Commit
•
0e7d8a1
1
Parent(s):
0e902bc
End of training
Browse files- README.md +1 -1
- all_results.json +13 -0
- eval_results.json +8 -0
- runs/May22_16-23-57_927069b479b5/events.out.tfevents.1716395466.927069b479b5.252.45 +3 -0
- train_results.json +8 -0
- trainer_state.json +1021 -0
README.md
CHANGED
|
@@ -32,7 +32,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [facebook/deit-base-distilled-patch16-224](https://huggingface.co/facebook/deit-base-distilled-patch16-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss:
|
| 36 |
- Accuracy: 0.7273
|
| 37 |
|
| 38 |
## Model description
|
|
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [facebook/deit-base-distilled-patch16-224](https://huggingface.co/facebook/deit-base-distilled-patch16-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.7292
|
| 36 |
- Accuracy: 0.7273
|
| 37 |
|
| 38 |
## Model description
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 100.0,
|
| 3 |
+
"eval_accuracy": 0.7272727272727273,
|
| 4 |
+
"eval_loss": 0.7291980385780334,
|
| 5 |
+
"eval_runtime": 0.2173,
|
| 6 |
+
"eval_samples_per_second": 50.614,
|
| 7 |
+
"eval_steps_per_second": 4.601,
|
| 8 |
+
"total_flos": 4.572150213593088e+17,
|
| 9 |
+
"train_loss": 0.0869519267976284,
|
| 10 |
+
"train_runtime": 406.2726,
|
| 11 |
+
"train_samples_per_second": 14.522,
|
| 12 |
+
"train_steps_per_second": 0.246
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 100.0,
|
| 3 |
+
"eval_accuracy": 0.7272727272727273,
|
| 4 |
+
"eval_loss": 0.7291980385780334,
|
| 5 |
+
"eval_runtime": 0.2173,
|
| 6 |
+
"eval_samples_per_second": 50.614,
|
| 7 |
+
"eval_steps_per_second": 4.601
|
| 8 |
+
}
|
runs/May22_16-23-57_927069b479b5/events.out.tfevents.1716395466.927069b479b5.252.45
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:876ef7a64995800066300f76cdaabda9516793c600751509f4805ea80a0b796f
|
| 3 |
+
size 405
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 100.0,
|
| 3 |
+
"total_flos": 4.572150213593088e+17,
|
| 4 |
+
"train_loss": 0.0869519267976284,
|
| 5 |
+
"train_runtime": 406.2726,
|
| 6 |
+
"train_samples_per_second": 14.522,
|
| 7 |
+
"train_steps_per_second": 0.246
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1021 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7272727272727273,
|
| 3 |
+
"best_model_checkpoint": "deit-base-distilled-patch16-224-hasta-85-fold5/checkpoint-4",
|
| 4 |
+
"epoch": 100.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 100,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_accuracy": 0.2727272727272727,
|
| 14 |
+
"eval_loss": 1.3529654741287231,
|
| 15 |
+
"eval_runtime": 0.1719,
|
| 16 |
+
"eval_samples_per_second": 64.009,
|
| 17 |
+
"eval_steps_per_second": 5.819,
|
| 18 |
+
"step": 1
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 2.0,
|
| 22 |
+
"eval_accuracy": 0.2727272727272727,
|
| 23 |
+
"eval_loss": 1.1775329113006592,
|
| 24 |
+
"eval_runtime": 0.1803,
|
| 25 |
+
"eval_samples_per_second": 61.012,
|
| 26 |
+
"eval_steps_per_second": 5.547,
|
| 27 |
+
"step": 2
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 3.0,
|
| 31 |
+
"eval_accuracy": 0.5454545454545454,
|
| 32 |
+
"eval_loss": 0.9127957820892334,
|
| 33 |
+
"eval_runtime": 0.1756,
|
| 34 |
+
"eval_samples_per_second": 62.634,
|
| 35 |
+
"eval_steps_per_second": 5.694,
|
| 36 |
+
"step": 3
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 4.0,
|
| 40 |
+
"eval_accuracy": 0.7272727272727273,
|
| 41 |
+
"eval_loss": 0.7291980385780334,
|
| 42 |
+
"eval_runtime": 0.1718,
|
| 43 |
+
"eval_samples_per_second": 64.037,
|
| 44 |
+
"eval_steps_per_second": 5.822,
|
| 45 |
+
"step": 4
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 5.0,
|
| 49 |
+
"eval_accuracy": 0.7272727272727273,
|
| 50 |
+
"eval_loss": 0.7752578854560852,
|
| 51 |
+
"eval_runtime": 0.1697,
|
| 52 |
+
"eval_samples_per_second": 64.839,
|
| 53 |
+
"eval_steps_per_second": 5.894,
|
| 54 |
+
"step": 5
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 6.0,
|
| 58 |
+
"eval_accuracy": 0.7272727272727273,
|
| 59 |
+
"eval_loss": 0.9951526522636414,
|
| 60 |
+
"eval_runtime": 0.1716,
|
| 61 |
+
"eval_samples_per_second": 64.099,
|
| 62 |
+
"eval_steps_per_second": 5.827,
|
| 63 |
+
"step": 6
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 7.0,
|
| 67 |
+
"eval_accuracy": 0.7272727272727273,
|
| 68 |
+
"eval_loss": 1.1799362897872925,
|
| 69 |
+
"eval_runtime": 0.1737,
|
| 70 |
+
"eval_samples_per_second": 63.314,
|
| 71 |
+
"eval_steps_per_second": 5.756,
|
| 72 |
+
"step": 7
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 8.0,
|
| 76 |
+
"eval_accuracy": 0.7272727272727273,
|
| 77 |
+
"eval_loss": 1.2698947191238403,
|
| 78 |
+
"eval_runtime": 0.1741,
|
| 79 |
+
"eval_samples_per_second": 63.189,
|
| 80 |
+
"eval_steps_per_second": 5.744,
|
| 81 |
+
"step": 8
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 9.0,
|
| 85 |
+
"eval_accuracy": 0.7272727272727273,
|
| 86 |
+
"eval_loss": 1.2729337215423584,
|
| 87 |
+
"eval_runtime": 0.1654,
|
| 88 |
+
"eval_samples_per_second": 66.495,
|
| 89 |
+
"eval_steps_per_second": 6.045,
|
| 90 |
+
"step": 9
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 10.0,
|
| 94 |
+
"grad_norm": 1.2218341827392578,
|
| 95 |
+
"learning_rate": 5e-05,
|
| 96 |
+
"loss": 0.38,
|
| 97 |
+
"step": 10
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 10.0,
|
| 101 |
+
"eval_accuracy": 0.7272727272727273,
|
| 102 |
+
"eval_loss": 1.2450836896896362,
|
| 103 |
+
"eval_runtime": 0.1667,
|
| 104 |
+
"eval_samples_per_second": 65.993,
|
| 105 |
+
"eval_steps_per_second": 5.999,
|
| 106 |
+
"step": 10
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 11.0,
|
| 110 |
+
"eval_accuracy": 0.7272727272727273,
|
| 111 |
+
"eval_loss": 1.2340657711029053,
|
| 112 |
+
"eval_runtime": 0.1699,
|
| 113 |
+
"eval_samples_per_second": 64.761,
|
| 114 |
+
"eval_steps_per_second": 5.887,
|
| 115 |
+
"step": 11
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 12.0,
|
| 119 |
+
"eval_accuracy": 0.7272727272727273,
|
| 120 |
+
"eval_loss": 1.2152786254882812,
|
| 121 |
+
"eval_runtime": 0.1741,
|
| 122 |
+
"eval_samples_per_second": 63.166,
|
| 123 |
+
"eval_steps_per_second": 5.742,
|
| 124 |
+
"step": 12
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 13.0,
|
| 128 |
+
"eval_accuracy": 0.7272727272727273,
|
| 129 |
+
"eval_loss": 1.184658408164978,
|
| 130 |
+
"eval_runtime": 0.1684,
|
| 131 |
+
"eval_samples_per_second": 65.309,
|
| 132 |
+
"eval_steps_per_second": 5.937,
|
| 133 |
+
"step": 13
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 14.0,
|
| 137 |
+
"eval_accuracy": 0.7272727272727273,
|
| 138 |
+
"eval_loss": 1.190322995185852,
|
| 139 |
+
"eval_runtime": 0.1708,
|
| 140 |
+
"eval_samples_per_second": 64.413,
|
| 141 |
+
"eval_steps_per_second": 5.856,
|
| 142 |
+
"step": 14
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 15.0,
|
| 146 |
+
"eval_accuracy": 0.7272727272727273,
|
| 147 |
+
"eval_loss": 1.21282160282135,
|
| 148 |
+
"eval_runtime": 0.1699,
|
| 149 |
+
"eval_samples_per_second": 64.74,
|
| 150 |
+
"eval_steps_per_second": 5.885,
|
| 151 |
+
"step": 15
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 16.0,
|
| 155 |
+
"eval_accuracy": 0.7272727272727273,
|
| 156 |
+
"eval_loss": 1.172433853149414,
|
| 157 |
+
"eval_runtime": 0.1741,
|
| 158 |
+
"eval_samples_per_second": 63.186,
|
| 159 |
+
"eval_steps_per_second": 5.744,
|
| 160 |
+
"step": 16
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 17.0,
|
| 164 |
+
"eval_accuracy": 0.7272727272727273,
|
| 165 |
+
"eval_loss": 1.0705375671386719,
|
| 166 |
+
"eval_runtime": 0.1704,
|
| 167 |
+
"eval_samples_per_second": 64.561,
|
| 168 |
+
"eval_steps_per_second": 5.869,
|
| 169 |
+
"step": 17
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 18.0,
|
| 173 |
+
"eval_accuracy": 0.7272727272727273,
|
| 174 |
+
"eval_loss": 1.010569453239441,
|
| 175 |
+
"eval_runtime": 0.1689,
|
| 176 |
+
"eval_samples_per_second": 65.128,
|
| 177 |
+
"eval_steps_per_second": 5.921,
|
| 178 |
+
"step": 18
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 19.0,
|
| 182 |
+
"eval_accuracy": 0.7272727272727273,
|
| 183 |
+
"eval_loss": 1.0238350629806519,
|
| 184 |
+
"eval_runtime": 0.1664,
|
| 185 |
+
"eval_samples_per_second": 66.124,
|
| 186 |
+
"eval_steps_per_second": 6.011,
|
| 187 |
+
"step": 19
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 20.0,
|
| 191 |
+
"grad_norm": 1.2547463178634644,
|
| 192 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 193 |
+
"loss": 0.1729,
|
| 194 |
+
"step": 20
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 20.0,
|
| 198 |
+
"eval_accuracy": 0.7272727272727273,
|
| 199 |
+
"eval_loss": 1.0593870878219604,
|
| 200 |
+
"eval_runtime": 0.1631,
|
| 201 |
+
"eval_samples_per_second": 67.431,
|
| 202 |
+
"eval_steps_per_second": 6.13,
|
| 203 |
+
"step": 20
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 21.0,
|
| 207 |
+
"eval_accuracy": 0.7272727272727273,
|
| 208 |
+
"eval_loss": 1.1695011854171753,
|
| 209 |
+
"eval_runtime": 0.189,
|
| 210 |
+
"eval_samples_per_second": 58.212,
|
| 211 |
+
"eval_steps_per_second": 5.292,
|
| 212 |
+
"step": 21
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 22.0,
|
| 216 |
+
"eval_accuracy": 0.7272727272727273,
|
| 217 |
+
"eval_loss": 1.2465709447860718,
|
| 218 |
+
"eval_runtime": 0.1698,
|
| 219 |
+
"eval_samples_per_second": 64.775,
|
| 220 |
+
"eval_steps_per_second": 5.889,
|
| 221 |
+
"step": 22
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 23.0,
|
| 225 |
+
"eval_accuracy": 0.7272727272727273,
|
| 226 |
+
"eval_loss": 1.2861061096191406,
|
| 227 |
+
"eval_runtime": 0.1673,
|
| 228 |
+
"eval_samples_per_second": 65.737,
|
| 229 |
+
"eval_steps_per_second": 5.976,
|
| 230 |
+
"step": 23
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 24.0,
|
| 234 |
+
"eval_accuracy": 0.7272727272727273,
|
| 235 |
+
"eval_loss": 1.279003381729126,
|
| 236 |
+
"eval_runtime": 0.1655,
|
| 237 |
+
"eval_samples_per_second": 66.467,
|
| 238 |
+
"eval_steps_per_second": 6.042,
|
| 239 |
+
"step": 24
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 25.0,
|
| 243 |
+
"eval_accuracy": 0.7272727272727273,
|
| 244 |
+
"eval_loss": 1.31769859790802,
|
| 245 |
+
"eval_runtime": 0.1688,
|
| 246 |
+
"eval_samples_per_second": 65.184,
|
| 247 |
+
"eval_steps_per_second": 5.926,
|
| 248 |
+
"step": 25
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 26.0,
|
| 252 |
+
"eval_accuracy": 0.7272727272727273,
|
| 253 |
+
"eval_loss": 1.413009524345398,
|
| 254 |
+
"eval_runtime": 0.1688,
|
| 255 |
+
"eval_samples_per_second": 65.178,
|
| 256 |
+
"eval_steps_per_second": 5.925,
|
| 257 |
+
"step": 26
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 27.0,
|
| 261 |
+
"eval_accuracy": 0.7272727272727273,
|
| 262 |
+
"eval_loss": 1.5154972076416016,
|
| 263 |
+
"eval_runtime": 0.1702,
|
| 264 |
+
"eval_samples_per_second": 64.632,
|
| 265 |
+
"eval_steps_per_second": 5.876,
|
| 266 |
+
"step": 27
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 28.0,
|
| 270 |
+
"eval_accuracy": 0.7272727272727273,
|
| 271 |
+
"eval_loss": 1.6224372386932373,
|
| 272 |
+
"eval_runtime": 0.1671,
|
| 273 |
+
"eval_samples_per_second": 65.816,
|
| 274 |
+
"eval_steps_per_second": 5.983,
|
| 275 |
+
"step": 28
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 29.0,
|
| 279 |
+
"eval_accuracy": 0.7272727272727273,
|
| 280 |
+
"eval_loss": 1.5918177366256714,
|
| 281 |
+
"eval_runtime": 0.1724,
|
| 282 |
+
"eval_samples_per_second": 63.792,
|
| 283 |
+
"eval_steps_per_second": 5.799,
|
| 284 |
+
"step": 29
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 30.0,
|
| 288 |
+
"grad_norm": 0.9141814708709717,
|
| 289 |
+
"learning_rate": 3.888888888888889e-05,
|
| 290 |
+
"loss": 0.0904,
|
| 291 |
+
"step": 30
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 30.0,
|
| 295 |
+
"eval_accuracy": 0.7272727272727273,
|
| 296 |
+
"eval_loss": 1.4098824262619019,
|
| 297 |
+
"eval_runtime": 0.1704,
|
| 298 |
+
"eval_samples_per_second": 64.547,
|
| 299 |
+
"eval_steps_per_second": 5.868,
|
| 300 |
+
"step": 30
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 31.0,
|
| 304 |
+
"eval_accuracy": 0.7272727272727273,
|
| 305 |
+
"eval_loss": 1.268126368522644,
|
| 306 |
+
"eval_runtime": 0.1689,
|
| 307 |
+
"eval_samples_per_second": 65.13,
|
| 308 |
+
"eval_steps_per_second": 5.921,
|
| 309 |
+
"step": 31
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 32.0,
|
| 313 |
+
"eval_accuracy": 0.7272727272727273,
|
| 314 |
+
"eval_loss": 1.1371163129806519,
|
| 315 |
+
"eval_runtime": 0.1754,
|
| 316 |
+
"eval_samples_per_second": 62.723,
|
| 317 |
+
"eval_steps_per_second": 5.702,
|
| 318 |
+
"step": 32
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 33.0,
|
| 322 |
+
"eval_accuracy": 0.7272727272727273,
|
| 323 |
+
"eval_loss": 1.0387264490127563,
|
| 324 |
+
"eval_runtime": 0.1708,
|
| 325 |
+
"eval_samples_per_second": 64.417,
|
| 326 |
+
"eval_steps_per_second": 5.856,
|
| 327 |
+
"step": 33
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 34.0,
|
| 331 |
+
"eval_accuracy": 0.7272727272727273,
|
| 332 |
+
"eval_loss": 1.012789011001587,
|
| 333 |
+
"eval_runtime": 0.1768,
|
| 334 |
+
"eval_samples_per_second": 62.211,
|
| 335 |
+
"eval_steps_per_second": 5.656,
|
| 336 |
+
"step": 34
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 35.0,
|
| 340 |
+
"eval_accuracy": 0.7272727272727273,
|
| 341 |
+
"eval_loss": 1.0423420667648315,
|
| 342 |
+
"eval_runtime": 0.1748,
|
| 343 |
+
"eval_samples_per_second": 62.928,
|
| 344 |
+
"eval_steps_per_second": 5.721,
|
| 345 |
+
"step": 35
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 36.0,
|
| 349 |
+
"eval_accuracy": 0.7272727272727273,
|
| 350 |
+
"eval_loss": 1.1729811429977417,
|
| 351 |
+
"eval_runtime": 0.1734,
|
| 352 |
+
"eval_samples_per_second": 63.442,
|
| 353 |
+
"eval_steps_per_second": 5.767,
|
| 354 |
+
"step": 36
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 37.0,
|
| 358 |
+
"eval_accuracy": 0.7272727272727273,
|
| 359 |
+
"eval_loss": 1.3305331468582153,
|
| 360 |
+
"eval_runtime": 0.1765,
|
| 361 |
+
"eval_samples_per_second": 62.331,
|
| 362 |
+
"eval_steps_per_second": 5.666,
|
| 363 |
+
"step": 37
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 38.0,
|
| 367 |
+
"eval_accuracy": 0.7272727272727273,
|
| 368 |
+
"eval_loss": 1.382030725479126,
|
| 369 |
+
"eval_runtime": 0.1793,
|
| 370 |
+
"eval_samples_per_second": 61.34,
|
| 371 |
+
"eval_steps_per_second": 5.576,
|
| 372 |
+
"step": 38
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 39.0,
|
| 376 |
+
"eval_accuracy": 0.7272727272727273,
|
| 377 |
+
"eval_loss": 1.3681752681732178,
|
| 378 |
+
"eval_runtime": 0.1677,
|
| 379 |
+
"eval_samples_per_second": 65.605,
|
| 380 |
+
"eval_steps_per_second": 5.964,
|
| 381 |
+
"step": 39
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 40.0,
|
| 385 |
+
"grad_norm": 1.4764775037765503,
|
| 386 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 387 |
+
"loss": 0.0591,
|
| 388 |
+
"step": 40
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 40.0,
|
| 392 |
+
"eval_accuracy": 0.7272727272727273,
|
| 393 |
+
"eval_loss": 1.285431981086731,
|
| 394 |
+
"eval_runtime": 0.17,
|
| 395 |
+
"eval_samples_per_second": 64.708,
|
| 396 |
+
"eval_steps_per_second": 5.883,
|
| 397 |
+
"step": 40
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 41.0,
|
| 401 |
+
"eval_accuracy": 0.7272727272727273,
|
| 402 |
+
"eval_loss": 1.2000277042388916,
|
| 403 |
+
"eval_runtime": 0.1713,
|
| 404 |
+
"eval_samples_per_second": 64.199,
|
| 405 |
+
"eval_steps_per_second": 5.836,
|
| 406 |
+
"step": 41
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 42.0,
|
| 410 |
+
"eval_accuracy": 0.7272727272727273,
|
| 411 |
+
"eval_loss": 1.207851767539978,
|
| 412 |
+
"eval_runtime": 0.1864,
|
| 413 |
+
"eval_samples_per_second": 58.998,
|
| 414 |
+
"eval_steps_per_second": 5.363,
|
| 415 |
+
"step": 42
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 43.0,
|
| 419 |
+
"eval_accuracy": 0.7272727272727273,
|
| 420 |
+
"eval_loss": 1.2967201471328735,
|
| 421 |
+
"eval_runtime": 0.1746,
|
| 422 |
+
"eval_samples_per_second": 63.0,
|
| 423 |
+
"eval_steps_per_second": 5.727,
|
| 424 |
+
"step": 43
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 44.0,
|
| 428 |
+
"eval_accuracy": 0.7272727272727273,
|
| 429 |
+
"eval_loss": 1.3672311305999756,
|
| 430 |
+
"eval_runtime": 0.1673,
|
| 431 |
+
"eval_samples_per_second": 65.735,
|
| 432 |
+
"eval_steps_per_second": 5.976,
|
| 433 |
+
"step": 44
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 45.0,
|
| 437 |
+
"eval_accuracy": 0.7272727272727273,
|
| 438 |
+
"eval_loss": 1.370935082435608,
|
| 439 |
+
"eval_runtime": 0.1704,
|
| 440 |
+
"eval_samples_per_second": 64.553,
|
| 441 |
+
"eval_steps_per_second": 5.868,
|
| 442 |
+
"step": 45
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 46.0,
|
| 446 |
+
"eval_accuracy": 0.7272727272727273,
|
| 447 |
+
"eval_loss": 1.4370254278182983,
|
| 448 |
+
"eval_runtime": 0.1662,
|
| 449 |
+
"eval_samples_per_second": 66.189,
|
| 450 |
+
"eval_steps_per_second": 6.017,
|
| 451 |
+
"step": 46
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 47.0,
|
| 455 |
+
"eval_accuracy": 0.7272727272727273,
|
| 456 |
+
"eval_loss": 1.486308217048645,
|
| 457 |
+
"eval_runtime": 0.1673,
|
| 458 |
+
"eval_samples_per_second": 65.742,
|
| 459 |
+
"eval_steps_per_second": 5.977,
|
| 460 |
+
"step": 47
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 48.0,
|
| 464 |
+
"eval_accuracy": 0.7272727272727273,
|
| 465 |
+
"eval_loss": 1.5696362257003784,
|
| 466 |
+
"eval_runtime": 0.1724,
|
| 467 |
+
"eval_samples_per_second": 63.797,
|
| 468 |
+
"eval_steps_per_second": 5.8,
|
| 469 |
+
"step": 48
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 49.0,
|
| 473 |
+
"eval_accuracy": 0.7272727272727273,
|
| 474 |
+
"eval_loss": 1.5678352117538452,
|
| 475 |
+
"eval_runtime": 0.1701,
|
| 476 |
+
"eval_samples_per_second": 64.684,
|
| 477 |
+
"eval_steps_per_second": 5.88,
|
| 478 |
+
"step": 49
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 50.0,
|
| 482 |
+
"grad_norm": 1.1623984575271606,
|
| 483 |
+
"learning_rate": 2.777777777777778e-05,
|
| 484 |
+
"loss": 0.0289,
|
| 485 |
+
"step": 50
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 50.0,
|
| 489 |
+
"eval_accuracy": 0.7272727272727273,
|
| 490 |
+
"eval_loss": 1.544366717338562,
|
| 491 |
+
"eval_runtime": 0.1701,
|
| 492 |
+
"eval_samples_per_second": 64.677,
|
| 493 |
+
"eval_steps_per_second": 5.88,
|
| 494 |
+
"step": 50
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 51.0,
|
| 498 |
+
"eval_accuracy": 0.7272727272727273,
|
| 499 |
+
"eval_loss": 1.5086143016815186,
|
| 500 |
+
"eval_runtime": 0.17,
|
| 501 |
+
"eval_samples_per_second": 64.71,
|
| 502 |
+
"eval_steps_per_second": 5.883,
|
| 503 |
+
"step": 51
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 52.0,
|
| 507 |
+
"eval_accuracy": 0.7272727272727273,
|
| 508 |
+
"eval_loss": 1.4332855939865112,
|
| 509 |
+
"eval_runtime": 0.1809,
|
| 510 |
+
"eval_samples_per_second": 60.823,
|
| 511 |
+
"eval_steps_per_second": 5.529,
|
| 512 |
+
"step": 52
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 53.0,
|
| 516 |
+
"eval_accuracy": 0.7272727272727273,
|
| 517 |
+
"eval_loss": 1.364355206489563,
|
| 518 |
+
"eval_runtime": 0.1768,
|
| 519 |
+
"eval_samples_per_second": 62.214,
|
| 520 |
+
"eval_steps_per_second": 5.656,
|
| 521 |
+
"step": 53
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 54.0,
|
| 525 |
+
"eval_accuracy": 0.7272727272727273,
|
| 526 |
+
"eval_loss": 1.3098602294921875,
|
| 527 |
+
"eval_runtime": 0.1685,
|
| 528 |
+
"eval_samples_per_second": 65.295,
|
| 529 |
+
"eval_steps_per_second": 5.936,
|
| 530 |
+
"step": 54
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 55.0,
|
| 534 |
+
"eval_accuracy": 0.7272727272727273,
|
| 535 |
+
"eval_loss": 1.3354856967926025,
|
| 536 |
+
"eval_runtime": 0.174,
|
| 537 |
+
"eval_samples_per_second": 63.234,
|
| 538 |
+
"eval_steps_per_second": 5.749,
|
| 539 |
+
"step": 55
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 56.0,
|
| 543 |
+
"eval_accuracy": 0.7272727272727273,
|
| 544 |
+
"eval_loss": 1.428562045097351,
|
| 545 |
+
"eval_runtime": 0.1728,
|
| 546 |
+
"eval_samples_per_second": 63.669,
|
| 547 |
+
"eval_steps_per_second": 5.788,
|
| 548 |
+
"step": 56
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 57.0,
|
| 552 |
+
"eval_accuracy": 0.7272727272727273,
|
| 553 |
+
"eval_loss": 1.6121271848678589,
|
| 554 |
+
"eval_runtime": 0.1744,
|
| 555 |
+
"eval_samples_per_second": 63.061,
|
| 556 |
+
"eval_steps_per_second": 5.733,
|
| 557 |
+
"step": 57
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 58.0,
|
| 561 |
+
"eval_accuracy": 0.7272727272727273,
|
| 562 |
+
"eval_loss": 1.8074326515197754,
|
| 563 |
+
"eval_runtime": 0.1723,
|
| 564 |
+
"eval_samples_per_second": 63.851,
|
| 565 |
+
"eval_steps_per_second": 5.805,
|
| 566 |
+
"step": 58
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 59.0,
|
| 570 |
+
"eval_accuracy": 0.7272727272727273,
|
| 571 |
+
"eval_loss": 1.9460711479187012,
|
| 572 |
+
"eval_runtime": 0.1782,
|
| 573 |
+
"eval_samples_per_second": 61.729,
|
| 574 |
+
"eval_steps_per_second": 5.612,
|
| 575 |
+
"step": 59
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 60.0,
|
| 579 |
+
"grad_norm": 0.7182336449623108,
|
| 580 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 581 |
+
"loss": 0.0342,
|
| 582 |
+
"step": 60
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 60.0,
|
| 586 |
+
"eval_accuracy": 0.7272727272727273,
|
| 587 |
+
"eval_loss": 2.0313925743103027,
|
| 588 |
+
"eval_runtime": 0.1782,
|
| 589 |
+
"eval_samples_per_second": 61.712,
|
| 590 |
+
"eval_steps_per_second": 5.61,
|
| 591 |
+
"step": 60
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 61.0,
|
| 595 |
+
"eval_accuracy": 0.7272727272727273,
|
| 596 |
+
"eval_loss": 2.0407793521881104,
|
| 597 |
+
"eval_runtime": 0.1689,
|
| 598 |
+
"eval_samples_per_second": 65.12,
|
| 599 |
+
"eval_steps_per_second": 5.92,
|
| 600 |
+
"step": 61
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 62.0,
|
| 604 |
+
"eval_accuracy": 0.7272727272727273,
|
| 605 |
+
"eval_loss": 2.047626495361328,
|
| 606 |
+
"eval_runtime": 0.1696,
|
| 607 |
+
"eval_samples_per_second": 64.868,
|
| 608 |
+
"eval_steps_per_second": 5.897,
|
| 609 |
+
"step": 62
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 63.0,
|
| 613 |
+
"eval_accuracy": 0.7272727272727273,
|
| 614 |
+
"eval_loss": 2.051710605621338,
|
| 615 |
+
"eval_runtime": 0.1741,
|
| 616 |
+
"eval_samples_per_second": 63.196,
|
| 617 |
+
"eval_steps_per_second": 5.745,
|
| 618 |
+
"step": 63
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 64.0,
|
| 622 |
+
"eval_accuracy": 0.7272727272727273,
|
| 623 |
+
"eval_loss": 2.021721601486206,
|
| 624 |
+
"eval_runtime": 0.1668,
|
| 625 |
+
"eval_samples_per_second": 65.951,
|
| 626 |
+
"eval_steps_per_second": 5.996,
|
| 627 |
+
"step": 64
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 65.0,
|
| 631 |
+
"eval_accuracy": 0.7272727272727273,
|
| 632 |
+
"eval_loss": 1.9581713676452637,
|
| 633 |
+
"eval_runtime": 0.1741,
|
| 634 |
+
"eval_samples_per_second": 63.17,
|
| 635 |
+
"eval_steps_per_second": 5.743,
|
| 636 |
+
"step": 65
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 66.0,
|
| 640 |
+
"eval_accuracy": 0.7272727272727273,
|
| 641 |
+
"eval_loss": 1.8824611902236938,
|
| 642 |
+
"eval_runtime": 0.1698,
|
| 643 |
+
"eval_samples_per_second": 64.782,
|
| 644 |
+
"eval_steps_per_second": 5.889,
|
| 645 |
+
"step": 66
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 67.0,
|
| 649 |
+
"eval_accuracy": 0.7272727272727273,
|
| 650 |
+
"eval_loss": 1.8085075616836548,
|
| 651 |
+
"eval_runtime": 0.1674,
|
| 652 |
+
"eval_samples_per_second": 65.719,
|
| 653 |
+
"eval_steps_per_second": 5.974,
|
| 654 |
+
"step": 67
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 68.0,
|
| 658 |
+
"eval_accuracy": 0.7272727272727273,
|
| 659 |
+
"eval_loss": 1.787988305091858,
|
| 660 |
+
"eval_runtime": 0.1717,
|
| 661 |
+
"eval_samples_per_second": 64.058,
|
| 662 |
+
"eval_steps_per_second": 5.823,
|
| 663 |
+
"step": 68
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 69.0,
|
| 667 |
+
"eval_accuracy": 0.7272727272727273,
|
| 668 |
+
"eval_loss": 1.7796345949172974,
|
| 669 |
+
"eval_runtime": 0.1677,
|
| 670 |
+
"eval_samples_per_second": 65.61,
|
| 671 |
+
"eval_steps_per_second": 5.965,
|
| 672 |
+
"step": 69
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 70.0,
|
| 676 |
+
"grad_norm": 0.4171023368835449,
|
| 677 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 678 |
+
"loss": 0.0203,
|
| 679 |
+
"step": 70
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 70.0,
|
| 683 |
+
"eval_accuracy": 0.7272727272727273,
|
| 684 |
+
"eval_loss": 1.7929339408874512,
|
| 685 |
+
"eval_runtime": 0.1647,
|
| 686 |
+
"eval_samples_per_second": 66.786,
|
| 687 |
+
"eval_steps_per_second": 6.071,
|
| 688 |
+
"step": 70
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 71.0,
|
| 692 |
+
"eval_accuracy": 0.7272727272727273,
|
| 693 |
+
"eval_loss": 1.8213086128234863,
|
| 694 |
+
"eval_runtime": 0.1752,
|
| 695 |
+
"eval_samples_per_second": 62.779,
|
| 696 |
+
"eval_steps_per_second": 5.707,
|
| 697 |
+
"step": 71
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 72.0,
|
| 701 |
+
"eval_accuracy": 0.7272727272727273,
|
| 702 |
+
"eval_loss": 1.8387740850448608,
|
| 703 |
+
"eval_runtime": 0.1718,
|
| 704 |
+
"eval_samples_per_second": 64.032,
|
| 705 |
+
"eval_steps_per_second": 5.821,
|
| 706 |
+
"step": 72
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 73.0,
|
| 710 |
+
"eval_accuracy": 0.7272727272727273,
|
| 711 |
+
"eval_loss": 1.8488353490829468,
|
| 712 |
+
"eval_runtime": 0.168,
|
| 713 |
+
"eval_samples_per_second": 65.475,
|
| 714 |
+
"eval_steps_per_second": 5.952,
|
| 715 |
+
"step": 73
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 74.0,
|
| 719 |
+
"eval_accuracy": 0.7272727272727273,
|
| 720 |
+
"eval_loss": 1.8752758502960205,
|
| 721 |
+
"eval_runtime": 0.1669,
|
| 722 |
+
"eval_samples_per_second": 65.926,
|
| 723 |
+
"eval_steps_per_second": 5.993,
|
| 724 |
+
"step": 74
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 75.0,
|
| 728 |
+
"eval_accuracy": 0.7272727272727273,
|
| 729 |
+
"eval_loss": 1.9079365730285645,
|
| 730 |
+
"eval_runtime": 0.175,
|
| 731 |
+
"eval_samples_per_second": 62.846,
|
| 732 |
+
"eval_steps_per_second": 5.713,
|
| 733 |
+
"step": 75
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 76.0,
|
| 737 |
+
"eval_accuracy": 0.7272727272727273,
|
| 738 |
+
"eval_loss": 1.9395884275436401,
|
| 739 |
+
"eval_runtime": 0.1664,
|
| 740 |
+
"eval_samples_per_second": 66.091,
|
| 741 |
+
"eval_steps_per_second": 6.008,
|
| 742 |
+
"step": 76
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 77.0,
|
| 746 |
+
"eval_accuracy": 0.7272727272727273,
|
| 747 |
+
"eval_loss": 1.9556442499160767,
|
| 748 |
+
"eval_runtime": 0.1701,
|
| 749 |
+
"eval_samples_per_second": 64.665,
|
| 750 |
+
"eval_steps_per_second": 5.879,
|
| 751 |
+
"step": 77
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 78.0,
|
| 755 |
+
"eval_accuracy": 0.7272727272727273,
|
| 756 |
+
"eval_loss": 1.9590537548065186,
|
| 757 |
+
"eval_runtime": 0.167,
|
| 758 |
+
"eval_samples_per_second": 65.861,
|
| 759 |
+
"eval_steps_per_second": 5.987,
|
| 760 |
+
"step": 78
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 79.0,
|
| 764 |
+
"eval_accuracy": 0.7272727272727273,
|
| 765 |
+
"eval_loss": 1.966783881187439,
|
| 766 |
+
"eval_runtime": 0.1642,
|
| 767 |
+
"eval_samples_per_second": 66.993,
|
| 768 |
+
"eval_steps_per_second": 6.09,
|
| 769 |
+
"step": 79
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 80.0,
|
| 773 |
+
"grad_norm": 0.9364380836486816,
|
| 774 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 775 |
+
"loss": 0.0324,
|
| 776 |
+
"step": 80
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 80.0,
|
| 780 |
+
"eval_accuracy": 0.7272727272727273,
|
| 781 |
+
"eval_loss": 1.9864659309387207,
|
| 782 |
+
"eval_runtime": 0.1632,
|
| 783 |
+
"eval_samples_per_second": 67.403,
|
| 784 |
+
"eval_steps_per_second": 6.128,
|
| 785 |
+
"step": 80
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 81.0,
|
| 789 |
+
"eval_accuracy": 0.7272727272727273,
|
| 790 |
+
"eval_loss": 2.0098299980163574,
|
| 791 |
+
"eval_runtime": 0.1689,
|
| 792 |
+
"eval_samples_per_second": 65.144,
|
| 793 |
+
"eval_steps_per_second": 5.922,
|
| 794 |
+
"step": 81
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 82.0,
|
| 798 |
+
"eval_accuracy": 0.7272727272727273,
|
| 799 |
+
"eval_loss": 2.0383646488189697,
|
| 800 |
+
"eval_runtime": 0.1676,
|
| 801 |
+
"eval_samples_per_second": 65.648,
|
| 802 |
+
"eval_steps_per_second": 5.968,
|
| 803 |
+
"step": 82
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 83.0,
|
| 807 |
+
"eval_accuracy": 0.7272727272727273,
|
| 808 |
+
"eval_loss": 2.0658936500549316,
|
| 809 |
+
"eval_runtime": 0.1694,
|
| 810 |
+
"eval_samples_per_second": 64.949,
|
| 811 |
+
"eval_steps_per_second": 5.904,
|
| 812 |
+
"step": 83
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 84.0,
|
| 816 |
+
"eval_accuracy": 0.7272727272727273,
|
| 817 |
+
"eval_loss": 2.0952181816101074,
|
| 818 |
+
"eval_runtime": 0.1677,
|
| 819 |
+
"eval_samples_per_second": 65.585,
|
| 820 |
+
"eval_steps_per_second": 5.962,
|
| 821 |
+
"step": 84
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 85.0,
|
| 825 |
+
"eval_accuracy": 0.7272727272727273,
|
| 826 |
+
"eval_loss": 2.1068856716156006,
|
| 827 |
+
"eval_runtime": 0.1624,
|
| 828 |
+
"eval_samples_per_second": 67.74,
|
| 829 |
+
"eval_steps_per_second": 6.158,
|
| 830 |
+
"step": 85
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 86.0,
|
| 834 |
+
"eval_accuracy": 0.7272727272727273,
|
| 835 |
+
"eval_loss": 2.113046407699585,
|
| 836 |
+
"eval_runtime": 0.1693,
|
| 837 |
+
"eval_samples_per_second": 64.983,
|
| 838 |
+
"eval_steps_per_second": 5.908,
|
| 839 |
+
"step": 86
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 87.0,
|
| 843 |
+
"eval_accuracy": 0.7272727272727273,
|
| 844 |
+
"eval_loss": 2.118079423904419,
|
| 845 |
+
"eval_runtime": 0.1677,
|
| 846 |
+
"eval_samples_per_second": 65.591,
|
| 847 |
+
"eval_steps_per_second": 5.963,
|
| 848 |
+
"step": 87
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 88.0,
|
| 852 |
+
"eval_accuracy": 0.7272727272727273,
|
| 853 |
+
"eval_loss": 2.117971658706665,
|
| 854 |
+
"eval_runtime": 0.1661,
|
| 855 |
+
"eval_samples_per_second": 66.217,
|
| 856 |
+
"eval_steps_per_second": 6.02,
|
| 857 |
+
"step": 88
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 89.0,
|
| 861 |
+
"eval_accuracy": 0.7272727272727273,
|
| 862 |
+
"eval_loss": 2.1172935962677,
|
| 863 |
+
"eval_runtime": 0.1659,
|
| 864 |
+
"eval_samples_per_second": 66.288,
|
| 865 |
+
"eval_steps_per_second": 6.026,
|
| 866 |
+
"step": 89
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 90.0,
|
| 870 |
+
"grad_norm": 0.6589764356613159,
|
| 871 |
+
"learning_rate": 5.555555555555556e-06,
|
| 872 |
+
"loss": 0.0244,
|
| 873 |
+
"step": 90
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 90.0,
|
| 877 |
+
"eval_accuracy": 0.7272727272727273,
|
| 878 |
+
"eval_loss": 2.1193482875823975,
|
| 879 |
+
"eval_runtime": 0.166,
|
| 880 |
+
"eval_samples_per_second": 66.245,
|
| 881 |
+
"eval_steps_per_second": 6.022,
|
| 882 |
+
"step": 90
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 91.0,
|
| 886 |
+
"eval_accuracy": 0.7272727272727273,
|
| 887 |
+
"eval_loss": 2.122624158859253,
|
| 888 |
+
"eval_runtime": 0.1649,
|
| 889 |
+
"eval_samples_per_second": 66.724,
|
| 890 |
+
"eval_steps_per_second": 6.066,
|
| 891 |
+
"step": 91
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 92.0,
|
| 895 |
+
"eval_accuracy": 0.7272727272727273,
|
| 896 |
+
"eval_loss": 2.1255929470062256,
|
| 897 |
+
"eval_runtime": 0.1657,
|
| 898 |
+
"eval_samples_per_second": 66.403,
|
| 899 |
+
"eval_steps_per_second": 6.037,
|
| 900 |
+
"step": 92
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 93.0,
|
| 904 |
+
"eval_accuracy": 0.7272727272727273,
|
| 905 |
+
"eval_loss": 2.131207227706909,
|
| 906 |
+
"eval_runtime": 0.1672,
|
| 907 |
+
"eval_samples_per_second": 65.802,
|
| 908 |
+
"eval_steps_per_second": 5.982,
|
| 909 |
+
"step": 93
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 94.0,
|
| 913 |
+
"eval_accuracy": 0.7272727272727273,
|
| 914 |
+
"eval_loss": 2.133344888687134,
|
| 915 |
+
"eval_runtime": 0.1631,
|
| 916 |
+
"eval_samples_per_second": 67.457,
|
| 917 |
+
"eval_steps_per_second": 6.132,
|
| 918 |
+
"step": 94
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 95.0,
|
| 922 |
+
"eval_accuracy": 0.7272727272727273,
|
| 923 |
+
"eval_loss": 2.1370675563812256,
|
| 924 |
+
"eval_runtime": 0.2387,
|
| 925 |
+
"eval_samples_per_second": 46.081,
|
| 926 |
+
"eval_steps_per_second": 4.189,
|
| 927 |
+
"step": 95
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 96.0,
|
| 931 |
+
"eval_accuracy": 0.7272727272727273,
|
| 932 |
+
"eval_loss": 2.1412885189056396,
|
| 933 |
+
"eval_runtime": 0.1672,
|
| 934 |
+
"eval_samples_per_second": 65.79,
|
| 935 |
+
"eval_steps_per_second": 5.981,
|
| 936 |
+
"step": 96
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 97.0,
|
| 940 |
+
"eval_accuracy": 0.7272727272727273,
|
| 941 |
+
"eval_loss": 2.143777370452881,
|
| 942 |
+
"eval_runtime": 0.1595,
|
| 943 |
+
"eval_samples_per_second": 68.985,
|
| 944 |
+
"eval_steps_per_second": 6.271,
|
| 945 |
+
"step": 97
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 98.0,
|
| 949 |
+
"eval_accuracy": 0.7272727272727273,
|
| 950 |
+
"eval_loss": 2.14536452293396,
|
| 951 |
+
"eval_runtime": 0.173,
|
| 952 |
+
"eval_samples_per_second": 63.578,
|
| 953 |
+
"eval_steps_per_second": 5.78,
|
| 954 |
+
"step": 98
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 99.0,
|
| 958 |
+
"eval_accuracy": 0.7272727272727273,
|
| 959 |
+
"eval_loss": 2.1451478004455566,
|
| 960 |
+
"eval_runtime": 0.1615,
|
| 961 |
+
"eval_samples_per_second": 68.109,
|
| 962 |
+
"eval_steps_per_second": 6.192,
|
| 963 |
+
"step": 99
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 100.0,
|
| 967 |
+
"grad_norm": 1.9433962106704712,
|
| 968 |
+
"learning_rate": 0.0,
|
| 969 |
+
"loss": 0.027,
|
| 970 |
+
"step": 100
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 100.0,
|
| 974 |
+
"eval_accuracy": 0.7272727272727273,
|
| 975 |
+
"eval_loss": 2.1447601318359375,
|
| 976 |
+
"eval_runtime": 0.1574,
|
| 977 |
+
"eval_samples_per_second": 69.896,
|
| 978 |
+
"eval_steps_per_second": 6.354,
|
| 979 |
+
"step": 100
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"epoch": 100.0,
|
| 983 |
+
"step": 100,
|
| 984 |
+
"total_flos": 4.572150213593088e+17,
|
| 985 |
+
"train_loss": 0.0869519267976284,
|
| 986 |
+
"train_runtime": 406.2726,
|
| 987 |
+
"train_samples_per_second": 14.522,
|
| 988 |
+
"train_steps_per_second": 0.246
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 100.0,
|
| 992 |
+
"eval_accuracy": 0.7272727272727273,
|
| 993 |
+
"eval_loss": 0.7291980385780334,
|
| 994 |
+
"eval_runtime": 0.2173,
|
| 995 |
+
"eval_samples_per_second": 50.614,
|
| 996 |
+
"eval_steps_per_second": 4.601,
|
| 997 |
+
"step": 100
|
| 998 |
+
}
|
| 999 |
+
],
|
| 1000 |
+
"logging_steps": 10,
|
| 1001 |
+
"max_steps": 100,
|
| 1002 |
+
"num_input_tokens_seen": 0,
|
| 1003 |
+
"num_train_epochs": 100,
|
| 1004 |
+
"save_steps": 500,
|
| 1005 |
+
"stateful_callbacks": {
|
| 1006 |
+
"TrainerControl": {
|
| 1007 |
+
"args": {
|
| 1008 |
+
"should_epoch_stop": false,
|
| 1009 |
+
"should_evaluate": false,
|
| 1010 |
+
"should_log": false,
|
| 1011 |
+
"should_save": true,
|
| 1012 |
+
"should_training_stop": true
|
| 1013 |
+
},
|
| 1014 |
+
"attributes": {}
|
| 1015 |
+
}
|
| 1016 |
+
},
|
| 1017 |
+
"total_flos": 4.572150213593088e+17,
|
| 1018 |
+
"train_batch_size": 32,
|
| 1019 |
+
"trial_name": null,
|
| 1020 |
+
"trial_params": null
|
| 1021 |
+
}
|