0.0588,
|
| 150 |
+
"step": 75
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 3.4782608695652173,
|
| 154 |
+
"grad_norm": 2.4715771675109863,
|
| 155 |
+
"learning_rate": 4.589371980676328e-05,
|
| 156 |
+
"loss": 0.0537,
|
| 157 |
+
"step": 80
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 3.6956521739130435,
|
| 161 |
+
"grad_norm": 2.045220375061035,
|
| 162 |
+
"learning_rate": 4.528985507246377e-05,
|
| 163 |
+
"loss": 0.0451,
|
| 164 |
+
"step": 85
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 3.9130434782608696,
|
| 168 |
+
"grad_norm": 2.7747068405151367,
|
| 169 |
+
"learning_rate": 4.4685990338164255e-05,
|
| 170 |
+
"loss": 0.0394,
|
| 171 |
+
"step": 90
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 4.0,
|
| 175 |
+
"eval_accuracy": 0.9876923076923076,
|
| 176 |
+
"eval_f1": 0.9777777777777779,
|
| 177 |
+
"eval_loss": 0.055703382939100266,
|
| 178 |
+
"eval_precision": 0.967032967032967,
|
| 179 |
+
"eval_recall": 0.9887640449438202,
|
| 180 |
+
"eval_runtime": 0.6278,
|
| 181 |
+
"eval_samples_per_second": 517.661,
|
| 182 |
+
"eval_steps_per_second": 17.521,
|
| 183 |
+
"step": 92
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 4.130434782608695,
|
| 187 |
+
"grad_norm": 1.9641977548599243,
|
| 188 |
+
"learning_rate": 4.408212560386474e-05,
|
| 189 |
+
"loss": 0.0728,
|
| 190 |
+
"step": 95
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 4.3478260869565215,
|
| 194 |
+
"grad_norm": 3.0312821865081787,
|
| 195 |
+
"learning_rate": 4.347826086956522e-05,
|
| 196 |
+
"loss": 0.0611,
|
| 197 |
+
"step": 100
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 4.565217391304348,
|
| 201 |
+
"grad_norm": 2.8319077491760254,
|
| 202 |
+
"learning_rate": 4.2874396135265707e-05,
|
| 203 |
+
"loss": 0.0467,
|
| 204 |
+
"step": 105
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 4.782608695652174,
|
| 208 |
+
"grad_norm": 0.7883936762809753,
|
| 209 |
+
"learning_rate": 4.2270531400966186e-05,
|
| 210 |
+
"loss": 0.0433,
|
| 211 |
+
"step": 110
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 5.0,
|
| 215 |
+
"grad_norm": 3.4693968296051025,
|
| 216 |
+
"learning_rate": 4.166666666666667e-05,
|
| 217 |
+
"loss": 0.0909,
|
| 218 |
+
"step": 115
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 5.0,
|
| 222 |
+
"eval_accuracy": 0.9907692307692307,
|
| 223 |
+
"eval_f1": 0.9834254143646408,
|
| 224 |
+
"eval_loss": 0.04008618742227554,
|
| 225 |
+
"eval_precision": 0.967391304347826,
|
| 226 |
+
"eval_recall": 1.0,
|
| 227 |
+
"eval_runtime": 0.6227,
|
| 228 |
+
"eval_samples_per_second": 521.945,
|
| 229 |
+
"eval_steps_per_second": 17.666,
|
| 230 |
+
"step": 115
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 5.217391304347826,
|
| 234 |
+
"grad_norm": 2.560603618621826,
|
| 235 |
+
"learning_rate": 4.106280193236715e-05,
|
| 236 |
+
"loss": 0.0683,
|
| 237 |
+
"step": 120
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 5.434782608695652,
|
| 241 |
+
"grad_norm": 1.258954644203186,
|
| 242 |
+
"learning_rate": 4.045893719806764e-05,
|
| 243 |
+
"loss": 0.045,
|
| 244 |
+
"step": 125
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 5.6521739130434785,
|
| 248 |
+
"grad_norm": 1.6040618419647217,
|
| 249 |
+
"learning_rate": 3.985507246376812e-05,
|
| 250 |
+
"loss": 0.0334,
|
| 251 |
+
"step": 130
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 5.869565217391305,
|
| 255 |
+
"grad_norm": 2.980376720428467,
|
| 256 |
+
"learning_rate": 3.92512077294686e-05,
|
| 257 |
+
"loss": 0.05,
|
| 258 |
+
"step": 135
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 6.0,
|
| 262 |
+
"eval_accuracy": 0.9876923076923076,
|
| 263 |
+
"eval_f1": 0.9777777777777779,
|
| 264 |
+
"eval_loss": 0.025248104706406593,
|
| 265 |
+
"eval_precision": 0.967032967032967,
|
| 266 |
+
"eval_recall": 0.9887640449438202,
|
| 267 |
+
"eval_runtime": 0.6255,
|
| 268 |
+
"eval_samples_per_second": 519.608,
|
| 269 |
+
"eval_steps_per_second": 17.587,
|
| 270 |
+
"step": 138
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 6.086956521739131,
|
| 274 |
+
"grad_norm": 1.547420859336853,
|
| 275 |
+
"learning_rate": 3.864734299516908e-05,
|
| 276 |
+
"loss": 0.0215,
|
| 277 |
+
"step": 140
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 6.304347826086957,
|
| 281 |
+
"grad_norm": 1.0269052982330322,
|
| 282 |
+
"learning_rate": 3.804347826086957e-05,
|
| 283 |
+
"loss": 0.0513,
|
| 284 |
+
"step": 145
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 6.521739130434782,
|
| 288 |
+
"grad_norm": 1.4050897359848022,
|
| 289 |
+
"learning_rate": 3.743961352657005e-05,
|
| 290 |
+
"loss": 0.0324,
|
| 291 |
+
"step": 150
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 6.739130434782608,
|
| 295 |
+
"grad_norm": 2.9087464809417725,
|
| 296 |
+
"learning_rate": 3.6835748792270534e-05,
|
| 297 |
+
"loss": 0.0246,
|
| 298 |
+
"step": 155
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 6.956521739130435,
|
| 302 |
+
"grad_norm": 2.945462942123413,
|
| 303 |
+
"learning_rate": 3.6231884057971014e-05,
|
| 304 |
+
"loss": 0.0451,
|
| 305 |
+
"step": 160
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 7.0,
|
| 309 |
+
"eval_accuracy": 0.9876923076923076,
|
| 310 |
+
"eval_f1": 0.9772727272727273,
|
| 311 |
+
"eval_loss": 0.02794536016881466,
|
| 312 |
+
"eval_precision": 0.9885057471264368,
|
| 313 |
+
"eval_recall": 0.9662921348314607,
|
| 314 |
+
"eval_runtime": 0.638,
|
| 315 |
+
"eval_samples_per_second": 509.374,
|
| 316 |
+
"eval_steps_per_second": 17.24,
|
| 317 |
+
"step": 161
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 7.173913043478261,
|
| 321 |
+
"grad_norm": 0.28256598114967346,
|
| 322 |
+
"learning_rate": 3.56280193236715e-05,
|
| 323 |
+
"loss": 0.0499,
|
| 324 |
+
"step": 165
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 7.391304347826087,
|
| 328 |
+
"grad_norm": 2.3740286827087402,
|
| 329 |
+
"learning_rate": 3.502415458937198e-05,
|
| 330 |
+
"loss": 0.0358,
|
| 331 |
+
"step": 170
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 7.608695652173913,
|
| 335 |
+
"grad_norm": 1.025823950767517,
|
| 336 |
+
"learning_rate": 3.4420289855072465e-05,
|
| 337 |
+
"loss": 0.0306,
|
| 338 |
+
"step": 175
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 7.826086956521739,
|
| 342 |
+
"grad_norm": 0.7179997563362122,
|
| 343 |
+
"learning_rate": 3.381642512077295e-05,
|
| 344 |
+
"loss": 0.0231,
|
| 345 |
+
"step": 180
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 8.0,
|
| 349 |
+
"eval_accuracy": 0.9938461538461538,
|
| 350 |
+
"eval_f1": 0.9888888888888888,
|
| 351 |
+
"eval_loss": 0.02782590501010418,
|
| 352 |
+
"eval_precision": 0.978021978021978,
|
| 353 |
+
"eval_recall": 1.0,
|
| 354 |
+
"eval_runtime": 0.6231,
|
| 355 |
+
"eval_samples_per_second": 521.596,
|
| 356 |
+
"eval_steps_per_second": 17.654,
|
| 357 |
+
"step": 184
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 8.043478260869565,
|
| 361 |
+
"grad_norm": 0.5594707131385803,
|
| 362 |
+
"learning_rate": 3.321256038647343e-05,
|
| 363 |
+
"loss": 0.024,
|
| 364 |
+
"step": 185
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 8.26086956521739,
|
| 368 |
+
"grad_norm": 2.8453502655029297,
|
| 369 |
+
"learning_rate": 3.260869565217392e-05,
|
| 370 |
+
"loss": 0.03,
|
| 371 |
+
"step": 190
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 8.478260869565217,
|
| 375 |
+
"grad_norm": 1.5159822702407837,
|
| 376 |
+
"learning_rate": 3.2004830917874396e-05,
|
| 377 |
+
"loss": 0.0203,
|
| 378 |
+
"step": 195
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 8.695652173913043,
|
| 382 |
+
"grad_norm": 2.250065326690674,
|
| 383 |
+
"learning_rate": 3.140096618357488e-05,
|
| 384 |
+
"loss": 0.0282,
|
| 385 |
+
"step": 200
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 8.91304347826087,
|
| 389 |
+
"grad_norm": 3.3784470558166504,
|
| 390 |
+
"learning_rate": 3.079710144927536e-05,
|
| 391 |
+
"loss": 0.0404,
|
| 392 |
+
"step": 205
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 9.0,
|
| 396 |
+
"eval_accuracy": 0.9876923076923076,
|
| 397 |
+
"eval_f1": 0.9775280898876404,
|
| 398 |
+
"eval_loss": 0.025601999834179878,
|
| 399 |
+
"eval_precision": 0.9775280898876404,
|
| 400 |
+
"eval_recall": 0.9775280898876404,
|
| 401 |
+
"eval_runtime": 0.6288,
|
| 402 |
+
"eval_samples_per_second": 516.888,
|
| 403 |
+
"eval_steps_per_second": 17.495,
|
| 404 |
+
"step": 207
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 9.130434782608695,
|
| 408 |
+
"grad_norm": 4.156078815460205,
|
| 409 |
+
"learning_rate": 3.0193236714975848e-05,
|
| 410 |
+
"loss": 0.0135,
|
| 411 |
+
"step": 210
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 9.347826086956522,
|
| 415 |
+
"grad_norm": 1.2355906963348389,
|
| 416 |
+
"learning_rate": 2.9589371980676327e-05,
|
| 417 |
+
"loss": 0.0377,
|
| 418 |
+
"step": 215
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 9.565217391304348,
|
| 422 |
+
"grad_norm": 4.165219783782959,
|
| 423 |
+
"learning_rate": 2.8985507246376814e-05,
|
| 424 |
+
"loss": 0.0354,
|
| 425 |
+
"step": 220
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 9.782608695652174,
|
| 429 |
+
"grad_norm": 1.0178390741348267,
|
| 430 |
+
"learning_rate": 2.8381642512077293e-05,
|
| 431 |
+
"loss": 0.0331,
|
| 432 |
+
"step": 225
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 10.0,
|
| 436 |
+
"grad_norm": 4.175224304199219,
|
| 437 |
+
"learning_rate": 2.777777777777778e-05,
|
| 438 |
+
"loss": 0.0297,
|
| 439 |
+
"step": 230
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 10.0,
|
| 443 |
+
"eval_accuracy": 0.9907692307692307,
|
| 444 |
+
"eval_f1": 0.9832402234636872,
|
| 445 |
+
"eval_loss": 0.02601032890379429,
|
| 446 |
+
"eval_precision": 0.9777777777777777,
|
| 447 |
+
"eval_recall": 0.9887640449438202,
|
| 448 |
+
"eval_runtime": 0.6221,
|
| 449 |
+
"eval_samples_per_second": 522.441,
|
| 450 |
+
"eval_steps_per_second": 17.683,
|
| 451 |
+
"step": 230
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 10.217391304347826,
|
| 455 |
+
"grad_norm": 0.14615581929683685,
|
| 456 |
+
"learning_rate": 2.7173913043478262e-05,
|
| 457 |
+
"loss": 0.009,
|
| 458 |
+
"step": 235
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 10.434782608695652,
|
| 462 |
+
"grad_norm": 5.359668731689453,
|
| 463 |
+
"learning_rate": 2.6570048309178748e-05,
|
| 464 |
+
"loss": 0.0176,
|
| 465 |
+
"step": 240
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 10.652173913043478,
|
| 469 |
+
"grad_norm": 0.387389212846756,
|
| 470 |
+
"learning_rate": 2.5966183574879227e-05,
|
| 471 |
+
"loss": 0.0251,
|
| 472 |
+
"step": 245
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 10.869565217391305,
|
| 476 |
+
"grad_norm": 1.7574446201324463,
|
| 477 |
+
"learning_rate": 2.5362318840579714e-05,
|
| 478 |
+
"loss": 0.0327,
|
| 479 |
+
"step": 250
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 11.0,
|
| 483 |
+
"eval_accuracy": 0.9938461538461538,
|
| 484 |
+
"eval_f1": 0.9888888888888888,
|
| 485 |
+
"eval_loss": 0.02298262156546116,
|
| 486 |
+
"eval_precision": 0.978021978021978,
|
| 487 |
+
"eval_recall": 1.0,
|
| 488 |
+
"eval_runtime": 0.63,
|
| 489 |
+
"eval_samples_per_second": 515.887,
|
| 490 |
+
"eval_steps_per_second": 17.461,
|
| 491 |
+
"step": 253
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 11.08695652173913,
|
| 495 |
+
"grad_norm": 1.124037504196167,
|
| 496 |
+
"learning_rate": 2.4758454106280193e-05,
|
| 497 |
+
"loss": 0.0397,
|
| 498 |
+
"step": 255
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 11.304347826086957,
|
| 502 |
+
"grad_norm": 2.474566698074341,
|
| 503 |
+
"learning_rate": 2.4154589371980676e-05,
|
| 504 |
+
"loss": 0.0427,
|
| 505 |
+
"step": 260
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 11.521739130434783,
|
| 509 |
+
"grad_norm": 1.6105717420578003,
|
| 510 |
+
"learning_rate": 2.355072463768116e-05,
|
| 511 |
+
"loss": 0.0157,
|
| 512 |
+
"step": 265
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 11.73913043478261,
|
| 516 |
+
"grad_norm": 0.6210281252861023,
|
| 517 |
+
"learning_rate": 2.294685990338164e-05,
|
| 518 |
+
"loss": 0.0297,
|
| 519 |
+
"step": 270
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 11.956521739130435,
|
| 523 |
+
"grad_norm": 2.6540639400482178,
|
| 524 |
+
"learning_rate": 2.2342995169082127e-05,
|
| 525 |
+
"loss": 0.0221,
|
| 526 |
+
"step": 275
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 12.0,
|
| 530 |
+
"eval_accuracy": 0.9969230769230769,
|
| 531 |
+
"eval_f1": 0.9944134078212291,
|
| 532 |
+
"eval_loss": 0.01398832444101572,
|
| 533 |
+
"eval_precision": 0.9888888888888889,
|
| 534 |
+
"eval_recall": 1.0,
|
| 535 |
+
"eval_runtime": 0.6237,
|
| 536 |
+
"eval_samples_per_second": 521.045,
|
| 537 |
+
"eval_steps_per_second": 17.635,
|
| 538 |
+
"step": 276
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 12.173913043478262,
|
| 542 |
+
"grad_norm": 2.6183152198791504,
|
| 543 |
+
"learning_rate": 2.173913043478261e-05,
|
| 544 |
+
"loss": 0.0267,
|
| 545 |
+
"step": 280
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 12.391304347826088,
|
| 549 |
+
"grad_norm": 0.8627565503120422,
|
| 550 |
+
"learning_rate": 2.1135265700483093e-05,
|
| 551 |
+
"loss": 0.0195,
|
| 552 |
+
"step": 285
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 12.608695652173914,
|
| 556 |
+
"grad_norm": 0.576085090637207,
|
| 557 |
+
"learning_rate": 2.0531400966183576e-05,
|
| 558 |
+
"loss": 0.0322,
|
| 559 |
+
"step": 290
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 12.826086956521738,
|
| 563 |
+
"grad_norm": 3.6716318130493164,
|
| 564 |
+
"learning_rate": 1.992753623188406e-05,
|
| 565 |
+
"loss": 0.0294,
|
| 566 |
+
"step": 295
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 13.0,
|
| 570 |
+
"eval_accuracy": 0.9969230769230769,
|
| 571 |
+
"eval_f1": 0.9944134078212291,
|
| 572 |
+
"eval_loss": 0.01057437900453806,
|
| 573 |
+
"eval_precision": 0.9888888888888889,
|
| 574 |
+
"eval_recall": 1.0,
|
| 575 |
+
"eval_runtime": 0.6324,
|
| 576 |
+
"eval_samples_per_second": 513.948,
|
| 577 |
+
"eval_steps_per_second": 17.395,
|
| 578 |
+
"step": 299
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 13.043478260869565,
|
| 582 |
+
"grad_norm": 0.19212637841701508,
|
| 583 |
+
"learning_rate": 1.932367149758454e-05,
|
| 584 |
+
"loss": 0.0298,
|
| 585 |
+
"step": 300
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 13.26086956521739,
|
| 589 |
+
"grad_norm": 1.9307483434677124,
|
| 590 |
+
"learning_rate": 1.8719806763285024e-05,
|
| 591 |
+
"loss": 0.0231,
|
| 592 |
+
"step": 305
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 13.478260869565217,
|
| 596 |
+
"grad_norm": 2.444979667663574,
|
| 597 |
+
"learning_rate": 1.8115942028985507e-05,
|
| 598 |
+
"loss": 0.0201,
|
| 599 |
+
"step": 310
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 13.695652173913043,
|
| 603 |
+
"grad_norm": 2.9044065475463867,
|
| 604 |
+
"learning_rate": 1.751207729468599e-05,
|
| 605 |
+
"loss": 0.0243,
|
| 606 |
+
"step": 315
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 13.91304347826087,
|
| 610 |
+
"grad_norm": 1.5113251209259033,
|
| 611 |
+
"learning_rate": 1.6908212560386476e-05,
|
| 612 |
+
"loss": 0.0292,
|
| 613 |
+
"step": 320
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 14.0,
|
| 617 |
+
"eval_accuracy": 0.9969230769230769,
|
| 618 |
+
"eval_f1": 0.9944134078212291,
|
| 619 |
+
"eval_loss": 0.013215974904596806,
|
| 620 |
+
"eval_precision": 0.9888888888888889,
|
| 621 |
+
"eval_recall": 1.0,
|
| 622 |
+
"eval_runtime": 0.6382,
|
| 623 |
+
"eval_samples_per_second": 509.263,
|
| 624 |
+
"eval_steps_per_second": 17.237,
|
| 625 |
+
"step": 322
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 14.130434782608695,
|
| 629 |
+
"grad_norm": 0.16032224893569946,
|
| 630 |
+
"learning_rate": 1.630434782608696e-05,
|
| 631 |
+
"loss": 0.0056,
|
| 632 |
+
"step": 325
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 14.347826086956522,
|
| 636 |
+
"grad_norm": 1.7882447242736816,
|
| 637 |
+
"learning_rate": 1.570048309178744e-05,
|
| 638 |
+
"loss": 0.0203,
|
| 639 |
+
"step": 330
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 14.565217391304348,
|
| 643 |
+
"grad_norm": 1.206709861755371,
|
| 644 |
+
"learning_rate": 1.5096618357487924e-05,
|
| 645 |
+
"loss": 0.0205,
|
| 646 |
+
"step": 335
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 14.782608695652174,
|
| 650 |
+
"grad_norm": 2.7993412017822266,
|
| 651 |
+
"learning_rate": 1.4492753623188407e-05,
|
| 652 |
+
"loss": 0.0227,
|
| 653 |
+
"step": 340
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 15.0,
|
| 657 |
+
"grad_norm": 1.1518446207046509,
|
| 658 |
+
"learning_rate": 1.388888888888889e-05,
|
| 659 |
+
"loss": 0.0064,
|
| 660 |
+
"step": 345
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 15.0,
|
| 664 |
+
"eval_accuracy": 0.9907692307692307,
|
| 665 |
+
"eval_f1": 0.9834254143646408,
|
| 666 |
+
"eval_loss": 0.02308599278330803,
|
| 667 |
+
"eval_precision": 0.967391304347826,
|
| 668 |
+
"eval_recall": 1.0,
|
| 669 |
+
"eval_runtime": 0.6311,
|
| 670 |
+
"eval_samples_per_second": 514.958,
|
| 671 |
+
"eval_steps_per_second": 17.429,
|
| 672 |
+
"step": 345
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 15.217391304347826,
|
| 676 |
+
"grad_norm": 1.4991214275360107,
|
| 677 |
+
"learning_rate": 1.3285024154589374e-05,
|
| 678 |
+
"loss": 0.0152,
|
| 679 |
+
"step": 350
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 15.434782608695652,
|
| 683 |
+
"grad_norm": 1.1912800073623657,
|
| 684 |
+
"learning_rate": 1.2681159420289857e-05,
|
| 685 |
+
"loss": 0.0066,
|
| 686 |
+
"step": 355
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 15.652173913043478,
|
| 690 |
+
"grad_norm": 0.4402332603931427,
|
| 691 |
+
"learning_rate": 1.2077294685990338e-05,
|
| 692 |
+
"loss": 0.0051,
|
| 693 |
+
"step": 360
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 15.869565217391305,
|
| 697 |
+
"grad_norm": 0.8945227861404419,
|
| 698 |
+
"learning_rate": 1.147342995169082e-05,
|
| 699 |
+
"loss": 0.02,
|
| 700 |
+
"step": 365
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 16.0,
|
| 704 |
+
"eval_accuracy": 0.9969230769230769,
|
| 705 |
+
"eval_f1": 0.9944134078212291,
|
| 706 |
+
"eval_loss": 0.008727076463401318,
|
| 707 |
+
"eval_precision": 0.9888888888888889,
|
| 708 |
+
"eval_recall": 1.0,
|
| 709 |
+
"eval_runtime": 0.6362,
|
| 710 |
+
"eval_samples_per_second": 510.858,
|
| 711 |
+
"eval_steps_per_second": 17.291,
|
| 712 |
+
"step": 368
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 16.08695652173913,
|
| 716 |
+
"grad_norm": 1.353935718536377,
|
| 717 |
+
"learning_rate": 1.0869565217391305e-05,
|
| 718 |
+
"loss": 0.0422,
|
| 719 |
+
"step": 370
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 16.304347826086957,
|
| 723 |
+
"grad_norm": 2.2760603427886963,
|
| 724 |
+
"learning_rate": 1.0265700483091788e-05,
|
| 725 |
+
"loss": 0.0314,
|
| 726 |
+
"step": 375
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 16.52173913043478,
|
| 730 |
+
"grad_norm": 1.7415324449539185,
|
| 731 |
+
"learning_rate": 9.66183574879227e-06,
|
| 732 |
+
"loss": 0.0105,
|
| 733 |
+
"step": 380
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 16.73913043478261,
|
| 737 |
+
"grad_norm": 0.31125152111053467,
|
| 738 |
+
"learning_rate": 9.057971014492753e-06,
|
| 739 |
+
"loss": 0.0249,
|
| 740 |
+
"step": 385
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 16.956521739130434,
|
| 744 |
+
"grad_norm": 3.789961814880371,
|
| 745 |
+
"learning_rate": 8.454106280193238e-06,
|
| 746 |
+
"loss": 0.0356,
|
| 747 |
+
"step": 390
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 17.0,
|
| 751 |
+
"eval_accuracy": 0.9969230769230769,
|
| 752 |
+
"eval_f1": 0.9944134078212291,
|
| 753 |
+
"eval_loss": 0.011419730260968208,
|
| 754 |
+
"eval_precision": 0.9888888888888889,
|
| 755 |
+
"eval_recall": 1.0,
|
| 756 |
+
"eval_runtime": 0.6273,
|
| 757 |
+
"eval_samples_per_second": 518.129,
|
| 758 |
+
"eval_steps_per_second": 17.537,
|
| 759 |
+
"step": 391
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 17.17391304347826,
|
| 763 |
+
"grad_norm": 0.2875424027442932,
|
| 764 |
+
"learning_rate": 7.85024154589372e-06,
|
| 765 |
+
"loss": 0.0102,
|
| 766 |
+
"step": 395
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 17.391304347826086,
|
| 770 |
+
"grad_norm": 1.2512189149856567,
|
| 771 |
+
"learning_rate": 7.246376811594203e-06,
|
| 772 |
+
"loss": 0.0114,
|
| 773 |
+
"step": 400
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 17.608695652173914,
|
| 777 |
+
"grad_norm": 2.634803295135498,
|
| 778 |
+
"learning_rate": 6.642512077294687e-06,
|
| 779 |
+
"loss": 0.0274,
|
| 780 |
+
"step": 405
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 17.82608695652174,
|
| 784 |
+
"grad_norm": 1.524092674255371,
|
| 785 |
+
"learning_rate": 6.038647342995169e-06,
|
| 786 |
+
"loss": 0.0232,
|
| 787 |
+
"step": 410
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 18.0,
|
| 791 |
+
"eval_accuracy": 1.0,
|
| 792 |
+
"eval_f1": 1.0,
|
| 793 |
+
"eval_loss": 0.00724475271999836,
|
| 794 |
+
"eval_precision": 1.0,
|
| 795 |
+
"eval_recall": 1.0,
|
| 796 |
+
"eval_runtime": 0.6289,
|
| 797 |
+
"eval_samples_per_second": 516.744,
|
| 798 |
+
"eval_steps_per_second": 17.49,
|
| 799 |
+
"step": 414
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 18.043478260869566,
|
| 803 |
+
"grad_norm": 0.8228383660316467,
|
| 804 |
+
"learning_rate": 5.4347826086956525e-06,
|
| 805 |
+
"loss": 0.0187,
|
| 806 |
+
"step": 415
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 18.26086956521739,
|
| 810 |
+
"grad_norm": 0.26993948221206665,
|
| 811 |
+
"learning_rate": 4.830917874396135e-06,
|
| 812 |
+
"loss": 0.0176,
|
| 813 |
+
"step": 420
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 18.47826086956522,
|
| 817 |
+
"grad_norm": 1.4451013803482056,
|
| 818 |
+
"learning_rate": 4.227053140096619e-06,
|
| 819 |
+
"loss": 0.017,
|
| 820 |
+
"step": 425
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 18.695652173913043,
|
| 824 |
+
"grad_norm": 1.0776654481887817,
|
| 825 |
+
"learning_rate": 3.6231884057971017e-06,
|
| 826 |
+
"loss": 0.0225,
|
| 827 |
+
"step": 430
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 18.91304347826087,
|
| 831 |
+
"grad_norm": 0.6803100109100342,
|
| 832 |
+
"learning_rate": 3.0193236714975845e-06,
|
| 833 |
+
"loss": 0.0351,
|
| 834 |
+
"step": 435
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 19.0,
|
| 838 |
+
"eval_accuracy": 0.9969230769230769,
|
| 839 |
+
"eval_f1": 0.9944134078212291,
|
| 840 |
+
"eval_loss": 0.008730148896574974,
|
| 841 |
+
"eval_precision": 0.9888888888888889,
|
| 842 |
+
"eval_recall": 1.0,
|
| 843 |
+
"eval_runtime": 0.629,
|
| 844 |
+
"eval_samples_per_second": 516.656,
|
| 845 |
+
"eval_steps_per_second": 17.487,
|
| 846 |
+
"step": 437
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 19.130434782608695,
|
| 850 |
+
"grad_norm": 3.2962541580200195,
|
| 851 |
+
"learning_rate": 2.4154589371980677e-06,
|
| 852 |
+
"loss": 0.0138,
|
| 853 |
+
"step": 440
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 19.347826086956523,
|
| 857 |
+
"grad_norm": 2.5289676189422607,
|
| 858 |
+
"learning_rate": 1.8115942028985508e-06,
|
| 859 |
+
"loss": 0.0192,
|
| 860 |
+
"step": 445
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 19.565217391304348,
|
| 864 |
+
"grad_norm": 0.09774911403656006,
|
| 865 |
+
"learning_rate": 1.2077294685990338e-06,
|
| 866 |
+
"loss": 0.0136,
|
| 867 |
+
"step": 450
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 19.782608695652176,
|
| 871 |
+
"grad_norm": 0.9112738370895386,
|
| 872 |
+
"learning_rate": 6.038647342995169e-07,
|
| 873 |
+
"loss": 0.0213,
|
| 874 |
+
"step": 455
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 20.0,
|
| 878 |
+
"grad_norm": 0.6033933162689209,
|
| 879 |
+
"learning_rate": 0.0,
|
| 880 |
+
"loss": 0.0155,
|
| 881 |
+
"step": 460
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 20.0,
|
| 885 |
+
"eval_accuracy": 0.9969230769230769,
|
| 886 |
+
"eval_f1": 0.9944134078212291,
|
| 887 |
+
"eval_loss": 0.007528003770858049,
|
| 888 |
+
"eval_precision": 0.9888888888888889,
|
| 889 |
+
"eval_recall": 1.0,
|
| 890 |
+
"eval_runtime": 0.6414,
|
| 891 |
+
"eval_samples_per_second": 506.707,
|
| 892 |
+
"eval_steps_per_second": 17.15,
|
| 893 |
+
"step": 460
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 20.0,
|
| 897 |
+
"step": 460,
|
| 898 |
+
"total_flos": 1.4530811161131418e+18,
|
| 899 |
+
"train_loss": 0.0580909106111073,
|
| 900 |
+
"train_runtime": 291.8902,
|
| 901 |
+
"train_samples_per_second": 200.281,
|
| 902 |
+
"train_steps_per_second": 1.576
|
| 903 |
+
}
|
| 904 |
+
],
|
| 905 |
+
"logging_steps": 5,
|
| 906 |
+
"max_steps": 460,
|
| 907 |
+
"num_input_tokens_seen": 0,
|
| 908 |
+
"num_train_epochs": 20,
|
| 909 |
+
"save_steps": 500,
|
| 910 |
+
"stateful_callbacks": {
|
| 911 |
+
"TrainerControl": {
|
| 912 |
+
"args": {
|
| 913 |
+
"should_epoch_stop": false,
|
| 914 |
+
"should_evaluate": false,
|
| 915 |
+
"should_log": false,
|
| 916 |
+
"should_save": true,
|
| 917 |
+
"should_training_stop": true
|
| 918 |
+
},
|
| 919 |
+
"attributes": {}
|
| 920 |
+
}
|
| 921 |
+
},
|
| 922 |
+
"total_flos": 1.4530811161131418e+18,
|
| 923 |
+
"train_batch_size": 32,
|
| 924 |
+
"trial_name": null,
|
| 925 |
+
"trial_params": null
|
| 926 |
+
}
|