End of training
Browse files- README.md +1 -1
- all_results.json +13 -0
- eval_results.json +8 -0
- runs/May22_15-53-51_927069b479b5/events.out.tfevents.1716393675.927069b479b5.252.37 +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: 0.9744
|
| 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": 0.9744274020195007,
|
| 5 |
+
"eval_runtime": 0.2198,
|
| 6 |
+
"eval_samples_per_second": 50.054,
|
| 7 |
+
"eval_steps_per_second": 4.55,
|
| 8 |
+
"total_flos": 4.572150213593088e+17,
|
| 9 |
+
"train_loss": 0.07446861431002617,
|
| 10 |
+
"train_runtime": 420.0976,
|
| 11 |
+
"train_samples_per_second": 14.044,
|
| 12 |
+
"train_steps_per_second": 0.238
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 100.0,
|
| 3 |
+
"eval_accuracy": 0.7272727272727273,
|
| 4 |
+
"eval_loss": 0.9744274020195007,
|
| 5 |
+
"eval_runtime": 0.2198,
|
| 6 |
+
"eval_samples_per_second": 50.054,
|
| 7 |
+
"eval_steps_per_second": 4.55
|
| 8 |
+
}
|
runs/May22_15-53-51_927069b479b5/events.out.tfevents.1716393675.927069b479b5.252.37
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9ccbe782e721926adabe212c1aa5234ef7dfa55042fddf5051ed295fbd4aeb4
|
| 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": 0.07446861431002617,
|
| 5 |
+
"train_runtime": 420.0976,
|
| 6 |
+
"train_samples_per_second": 14.044,
|
| 7 |
+
"train_steps_per_second": 0.238
|
| 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-fold1/checkpoint-3",
|
| 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": 0.09090909090909091,
|
| 14 |
+
"eval_loss": 1.2771788835525513,
|
| 15 |
+
"eval_runtime": 0.1734,
|
| 16 |
+
"eval_samples_per_second": 63.434,
|
| 17 |
+
"eval_steps_per_second": 5.767,
|
| 18 |
+
"step": 1
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 2.0,
|
| 22 |
+
"eval_accuracy": 0.18181818181818182,
|
| 23 |
+
"eval_loss": 1.1447755098342896,
|
| 24 |
+
"eval_runtime": 0.1646,
|
| 25 |
+
"eval_samples_per_second": 66.839,
|
| 26 |
+
"eval_steps_per_second": 6.076,
|
| 27 |
+
"step": 2
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 3.0,
|
| 31 |
+
"eval_accuracy": 0.7272727272727273,
|
| 32 |
+
"eval_loss": 0.9744274020195007,
|
| 33 |
+
"eval_runtime": 0.1717,
|
| 34 |
+
"eval_samples_per_second": 64.083,
|
| 35 |
+
"eval_steps_per_second": 5.826,
|
| 36 |
+
"step": 3
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 4.0,
|
| 40 |
+
"eval_accuracy": 0.7272727272727273,
|
| 41 |
+
"eval_loss": 0.9233787655830383,
|
| 42 |
+
"eval_runtime": 0.172,
|
| 43 |
+
"eval_samples_per_second": 63.969,
|
| 44 |
+
"eval_steps_per_second": 5.815,
|
| 45 |
+
"step": 4
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 5.0,
|
| 49 |
+
"eval_accuracy": 0.7272727272727273,
|
| 50 |
+
"eval_loss": 1.0760316848754883,
|
| 51 |
+
"eval_runtime": 0.1729,
|
| 52 |
+
"eval_samples_per_second": 63.616,
|
| 53 |
+
"eval_steps_per_second": 5.783,
|
| 54 |
+
"step": 5
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 6.0,
|
| 58 |
+
"eval_accuracy": 0.7272727272727273,
|
| 59 |
+
"eval_loss": 1.3222259283065796,
|
| 60 |
+
"eval_runtime": 0.1683,
|
| 61 |
+
"eval_samples_per_second": 65.343,
|
| 62 |
+
"eval_steps_per_second": 5.94,
|
| 63 |
+
"step": 6
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 7.0,
|
| 67 |
+
"eval_accuracy": 0.7272727272727273,
|
| 68 |
+
"eval_loss": 1.5247870683670044,
|
| 69 |
+
"eval_runtime": 0.1317,
|
| 70 |
+
"eval_samples_per_second": 83.521,
|
| 71 |
+
"eval_steps_per_second": 7.593,
|
| 72 |
+
"step": 7
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 8.0,
|
| 76 |
+
"eval_accuracy": 0.7272727272727273,
|
| 77 |
+
"eval_loss": 1.6138737201690674,
|
| 78 |
+
"eval_runtime": 0.1738,
|
| 79 |
+
"eval_samples_per_second": 63.299,
|
| 80 |
+
"eval_steps_per_second": 5.754,
|
| 81 |
+
"step": 8
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 9.0,
|
| 85 |
+
"eval_accuracy": 0.7272727272727273,
|
| 86 |
+
"eval_loss": 1.671146035194397,
|
| 87 |
+
"eval_runtime": 0.1801,
|
| 88 |
+
"eval_samples_per_second": 61.094,
|
| 89 |
+
"eval_steps_per_second": 5.554,
|
| 90 |
+
"step": 9
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 10.0,
|
| 94 |
+
"grad_norm": 1.1924768686294556,
|
| 95 |
+
"learning_rate": 5e-05,
|
| 96 |
+
"loss": 0.3554,
|
| 97 |
+
"step": 10
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 10.0,
|
| 101 |
+
"eval_accuracy": 0.7272727272727273,
|
| 102 |
+
"eval_loss": 1.7354072332382202,
|
| 103 |
+
"eval_runtime": 0.1604,
|
| 104 |
+
"eval_samples_per_second": 68.592,
|
| 105 |
+
"eval_steps_per_second": 6.236,
|
| 106 |
+
"step": 10
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 11.0,
|
| 110 |
+
"eval_accuracy": 0.7272727272727273,
|
| 111 |
+
"eval_loss": 1.6721187829971313,
|
| 112 |
+
"eval_runtime": 0.1745,
|
| 113 |
+
"eval_samples_per_second": 63.042,
|
| 114 |
+
"eval_steps_per_second": 5.731,
|
| 115 |
+
"step": 11
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 12.0,
|
| 119 |
+
"eval_accuracy": 0.7272727272727273,
|
| 120 |
+
"eval_loss": 1.5987907648086548,
|
| 121 |
+
"eval_runtime": 0.1742,
|
| 122 |
+
"eval_samples_per_second": 63.135,
|
| 123 |
+
"eval_steps_per_second": 5.74,
|
| 124 |
+
"step": 12
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 13.0,
|
| 128 |
+
"eval_accuracy": 0.7272727272727273,
|
| 129 |
+
"eval_loss": 1.5959930419921875,
|
| 130 |
+
"eval_runtime": 0.1674,
|
| 131 |
+
"eval_samples_per_second": 65.72,
|
| 132 |
+
"eval_steps_per_second": 5.975,
|
| 133 |
+
"step": 13
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 14.0,
|
| 137 |
+
"eval_accuracy": 0.7272727272727273,
|
| 138 |
+
"eval_loss": 1.583227515220642,
|
| 139 |
+
"eval_runtime": 0.1711,
|
| 140 |
+
"eval_samples_per_second": 64.284,
|
| 141 |
+
"eval_steps_per_second": 5.844,
|
| 142 |
+
"step": 14
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 15.0,
|
| 146 |
+
"eval_accuracy": 0.7272727272727273,
|
| 147 |
+
"eval_loss": 1.568271517753601,
|
| 148 |
+
"eval_runtime": 0.17,
|
| 149 |
+
"eval_samples_per_second": 64.702,
|
| 150 |
+
"eval_steps_per_second": 5.882,
|
| 151 |
+
"step": 15
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 16.0,
|
| 155 |
+
"eval_accuracy": 0.7272727272727273,
|
| 156 |
+
"eval_loss": 1.5774298906326294,
|
| 157 |
+
"eval_runtime": 0.1701,
|
| 158 |
+
"eval_samples_per_second": 64.672,
|
| 159 |
+
"eval_steps_per_second": 5.879,
|
| 160 |
+
"step": 16
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 17.0,
|
| 164 |
+
"eval_accuracy": 0.7272727272727273,
|
| 165 |
+
"eval_loss": 1.6467945575714111,
|
| 166 |
+
"eval_runtime": 0.1692,
|
| 167 |
+
"eval_samples_per_second": 65.014,
|
| 168 |
+
"eval_steps_per_second": 5.91,
|
| 169 |
+
"step": 17
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 18.0,
|
| 173 |
+
"eval_accuracy": 0.7272727272727273,
|
| 174 |
+
"eval_loss": 1.7090667486190796,
|
| 175 |
+
"eval_runtime": 0.1688,
|
| 176 |
+
"eval_samples_per_second": 65.178,
|
| 177 |
+
"eval_steps_per_second": 5.925,
|
| 178 |
+
"step": 18
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 19.0,
|
| 182 |
+
"eval_accuracy": 0.7272727272727273,
|
| 183 |
+
"eval_loss": 1.7276203632354736,
|
| 184 |
+
"eval_runtime": 0.1682,
|
| 185 |
+
"eval_samples_per_second": 65.379,
|
| 186 |
+
"eval_steps_per_second": 5.944,
|
| 187 |
+
"step": 19
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 20.0,
|
| 191 |
+
"grad_norm": 1.0401579141616821,
|
| 192 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 193 |
+
"loss": 0.1335,
|
| 194 |
+
"step": 20
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 20.0,
|
| 198 |
+
"eval_accuracy": 0.7272727272727273,
|
| 199 |
+
"eval_loss": 1.7052208185195923,
|
| 200 |
+
"eval_runtime": 0.1669,
|
| 201 |
+
"eval_samples_per_second": 65.92,
|
| 202 |
+
"eval_steps_per_second": 5.993,
|
| 203 |
+
"step": 20
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 21.0,
|
| 207 |
+
"eval_accuracy": 0.7272727272727273,
|
| 208 |
+
"eval_loss": 1.642613172531128,
|
| 209 |
+
"eval_runtime": 0.1706,
|
| 210 |
+
"eval_samples_per_second": 64.477,
|
| 211 |
+
"eval_steps_per_second": 5.862,
|
| 212 |
+
"step": 21
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 22.0,
|
| 216 |
+
"eval_accuracy": 0.7272727272727273,
|
| 217 |
+
"eval_loss": 1.5315605401992798,
|
| 218 |
+
"eval_runtime": 0.1679,
|
| 219 |
+
"eval_samples_per_second": 65.515,
|
| 220 |
+
"eval_steps_per_second": 5.956,
|
| 221 |
+
"step": 22
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 23.0,
|
| 225 |
+
"eval_accuracy": 0.7272727272727273,
|
| 226 |
+
"eval_loss": 1.401681661605835,
|
| 227 |
+
"eval_runtime": 0.2092,
|
| 228 |
+
"eval_samples_per_second": 52.574,
|
| 229 |
+
"eval_steps_per_second": 4.779,
|
| 230 |
+
"step": 23
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 24.0,
|
| 234 |
+
"eval_accuracy": 0.7272727272727273,
|
| 235 |
+
"eval_loss": 1.300853967666626,
|
| 236 |
+
"eval_runtime": 0.1638,
|
| 237 |
+
"eval_samples_per_second": 67.161,
|
| 238 |
+
"eval_steps_per_second": 6.106,
|
| 239 |
+
"step": 24
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 25.0,
|
| 243 |
+
"eval_accuracy": 0.7272727272727273,
|
| 244 |
+
"eval_loss": 1.2863625288009644,
|
| 245 |
+
"eval_runtime": 0.1692,
|
| 246 |
+
"eval_samples_per_second": 64.994,
|
| 247 |
+
"eval_steps_per_second": 5.909,
|
| 248 |
+
"step": 25
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 26.0,
|
| 252 |
+
"eval_accuracy": 0.7272727272727273,
|
| 253 |
+
"eval_loss": 1.393377423286438,
|
| 254 |
+
"eval_runtime": 0.1719,
|
| 255 |
+
"eval_samples_per_second": 64.001,
|
| 256 |
+
"eval_steps_per_second": 5.818,
|
| 257 |
+
"step": 26
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 27.0,
|
| 261 |
+
"eval_accuracy": 0.7272727272727273,
|
| 262 |
+
"eval_loss": 1.4435607194900513,
|
| 263 |
+
"eval_runtime": 0.171,
|
| 264 |
+
"eval_samples_per_second": 64.321,
|
| 265 |
+
"eval_steps_per_second": 5.847,
|
| 266 |
+
"step": 27
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 28.0,
|
| 270 |
+
"eval_accuracy": 0.7272727272727273,
|
| 271 |
+
"eval_loss": 1.5751649141311646,
|
| 272 |
+
"eval_runtime": 0.1734,
|
| 273 |
+
"eval_samples_per_second": 63.455,
|
| 274 |
+
"eval_steps_per_second": 5.769,
|
| 275 |
+
"step": 28
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 29.0,
|
| 279 |
+
"eval_accuracy": 0.7272727272727273,
|
| 280 |
+
"eval_loss": 1.6211150884628296,
|
| 281 |
+
"eval_runtime": 0.1701,
|
| 282 |
+
"eval_samples_per_second": 64.665,
|
| 283 |
+
"eval_steps_per_second": 5.879,
|
| 284 |
+
"step": 29
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 30.0,
|
| 288 |
+
"grad_norm": 1.1806550025939941,
|
| 289 |
+
"learning_rate": 3.888888888888889e-05,
|
| 290 |
+
"loss": 0.0769,
|
| 291 |
+
"step": 30
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 30.0,
|
| 295 |
+
"eval_accuracy": 0.7272727272727273,
|
| 296 |
+
"eval_loss": 1.5944229364395142,
|
| 297 |
+
"eval_runtime": 0.1629,
|
| 298 |
+
"eval_samples_per_second": 67.545,
|
| 299 |
+
"eval_steps_per_second": 6.14,
|
| 300 |
+
"step": 30
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 31.0,
|
| 304 |
+
"eval_accuracy": 0.7272727272727273,
|
| 305 |
+
"eval_loss": 1.5282962322235107,
|
| 306 |
+
"eval_runtime": 0.1679,
|
| 307 |
+
"eval_samples_per_second": 65.5,
|
| 308 |
+
"eval_steps_per_second": 5.955,
|
| 309 |
+
"step": 31
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 32.0,
|
| 313 |
+
"eval_accuracy": 0.7272727272727273,
|
| 314 |
+
"eval_loss": 1.4341241121292114,
|
| 315 |
+
"eval_runtime": 0.1709,
|
| 316 |
+
"eval_samples_per_second": 64.372,
|
| 317 |
+
"eval_steps_per_second": 5.852,
|
| 318 |
+
"step": 32
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 33.0,
|
| 322 |
+
"eval_accuracy": 0.7272727272727273,
|
| 323 |
+
"eval_loss": 1.451222538948059,
|
| 324 |
+
"eval_runtime": 0.1774,
|
| 325 |
+
"eval_samples_per_second": 62.024,
|
| 326 |
+
"eval_steps_per_second": 5.639,
|
| 327 |
+
"step": 33
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 34.0,
|
| 331 |
+
"eval_accuracy": 0.7272727272727273,
|
| 332 |
+
"eval_loss": 1.4979816675186157,
|
| 333 |
+
"eval_runtime": 0.1698,
|
| 334 |
+
"eval_samples_per_second": 64.797,
|
| 335 |
+
"eval_steps_per_second": 5.891,
|
| 336 |
+
"step": 34
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 35.0,
|
| 340 |
+
"eval_accuracy": 0.7272727272727273,
|
| 341 |
+
"eval_loss": 1.5802719593048096,
|
| 342 |
+
"eval_runtime": 0.1718,
|
| 343 |
+
"eval_samples_per_second": 64.014,
|
| 344 |
+
"eval_steps_per_second": 5.819,
|
| 345 |
+
"step": 35
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 36.0,
|
| 349 |
+
"eval_accuracy": 0.7272727272727273,
|
| 350 |
+
"eval_loss": 1.7675877809524536,
|
| 351 |
+
"eval_runtime": 0.1737,
|
| 352 |
+
"eval_samples_per_second": 63.319,
|
| 353 |
+
"eval_steps_per_second": 5.756,
|
| 354 |
+
"step": 36
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 37.0,
|
| 358 |
+
"eval_accuracy": 0.7272727272727273,
|
| 359 |
+
"eval_loss": 1.8581143617630005,
|
| 360 |
+
"eval_runtime": 0.1763,
|
| 361 |
+
"eval_samples_per_second": 62.379,
|
| 362 |
+
"eval_steps_per_second": 5.671,
|
| 363 |
+
"step": 37
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 38.0,
|
| 367 |
+
"eval_accuracy": 0.7272727272727273,
|
| 368 |
+
"eval_loss": 1.8816009759902954,
|
| 369 |
+
"eval_runtime": 0.1739,
|
| 370 |
+
"eval_samples_per_second": 63.25,
|
| 371 |
+
"eval_steps_per_second": 5.75,
|
| 372 |
+
"step": 38
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 39.0,
|
| 376 |
+
"eval_accuracy": 0.7272727272727273,
|
| 377 |
+
"eval_loss": 1.8316550254821777,
|
| 378 |
+
"eval_runtime": 0.1703,
|
| 379 |
+
"eval_samples_per_second": 64.601,
|
| 380 |
+
"eval_steps_per_second": 5.873,
|
| 381 |
+
"step": 39
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 40.0,
|
| 385 |
+
"grad_norm": 0.9434149861335754,
|
| 386 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 387 |
+
"loss": 0.0505,
|
| 388 |
+
"step": 40
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 40.0,
|
| 392 |
+
"eval_accuracy": 0.7272727272727273,
|
| 393 |
+
"eval_loss": 1.7445045709609985,
|
| 394 |
+
"eval_runtime": 0.1655,
|
| 395 |
+
"eval_samples_per_second": 66.473,
|
| 396 |
+
"eval_steps_per_second": 6.043,
|
| 397 |
+
"step": 40
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 41.0,
|
| 401 |
+
"eval_accuracy": 0.7272727272727273,
|
| 402 |
+
"eval_loss": 1.6965172290802002,
|
| 403 |
+
"eval_runtime": 0.1727,
|
| 404 |
+
"eval_samples_per_second": 63.702,
|
| 405 |
+
"eval_steps_per_second": 5.791,
|
| 406 |
+
"step": 41
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 42.0,
|
| 410 |
+
"eval_accuracy": 0.7272727272727273,
|
| 411 |
+
"eval_loss": 1.721003770828247,
|
| 412 |
+
"eval_runtime": 0.1728,
|
| 413 |
+
"eval_samples_per_second": 63.673,
|
| 414 |
+
"eval_steps_per_second": 5.788,
|
| 415 |
+
"step": 42
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 43.0,
|
| 419 |
+
"eval_accuracy": 0.7272727272727273,
|
| 420 |
+
"eval_loss": 1.6903266906738281,
|
| 421 |
+
"eval_runtime": 0.1704,
|
| 422 |
+
"eval_samples_per_second": 64.544,
|
| 423 |
+
"eval_steps_per_second": 5.868,
|
| 424 |
+
"step": 43
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 44.0,
|
| 428 |
+
"eval_accuracy": 0.7272727272727273,
|
| 429 |
+
"eval_loss": 1.694361925125122,
|
| 430 |
+
"eval_runtime": 0.1732,
|
| 431 |
+
"eval_samples_per_second": 63.528,
|
| 432 |
+
"eval_steps_per_second": 5.775,
|
| 433 |
+
"step": 44
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 45.0,
|
| 437 |
+
"eval_accuracy": 0.7272727272727273,
|
| 438 |
+
"eval_loss": 1.6923259496688843,
|
| 439 |
+
"eval_runtime": 0.1663,
|
| 440 |
+
"eval_samples_per_second": 66.135,
|
| 441 |
+
"eval_steps_per_second": 6.012,
|
| 442 |
+
"step": 45
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 46.0,
|
| 446 |
+
"eval_accuracy": 0.7272727272727273,
|
| 447 |
+
"eval_loss": 1.7470028400421143,
|
| 448 |
+
"eval_runtime": 0.1683,
|
| 449 |
+
"eval_samples_per_second": 65.348,
|
| 450 |
+
"eval_steps_per_second": 5.941,
|
| 451 |
+
"step": 46
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 47.0,
|
| 455 |
+
"eval_accuracy": 0.7272727272727273,
|
| 456 |
+
"eval_loss": 1.7501949071884155,
|
| 457 |
+
"eval_runtime": 0.1672,
|
| 458 |
+
"eval_samples_per_second": 65.8,
|
| 459 |
+
"eval_steps_per_second": 5.982,
|
| 460 |
+
"step": 47
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 48.0,
|
| 464 |
+
"eval_accuracy": 0.7272727272727273,
|
| 465 |
+
"eval_loss": 1.7738779783248901,
|
| 466 |
+
"eval_runtime": 0.174,
|
| 467 |
+
"eval_samples_per_second": 63.224,
|
| 468 |
+
"eval_steps_per_second": 5.748,
|
| 469 |
+
"step": 48
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 49.0,
|
| 473 |
+
"eval_accuracy": 0.7272727272727273,
|
| 474 |
+
"eval_loss": 1.7819253206253052,
|
| 475 |
+
"eval_runtime": 0.1701,
|
| 476 |
+
"eval_samples_per_second": 64.658,
|
| 477 |
+
"eval_steps_per_second": 5.878,
|
| 478 |
+
"step": 49
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 50.0,
|
| 482 |
+
"grad_norm": 0.3251829743385315,
|
| 483 |
+
"learning_rate": 2.777777777777778e-05,
|
| 484 |
+
"loss": 0.0255,
|
| 485 |
+
"step": 50
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 50.0,
|
| 489 |
+
"eval_accuracy": 0.7272727272727273,
|
| 490 |
+
"eval_loss": 1.8199766874313354,
|
| 491 |
+
"eval_runtime": 0.1617,
|
| 492 |
+
"eval_samples_per_second": 68.041,
|
| 493 |
+
"eval_steps_per_second": 6.186,
|
| 494 |
+
"step": 50
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 51.0,
|
| 498 |
+
"eval_accuracy": 0.7272727272727273,
|
| 499 |
+
"eval_loss": 1.8121682405471802,
|
| 500 |
+
"eval_runtime": 0.1715,
|
| 501 |
+
"eval_samples_per_second": 64.129,
|
| 502 |
+
"eval_steps_per_second": 5.83,
|
| 503 |
+
"step": 51
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 52.0,
|
| 507 |
+
"eval_accuracy": 0.7272727272727273,
|
| 508 |
+
"eval_loss": 1.7939274311065674,
|
| 509 |
+
"eval_runtime": 0.1789,
|
| 510 |
+
"eval_samples_per_second": 61.501,
|
| 511 |
+
"eval_steps_per_second": 5.591,
|
| 512 |
+
"step": 52
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 53.0,
|
| 516 |
+
"eval_accuracy": 0.7272727272727273,
|
| 517 |
+
"eval_loss": 1.7736003398895264,
|
| 518 |
+
"eval_runtime": 0.1717,
|
| 519 |
+
"eval_samples_per_second": 64.058,
|
| 520 |
+
"eval_steps_per_second": 5.823,
|
| 521 |
+
"step": 53
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 54.0,
|
| 525 |
+
"eval_accuracy": 0.7272727272727273,
|
| 526 |
+
"eval_loss": 1.7411243915557861,
|
| 527 |
+
"eval_runtime": 0.17,
|
| 528 |
+
"eval_samples_per_second": 64.709,
|
| 529 |
+
"eval_steps_per_second": 5.883,
|
| 530 |
+
"step": 54
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 55.0,
|
| 534 |
+
"eval_accuracy": 0.7272727272727273,
|
| 535 |
+
"eval_loss": 1.6772898435592651,
|
| 536 |
+
"eval_runtime": 0.1718,
|
| 537 |
+
"eval_samples_per_second": 64.013,
|
| 538 |
+
"eval_steps_per_second": 5.819,
|
| 539 |
+
"step": 55
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 56.0,
|
| 543 |
+
"eval_accuracy": 0.7272727272727273,
|
| 544 |
+
"eval_loss": 1.6555858850479126,
|
| 545 |
+
"eval_runtime": 0.172,
|
| 546 |
+
"eval_samples_per_second": 63.951,
|
| 547 |
+
"eval_steps_per_second": 5.814,
|
| 548 |
+
"step": 56
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 57.0,
|
| 552 |
+
"eval_accuracy": 0.7272727272727273,
|
| 553 |
+
"eval_loss": 1.6766685247421265,
|
| 554 |
+
"eval_runtime": 0.1687,
|
| 555 |
+
"eval_samples_per_second": 65.223,
|
| 556 |
+
"eval_steps_per_second": 5.929,
|
| 557 |
+
"step": 57
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 58.0,
|
| 561 |
+
"eval_accuracy": 0.7272727272727273,
|
| 562 |
+
"eval_loss": 1.6623153686523438,
|
| 563 |
+
"eval_runtime": 0.1813,
|
| 564 |
+
"eval_samples_per_second": 60.676,
|
| 565 |
+
"eval_steps_per_second": 5.516,
|
| 566 |
+
"step": 58
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 59.0,
|
| 570 |
+
"eval_accuracy": 0.7272727272727273,
|
| 571 |
+
"eval_loss": 1.6553212404251099,
|
| 572 |
+
"eval_runtime": 0.1694,
|
| 573 |
+
"eval_samples_per_second": 64.947,
|
| 574 |
+
"eval_steps_per_second": 5.904,
|
| 575 |
+
"step": 59
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 60.0,
|
| 579 |
+
"grad_norm": 0.4616081416606903,
|
| 580 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 581 |
+
"loss": 0.0227,
|
| 582 |
+
"step": 60
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 60.0,
|
| 586 |
+
"eval_accuracy": 0.7272727272727273,
|
| 587 |
+
"eval_loss": 1.6682250499725342,
|
| 588 |
+
"eval_runtime": 0.1787,
|
| 589 |
+
"eval_samples_per_second": 61.567,
|
| 590 |
+
"eval_steps_per_second": 5.597,
|
| 591 |
+
"step": 60
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 61.0,
|
| 595 |
+
"eval_accuracy": 0.7272727272727273,
|
| 596 |
+
"eval_loss": 1.62090265750885,
|
| 597 |
+
"eval_runtime": 0.1815,
|
| 598 |
+
"eval_samples_per_second": 60.623,
|
| 599 |
+
"eval_steps_per_second": 5.511,
|
| 600 |
+
"step": 61
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 62.0,
|
| 604 |
+
"eval_accuracy": 0.7272727272727273,
|
| 605 |
+
"eval_loss": 1.6187800168991089,
|
| 606 |
+
"eval_runtime": 0.1699,
|
| 607 |
+
"eval_samples_per_second": 64.734,
|
| 608 |
+
"eval_steps_per_second": 5.885,
|
| 609 |
+
"step": 62
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 63.0,
|
| 613 |
+
"eval_accuracy": 0.7272727272727273,
|
| 614 |
+
"eval_loss": 1.6919440031051636,
|
| 615 |
+
"eval_runtime": 0.1718,
|
| 616 |
+
"eval_samples_per_second": 64.021,
|
| 617 |
+
"eval_steps_per_second": 5.82,
|
| 618 |
+
"step": 63
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 64.0,
|
| 622 |
+
"eval_accuracy": 0.7272727272727273,
|
| 623 |
+
"eval_loss": 1.7957440614700317,
|
| 624 |
+
"eval_runtime": 0.171,
|
| 625 |
+
"eval_samples_per_second": 64.31,
|
| 626 |
+
"eval_steps_per_second": 5.846,
|
| 627 |
+
"step": 64
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 65.0,
|
| 631 |
+
"eval_accuracy": 0.7272727272727273,
|
| 632 |
+
"eval_loss": 1.8749808073043823,
|
| 633 |
+
"eval_runtime": 0.1689,
|
| 634 |
+
"eval_samples_per_second": 65.119,
|
| 635 |
+
"eval_steps_per_second": 5.92,
|
| 636 |
+
"step": 65
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 66.0,
|
| 640 |
+
"eval_accuracy": 0.7272727272727273,
|
| 641 |
+
"eval_loss": 1.9156414270401,
|
| 642 |
+
"eval_runtime": 0.1703,
|
| 643 |
+
"eval_samples_per_second": 64.59,
|
| 644 |
+
"eval_steps_per_second": 5.872,
|
| 645 |
+
"step": 66
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 67.0,
|
| 649 |
+
"eval_accuracy": 0.7272727272727273,
|
| 650 |
+
"eval_loss": 1.9163463115692139,
|
| 651 |
+
"eval_runtime": 0.1741,
|
| 652 |
+
"eval_samples_per_second": 63.174,
|
| 653 |
+
"eval_steps_per_second": 5.743,
|
| 654 |
+
"step": 67
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 68.0,
|
| 658 |
+
"eval_accuracy": 0.7272727272727273,
|
| 659 |
+
"eval_loss": 1.8968899250030518,
|
| 660 |
+
"eval_runtime": 0.1686,
|
| 661 |
+
"eval_samples_per_second": 65.251,
|
| 662 |
+
"eval_steps_per_second": 5.932,
|
| 663 |
+
"step": 68
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 69.0,
|
| 667 |
+
"eval_accuracy": 0.7272727272727273,
|
| 668 |
+
"eval_loss": 1.881422519683838,
|
| 669 |
+
"eval_runtime": 0.171,
|
| 670 |
+
"eval_samples_per_second": 64.319,
|
| 671 |
+
"eval_steps_per_second": 5.847,
|
| 672 |
+
"step": 69
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 70.0,
|
| 676 |
+
"grad_norm": 0.3331330716609955,
|
| 677 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 678 |
+
"loss": 0.0185,
|
| 679 |
+
"step": 70
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 70.0,
|
| 683 |
+
"eval_accuracy": 0.7272727272727273,
|
| 684 |
+
"eval_loss": 1.8714560270309448,
|
| 685 |
+
"eval_runtime": 0.1697,
|
| 686 |
+
"eval_samples_per_second": 64.821,
|
| 687 |
+
"eval_steps_per_second": 5.893,
|
| 688 |
+
"step": 70
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 71.0,
|
| 692 |
+
"eval_accuracy": 0.7272727272727273,
|
| 693 |
+
"eval_loss": 1.8891681432724,
|
| 694 |
+
"eval_runtime": 0.1694,
|
| 695 |
+
"eval_samples_per_second": 64.943,
|
| 696 |
+
"eval_steps_per_second": 5.904,
|
| 697 |
+
"step": 71
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 72.0,
|
| 701 |
+
"eval_accuracy": 0.7272727272727273,
|
| 702 |
+
"eval_loss": 1.9382548332214355,
|
| 703 |
+
"eval_runtime": 0.1738,
|
| 704 |
+
"eval_samples_per_second": 63.278,
|
| 705 |
+
"eval_steps_per_second": 5.753,
|
| 706 |
+
"step": 72
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 73.0,
|
| 710 |
+
"eval_accuracy": 0.7272727272727273,
|
| 711 |
+
"eval_loss": 1.9627383947372437,
|
| 712 |
+
"eval_runtime": 0.1697,
|
| 713 |
+
"eval_samples_per_second": 64.822,
|
| 714 |
+
"eval_steps_per_second": 5.893,
|
| 715 |
+
"step": 73
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 74.0,
|
| 719 |
+
"eval_accuracy": 0.7272727272727273,
|
| 720 |
+
"eval_loss": 2.0154221057891846,
|
| 721 |
+
"eval_runtime": 0.1705,
|
| 722 |
+
"eval_samples_per_second": 64.527,
|
| 723 |
+
"eval_steps_per_second": 5.866,
|
| 724 |
+
"step": 74
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 75.0,
|
| 728 |
+
"eval_accuracy": 0.7272727272727273,
|
| 729 |
+
"eval_loss": 2.032640218734741,
|
| 730 |
+
"eval_runtime": 0.1767,
|
| 731 |
+
"eval_samples_per_second": 62.244,
|
| 732 |
+
"eval_steps_per_second": 5.659,
|
| 733 |
+
"step": 75
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 76.0,
|
| 737 |
+
"eval_accuracy": 0.7272727272727273,
|
| 738 |
+
"eval_loss": 2.0424911975860596,
|
| 739 |
+
"eval_runtime": 0.1711,
|
| 740 |
+
"eval_samples_per_second": 64.272,
|
| 741 |
+
"eval_steps_per_second": 5.843,
|
| 742 |
+
"step": 76
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 77.0,
|
| 746 |
+
"eval_accuracy": 0.7272727272727273,
|
| 747 |
+
"eval_loss": 2.0586304664611816,
|
| 748 |
+
"eval_runtime": 0.177,
|
| 749 |
+
"eval_samples_per_second": 62.132,
|
| 750 |
+
"eval_steps_per_second": 5.648,
|
| 751 |
+
"step": 77
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 78.0,
|
| 755 |
+
"eval_accuracy": 0.7272727272727273,
|
| 756 |
+
"eval_loss": 2.058166265487671,
|
| 757 |
+
"eval_runtime": 0.1793,
|
| 758 |
+
"eval_samples_per_second": 61.357,
|
| 759 |
+
"eval_steps_per_second": 5.578,
|
| 760 |
+
"step": 78
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 79.0,
|
| 764 |
+
"eval_accuracy": 0.7272727272727273,
|
| 765 |
+
"eval_loss": 2.086315870285034,
|
| 766 |
+
"eval_runtime": 0.1722,
|
| 767 |
+
"eval_samples_per_second": 63.888,
|
| 768 |
+
"eval_steps_per_second": 5.808,
|
| 769 |
+
"step": 79
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 80.0,
|
| 773 |
+
"grad_norm": 0.5901564955711365,
|
| 774 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 775 |
+
"loss": 0.0246,
|
| 776 |
+
"step": 80
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 80.0,
|
| 780 |
+
"eval_accuracy": 0.7272727272727273,
|
| 781 |
+
"eval_loss": 2.123337507247925,
|
| 782 |
+
"eval_runtime": 0.168,
|
| 783 |
+
"eval_samples_per_second": 65.467,
|
| 784 |
+
"eval_steps_per_second": 5.952,
|
| 785 |
+
"step": 80
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 81.0,
|
| 789 |
+
"eval_accuracy": 0.7272727272727273,
|
| 790 |
+
"eval_loss": 2.1527483463287354,
|
| 791 |
+
"eval_runtime": 0.1714,
|
| 792 |
+
"eval_samples_per_second": 64.176,
|
| 793 |
+
"eval_steps_per_second": 5.834,
|
| 794 |
+
"step": 81
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 82.0,
|
| 798 |
+
"eval_accuracy": 0.7272727272727273,
|
| 799 |
+
"eval_loss": 2.176025152206421,
|
| 800 |
+
"eval_runtime": 0.177,
|
| 801 |
+
"eval_samples_per_second": 62.154,
|
| 802 |
+
"eval_steps_per_second": 5.65,
|
| 803 |
+
"step": 82
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 83.0,
|
| 807 |
+
"eval_accuracy": 0.7272727272727273,
|
| 808 |
+
"eval_loss": 2.190654993057251,
|
| 809 |
+
"eval_runtime": 0.1738,
|
| 810 |
+
"eval_samples_per_second": 63.301,
|
| 811 |
+
"eval_steps_per_second": 5.755,
|
| 812 |
+
"step": 83
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 84.0,
|
| 816 |
+
"eval_accuracy": 0.7272727272727273,
|
| 817 |
+
"eval_loss": 2.1858766078948975,
|
| 818 |
+
"eval_runtime": 0.179,
|
| 819 |
+
"eval_samples_per_second": 61.465,
|
| 820 |
+
"eval_steps_per_second": 5.588,
|
| 821 |
+
"step": 84
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 85.0,
|
| 825 |
+
"eval_accuracy": 0.7272727272727273,
|
| 826 |
+
"eval_loss": 2.165440320968628,
|
| 827 |
+
"eval_runtime": 0.1802,
|
| 828 |
+
"eval_samples_per_second": 61.042,
|
| 829 |
+
"eval_steps_per_second": 5.549,
|
| 830 |
+
"step": 85
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 86.0,
|
| 834 |
+
"eval_accuracy": 0.7272727272727273,
|
| 835 |
+
"eval_loss": 2.1478655338287354,
|
| 836 |
+
"eval_runtime": 0.1681,
|
| 837 |
+
"eval_samples_per_second": 65.441,
|
| 838 |
+
"eval_steps_per_second": 5.949,
|
| 839 |
+
"step": 86
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 87.0,
|
| 843 |
+
"eval_accuracy": 0.7272727272727273,
|
| 844 |
+
"eval_loss": 2.1194212436676025,
|
| 845 |
+
"eval_runtime": 0.1706,
|
| 846 |
+
"eval_samples_per_second": 64.486,
|
| 847 |
+
"eval_steps_per_second": 5.862,
|
| 848 |
+
"step": 87
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 88.0,
|
| 852 |
+
"eval_accuracy": 0.7272727272727273,
|
| 853 |
+
"eval_loss": 2.1058995723724365,
|
| 854 |
+
"eval_runtime": 0.173,
|
| 855 |
+
"eval_samples_per_second": 63.597,
|
| 856 |
+
"eval_steps_per_second": 5.782,
|
| 857 |
+
"step": 88
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 89.0,
|
| 861 |
+
"eval_accuracy": 0.7272727272727273,
|
| 862 |
+
"eval_loss": 2.103247880935669,
|
| 863 |
+
"eval_runtime": 0.1721,
|
| 864 |
+
"eval_samples_per_second": 63.931,
|
| 865 |
+
"eval_steps_per_second": 5.812,
|
| 866 |
+
"step": 89
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 90.0,
|
| 870 |
+
"grad_norm": 1.2021247148513794,
|
| 871 |
+
"learning_rate": 5.555555555555556e-06,
|
| 872 |
+
"loss": 0.0228,
|
| 873 |
+
"step": 90
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 90.0,
|
| 877 |
+
"eval_accuracy": 0.7272727272727273,
|
| 878 |
+
"eval_loss": 2.0998663902282715,
|
| 879 |
+
"eval_runtime": 0.1654,
|
| 880 |
+
"eval_samples_per_second": 66.509,
|
| 881 |
+
"eval_steps_per_second": 6.046,
|
| 882 |
+
"step": 90
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 91.0,
|
| 886 |
+
"eval_accuracy": 0.7272727272727273,
|
| 887 |
+
"eval_loss": 2.1037116050720215,
|
| 888 |
+
"eval_runtime": 0.1718,
|
| 889 |
+
"eval_samples_per_second": 64.033,
|
| 890 |
+
"eval_steps_per_second": 5.821,
|
| 891 |
+
"step": 91
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 92.0,
|
| 895 |
+
"eval_accuracy": 0.7272727272727273,
|
| 896 |
+
"eval_loss": 2.1025755405426025,
|
| 897 |
+
"eval_runtime": 0.175,
|
| 898 |
+
"eval_samples_per_second": 62.874,
|
| 899 |
+
"eval_steps_per_second": 5.716,
|
| 900 |
+
"step": 92
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 93.0,
|
| 904 |
+
"eval_accuracy": 0.7272727272727273,
|
| 905 |
+
"eval_loss": 2.1132094860076904,
|
| 906 |
+
"eval_runtime": 0.1668,
|
| 907 |
+
"eval_samples_per_second": 65.929,
|
| 908 |
+
"eval_steps_per_second": 5.994,
|
| 909 |
+
"step": 93
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 94.0,
|
| 913 |
+
"eval_accuracy": 0.7272727272727273,
|
| 914 |
+
"eval_loss": 2.1301839351654053,
|
| 915 |
+
"eval_runtime": 0.171,
|
| 916 |
+
"eval_samples_per_second": 64.331,
|
| 917 |
+
"eval_steps_per_second": 5.848,
|
| 918 |
+
"step": 94
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 95.0,
|
| 922 |
+
"eval_accuracy": 0.7272727272727273,
|
| 923 |
+
"eval_loss": 2.1452560424804688,
|
| 924 |
+
"eval_runtime": 0.1758,
|
| 925 |
+
"eval_samples_per_second": 62.58,
|
| 926 |
+
"eval_steps_per_second": 5.689,
|
| 927 |
+
"step": 95
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 96.0,
|
| 931 |
+
"eval_accuracy": 0.7272727272727273,
|
| 932 |
+
"eval_loss": 2.163395643234253,
|
| 933 |
+
"eval_runtime": 0.1756,
|
| 934 |
+
"eval_samples_per_second": 62.64,
|
| 935 |
+
"eval_steps_per_second": 5.695,
|
| 936 |
+
"step": 96
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 97.0,
|
| 940 |
+
"eval_accuracy": 0.7272727272727273,
|
| 941 |
+
"eval_loss": 2.1761701107025146,
|
| 942 |
+
"eval_runtime": 0.1744,
|
| 943 |
+
"eval_samples_per_second": 63.075,
|
| 944 |
+
"eval_steps_per_second": 5.734,
|
| 945 |
+
"step": 97
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 98.0,
|
| 949 |
+
"eval_accuracy": 0.7272727272727273,
|
| 950 |
+
"eval_loss": 2.1859476566314697,
|
| 951 |
+
"eval_runtime": 0.1746,
|
| 952 |
+
"eval_samples_per_second": 63.0,
|
| 953 |
+
"eval_steps_per_second": 5.727,
|
| 954 |
+
"step": 98
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 99.0,
|
| 958 |
+
"eval_accuracy": 0.7272727272727273,
|
| 959 |
+
"eval_loss": 2.1915647983551025,
|
| 960 |
+
"eval_runtime": 0.1687,
|
| 961 |
+
"eval_samples_per_second": 65.197,
|
| 962 |
+
"eval_steps_per_second": 5.927,
|
| 963 |
+
"step": 99
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 100.0,
|
| 967 |
+
"grad_norm": 1.034210205078125,
|
| 968 |
+
"learning_rate": 0.0,
|
| 969 |
+
"loss": 0.0142,
|
| 970 |
+
"step": 100
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 100.0,
|
| 974 |
+
"eval_accuracy": 0.7272727272727273,
|
| 975 |
+
"eval_loss": 2.193308115005493,
|
| 976 |
+
"eval_runtime": 0.1657,
|
| 977 |
+
"eval_samples_per_second": 66.395,
|
| 978 |
+
"eval_steps_per_second": 6.036,
|
| 979 |
+
"step": 100
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"epoch": 100.0,
|
| 983 |
+
"step": 100,
|
| 984 |
+
"total_flos": 4.572150213593088e+17,
|
| 985 |
+
"train_loss": 0.07446861431002617,
|
| 986 |
+
"train_runtime": 420.0976,
|
| 987 |
+
"train_samples_per_second": 14.044,
|
| 988 |
+
"train_steps_per_second": 0.238
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 100.0,
|
| 992 |
+
"eval_accuracy": 0.7272727272727273,
|
| 993 |
+
"eval_loss": 0.9744274020195007,
|
| 994 |
+
"eval_runtime": 0.2198,
|
| 995 |
+
"eval_samples_per_second": 50.054,
|
| 996 |
+
"eval_steps_per_second": 4.55,
|
| 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 |
+
}
|