Nguyen Tien
commited on
Commit
•
b31ca8b
1
Parent(s):
6613afe
vuihocrnd/teacher-status-van-tiny-256
Browse files- README.md +6 -6
- all_results.json +16 -0
- eval_results.json +11 -0
- train_results.json +8 -0
- trainer_state.json +858 -0
README.md
CHANGED
|
@@ -24,13 +24,13 @@ model-index:
|
|
| 24 |
metrics:
|
| 25 |
- name: Accuracy
|
| 26 |
type: accuracy
|
| 27 |
-
value: 0.
|
| 28 |
- name: Recall
|
| 29 |
type: recall
|
| 30 |
value: 0.9756944444444444
|
| 31 |
- name: Precision
|
| 32 |
type: precision
|
| 33 |
-
value: 0.
|
| 34 |
---
|
| 35 |
|
| 36 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -40,11 +40,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 40 |
|
| 41 |
This model is a fine-tuned version of [Visual-Attention-Network/van-tiny](https://huggingface.co/Visual-Attention-Network/van-tiny) on the imagefolder dataset.
|
| 42 |
It achieves the following results on the evaluation set:
|
| 43 |
-
- Loss: 0.
|
| 44 |
-
- Accuracy: 0.
|
| 45 |
-
- F1 Score: 0.
|
| 46 |
- Recall: 0.9757
|
| 47 |
-
- Precision: 0.
|
| 48 |
|
| 49 |
## Model description
|
| 50 |
|
|
|
|
| 24 |
metrics:
|
| 25 |
- name: Accuracy
|
| 26 |
type: accuracy
|
| 27 |
+
value: 0.9759358288770054
|
| 28 |
- name: Recall
|
| 29 |
type: recall
|
| 30 |
value: 0.9756944444444444
|
| 31 |
- name: Precision
|
| 32 |
type: precision
|
| 33 |
+
value: 0.9929328621908127
|
| 34 |
---
|
| 35 |
|
| 36 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 40 |
|
| 41 |
This model is a fine-tuned version of [Visual-Attention-Network/van-tiny](https://huggingface.co/Visual-Attention-Network/van-tiny) on the imagefolder dataset.
|
| 42 |
It achieves the following results on the evaluation set:
|
| 43 |
+
- Loss: 0.0916
|
| 44 |
+
- Accuracy: 0.9759
|
| 45 |
+
- F1 Score: 0.9842
|
| 46 |
- Recall: 0.9757
|
| 47 |
+
- Precision: 0.9929
|
| 48 |
|
| 49 |
## Model description
|
| 50 |
|
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 29.71,
|
| 3 |
+
"eval_accuracy": 0.9759358288770054,
|
| 4 |
+
"eval_f1_score": 0.9842381786339754,
|
| 5 |
+
"eval_loss": 0.09159436821937561,
|
| 6 |
+
"eval_precision": 0.9929328621908127,
|
| 7 |
+
"eval_recall": 0.9756944444444444,
|
| 8 |
+
"eval_runtime": 2.9334,
|
| 9 |
+
"eval_samples_per_second": 127.496,
|
| 10 |
+
"eval_steps_per_second": 4.091,
|
| 11 |
+
"total_flos": 4.5315392030480794e+17,
|
| 12 |
+
"train_loss": 0.2131147768252935,
|
| 13 |
+
"train_runtime": 1561.1697,
|
| 14 |
+
"train_samples_per_second": 64.529,
|
| 15 |
+
"train_steps_per_second": 0.5
|
| 16 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 29.71,
|
| 3 |
+
"eval_accuracy": 0.9759358288770054,
|
| 4 |
+
"eval_f1_score": 0.9842381786339754,
|
| 5 |
+
"eval_loss": 0.09159436821937561,
|
| 6 |
+
"eval_precision": 0.9929328621908127,
|
| 7 |
+
"eval_recall": 0.9756944444444444,
|
| 8 |
+
"eval_runtime": 2.9334,
|
| 9 |
+
"eval_samples_per_second": 127.496,
|
| 10 |
+
"eval_steps_per_second": 4.091
|
| 11 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 29.71,
|
| 3 |
+
"total_flos": 4.5315392030480794e+17,
|
| 4 |
+
"train_loss": 0.2131147768252935,
|
| 5 |
+
"train_runtime": 1561.1697,
|
| 6 |
+
"train_samples_per_second": 64.529,
|
| 7 |
+
"train_steps_per_second": 0.5
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,858 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9842381786339754,
|
| 3 |
+
"best_model_checkpoint": "teacher-status-van-tiny-256-2/checkpoint-420",
|
| 4 |
+
"epoch": 29.714285714285715,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 780,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.38,
|
| 13 |
+
"learning_rate": 6.41025641025641e-06,
|
| 14 |
+
"loss": 0.6928,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.76,
|
| 19 |
+
"learning_rate": 1.282051282051282e-05,
|
| 20 |
+
"loss": 0.6896,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.99,
|
| 25 |
+
"eval_accuracy": 0.7700534759358288,
|
| 26 |
+
"eval_f1_score": 0.8700906344410876,
|
| 27 |
+
"eval_loss": 0.670672595500946,
|
| 28 |
+
"eval_precision": 0.7700534759358288,
|
| 29 |
+
"eval_recall": 1.0,
|
| 30 |
+
"eval_runtime": 2.6151,
|
| 31 |
+
"eval_samples_per_second": 143.014,
|
| 32 |
+
"eval_steps_per_second": 4.589,
|
| 33 |
+
"step": 26
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 1.14,
|
| 37 |
+
"learning_rate": 1.923076923076923e-05,
|
| 38 |
+
"loss": 0.6763,
|
| 39 |
+
"step": 30
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.52,
|
| 43 |
+
"learning_rate": 2.564102564102564e-05,
|
| 44 |
+
"loss": 0.6376,
|
| 45 |
+
"step": 40
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.9,
|
| 49 |
+
"learning_rate": 3.205128205128206e-05,
|
| 50 |
+
"loss": 0.5438,
|
| 51 |
+
"step": 50
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.98,
|
| 55 |
+
"eval_accuracy": 0.7700534759358288,
|
| 56 |
+
"eval_f1_score": 0.8700906344410876,
|
| 57 |
+
"eval_loss": 0.43023183941841125,
|
| 58 |
+
"eval_precision": 0.7700534759358288,
|
| 59 |
+
"eval_recall": 1.0,
|
| 60 |
+
"eval_runtime": 2.5825,
|
| 61 |
+
"eval_samples_per_second": 144.822,
|
| 62 |
+
"eval_steps_per_second": 4.647,
|
| 63 |
+
"step": 52
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 2.29,
|
| 67 |
+
"learning_rate": 3.846153846153846e-05,
|
| 68 |
+
"loss": 0.4252,
|
| 69 |
+
"step": 60
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 2.67,
|
| 73 |
+
"learning_rate": 4.4871794871794874e-05,
|
| 74 |
+
"loss": 0.3756,
|
| 75 |
+
"step": 70
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 2.97,
|
| 79 |
+
"eval_accuracy": 0.8850267379679144,
|
| 80 |
+
"eval_f1_score": 0.9284525790349417,
|
| 81 |
+
"eval_loss": 0.2762328088283539,
|
| 82 |
+
"eval_precision": 0.8913738019169329,
|
| 83 |
+
"eval_recall": 0.96875,
|
| 84 |
+
"eval_runtime": 2.711,
|
| 85 |
+
"eval_samples_per_second": 137.957,
|
| 86 |
+
"eval_steps_per_second": 4.426,
|
| 87 |
+
"step": 78
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 3.05,
|
| 91 |
+
"learning_rate": 4.985754985754986e-05,
|
| 92 |
+
"loss": 0.3572,
|
| 93 |
+
"step": 80
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 3.43,
|
| 97 |
+
"learning_rate": 4.9145299145299147e-05,
|
| 98 |
+
"loss": 0.3217,
|
| 99 |
+
"step": 90
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 3.81,
|
| 103 |
+
"learning_rate": 4.8433048433048433e-05,
|
| 104 |
+
"loss": 0.3017,
|
| 105 |
+
"step": 100
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 4.0,
|
| 109 |
+
"eval_accuracy": 0.9224598930481284,
|
| 110 |
+
"eval_f1_score": 0.9502572898799314,
|
| 111 |
+
"eval_loss": 0.20020952820777893,
|
| 112 |
+
"eval_precision": 0.9389830508474576,
|
| 113 |
+
"eval_recall": 0.9618055555555556,
|
| 114 |
+
"eval_runtime": 2.7006,
|
| 115 |
+
"eval_samples_per_second": 138.487,
|
| 116 |
+
"eval_steps_per_second": 4.443,
|
| 117 |
+
"step": 105
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 4.19,
|
| 121 |
+
"learning_rate": 4.772079772079772e-05,
|
| 122 |
+
"loss": 0.2563,
|
| 123 |
+
"step": 110
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 4.57,
|
| 127 |
+
"learning_rate": 4.700854700854701e-05,
|
| 128 |
+
"loss": 0.2548,
|
| 129 |
+
"step": 120
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 4.95,
|
| 133 |
+
"learning_rate": 4.62962962962963e-05,
|
| 134 |
+
"loss": 0.257,
|
| 135 |
+
"step": 130
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 4.99,
|
| 139 |
+
"eval_accuracy": 0.9385026737967914,
|
| 140 |
+
"eval_f1_score": 0.9605488850771869,
|
| 141 |
+
"eval_loss": 0.17939455807209015,
|
| 142 |
+
"eval_precision": 0.9491525423728814,
|
| 143 |
+
"eval_recall": 0.9722222222222222,
|
| 144 |
+
"eval_runtime": 2.4102,
|
| 145 |
+
"eval_samples_per_second": 155.173,
|
| 146 |
+
"eval_steps_per_second": 4.979,
|
| 147 |
+
"step": 131
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 5.33,
|
| 151 |
+
"learning_rate": 4.558404558404559e-05,
|
| 152 |
+
"loss": 0.2484,
|
| 153 |
+
"step": 140
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 5.71,
|
| 157 |
+
"learning_rate": 4.4871794871794874e-05,
|
| 158 |
+
"loss": 0.2345,
|
| 159 |
+
"step": 150
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 5.98,
|
| 163 |
+
"eval_accuracy": 0.9358288770053476,
|
| 164 |
+
"eval_f1_score": 0.9581881533101045,
|
| 165 |
+
"eval_loss": 0.14852212369441986,
|
| 166 |
+
"eval_precision": 0.9615384615384616,
|
| 167 |
+
"eval_recall": 0.9548611111111112,
|
| 168 |
+
"eval_runtime": 2.3968,
|
| 169 |
+
"eval_samples_per_second": 156.039,
|
| 170 |
+
"eval_steps_per_second": 5.007,
|
| 171 |
+
"step": 157
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 6.1,
|
| 175 |
+
"learning_rate": 4.415954415954416e-05,
|
| 176 |
+
"loss": 0.2514,
|
| 177 |
+
"step": 160
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 6.48,
|
| 181 |
+
"learning_rate": 4.344729344729345e-05,
|
| 182 |
+
"loss": 0.2179,
|
| 183 |
+
"step": 170
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 6.86,
|
| 187 |
+
"learning_rate": 4.2735042735042735e-05,
|
| 188 |
+
"loss": 0.2318,
|
| 189 |
+
"step": 180
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 6.97,
|
| 193 |
+
"eval_accuracy": 0.9438502673796791,
|
| 194 |
+
"eval_f1_score": 0.9630931458699472,
|
| 195 |
+
"eval_loss": 0.13021136820316315,
|
| 196 |
+
"eval_precision": 0.9750889679715302,
|
| 197 |
+
"eval_recall": 0.9513888888888888,
|
| 198 |
+
"eval_runtime": 2.3767,
|
| 199 |
+
"eval_samples_per_second": 157.361,
|
| 200 |
+
"eval_steps_per_second": 5.049,
|
| 201 |
+
"step": 183
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 7.24,
|
| 205 |
+
"learning_rate": 4.202279202279202e-05,
|
| 206 |
+
"loss": 0.2151,
|
| 207 |
+
"step": 190
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 7.62,
|
| 211 |
+
"learning_rate": 4.131054131054131e-05,
|
| 212 |
+
"loss": 0.2311,
|
| 213 |
+
"step": 200
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 8.0,
|
| 217 |
+
"learning_rate": 4.05982905982906e-05,
|
| 218 |
+
"loss": 0.2173,
|
| 219 |
+
"step": 210
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 8.0,
|
| 223 |
+
"eval_accuracy": 0.9518716577540107,
|
| 224 |
+
"eval_f1_score": 0.9688581314878894,
|
| 225 |
+
"eval_loss": 0.12773053348064423,
|
| 226 |
+
"eval_precision": 0.9655172413793104,
|
| 227 |
+
"eval_recall": 0.9722222222222222,
|
| 228 |
+
"eval_runtime": 2.3674,
|
| 229 |
+
"eval_samples_per_second": 157.977,
|
| 230 |
+
"eval_steps_per_second": 5.069,
|
| 231 |
+
"step": 210
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 8.38,
|
| 235 |
+
"learning_rate": 3.988603988603989e-05,
|
| 236 |
+
"loss": 0.1934,
|
| 237 |
+
"step": 220
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 8.76,
|
| 241 |
+
"learning_rate": 3.9173789173789176e-05,
|
| 242 |
+
"loss": 0.2058,
|
| 243 |
+
"step": 230
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 8.99,
|
| 247 |
+
"eval_accuracy": 0.9572192513368984,
|
| 248 |
+
"eval_f1_score": 0.9722222222222222,
|
| 249 |
+
"eval_loss": 0.1269279271364212,
|
| 250 |
+
"eval_precision": 0.9722222222222222,
|
| 251 |
+
"eval_recall": 0.9722222222222222,
|
| 252 |
+
"eval_runtime": 2.2694,
|
| 253 |
+
"eval_samples_per_second": 164.802,
|
| 254 |
+
"eval_steps_per_second": 5.288,
|
| 255 |
+
"step": 236
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 9.14,
|
| 259 |
+
"learning_rate": 3.846153846153846e-05,
|
| 260 |
+
"loss": 0.1959,
|
| 261 |
+
"step": 240
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 9.52,
|
| 265 |
+
"learning_rate": 3.774928774928775e-05,
|
| 266 |
+
"loss": 0.2016,
|
| 267 |
+
"step": 250
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 9.9,
|
| 271 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 272 |
+
"loss": 0.1955,
|
| 273 |
+
"step": 260
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 9.98,
|
| 277 |
+
"eval_accuracy": 0.9572192513368984,
|
| 278 |
+
"eval_f1_score": 0.9724137931034483,
|
| 279 |
+
"eval_loss": 0.11462008953094482,
|
| 280 |
+
"eval_precision": 0.9657534246575342,
|
| 281 |
+
"eval_recall": 0.9791666666666666,
|
| 282 |
+
"eval_runtime": 2.2006,
|
| 283 |
+
"eval_samples_per_second": 169.954,
|
| 284 |
+
"eval_steps_per_second": 5.453,
|
| 285 |
+
"step": 262
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 10.29,
|
| 289 |
+
"learning_rate": 3.6324786324786323e-05,
|
| 290 |
+
"loss": 0.2038,
|
| 291 |
+
"step": 270
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 10.67,
|
| 295 |
+
"learning_rate": 3.561253561253561e-05,
|
| 296 |
+
"loss": 0.2083,
|
| 297 |
+
"step": 280
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 10.97,
|
| 301 |
+
"eval_accuracy": 0.9652406417112299,
|
| 302 |
+
"eval_f1_score": 0.9772329246935202,
|
| 303 |
+
"eval_loss": 0.1083158627152443,
|
| 304 |
+
"eval_precision": 0.9858657243816255,
|
| 305 |
+
"eval_recall": 0.96875,
|
| 306 |
+
"eval_runtime": 2.2496,
|
| 307 |
+
"eval_samples_per_second": 166.25,
|
| 308 |
+
"eval_steps_per_second": 5.334,
|
| 309 |
+
"step": 288
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 11.05,
|
| 313 |
+
"learning_rate": 3.4900284900284904e-05,
|
| 314 |
+
"loss": 0.2107,
|
| 315 |
+
"step": 290
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 11.43,
|
| 319 |
+
"learning_rate": 3.418803418803419e-05,
|
| 320 |
+
"loss": 0.1725,
|
| 321 |
+
"step": 300
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 11.81,
|
| 325 |
+
"learning_rate": 3.347578347578348e-05,
|
| 326 |
+
"loss": 0.1886,
|
| 327 |
+
"step": 310
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 12.0,
|
| 331 |
+
"eval_accuracy": 0.9598930481283422,
|
| 332 |
+
"eval_f1_score": 0.9740932642487047,
|
| 333 |
+
"eval_loss": 0.10481037944555283,
|
| 334 |
+
"eval_precision": 0.9690721649484536,
|
| 335 |
+
"eval_recall": 0.9791666666666666,
|
| 336 |
+
"eval_runtime": 2.1714,
|
| 337 |
+
"eval_samples_per_second": 172.242,
|
| 338 |
+
"eval_steps_per_second": 5.526,
|
| 339 |
+
"step": 315
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 12.19,
|
| 343 |
+
"learning_rate": 3.2763532763532764e-05,
|
| 344 |
+
"loss": 0.1703,
|
| 345 |
+
"step": 320
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 12.57,
|
| 349 |
+
"learning_rate": 3.205128205128206e-05,
|
| 350 |
+
"loss": 0.1817,
|
| 351 |
+
"step": 330
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 12.95,
|
| 355 |
+
"learning_rate": 3.133903133903134e-05,
|
| 356 |
+
"loss": 0.1618,
|
| 357 |
+
"step": 340
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 12.99,
|
| 361 |
+
"eval_accuracy": 0.9625668449197861,
|
| 362 |
+
"eval_f1_score": 0.9756944444444444,
|
| 363 |
+
"eval_loss": 0.10334747284650803,
|
| 364 |
+
"eval_precision": 0.9756944444444444,
|
| 365 |
+
"eval_recall": 0.9756944444444444,
|
| 366 |
+
"eval_runtime": 2.1514,
|
| 367 |
+
"eval_samples_per_second": 173.842,
|
| 368 |
+
"eval_steps_per_second": 5.578,
|
| 369 |
+
"step": 341
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 13.33,
|
| 373 |
+
"learning_rate": 3.0626780626780625e-05,
|
| 374 |
+
"loss": 0.1733,
|
| 375 |
+
"step": 350
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 13.71,
|
| 379 |
+
"learning_rate": 2.9914529914529915e-05,
|
| 380 |
+
"loss": 0.1908,
|
| 381 |
+
"step": 360
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 13.98,
|
| 385 |
+
"eval_accuracy": 0.9598930481283422,
|
| 386 |
+
"eval_f1_score": 0.9739130434782608,
|
| 387 |
+
"eval_loss": 0.10439594089984894,
|
| 388 |
+
"eval_precision": 0.975609756097561,
|
| 389 |
+
"eval_recall": 0.9722222222222222,
|
| 390 |
+
"eval_runtime": 2.2063,
|
| 391 |
+
"eval_samples_per_second": 169.517,
|
| 392 |
+
"eval_steps_per_second": 5.439,
|
| 393 |
+
"step": 367
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 14.1,
|
| 397 |
+
"learning_rate": 2.9202279202279202e-05,
|
| 398 |
+
"loss": 0.1677,
|
| 399 |
+
"step": 370
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 14.48,
|
| 403 |
+
"learning_rate": 2.8490028490028492e-05,
|
| 404 |
+
"loss": 0.1641,
|
| 405 |
+
"step": 380
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 14.86,
|
| 409 |
+
"learning_rate": 2.777777777777778e-05,
|
| 410 |
+
"loss": 0.1594,
|
| 411 |
+
"step": 390
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 14.97,
|
| 415 |
+
"eval_accuracy": 0.9625668449197861,
|
| 416 |
+
"eval_f1_score": 0.9757785467128027,
|
| 417 |
+
"eval_loss": 0.09152617305517197,
|
| 418 |
+
"eval_precision": 0.9724137931034482,
|
| 419 |
+
"eval_recall": 0.9791666666666666,
|
| 420 |
+
"eval_runtime": 2.146,
|
| 421 |
+
"eval_samples_per_second": 174.274,
|
| 422 |
+
"eval_steps_per_second": 5.592,
|
| 423 |
+
"step": 393
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 15.24,
|
| 427 |
+
"learning_rate": 2.706552706552707e-05,
|
| 428 |
+
"loss": 0.1621,
|
| 429 |
+
"step": 400
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 15.62,
|
| 433 |
+
"learning_rate": 2.6353276353276356e-05,
|
| 434 |
+
"loss": 0.1698,
|
| 435 |
+
"step": 410
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 16.0,
|
| 439 |
+
"learning_rate": 2.564102564102564e-05,
|
| 440 |
+
"loss": 0.1474,
|
| 441 |
+
"step": 420
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 16.0,
|
| 445 |
+
"eval_accuracy": 0.9759358288770054,
|
| 446 |
+
"eval_f1_score": 0.9842381786339754,
|
| 447 |
+
"eval_loss": 0.09159436821937561,
|
| 448 |
+
"eval_precision": 0.9929328621908127,
|
| 449 |
+
"eval_recall": 0.9756944444444444,
|
| 450 |
+
"eval_runtime": 2.1573,
|
| 451 |
+
"eval_samples_per_second": 173.367,
|
| 452 |
+
"eval_steps_per_second": 5.563,
|
| 453 |
+
"step": 420
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 16.38,
|
| 457 |
+
"learning_rate": 2.492877492877493e-05,
|
| 458 |
+
"loss": 0.1326,
|
| 459 |
+
"step": 430
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 16.76,
|
| 463 |
+
"learning_rate": 2.4216524216524217e-05,
|
| 464 |
+
"loss": 0.1734,
|
| 465 |
+
"step": 440
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 16.99,
|
| 469 |
+
"eval_accuracy": 0.9652406417112299,
|
| 470 |
+
"eval_f1_score": 0.9773123909249563,
|
| 471 |
+
"eval_loss": 0.09513744711875916,
|
| 472 |
+
"eval_precision": 0.9824561403508771,
|
| 473 |
+
"eval_recall": 0.9722222222222222,
|
| 474 |
+
"eval_runtime": 2.1734,
|
| 475 |
+
"eval_samples_per_second": 172.078,
|
| 476 |
+
"eval_steps_per_second": 5.521,
|
| 477 |
+
"step": 446
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 17.14,
|
| 481 |
+
"learning_rate": 2.3504273504273504e-05,
|
| 482 |
+
"loss": 0.1827,
|
| 483 |
+
"step": 450
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 17.52,
|
| 487 |
+
"learning_rate": 2.2792022792022794e-05,
|
| 488 |
+
"loss": 0.1419,
|
| 489 |
+
"step": 460
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 17.9,
|
| 493 |
+
"learning_rate": 2.207977207977208e-05,
|
| 494 |
+
"loss": 0.1484,
|
| 495 |
+
"step": 470
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 17.98,
|
| 499 |
+
"eval_accuracy": 0.9705882352941176,
|
| 500 |
+
"eval_f1_score": 0.9808695652173912,
|
| 501 |
+
"eval_loss": 0.10494749993085861,
|
| 502 |
+
"eval_precision": 0.9825783972125436,
|
| 503 |
+
"eval_recall": 0.9791666666666666,
|
| 504 |
+
"eval_runtime": 2.155,
|
| 505 |
+
"eval_samples_per_second": 173.55,
|
| 506 |
+
"eval_steps_per_second": 5.568,
|
| 507 |
+
"step": 472
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 18.29,
|
| 511 |
+
"learning_rate": 2.1367521367521368e-05,
|
| 512 |
+
"loss": 0.1515,
|
| 513 |
+
"step": 480
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 18.67,
|
| 517 |
+
"learning_rate": 2.0655270655270654e-05,
|
| 518 |
+
"loss": 0.1495,
|
| 519 |
+
"step": 490
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 18.97,
|
| 523 |
+
"eval_accuracy": 0.9679144385026738,
|
| 524 |
+
"eval_f1_score": 0.9790940766550522,
|
| 525 |
+
"eval_loss": 0.09304243326187134,
|
| 526 |
+
"eval_precision": 0.9825174825174825,
|
| 527 |
+
"eval_recall": 0.9756944444444444,
|
| 528 |
+
"eval_runtime": 2.1676,
|
| 529 |
+
"eval_samples_per_second": 172.538,
|
| 530 |
+
"eval_steps_per_second": 5.536,
|
| 531 |
+
"step": 498
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 19.05,
|
| 535 |
+
"learning_rate": 1.9943019943019945e-05,
|
| 536 |
+
"loss": 0.1525,
|
| 537 |
+
"step": 500
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 19.43,
|
| 541 |
+
"learning_rate": 1.923076923076923e-05,
|
| 542 |
+
"loss": 0.1575,
|
| 543 |
+
"step": 510
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 19.81,
|
| 547 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 548 |
+
"loss": 0.1385,
|
| 549 |
+
"step": 520
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 20.0,
|
| 553 |
+
"eval_accuracy": 0.9625668449197861,
|
| 554 |
+
"eval_f1_score": 0.9758620689655172,
|
| 555 |
+
"eval_loss": 0.095456063747406,
|
| 556 |
+
"eval_precision": 0.9691780821917808,
|
| 557 |
+
"eval_recall": 0.9826388888888888,
|
| 558 |
+
"eval_runtime": 2.217,
|
| 559 |
+
"eval_samples_per_second": 168.695,
|
| 560 |
+
"eval_steps_per_second": 5.413,
|
| 561 |
+
"step": 525
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 20.19,
|
| 565 |
+
"learning_rate": 1.7806267806267805e-05,
|
| 566 |
+
"loss": 0.139,
|
| 567 |
+
"step": 530
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 20.57,
|
| 571 |
+
"learning_rate": 1.7094017094017095e-05,
|
| 572 |
+
"loss": 0.1567,
|
| 573 |
+
"step": 540
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 20.95,
|
| 577 |
+
"learning_rate": 1.6381766381766382e-05,
|
| 578 |
+
"loss": 0.1492,
|
| 579 |
+
"step": 550
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 20.99,
|
| 583 |
+
"eval_accuracy": 0.9598930481283422,
|
| 584 |
+
"eval_f1_score": 0.9740932642487047,
|
| 585 |
+
"eval_loss": 0.09114021807909012,
|
| 586 |
+
"eval_precision": 0.9690721649484536,
|
| 587 |
+
"eval_recall": 0.9791666666666666,
|
| 588 |
+
"eval_runtime": 2.1474,
|
| 589 |
+
"eval_samples_per_second": 174.163,
|
| 590 |
+
"eval_steps_per_second": 5.588,
|
| 591 |
+
"step": 551
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 21.33,
|
| 595 |
+
"learning_rate": 1.566951566951567e-05,
|
| 596 |
+
"loss": 0.1664,
|
| 597 |
+
"step": 560
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 21.71,
|
| 601 |
+
"learning_rate": 1.4957264957264958e-05,
|
| 602 |
+
"loss": 0.1401,
|
| 603 |
+
"step": 570
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 21.98,
|
| 607 |
+
"eval_accuracy": 0.9705882352941176,
|
| 608 |
+
"eval_f1_score": 0.9808695652173912,
|
| 609 |
+
"eval_loss": 0.09274759143590927,
|
| 610 |
+
"eval_precision": 0.9825783972125436,
|
| 611 |
+
"eval_recall": 0.9791666666666666,
|
| 612 |
+
"eval_runtime": 2.1665,
|
| 613 |
+
"eval_samples_per_second": 172.63,
|
| 614 |
+
"eval_steps_per_second": 5.539,
|
| 615 |
+
"step": 577
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 22.1,
|
| 619 |
+
"learning_rate": 1.4245014245014246e-05,
|
| 620 |
+
"loss": 0.1538,
|
| 621 |
+
"step": 580
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 22.48,
|
| 625 |
+
"learning_rate": 1.3532763532763535e-05,
|
| 626 |
+
"loss": 0.1245,
|
| 627 |
+
"step": 590
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 22.86,
|
| 631 |
+
"learning_rate": 1.282051282051282e-05,
|
| 632 |
+
"loss": 0.1288,
|
| 633 |
+
"step": 600
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 22.97,
|
| 637 |
+
"eval_accuracy": 0.9705882352941176,
|
| 638 |
+
"eval_f1_score": 0.9808695652173912,
|
| 639 |
+
"eval_loss": 0.09401033818721771,
|
| 640 |
+
"eval_precision": 0.9825783972125436,
|
| 641 |
+
"eval_recall": 0.9791666666666666,
|
| 642 |
+
"eval_runtime": 2.1911,
|
| 643 |
+
"eval_samples_per_second": 170.692,
|
| 644 |
+
"eval_steps_per_second": 5.477,
|
| 645 |
+
"step": 603
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 23.24,
|
| 649 |
+
"learning_rate": 1.2108262108262108e-05,
|
| 650 |
+
"loss": 0.1422,
|
| 651 |
+
"step": 610
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 23.62,
|
| 655 |
+
"learning_rate": 1.1396011396011397e-05,
|
| 656 |
+
"loss": 0.1262,
|
| 657 |
+
"step": 620
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 24.0,
|
| 661 |
+
"learning_rate": 1.0683760683760684e-05,
|
| 662 |
+
"loss": 0.1304,
|
| 663 |
+
"step": 630
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 24.0,
|
| 667 |
+
"eval_accuracy": 0.9652406417112299,
|
| 668 |
+
"eval_f1_score": 0.9775474956822107,
|
| 669 |
+
"eval_loss": 0.09132420271635056,
|
| 670 |
+
"eval_precision": 0.9725085910652921,
|
| 671 |
+
"eval_recall": 0.9826388888888888,
|
| 672 |
+
"eval_runtime": 2.1685,
|
| 673 |
+
"eval_samples_per_second": 172.467,
|
| 674 |
+
"eval_steps_per_second": 5.534,
|
| 675 |
+
"step": 630
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 24.38,
|
| 679 |
+
"learning_rate": 9.971509971509972e-06,
|
| 680 |
+
"loss": 0.1542,
|
| 681 |
+
"step": 640
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 24.76,
|
| 685 |
+
"learning_rate": 9.259259259259259e-06,
|
| 686 |
+
"loss": 0.14,
|
| 687 |
+
"step": 650
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 24.99,
|
| 691 |
+
"eval_accuracy": 0.9652406417112299,
|
| 692 |
+
"eval_f1_score": 0.9776247848537005,
|
| 693 |
+
"eval_loss": 0.09787322580814362,
|
| 694 |
+
"eval_precision": 0.9692832764505119,
|
| 695 |
+
"eval_recall": 0.9861111111111112,
|
| 696 |
+
"eval_runtime": 2.1719,
|
| 697 |
+
"eval_samples_per_second": 172.201,
|
| 698 |
+
"eval_steps_per_second": 5.525,
|
| 699 |
+
"step": 656
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 25.14,
|
| 703 |
+
"learning_rate": 8.547008547008548e-06,
|
| 704 |
+
"loss": 0.1529,
|
| 705 |
+
"step": 660
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 25.52,
|
| 709 |
+
"learning_rate": 7.834757834757835e-06,
|
| 710 |
+
"loss": 0.1367,
|
| 711 |
+
"step": 670
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 25.9,
|
| 715 |
+
"learning_rate": 7.122507122507123e-06,
|
| 716 |
+
"loss": 0.1461,
|
| 717 |
+
"step": 680
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 25.98,
|
| 721 |
+
"eval_accuracy": 0.9705882352941176,
|
| 722 |
+
"eval_f1_score": 0.9810017271157168,
|
| 723 |
+
"eval_loss": 0.08736571669578552,
|
| 724 |
+
"eval_precision": 0.9759450171821306,
|
| 725 |
+
"eval_recall": 0.9861111111111112,
|
| 726 |
+
"eval_runtime": 2.1664,
|
| 727 |
+
"eval_samples_per_second": 172.637,
|
| 728 |
+
"eval_steps_per_second": 5.539,
|
| 729 |
+
"step": 682
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 26.29,
|
| 733 |
+
"learning_rate": 6.41025641025641e-06,
|
| 734 |
+
"loss": 0.1349,
|
| 735 |
+
"step": 690
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 26.67,
|
| 739 |
+
"learning_rate": 5.6980056980056985e-06,
|
| 740 |
+
"loss": 0.1429,
|
| 741 |
+
"step": 700
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 26.97,
|
| 745 |
+
"eval_accuracy": 0.9705882352941176,
|
| 746 |
+
"eval_f1_score": 0.9808027923211169,
|
| 747 |
+
"eval_loss": 0.08370037376880646,
|
| 748 |
+
"eval_precision": 0.9859649122807017,
|
| 749 |
+
"eval_recall": 0.9756944444444444,
|
| 750 |
+
"eval_runtime": 2.1544,
|
| 751 |
+
"eval_samples_per_second": 173.601,
|
| 752 |
+
"eval_steps_per_second": 5.57,
|
| 753 |
+
"step": 708
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 27.05,
|
| 757 |
+
"learning_rate": 4.985754985754986e-06,
|
| 758 |
+
"loss": 0.134,
|
| 759 |
+
"step": 710
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 27.43,
|
| 763 |
+
"learning_rate": 4.273504273504274e-06,
|
| 764 |
+
"loss": 0.1366,
|
| 765 |
+
"step": 720
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 27.81,
|
| 769 |
+
"learning_rate": 3.5612535612535615e-06,
|
| 770 |
+
"loss": 0.1444,
|
| 771 |
+
"step": 730
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 28.0,
|
| 775 |
+
"eval_accuracy": 0.9679144385026738,
|
| 776 |
+
"eval_f1_score": 0.9791666666666666,
|
| 777 |
+
"eval_loss": 0.08762019872665405,
|
| 778 |
+
"eval_precision": 0.9791666666666666,
|
| 779 |
+
"eval_recall": 0.9791666666666666,
|
| 780 |
+
"eval_runtime": 2.1635,
|
| 781 |
+
"eval_samples_per_second": 172.868,
|
| 782 |
+
"eval_steps_per_second": 5.547,
|
| 783 |
+
"step": 735
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 28.19,
|
| 787 |
+
"learning_rate": 2.8490028490028492e-06,
|
| 788 |
+
"loss": 0.1167,
|
| 789 |
+
"step": 740
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 28.57,
|
| 793 |
+
"learning_rate": 2.136752136752137e-06,
|
| 794 |
+
"loss": 0.1129,
|
| 795 |
+
"step": 750
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 28.95,
|
| 799 |
+
"learning_rate": 1.4245014245014246e-06,
|
| 800 |
+
"loss": 0.145,
|
| 801 |
+
"step": 760
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 28.99,
|
| 805 |
+
"eval_accuracy": 0.9705882352941176,
|
| 806 |
+
"eval_f1_score": 0.9808695652173912,
|
| 807 |
+
"eval_loss": 0.09031202644109726,
|
| 808 |
+
"eval_precision": 0.9825783972125436,
|
| 809 |
+
"eval_recall": 0.9791666666666666,
|
| 810 |
+
"eval_runtime": 2.1632,
|
| 811 |
+
"eval_samples_per_second": 172.893,
|
| 812 |
+
"eval_steps_per_second": 5.547,
|
| 813 |
+
"step": 761
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 29.33,
|
| 817 |
+
"learning_rate": 7.122507122507123e-07,
|
| 818 |
+
"loss": 0.1334,
|
| 819 |
+
"step": 770
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 29.71,
|
| 823 |
+
"learning_rate": 0.0,
|
| 824 |
+
"loss": 0.1445,
|
| 825 |
+
"step": 780
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 29.71,
|
| 829 |
+
"eval_accuracy": 0.9679144385026738,
|
| 830 |
+
"eval_f1_score": 0.9790940766550522,
|
| 831 |
+
"eval_loss": 0.08815235644578934,
|
| 832 |
+
"eval_precision": 0.9825174825174825,
|
| 833 |
+
"eval_recall": 0.9756944444444444,
|
| 834 |
+
"eval_runtime": 3.4052,
|
| 835 |
+
"eval_samples_per_second": 109.832,
|
| 836 |
+
"eval_steps_per_second": 3.524,
|
| 837 |
+
"step": 780
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 29.71,
|
| 841 |
+
"step": 780,
|
| 842 |
+
"total_flos": 4.5315392030480794e+17,
|
| 843 |
+
"train_loss": 0.2131147768252935,
|
| 844 |
+
"train_runtime": 1561.1697,
|
| 845 |
+
"train_samples_per_second": 64.529,
|
| 846 |
+
"train_steps_per_second": 0.5
|
| 847 |
+
}
|
| 848 |
+
],
|
| 849 |
+
"logging_steps": 10,
|
| 850 |
+
"max_steps": 780,
|
| 851 |
+
"num_input_tokens_seen": 0,
|
| 852 |
+
"num_train_epochs": 30,
|
| 853 |
+
"save_steps": 500,
|
| 854 |
+
"total_flos": 4.5315392030480794e+17,
|
| 855 |
+
"train_batch_size": 32,
|
| 856 |
+
"trial_name": null,
|
| 857 |
+
"trial_params": null
|
| 858 |
+
}
|