End of training
Browse files- README.md +8 -6
- all_results.json +15 -0
- eval_results.json +11 -0
- train_results.json +7 -0
- trainer_state.json +948 -0
README.md
CHANGED
|
@@ -2,6 +2,8 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: facebook/dinov2-small
|
| 4 |
tags:
|
|
|
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
metrics:
|
| 7 |
- accuracy
|
|
@@ -18,13 +20,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
# dinov2-small-finetuned-galaxy10-decals
|
| 20 |
|
| 21 |
-
This model is a fine-tuned version of [facebook/dinov2-small](https://huggingface.co/facebook/dinov2-small) on
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
-
- Loss: 0.
|
| 24 |
-
- Accuracy: 0.
|
| 25 |
-
- Precision: 0.
|
| 26 |
-
- Recall: 0.
|
| 27 |
-
- F1: 0.
|
| 28 |
|
| 29 |
## Model description
|
| 30 |
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: facebook/dinov2-small
|
| 4 |
tags:
|
| 5 |
+
- image-classification
|
| 6 |
+
- vision
|
| 7 |
- generated_from_trainer
|
| 8 |
metrics:
|
| 9 |
- accuracy
|
|
|
|
| 20 |
|
| 21 |
# dinov2-small-finetuned-galaxy10-decals
|
| 22 |
|
| 23 |
+
This model is a fine-tuned version of [facebook/dinov2-small](https://huggingface.co/facebook/dinov2-small) on the matthieulel/galaxy10_decals dataset.
|
| 24 |
It achieves the following results on the evaluation set:
|
| 25 |
+
- Loss: 0.4852
|
| 26 |
+
- Accuracy: 0.8613
|
| 27 |
+
- Precision: 0.8626
|
| 28 |
+
- Recall: 0.8613
|
| 29 |
+
- F1: 0.8615
|
| 30 |
|
| 31 |
## Model description
|
| 32 |
|
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 29.76,
|
| 3 |
+
"eval_accuracy": 0.8613303269447576,
|
| 4 |
+
"eval_f1": 0.861465358212238,
|
| 5 |
+
"eval_loss": 0.48520544171333313,
|
| 6 |
+
"eval_precision": 0.8626143442892683,
|
| 7 |
+
"eval_recall": 0.8613303269447576,
|
| 8 |
+
"eval_runtime": 9.3978,
|
| 9 |
+
"eval_samples_per_second": 188.767,
|
| 10 |
+
"eval_steps_per_second": 1.49,
|
| 11 |
+
"train_loss": 0.49311745294960596,
|
| 12 |
+
"train_runtime": 4214.8321,
|
| 13 |
+
"train_samples_per_second": 113.613,
|
| 14 |
+
"train_steps_per_second": 0.221
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 29.76,
|
| 3 |
+
"eval_accuracy": 0.8613303269447576,
|
| 4 |
+
"eval_f1": 0.861465358212238,
|
| 5 |
+
"eval_loss": 0.48520544171333313,
|
| 6 |
+
"eval_precision": 0.8626143442892683,
|
| 7 |
+
"eval_recall": 0.8613303269447576,
|
| 8 |
+
"eval_runtime": 9.3978,
|
| 9 |
+
"eval_samples_per_second": 188.767,
|
| 10 |
+
"eval_steps_per_second": 1.49
|
| 11 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 29.76,
|
| 3 |
+
"train_loss": 0.49311745294960596,
|
| 4 |
+
"train_runtime": 4214.8321,
|
| 5 |
+
"train_samples_per_second": 113.613,
|
| 6 |
+
"train_steps_per_second": 0.221
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,948 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8613303269447576,
|
| 3 |
+
"best_model_checkpoint": "dinov2-small-finetuned-galaxy10-decals/checkpoint-843",
|
| 4 |
+
"epoch": 29.76,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 930,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.32,
|
| 13 |
+
"learning_rate": 5.376344086021506e-06,
|
| 14 |
+
"loss": 2.4305,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.64,
|
| 19 |
+
"learning_rate": 1.0752688172043012e-05,
|
| 20 |
+
"loss": 1.7384,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.96,
|
| 25 |
+
"learning_rate": 1.6129032258064517e-05,
|
| 26 |
+
"loss": 1.279,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.99,
|
| 31 |
+
"eval_accuracy": 0.64543404735062,
|
| 32 |
+
"eval_f1": 0.6242340263402473,
|
| 33 |
+
"eval_loss": 0.9926303625106812,
|
| 34 |
+
"eval_precision": 0.6589011432073757,
|
| 35 |
+
"eval_recall": 0.64543404735062,
|
| 36 |
+
"eval_runtime": 9.3596,
|
| 37 |
+
"eval_samples_per_second": 189.538,
|
| 38 |
+
"eval_steps_per_second": 1.496,
|
| 39 |
+
"step": 31
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.28,
|
| 43 |
+
"learning_rate": 2.1505376344086024e-05,
|
| 44 |
+
"loss": 1.0405,
|
| 45 |
+
"step": 40
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.6,
|
| 49 |
+
"learning_rate": 2.6881720430107527e-05,
|
| 50 |
+
"loss": 0.8614,
|
| 51 |
+
"step": 50
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.92,
|
| 55 |
+
"learning_rate": 3.2258064516129034e-05,
|
| 56 |
+
"loss": 0.8187,
|
| 57 |
+
"step": 60
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 1.98,
|
| 61 |
+
"eval_accuracy": 0.7948139797068771,
|
| 62 |
+
"eval_f1": 0.7947500876210484,
|
| 63 |
+
"eval_loss": 0.601404070854187,
|
| 64 |
+
"eval_precision": 0.815133947285654,
|
| 65 |
+
"eval_recall": 0.7948139797068771,
|
| 66 |
+
"eval_runtime": 9.494,
|
| 67 |
+
"eval_samples_per_second": 186.855,
|
| 68 |
+
"eval_steps_per_second": 1.475,
|
| 69 |
+
"step": 62
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 2.24,
|
| 73 |
+
"learning_rate": 3.763440860215054e-05,
|
| 74 |
+
"loss": 0.804,
|
| 75 |
+
"step": 70
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 2.56,
|
| 79 |
+
"learning_rate": 4.301075268817205e-05,
|
| 80 |
+
"loss": 0.8018,
|
| 81 |
+
"step": 80
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 2.88,
|
| 85 |
+
"learning_rate": 4.8387096774193554e-05,
|
| 86 |
+
"loss": 0.77,
|
| 87 |
+
"step": 90
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 2.98,
|
| 91 |
+
"eval_accuracy": 0.7818489289740699,
|
| 92 |
+
"eval_f1": 0.7777498847922488,
|
| 93 |
+
"eval_loss": 0.6322661638259888,
|
| 94 |
+
"eval_precision": 0.792845144303136,
|
| 95 |
+
"eval_recall": 0.7818489289740699,
|
| 96 |
+
"eval_runtime": 9.3073,
|
| 97 |
+
"eval_samples_per_second": 190.603,
|
| 98 |
+
"eval_steps_per_second": 1.504,
|
| 99 |
+
"step": 93
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 3.2,
|
| 103 |
+
"learning_rate": 4.9581839904420555e-05,
|
| 104 |
+
"loss": 0.8237,
|
| 105 |
+
"step": 100
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 3.52,
|
| 109 |
+
"learning_rate": 4.898446833930705e-05,
|
| 110 |
+
"loss": 0.7688,
|
| 111 |
+
"step": 110
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 3.84,
|
| 115 |
+
"learning_rate": 4.8387096774193554e-05,
|
| 116 |
+
"loss": 0.6743,
|
| 117 |
+
"step": 120
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 4.0,
|
| 121 |
+
"eval_accuracy": 0.8139797068771139,
|
| 122 |
+
"eval_f1": 0.8083410489046907,
|
| 123 |
+
"eval_loss": 0.5554975867271423,
|
| 124 |
+
"eval_precision": 0.8149070860867645,
|
| 125 |
+
"eval_recall": 0.8139797068771139,
|
| 126 |
+
"eval_runtime": 9.2832,
|
| 127 |
+
"eval_samples_per_second": 191.097,
|
| 128 |
+
"eval_steps_per_second": 1.508,
|
| 129 |
+
"step": 125
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 4.16,
|
| 133 |
+
"learning_rate": 4.778972520908005e-05,
|
| 134 |
+
"loss": 0.6708,
|
| 135 |
+
"step": 130
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 4.48,
|
| 139 |
+
"learning_rate": 4.7192353643966546e-05,
|
| 140 |
+
"loss": 0.6506,
|
| 141 |
+
"step": 140
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 4.8,
|
| 145 |
+
"learning_rate": 4.659498207885305e-05,
|
| 146 |
+
"loss": 0.6407,
|
| 147 |
+
"step": 150
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 4.99,
|
| 151 |
+
"eval_accuracy": 0.8077790304396844,
|
| 152 |
+
"eval_f1": 0.8096290518551817,
|
| 153 |
+
"eval_loss": 0.5731789469718933,
|
| 154 |
+
"eval_precision": 0.8173808911652968,
|
| 155 |
+
"eval_recall": 0.8077790304396844,
|
| 156 |
+
"eval_runtime": 10.0887,
|
| 157 |
+
"eval_samples_per_second": 175.84,
|
| 158 |
+
"eval_steps_per_second": 1.388,
|
| 159 |
+
"step": 156
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 5.12,
|
| 163 |
+
"learning_rate": 4.5997610513739546e-05,
|
| 164 |
+
"loss": 0.6176,
|
| 165 |
+
"step": 160
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 5.44,
|
| 169 |
+
"learning_rate": 4.540023894862604e-05,
|
| 170 |
+
"loss": 0.6407,
|
| 171 |
+
"step": 170
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 5.76,
|
| 175 |
+
"learning_rate": 4.4802867383512545e-05,
|
| 176 |
+
"loss": 0.64,
|
| 177 |
+
"step": 180
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 5.98,
|
| 181 |
+
"eval_accuracy": 0.8359639233370914,
|
| 182 |
+
"eval_f1": 0.8320665323451614,
|
| 183 |
+
"eval_loss": 0.49118176102638245,
|
| 184 |
+
"eval_precision": 0.8344483546731383,
|
| 185 |
+
"eval_recall": 0.8359639233370914,
|
| 186 |
+
"eval_runtime": 9.7793,
|
| 187 |
+
"eval_samples_per_second": 181.404,
|
| 188 |
+
"eval_steps_per_second": 1.432,
|
| 189 |
+
"step": 187
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 6.08,
|
| 193 |
+
"learning_rate": 4.420549581839905e-05,
|
| 194 |
+
"loss": 0.6076,
|
| 195 |
+
"step": 190
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 6.4,
|
| 199 |
+
"learning_rate": 4.360812425328555e-05,
|
| 200 |
+
"loss": 0.6048,
|
| 201 |
+
"step": 200
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 6.72,
|
| 205 |
+
"learning_rate": 4.301075268817205e-05,
|
| 206 |
+
"loss": 0.5685,
|
| 207 |
+
"step": 210
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 6.98,
|
| 211 |
+
"eval_accuracy": 0.818489289740699,
|
| 212 |
+
"eval_f1": 0.8163008296617178,
|
| 213 |
+
"eval_loss": 0.5089312195777893,
|
| 214 |
+
"eval_precision": 0.8194969459682901,
|
| 215 |
+
"eval_recall": 0.818489289740699,
|
| 216 |
+
"eval_runtime": 9.8459,
|
| 217 |
+
"eval_samples_per_second": 180.176,
|
| 218 |
+
"eval_steps_per_second": 1.422,
|
| 219 |
+
"step": 218
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 7.04,
|
| 223 |
+
"learning_rate": 4.241338112305854e-05,
|
| 224 |
+
"loss": 0.5828,
|
| 225 |
+
"step": 220
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 7.36,
|
| 229 |
+
"learning_rate": 4.1816009557945046e-05,
|
| 230 |
+
"loss": 0.5658,
|
| 231 |
+
"step": 230
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 7.68,
|
| 235 |
+
"learning_rate": 4.121863799283154e-05,
|
| 236 |
+
"loss": 0.5621,
|
| 237 |
+
"step": 240
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 8.0,
|
| 241 |
+
"learning_rate": 4.062126642771804e-05,
|
| 242 |
+
"loss": 0.5438,
|
| 243 |
+
"step": 250
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 8.0,
|
| 247 |
+
"eval_accuracy": 0.8320180383314544,
|
| 248 |
+
"eval_f1": 0.8293166855099415,
|
| 249 |
+
"eval_loss": 0.48060280084609985,
|
| 250 |
+
"eval_precision": 0.8324876613114235,
|
| 251 |
+
"eval_recall": 0.8320180383314544,
|
| 252 |
+
"eval_runtime": 10.2661,
|
| 253 |
+
"eval_samples_per_second": 172.802,
|
| 254 |
+
"eval_steps_per_second": 1.364,
|
| 255 |
+
"step": 250
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 8.32,
|
| 259 |
+
"learning_rate": 4.002389486260454e-05,
|
| 260 |
+
"loss": 0.5032,
|
| 261 |
+
"step": 260
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 8.64,
|
| 265 |
+
"learning_rate": 3.9426523297491045e-05,
|
| 266 |
+
"loss": 0.5369,
|
| 267 |
+
"step": 270
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 8.96,
|
| 271 |
+
"learning_rate": 3.882915173237754e-05,
|
| 272 |
+
"loss": 0.5455,
|
| 273 |
+
"step": 280
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 8.99,
|
| 277 |
+
"eval_accuracy": 0.8410372040586246,
|
| 278 |
+
"eval_f1": 0.8406080099403899,
|
| 279 |
+
"eval_loss": 0.4780590534210205,
|
| 280 |
+
"eval_precision": 0.8442146002171846,
|
| 281 |
+
"eval_recall": 0.8410372040586246,
|
| 282 |
+
"eval_runtime": 9.9357,
|
| 283 |
+
"eval_samples_per_second": 178.549,
|
| 284 |
+
"eval_steps_per_second": 1.409,
|
| 285 |
+
"step": 281
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 9.28,
|
| 289 |
+
"learning_rate": 3.8231780167264044e-05,
|
| 290 |
+
"loss": 0.5103,
|
| 291 |
+
"step": 290
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 9.6,
|
| 295 |
+
"learning_rate": 3.763440860215054e-05,
|
| 296 |
+
"loss": 0.5276,
|
| 297 |
+
"step": 300
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 9.92,
|
| 301 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 302 |
+
"loss": 0.5002,
|
| 303 |
+
"step": 310
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 9.98,
|
| 307 |
+
"eval_accuracy": 0.8478015783540023,
|
| 308 |
+
"eval_f1": 0.8451845858868778,
|
| 309 |
+
"eval_loss": 0.44031190872192383,
|
| 310 |
+
"eval_precision": 0.8456549868370505,
|
| 311 |
+
"eval_recall": 0.8478015783540023,
|
| 312 |
+
"eval_runtime": 9.9555,
|
| 313 |
+
"eval_samples_per_second": 178.194,
|
| 314 |
+
"eval_steps_per_second": 1.406,
|
| 315 |
+
"step": 312
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 10.24,
|
| 319 |
+
"learning_rate": 3.643966547192354e-05,
|
| 320 |
+
"loss": 0.5065,
|
| 321 |
+
"step": 320
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 10.56,
|
| 325 |
+
"learning_rate": 3.5842293906810036e-05,
|
| 326 |
+
"loss": 0.5299,
|
| 327 |
+
"step": 330
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 10.88,
|
| 331 |
+
"learning_rate": 3.524492234169653e-05,
|
| 332 |
+
"loss": 0.5003,
|
| 333 |
+
"step": 340
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 10.98,
|
| 337 |
+
"eval_accuracy": 0.8151071025930101,
|
| 338 |
+
"eval_f1": 0.8156343828661431,
|
| 339 |
+
"eval_loss": 0.5079108476638794,
|
| 340 |
+
"eval_precision": 0.8355471801083442,
|
| 341 |
+
"eval_recall": 0.8151071025930101,
|
| 342 |
+
"eval_runtime": 9.4315,
|
| 343 |
+
"eval_samples_per_second": 188.093,
|
| 344 |
+
"eval_steps_per_second": 1.484,
|
| 345 |
+
"step": 343
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 11.2,
|
| 349 |
+
"learning_rate": 3.4647550776583035e-05,
|
| 350 |
+
"loss": 0.4944,
|
| 351 |
+
"step": 350
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 11.52,
|
| 355 |
+
"learning_rate": 3.405017921146954e-05,
|
| 356 |
+
"loss": 0.4664,
|
| 357 |
+
"step": 360
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 11.84,
|
| 361 |
+
"learning_rate": 3.3452807646356034e-05,
|
| 362 |
+
"loss": 0.4828,
|
| 363 |
+
"step": 370
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 12.0,
|
| 367 |
+
"eval_accuracy": 0.8190529875986471,
|
| 368 |
+
"eval_f1": 0.8146851277474468,
|
| 369 |
+
"eval_loss": 0.5306578874588013,
|
| 370 |
+
"eval_precision": 0.8196844043471049,
|
| 371 |
+
"eval_recall": 0.8190529875986471,
|
| 372 |
+
"eval_runtime": 9.2903,
|
| 373 |
+
"eval_samples_per_second": 190.951,
|
| 374 |
+
"eval_steps_per_second": 1.507,
|
| 375 |
+
"step": 375
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 12.16,
|
| 379 |
+
"learning_rate": 3.285543608124254e-05,
|
| 380 |
+
"loss": 0.4653,
|
| 381 |
+
"step": 380
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 12.48,
|
| 385 |
+
"learning_rate": 3.2258064516129034e-05,
|
| 386 |
+
"loss": 0.4663,
|
| 387 |
+
"step": 390
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 12.8,
|
| 391 |
+
"learning_rate": 3.1660692951015537e-05,
|
| 392 |
+
"loss": 0.4674,
|
| 393 |
+
"step": 400
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 12.99,
|
| 397 |
+
"eval_accuracy": 0.8444193912063134,
|
| 398 |
+
"eval_f1": 0.8430917605672317,
|
| 399 |
+
"eval_loss": 0.4731869101524353,
|
| 400 |
+
"eval_precision": 0.8449597828117058,
|
| 401 |
+
"eval_recall": 0.8444193912063134,
|
| 402 |
+
"eval_runtime": 9.3676,
|
| 403 |
+
"eval_samples_per_second": 189.377,
|
| 404 |
+
"eval_steps_per_second": 1.495,
|
| 405 |
+
"step": 406
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 13.12,
|
| 409 |
+
"learning_rate": 3.106332138590203e-05,
|
| 410 |
+
"loss": 0.4459,
|
| 411 |
+
"step": 410
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 13.44,
|
| 415 |
+
"learning_rate": 3.046594982078853e-05,
|
| 416 |
+
"loss": 0.4516,
|
| 417 |
+
"step": 420
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 13.76,
|
| 421 |
+
"learning_rate": 2.9868578255675032e-05,
|
| 422 |
+
"loss": 0.4646,
|
| 423 |
+
"step": 430
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 13.98,
|
| 427 |
+
"eval_accuracy": 0.8280721533258174,
|
| 428 |
+
"eval_f1": 0.8250541740714602,
|
| 429 |
+
"eval_loss": 0.49517446756362915,
|
| 430 |
+
"eval_precision": 0.8341535339626841,
|
| 431 |
+
"eval_recall": 0.8280721533258174,
|
| 432 |
+
"eval_runtime": 9.3472,
|
| 433 |
+
"eval_samples_per_second": 189.789,
|
| 434 |
+
"eval_steps_per_second": 1.498,
|
| 435 |
+
"step": 437
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 14.08,
|
| 439 |
+
"learning_rate": 2.9271206690561532e-05,
|
| 440 |
+
"loss": 0.4704,
|
| 441 |
+
"step": 440
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 14.4,
|
| 445 |
+
"learning_rate": 2.8673835125448028e-05,
|
| 446 |
+
"loss": 0.4273,
|
| 447 |
+
"step": 450
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 14.72,
|
| 451 |
+
"learning_rate": 2.807646356033453e-05,
|
| 452 |
+
"loss": 0.4477,
|
| 453 |
+
"step": 460
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 14.98,
|
| 457 |
+
"eval_accuracy": 0.8523111612175873,
|
| 458 |
+
"eval_f1": 0.851424593229574,
|
| 459 |
+
"eval_loss": 0.46072810888290405,
|
| 460 |
+
"eval_precision": 0.8516225149535614,
|
| 461 |
+
"eval_recall": 0.8523111612175873,
|
| 462 |
+
"eval_runtime": 9.3756,
|
| 463 |
+
"eval_samples_per_second": 189.215,
|
| 464 |
+
"eval_steps_per_second": 1.493,
|
| 465 |
+
"step": 468
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 15.04,
|
| 469 |
+
"learning_rate": 2.747909199522103e-05,
|
| 470 |
+
"loss": 0.4123,
|
| 471 |
+
"step": 470
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 15.36,
|
| 475 |
+
"learning_rate": 2.6881720430107527e-05,
|
| 476 |
+
"loss": 0.3969,
|
| 477 |
+
"step": 480
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 15.68,
|
| 481 |
+
"learning_rate": 2.628434886499403e-05,
|
| 482 |
+
"loss": 0.4122,
|
| 483 |
+
"step": 490
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 16.0,
|
| 487 |
+
"learning_rate": 2.5686977299880526e-05,
|
| 488 |
+
"loss": 0.4224,
|
| 489 |
+
"step": 500
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 16.0,
|
| 493 |
+
"eval_accuracy": 0.850620067643743,
|
| 494 |
+
"eval_f1": 0.8494661464143937,
|
| 495 |
+
"eval_loss": 0.45143523812294006,
|
| 496 |
+
"eval_precision": 0.8515937584391022,
|
| 497 |
+
"eval_recall": 0.850620067643743,
|
| 498 |
+
"eval_runtime": 9.3567,
|
| 499 |
+
"eval_samples_per_second": 189.597,
|
| 500 |
+
"eval_steps_per_second": 1.496,
|
| 501 |
+
"step": 500
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 16.32,
|
| 505 |
+
"learning_rate": 2.5089605734767026e-05,
|
| 506 |
+
"loss": 0.3961,
|
| 507 |
+
"step": 510
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 16.64,
|
| 511 |
+
"learning_rate": 2.4492234169653525e-05,
|
| 512 |
+
"loss": 0.4067,
|
| 513 |
+
"step": 520
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 16.96,
|
| 517 |
+
"learning_rate": 2.3894862604540025e-05,
|
| 518 |
+
"loss": 0.3751,
|
| 519 |
+
"step": 530
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 16.99,
|
| 523 |
+
"eval_accuracy": 0.8483652762119503,
|
| 524 |
+
"eval_f1": 0.8471762712292636,
|
| 525 |
+
"eval_loss": 0.4664769172668457,
|
| 526 |
+
"eval_precision": 0.8480191707831453,
|
| 527 |
+
"eval_recall": 0.8483652762119503,
|
| 528 |
+
"eval_runtime": 9.2158,
|
| 529 |
+
"eval_samples_per_second": 192.496,
|
| 530 |
+
"eval_steps_per_second": 1.519,
|
| 531 |
+
"step": 531
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 17.28,
|
| 535 |
+
"learning_rate": 2.3297491039426525e-05,
|
| 536 |
+
"loss": 0.3949,
|
| 537 |
+
"step": 540
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 17.6,
|
| 541 |
+
"learning_rate": 2.270011947431302e-05,
|
| 542 |
+
"loss": 0.4007,
|
| 543 |
+
"step": 550
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 17.92,
|
| 547 |
+
"learning_rate": 2.2102747909199524e-05,
|
| 548 |
+
"loss": 0.3874,
|
| 549 |
+
"step": 560
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 17.98,
|
| 553 |
+
"eval_accuracy": 0.8489289740698985,
|
| 554 |
+
"eval_f1": 0.8476872697009592,
|
| 555 |
+
"eval_loss": 0.4461875259876251,
|
| 556 |
+
"eval_precision": 0.8488536060848715,
|
| 557 |
+
"eval_recall": 0.8489289740698985,
|
| 558 |
+
"eval_runtime": 9.3651,
|
| 559 |
+
"eval_samples_per_second": 189.427,
|
| 560 |
+
"eval_steps_per_second": 1.495,
|
| 561 |
+
"step": 562
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 18.24,
|
| 565 |
+
"learning_rate": 2.1505376344086024e-05,
|
| 566 |
+
"loss": 0.3669,
|
| 567 |
+
"step": 570
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 18.56,
|
| 571 |
+
"learning_rate": 2.0908004778972523e-05,
|
| 572 |
+
"loss": 0.3703,
|
| 573 |
+
"step": 580
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 18.88,
|
| 577 |
+
"learning_rate": 2.031063321385902e-05,
|
| 578 |
+
"loss": 0.3675,
|
| 579 |
+
"step": 590
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 18.98,
|
| 583 |
+
"eval_accuracy": 0.8483652762119503,
|
| 584 |
+
"eval_f1": 0.8471316837014181,
|
| 585 |
+
"eval_loss": 0.46742817759513855,
|
| 586 |
+
"eval_precision": 0.8507897089204829,
|
| 587 |
+
"eval_recall": 0.8483652762119503,
|
| 588 |
+
"eval_runtime": 9.3157,
|
| 589 |
+
"eval_samples_per_second": 190.43,
|
| 590 |
+
"eval_steps_per_second": 1.503,
|
| 591 |
+
"step": 593
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 19.2,
|
| 595 |
+
"learning_rate": 1.9713261648745522e-05,
|
| 596 |
+
"loss": 0.363,
|
| 597 |
+
"step": 600
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 19.52,
|
| 601 |
+
"learning_rate": 1.9115890083632022e-05,
|
| 602 |
+
"loss": 0.3561,
|
| 603 |
+
"step": 610
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 19.84,
|
| 607 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 608 |
+
"loss": 0.3434,
|
| 609 |
+
"step": 620
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 20.0,
|
| 613 |
+
"eval_accuracy": 0.8511837655016911,
|
| 614 |
+
"eval_f1": 0.8462300511726165,
|
| 615 |
+
"eval_loss": 0.4643685519695282,
|
| 616 |
+
"eval_precision": 0.8485763166557468,
|
| 617 |
+
"eval_recall": 0.8511837655016911,
|
| 618 |
+
"eval_runtime": 9.458,
|
| 619 |
+
"eval_samples_per_second": 187.567,
|
| 620 |
+
"eval_steps_per_second": 1.48,
|
| 621 |
+
"step": 625
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 20.16,
|
| 625 |
+
"learning_rate": 1.7921146953405018e-05,
|
| 626 |
+
"loss": 0.3409,
|
| 627 |
+
"step": 630
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 20.48,
|
| 631 |
+
"learning_rate": 1.7323775388291518e-05,
|
| 632 |
+
"loss": 0.3309,
|
| 633 |
+
"step": 640
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 20.8,
|
| 637 |
+
"learning_rate": 1.6726403823178017e-05,
|
| 638 |
+
"loss": 0.3332,
|
| 639 |
+
"step": 650
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 20.99,
|
| 643 |
+
"eval_accuracy": 0.8556933483652762,
|
| 644 |
+
"eval_f1": 0.8525291061586084,
|
| 645 |
+
"eval_loss": 0.47109487652778625,
|
| 646 |
+
"eval_precision": 0.8548396749990268,
|
| 647 |
+
"eval_recall": 0.8556933483652762,
|
| 648 |
+
"eval_runtime": 9.4367,
|
| 649 |
+
"eval_samples_per_second": 187.99,
|
| 650 |
+
"eval_steps_per_second": 1.484,
|
| 651 |
+
"step": 656
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 21.12,
|
| 655 |
+
"learning_rate": 1.6129032258064517e-05,
|
| 656 |
+
"loss": 0.3161,
|
| 657 |
+
"step": 660
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 21.44,
|
| 661 |
+
"learning_rate": 1.5531660692951016e-05,
|
| 662 |
+
"loss": 0.3126,
|
| 663 |
+
"step": 670
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 21.76,
|
| 667 |
+
"learning_rate": 1.4934289127837516e-05,
|
| 668 |
+
"loss": 0.3187,
|
| 669 |
+
"step": 680
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 21.98,
|
| 673 |
+
"eval_accuracy": 0.8534385569334837,
|
| 674 |
+
"eval_f1": 0.8523790763674031,
|
| 675 |
+
"eval_loss": 0.4664561152458191,
|
| 676 |
+
"eval_precision": 0.8539347187356369,
|
| 677 |
+
"eval_recall": 0.8534385569334837,
|
| 678 |
+
"eval_runtime": 9.3613,
|
| 679 |
+
"eval_samples_per_second": 189.504,
|
| 680 |
+
"eval_steps_per_second": 1.496,
|
| 681 |
+
"step": 687
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 22.08,
|
| 685 |
+
"learning_rate": 1.4336917562724014e-05,
|
| 686 |
+
"loss": 0.3295,
|
| 687 |
+
"step": 690
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 22.4,
|
| 691 |
+
"learning_rate": 1.3739545997610515e-05,
|
| 692 |
+
"loss": 0.3064,
|
| 693 |
+
"step": 700
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 22.72,
|
| 697 |
+
"learning_rate": 1.3142174432497015e-05,
|
| 698 |
+
"loss": 0.3039,
|
| 699 |
+
"step": 710
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 22.98,
|
| 703 |
+
"eval_accuracy": 0.8438556933483653,
|
| 704 |
+
"eval_f1": 0.8423406295566305,
|
| 705 |
+
"eval_loss": 0.5015249848365784,
|
| 706 |
+
"eval_precision": 0.8427081666869208,
|
| 707 |
+
"eval_recall": 0.8438556933483653,
|
| 708 |
+
"eval_runtime": 9.3244,
|
| 709 |
+
"eval_samples_per_second": 190.253,
|
| 710 |
+
"eval_steps_per_second": 1.501,
|
| 711 |
+
"step": 718
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 23.04,
|
| 715 |
+
"learning_rate": 1.2544802867383513e-05,
|
| 716 |
+
"loss": 0.3037,
|
| 717 |
+
"step": 720
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 23.36,
|
| 721 |
+
"learning_rate": 1.1947431302270013e-05,
|
| 722 |
+
"loss": 0.2933,
|
| 723 |
+
"step": 730
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 23.68,
|
| 727 |
+
"learning_rate": 1.135005973715651e-05,
|
| 728 |
+
"loss": 0.3083,
|
| 729 |
+
"step": 740
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 24.0,
|
| 733 |
+
"learning_rate": 1.0752688172043012e-05,
|
| 734 |
+
"loss": 0.282,
|
| 735 |
+
"step": 750
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 24.0,
|
| 739 |
+
"eval_accuracy": 0.8562570462232244,
|
| 740 |
+
"eval_f1": 0.8558695619667928,
|
| 741 |
+
"eval_loss": 0.4782754182815552,
|
| 742 |
+
"eval_precision": 0.856302163200596,
|
| 743 |
+
"eval_recall": 0.8562570462232244,
|
| 744 |
+
"eval_runtime": 9.4264,
|
| 745 |
+
"eval_samples_per_second": 188.195,
|
| 746 |
+
"eval_steps_per_second": 1.485,
|
| 747 |
+
"step": 750
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 24.32,
|
| 751 |
+
"learning_rate": 1.015531660692951e-05,
|
| 752 |
+
"loss": 0.2996,
|
| 753 |
+
"step": 760
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 24.64,
|
| 757 |
+
"learning_rate": 9.557945041816011e-06,
|
| 758 |
+
"loss": 0.2778,
|
| 759 |
+
"step": 770
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 24.96,
|
| 763 |
+
"learning_rate": 8.960573476702509e-06,
|
| 764 |
+
"loss": 0.2843,
|
| 765 |
+
"step": 780
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 24.99,
|
| 769 |
+
"eval_accuracy": 0.8534385569334837,
|
| 770 |
+
"eval_f1": 0.8513643676170913,
|
| 771 |
+
"eval_loss": 0.5064074397087097,
|
| 772 |
+
"eval_precision": 0.8518978579098605,
|
| 773 |
+
"eval_recall": 0.8534385569334837,
|
| 774 |
+
"eval_runtime": 9.4519,
|
| 775 |
+
"eval_samples_per_second": 187.687,
|
| 776 |
+
"eval_steps_per_second": 1.481,
|
| 777 |
+
"step": 781
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 25.28,
|
| 781 |
+
"learning_rate": 8.363201911589009e-06,
|
| 782 |
+
"loss": 0.2571,
|
| 783 |
+
"step": 790
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 25.6,
|
| 787 |
+
"learning_rate": 7.765830346475508e-06,
|
| 788 |
+
"loss": 0.271,
|
| 789 |
+
"step": 800
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 25.92,
|
| 793 |
+
"learning_rate": 7.168458781362007e-06,
|
| 794 |
+
"loss": 0.2661,
|
| 795 |
+
"step": 810
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 25.98,
|
| 799 |
+
"eval_accuracy": 0.8483652762119503,
|
| 800 |
+
"eval_f1": 0.8459949962688994,
|
| 801 |
+
"eval_loss": 0.5021128058433533,
|
| 802 |
+
"eval_precision": 0.8476393382479328,
|
| 803 |
+
"eval_recall": 0.8483652762119503,
|
| 804 |
+
"eval_runtime": 9.3566,
|
| 805 |
+
"eval_samples_per_second": 189.598,
|
| 806 |
+
"eval_steps_per_second": 1.496,
|
| 807 |
+
"step": 812
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 26.24,
|
| 811 |
+
"learning_rate": 6.5710872162485075e-06,
|
| 812 |
+
"loss": 0.2817,
|
| 813 |
+
"step": 820
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 26.56,
|
| 817 |
+
"learning_rate": 5.973715651135006e-06,
|
| 818 |
+
"loss": 0.2615,
|
| 819 |
+
"step": 830
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 26.88,
|
| 823 |
+
"learning_rate": 5.376344086021506e-06,
|
| 824 |
+
"loss": 0.2595,
|
| 825 |
+
"step": 840
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 26.98,
|
| 829 |
+
"eval_accuracy": 0.8613303269447576,
|
| 830 |
+
"eval_f1": 0.861465358212238,
|
| 831 |
+
"eval_loss": 0.48520544171333313,
|
| 832 |
+
"eval_precision": 0.8626143442892683,
|
| 833 |
+
"eval_recall": 0.8613303269447576,
|
| 834 |
+
"eval_runtime": 9.328,
|
| 835 |
+
"eval_samples_per_second": 190.181,
|
| 836 |
+
"eval_steps_per_second": 1.501,
|
| 837 |
+
"step": 843
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 27.2,
|
| 841 |
+
"learning_rate": 4.7789725209080055e-06,
|
| 842 |
+
"loss": 0.2545,
|
| 843 |
+
"step": 850
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 27.52,
|
| 847 |
+
"learning_rate": 4.181600955794504e-06,
|
| 848 |
+
"loss": 0.2669,
|
| 849 |
+
"step": 860
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 27.84,
|
| 853 |
+
"learning_rate": 3.5842293906810035e-06,
|
| 854 |
+
"loss": 0.2442,
|
| 855 |
+
"step": 870
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 28.0,
|
| 859 |
+
"eval_accuracy": 0.8568207440811725,
|
| 860 |
+
"eval_f1": 0.8542669512232386,
|
| 861 |
+
"eval_loss": 0.49029698967933655,
|
| 862 |
+
"eval_precision": 0.8546300815174016,
|
| 863 |
+
"eval_recall": 0.8568207440811725,
|
| 864 |
+
"eval_runtime": 9.4608,
|
| 865 |
+
"eval_samples_per_second": 187.51,
|
| 866 |
+
"eval_steps_per_second": 1.48,
|
| 867 |
+
"step": 875
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 28.16,
|
| 871 |
+
"learning_rate": 2.986857825567503e-06,
|
| 872 |
+
"loss": 0.2568,
|
| 873 |
+
"step": 880
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 28.48,
|
| 877 |
+
"learning_rate": 2.3894862604540028e-06,
|
| 878 |
+
"loss": 0.2445,
|
| 879 |
+
"step": 890
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 28.8,
|
| 883 |
+
"learning_rate": 1.7921146953405017e-06,
|
| 884 |
+
"loss": 0.2477,
|
| 885 |
+
"step": 900
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 28.99,
|
| 889 |
+
"eval_accuracy": 0.8585118376550169,
|
| 890 |
+
"eval_f1": 0.8569651539184984,
|
| 891 |
+
"eval_loss": 0.4780934751033783,
|
| 892 |
+
"eval_precision": 0.8569316478704299,
|
| 893 |
+
"eval_recall": 0.8585118376550169,
|
| 894 |
+
"eval_runtime": 9.4954,
|
| 895 |
+
"eval_samples_per_second": 186.827,
|
| 896 |
+
"eval_steps_per_second": 1.474,
|
| 897 |
+
"step": 906
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 29.12,
|
| 901 |
+
"learning_rate": 1.1947431302270014e-06,
|
| 902 |
+
"loss": 0.2435,
|
| 903 |
+
"step": 910
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 29.44,
|
| 907 |
+
"learning_rate": 5.973715651135007e-07,
|
| 908 |
+
"loss": 0.2307,
|
| 909 |
+
"step": 920
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 29.76,
|
| 913 |
+
"learning_rate": 0.0,
|
| 914 |
+
"loss": 0.2437,
|
| 915 |
+
"step": 930
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 29.76,
|
| 919 |
+
"eval_accuracy": 0.8585118376550169,
|
| 920 |
+
"eval_f1": 0.8577007947643565,
|
| 921 |
+
"eval_loss": 0.47721412777900696,
|
| 922 |
+
"eval_precision": 0.8579618397115243,
|
| 923 |
+
"eval_recall": 0.8585118376550169,
|
| 924 |
+
"eval_runtime": 9.6381,
|
| 925 |
+
"eval_samples_per_second": 184.062,
|
| 926 |
+
"eval_steps_per_second": 1.453,
|
| 927 |
+
"step": 930
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 29.76,
|
| 931 |
+
"step": 930,
|
| 932 |
+
"total_flos": 1.2364841575625785e+19,
|
| 933 |
+
"train_loss": 0.49311745294960596,
|
| 934 |
+
"train_runtime": 4214.8321,
|
| 935 |
+
"train_samples_per_second": 113.613,
|
| 936 |
+
"train_steps_per_second": 0.221
|
| 937 |
+
}
|
| 938 |
+
],
|
| 939 |
+
"logging_steps": 10,
|
| 940 |
+
"max_steps": 930,
|
| 941 |
+
"num_input_tokens_seen": 0,
|
| 942 |
+
"num_train_epochs": 30,
|
| 943 |
+
"save_steps": 500,
|
| 944 |
+
"total_flos": 1.2364841575625785e+19,
|
| 945 |
+
"train_batch_size": 128,
|
| 946 |
+
"trial_name": null,
|
| 947 |
+
"trial_params": null
|
| 948 |
+
}
|