End of training
Browse files- README.md +28 -7
- all_results.json +17 -0
- eval_results.json +12 -0
- train_results.json +8 -0
- trainer_state.json +1272 -0
README.md
CHANGED
|
@@ -3,6 +3,8 @@ license: mit
|
|
| 3 |
base_model: roberta-large
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
metrics:
|
| 7 |
- precision
|
| 8 |
- recall
|
|
@@ -10,7 +12,26 @@ metrics:
|
|
| 10 |
- accuracy
|
| 11 |
model-index:
|
| 12 |
- name: ner-gec-roberta-large-v4
|
| 13 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
---
|
| 15 |
|
| 16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -18,13 +39,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
# ner-gec-roberta-large-v4
|
| 20 |
|
| 21 |
-
This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
-
- Loss: 0.
|
| 24 |
-
- Precision: 0.
|
| 25 |
-
- Recall: 0.
|
| 26 |
-
- F1: 0.
|
| 27 |
-
- Accuracy: 0.
|
| 28 |
|
| 29 |
## Model description
|
| 30 |
|
|
|
|
| 3 |
base_model: roberta-large
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- fursov/gec_ner_val3
|
| 8 |
metrics:
|
| 9 |
- precision
|
| 10 |
- recall
|
|
|
|
| 12 |
- accuracy
|
| 13 |
model-index:
|
| 14 |
- name: ner-gec-roberta-large-v4
|
| 15 |
+
results:
|
| 16 |
+
- task:
|
| 17 |
+
name: Token Classification
|
| 18 |
+
type: token-classification
|
| 19 |
+
dataset:
|
| 20 |
+
name: fursov/gec_ner_val3
|
| 21 |
+
type: fursov/gec_ner_val3
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Precision
|
| 24 |
+
type: precision
|
| 25 |
+
value: 0.643409688321442
|
| 26 |
+
- name: Recall
|
| 27 |
+
type: recall
|
| 28 |
+
value: 0.5775246056357017
|
| 29 |
+
- name: F1
|
| 30 |
+
type: f1
|
| 31 |
+
value: 0.6086894738711854
|
| 32 |
+
- name: Accuracy
|
| 33 |
+
type: accuracy
|
| 34 |
+
value: 0.9614897122818877
|
| 35 |
---
|
| 36 |
|
| 37 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 39 |
|
| 40 |
# ner-gec-roberta-large-v4
|
| 41 |
|
| 42 |
+
This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on the fursov/gec_ner_val3 dataset.
|
| 43 |
It achieves the following results on the evaluation set:
|
| 44 |
+
- Loss: 0.2489
|
| 45 |
+
- Precision: 0.6434
|
| 46 |
+
- Recall: 0.5775
|
| 47 |
+
- F1: 0.6087
|
| 48 |
+
- Accuracy: 0.9615
|
| 49 |
|
| 50 |
## Model description
|
| 51 |
|
all_results.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.9614897122818877,
|
| 4 |
+
"eval_f1": 0.6086894738711854,
|
| 5 |
+
"eval_loss": 0.24887563288211823,
|
| 6 |
+
"eval_precision": 0.643409688321442,
|
| 7 |
+
"eval_recall": 0.5775246056357017,
|
| 8 |
+
"eval_runtime": 11.0558,
|
| 9 |
+
"eval_samples": 4000,
|
| 10 |
+
"eval_samples_per_second": 361.799,
|
| 11 |
+
"eval_steps_per_second": 45.225,
|
| 12 |
+
"train_loss": 0.015828275546637547,
|
| 13 |
+
"train_runtime": 947.6725,
|
| 14 |
+
"train_samples": 55538,
|
| 15 |
+
"train_samples_per_second": 586.046,
|
| 16 |
+
"train_steps_per_second": 9.159
|
| 17 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.9614897122818877,
|
| 4 |
+
"eval_f1": 0.6086894738711854,
|
| 5 |
+
"eval_loss": 0.24887563288211823,
|
| 6 |
+
"eval_precision": 0.643409688321442,
|
| 7 |
+
"eval_recall": 0.5775246056357017,
|
| 8 |
+
"eval_runtime": 11.0558,
|
| 9 |
+
"eval_samples": 4000,
|
| 10 |
+
"eval_samples_per_second": 361.799,
|
| 11 |
+
"eval_steps_per_second": 45.225
|
| 12 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 0.015828275546637547,
|
| 4 |
+
"train_runtime": 947.6725,
|
| 5 |
+
"train_samples": 55538,
|
| 6 |
+
"train_samples_per_second": 586.046,
|
| 7 |
+
"train_steps_per_second": 9.159
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1272 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 8680,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.06,
|
| 13 |
+
"learning_rate": 4.971198156682028e-05,
|
| 14 |
+
"loss": 0.3578,
|
| 15 |
+
"step": 50
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.12,
|
| 19 |
+
"learning_rate": 4.9423963133640554e-05,
|
| 20 |
+
"loss": 0.2849,
|
| 21 |
+
"step": 100
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.17,
|
| 25 |
+
"learning_rate": 4.913594470046083e-05,
|
| 26 |
+
"loss": 0.2763,
|
| 27 |
+
"step": 150
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.23,
|
| 31 |
+
"learning_rate": 4.8847926267281106e-05,
|
| 32 |
+
"loss": 0.2625,
|
| 33 |
+
"step": 200
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.29,
|
| 37 |
+
"learning_rate": 4.8559907834101385e-05,
|
| 38 |
+
"loss": 0.2641,
|
| 39 |
+
"step": 250
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.35,
|
| 43 |
+
"learning_rate": 4.827188940092166e-05,
|
| 44 |
+
"loss": 0.2656,
|
| 45 |
+
"step": 300
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.4,
|
| 49 |
+
"learning_rate": 4.7983870967741937e-05,
|
| 50 |
+
"loss": 0.2574,
|
| 51 |
+
"step": 350
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.46,
|
| 55 |
+
"learning_rate": 4.7695852534562216e-05,
|
| 56 |
+
"loss": 0.262,
|
| 57 |
+
"step": 400
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.52,
|
| 61 |
+
"learning_rate": 4.7407834101382495e-05,
|
| 62 |
+
"loss": 0.2602,
|
| 63 |
+
"step": 450
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.58,
|
| 67 |
+
"learning_rate": 4.711981566820277e-05,
|
| 68 |
+
"loss": 0.2536,
|
| 69 |
+
"step": 500
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.58,
|
| 73 |
+
"eval_accuracy": 0.9346613714140859,
|
| 74 |
+
"eval_f1": 0.037628278221208664,
|
| 75 |
+
"eval_loss": 0.24692244827747345,
|
| 76 |
+
"eval_precision": 0.08139013452914798,
|
| 77 |
+
"eval_recall": 0.024470810300660645,
|
| 78 |
+
"eval_runtime": 11.142,
|
| 79 |
+
"eval_samples_per_second": 359.002,
|
| 80 |
+
"eval_steps_per_second": 44.875,
|
| 81 |
+
"step": 500
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.63,
|
| 85 |
+
"learning_rate": 4.6831797235023047e-05,
|
| 86 |
+
"loss": 0.2516,
|
| 87 |
+
"step": 550
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.69,
|
| 91 |
+
"learning_rate": 4.654377880184332e-05,
|
| 92 |
+
"loss": 0.251,
|
| 93 |
+
"step": 600
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.75,
|
| 97 |
+
"learning_rate": 4.62557603686636e-05,
|
| 98 |
+
"loss": 0.2515,
|
| 99 |
+
"step": 650
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.81,
|
| 103 |
+
"learning_rate": 4.596774193548387e-05,
|
| 104 |
+
"loss": 0.247,
|
| 105 |
+
"step": 700
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.86,
|
| 109 |
+
"learning_rate": 4.567972350230415e-05,
|
| 110 |
+
"loss": 0.251,
|
| 111 |
+
"step": 750
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.92,
|
| 115 |
+
"learning_rate": 4.539170506912442e-05,
|
| 116 |
+
"loss": 0.26,
|
| 117 |
+
"step": 800
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.98,
|
| 121 |
+
"learning_rate": 4.51036866359447e-05,
|
| 122 |
+
"loss": 0.2465,
|
| 123 |
+
"step": 850
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.04,
|
| 127 |
+
"learning_rate": 4.4815668202764974e-05,
|
| 128 |
+
"loss": 0.2415,
|
| 129 |
+
"step": 900
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.09,
|
| 133 |
+
"learning_rate": 4.452764976958525e-05,
|
| 134 |
+
"loss": 0.238,
|
| 135 |
+
"step": 950
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.15,
|
| 139 |
+
"learning_rate": 4.423963133640553e-05,
|
| 140 |
+
"loss": 0.2316,
|
| 141 |
+
"step": 1000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 1.15,
|
| 145 |
+
"eval_accuracy": 0.935907727407157,
|
| 146 |
+
"eval_f1": 0.13649655692859164,
|
| 147 |
+
"eval_loss": 0.23386752605438232,
|
| 148 |
+
"eval_precision": 0.22722989949748743,
|
| 149 |
+
"eval_recall": 0.09754617769987865,
|
| 150 |
+
"eval_runtime": 11.2428,
|
| 151 |
+
"eval_samples_per_second": 355.782,
|
| 152 |
+
"eval_steps_per_second": 44.473,
|
| 153 |
+
"step": 1000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 1.21,
|
| 157 |
+
"learning_rate": 4.395161290322581e-05,
|
| 158 |
+
"loss": 0.2301,
|
| 159 |
+
"step": 1050
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 1.27,
|
| 163 |
+
"learning_rate": 4.366359447004609e-05,
|
| 164 |
+
"loss": 0.226,
|
| 165 |
+
"step": 1100
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.32,
|
| 169 |
+
"learning_rate": 4.337557603686636e-05,
|
| 170 |
+
"loss": 0.2298,
|
| 171 |
+
"step": 1150
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.38,
|
| 175 |
+
"learning_rate": 4.308755760368664e-05,
|
| 176 |
+
"loss": 0.2252,
|
| 177 |
+
"step": 1200
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.44,
|
| 181 |
+
"learning_rate": 4.2799539170506915e-05,
|
| 182 |
+
"loss": 0.2249,
|
| 183 |
+
"step": 1250
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 1.5,
|
| 187 |
+
"learning_rate": 4.2511520737327194e-05,
|
| 188 |
+
"loss": 0.2285,
|
| 189 |
+
"step": 1300
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.56,
|
| 193 |
+
"learning_rate": 4.2223502304147466e-05,
|
| 194 |
+
"loss": 0.2189,
|
| 195 |
+
"step": 1350
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.61,
|
| 199 |
+
"learning_rate": 4.1935483870967746e-05,
|
| 200 |
+
"loss": 0.2256,
|
| 201 |
+
"step": 1400
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.67,
|
| 205 |
+
"learning_rate": 4.164746543778802e-05,
|
| 206 |
+
"loss": 0.2247,
|
| 207 |
+
"step": 1450
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.73,
|
| 211 |
+
"learning_rate": 4.13594470046083e-05,
|
| 212 |
+
"loss": 0.2175,
|
| 213 |
+
"step": 1500
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.73,
|
| 217 |
+
"eval_accuracy": 0.9391926148126241,
|
| 218 |
+
"eval_f1": 0.18226781461806188,
|
| 219 |
+
"eval_loss": 0.21722067892551422,
|
| 220 |
+
"eval_precision": 0.2842045129962868,
|
| 221 |
+
"eval_recall": 0.13415127410004044,
|
| 222 |
+
"eval_runtime": 11.2492,
|
| 223 |
+
"eval_samples_per_second": 355.579,
|
| 224 |
+
"eval_steps_per_second": 44.447,
|
| 225 |
+
"step": 1500
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.79,
|
| 229 |
+
"learning_rate": 4.107142857142857e-05,
|
| 230 |
+
"loss": 0.2143,
|
| 231 |
+
"step": 1550
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 1.84,
|
| 235 |
+
"learning_rate": 4.078341013824885e-05,
|
| 236 |
+
"loss": 0.2157,
|
| 237 |
+
"step": 1600
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.9,
|
| 241 |
+
"learning_rate": 4.049539170506912e-05,
|
| 242 |
+
"loss": 0.216,
|
| 243 |
+
"step": 1650
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 1.96,
|
| 247 |
+
"learning_rate": 4.02073732718894e-05,
|
| 248 |
+
"loss": 0.2156,
|
| 249 |
+
"step": 1700
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 2.02,
|
| 253 |
+
"learning_rate": 3.991935483870968e-05,
|
| 254 |
+
"loss": 0.2038,
|
| 255 |
+
"step": 1750
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 2.07,
|
| 259 |
+
"learning_rate": 3.963133640552996e-05,
|
| 260 |
+
"loss": 0.1842,
|
| 261 |
+
"step": 1800
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 2.13,
|
| 265 |
+
"learning_rate": 3.934331797235023e-05,
|
| 266 |
+
"loss": 0.1829,
|
| 267 |
+
"step": 1850
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 2.19,
|
| 271 |
+
"learning_rate": 3.905529953917051e-05,
|
| 272 |
+
"loss": 0.1812,
|
| 273 |
+
"step": 1900
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 2.25,
|
| 277 |
+
"learning_rate": 3.876728110599078e-05,
|
| 278 |
+
"loss": 0.1802,
|
| 279 |
+
"step": 1950
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 2.3,
|
| 283 |
+
"learning_rate": 3.847926267281106e-05,
|
| 284 |
+
"loss": 0.1757,
|
| 285 |
+
"step": 2000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 2.3,
|
| 289 |
+
"eval_accuracy": 0.9438294816004056,
|
| 290 |
+
"eval_f1": 0.31225296442687744,
|
| 291 |
+
"eval_loss": 0.19787320494651794,
|
| 292 |
+
"eval_precision": 0.40110006346519994,
|
| 293 |
+
"eval_recall": 0.25562896049615746,
|
| 294 |
+
"eval_runtime": 11.3248,
|
| 295 |
+
"eval_samples_per_second": 353.209,
|
| 296 |
+
"eval_steps_per_second": 44.151,
|
| 297 |
+
"step": 2000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 2.36,
|
| 301 |
+
"learning_rate": 3.819124423963134e-05,
|
| 302 |
+
"loss": 0.1801,
|
| 303 |
+
"step": 2050
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 2.42,
|
| 307 |
+
"learning_rate": 3.7903225806451614e-05,
|
| 308 |
+
"loss": 0.1779,
|
| 309 |
+
"step": 2100
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 2.48,
|
| 313 |
+
"learning_rate": 3.761520737327189e-05,
|
| 314 |
+
"loss": 0.1743,
|
| 315 |
+
"step": 2150
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 2.53,
|
| 319 |
+
"learning_rate": 3.7327188940092166e-05,
|
| 320 |
+
"loss": 0.1733,
|
| 321 |
+
"step": 2200
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 2.59,
|
| 325 |
+
"learning_rate": 3.7039170506912445e-05,
|
| 326 |
+
"loss": 0.1717,
|
| 327 |
+
"step": 2250
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 2.65,
|
| 331 |
+
"learning_rate": 3.675115207373272e-05,
|
| 332 |
+
"loss": 0.1721,
|
| 333 |
+
"step": 2300
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 2.71,
|
| 337 |
+
"learning_rate": 3.6463133640552996e-05,
|
| 338 |
+
"loss": 0.1713,
|
| 339 |
+
"step": 2350
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.76,
|
| 343 |
+
"learning_rate": 3.6175115207373276e-05,
|
| 344 |
+
"loss": 0.1699,
|
| 345 |
+
"step": 2400
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.82,
|
| 349 |
+
"learning_rate": 3.5887096774193555e-05,
|
| 350 |
+
"loss": 0.1656,
|
| 351 |
+
"step": 2450
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 2.88,
|
| 355 |
+
"learning_rate": 3.559907834101383e-05,
|
| 356 |
+
"loss": 0.1682,
|
| 357 |
+
"step": 2500
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 2.88,
|
| 361 |
+
"eval_accuracy": 0.9502196966496261,
|
| 362 |
+
"eval_f1": 0.3911483253588517,
|
| 363 |
+
"eval_loss": 0.18166299164295197,
|
| 364 |
+
"eval_precision": 0.4787234042553192,
|
| 365 |
+
"eval_recall": 0.3306592962114062,
|
| 366 |
+
"eval_runtime": 11.6137,
|
| 367 |
+
"eval_samples_per_second": 344.421,
|
| 368 |
+
"eval_steps_per_second": 43.053,
|
| 369 |
+
"step": 2500
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 2.94,
|
| 373 |
+
"learning_rate": 3.5311059907834107e-05,
|
| 374 |
+
"loss": 0.1664,
|
| 375 |
+
"step": 2550
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 3.0,
|
| 379 |
+
"learning_rate": 3.502304147465438e-05,
|
| 380 |
+
"loss": 0.1616,
|
| 381 |
+
"step": 2600
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 3.05,
|
| 385 |
+
"learning_rate": 3.473502304147466e-05,
|
| 386 |
+
"loss": 0.129,
|
| 387 |
+
"step": 2650
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 3.11,
|
| 391 |
+
"learning_rate": 3.444700460829493e-05,
|
| 392 |
+
"loss": 0.1245,
|
| 393 |
+
"step": 2700
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 3.17,
|
| 397 |
+
"learning_rate": 3.415898617511521e-05,
|
| 398 |
+
"loss": 0.1237,
|
| 399 |
+
"step": 2750
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 3.23,
|
| 403 |
+
"learning_rate": 3.387096774193548e-05,
|
| 404 |
+
"loss": 0.1235,
|
| 405 |
+
"step": 2800
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 3.28,
|
| 409 |
+
"learning_rate": 3.358294930875576e-05,
|
| 410 |
+
"loss": 0.1238,
|
| 411 |
+
"step": 2850
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 3.34,
|
| 415 |
+
"learning_rate": 3.3294930875576034e-05,
|
| 416 |
+
"loss": 0.1225,
|
| 417 |
+
"step": 2900
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 3.4,
|
| 421 |
+
"learning_rate": 3.300691244239631e-05,
|
| 422 |
+
"loss": 0.1268,
|
| 423 |
+
"step": 2950
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 3.46,
|
| 427 |
+
"learning_rate": 3.271889400921659e-05,
|
| 428 |
+
"loss": 0.121,
|
| 429 |
+
"step": 3000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 3.46,
|
| 433 |
+
"eval_accuracy": 0.9536841438168068,
|
| 434 |
+
"eval_f1": 0.450363008114299,
|
| 435 |
+
"eval_loss": 0.17527730762958527,
|
| 436 |
+
"eval_precision": 0.5309896548567243,
|
| 437 |
+
"eval_recall": 0.39099366320614803,
|
| 438 |
+
"eval_runtime": 11.2537,
|
| 439 |
+
"eval_samples_per_second": 355.44,
|
| 440 |
+
"eval_steps_per_second": 44.43,
|
| 441 |
+
"step": 3000
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 3.51,
|
| 445 |
+
"learning_rate": 3.2430875576036865e-05,
|
| 446 |
+
"loss": 0.1235,
|
| 447 |
+
"step": 3050
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 3.57,
|
| 451 |
+
"learning_rate": 3.2142857142857144e-05,
|
| 452 |
+
"loss": 0.1257,
|
| 453 |
+
"step": 3100
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 3.63,
|
| 457 |
+
"learning_rate": 3.185483870967742e-05,
|
| 458 |
+
"loss": 0.1187,
|
| 459 |
+
"step": 3150
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 3.69,
|
| 463 |
+
"learning_rate": 3.15668202764977e-05,
|
| 464 |
+
"loss": 0.1227,
|
| 465 |
+
"step": 3200
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 3.74,
|
| 469 |
+
"learning_rate": 3.1278801843317975e-05,
|
| 470 |
+
"loss": 0.1204,
|
| 471 |
+
"step": 3250
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 3.8,
|
| 475 |
+
"learning_rate": 3.0990783410138254e-05,
|
| 476 |
+
"loss": 0.1228,
|
| 477 |
+
"step": 3300
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 3.86,
|
| 481 |
+
"learning_rate": 3.0702764976958526e-05,
|
| 482 |
+
"loss": 0.1189,
|
| 483 |
+
"step": 3350
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 3.92,
|
| 487 |
+
"learning_rate": 3.0414746543778806e-05,
|
| 488 |
+
"loss": 0.1206,
|
| 489 |
+
"step": 3400
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 3.97,
|
| 493 |
+
"learning_rate": 3.0126728110599078e-05,
|
| 494 |
+
"loss": 0.1197,
|
| 495 |
+
"step": 3450
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 4.03,
|
| 499 |
+
"learning_rate": 2.9838709677419357e-05,
|
| 500 |
+
"loss": 0.0982,
|
| 501 |
+
"step": 3500
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 4.03,
|
| 505 |
+
"eval_accuracy": 0.9555959271621107,
|
| 506 |
+
"eval_f1": 0.4979952786000675,
|
| 507 |
+
"eval_loss": 0.18066732585430145,
|
| 508 |
+
"eval_precision": 0.5606175651733738,
|
| 509 |
+
"eval_recall": 0.4479573951732506,
|
| 510 |
+
"eval_runtime": 11.3416,
|
| 511 |
+
"eval_samples_per_second": 352.685,
|
| 512 |
+
"eval_steps_per_second": 44.086,
|
| 513 |
+
"step": 3500
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 4.09,
|
| 517 |
+
"learning_rate": 2.955069124423963e-05,
|
| 518 |
+
"loss": 0.0831,
|
| 519 |
+
"step": 3550
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 4.15,
|
| 523 |
+
"learning_rate": 2.926267281105991e-05,
|
| 524 |
+
"loss": 0.0855,
|
| 525 |
+
"step": 3600
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 4.21,
|
| 529 |
+
"learning_rate": 2.8974654377880185e-05,
|
| 530 |
+
"loss": 0.0819,
|
| 531 |
+
"step": 3650
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 4.26,
|
| 535 |
+
"learning_rate": 2.8686635944700464e-05,
|
| 536 |
+
"loss": 0.0864,
|
| 537 |
+
"step": 3700
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 4.32,
|
| 541 |
+
"learning_rate": 2.8398617511520736e-05,
|
| 542 |
+
"loss": 0.0846,
|
| 543 |
+
"step": 3750
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 4.38,
|
| 547 |
+
"learning_rate": 2.8110599078341016e-05,
|
| 548 |
+
"loss": 0.0854,
|
| 549 |
+
"step": 3800
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 4.44,
|
| 553 |
+
"learning_rate": 2.7822580645161288e-05,
|
| 554 |
+
"loss": 0.0852,
|
| 555 |
+
"step": 3850
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 4.49,
|
| 559 |
+
"learning_rate": 2.7534562211981567e-05,
|
| 560 |
+
"loss": 0.0828,
|
| 561 |
+
"step": 3900
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 4.55,
|
| 565 |
+
"learning_rate": 2.7246543778801846e-05,
|
| 566 |
+
"loss": 0.0855,
|
| 567 |
+
"step": 3950
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 4.61,
|
| 571 |
+
"learning_rate": 2.6958525345622122e-05,
|
| 572 |
+
"loss": 0.0858,
|
| 573 |
+
"step": 4000
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 4.61,
|
| 577 |
+
"eval_accuracy": 0.9576767079302041,
|
| 578 |
+
"eval_f1": 0.5303679621693512,
|
| 579 |
+
"eval_loss": 0.1731788069009781,
|
| 580 |
+
"eval_precision": 0.5867255190452836,
|
| 581 |
+
"eval_recall": 0.4838883645678846,
|
| 582 |
+
"eval_runtime": 11.3506,
|
| 583 |
+
"eval_samples_per_second": 352.406,
|
| 584 |
+
"eval_steps_per_second": 44.051,
|
| 585 |
+
"step": 4000
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 4.67,
|
| 589 |
+
"learning_rate": 2.66705069124424e-05,
|
| 590 |
+
"loss": 0.0867,
|
| 591 |
+
"step": 4050
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 4.72,
|
| 595 |
+
"learning_rate": 2.6382488479262674e-05,
|
| 596 |
+
"loss": 0.0872,
|
| 597 |
+
"step": 4100
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 4.78,
|
| 601 |
+
"learning_rate": 2.6094470046082953e-05,
|
| 602 |
+
"loss": 0.0844,
|
| 603 |
+
"step": 4150
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 4.84,
|
| 607 |
+
"learning_rate": 2.5806451612903226e-05,
|
| 608 |
+
"loss": 0.0877,
|
| 609 |
+
"step": 4200
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 4.9,
|
| 613 |
+
"learning_rate": 2.5518433179723505e-05,
|
| 614 |
+
"loss": 0.0837,
|
| 615 |
+
"step": 4250
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 4.95,
|
| 619 |
+
"learning_rate": 2.523041474654378e-05,
|
| 620 |
+
"loss": 0.0827,
|
| 621 |
+
"step": 4300
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 5.01,
|
| 625 |
+
"learning_rate": 2.4942396313364056e-05,
|
| 626 |
+
"loss": 0.054,
|
| 627 |
+
"step": 4350
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 5.07,
|
| 631 |
+
"learning_rate": 2.4654377880184332e-05,
|
| 632 |
+
"loss": 0.0576,
|
| 633 |
+
"step": 4400
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 5.13,
|
| 637 |
+
"learning_rate": 2.436635944700461e-05,
|
| 638 |
+
"loss": 0.0581,
|
| 639 |
+
"step": 4450
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 5.18,
|
| 643 |
+
"learning_rate": 2.4078341013824887e-05,
|
| 644 |
+
"loss": 0.0563,
|
| 645 |
+
"step": 4500
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 5.18,
|
| 649 |
+
"eval_accuracy": 0.9584794456884532,
|
| 650 |
+
"eval_f1": 0.5548340286595319,
|
| 651 |
+
"eval_loss": 0.1838800460100174,
|
| 652 |
+
"eval_precision": 0.6006598067708743,
|
| 653 |
+
"eval_recall": 0.5155049211271403,
|
| 654 |
+
"eval_runtime": 11.156,
|
| 655 |
+
"eval_samples_per_second": 358.552,
|
| 656 |
+
"eval_steps_per_second": 44.819,
|
| 657 |
+
"step": 4500
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 5.24,
|
| 661 |
+
"learning_rate": 2.3790322580645163e-05,
|
| 662 |
+
"loss": 0.0598,
|
| 663 |
+
"step": 4550
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 5.3,
|
| 667 |
+
"learning_rate": 2.350230414746544e-05,
|
| 668 |
+
"loss": 0.0585,
|
| 669 |
+
"step": 4600
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 5.36,
|
| 673 |
+
"learning_rate": 2.3214285714285715e-05,
|
| 674 |
+
"loss": 0.0564,
|
| 675 |
+
"step": 4650
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 5.41,
|
| 679 |
+
"learning_rate": 2.2926267281105994e-05,
|
| 680 |
+
"loss": 0.0571,
|
| 681 |
+
"step": 4700
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 5.47,
|
| 685 |
+
"learning_rate": 2.263824884792627e-05,
|
| 686 |
+
"loss": 0.0615,
|
| 687 |
+
"step": 4750
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 5.53,
|
| 691 |
+
"learning_rate": 2.2350230414746546e-05,
|
| 692 |
+
"loss": 0.0584,
|
| 693 |
+
"step": 4800
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 5.59,
|
| 697 |
+
"learning_rate": 2.206221198156682e-05,
|
| 698 |
+
"loss": 0.0589,
|
| 699 |
+
"step": 4850
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 5.65,
|
| 703 |
+
"learning_rate": 2.1774193548387097e-05,
|
| 704 |
+
"loss": 0.0591,
|
| 705 |
+
"step": 4900
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 5.7,
|
| 709 |
+
"learning_rate": 2.1486175115207373e-05,
|
| 710 |
+
"loss": 0.0609,
|
| 711 |
+
"step": 4950
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 5.76,
|
| 715 |
+
"learning_rate": 2.1198156682027652e-05,
|
| 716 |
+
"loss": 0.0586,
|
| 717 |
+
"step": 5000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 5.76,
|
| 721 |
+
"eval_accuracy": 0.9605179771008492,
|
| 722 |
+
"eval_f1": 0.569084249084249,
|
| 723 |
+
"eval_loss": 0.18037766218185425,
|
| 724 |
+
"eval_precision": 0.6231349270014439,
|
| 725 |
+
"eval_recall": 0.5236618578940272,
|
| 726 |
+
"eval_runtime": 11.0173,
|
| 727 |
+
"eval_samples_per_second": 363.066,
|
| 728 |
+
"eval_steps_per_second": 45.383,
|
| 729 |
+
"step": 5000
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 5.82,
|
| 733 |
+
"learning_rate": 2.0910138248847928e-05,
|
| 734 |
+
"loss": 0.0608,
|
| 735 |
+
"step": 5050
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 5.88,
|
| 739 |
+
"learning_rate": 2.0622119815668204e-05,
|
| 740 |
+
"loss": 0.0583,
|
| 741 |
+
"step": 5100
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 5.93,
|
| 745 |
+
"learning_rate": 2.033410138248848e-05,
|
| 746 |
+
"loss": 0.0597,
|
| 747 |
+
"step": 5150
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 5.99,
|
| 751 |
+
"learning_rate": 2.0046082949308755e-05,
|
| 752 |
+
"loss": 0.0591,
|
| 753 |
+
"step": 5200
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 6.05,
|
| 757 |
+
"learning_rate": 1.975806451612903e-05,
|
| 758 |
+
"loss": 0.0422,
|
| 759 |
+
"step": 5250
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 6.11,
|
| 763 |
+
"learning_rate": 1.9470046082949307e-05,
|
| 764 |
+
"loss": 0.037,
|
| 765 |
+
"step": 5300
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 6.16,
|
| 769 |
+
"learning_rate": 1.9182027649769586e-05,
|
| 770 |
+
"loss": 0.0387,
|
| 771 |
+
"step": 5350
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 6.22,
|
| 775 |
+
"learning_rate": 1.8894009216589862e-05,
|
| 776 |
+
"loss": 0.0425,
|
| 777 |
+
"step": 5400
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 6.28,
|
| 781 |
+
"learning_rate": 1.860599078341014e-05,
|
| 782 |
+
"loss": 0.0407,
|
| 783 |
+
"step": 5450
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 6.34,
|
| 787 |
+
"learning_rate": 1.8317972350230417e-05,
|
| 788 |
+
"loss": 0.0404,
|
| 789 |
+
"step": 5500
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 6.34,
|
| 793 |
+
"eval_accuracy": 0.9598631120875407,
|
| 794 |
+
"eval_f1": 0.5791728159533494,
|
| 795 |
+
"eval_loss": 0.1948222666978836,
|
| 796 |
+
"eval_precision": 0.6213794701475245,
|
| 797 |
+
"eval_recall": 0.5423351759471484,
|
| 798 |
+
"eval_runtime": 11.5255,
|
| 799 |
+
"eval_samples_per_second": 347.055,
|
| 800 |
+
"eval_steps_per_second": 43.382,
|
| 801 |
+
"step": 5500
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 6.39,
|
| 805 |
+
"learning_rate": 1.8029953917050693e-05,
|
| 806 |
+
"loss": 0.0421,
|
| 807 |
+
"step": 5550
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 6.45,
|
| 811 |
+
"learning_rate": 1.774193548387097e-05,
|
| 812 |
+
"loss": 0.04,
|
| 813 |
+
"step": 5600
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 6.51,
|
| 817 |
+
"learning_rate": 1.7453917050691245e-05,
|
| 818 |
+
"loss": 0.0412,
|
| 819 |
+
"step": 5650
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 6.57,
|
| 823 |
+
"learning_rate": 1.7165898617511524e-05,
|
| 824 |
+
"loss": 0.0397,
|
| 825 |
+
"step": 5700
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 6.62,
|
| 829 |
+
"learning_rate": 1.68778801843318e-05,
|
| 830 |
+
"loss": 0.0435,
|
| 831 |
+
"step": 5750
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 6.68,
|
| 835 |
+
"learning_rate": 1.6589861751152075e-05,
|
| 836 |
+
"loss": 0.0396,
|
| 837 |
+
"step": 5800
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 6.74,
|
| 841 |
+
"learning_rate": 1.630184331797235e-05,
|
| 842 |
+
"loss": 0.0428,
|
| 843 |
+
"step": 5850
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 6.8,
|
| 847 |
+
"learning_rate": 1.6013824884792627e-05,
|
| 848 |
+
"loss": 0.0383,
|
| 849 |
+
"step": 5900
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 6.85,
|
| 853 |
+
"learning_rate": 1.5725806451612903e-05,
|
| 854 |
+
"loss": 0.0426,
|
| 855 |
+
"step": 5950
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 6.91,
|
| 859 |
+
"learning_rate": 1.543778801843318e-05,
|
| 860 |
+
"loss": 0.0397,
|
| 861 |
+
"step": 6000
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 6.91,
|
| 865 |
+
"eval_accuracy": 0.9610460940470658,
|
| 866 |
+
"eval_f1": 0.5852459608920374,
|
| 867 |
+
"eval_loss": 0.1994314044713974,
|
| 868 |
+
"eval_precision": 0.6308735291825762,
|
| 869 |
+
"eval_recall": 0.5457732236753404,
|
| 870 |
+
"eval_runtime": 11.4564,
|
| 871 |
+
"eval_samples_per_second": 349.151,
|
| 872 |
+
"eval_steps_per_second": 43.644,
|
| 873 |
+
"step": 6000
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 6.97,
|
| 877 |
+
"learning_rate": 1.5149769585253456e-05,
|
| 878 |
+
"loss": 0.0386,
|
| 879 |
+
"step": 6050
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 7.03,
|
| 883 |
+
"learning_rate": 1.4861751152073732e-05,
|
| 884 |
+
"loss": 0.0339,
|
| 885 |
+
"step": 6100
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 7.09,
|
| 889 |
+
"learning_rate": 1.457373271889401e-05,
|
| 890 |
+
"loss": 0.0269,
|
| 891 |
+
"step": 6150
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 7.14,
|
| 895 |
+
"learning_rate": 1.4285714285714285e-05,
|
| 896 |
+
"loss": 0.028,
|
| 897 |
+
"step": 6200
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 7.2,
|
| 901 |
+
"learning_rate": 1.3997695852534561e-05,
|
| 902 |
+
"loss": 0.0257,
|
| 903 |
+
"step": 6250
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 7.26,
|
| 907 |
+
"learning_rate": 1.3709677419354839e-05,
|
| 908 |
+
"loss": 0.0281,
|
| 909 |
+
"step": 6300
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 7.32,
|
| 913 |
+
"learning_rate": 1.3421658986175115e-05,
|
| 914 |
+
"loss": 0.0269,
|
| 915 |
+
"step": 6350
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 7.37,
|
| 919 |
+
"learning_rate": 1.313364055299539e-05,
|
| 920 |
+
"loss": 0.0253,
|
| 921 |
+
"step": 6400
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 7.43,
|
| 925 |
+
"learning_rate": 1.284562211981567e-05,
|
| 926 |
+
"loss": 0.0274,
|
| 927 |
+
"step": 6450
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 7.49,
|
| 931 |
+
"learning_rate": 1.2557603686635947e-05,
|
| 932 |
+
"loss": 0.0281,
|
| 933 |
+
"step": 6500
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 7.49,
|
| 937 |
+
"eval_accuracy": 0.9610460940470658,
|
| 938 |
+
"eval_f1": 0.5931138477004273,
|
| 939 |
+
"eval_loss": 0.21313945949077606,
|
| 940 |
+
"eval_precision": 0.6344573315922882,
|
| 941 |
+
"eval_recall": 0.556828906565997,
|
| 942 |
+
"eval_runtime": 11.2791,
|
| 943 |
+
"eval_samples_per_second": 354.637,
|
| 944 |
+
"eval_steps_per_second": 44.33,
|
| 945 |
+
"step": 6500
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 7.55,
|
| 949 |
+
"learning_rate": 1.2269585253456221e-05,
|
| 950 |
+
"loss": 0.0263,
|
| 951 |
+
"step": 6550
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 7.6,
|
| 955 |
+
"learning_rate": 1.1981566820276497e-05,
|
| 956 |
+
"loss": 0.0255,
|
| 957 |
+
"step": 6600
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 7.66,
|
| 961 |
+
"learning_rate": 1.1693548387096775e-05,
|
| 962 |
+
"loss": 0.0279,
|
| 963 |
+
"step": 6650
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 7.72,
|
| 967 |
+
"learning_rate": 1.1405529953917052e-05,
|
| 968 |
+
"loss": 0.0286,
|
| 969 |
+
"step": 6700
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 7.78,
|
| 973 |
+
"learning_rate": 1.1117511520737328e-05,
|
| 974 |
+
"loss": 0.0281,
|
| 975 |
+
"step": 6750
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 7.83,
|
| 979 |
+
"learning_rate": 1.0829493087557604e-05,
|
| 980 |
+
"loss": 0.0273,
|
| 981 |
+
"step": 6800
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 7.89,
|
| 985 |
+
"learning_rate": 1.0541474654377881e-05,
|
| 986 |
+
"loss": 0.0271,
|
| 987 |
+
"step": 6850
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 7.95,
|
| 991 |
+
"learning_rate": 1.0253456221198157e-05,
|
| 992 |
+
"loss": 0.0294,
|
| 993 |
+
"step": 6900
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 8.01,
|
| 997 |
+
"learning_rate": 9.965437788018433e-06,
|
| 998 |
+
"loss": 0.0271,
|
| 999 |
+
"step": 6950
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 8.06,
|
| 1003 |
+
"learning_rate": 9.67741935483871e-06,
|
| 1004 |
+
"loss": 0.0182,
|
| 1005 |
+
"step": 7000
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 8.06,
|
| 1009 |
+
"eval_accuracy": 0.9625142591575478,
|
| 1010 |
+
"eval_f1": 0.6047417992854823,
|
| 1011 |
+
"eval_loss": 0.22494320571422577,
|
| 1012 |
+
"eval_precision": 0.6506950376640522,
|
| 1013 |
+
"eval_recall": 0.5648510179317784,
|
| 1014 |
+
"eval_runtime": 11.2013,
|
| 1015 |
+
"eval_samples_per_second": 357.1,
|
| 1016 |
+
"eval_steps_per_second": 44.638,
|
| 1017 |
+
"step": 7000
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 8.12,
|
| 1021 |
+
"learning_rate": 9.389400921658986e-06,
|
| 1022 |
+
"loss": 0.0187,
|
| 1023 |
+
"step": 7050
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 8.18,
|
| 1027 |
+
"learning_rate": 9.101382488479262e-06,
|
| 1028 |
+
"loss": 0.019,
|
| 1029 |
+
"step": 7100
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 8.24,
|
| 1033 |
+
"learning_rate": 8.81336405529954e-06,
|
| 1034 |
+
"loss": 0.0193,
|
| 1035 |
+
"step": 7150
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 8.29,
|
| 1039 |
+
"learning_rate": 8.525345622119817e-06,
|
| 1040 |
+
"loss": 0.0192,
|
| 1041 |
+
"step": 7200
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 8.35,
|
| 1045 |
+
"learning_rate": 8.237327188940093e-06,
|
| 1046 |
+
"loss": 0.0189,
|
| 1047 |
+
"step": 7250
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 8.41,
|
| 1051 |
+
"learning_rate": 7.949308755760369e-06,
|
| 1052 |
+
"loss": 0.0187,
|
| 1053 |
+
"step": 7300
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 8.47,
|
| 1057 |
+
"learning_rate": 7.661290322580646e-06,
|
| 1058 |
+
"loss": 0.0184,
|
| 1059 |
+
"step": 7350
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 8.53,
|
| 1063 |
+
"learning_rate": 7.373271889400922e-06,
|
| 1064 |
+
"loss": 0.0194,
|
| 1065 |
+
"step": 7400
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 8.58,
|
| 1069 |
+
"learning_rate": 7.085253456221199e-06,
|
| 1070 |
+
"loss": 0.02,
|
| 1071 |
+
"step": 7450
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 8.64,
|
| 1075 |
+
"learning_rate": 6.7972350230414745e-06,
|
| 1076 |
+
"loss": 0.0188,
|
| 1077 |
+
"step": 7500
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 8.64,
|
| 1081 |
+
"eval_accuracy": 0.9612467784866281,
|
| 1082 |
+
"eval_f1": 0.6081037966606403,
|
| 1083 |
+
"eval_loss": 0.23223160207271576,
|
| 1084 |
+
"eval_precision": 0.6412710280373832,
|
| 1085 |
+
"eval_recall": 0.5781987326412296,
|
| 1086 |
+
"eval_runtime": 11.0711,
|
| 1087 |
+
"eval_samples_per_second": 361.3,
|
| 1088 |
+
"eval_steps_per_second": 45.162,
|
| 1089 |
+
"step": 7500
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 8.7,
|
| 1093 |
+
"learning_rate": 6.509216589861751e-06,
|
| 1094 |
+
"loss": 0.0192,
|
| 1095 |
+
"step": 7550
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 8.76,
|
| 1099 |
+
"learning_rate": 6.221198156682028e-06,
|
| 1100 |
+
"loss": 0.019,
|
| 1101 |
+
"step": 7600
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 8.81,
|
| 1105 |
+
"learning_rate": 5.9331797235023045e-06,
|
| 1106 |
+
"loss": 0.0171,
|
| 1107 |
+
"step": 7650
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 8.87,
|
| 1111 |
+
"learning_rate": 5.64516129032258e-06,
|
| 1112 |
+
"loss": 0.0173,
|
| 1113 |
+
"step": 7700
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 8.93,
|
| 1117 |
+
"learning_rate": 5.357142857142857e-06,
|
| 1118 |
+
"loss": 0.0161,
|
| 1119 |
+
"step": 7750
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 8.99,
|
| 1123 |
+
"learning_rate": 5.0691244239631346e-06,
|
| 1124 |
+
"loss": 0.019,
|
| 1125 |
+
"step": 7800
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 9.04,
|
| 1129 |
+
"learning_rate": 4.78110599078341e-06,
|
| 1130 |
+
"loss": 0.0153,
|
| 1131 |
+
"step": 7850
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 9.1,
|
| 1135 |
+
"learning_rate": 4.493087557603687e-06,
|
| 1136 |
+
"loss": 0.0141,
|
| 1137 |
+
"step": 7900
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 9.16,
|
| 1141 |
+
"learning_rate": 4.205069124423963e-06,
|
| 1142 |
+
"loss": 0.013,
|
| 1143 |
+
"step": 7950
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 9.22,
|
| 1147 |
+
"learning_rate": 3.9170506912442395e-06,
|
| 1148 |
+
"loss": 0.0123,
|
| 1149 |
+
"step": 8000
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 9.22,
|
| 1153 |
+
"eval_accuracy": 0.9621762643119692,
|
| 1154 |
+
"eval_f1": 0.6119898596779377,
|
| 1155 |
+
"eval_loss": 0.24726828932762146,
|
| 1156 |
+
"eval_precision": 0.6505731420329461,
|
| 1157 |
+
"eval_recall": 0.5777268437373602,
|
| 1158 |
+
"eval_runtime": 11.3598,
|
| 1159 |
+
"eval_samples_per_second": 352.118,
|
| 1160 |
+
"eval_steps_per_second": 44.015,
|
| 1161 |
+
"step": 8000
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 9.27,
|
| 1165 |
+
"learning_rate": 3.6290322580645166e-06,
|
| 1166 |
+
"loss": 0.0127,
|
| 1167 |
+
"step": 8050
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 9.33,
|
| 1171 |
+
"learning_rate": 3.341013824884793e-06,
|
| 1172 |
+
"loss": 0.014,
|
| 1173 |
+
"step": 8100
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 9.39,
|
| 1177 |
+
"learning_rate": 3.052995391705069e-06,
|
| 1178 |
+
"loss": 0.0135,
|
| 1179 |
+
"step": 8150
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 9.45,
|
| 1183 |
+
"learning_rate": 2.7649769585253458e-06,
|
| 1184 |
+
"loss": 0.0141,
|
| 1185 |
+
"step": 8200
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 9.5,
|
| 1189 |
+
"learning_rate": 2.4769585253456224e-06,
|
| 1190 |
+
"loss": 0.0135,
|
| 1191 |
+
"step": 8250
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 9.56,
|
| 1195 |
+
"learning_rate": 2.1889400921658987e-06,
|
| 1196 |
+
"loss": 0.0127,
|
| 1197 |
+
"step": 8300
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 9.62,
|
| 1201 |
+
"learning_rate": 1.9009216589861754e-06,
|
| 1202 |
+
"loss": 0.0129,
|
| 1203 |
+
"step": 8350
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 9.68,
|
| 1207 |
+
"learning_rate": 1.6129032258064516e-06,
|
| 1208 |
+
"loss": 0.0132,
|
| 1209 |
+
"step": 8400
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 9.74,
|
| 1213 |
+
"learning_rate": 1.3248847926267283e-06,
|
| 1214 |
+
"loss": 0.0129,
|
| 1215 |
+
"step": 8450
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 9.79,
|
| 1219 |
+
"learning_rate": 1.0368663594470047e-06,
|
| 1220 |
+
"loss": 0.0123,
|
| 1221 |
+
"step": 8500
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 9.79,
|
| 1225 |
+
"eval_accuracy": 0.961405213570493,
|
| 1226 |
+
"eval_f1": 0.6081335464393536,
|
| 1227 |
+
"eval_loss": 0.24913595616817474,
|
| 1228 |
+
"eval_precision": 0.6426694692590647,
|
| 1229 |
+
"eval_recall": 0.5771201294323851,
|
| 1230 |
+
"eval_runtime": 11.5972,
|
| 1231 |
+
"eval_samples_per_second": 344.912,
|
| 1232 |
+
"eval_steps_per_second": 43.114,
|
| 1233 |
+
"step": 8500
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 9.85,
|
| 1237 |
+
"learning_rate": 7.488479262672811e-07,
|
| 1238 |
+
"loss": 0.0145,
|
| 1239 |
+
"step": 8550
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 9.91,
|
| 1243 |
+
"learning_rate": 4.6082949308755763e-07,
|
| 1244 |
+
"loss": 0.0129,
|
| 1245 |
+
"step": 8600
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 9.97,
|
| 1249 |
+
"learning_rate": 1.728110599078341e-07,
|
| 1250 |
+
"loss": 0.0134,
|
| 1251 |
+
"step": 8650
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 10.0,
|
| 1255 |
+
"step": 8680,
|
| 1256 |
+
"total_flos": 4.589148928762742e+16,
|
| 1257 |
+
"train_loss": 0.015828275546637547,
|
| 1258 |
+
"train_runtime": 947.6725,
|
| 1259 |
+
"train_samples_per_second": 586.046,
|
| 1260 |
+
"train_steps_per_second": 9.159
|
| 1261 |
+
}
|
| 1262 |
+
],
|
| 1263 |
+
"logging_steps": 50,
|
| 1264 |
+
"max_steps": 8680,
|
| 1265 |
+
"num_input_tokens_seen": 0,
|
| 1266 |
+
"num_train_epochs": 10,
|
| 1267 |
+
"save_steps": 500,
|
| 1268 |
+
"total_flos": 4.589148928762742e+16,
|
| 1269 |
+
"train_batch_size": 64,
|
| 1270 |
+
"trial_name": null,
|
| 1271 |
+
"trial_params": null
|
| 1272 |
+
}
|