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-base-imagenet1k-1-layer
|
| 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-base-imagenet1k-1-layer-head-finetuned-galaxy_mnist
|
| 20 |
|
| 21 |
-
This model is a fine-tuned version of [facebook/dinov2-base-imagenet1k-1-layer](https://huggingface.co/facebook/dinov2-base-imagenet1k-1-layer) 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-base-imagenet1k-1-layer
|
| 4 |
tags:
|
| 5 |
+
- image-classification
|
| 6 |
+
- vision
|
| 7 |
- generated_from_trainer
|
| 8 |
metrics:
|
| 9 |
- accuracy
|
|
|
|
| 20 |
|
| 21 |
# dinov2-base-imagenet1k-1-layer-head-finetuned-galaxy_mnist
|
| 22 |
|
| 23 |
+
This model is a fine-tuned version of [facebook/dinov2-base-imagenet1k-1-layer](https://huggingface.co/facebook/dinov2-base-imagenet1k-1-layer) on the matthieulel/galaxy_mnist dataset.
|
| 24 |
It achieves the following results on the evaluation set:
|
| 25 |
+
- Loss: 0.4438
|
| 26 |
+
- Accuracy: 0.8385
|
| 27 |
+
- Precision: 0.8388
|
| 28 |
+
- Recall: 0.8385
|
| 29 |
+
- F1: 0.8386
|
| 30 |
|
| 31 |
## Model description
|
| 32 |
|
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 29.76,
|
| 3 |
+
"eval_accuracy": 0.8385,
|
| 4 |
+
"eval_f1": 0.8385912865364268,
|
| 5 |
+
"eval_loss": 0.4437757730484009,
|
| 6 |
+
"eval_precision": 0.8387790249591575,
|
| 7 |
+
"eval_recall": 0.8385,
|
| 8 |
+
"eval_runtime": 15.7985,
|
| 9 |
+
"eval_samples_per_second": 126.594,
|
| 10 |
+
"eval_steps_per_second": 2.026,
|
| 11 |
+
"train_loss": 0.5888608142893802,
|
| 12 |
+
"train_runtime": 2857.7767,
|
| 13 |
+
"train_samples_per_second": 83.981,
|
| 14 |
+
"train_steps_per_second": 0.325
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 29.76,
|
| 3 |
+
"eval_accuracy": 0.8385,
|
| 4 |
+
"eval_f1": 0.8385912865364268,
|
| 5 |
+
"eval_loss": 0.4437757730484009,
|
| 6 |
+
"eval_precision": 0.8387790249591575,
|
| 7 |
+
"eval_recall": 0.8385,
|
| 8 |
+
"eval_runtime": 15.7985,
|
| 9 |
+
"eval_samples_per_second": 126.594,
|
| 10 |
+
"eval_steps_per_second": 2.026
|
| 11 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 29.76,
|
| 3 |
+
"train_loss": 0.5888608142893802,
|
| 4 |
+
"train_runtime": 2857.7767,
|
| 5 |
+
"train_samples_per_second": 83.981,
|
| 6 |
+
"train_steps_per_second": 0.325
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,948 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8385,
|
| 3 |
+
"best_model_checkpoint": "dinov2-base-imagenet1k-1-layer-head-finetuned-galaxy_mnist/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": 1.8343,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.64,
|
| 19 |
+
"learning_rate": 2.1505376344086024e-05,
|
| 20 |
+
"loss": 1.7312,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.96,
|
| 25 |
+
"learning_rate": 3.2258064516129034e-05,
|
| 26 |
+
"loss": 1.5682,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.99,
|
| 31 |
+
"eval_accuracy": 0.279,
|
| 32 |
+
"eval_f1": 0.24470529579802525,
|
| 33 |
+
"eval_loss": 1.4743605852127075,
|
| 34 |
+
"eval_precision": 0.35184770041538516,
|
| 35 |
+
"eval_recall": 0.279,
|
| 36 |
+
"eval_runtime": 16.0668,
|
| 37 |
+
"eval_samples_per_second": 124.48,
|
| 38 |
+
"eval_steps_per_second": 1.992,
|
| 39 |
+
"step": 31
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.28,
|
| 43 |
+
"learning_rate": 4.301075268817205e-05,
|
| 44 |
+
"loss": 1.4498,
|
| 45 |
+
"step": 40
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.6,
|
| 49 |
+
"learning_rate": 5.3763440860215054e-05,
|
| 50 |
+
"loss": 1.3215,
|
| 51 |
+
"step": 50
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.92,
|
| 55 |
+
"learning_rate": 6.451612903225807e-05,
|
| 56 |
+
"loss": 1.1895,
|
| 57 |
+
"step": 60
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 1.98,
|
| 61 |
+
"eval_accuracy": 0.5175,
|
| 62 |
+
"eval_f1": 0.5207609763368981,
|
| 63 |
+
"eval_loss": 1.1500117778778076,
|
| 64 |
+
"eval_precision": 0.5367425193081468,
|
| 65 |
+
"eval_recall": 0.5175,
|
| 66 |
+
"eval_runtime": 17.407,
|
| 67 |
+
"eval_samples_per_second": 114.896,
|
| 68 |
+
"eval_steps_per_second": 1.838,
|
| 69 |
+
"step": 62
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 2.24,
|
| 73 |
+
"learning_rate": 7.526881720430108e-05,
|
| 74 |
+
"loss": 1.0838,
|
| 75 |
+
"step": 70
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 2.56,
|
| 79 |
+
"learning_rate": 8.60215053763441e-05,
|
| 80 |
+
"loss": 0.9978,
|
| 81 |
+
"step": 80
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 2.88,
|
| 85 |
+
"learning_rate": 9.677419354838711e-05,
|
| 86 |
+
"loss": 0.8876,
|
| 87 |
+
"step": 90
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 2.98,
|
| 91 |
+
"eval_accuracy": 0.673,
|
| 92 |
+
"eval_f1": 0.6691965326550267,
|
| 93 |
+
"eval_loss": 0.8869444727897644,
|
| 94 |
+
"eval_precision": 0.6822449196932835,
|
| 95 |
+
"eval_recall": 0.673,
|
| 96 |
+
"eval_runtime": 17.5001,
|
| 97 |
+
"eval_samples_per_second": 114.285,
|
| 98 |
+
"eval_steps_per_second": 1.829,
|
| 99 |
+
"step": 93
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 3.2,
|
| 103 |
+
"learning_rate": 9.916367980884111e-05,
|
| 104 |
+
"loss": 0.8361,
|
| 105 |
+
"step": 100
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 3.52,
|
| 109 |
+
"learning_rate": 9.79689366786141e-05,
|
| 110 |
+
"loss": 0.7622,
|
| 111 |
+
"step": 110
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 3.84,
|
| 115 |
+
"learning_rate": 9.677419354838711e-05,
|
| 116 |
+
"loss": 0.7366,
|
| 117 |
+
"step": 120
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 4.0,
|
| 121 |
+
"eval_accuracy": 0.744,
|
| 122 |
+
"eval_f1": 0.7433145600454458,
|
| 123 |
+
"eval_loss": 0.7267060875892639,
|
| 124 |
+
"eval_precision": 0.7471531906348257,
|
| 125 |
+
"eval_recall": 0.744,
|
| 126 |
+
"eval_runtime": 17.2072,
|
| 127 |
+
"eval_samples_per_second": 116.231,
|
| 128 |
+
"eval_steps_per_second": 1.86,
|
| 129 |
+
"step": 125
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 4.16,
|
| 133 |
+
"learning_rate": 9.55794504181601e-05,
|
| 134 |
+
"loss": 0.6961,
|
| 135 |
+
"step": 130
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 4.48,
|
| 139 |
+
"learning_rate": 9.438470728793309e-05,
|
| 140 |
+
"loss": 0.6747,
|
| 141 |
+
"step": 140
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 4.8,
|
| 145 |
+
"learning_rate": 9.31899641577061e-05,
|
| 146 |
+
"loss": 0.6499,
|
| 147 |
+
"step": 150
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 4.99,
|
| 151 |
+
"eval_accuracy": 0.753,
|
| 152 |
+
"eval_f1": 0.753308564854333,
|
| 153 |
+
"eval_loss": 0.6572905778884888,
|
| 154 |
+
"eval_precision": 0.7566016111468172,
|
| 155 |
+
"eval_recall": 0.753,
|
| 156 |
+
"eval_runtime": 17.661,
|
| 157 |
+
"eval_samples_per_second": 113.244,
|
| 158 |
+
"eval_steps_per_second": 1.812,
|
| 159 |
+
"step": 156
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 5.12,
|
| 163 |
+
"learning_rate": 9.199522102747909e-05,
|
| 164 |
+
"loss": 0.6334,
|
| 165 |
+
"step": 160
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 5.44,
|
| 169 |
+
"learning_rate": 9.080047789725208e-05,
|
| 170 |
+
"loss": 0.5973,
|
| 171 |
+
"step": 170
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 5.76,
|
| 175 |
+
"learning_rate": 8.960573476702509e-05,
|
| 176 |
+
"loss": 0.6147,
|
| 177 |
+
"step": 180
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 5.98,
|
| 181 |
+
"eval_accuracy": 0.7695,
|
| 182 |
+
"eval_f1": 0.7695196643972955,
|
| 183 |
+
"eval_loss": 0.6208649277687073,
|
| 184 |
+
"eval_precision": 0.7759966807360141,
|
| 185 |
+
"eval_recall": 0.7695,
|
| 186 |
+
"eval_runtime": 17.5025,
|
| 187 |
+
"eval_samples_per_second": 114.27,
|
| 188 |
+
"eval_steps_per_second": 1.828,
|
| 189 |
+
"step": 187
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 6.08,
|
| 193 |
+
"learning_rate": 8.84109916367981e-05,
|
| 194 |
+
"loss": 0.6088,
|
| 195 |
+
"step": 190
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 6.4,
|
| 199 |
+
"learning_rate": 8.72162485065711e-05,
|
| 200 |
+
"loss": 0.5726,
|
| 201 |
+
"step": 200
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 6.72,
|
| 205 |
+
"learning_rate": 8.60215053763441e-05,
|
| 206 |
+
"loss": 0.5911,
|
| 207 |
+
"step": 210
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 6.98,
|
| 211 |
+
"eval_accuracy": 0.7855,
|
| 212 |
+
"eval_f1": 0.785996582684527,
|
| 213 |
+
"eval_loss": 0.5802152752876282,
|
| 214 |
+
"eval_precision": 0.7868804978372835,
|
| 215 |
+
"eval_recall": 0.7855,
|
| 216 |
+
"eval_runtime": 15.8544,
|
| 217 |
+
"eval_samples_per_second": 126.148,
|
| 218 |
+
"eval_steps_per_second": 2.018,
|
| 219 |
+
"step": 218
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 7.04,
|
| 223 |
+
"learning_rate": 8.482676224611709e-05,
|
| 224 |
+
"loss": 0.574,
|
| 225 |
+
"step": 220
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 7.36,
|
| 229 |
+
"learning_rate": 8.363201911589009e-05,
|
| 230 |
+
"loss": 0.5599,
|
| 231 |
+
"step": 230
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 7.68,
|
| 235 |
+
"learning_rate": 8.243727598566309e-05,
|
| 236 |
+
"loss": 0.5816,
|
| 237 |
+
"step": 240
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 8.0,
|
| 241 |
+
"learning_rate": 8.124253285543608e-05,
|
| 242 |
+
"loss": 0.5489,
|
| 243 |
+
"step": 250
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 8.0,
|
| 247 |
+
"eval_accuracy": 0.799,
|
| 248 |
+
"eval_f1": 0.7991931870344942,
|
| 249 |
+
"eval_loss": 0.5572564601898193,
|
| 250 |
+
"eval_precision": 0.8018740297589478,
|
| 251 |
+
"eval_recall": 0.799,
|
| 252 |
+
"eval_runtime": 17.6613,
|
| 253 |
+
"eval_samples_per_second": 113.242,
|
| 254 |
+
"eval_steps_per_second": 1.812,
|
| 255 |
+
"step": 250
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 8.32,
|
| 259 |
+
"learning_rate": 8.004778972520908e-05,
|
| 260 |
+
"loss": 0.5431,
|
| 261 |
+
"step": 260
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 8.64,
|
| 265 |
+
"learning_rate": 7.885304659498209e-05,
|
| 266 |
+
"loss": 0.5261,
|
| 267 |
+
"step": 270
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 8.96,
|
| 271 |
+
"learning_rate": 7.765830346475508e-05,
|
| 272 |
+
"loss": 0.5306,
|
| 273 |
+
"step": 280
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 8.99,
|
| 277 |
+
"eval_accuracy": 0.801,
|
| 278 |
+
"eval_f1": 0.8003823815574242,
|
| 279 |
+
"eval_loss": 0.5317801237106323,
|
| 280 |
+
"eval_precision": 0.8004506457265061,
|
| 281 |
+
"eval_recall": 0.801,
|
| 282 |
+
"eval_runtime": 17.5329,
|
| 283 |
+
"eval_samples_per_second": 114.071,
|
| 284 |
+
"eval_steps_per_second": 1.825,
|
| 285 |
+
"step": 281
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 9.28,
|
| 289 |
+
"learning_rate": 7.646356033452809e-05,
|
| 290 |
+
"loss": 0.5338,
|
| 291 |
+
"step": 290
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 9.6,
|
| 295 |
+
"learning_rate": 7.526881720430108e-05,
|
| 296 |
+
"loss": 0.5169,
|
| 297 |
+
"step": 300
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 9.92,
|
| 301 |
+
"learning_rate": 7.407407407407407e-05,
|
| 302 |
+
"loss": 0.5154,
|
| 303 |
+
"step": 310
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 9.98,
|
| 307 |
+
"eval_accuracy": 0.8095,
|
| 308 |
+
"eval_f1": 0.8096375433282135,
|
| 309 |
+
"eval_loss": 0.5176502466201782,
|
| 310 |
+
"eval_precision": 0.8098218679903535,
|
| 311 |
+
"eval_recall": 0.8095,
|
| 312 |
+
"eval_runtime": 17.5997,
|
| 313 |
+
"eval_samples_per_second": 113.638,
|
| 314 |
+
"eval_steps_per_second": 1.818,
|
| 315 |
+
"step": 312
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 10.24,
|
| 319 |
+
"learning_rate": 7.287933094384708e-05,
|
| 320 |
+
"loss": 0.5296,
|
| 321 |
+
"step": 320
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 10.56,
|
| 325 |
+
"learning_rate": 7.168458781362007e-05,
|
| 326 |
+
"loss": 0.5128,
|
| 327 |
+
"step": 330
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 10.88,
|
| 331 |
+
"learning_rate": 7.048984468339306e-05,
|
| 332 |
+
"loss": 0.4963,
|
| 333 |
+
"step": 340
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 10.98,
|
| 337 |
+
"eval_accuracy": 0.8155,
|
| 338 |
+
"eval_f1": 0.8149341274820462,
|
| 339 |
+
"eval_loss": 0.5097112059593201,
|
| 340 |
+
"eval_precision": 0.8156851505062301,
|
| 341 |
+
"eval_recall": 0.8155,
|
| 342 |
+
"eval_runtime": 17.4961,
|
| 343 |
+
"eval_samples_per_second": 114.311,
|
| 344 |
+
"eval_steps_per_second": 1.829,
|
| 345 |
+
"step": 343
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 11.2,
|
| 349 |
+
"learning_rate": 6.929510155316607e-05,
|
| 350 |
+
"loss": 0.5041,
|
| 351 |
+
"step": 350
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 11.52,
|
| 355 |
+
"learning_rate": 6.810035842293908e-05,
|
| 356 |
+
"loss": 0.502,
|
| 357 |
+
"step": 360
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 11.84,
|
| 361 |
+
"learning_rate": 6.690561529271207e-05,
|
| 362 |
+
"loss": 0.5304,
|
| 363 |
+
"step": 370
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 12.0,
|
| 367 |
+
"eval_accuracy": 0.814,
|
| 368 |
+
"eval_f1": 0.8138644671410906,
|
| 369 |
+
"eval_loss": 0.4970574975013733,
|
| 370 |
+
"eval_precision": 0.8144361942556226,
|
| 371 |
+
"eval_recall": 0.814,
|
| 372 |
+
"eval_runtime": 15.7883,
|
| 373 |
+
"eval_samples_per_second": 126.676,
|
| 374 |
+
"eval_steps_per_second": 2.027,
|
| 375 |
+
"step": 375
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 12.16,
|
| 379 |
+
"learning_rate": 6.571087216248507e-05,
|
| 380 |
+
"loss": 0.4829,
|
| 381 |
+
"step": 380
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 12.48,
|
| 385 |
+
"learning_rate": 6.451612903225807e-05,
|
| 386 |
+
"loss": 0.5102,
|
| 387 |
+
"step": 390
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 12.8,
|
| 391 |
+
"learning_rate": 6.332138590203107e-05,
|
| 392 |
+
"loss": 0.4779,
|
| 393 |
+
"step": 400
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 12.99,
|
| 397 |
+
"eval_accuracy": 0.817,
|
| 398 |
+
"eval_f1": 0.8159780446201869,
|
| 399 |
+
"eval_loss": 0.4889465868473053,
|
| 400 |
+
"eval_precision": 0.8182092201948158,
|
| 401 |
+
"eval_recall": 0.817,
|
| 402 |
+
"eval_runtime": 16.144,
|
| 403 |
+
"eval_samples_per_second": 123.885,
|
| 404 |
+
"eval_steps_per_second": 1.982,
|
| 405 |
+
"step": 406
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 13.12,
|
| 409 |
+
"learning_rate": 6.212664277180407e-05,
|
| 410 |
+
"loss": 0.4971,
|
| 411 |
+
"step": 410
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 13.44,
|
| 415 |
+
"learning_rate": 6.093189964157706e-05,
|
| 416 |
+
"loss": 0.4947,
|
| 417 |
+
"step": 420
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 13.76,
|
| 421 |
+
"learning_rate": 5.9737156511350064e-05,
|
| 422 |
+
"loss": 0.4774,
|
| 423 |
+
"step": 430
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 13.98,
|
| 427 |
+
"eval_accuracy": 0.8245,
|
| 428 |
+
"eval_f1": 0.8249564797662794,
|
| 429 |
+
"eval_loss": 0.4821632504463196,
|
| 430 |
+
"eval_precision": 0.825530913664521,
|
| 431 |
+
"eval_recall": 0.8245,
|
| 432 |
+
"eval_runtime": 17.0982,
|
| 433 |
+
"eval_samples_per_second": 116.971,
|
| 434 |
+
"eval_steps_per_second": 1.872,
|
| 435 |
+
"step": 437
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 14.08,
|
| 439 |
+
"learning_rate": 5.8542413381123063e-05,
|
| 440 |
+
"loss": 0.4832,
|
| 441 |
+
"step": 440
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 14.4,
|
| 445 |
+
"learning_rate": 5.7347670250896056e-05,
|
| 446 |
+
"loss": 0.5032,
|
| 447 |
+
"step": 450
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 14.72,
|
| 451 |
+
"learning_rate": 5.615292712066906e-05,
|
| 452 |
+
"loss": 0.4852,
|
| 453 |
+
"step": 460
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 14.98,
|
| 457 |
+
"eval_accuracy": 0.827,
|
| 458 |
+
"eval_f1": 0.8271831997924377,
|
| 459 |
+
"eval_loss": 0.4771851897239685,
|
| 460 |
+
"eval_precision": 0.8289603535889277,
|
| 461 |
+
"eval_recall": 0.827,
|
| 462 |
+
"eval_runtime": 17.6562,
|
| 463 |
+
"eval_samples_per_second": 113.275,
|
| 464 |
+
"eval_steps_per_second": 1.812,
|
| 465 |
+
"step": 468
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 15.04,
|
| 469 |
+
"learning_rate": 5.495818399044206e-05,
|
| 470 |
+
"loss": 0.4924,
|
| 471 |
+
"step": 470
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 15.36,
|
| 475 |
+
"learning_rate": 5.3763440860215054e-05,
|
| 476 |
+
"loss": 0.4776,
|
| 477 |
+
"step": 480
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 15.68,
|
| 481 |
+
"learning_rate": 5.256869772998806e-05,
|
| 482 |
+
"loss": 0.4932,
|
| 483 |
+
"step": 490
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 16.0,
|
| 487 |
+
"learning_rate": 5.137395459976105e-05,
|
| 488 |
+
"loss": 0.4693,
|
| 489 |
+
"step": 500
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 16.0,
|
| 493 |
+
"eval_accuracy": 0.8285,
|
| 494 |
+
"eval_f1": 0.828999602960504,
|
| 495 |
+
"eval_loss": 0.4724329710006714,
|
| 496 |
+
"eval_precision": 0.8308231137948684,
|
| 497 |
+
"eval_recall": 0.8285,
|
| 498 |
+
"eval_runtime": 17.5896,
|
| 499 |
+
"eval_samples_per_second": 113.704,
|
| 500 |
+
"eval_steps_per_second": 1.819,
|
| 501 |
+
"step": 500
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 16.32,
|
| 505 |
+
"learning_rate": 5.017921146953405e-05,
|
| 506 |
+
"loss": 0.4817,
|
| 507 |
+
"step": 510
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 16.64,
|
| 511 |
+
"learning_rate": 4.898446833930705e-05,
|
| 512 |
+
"loss": 0.4783,
|
| 513 |
+
"step": 520
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 16.96,
|
| 517 |
+
"learning_rate": 4.778972520908005e-05,
|
| 518 |
+
"loss": 0.456,
|
| 519 |
+
"step": 530
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 16.99,
|
| 523 |
+
"eval_accuracy": 0.829,
|
| 524 |
+
"eval_f1": 0.828883524987889,
|
| 525 |
+
"eval_loss": 0.4636474549770355,
|
| 526 |
+
"eval_precision": 0.8294055346848391,
|
| 527 |
+
"eval_recall": 0.829,
|
| 528 |
+
"eval_runtime": 15.9015,
|
| 529 |
+
"eval_samples_per_second": 125.775,
|
| 530 |
+
"eval_steps_per_second": 2.012,
|
| 531 |
+
"step": 531
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 17.28,
|
| 535 |
+
"learning_rate": 4.659498207885305e-05,
|
| 536 |
+
"loss": 0.4883,
|
| 537 |
+
"step": 540
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 17.6,
|
| 541 |
+
"learning_rate": 4.540023894862604e-05,
|
| 542 |
+
"loss": 0.4785,
|
| 543 |
+
"step": 550
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 17.92,
|
| 547 |
+
"learning_rate": 4.420549581839905e-05,
|
| 548 |
+
"loss": 0.4703,
|
| 549 |
+
"step": 560
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 17.98,
|
| 553 |
+
"eval_accuracy": 0.829,
|
| 554 |
+
"eval_f1": 0.8291218466984425,
|
| 555 |
+
"eval_loss": 0.4623468220233917,
|
| 556 |
+
"eval_precision": 0.8303268779532134,
|
| 557 |
+
"eval_recall": 0.829,
|
| 558 |
+
"eval_runtime": 15.8278,
|
| 559 |
+
"eval_samples_per_second": 126.36,
|
| 560 |
+
"eval_steps_per_second": 2.022,
|
| 561 |
+
"step": 562
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 18.24,
|
| 565 |
+
"learning_rate": 4.301075268817205e-05,
|
| 566 |
+
"loss": 0.4832,
|
| 567 |
+
"step": 570
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 18.56,
|
| 571 |
+
"learning_rate": 4.1816009557945046e-05,
|
| 572 |
+
"loss": 0.4631,
|
| 573 |
+
"step": 580
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 18.88,
|
| 577 |
+
"learning_rate": 4.062126642771804e-05,
|
| 578 |
+
"loss": 0.4715,
|
| 579 |
+
"step": 590
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 18.98,
|
| 583 |
+
"eval_accuracy": 0.8305,
|
| 584 |
+
"eval_f1": 0.8308322842454664,
|
| 585 |
+
"eval_loss": 0.46094366908073425,
|
| 586 |
+
"eval_precision": 0.8328933669816244,
|
| 587 |
+
"eval_recall": 0.8305,
|
| 588 |
+
"eval_runtime": 16.9194,
|
| 589 |
+
"eval_samples_per_second": 118.208,
|
| 590 |
+
"eval_steps_per_second": 1.891,
|
| 591 |
+
"step": 593
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 19.2,
|
| 595 |
+
"learning_rate": 3.9426523297491045e-05,
|
| 596 |
+
"loss": 0.4601,
|
| 597 |
+
"step": 600
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 19.52,
|
| 601 |
+
"learning_rate": 3.8231780167264044e-05,
|
| 602 |
+
"loss": 0.4562,
|
| 603 |
+
"step": 610
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 19.84,
|
| 607 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 608 |
+
"loss": 0.4775,
|
| 609 |
+
"step": 620
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 20.0,
|
| 613 |
+
"eval_accuracy": 0.835,
|
| 614 |
+
"eval_f1": 0.8353228393166162,
|
| 615 |
+
"eval_loss": 0.4573521614074707,
|
| 616 |
+
"eval_precision": 0.83694143255206,
|
| 617 |
+
"eval_recall": 0.835,
|
| 618 |
+
"eval_runtime": 16.4171,
|
| 619 |
+
"eval_samples_per_second": 121.824,
|
| 620 |
+
"eval_steps_per_second": 1.949,
|
| 621 |
+
"step": 625
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 20.16,
|
| 625 |
+
"learning_rate": 3.5842293906810036e-05,
|
| 626 |
+
"loss": 0.463,
|
| 627 |
+
"step": 630
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 20.48,
|
| 631 |
+
"learning_rate": 3.4647550776583035e-05,
|
| 632 |
+
"loss": 0.4718,
|
| 633 |
+
"step": 640
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 20.8,
|
| 637 |
+
"learning_rate": 3.3452807646356034e-05,
|
| 638 |
+
"loss": 0.4776,
|
| 639 |
+
"step": 650
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 20.99,
|
| 643 |
+
"eval_accuracy": 0.833,
|
| 644 |
+
"eval_f1": 0.8331634514524776,
|
| 645 |
+
"eval_loss": 0.4531126022338867,
|
| 646 |
+
"eval_precision": 0.8337808849020805,
|
| 647 |
+
"eval_recall": 0.833,
|
| 648 |
+
"eval_runtime": 17.8976,
|
| 649 |
+
"eval_samples_per_second": 111.747,
|
| 650 |
+
"eval_steps_per_second": 1.788,
|
| 651 |
+
"step": 656
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 21.12,
|
| 655 |
+
"learning_rate": 3.2258064516129034e-05,
|
| 656 |
+
"loss": 0.4596,
|
| 657 |
+
"step": 660
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 21.44,
|
| 661 |
+
"learning_rate": 3.106332138590203e-05,
|
| 662 |
+
"loss": 0.4734,
|
| 663 |
+
"step": 670
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 21.76,
|
| 667 |
+
"learning_rate": 2.9868578255675032e-05,
|
| 668 |
+
"loss": 0.4599,
|
| 669 |
+
"step": 680
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 21.98,
|
| 673 |
+
"eval_accuracy": 0.8325,
|
| 674 |
+
"eval_f1": 0.8325183714479544,
|
| 675 |
+
"eval_loss": 0.44997453689575195,
|
| 676 |
+
"eval_precision": 0.8332624770493785,
|
| 677 |
+
"eval_recall": 0.8325,
|
| 678 |
+
"eval_runtime": 17.8768,
|
| 679 |
+
"eval_samples_per_second": 111.877,
|
| 680 |
+
"eval_steps_per_second": 1.79,
|
| 681 |
+
"step": 687
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 22.08,
|
| 685 |
+
"learning_rate": 2.8673835125448028e-05,
|
| 686 |
+
"loss": 0.4518,
|
| 687 |
+
"step": 690
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 22.4,
|
| 691 |
+
"learning_rate": 2.747909199522103e-05,
|
| 692 |
+
"loss": 0.4564,
|
| 693 |
+
"step": 700
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 22.72,
|
| 697 |
+
"learning_rate": 2.628434886499403e-05,
|
| 698 |
+
"loss": 0.4391,
|
| 699 |
+
"step": 710
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 22.98,
|
| 703 |
+
"eval_accuracy": 0.832,
|
| 704 |
+
"eval_f1": 0.8321062492294122,
|
| 705 |
+
"eval_loss": 0.4509717524051666,
|
| 706 |
+
"eval_precision": 0.8341271499003579,
|
| 707 |
+
"eval_recall": 0.832,
|
| 708 |
+
"eval_runtime": 17.5712,
|
| 709 |
+
"eval_samples_per_second": 113.823,
|
| 710 |
+
"eval_steps_per_second": 1.821,
|
| 711 |
+
"step": 718
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 23.04,
|
| 715 |
+
"learning_rate": 2.5089605734767026e-05,
|
| 716 |
+
"loss": 0.4637,
|
| 717 |
+
"step": 720
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 23.36,
|
| 721 |
+
"learning_rate": 2.3894862604540025e-05,
|
| 722 |
+
"loss": 0.4555,
|
| 723 |
+
"step": 730
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 23.68,
|
| 727 |
+
"learning_rate": 2.270011947431302e-05,
|
| 728 |
+
"loss": 0.4606,
|
| 729 |
+
"step": 740
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 24.0,
|
| 733 |
+
"learning_rate": 2.1505376344086024e-05,
|
| 734 |
+
"loss": 0.4537,
|
| 735 |
+
"step": 750
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 24.0,
|
| 739 |
+
"eval_accuracy": 0.835,
|
| 740 |
+
"eval_f1": 0.8351577732253366,
|
| 741 |
+
"eval_loss": 0.44663989543914795,
|
| 742 |
+
"eval_precision": 0.83556710984565,
|
| 743 |
+
"eval_recall": 0.835,
|
| 744 |
+
"eval_runtime": 15.86,
|
| 745 |
+
"eval_samples_per_second": 126.104,
|
| 746 |
+
"eval_steps_per_second": 2.018,
|
| 747 |
+
"step": 750
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 24.32,
|
| 751 |
+
"learning_rate": 2.031063321385902e-05,
|
| 752 |
+
"loss": 0.4541,
|
| 753 |
+
"step": 760
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 24.64,
|
| 757 |
+
"learning_rate": 1.9115890083632022e-05,
|
| 758 |
+
"loss": 0.4615,
|
| 759 |
+
"step": 770
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 24.96,
|
| 763 |
+
"learning_rate": 1.7921146953405018e-05,
|
| 764 |
+
"loss": 0.4555,
|
| 765 |
+
"step": 780
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 24.99,
|
| 769 |
+
"eval_accuracy": 0.8355,
|
| 770 |
+
"eval_f1": 0.8355792632536996,
|
| 771 |
+
"eval_loss": 0.44507473707199097,
|
| 772 |
+
"eval_precision": 0.8365371015464631,
|
| 773 |
+
"eval_recall": 0.8355,
|
| 774 |
+
"eval_runtime": 17.5288,
|
| 775 |
+
"eval_samples_per_second": 114.098,
|
| 776 |
+
"eval_steps_per_second": 1.826,
|
| 777 |
+
"step": 781
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 25.28,
|
| 781 |
+
"learning_rate": 1.6726403823178017e-05,
|
| 782 |
+
"loss": 0.4664,
|
| 783 |
+
"step": 790
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 25.6,
|
| 787 |
+
"learning_rate": 1.5531660692951016e-05,
|
| 788 |
+
"loss": 0.472,
|
| 789 |
+
"step": 800
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 25.92,
|
| 793 |
+
"learning_rate": 1.4336917562724014e-05,
|
| 794 |
+
"loss": 0.4476,
|
| 795 |
+
"step": 810
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 25.98,
|
| 799 |
+
"eval_accuracy": 0.8385,
|
| 800 |
+
"eval_f1": 0.8385912865364268,
|
| 801 |
+
"eval_loss": 0.4437757730484009,
|
| 802 |
+
"eval_precision": 0.8387790249591575,
|
| 803 |
+
"eval_recall": 0.8385,
|
| 804 |
+
"eval_runtime": 17.5608,
|
| 805 |
+
"eval_samples_per_second": 113.89,
|
| 806 |
+
"eval_steps_per_second": 1.822,
|
| 807 |
+
"step": 812
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 26.24,
|
| 811 |
+
"learning_rate": 1.3142174432497015e-05,
|
| 812 |
+
"loss": 0.4375,
|
| 813 |
+
"step": 820
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 26.56,
|
| 817 |
+
"learning_rate": 1.1947431302270013e-05,
|
| 818 |
+
"loss": 0.4614,
|
| 819 |
+
"step": 830
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 26.88,
|
| 823 |
+
"learning_rate": 1.0752688172043012e-05,
|
| 824 |
+
"loss": 0.4618,
|
| 825 |
+
"step": 840
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 26.98,
|
| 829 |
+
"eval_accuracy": 0.8355,
|
| 830 |
+
"eval_f1": 0.8357844536409353,
|
| 831 |
+
"eval_loss": 0.44403398036956787,
|
| 832 |
+
"eval_precision": 0.8365852918961869,
|
| 833 |
+
"eval_recall": 0.8355,
|
| 834 |
+
"eval_runtime": 17.0197,
|
| 835 |
+
"eval_samples_per_second": 117.511,
|
| 836 |
+
"eval_steps_per_second": 1.88,
|
| 837 |
+
"step": 843
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 27.2,
|
| 841 |
+
"learning_rate": 9.557945041816011e-06,
|
| 842 |
+
"loss": 0.4643,
|
| 843 |
+
"step": 850
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 27.52,
|
| 847 |
+
"learning_rate": 8.363201911589009e-06,
|
| 848 |
+
"loss": 0.4367,
|
| 849 |
+
"step": 860
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 27.84,
|
| 853 |
+
"learning_rate": 7.168458781362007e-06,
|
| 854 |
+
"loss": 0.4734,
|
| 855 |
+
"step": 870
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 28.0,
|
| 859 |
+
"eval_accuracy": 0.835,
|
| 860 |
+
"eval_f1": 0.8352230815495963,
|
| 861 |
+
"eval_loss": 0.4432300627231598,
|
| 862 |
+
"eval_precision": 0.836220591675889,
|
| 863 |
+
"eval_recall": 0.835,
|
| 864 |
+
"eval_runtime": 17.0846,
|
| 865 |
+
"eval_samples_per_second": 117.064,
|
| 866 |
+
"eval_steps_per_second": 1.873,
|
| 867 |
+
"step": 875
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 28.16,
|
| 871 |
+
"learning_rate": 5.973715651135006e-06,
|
| 872 |
+
"loss": 0.4705,
|
| 873 |
+
"step": 880
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 28.48,
|
| 877 |
+
"learning_rate": 4.7789725209080055e-06,
|
| 878 |
+
"loss": 0.4647,
|
| 879 |
+
"step": 890
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 28.8,
|
| 883 |
+
"learning_rate": 3.5842293906810035e-06,
|
| 884 |
+
"loss": 0.4453,
|
| 885 |
+
"step": 900
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 28.99,
|
| 889 |
+
"eval_accuracy": 0.8365,
|
| 890 |
+
"eval_f1": 0.8367327583839242,
|
| 891 |
+
"eval_loss": 0.44326910376548767,
|
| 892 |
+
"eval_precision": 0.8378063780559731,
|
| 893 |
+
"eval_recall": 0.8365,
|
| 894 |
+
"eval_runtime": 15.8101,
|
| 895 |
+
"eval_samples_per_second": 126.501,
|
| 896 |
+
"eval_steps_per_second": 2.024,
|
| 897 |
+
"step": 906
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 29.12,
|
| 901 |
+
"learning_rate": 2.3894862604540028e-06,
|
| 902 |
+
"loss": 0.4493,
|
| 903 |
+
"step": 910
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 29.44,
|
| 907 |
+
"learning_rate": 1.1947431302270014e-06,
|
| 908 |
+
"loss": 0.4455,
|
| 909 |
+
"step": 920
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 29.76,
|
| 913 |
+
"learning_rate": 0.0,
|
| 914 |
+
"loss": 0.4591,
|
| 915 |
+
"step": 930
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 29.76,
|
| 919 |
+
"eval_accuracy": 0.8365,
|
| 920 |
+
"eval_f1": 0.8367054051638796,
|
| 921 |
+
"eval_loss": 0.4430060386657715,
|
| 922 |
+
"eval_precision": 0.8376012647143584,
|
| 923 |
+
"eval_recall": 0.8365,
|
| 924 |
+
"eval_runtime": 16.1531,
|
| 925 |
+
"eval_samples_per_second": 123.815,
|
| 926 |
+
"eval_steps_per_second": 1.981,
|
| 927 |
+
"step": 930
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 29.76,
|
| 931 |
+
"step": 930,
|
| 932 |
+
"total_flos": 2.4317906065576428e+19,
|
| 933 |
+
"train_loss": 0.5888608142893802,
|
| 934 |
+
"train_runtime": 2857.7767,
|
| 935 |
+
"train_samples_per_second": 83.981,
|
| 936 |
+
"train_steps_per_second": 0.325
|
| 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": 2.4317906065576428e+19,
|
| 945 |
+
"train_batch_size": 64,
|
| 946 |
+
"trial_name": null,
|
| 947 |
+
"trial_params": null
|
| 948 |
+
}
|