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: google/vit-base-patch32-384
|
| 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 |
# vit-base-patch32-384-finetuned-galaxy10-decals
|
| 20 |
|
| 21 |
-
This model is a fine-tuned version of [google/vit-base-patch32-384](https://huggingface.co/google/vit-base-patch32-384) 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: google/vit-base-patch32-384
|
| 4 |
tags:
|
| 5 |
+
- image-classification
|
| 6 |
+
- vision
|
| 7 |
- generated_from_trainer
|
| 8 |
metrics:
|
| 9 |
- accuracy
|
|
|
|
| 20 |
|
| 21 |
# vit-base-patch32-384-finetuned-galaxy10-decals
|
| 22 |
|
| 23 |
+
This model is a fine-tuned version of [google/vit-base-patch32-384](https://huggingface.co/google/vit-base-patch32-384) on the matthieulel/galaxy10_decals dataset.
|
| 24 |
It achieves the following results on the evaluation set:
|
| 25 |
+
- Loss: 0.5542
|
| 26 |
+
- Accuracy: 0.8326
|
| 27 |
+
- Precision: 0.8324
|
| 28 |
+
- Recall: 0.8326
|
| 29 |
+
- F1: 0.8298
|
| 30 |
|
| 31 |
## Model description
|
| 32 |
|
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 29.76,
|
| 3 |
+
"eval_accuracy": 0.8325817361894025,
|
| 4 |
+
"eval_f1": 0.8298383554761921,
|
| 5 |
+
"eval_loss": 0.554213285446167,
|
| 6 |
+
"eval_precision": 0.8324005109556332,
|
| 7 |
+
"eval_recall": 0.8325817361894025,
|
| 8 |
+
"eval_runtime": 18.2503,
|
| 9 |
+
"eval_samples_per_second": 97.204,
|
| 10 |
+
"eval_steps_per_second": 0.767,
|
| 11 |
+
"train_loss": 0.479745574151316,
|
| 12 |
+
"train_runtime": 6462.6814,
|
| 13 |
+
"train_samples_per_second": 74.096,
|
| 14 |
+
"train_steps_per_second": 0.144
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 29.76,
|
| 3 |
+
"eval_accuracy": 0.8325817361894025,
|
| 4 |
+
"eval_f1": 0.8298383554761921,
|
| 5 |
+
"eval_loss": 0.554213285446167,
|
| 6 |
+
"eval_precision": 0.8324005109556332,
|
| 7 |
+
"eval_recall": 0.8325817361894025,
|
| 8 |
+
"eval_runtime": 18.2503,
|
| 9 |
+
"eval_samples_per_second": 97.204,
|
| 10 |
+
"eval_steps_per_second": 0.767
|
| 11 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 29.76,
|
| 3 |
+
"train_loss": 0.479745574151316,
|
| 4 |
+
"train_runtime": 6462.6814,
|
| 5 |
+
"train_samples_per_second": 74.096,
|
| 6 |
+
"train_steps_per_second": 0.144
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,948 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8325817361894025,
|
| 3 |
+
"best_model_checkpoint": "vit-base-patch32-384-finetuned-galaxy10-decals/checkpoint-812",
|
| 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": 1.0752688172043012e-05,
|
| 14 |
+
"loss": 2.3151,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.64,
|
| 19 |
+
"learning_rate": 2.1505376344086024e-05,
|
| 20 |
+
"loss": 2.0745,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.96,
|
| 25 |
+
"learning_rate": 3.2258064516129034e-05,
|
| 26 |
+
"loss": 1.68,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.99,
|
| 31 |
+
"eval_accuracy": 0.5259301014656145,
|
| 32 |
+
"eval_f1": 0.49215625127538787,
|
| 33 |
+
"eval_loss": 1.3834584951400757,
|
| 34 |
+
"eval_precision": 0.501400900398172,
|
| 35 |
+
"eval_recall": 0.5259301014656145,
|
| 36 |
+
"eval_runtime": 17.899,
|
| 37 |
+
"eval_samples_per_second": 99.112,
|
| 38 |
+
"eval_steps_per_second": 0.782,
|
| 39 |
+
"step": 31
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.28,
|
| 43 |
+
"learning_rate": 4.301075268817205e-05,
|
| 44 |
+
"loss": 1.3637,
|
| 45 |
+
"step": 40
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.6,
|
| 49 |
+
"learning_rate": 5.3763440860215054e-05,
|
| 50 |
+
"loss": 1.1117,
|
| 51 |
+
"step": 50
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.92,
|
| 55 |
+
"learning_rate": 6.451612903225807e-05,
|
| 56 |
+
"loss": 0.9395,
|
| 57 |
+
"step": 60
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 1.98,
|
| 61 |
+
"eval_accuracy": 0.7119503945885005,
|
| 62 |
+
"eval_f1": 0.6985631019873411,
|
| 63 |
+
"eval_loss": 0.8286036252975464,
|
| 64 |
+
"eval_precision": 0.7053418589153262,
|
| 65 |
+
"eval_recall": 0.7119503945885005,
|
| 66 |
+
"eval_runtime": 18.079,
|
| 67 |
+
"eval_samples_per_second": 98.125,
|
| 68 |
+
"eval_steps_per_second": 0.774,
|
| 69 |
+
"step": 62
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 2.24,
|
| 73 |
+
"learning_rate": 7.526881720430108e-05,
|
| 74 |
+
"loss": 0.8714,
|
| 75 |
+
"step": 70
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 2.56,
|
| 79 |
+
"learning_rate": 8.60215053763441e-05,
|
| 80 |
+
"loss": 0.8012,
|
| 81 |
+
"step": 80
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 2.88,
|
| 85 |
+
"learning_rate": 9.677419354838711e-05,
|
| 86 |
+
"loss": 0.7814,
|
| 87 |
+
"step": 90
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 2.98,
|
| 91 |
+
"eval_accuracy": 0.7604284103720406,
|
| 92 |
+
"eval_f1": 0.7456344452244981,
|
| 93 |
+
"eval_loss": 0.719430148601532,
|
| 94 |
+
"eval_precision": 0.751495894993987,
|
| 95 |
+
"eval_recall": 0.7604284103720406,
|
| 96 |
+
"eval_runtime": 18.293,
|
| 97 |
+
"eval_samples_per_second": 96.977,
|
| 98 |
+
"eval_steps_per_second": 0.765,
|
| 99 |
+
"step": 93
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 3.2,
|
| 103 |
+
"learning_rate": 9.916367980884111e-05,
|
| 104 |
+
"loss": 0.7608,
|
| 105 |
+
"step": 100
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 3.52,
|
| 109 |
+
"learning_rate": 9.79689366786141e-05,
|
| 110 |
+
"loss": 0.7232,
|
| 111 |
+
"step": 110
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 3.84,
|
| 115 |
+
"learning_rate": 9.677419354838711e-05,
|
| 116 |
+
"loss": 0.7227,
|
| 117 |
+
"step": 120
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 4.0,
|
| 121 |
+
"eval_accuracy": 0.7818489289740699,
|
| 122 |
+
"eval_f1": 0.7742784599684902,
|
| 123 |
+
"eval_loss": 0.6271353363990784,
|
| 124 |
+
"eval_precision": 0.791268453049323,
|
| 125 |
+
"eval_recall": 0.7818489289740699,
|
| 126 |
+
"eval_runtime": 18.0323,
|
| 127 |
+
"eval_samples_per_second": 98.379,
|
| 128 |
+
"eval_steps_per_second": 0.776,
|
| 129 |
+
"step": 125
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 4.16,
|
| 133 |
+
"learning_rate": 9.55794504181601e-05,
|
| 134 |
+
"loss": 0.6582,
|
| 135 |
+
"step": 130
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 4.48,
|
| 139 |
+
"learning_rate": 9.438470728793309e-05,
|
| 140 |
+
"loss": 0.6456,
|
| 141 |
+
"step": 140
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 4.8,
|
| 145 |
+
"learning_rate": 9.31899641577061e-05,
|
| 146 |
+
"loss": 0.6309,
|
| 147 |
+
"step": 150
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 4.99,
|
| 151 |
+
"eval_accuracy": 0.7959413754227734,
|
| 152 |
+
"eval_f1": 0.7952460967893825,
|
| 153 |
+
"eval_loss": 0.5944030284881592,
|
| 154 |
+
"eval_precision": 0.7958694770103485,
|
| 155 |
+
"eval_recall": 0.7959413754227734,
|
| 156 |
+
"eval_runtime": 17.9019,
|
| 157 |
+
"eval_samples_per_second": 99.096,
|
| 158 |
+
"eval_steps_per_second": 0.782,
|
| 159 |
+
"step": 156
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 5.12,
|
| 163 |
+
"learning_rate": 9.199522102747909e-05,
|
| 164 |
+
"loss": 0.6086,
|
| 165 |
+
"step": 160
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 5.44,
|
| 169 |
+
"learning_rate": 9.080047789725208e-05,
|
| 170 |
+
"loss": 0.6106,
|
| 171 |
+
"step": 170
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 5.76,
|
| 175 |
+
"learning_rate": 8.960573476702509e-05,
|
| 176 |
+
"loss": 0.5754,
|
| 177 |
+
"step": 180
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 5.98,
|
| 181 |
+
"eval_accuracy": 0.8111612175873731,
|
| 182 |
+
"eval_f1": 0.8086584642022627,
|
| 183 |
+
"eval_loss": 0.544803261756897,
|
| 184 |
+
"eval_precision": 0.8164540183683634,
|
| 185 |
+
"eval_recall": 0.8111612175873731,
|
| 186 |
+
"eval_runtime": 18.0808,
|
| 187 |
+
"eval_samples_per_second": 98.115,
|
| 188 |
+
"eval_steps_per_second": 0.774,
|
| 189 |
+
"step": 187
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 6.08,
|
| 193 |
+
"learning_rate": 8.84109916367981e-05,
|
| 194 |
+
"loss": 0.5729,
|
| 195 |
+
"step": 190
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 6.4,
|
| 199 |
+
"learning_rate": 8.72162485065711e-05,
|
| 200 |
+
"loss": 0.5472,
|
| 201 |
+
"step": 200
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 6.72,
|
| 205 |
+
"learning_rate": 8.60215053763441e-05,
|
| 206 |
+
"loss": 0.5519,
|
| 207 |
+
"step": 210
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 6.98,
|
| 211 |
+
"eval_accuracy": 0.8010146561443067,
|
| 212 |
+
"eval_f1": 0.7990741204184199,
|
| 213 |
+
"eval_loss": 0.545567512512207,
|
| 214 |
+
"eval_precision": 0.7989922986471379,
|
| 215 |
+
"eval_recall": 0.8010146561443067,
|
| 216 |
+
"eval_runtime": 18.0522,
|
| 217 |
+
"eval_samples_per_second": 98.27,
|
| 218 |
+
"eval_steps_per_second": 0.776,
|
| 219 |
+
"step": 218
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 7.04,
|
| 223 |
+
"learning_rate": 8.482676224611709e-05,
|
| 224 |
+
"loss": 0.5653,
|
| 225 |
+
"step": 220
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 7.36,
|
| 229 |
+
"learning_rate": 8.363201911589009e-05,
|
| 230 |
+
"loss": 0.5341,
|
| 231 |
+
"step": 230
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 7.68,
|
| 235 |
+
"learning_rate": 8.243727598566309e-05,
|
| 236 |
+
"loss": 0.5375,
|
| 237 |
+
"step": 240
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 8.0,
|
| 241 |
+
"learning_rate": 8.124253285543608e-05,
|
| 242 |
+
"loss": 0.5077,
|
| 243 |
+
"step": 250
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 8.0,
|
| 247 |
+
"eval_accuracy": 0.8190529875986471,
|
| 248 |
+
"eval_f1": 0.815964940186291,
|
| 249 |
+
"eval_loss": 0.5458173751831055,
|
| 250 |
+
"eval_precision": 0.8228870165717898,
|
| 251 |
+
"eval_recall": 0.8190529875986471,
|
| 252 |
+
"eval_runtime": 18.3831,
|
| 253 |
+
"eval_samples_per_second": 96.502,
|
| 254 |
+
"eval_steps_per_second": 0.762,
|
| 255 |
+
"step": 250
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 8.32,
|
| 259 |
+
"learning_rate": 8.004778972520908e-05,
|
| 260 |
+
"loss": 0.4912,
|
| 261 |
+
"step": 260
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 8.64,
|
| 265 |
+
"learning_rate": 7.885304659498209e-05,
|
| 266 |
+
"loss": 0.5177,
|
| 267 |
+
"step": 270
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 8.96,
|
| 271 |
+
"learning_rate": 7.765830346475508e-05,
|
| 272 |
+
"loss": 0.5086,
|
| 273 |
+
"step": 280
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 8.99,
|
| 277 |
+
"eval_accuracy": 0.8173618940248027,
|
| 278 |
+
"eval_f1": 0.8146009944447511,
|
| 279 |
+
"eval_loss": 0.5325806736946106,
|
| 280 |
+
"eval_precision": 0.8180841714209635,
|
| 281 |
+
"eval_recall": 0.8173618940248027,
|
| 282 |
+
"eval_runtime": 18.15,
|
| 283 |
+
"eval_samples_per_second": 97.741,
|
| 284 |
+
"eval_steps_per_second": 0.771,
|
| 285 |
+
"step": 281
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 9.28,
|
| 289 |
+
"learning_rate": 7.646356033452809e-05,
|
| 290 |
+
"loss": 0.4726,
|
| 291 |
+
"step": 290
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 9.6,
|
| 295 |
+
"learning_rate": 7.526881720430108e-05,
|
| 296 |
+
"loss": 0.4873,
|
| 297 |
+
"step": 300
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 9.92,
|
| 301 |
+
"learning_rate": 7.407407407407407e-05,
|
| 302 |
+
"loss": 0.455,
|
| 303 |
+
"step": 310
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 9.98,
|
| 307 |
+
"eval_accuracy": 0.8173618940248027,
|
| 308 |
+
"eval_f1": 0.8142694911819406,
|
| 309 |
+
"eval_loss": 0.53792405128479,
|
| 310 |
+
"eval_precision": 0.8179232436884962,
|
| 311 |
+
"eval_recall": 0.8173618940248027,
|
| 312 |
+
"eval_runtime": 18.1012,
|
| 313 |
+
"eval_samples_per_second": 98.004,
|
| 314 |
+
"eval_steps_per_second": 0.773,
|
| 315 |
+
"step": 312
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 10.24,
|
| 319 |
+
"learning_rate": 7.287933094384708e-05,
|
| 320 |
+
"loss": 0.4619,
|
| 321 |
+
"step": 320
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 10.56,
|
| 325 |
+
"learning_rate": 7.168458781362007e-05,
|
| 326 |
+
"loss": 0.4599,
|
| 327 |
+
"step": 330
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 10.88,
|
| 331 |
+
"learning_rate": 7.048984468339306e-05,
|
| 332 |
+
"loss": 0.4532,
|
| 333 |
+
"step": 340
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 10.98,
|
| 337 |
+
"eval_accuracy": 0.8246899661781285,
|
| 338 |
+
"eval_f1": 0.822479983441347,
|
| 339 |
+
"eval_loss": 0.5238922834396362,
|
| 340 |
+
"eval_precision": 0.8238059840177373,
|
| 341 |
+
"eval_recall": 0.8246899661781285,
|
| 342 |
+
"eval_runtime": 18.2898,
|
| 343 |
+
"eval_samples_per_second": 96.994,
|
| 344 |
+
"eval_steps_per_second": 0.765,
|
| 345 |
+
"step": 343
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 11.2,
|
| 349 |
+
"learning_rate": 6.929510155316607e-05,
|
| 350 |
+
"loss": 0.4298,
|
| 351 |
+
"step": 350
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 11.52,
|
| 355 |
+
"learning_rate": 6.810035842293908e-05,
|
| 356 |
+
"loss": 0.4163,
|
| 357 |
+
"step": 360
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 11.84,
|
| 361 |
+
"learning_rate": 6.690561529271207e-05,
|
| 362 |
+
"loss": 0.4311,
|
| 363 |
+
"step": 370
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 12.0,
|
| 367 |
+
"eval_accuracy": 0.8201803833145435,
|
| 368 |
+
"eval_f1": 0.8168990693763513,
|
| 369 |
+
"eval_loss": 0.5290399789810181,
|
| 370 |
+
"eval_precision": 0.8197152495757855,
|
| 371 |
+
"eval_recall": 0.8201803833145435,
|
| 372 |
+
"eval_runtime": 18.0257,
|
| 373 |
+
"eval_samples_per_second": 98.415,
|
| 374 |
+
"eval_steps_per_second": 0.777,
|
| 375 |
+
"step": 375
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 12.16,
|
| 379 |
+
"learning_rate": 6.571087216248507e-05,
|
| 380 |
+
"loss": 0.4122,
|
| 381 |
+
"step": 380
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 12.48,
|
| 385 |
+
"learning_rate": 6.451612903225807e-05,
|
| 386 |
+
"loss": 0.4083,
|
| 387 |
+
"step": 390
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 12.8,
|
| 391 |
+
"learning_rate": 6.332138590203107e-05,
|
| 392 |
+
"loss": 0.4399,
|
| 393 |
+
"step": 400
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 12.99,
|
| 397 |
+
"eval_accuracy": 0.8235625704622322,
|
| 398 |
+
"eval_f1": 0.8213010857091045,
|
| 399 |
+
"eval_loss": 0.5354549288749695,
|
| 400 |
+
"eval_precision": 0.8269184264744502,
|
| 401 |
+
"eval_recall": 0.8235625704622322,
|
| 402 |
+
"eval_runtime": 18.3287,
|
| 403 |
+
"eval_samples_per_second": 96.788,
|
| 404 |
+
"eval_steps_per_second": 0.764,
|
| 405 |
+
"step": 406
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 13.12,
|
| 409 |
+
"learning_rate": 6.212664277180407e-05,
|
| 410 |
+
"loss": 0.4211,
|
| 411 |
+
"step": 410
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 13.44,
|
| 415 |
+
"learning_rate": 6.093189964157706e-05,
|
| 416 |
+
"loss": 0.4011,
|
| 417 |
+
"step": 420
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 13.76,
|
| 421 |
+
"learning_rate": 5.9737156511350064e-05,
|
| 422 |
+
"loss": 0.4026,
|
| 423 |
+
"step": 430
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 13.98,
|
| 427 |
+
"eval_accuracy": 0.8303269447576099,
|
| 428 |
+
"eval_f1": 0.8268182891863524,
|
| 429 |
+
"eval_loss": 0.513204038143158,
|
| 430 |
+
"eval_precision": 0.8288124520696739,
|
| 431 |
+
"eval_recall": 0.8303269447576099,
|
| 432 |
+
"eval_runtime": 18.0895,
|
| 433 |
+
"eval_samples_per_second": 98.068,
|
| 434 |
+
"eval_steps_per_second": 0.774,
|
| 435 |
+
"step": 437
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 14.08,
|
| 439 |
+
"learning_rate": 5.8542413381123063e-05,
|
| 440 |
+
"loss": 0.3989,
|
| 441 |
+
"step": 440
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 14.4,
|
| 445 |
+
"learning_rate": 5.7347670250896056e-05,
|
| 446 |
+
"loss": 0.3631,
|
| 447 |
+
"step": 450
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 14.72,
|
| 451 |
+
"learning_rate": 5.615292712066906e-05,
|
| 452 |
+
"loss": 0.3964,
|
| 453 |
+
"step": 460
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 14.98,
|
| 457 |
+
"eval_accuracy": 0.826944757609921,
|
| 458 |
+
"eval_f1": 0.8247369346585104,
|
| 459 |
+
"eval_loss": 0.5100884437561035,
|
| 460 |
+
"eval_precision": 0.8290079065894101,
|
| 461 |
+
"eval_recall": 0.826944757609921,
|
| 462 |
+
"eval_runtime": 18.2782,
|
| 463 |
+
"eval_samples_per_second": 97.055,
|
| 464 |
+
"eval_steps_per_second": 0.766,
|
| 465 |
+
"step": 468
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 15.04,
|
| 469 |
+
"learning_rate": 5.495818399044206e-05,
|
| 470 |
+
"loss": 0.3751,
|
| 471 |
+
"step": 470
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 15.36,
|
| 475 |
+
"learning_rate": 5.3763440860215054e-05,
|
| 476 |
+
"loss": 0.3662,
|
| 477 |
+
"step": 480
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 15.68,
|
| 481 |
+
"learning_rate": 5.256869772998806e-05,
|
| 482 |
+
"loss": 0.3574,
|
| 483 |
+
"step": 490
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 16.0,
|
| 487 |
+
"learning_rate": 5.137395459976105e-05,
|
| 488 |
+
"loss": 0.3649,
|
| 489 |
+
"step": 500
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 16.0,
|
| 493 |
+
"eval_accuracy": 0.8252536640360767,
|
| 494 |
+
"eval_f1": 0.8221623485790522,
|
| 495 |
+
"eval_loss": 0.5295505523681641,
|
| 496 |
+
"eval_precision": 0.8241726390887584,
|
| 497 |
+
"eval_recall": 0.8252536640360767,
|
| 498 |
+
"eval_runtime": 18.3547,
|
| 499 |
+
"eval_samples_per_second": 96.651,
|
| 500 |
+
"eval_steps_per_second": 0.763,
|
| 501 |
+
"step": 500
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 16.32,
|
| 505 |
+
"learning_rate": 5.017921146953405e-05,
|
| 506 |
+
"loss": 0.3418,
|
| 507 |
+
"step": 510
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 16.64,
|
| 511 |
+
"learning_rate": 4.898446833930705e-05,
|
| 512 |
+
"loss": 0.369,
|
| 513 |
+
"step": 520
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 16.96,
|
| 517 |
+
"learning_rate": 4.778972520908005e-05,
|
| 518 |
+
"loss": 0.3353,
|
| 519 |
+
"step": 530
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 16.99,
|
| 523 |
+
"eval_accuracy": 0.8235625704622322,
|
| 524 |
+
"eval_f1": 0.8197713332912925,
|
| 525 |
+
"eval_loss": 0.5319215059280396,
|
| 526 |
+
"eval_precision": 0.8211832869182611,
|
| 527 |
+
"eval_recall": 0.8235625704622322,
|
| 528 |
+
"eval_runtime": 17.9965,
|
| 529 |
+
"eval_samples_per_second": 98.575,
|
| 530 |
+
"eval_steps_per_second": 0.778,
|
| 531 |
+
"step": 531
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 17.28,
|
| 535 |
+
"learning_rate": 4.659498207885305e-05,
|
| 536 |
+
"loss": 0.3414,
|
| 537 |
+
"step": 540
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 17.6,
|
| 541 |
+
"learning_rate": 4.540023894862604e-05,
|
| 542 |
+
"loss": 0.3582,
|
| 543 |
+
"step": 550
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 17.92,
|
| 547 |
+
"learning_rate": 4.420549581839905e-05,
|
| 548 |
+
"loss": 0.3372,
|
| 549 |
+
"step": 560
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 17.98,
|
| 553 |
+
"eval_accuracy": 0.8303269447576099,
|
| 554 |
+
"eval_f1": 0.8300139801870771,
|
| 555 |
+
"eval_loss": 0.5202580690383911,
|
| 556 |
+
"eval_precision": 0.8314798699201768,
|
| 557 |
+
"eval_recall": 0.8303269447576099,
|
| 558 |
+
"eval_runtime": 18.027,
|
| 559 |
+
"eval_samples_per_second": 98.408,
|
| 560 |
+
"eval_steps_per_second": 0.777,
|
| 561 |
+
"step": 562
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 18.24,
|
| 565 |
+
"learning_rate": 4.301075268817205e-05,
|
| 566 |
+
"loss": 0.3314,
|
| 567 |
+
"step": 570
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 18.56,
|
| 571 |
+
"learning_rate": 4.1816009557945046e-05,
|
| 572 |
+
"loss": 0.3092,
|
| 573 |
+
"step": 580
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 18.88,
|
| 577 |
+
"learning_rate": 4.062126642771804e-05,
|
| 578 |
+
"loss": 0.3281,
|
| 579 |
+
"step": 590
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 18.98,
|
| 583 |
+
"eval_accuracy": 0.8314543404735062,
|
| 584 |
+
"eval_f1": 0.8289212400177308,
|
| 585 |
+
"eval_loss": 0.5428072214126587,
|
| 586 |
+
"eval_precision": 0.8319340341603766,
|
| 587 |
+
"eval_recall": 0.8314543404735062,
|
| 588 |
+
"eval_runtime": 18.3008,
|
| 589 |
+
"eval_samples_per_second": 96.936,
|
| 590 |
+
"eval_steps_per_second": 0.765,
|
| 591 |
+
"step": 593
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 19.2,
|
| 595 |
+
"learning_rate": 3.9426523297491045e-05,
|
| 596 |
+
"loss": 0.3141,
|
| 597 |
+
"step": 600
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 19.52,
|
| 601 |
+
"learning_rate": 3.8231780167264044e-05,
|
| 602 |
+
"loss": 0.3193,
|
| 603 |
+
"step": 610
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 19.84,
|
| 607 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 608 |
+
"loss": 0.3152,
|
| 609 |
+
"step": 620
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 20.0,
|
| 613 |
+
"eval_accuracy": 0.826381059751973,
|
| 614 |
+
"eval_f1": 0.8261945773403931,
|
| 615 |
+
"eval_loss": 0.5452939867973328,
|
| 616 |
+
"eval_precision": 0.8283056369477921,
|
| 617 |
+
"eval_recall": 0.826381059751973,
|
| 618 |
+
"eval_runtime": 18.0828,
|
| 619 |
+
"eval_samples_per_second": 98.104,
|
| 620 |
+
"eval_steps_per_second": 0.774,
|
| 621 |
+
"step": 625
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 20.16,
|
| 625 |
+
"learning_rate": 3.5842293906810036e-05,
|
| 626 |
+
"loss": 0.3071,
|
| 627 |
+
"step": 630
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 20.48,
|
| 631 |
+
"learning_rate": 3.4647550776583035e-05,
|
| 632 |
+
"loss": 0.2964,
|
| 633 |
+
"step": 640
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 20.8,
|
| 637 |
+
"learning_rate": 3.3452807646356034e-05,
|
| 638 |
+
"loss": 0.3016,
|
| 639 |
+
"step": 650
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 20.99,
|
| 643 |
+
"eval_accuracy": 0.822435174746336,
|
| 644 |
+
"eval_f1": 0.8192218316685719,
|
| 645 |
+
"eval_loss": 0.5463992953300476,
|
| 646 |
+
"eval_precision": 0.8252246738496987,
|
| 647 |
+
"eval_recall": 0.822435174746336,
|
| 648 |
+
"eval_runtime": 18.0457,
|
| 649 |
+
"eval_samples_per_second": 98.306,
|
| 650 |
+
"eval_steps_per_second": 0.776,
|
| 651 |
+
"step": 656
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 21.12,
|
| 655 |
+
"learning_rate": 3.2258064516129034e-05,
|
| 656 |
+
"loss": 0.2794,
|
| 657 |
+
"step": 660
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 21.44,
|
| 661 |
+
"learning_rate": 3.106332138590203e-05,
|
| 662 |
+
"loss": 0.2918,
|
| 663 |
+
"step": 670
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 21.76,
|
| 667 |
+
"learning_rate": 2.9868578255675032e-05,
|
| 668 |
+
"loss": 0.2826,
|
| 669 |
+
"step": 680
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 21.98,
|
| 673 |
+
"eval_accuracy": 0.8241262683201804,
|
| 674 |
+
"eval_f1": 0.8213136602631909,
|
| 675 |
+
"eval_loss": 0.5472640991210938,
|
| 676 |
+
"eval_precision": 0.821406561903107,
|
| 677 |
+
"eval_recall": 0.8241262683201804,
|
| 678 |
+
"eval_runtime": 18.0065,
|
| 679 |
+
"eval_samples_per_second": 98.52,
|
| 680 |
+
"eval_steps_per_second": 0.777,
|
| 681 |
+
"step": 687
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 22.08,
|
| 685 |
+
"learning_rate": 2.8673835125448028e-05,
|
| 686 |
+
"loss": 0.2956,
|
| 687 |
+
"step": 690
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 22.4,
|
| 691 |
+
"learning_rate": 2.747909199522103e-05,
|
| 692 |
+
"loss": 0.2769,
|
| 693 |
+
"step": 700
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 22.72,
|
| 697 |
+
"learning_rate": 2.628434886499403e-05,
|
| 698 |
+
"loss": 0.2832,
|
| 699 |
+
"step": 710
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 22.98,
|
| 703 |
+
"eval_accuracy": 0.8275084554678692,
|
| 704 |
+
"eval_f1": 0.825541517713907,
|
| 705 |
+
"eval_loss": 0.5596175789833069,
|
| 706 |
+
"eval_precision": 0.8280844880930238,
|
| 707 |
+
"eval_recall": 0.8275084554678692,
|
| 708 |
+
"eval_runtime": 17.8695,
|
| 709 |
+
"eval_samples_per_second": 99.275,
|
| 710 |
+
"eval_steps_per_second": 0.783,
|
| 711 |
+
"step": 718
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 23.04,
|
| 715 |
+
"learning_rate": 2.5089605734767026e-05,
|
| 716 |
+
"loss": 0.2766,
|
| 717 |
+
"step": 720
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 23.36,
|
| 721 |
+
"learning_rate": 2.3894862604540025e-05,
|
| 722 |
+
"loss": 0.2753,
|
| 723 |
+
"step": 730
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 23.68,
|
| 727 |
+
"learning_rate": 2.270011947431302e-05,
|
| 728 |
+
"loss": 0.2794,
|
| 729 |
+
"step": 740
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 24.0,
|
| 733 |
+
"learning_rate": 2.1505376344086024e-05,
|
| 734 |
+
"loss": 0.2547,
|
| 735 |
+
"step": 750
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 24.0,
|
| 739 |
+
"eval_accuracy": 0.8246899661781285,
|
| 740 |
+
"eval_f1": 0.8243264512967534,
|
| 741 |
+
"eval_loss": 0.5767827033996582,
|
| 742 |
+
"eval_precision": 0.8260107392359419,
|
| 743 |
+
"eval_recall": 0.8246899661781285,
|
| 744 |
+
"eval_runtime": 18.3289,
|
| 745 |
+
"eval_samples_per_second": 96.787,
|
| 746 |
+
"eval_steps_per_second": 0.764,
|
| 747 |
+
"step": 750
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 24.32,
|
| 751 |
+
"learning_rate": 2.031063321385902e-05,
|
| 752 |
+
"loss": 0.2797,
|
| 753 |
+
"step": 760
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 24.64,
|
| 757 |
+
"learning_rate": 1.9115890083632022e-05,
|
| 758 |
+
"loss": 0.2624,
|
| 759 |
+
"step": 770
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 24.96,
|
| 763 |
+
"learning_rate": 1.7921146953405018e-05,
|
| 764 |
+
"loss": 0.2682,
|
| 765 |
+
"step": 780
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 24.99,
|
| 769 |
+
"eval_accuracy": 0.8229988726042841,
|
| 770 |
+
"eval_f1": 0.822594726363454,
|
| 771 |
+
"eval_loss": 0.5693235993385315,
|
| 772 |
+
"eval_precision": 0.8244008835278677,
|
| 773 |
+
"eval_recall": 0.8229988726042841,
|
| 774 |
+
"eval_runtime": 18.2972,
|
| 775 |
+
"eval_samples_per_second": 96.955,
|
| 776 |
+
"eval_steps_per_second": 0.765,
|
| 777 |
+
"step": 781
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 25.28,
|
| 781 |
+
"learning_rate": 1.6726403823178017e-05,
|
| 782 |
+
"loss": 0.2501,
|
| 783 |
+
"step": 790
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 25.6,
|
| 787 |
+
"learning_rate": 1.5531660692951016e-05,
|
| 788 |
+
"loss": 0.2588,
|
| 789 |
+
"step": 800
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 25.92,
|
| 793 |
+
"learning_rate": 1.4336917562724014e-05,
|
| 794 |
+
"loss": 0.245,
|
| 795 |
+
"step": 810
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 25.98,
|
| 799 |
+
"eval_accuracy": 0.8325817361894025,
|
| 800 |
+
"eval_f1": 0.8298383554761921,
|
| 801 |
+
"eval_loss": 0.554213285446167,
|
| 802 |
+
"eval_precision": 0.8324005109556332,
|
| 803 |
+
"eval_recall": 0.8325817361894025,
|
| 804 |
+
"eval_runtime": 17.8826,
|
| 805 |
+
"eval_samples_per_second": 99.202,
|
| 806 |
+
"eval_steps_per_second": 0.783,
|
| 807 |
+
"step": 812
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 26.24,
|
| 811 |
+
"learning_rate": 1.3142174432497015e-05,
|
| 812 |
+
"loss": 0.2577,
|
| 813 |
+
"step": 820
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 26.56,
|
| 817 |
+
"learning_rate": 1.1947431302270013e-05,
|
| 818 |
+
"loss": 0.2492,
|
| 819 |
+
"step": 830
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 26.88,
|
| 823 |
+
"learning_rate": 1.0752688172043012e-05,
|
| 824 |
+
"loss": 0.2575,
|
| 825 |
+
"step": 840
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 26.98,
|
| 829 |
+
"eval_accuracy": 0.8241262683201804,
|
| 830 |
+
"eval_f1": 0.8233634949265476,
|
| 831 |
+
"eval_loss": 0.5664796233177185,
|
| 832 |
+
"eval_precision": 0.8254373119279667,
|
| 833 |
+
"eval_recall": 0.8241262683201804,
|
| 834 |
+
"eval_runtime": 18.5085,
|
| 835 |
+
"eval_samples_per_second": 95.848,
|
| 836 |
+
"eval_steps_per_second": 0.756,
|
| 837 |
+
"step": 843
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 27.2,
|
| 841 |
+
"learning_rate": 9.557945041816011e-06,
|
| 842 |
+
"loss": 0.2521,
|
| 843 |
+
"step": 850
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 27.52,
|
| 847 |
+
"learning_rate": 8.363201911589009e-06,
|
| 848 |
+
"loss": 0.2606,
|
| 849 |
+
"step": 860
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 27.84,
|
| 853 |
+
"learning_rate": 7.168458781362007e-06,
|
| 854 |
+
"loss": 0.2386,
|
| 855 |
+
"step": 870
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 28.0,
|
| 859 |
+
"eval_accuracy": 0.830890642615558,
|
| 860 |
+
"eval_f1": 0.8292502821100518,
|
| 861 |
+
"eval_loss": 0.5716087818145752,
|
| 862 |
+
"eval_precision": 0.8314015784940263,
|
| 863 |
+
"eval_recall": 0.830890642615558,
|
| 864 |
+
"eval_runtime": 17.951,
|
| 865 |
+
"eval_samples_per_second": 98.825,
|
| 866 |
+
"eval_steps_per_second": 0.78,
|
| 867 |
+
"step": 875
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 28.16,
|
| 871 |
+
"learning_rate": 5.973715651135006e-06,
|
| 872 |
+
"loss": 0.2542,
|
| 873 |
+
"step": 880
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 28.48,
|
| 877 |
+
"learning_rate": 4.7789725209080055e-06,
|
| 878 |
+
"loss": 0.2358,
|
| 879 |
+
"step": 890
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 28.8,
|
| 883 |
+
"learning_rate": 3.5842293906810035e-06,
|
| 884 |
+
"loss": 0.2452,
|
| 885 |
+
"step": 900
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 28.99,
|
| 889 |
+
"eval_accuracy": 0.8303269447576099,
|
| 890 |
+
"eval_f1": 0.8279394042577151,
|
| 891 |
+
"eval_loss": 0.5659200549125671,
|
| 892 |
+
"eval_precision": 0.8294645935465704,
|
| 893 |
+
"eval_recall": 0.8303269447576099,
|
| 894 |
+
"eval_runtime": 17.9885,
|
| 895 |
+
"eval_samples_per_second": 98.619,
|
| 896 |
+
"eval_steps_per_second": 0.778,
|
| 897 |
+
"step": 906
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 29.12,
|
| 901 |
+
"learning_rate": 2.3894862604540028e-06,
|
| 902 |
+
"loss": 0.2507,
|
| 903 |
+
"step": 910
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 29.44,
|
| 907 |
+
"learning_rate": 1.1947431302270014e-06,
|
| 908 |
+
"loss": 0.2278,
|
| 909 |
+
"step": 920
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 29.76,
|
| 913 |
+
"learning_rate": 0.0,
|
| 914 |
+
"loss": 0.2394,
|
| 915 |
+
"step": 930
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 29.76,
|
| 919 |
+
"eval_accuracy": 0.8314543404735062,
|
| 920 |
+
"eval_f1": 0.8294440024756536,
|
| 921 |
+
"eval_loss": 0.5673945546150208,
|
| 922 |
+
"eval_precision": 0.8313035100192742,
|
| 923 |
+
"eval_recall": 0.8314543404735062,
|
| 924 |
+
"eval_runtime": 17.9035,
|
| 925 |
+
"eval_samples_per_second": 99.087,
|
| 926 |
+
"eval_steps_per_second": 0.782,
|
| 927 |
+
"step": 930
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 29.76,
|
| 931 |
+
"step": 930,
|
| 932 |
+
"total_flos": 1.103742338178625e+20,
|
| 933 |
+
"train_loss": 0.479745574151316,
|
| 934 |
+
"train_runtime": 6462.6814,
|
| 935 |
+
"train_samples_per_second": 74.096,
|
| 936 |
+
"train_steps_per_second": 0.144
|
| 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": 1.103742338178625e+20,
|
| 945 |
+
"train_batch_size": 128,
|
| 946 |
+
"trial_name": null,
|
| 947 |
+
"trial_params": null
|
| 948 |
+
}
|