Nguyen Tien
commited on
Commit
•
516cf2c
1
Parent(s):
3f1a536
vuihocrnd/teacher-status-van-tiny-256-1-2
Browse files- README.md +8 -8
- all_results.json +16 -0
- eval_results.json +11 -0
- train_results.json +8 -0
- trainer_state.json +984 -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.
|
| 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.
|
| 47 |
-
- Precision: 0.
|
| 48 |
|
| 49 |
## Model description
|
| 50 |
|
|
|
|
| 24 |
metrics:
|
| 25 |
- name: Accuracy
|
| 26 |
type: accuracy
|
| 27 |
+
value: 0.9716684155299056
|
| 28 |
- name: Recall
|
| 29 |
type: recall
|
| 30 |
+
value: 0.9754098360655737
|
| 31 |
- name: Precision
|
| 32 |
type: precision
|
| 33 |
+
value: 0.9802306425041186
|
| 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: 0.0859
|
| 44 |
+
- Accuracy: 0.9717
|
| 45 |
+
- F1 Score: 0.9778
|
| 46 |
+
- Recall: 0.9754
|
| 47 |
+
- Precision: 0.9802
|
| 48 |
|
| 49 |
## Model description
|
| 50 |
|
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 29.55,
|
| 3 |
+
"eval_accuracy": 0.9716684155299056,
|
| 4 |
+
"eval_f1_score": 0.9778142974527526,
|
| 5 |
+
"eval_loss": 0.0859055444598198,
|
| 6 |
+
"eval_precision": 0.9802306425041186,
|
| 7 |
+
"eval_recall": 0.9754098360655737,
|
| 8 |
+
"eval_runtime": 6.1587,
|
| 9 |
+
"eval_samples_per_second": 154.741,
|
| 10 |
+
"eval_steps_per_second": 1.299,
|
| 11 |
+
"total_flos": 1.1503239286004122e+18,
|
| 12 |
+
"train_loss": 0.2626483961789295,
|
| 13 |
+
"train_runtime": 6214.0737,
|
| 14 |
+
"train_samples_per_second": 41.379,
|
| 15 |
+
"train_steps_per_second": 0.159
|
| 16 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 29.55,
|
| 3 |
+
"eval_accuracy": 0.9716684155299056,
|
| 4 |
+
"eval_f1_score": 0.9778142974527526,
|
| 5 |
+
"eval_loss": 0.0859055444598198,
|
| 6 |
+
"eval_precision": 0.9802306425041186,
|
| 7 |
+
"eval_recall": 0.9754098360655737,
|
| 8 |
+
"eval_runtime": 6.1587,
|
| 9 |
+
"eval_samples_per_second": 154.741,
|
| 10 |
+
"eval_steps_per_second": 1.299
|
| 11 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 29.55,
|
| 3 |
+
"total_flos": 1.1503239286004122e+18,
|
| 4 |
+
"train_loss": 0.2626483961789295,
|
| 5 |
+
"train_runtime": 6214.0737,
|
| 6 |
+
"train_samples_per_second": 41.379,
|
| 7 |
+
"train_steps_per_second": 0.159
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,984 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9778142974527526,
|
| 3 |
+
"best_model_checkpoint": "teacher-status-van-tiny-256-1-2/checkpoint-703",
|
| 4 |
+
"epoch": 29.55223880597015,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 990,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.3,
|
| 13 |
+
"learning_rate": 5.050505050505051e-06,
|
| 14 |
+
"loss": 0.6865,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.6,
|
| 19 |
+
"learning_rate": 1.0101010101010101e-05,
|
| 20 |
+
"loss": 0.683,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.9,
|
| 25 |
+
"learning_rate": 1.5151515151515153e-05,
|
| 26 |
+
"loss": 0.6722,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.99,
|
| 31 |
+
"eval_accuracy": 0.640083945435467,
|
| 32 |
+
"eval_f1_score": 0.780550223928343,
|
| 33 |
+
"eval_loss": 0.6498541831970215,
|
| 34 |
+
"eval_precision": 0.640083945435467,
|
| 35 |
+
"eval_recall": 1.0,
|
| 36 |
+
"eval_runtime": 6.6964,
|
| 37 |
+
"eval_samples_per_second": 142.315,
|
| 38 |
+
"eval_steps_per_second": 1.195,
|
| 39 |
+
"step": 33
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.19,
|
| 43 |
+
"learning_rate": 2.0202020202020203e-05,
|
| 44 |
+
"loss": 0.646,
|
| 45 |
+
"step": 40
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.49,
|
| 49 |
+
"learning_rate": 2.5252525252525256e-05,
|
| 50 |
+
"loss": 0.6078,
|
| 51 |
+
"step": 50
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.79,
|
| 55 |
+
"learning_rate": 3.0303030303030306e-05,
|
| 56 |
+
"loss": 0.5431,
|
| 57 |
+
"step": 60
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 2.0,
|
| 61 |
+
"eval_accuracy": 0.7817418677859391,
|
| 62 |
+
"eval_f1_score": 0.8531073446327684,
|
| 63 |
+
"eval_loss": 0.4163793921470642,
|
| 64 |
+
"eval_precision": 0.749379652605459,
|
| 65 |
+
"eval_recall": 0.9901639344262295,
|
| 66 |
+
"eval_runtime": 6.7638,
|
| 67 |
+
"eval_samples_per_second": 140.898,
|
| 68 |
+
"eval_steps_per_second": 1.183,
|
| 69 |
+
"step": 67
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 2.09,
|
| 73 |
+
"learning_rate": 3.535353535353535e-05,
|
| 74 |
+
"loss": 0.497,
|
| 75 |
+
"step": 70
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 2.39,
|
| 79 |
+
"learning_rate": 4.0404040404040405e-05,
|
| 80 |
+
"loss": 0.4483,
|
| 81 |
+
"step": 80
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 2.69,
|
| 85 |
+
"learning_rate": 4.545454545454546e-05,
|
| 86 |
+
"loss": 0.4193,
|
| 87 |
+
"step": 90
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 2.99,
|
| 91 |
+
"learning_rate": 4.994388327721661e-05,
|
| 92 |
+
"loss": 0.393,
|
| 93 |
+
"step": 100
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 2.99,
|
| 97 |
+
"eval_accuracy": 0.887722980062959,
|
| 98 |
+
"eval_f1_score": 0.9078380706287683,
|
| 99 |
+
"eval_loss": 0.2832907438278198,
|
| 100 |
+
"eval_precision": 0.956442831215971,
|
| 101 |
+
"eval_recall": 0.8639344262295082,
|
| 102 |
+
"eval_runtime": 6.6321,
|
| 103 |
+
"eval_samples_per_second": 143.695,
|
| 104 |
+
"eval_steps_per_second": 1.206,
|
| 105 |
+
"step": 100
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 3.28,
|
| 109 |
+
"learning_rate": 4.938271604938271e-05,
|
| 110 |
+
"loss": 0.3729,
|
| 111 |
+
"step": 110
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 3.58,
|
| 115 |
+
"learning_rate": 4.882154882154882e-05,
|
| 116 |
+
"loss": 0.3616,
|
| 117 |
+
"step": 120
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 3.88,
|
| 121 |
+
"learning_rate": 4.8260381593714935e-05,
|
| 122 |
+
"loss": 0.354,
|
| 123 |
+
"step": 130
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 4.0,
|
| 127 |
+
"eval_accuracy": 0.9275970619097587,
|
| 128 |
+
"eval_f1_score": 0.9435813573180704,
|
| 129 |
+
"eval_loss": 0.19304586946964264,
|
| 130 |
+
"eval_precision": 0.9412724306688418,
|
| 131 |
+
"eval_recall": 0.9459016393442623,
|
| 132 |
+
"eval_runtime": 6.5785,
|
| 133 |
+
"eval_samples_per_second": 144.865,
|
| 134 |
+
"eval_steps_per_second": 1.216,
|
| 135 |
+
"step": 134
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 4.18,
|
| 139 |
+
"learning_rate": 4.7699214365881036e-05,
|
| 140 |
+
"loss": 0.3214,
|
| 141 |
+
"step": 140
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 4.48,
|
| 145 |
+
"learning_rate": 4.713804713804714e-05,
|
| 146 |
+
"loss": 0.3272,
|
| 147 |
+
"step": 150
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 4.78,
|
| 151 |
+
"learning_rate": 4.6576879910213244e-05,
|
| 152 |
+
"loss": 0.3007,
|
| 153 |
+
"step": 160
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 4.99,
|
| 157 |
+
"eval_accuracy": 0.9370409233997902,
|
| 158 |
+
"eval_f1_score": 0.9510603588907015,
|
| 159 |
+
"eval_loss": 0.15851934254169464,
|
| 160 |
+
"eval_precision": 0.9464285714285714,
|
| 161 |
+
"eval_recall": 0.9557377049180328,
|
| 162 |
+
"eval_runtime": 6.4566,
|
| 163 |
+
"eval_samples_per_second": 147.6,
|
| 164 |
+
"eval_steps_per_second": 1.239,
|
| 165 |
+
"step": 167
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 5.07,
|
| 169 |
+
"learning_rate": 4.601571268237935e-05,
|
| 170 |
+
"loss": 0.3006,
|
| 171 |
+
"step": 170
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 5.37,
|
| 175 |
+
"learning_rate": 4.545454545454546e-05,
|
| 176 |
+
"loss": 0.2935,
|
| 177 |
+
"step": 180
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 5.67,
|
| 181 |
+
"learning_rate": 4.4893378226711566e-05,
|
| 182 |
+
"loss": 0.3092,
|
| 183 |
+
"step": 190
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 5.97,
|
| 187 |
+
"learning_rate": 4.433221099887767e-05,
|
| 188 |
+
"loss": 0.2898,
|
| 189 |
+
"step": 200
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 6.0,
|
| 193 |
+
"eval_accuracy": 0.9464847848898216,
|
| 194 |
+
"eval_f1_score": 0.9580936729663106,
|
| 195 |
+
"eval_loss": 0.144499272108078,
|
| 196 |
+
"eval_precision": 0.9604612850082372,
|
| 197 |
+
"eval_recall": 0.9557377049180328,
|
| 198 |
+
"eval_runtime": 6.0258,
|
| 199 |
+
"eval_samples_per_second": 158.154,
|
| 200 |
+
"eval_steps_per_second": 1.328,
|
| 201 |
+
"step": 201
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 6.27,
|
| 205 |
+
"learning_rate": 4.3771043771043774e-05,
|
| 206 |
+
"loss": 0.2696,
|
| 207 |
+
"step": 210
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 6.57,
|
| 211 |
+
"learning_rate": 4.3209876543209875e-05,
|
| 212 |
+
"loss": 0.3025,
|
| 213 |
+
"step": 220
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 6.87,
|
| 217 |
+
"learning_rate": 4.264870931537598e-05,
|
| 218 |
+
"loss": 0.2824,
|
| 219 |
+
"step": 230
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 6.99,
|
| 223 |
+
"eval_accuracy": 0.9464847848898216,
|
| 224 |
+
"eval_f1_score": 0.9579554822753504,
|
| 225 |
+
"eval_loss": 0.13527622818946838,
|
| 226 |
+
"eval_precision": 0.9635157545605307,
|
| 227 |
+
"eval_recall": 0.9524590163934427,
|
| 228 |
+
"eval_runtime": 6.0159,
|
| 229 |
+
"eval_samples_per_second": 158.414,
|
| 230 |
+
"eval_steps_per_second": 1.33,
|
| 231 |
+
"step": 234
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 7.16,
|
| 235 |
+
"learning_rate": 4.208754208754209e-05,
|
| 236 |
+
"loss": 0.2782,
|
| 237 |
+
"step": 240
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 7.46,
|
| 241 |
+
"learning_rate": 4.15263748597082e-05,
|
| 242 |
+
"loss": 0.2629,
|
| 243 |
+
"step": 250
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 7.76,
|
| 247 |
+
"learning_rate": 4.0965207631874305e-05,
|
| 248 |
+
"loss": 0.2763,
|
| 249 |
+
"step": 260
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 8.0,
|
| 253 |
+
"eval_accuracy": 0.9485834207764953,
|
| 254 |
+
"eval_f1_score": 0.960323886639676,
|
| 255 |
+
"eval_loss": 0.13593612611293793,
|
| 256 |
+
"eval_precision": 0.9488,
|
| 257 |
+
"eval_recall": 0.9721311475409836,
|
| 258 |
+
"eval_runtime": 6.3017,
|
| 259 |
+
"eval_samples_per_second": 151.228,
|
| 260 |
+
"eval_steps_per_second": 1.269,
|
| 261 |
+
"step": 268
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 8.06,
|
| 265 |
+
"learning_rate": 4.0404040404040405e-05,
|
| 266 |
+
"loss": 0.2698,
|
| 267 |
+
"step": 270
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 8.36,
|
| 271 |
+
"learning_rate": 3.984287317620651e-05,
|
| 272 |
+
"loss": 0.2621,
|
| 273 |
+
"step": 280
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 8.66,
|
| 277 |
+
"learning_rate": 3.9281705948372613e-05,
|
| 278 |
+
"loss": 0.2631,
|
| 279 |
+
"step": 290
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 8.96,
|
| 283 |
+
"learning_rate": 3.872053872053872e-05,
|
| 284 |
+
"loss": 0.2473,
|
| 285 |
+
"step": 300
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 8.99,
|
| 289 |
+
"eval_accuracy": 0.9569779643231899,
|
| 290 |
+
"eval_f1_score": 0.9664209664209664,
|
| 291 |
+
"eval_loss": 0.12131528556346893,
|
| 292 |
+
"eval_precision": 0.9656301145662848,
|
| 293 |
+
"eval_recall": 0.9672131147540983,
|
| 294 |
+
"eval_runtime": 6.691,
|
| 295 |
+
"eval_samples_per_second": 142.431,
|
| 296 |
+
"eval_steps_per_second": 1.196,
|
| 297 |
+
"step": 301
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 9.25,
|
| 301 |
+
"learning_rate": 3.815937149270483e-05,
|
| 302 |
+
"loss": 0.2339,
|
| 303 |
+
"step": 310
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 9.55,
|
| 307 |
+
"learning_rate": 3.7598204264870936e-05,
|
| 308 |
+
"loss": 0.249,
|
| 309 |
+
"step": 320
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 9.85,
|
| 313 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 314 |
+
"loss": 0.2598,
|
| 315 |
+
"step": 330
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 10.0,
|
| 319 |
+
"eval_accuracy": 0.9569779643231899,
|
| 320 |
+
"eval_f1_score": 0.966530612244898,
|
| 321 |
+
"eval_loss": 0.10907502472400665,
|
| 322 |
+
"eval_precision": 0.9626016260162602,
|
| 323 |
+
"eval_recall": 0.9704918032786886,
|
| 324 |
+
"eval_runtime": 6.9942,
|
| 325 |
+
"eval_samples_per_second": 136.256,
|
| 326 |
+
"eval_steps_per_second": 1.144,
|
| 327 |
+
"step": 335
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 10.15,
|
| 331 |
+
"learning_rate": 3.6475869809203144e-05,
|
| 332 |
+
"loss": 0.2497,
|
| 333 |
+
"step": 340
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 10.45,
|
| 337 |
+
"learning_rate": 3.5914702581369245e-05,
|
| 338 |
+
"loss": 0.253,
|
| 339 |
+
"step": 350
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 10.75,
|
| 343 |
+
"learning_rate": 3.535353535353535e-05,
|
| 344 |
+
"loss": 0.2476,
|
| 345 |
+
"step": 360
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 10.99,
|
| 349 |
+
"eval_accuracy": 0.9632738719832109,
|
| 350 |
+
"eval_f1_score": 0.9714285714285714,
|
| 351 |
+
"eval_loss": 0.1040654331445694,
|
| 352 |
+
"eval_precision": 0.967479674796748,
|
| 353 |
+
"eval_recall": 0.9754098360655737,
|
| 354 |
+
"eval_runtime": 6.6817,
|
| 355 |
+
"eval_samples_per_second": 142.629,
|
| 356 |
+
"eval_steps_per_second": 1.197,
|
| 357 |
+
"step": 368
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 11.04,
|
| 361 |
+
"learning_rate": 3.4792368125701466e-05,
|
| 362 |
+
"loss": 0.2314,
|
| 363 |
+
"step": 370
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 11.34,
|
| 367 |
+
"learning_rate": 3.423120089786757e-05,
|
| 368 |
+
"loss": 0.2422,
|
| 369 |
+
"step": 380
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 11.64,
|
| 373 |
+
"learning_rate": 3.3670033670033675e-05,
|
| 374 |
+
"loss": 0.2406,
|
| 375 |
+
"step": 390
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 11.94,
|
| 379 |
+
"learning_rate": 3.3108866442199775e-05,
|
| 380 |
+
"loss": 0.2376,
|
| 381 |
+
"step": 400
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 12.0,
|
| 385 |
+
"eval_accuracy": 0.9601259181532005,
|
| 386 |
+
"eval_f1_score": 0.9686468646864688,
|
| 387 |
+
"eval_loss": 0.09974055737257004,
|
| 388 |
+
"eval_precision": 0.9750830564784053,
|
| 389 |
+
"eval_recall": 0.9622950819672131,
|
| 390 |
+
"eval_runtime": 6.6227,
|
| 391 |
+
"eval_samples_per_second": 143.899,
|
| 392 |
+
"eval_steps_per_second": 1.208,
|
| 393 |
+
"step": 402
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 12.24,
|
| 397 |
+
"learning_rate": 3.254769921436588e-05,
|
| 398 |
+
"loss": 0.2282,
|
| 399 |
+
"step": 410
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 12.54,
|
| 403 |
+
"learning_rate": 3.198653198653199e-05,
|
| 404 |
+
"loss": 0.2264,
|
| 405 |
+
"step": 420
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 12.84,
|
| 409 |
+
"learning_rate": 3.14253647586981e-05,
|
| 410 |
+
"loss": 0.2402,
|
| 411 |
+
"step": 430
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 12.99,
|
| 415 |
+
"eval_accuracy": 0.9622245540398741,
|
| 416 |
+
"eval_f1_score": 0.9703947368421052,
|
| 417 |
+
"eval_loss": 0.09718549996614456,
|
| 418 |
+
"eval_precision": 0.9735973597359736,
|
| 419 |
+
"eval_recall": 0.9672131147540983,
|
| 420 |
+
"eval_runtime": 6.1102,
|
| 421 |
+
"eval_samples_per_second": 155.969,
|
| 422 |
+
"eval_steps_per_second": 1.309,
|
| 423 |
+
"step": 435
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 13.13,
|
| 427 |
+
"learning_rate": 3.08641975308642e-05,
|
| 428 |
+
"loss": 0.2216,
|
| 429 |
+
"step": 440
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 13.43,
|
| 433 |
+
"learning_rate": 3.0303030303030306e-05,
|
| 434 |
+
"loss": 0.2361,
|
| 435 |
+
"step": 450
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 13.73,
|
| 439 |
+
"learning_rate": 2.9741863075196406e-05,
|
| 440 |
+
"loss": 0.2324,
|
| 441 |
+
"step": 460
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 14.0,
|
| 445 |
+
"eval_accuracy": 0.9664218258132214,
|
| 446 |
+
"eval_f1_score": 0.973941368078176,
|
| 447 |
+
"eval_loss": 0.09498707950115204,
|
| 448 |
+
"eval_precision": 0.9676375404530745,
|
| 449 |
+
"eval_recall": 0.980327868852459,
|
| 450 |
+
"eval_runtime": 6.0066,
|
| 451 |
+
"eval_samples_per_second": 158.659,
|
| 452 |
+
"eval_steps_per_second": 1.332,
|
| 453 |
+
"step": 469
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 14.03,
|
| 457 |
+
"learning_rate": 2.9180695847362517e-05,
|
| 458 |
+
"loss": 0.2223,
|
| 459 |
+
"step": 470
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 14.33,
|
| 463 |
+
"learning_rate": 2.8619528619528618e-05,
|
| 464 |
+
"loss": 0.213,
|
| 465 |
+
"step": 480
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 14.63,
|
| 469 |
+
"learning_rate": 2.8058361391694725e-05,
|
| 470 |
+
"loss": 0.2206,
|
| 471 |
+
"step": 490
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 14.93,
|
| 475 |
+
"learning_rate": 2.7497194163860833e-05,
|
| 476 |
+
"loss": 0.2256,
|
| 477 |
+
"step": 500
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 14.99,
|
| 481 |
+
"eval_accuracy": 0.9706190975865687,
|
| 482 |
+
"eval_f1_score": 0.9770114942528735,
|
| 483 |
+
"eval_loss": 0.09094734489917755,
|
| 484 |
+
"eval_precision": 0.9786184210526315,
|
| 485 |
+
"eval_recall": 0.9754098360655737,
|
| 486 |
+
"eval_runtime": 5.9668,
|
| 487 |
+
"eval_samples_per_second": 159.718,
|
| 488 |
+
"eval_steps_per_second": 1.341,
|
| 489 |
+
"step": 502
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 15.22,
|
| 493 |
+
"learning_rate": 2.6936026936026937e-05,
|
| 494 |
+
"loss": 0.209,
|
| 495 |
+
"step": 510
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 15.52,
|
| 499 |
+
"learning_rate": 2.6374859708193044e-05,
|
| 500 |
+
"loss": 0.2254,
|
| 501 |
+
"step": 520
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 15.82,
|
| 505 |
+
"learning_rate": 2.581369248035915e-05,
|
| 506 |
+
"loss": 0.21,
|
| 507 |
+
"step": 530
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 16.0,
|
| 511 |
+
"eval_accuracy": 0.9622245540398741,
|
| 512 |
+
"eval_f1_score": 0.970345963756178,
|
| 513 |
+
"eval_loss": 0.09220422059297562,
|
| 514 |
+
"eval_precision": 0.9751655629139073,
|
| 515 |
+
"eval_recall": 0.9655737704918033,
|
| 516 |
+
"eval_runtime": 6.5986,
|
| 517 |
+
"eval_samples_per_second": 144.424,
|
| 518 |
+
"eval_steps_per_second": 1.212,
|
| 519 |
+
"step": 536
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 16.12,
|
| 523 |
+
"learning_rate": 2.5252525252525256e-05,
|
| 524 |
+
"loss": 0.2114,
|
| 525 |
+
"step": 540
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 16.42,
|
| 529 |
+
"learning_rate": 2.4691358024691357e-05,
|
| 530 |
+
"loss": 0.1963,
|
| 531 |
+
"step": 550
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 16.72,
|
| 535 |
+
"learning_rate": 2.4130190796857467e-05,
|
| 536 |
+
"loss": 0.217,
|
| 537 |
+
"step": 560
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 16.99,
|
| 541 |
+
"eval_accuracy": 0.9611752360965372,
|
| 542 |
+
"eval_f1_score": 0.9695473251028807,
|
| 543 |
+
"eval_loss": 0.09329694509506226,
|
| 544 |
+
"eval_precision": 0.9735537190082645,
|
| 545 |
+
"eval_recall": 0.9655737704918033,
|
| 546 |
+
"eval_runtime": 6.5505,
|
| 547 |
+
"eval_samples_per_second": 145.485,
|
| 548 |
+
"eval_steps_per_second": 1.221,
|
| 549 |
+
"step": 569
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 17.01,
|
| 553 |
+
"learning_rate": 2.356902356902357e-05,
|
| 554 |
+
"loss": 0.219,
|
| 555 |
+
"step": 570
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 17.31,
|
| 559 |
+
"learning_rate": 2.3007856341189676e-05,
|
| 560 |
+
"loss": 0.2154,
|
| 561 |
+
"step": 580
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 17.61,
|
| 565 |
+
"learning_rate": 2.2446689113355783e-05,
|
| 566 |
+
"loss": 0.2157,
|
| 567 |
+
"step": 590
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 17.91,
|
| 571 |
+
"learning_rate": 2.1885521885521887e-05,
|
| 572 |
+
"loss": 0.2092,
|
| 573 |
+
"step": 600
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 18.0,
|
| 577 |
+
"eval_accuracy": 0.9664218258132214,
|
| 578 |
+
"eval_f1_score": 0.9738134206219312,
|
| 579 |
+
"eval_loss": 0.08909059315919876,
|
| 580 |
+
"eval_precision": 0.9722222222222222,
|
| 581 |
+
"eval_recall": 0.9754098360655737,
|
| 582 |
+
"eval_runtime": 5.9927,
|
| 583 |
+
"eval_samples_per_second": 159.027,
|
| 584 |
+
"eval_steps_per_second": 1.335,
|
| 585 |
+
"step": 603
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 18.21,
|
| 589 |
+
"learning_rate": 2.132435465768799e-05,
|
| 590 |
+
"loss": 0.1979,
|
| 591 |
+
"step": 610
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 18.51,
|
| 595 |
+
"learning_rate": 2.07631874298541e-05,
|
| 596 |
+
"loss": 0.1975,
|
| 597 |
+
"step": 620
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 18.81,
|
| 601 |
+
"learning_rate": 2.0202020202020203e-05,
|
| 602 |
+
"loss": 0.2063,
|
| 603 |
+
"step": 630
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 18.99,
|
| 607 |
+
"eval_accuracy": 0.9653725078698846,
|
| 608 |
+
"eval_f1_score": 0.972972972972973,
|
| 609 |
+
"eval_loss": 0.09130384773015976,
|
| 610 |
+
"eval_precision": 0.972176759410802,
|
| 611 |
+
"eval_recall": 0.9737704918032787,
|
| 612 |
+
"eval_runtime": 5.9748,
|
| 613 |
+
"eval_samples_per_second": 159.504,
|
| 614 |
+
"eval_steps_per_second": 1.339,
|
| 615 |
+
"step": 636
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 19.1,
|
| 619 |
+
"learning_rate": 1.9640852974186307e-05,
|
| 620 |
+
"loss": 0.215,
|
| 621 |
+
"step": 640
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 19.4,
|
| 625 |
+
"learning_rate": 1.9079685746352414e-05,
|
| 626 |
+
"loss": 0.214,
|
| 627 |
+
"step": 650
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 19.7,
|
| 631 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 632 |
+
"loss": 0.2072,
|
| 633 |
+
"step": 660
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 20.0,
|
| 637 |
+
"learning_rate": 1.7957351290684622e-05,
|
| 638 |
+
"loss": 0.2217,
|
| 639 |
+
"step": 670
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 20.0,
|
| 643 |
+
"eval_accuracy": 0.9643231899265478,
|
| 644 |
+
"eval_f1_score": 0.971993410214168,
|
| 645 |
+
"eval_loss": 0.09169190376996994,
|
| 646 |
+
"eval_precision": 0.9768211920529801,
|
| 647 |
+
"eval_recall": 0.9672131147540983,
|
| 648 |
+
"eval_runtime": 6.2954,
|
| 649 |
+
"eval_samples_per_second": 151.381,
|
| 650 |
+
"eval_steps_per_second": 1.271,
|
| 651 |
+
"step": 670
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 20.3,
|
| 655 |
+
"learning_rate": 1.7396184062850733e-05,
|
| 656 |
+
"loss": 0.1996,
|
| 657 |
+
"step": 680
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 20.6,
|
| 661 |
+
"learning_rate": 1.6835016835016837e-05,
|
| 662 |
+
"loss": 0.1968,
|
| 663 |
+
"step": 690
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 20.9,
|
| 667 |
+
"learning_rate": 1.627384960718294e-05,
|
| 668 |
+
"loss": 0.1952,
|
| 669 |
+
"step": 700
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 20.99,
|
| 673 |
+
"eval_accuracy": 0.9716684155299056,
|
| 674 |
+
"eval_f1_score": 0.9778142974527526,
|
| 675 |
+
"eval_loss": 0.0859055444598198,
|
| 676 |
+
"eval_precision": 0.9802306425041186,
|
| 677 |
+
"eval_recall": 0.9754098360655737,
|
| 678 |
+
"eval_runtime": 6.6363,
|
| 679 |
+
"eval_samples_per_second": 143.604,
|
| 680 |
+
"eval_steps_per_second": 1.205,
|
| 681 |
+
"step": 703
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 21.19,
|
| 685 |
+
"learning_rate": 1.571268237934905e-05,
|
| 686 |
+
"loss": 0.2051,
|
| 687 |
+
"step": 710
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 21.49,
|
| 691 |
+
"learning_rate": 1.5151515151515153e-05,
|
| 692 |
+
"loss": 0.1927,
|
| 693 |
+
"step": 720
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 21.79,
|
| 697 |
+
"learning_rate": 1.4590347923681259e-05,
|
| 698 |
+
"loss": 0.2068,
|
| 699 |
+
"step": 730
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 22.0,
|
| 703 |
+
"eval_accuracy": 0.968520461699895,
|
| 704 |
+
"eval_f1_score": 0.9754500818330606,
|
| 705 |
+
"eval_loss": 0.09068847447633743,
|
| 706 |
+
"eval_precision": 0.9738562091503268,
|
| 707 |
+
"eval_recall": 0.9770491803278688,
|
| 708 |
+
"eval_runtime": 6.1893,
|
| 709 |
+
"eval_samples_per_second": 153.975,
|
| 710 |
+
"eval_steps_per_second": 1.293,
|
| 711 |
+
"step": 737
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 22.09,
|
| 715 |
+
"learning_rate": 1.4029180695847363e-05,
|
| 716 |
+
"loss": 0.1957,
|
| 717 |
+
"step": 740
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 22.39,
|
| 721 |
+
"learning_rate": 1.3468013468013468e-05,
|
| 722 |
+
"loss": 0.2021,
|
| 723 |
+
"step": 750
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 22.69,
|
| 727 |
+
"learning_rate": 1.2906846240179574e-05,
|
| 728 |
+
"loss": 0.202,
|
| 729 |
+
"step": 760
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 22.99,
|
| 733 |
+
"learning_rate": 1.2345679012345678e-05,
|
| 734 |
+
"loss": 0.1914,
|
| 735 |
+
"step": 770
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 22.99,
|
| 739 |
+
"eval_accuracy": 0.9695697796432319,
|
| 740 |
+
"eval_f1_score": 0.9762878168438266,
|
| 741 |
+
"eval_loss": 0.08471482992172241,
|
| 742 |
+
"eval_precision": 0.9738988580750407,
|
| 743 |
+
"eval_recall": 0.978688524590164,
|
| 744 |
+
"eval_runtime": 5.9499,
|
| 745 |
+
"eval_samples_per_second": 160.172,
|
| 746 |
+
"eval_steps_per_second": 1.345,
|
| 747 |
+
"step": 770
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 23.28,
|
| 751 |
+
"learning_rate": 1.1784511784511786e-05,
|
| 752 |
+
"loss": 0.1937,
|
| 753 |
+
"step": 780
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 23.58,
|
| 757 |
+
"learning_rate": 1.1223344556677892e-05,
|
| 758 |
+
"loss": 0.1876,
|
| 759 |
+
"step": 790
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 23.88,
|
| 763 |
+
"learning_rate": 1.0662177328843996e-05,
|
| 764 |
+
"loss": 0.1961,
|
| 765 |
+
"step": 800
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 24.0,
|
| 769 |
+
"eval_accuracy": 0.968520461699895,
|
| 770 |
+
"eval_f1_score": 0.9754500818330606,
|
| 771 |
+
"eval_loss": 0.08703567832708359,
|
| 772 |
+
"eval_precision": 0.9738562091503268,
|
| 773 |
+
"eval_recall": 0.9770491803278688,
|
| 774 |
+
"eval_runtime": 6.0627,
|
| 775 |
+
"eval_samples_per_second": 157.191,
|
| 776 |
+
"eval_steps_per_second": 1.32,
|
| 777 |
+
"step": 804
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 24.18,
|
| 781 |
+
"learning_rate": 1.0101010101010101e-05,
|
| 782 |
+
"loss": 0.1817,
|
| 783 |
+
"step": 810
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 24.48,
|
| 787 |
+
"learning_rate": 9.539842873176207e-06,
|
| 788 |
+
"loss": 0.1869,
|
| 789 |
+
"step": 820
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 24.78,
|
| 793 |
+
"learning_rate": 8.978675645342311e-06,
|
| 794 |
+
"loss": 0.1911,
|
| 795 |
+
"step": 830
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 24.99,
|
| 799 |
+
"eval_accuracy": 0.9664218258132214,
|
| 800 |
+
"eval_f1_score": 0.9738562091503268,
|
| 801 |
+
"eval_loss": 0.08837948739528656,
|
| 802 |
+
"eval_precision": 0.9706840390879479,
|
| 803 |
+
"eval_recall": 0.9770491803278688,
|
| 804 |
+
"eval_runtime": 6.585,
|
| 805 |
+
"eval_samples_per_second": 144.722,
|
| 806 |
+
"eval_steps_per_second": 1.215,
|
| 807 |
+
"step": 837
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 25.07,
|
| 811 |
+
"learning_rate": 8.417508417508419e-06,
|
| 812 |
+
"loss": 0.1904,
|
| 813 |
+
"step": 840
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 25.37,
|
| 817 |
+
"learning_rate": 7.856341189674524e-06,
|
| 818 |
+
"loss": 0.1831,
|
| 819 |
+
"step": 850
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 25.67,
|
| 823 |
+
"learning_rate": 7.295173961840629e-06,
|
| 824 |
+
"loss": 0.184,
|
| 825 |
+
"step": 860
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 25.97,
|
| 829 |
+
"learning_rate": 6.734006734006734e-06,
|
| 830 |
+
"loss": 0.1961,
|
| 831 |
+
"step": 870
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 26.0,
|
| 835 |
+
"eval_accuracy": 0.968520461699895,
|
| 836 |
+
"eval_f1_score": 0.9753694581280787,
|
| 837 |
+
"eval_loss": 0.08696460723876953,
|
| 838 |
+
"eval_precision": 0.9769736842105263,
|
| 839 |
+
"eval_recall": 0.9737704918032787,
|
| 840 |
+
"eval_runtime": 6.5592,
|
| 841 |
+
"eval_samples_per_second": 145.293,
|
| 842 |
+
"eval_steps_per_second": 1.22,
|
| 843 |
+
"step": 871
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 26.27,
|
| 847 |
+
"learning_rate": 6.172839506172839e-06,
|
| 848 |
+
"loss": 0.1988,
|
| 849 |
+
"step": 880
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 26.57,
|
| 853 |
+
"learning_rate": 5.611672278338946e-06,
|
| 854 |
+
"loss": 0.1796,
|
| 855 |
+
"step": 890
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 26.87,
|
| 859 |
+
"learning_rate": 5.050505050505051e-06,
|
| 860 |
+
"loss": 0.1978,
|
| 861 |
+
"step": 900
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 26.99,
|
| 865 |
+
"eval_accuracy": 0.968520461699895,
|
| 866 |
+
"eval_f1_score": 0.9754098360655737,
|
| 867 |
+
"eval_loss": 0.08714743703603745,
|
| 868 |
+
"eval_precision": 0.9754098360655737,
|
| 869 |
+
"eval_recall": 0.9754098360655737,
|
| 870 |
+
"eval_runtime": 5.8888,
|
| 871 |
+
"eval_samples_per_second": 161.832,
|
| 872 |
+
"eval_steps_per_second": 1.359,
|
| 873 |
+
"step": 904
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 27.16,
|
| 877 |
+
"learning_rate": 4.489337822671156e-06,
|
| 878 |
+
"loss": 0.2099,
|
| 879 |
+
"step": 910
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 27.46,
|
| 883 |
+
"learning_rate": 3.928170594837262e-06,
|
| 884 |
+
"loss": 0.1867,
|
| 885 |
+
"step": 920
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 27.76,
|
| 889 |
+
"learning_rate": 3.367003367003367e-06,
|
| 890 |
+
"loss": 0.1854,
|
| 891 |
+
"step": 930
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 28.0,
|
| 895 |
+
"eval_accuracy": 0.968520461699895,
|
| 896 |
+
"eval_f1_score": 0.9754500818330606,
|
| 897 |
+
"eval_loss": 0.08582841604948044,
|
| 898 |
+
"eval_precision": 0.9738562091503268,
|
| 899 |
+
"eval_recall": 0.9770491803278688,
|
| 900 |
+
"eval_runtime": 5.9622,
|
| 901 |
+
"eval_samples_per_second": 159.839,
|
| 902 |
+
"eval_steps_per_second": 1.342,
|
| 903 |
+
"step": 938
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 28.06,
|
| 907 |
+
"learning_rate": 2.805836139169473e-06,
|
| 908 |
+
"loss": 0.1931,
|
| 909 |
+
"step": 940
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 28.36,
|
| 913 |
+
"learning_rate": 2.244668911335578e-06,
|
| 914 |
+
"loss": 0.1957,
|
| 915 |
+
"step": 950
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 28.66,
|
| 919 |
+
"learning_rate": 1.6835016835016836e-06,
|
| 920 |
+
"loss": 0.1849,
|
| 921 |
+
"step": 960
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 28.96,
|
| 925 |
+
"learning_rate": 1.122334455667789e-06,
|
| 926 |
+
"loss": 0.1733,
|
| 927 |
+
"step": 970
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 28.99,
|
| 931 |
+
"eval_accuracy": 0.968520461699895,
|
| 932 |
+
"eval_f1_score": 0.9753694581280787,
|
| 933 |
+
"eval_loss": 0.08600697666406631,
|
| 934 |
+
"eval_precision": 0.9769736842105263,
|
| 935 |
+
"eval_recall": 0.9737704918032787,
|
| 936 |
+
"eval_runtime": 6.5847,
|
| 937 |
+
"eval_samples_per_second": 144.729,
|
| 938 |
+
"eval_steps_per_second": 1.215,
|
| 939 |
+
"step": 971
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 29.25,
|
| 943 |
+
"learning_rate": 5.611672278338944e-07,
|
| 944 |
+
"loss": 0.202,
|
| 945 |
+
"step": 980
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 29.55,
|
| 949 |
+
"learning_rate": 0.0,
|
| 950 |
+
"loss": 0.1762,
|
| 951 |
+
"step": 990
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 29.55,
|
| 955 |
+
"eval_accuracy": 0.9664218258132214,
|
| 956 |
+
"eval_f1_score": 0.9737704918032787,
|
| 957 |
+
"eval_loss": 0.0858435109257698,
|
| 958 |
+
"eval_precision": 0.9737704918032787,
|
| 959 |
+
"eval_recall": 0.9737704918032787,
|
| 960 |
+
"eval_runtime": 6.517,
|
| 961 |
+
"eval_samples_per_second": 146.233,
|
| 962 |
+
"eval_steps_per_second": 1.228,
|
| 963 |
+
"step": 990
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 29.55,
|
| 967 |
+
"step": 990,
|
| 968 |
+
"total_flos": 1.1503239286004122e+18,
|
| 969 |
+
"train_loss": 0.2626483961789295,
|
| 970 |
+
"train_runtime": 6214.0737,
|
| 971 |
+
"train_samples_per_second": 41.379,
|
| 972 |
+
"train_steps_per_second": 0.159
|
| 973 |
+
}
|
| 974 |
+
],
|
| 975 |
+
"logging_steps": 10,
|
| 976 |
+
"max_steps": 990,
|
| 977 |
+
"num_input_tokens_seen": 0,
|
| 978 |
+
"num_train_epochs": 30,
|
| 979 |
+
"save_steps": 500,
|
| 980 |
+
"total_flos": 1.1503239286004122e+18,
|
| 981 |
+
"train_batch_size": 128,
|
| 982 |
+
"trial_name": null,
|
| 983 |
+
"trial_params": null
|
| 984 |
+
}
|