End of training
Browse files- README.md +1 -1
- all_results.json +13 -0
- eval_results.json +8 -0
- runs/May23_15-11-04_2bc4f829fe52/events.out.tfevents.1716477514.2bc4f829fe52.989.31 +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 [microsoft/beit-base-patch16-224](https://huggingface.co/microsoft/beit-base-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 [microsoft/beit-base-patch16-224](https://huggingface.co/microsoft/beit-base-patch16-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.9074
|
| 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": 0.9074404239654541,
|
| 5 |
+
"eval_runtime": 0.218,
|
| 6 |
+
"eval_samples_per_second": 50.454,
|
| 7 |
+
"eval_steps_per_second": 4.587,
|
| 8 |
+
"total_flos": 4.570114227259392e+17,
|
| 9 |
+
"train_loss": 0.09848821982741356,
|
| 10 |
+
"train_runtime": 419.3344,
|
| 11 |
+
"train_samples_per_second": 14.07,
|
| 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": 0.9074404239654541,
|
| 5 |
+
"eval_runtime": 0.218,
|
| 6 |
+
"eval_samples_per_second": 50.454,
|
| 7 |
+
"eval_steps_per_second": 4.587
|
| 8 |
+
}
|
runs/May23_15-11-04_2bc4f829fe52/events.out.tfevents.1716477514.2bc4f829fe52.989.31
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0d26c4147d6739253d96fb4cb3df9a78cb50d4b7397b8862ceb8e82a6794652
|
| 3 |
+
size 405
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 100.0,
|
| 3 |
+
"total_flos": 4.570114227259392e+17,
|
| 4 |
+
"train_loss": 0.09848821982741356,
|
| 5 |
+
"train_runtime": 419.3344,
|
| 6 |
+
"train_samples_per_second": 14.07,
|
| 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": "beit-base-patch16-224-hasta-85-fold1/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": 1.4041039943695068,
|
| 15 |
+
"eval_runtime": 0.1564,
|
| 16 |
+
"eval_samples_per_second": 70.351,
|
| 17 |
+
"eval_steps_per_second": 6.396,
|
| 18 |
+
"step": 1
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 2.0,
|
| 22 |
+
"eval_accuracy": 0.5454545454545454,
|
| 23 |
+
"eval_loss": 1.1167134046554565,
|
| 24 |
+
"eval_runtime": 0.1613,
|
| 25 |
+
"eval_samples_per_second": 68.177,
|
| 26 |
+
"eval_steps_per_second": 6.198,
|
| 27 |
+
"step": 2
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 3.0,
|
| 31 |
+
"eval_accuracy": 0.6363636363636364,
|
| 32 |
+
"eval_loss": 0.7943854928016663,
|
| 33 |
+
"eval_runtime": 0.1622,
|
| 34 |
+
"eval_samples_per_second": 67.81,
|
| 35 |
+
"eval_steps_per_second": 6.165,
|
| 36 |
+
"step": 3
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 4.0,
|
| 40 |
+
"eval_accuracy": 0.7272727272727273,
|
| 41 |
+
"eval_loss": 0.9074404239654541,
|
| 42 |
+
"eval_runtime": 0.1651,
|
| 43 |
+
"eval_samples_per_second": 66.609,
|
| 44 |
+
"eval_steps_per_second": 6.055,
|
| 45 |
+
"step": 4
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 5.0,
|
| 49 |
+
"eval_accuracy": 0.7272727272727273,
|
| 50 |
+
"eval_loss": 1.3599826097488403,
|
| 51 |
+
"eval_runtime": 0.163,
|
| 52 |
+
"eval_samples_per_second": 67.502,
|
| 53 |
+
"eval_steps_per_second": 6.137,
|
| 54 |
+
"step": 5
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 6.0,
|
| 58 |
+
"eval_accuracy": 0.7272727272727273,
|
| 59 |
+
"eval_loss": 1.6643478870391846,
|
| 60 |
+
"eval_runtime": 0.1618,
|
| 61 |
+
"eval_samples_per_second": 68.001,
|
| 62 |
+
"eval_steps_per_second": 6.182,
|
| 63 |
+
"step": 6
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 7.0,
|
| 67 |
+
"eval_accuracy": 0.7272727272727273,
|
| 68 |
+
"eval_loss": 1.6410090923309326,
|
| 69 |
+
"eval_runtime": 0.1639,
|
| 70 |
+
"eval_samples_per_second": 67.133,
|
| 71 |
+
"eval_steps_per_second": 6.103,
|
| 72 |
+
"step": 7
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 8.0,
|
| 76 |
+
"eval_accuracy": 0.7272727272727273,
|
| 77 |
+
"eval_loss": 1.4549148082733154,
|
| 78 |
+
"eval_runtime": 0.1631,
|
| 79 |
+
"eval_samples_per_second": 67.435,
|
| 80 |
+
"eval_steps_per_second": 6.13,
|
| 81 |
+
"step": 8
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 9.0,
|
| 85 |
+
"eval_accuracy": 0.36363636363636365,
|
| 86 |
+
"eval_loss": 1.481427788734436,
|
| 87 |
+
"eval_runtime": 0.1669,
|
| 88 |
+
"eval_samples_per_second": 65.926,
|
| 89 |
+
"eval_steps_per_second": 5.993,
|
| 90 |
+
"step": 9
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 10.0,
|
| 94 |
+
"grad_norm": 5.92126989364624,
|
| 95 |
+
"learning_rate": 5e-05,
|
| 96 |
+
"loss": 0.4133,
|
| 97 |
+
"step": 10
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 10.0,
|
| 101 |
+
"eval_accuracy": 0.6363636363636364,
|
| 102 |
+
"eval_loss": 1.2719258069992065,
|
| 103 |
+
"eval_runtime": 0.1585,
|
| 104 |
+
"eval_samples_per_second": 69.4,
|
| 105 |
+
"eval_steps_per_second": 6.309,
|
| 106 |
+
"step": 10
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 11.0,
|
| 110 |
+
"eval_accuracy": 0.7272727272727273,
|
| 111 |
+
"eval_loss": 1.0360393524169922,
|
| 112 |
+
"eval_runtime": 0.1623,
|
| 113 |
+
"eval_samples_per_second": 67.778,
|
| 114 |
+
"eval_steps_per_second": 6.162,
|
| 115 |
+
"step": 11
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 12.0,
|
| 119 |
+
"eval_accuracy": 0.7272727272727273,
|
| 120 |
+
"eval_loss": 1.0690698623657227,
|
| 121 |
+
"eval_runtime": 0.1755,
|
| 122 |
+
"eval_samples_per_second": 62.693,
|
| 123 |
+
"eval_steps_per_second": 5.699,
|
| 124 |
+
"step": 12
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 13.0,
|
| 128 |
+
"eval_accuracy": 0.7272727272727273,
|
| 129 |
+
"eval_loss": 0.9527618288993835,
|
| 130 |
+
"eval_runtime": 0.1656,
|
| 131 |
+
"eval_samples_per_second": 66.416,
|
| 132 |
+
"eval_steps_per_second": 6.038,
|
| 133 |
+
"step": 13
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 14.0,
|
| 137 |
+
"eval_accuracy": 0.7272727272727273,
|
| 138 |
+
"eval_loss": 1.0429974794387817,
|
| 139 |
+
"eval_runtime": 0.1666,
|
| 140 |
+
"eval_samples_per_second": 66.046,
|
| 141 |
+
"eval_steps_per_second": 6.004,
|
| 142 |
+
"step": 14
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 15.0,
|
| 146 |
+
"eval_accuracy": 0.7272727272727273,
|
| 147 |
+
"eval_loss": 1.3220728635787964,
|
| 148 |
+
"eval_runtime": 0.1667,
|
| 149 |
+
"eval_samples_per_second": 66.001,
|
| 150 |
+
"eval_steps_per_second": 6.0,
|
| 151 |
+
"step": 15
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 16.0,
|
| 155 |
+
"eval_accuracy": 0.7272727272727273,
|
| 156 |
+
"eval_loss": 1.523647665977478,
|
| 157 |
+
"eval_runtime": 0.1662,
|
| 158 |
+
"eval_samples_per_second": 66.196,
|
| 159 |
+
"eval_steps_per_second": 6.018,
|
| 160 |
+
"step": 16
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 17.0,
|
| 164 |
+
"eval_accuracy": 0.7272727272727273,
|
| 165 |
+
"eval_loss": 1.5914199352264404,
|
| 166 |
+
"eval_runtime": 0.1656,
|
| 167 |
+
"eval_samples_per_second": 66.437,
|
| 168 |
+
"eval_steps_per_second": 6.04,
|
| 169 |
+
"step": 17
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 18.0,
|
| 173 |
+
"eval_accuracy": 0.7272727272727273,
|
| 174 |
+
"eval_loss": 1.5015144348144531,
|
| 175 |
+
"eval_runtime": 0.1626,
|
| 176 |
+
"eval_samples_per_second": 67.653,
|
| 177 |
+
"eval_steps_per_second": 6.15,
|
| 178 |
+
"step": 18
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 19.0,
|
| 182 |
+
"eval_accuracy": 0.7272727272727273,
|
| 183 |
+
"eval_loss": 1.3859347105026245,
|
| 184 |
+
"eval_runtime": 0.1646,
|
| 185 |
+
"eval_samples_per_second": 66.841,
|
| 186 |
+
"eval_steps_per_second": 6.076,
|
| 187 |
+
"step": 19
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 20.0,
|
| 191 |
+
"grad_norm": 3.4740612506866455,
|
| 192 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 193 |
+
"loss": 0.1601,
|
| 194 |
+
"step": 20
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 20.0,
|
| 198 |
+
"eval_accuracy": 0.7272727272727273,
|
| 199 |
+
"eval_loss": 1.4513541460037231,
|
| 200 |
+
"eval_runtime": 0.1604,
|
| 201 |
+
"eval_samples_per_second": 68.587,
|
| 202 |
+
"eval_steps_per_second": 6.235,
|
| 203 |
+
"step": 20
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 21.0,
|
| 207 |
+
"eval_accuracy": 0.7272727272727273,
|
| 208 |
+
"eval_loss": 1.6168898344039917,
|
| 209 |
+
"eval_runtime": 0.1618,
|
| 210 |
+
"eval_samples_per_second": 67.969,
|
| 211 |
+
"eval_steps_per_second": 6.179,
|
| 212 |
+
"step": 21
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 22.0,
|
| 216 |
+
"eval_accuracy": 0.7272727272727273,
|
| 217 |
+
"eval_loss": 1.522349238395691,
|
| 218 |
+
"eval_runtime": 0.1647,
|
| 219 |
+
"eval_samples_per_second": 66.798,
|
| 220 |
+
"eval_steps_per_second": 6.073,
|
| 221 |
+
"step": 22
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 23.0,
|
| 225 |
+
"eval_accuracy": 0.7272727272727273,
|
| 226 |
+
"eval_loss": 1.4171791076660156,
|
| 227 |
+
"eval_runtime": 0.1698,
|
| 228 |
+
"eval_samples_per_second": 64.781,
|
| 229 |
+
"eval_steps_per_second": 5.889,
|
| 230 |
+
"step": 23
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 24.0,
|
| 234 |
+
"eval_accuracy": 0.6363636363636364,
|
| 235 |
+
"eval_loss": 1.475338339805603,
|
| 236 |
+
"eval_runtime": 0.1633,
|
| 237 |
+
"eval_samples_per_second": 67.361,
|
| 238 |
+
"eval_steps_per_second": 6.124,
|
| 239 |
+
"step": 24
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 25.0,
|
| 243 |
+
"eval_accuracy": 0.7272727272727273,
|
| 244 |
+
"eval_loss": 1.5207356214523315,
|
| 245 |
+
"eval_runtime": 0.16,
|
| 246 |
+
"eval_samples_per_second": 68.731,
|
| 247 |
+
"eval_steps_per_second": 6.248,
|
| 248 |
+
"step": 25
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 26.0,
|
| 252 |
+
"eval_accuracy": 0.7272727272727273,
|
| 253 |
+
"eval_loss": 1.7054632902145386,
|
| 254 |
+
"eval_runtime": 0.1664,
|
| 255 |
+
"eval_samples_per_second": 66.109,
|
| 256 |
+
"eval_steps_per_second": 6.01,
|
| 257 |
+
"step": 26
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 27.0,
|
| 261 |
+
"eval_accuracy": 0.7272727272727273,
|
| 262 |
+
"eval_loss": 1.7900539636611938,
|
| 263 |
+
"eval_runtime": 0.1635,
|
| 264 |
+
"eval_samples_per_second": 67.283,
|
| 265 |
+
"eval_steps_per_second": 6.117,
|
| 266 |
+
"step": 27
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 28.0,
|
| 270 |
+
"eval_accuracy": 0.7272727272727273,
|
| 271 |
+
"eval_loss": 1.9109127521514893,
|
| 272 |
+
"eval_runtime": 0.1698,
|
| 273 |
+
"eval_samples_per_second": 64.798,
|
| 274 |
+
"eval_steps_per_second": 5.891,
|
| 275 |
+
"step": 28
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 29.0,
|
| 279 |
+
"eval_accuracy": 0.7272727272727273,
|
| 280 |
+
"eval_loss": 1.8261302709579468,
|
| 281 |
+
"eval_runtime": 0.1653,
|
| 282 |
+
"eval_samples_per_second": 66.528,
|
| 283 |
+
"eval_steps_per_second": 6.048,
|
| 284 |
+
"step": 29
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 30.0,
|
| 288 |
+
"grad_norm": 2.863417863845825,
|
| 289 |
+
"learning_rate": 3.888888888888889e-05,
|
| 290 |
+
"loss": 0.1015,
|
| 291 |
+
"step": 30
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 30.0,
|
| 295 |
+
"eval_accuracy": 0.7272727272727273,
|
| 296 |
+
"eval_loss": 1.5656546354293823,
|
| 297 |
+
"eval_runtime": 0.1619,
|
| 298 |
+
"eval_samples_per_second": 67.926,
|
| 299 |
+
"eval_steps_per_second": 6.175,
|
| 300 |
+
"step": 30
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 31.0,
|
| 304 |
+
"eval_accuracy": 0.7272727272727273,
|
| 305 |
+
"eval_loss": 1.3513237237930298,
|
| 306 |
+
"eval_runtime": 0.1609,
|
| 307 |
+
"eval_samples_per_second": 68.346,
|
| 308 |
+
"eval_steps_per_second": 6.213,
|
| 309 |
+
"step": 31
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 32.0,
|
| 313 |
+
"eval_accuracy": 0.7272727272727273,
|
| 314 |
+
"eval_loss": 1.3374041318893433,
|
| 315 |
+
"eval_runtime": 0.1668,
|
| 316 |
+
"eval_samples_per_second": 65.94,
|
| 317 |
+
"eval_steps_per_second": 5.995,
|
| 318 |
+
"step": 32
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 33.0,
|
| 322 |
+
"eval_accuracy": 0.7272727272727273,
|
| 323 |
+
"eval_loss": 1.4942458868026733,
|
| 324 |
+
"eval_runtime": 0.1594,
|
| 325 |
+
"eval_samples_per_second": 69.018,
|
| 326 |
+
"eval_steps_per_second": 6.274,
|
| 327 |
+
"step": 33
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 34.0,
|
| 331 |
+
"eval_accuracy": 0.7272727272727273,
|
| 332 |
+
"eval_loss": 1.773066759109497,
|
| 333 |
+
"eval_runtime": 0.1685,
|
| 334 |
+
"eval_samples_per_second": 65.276,
|
| 335 |
+
"eval_steps_per_second": 5.934,
|
| 336 |
+
"step": 34
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 35.0,
|
| 340 |
+
"eval_accuracy": 0.7272727272727273,
|
| 341 |
+
"eval_loss": 1.8369468450546265,
|
| 342 |
+
"eval_runtime": 0.1744,
|
| 343 |
+
"eval_samples_per_second": 63.091,
|
| 344 |
+
"eval_steps_per_second": 5.736,
|
| 345 |
+
"step": 35
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 36.0,
|
| 349 |
+
"eval_accuracy": 0.7272727272727273,
|
| 350 |
+
"eval_loss": 1.7328110933303833,
|
| 351 |
+
"eval_runtime": 0.165,
|
| 352 |
+
"eval_samples_per_second": 66.653,
|
| 353 |
+
"eval_steps_per_second": 6.059,
|
| 354 |
+
"step": 36
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 37.0,
|
| 358 |
+
"eval_accuracy": 0.7272727272727273,
|
| 359 |
+
"eval_loss": 1.5451053380966187,
|
| 360 |
+
"eval_runtime": 0.1619,
|
| 361 |
+
"eval_samples_per_second": 67.933,
|
| 362 |
+
"eval_steps_per_second": 6.176,
|
| 363 |
+
"step": 37
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 38.0,
|
| 367 |
+
"eval_accuracy": 0.7272727272727273,
|
| 368 |
+
"eval_loss": 1.4483166933059692,
|
| 369 |
+
"eval_runtime": 0.1652,
|
| 370 |
+
"eval_samples_per_second": 66.579,
|
| 371 |
+
"eval_steps_per_second": 6.053,
|
| 372 |
+
"step": 38
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 39.0,
|
| 376 |
+
"eval_accuracy": 0.7272727272727273,
|
| 377 |
+
"eval_loss": 1.428899884223938,
|
| 378 |
+
"eval_runtime": 0.1784,
|
| 379 |
+
"eval_samples_per_second": 61.66,
|
| 380 |
+
"eval_steps_per_second": 5.605,
|
| 381 |
+
"step": 39
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 40.0,
|
| 385 |
+
"grad_norm": 2.0319314002990723,
|
| 386 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 387 |
+
"loss": 0.0819,
|
| 388 |
+
"step": 40
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 40.0,
|
| 392 |
+
"eval_accuracy": 0.7272727272727273,
|
| 393 |
+
"eval_loss": 1.3921602964401245,
|
| 394 |
+
"eval_runtime": 0.1575,
|
| 395 |
+
"eval_samples_per_second": 69.834,
|
| 396 |
+
"eval_steps_per_second": 6.349,
|
| 397 |
+
"step": 40
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 41.0,
|
| 401 |
+
"eval_accuracy": 0.7272727272727273,
|
| 402 |
+
"eval_loss": 1.4001747369766235,
|
| 403 |
+
"eval_runtime": 0.1717,
|
| 404 |
+
"eval_samples_per_second": 64.056,
|
| 405 |
+
"eval_steps_per_second": 5.823,
|
| 406 |
+
"step": 41
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 42.0,
|
| 410 |
+
"eval_accuracy": 0.7272727272727273,
|
| 411 |
+
"eval_loss": 1.3672713041305542,
|
| 412 |
+
"eval_runtime": 0.163,
|
| 413 |
+
"eval_samples_per_second": 67.498,
|
| 414 |
+
"eval_steps_per_second": 6.136,
|
| 415 |
+
"step": 42
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 43.0,
|
| 419 |
+
"eval_accuracy": 0.7272727272727273,
|
| 420 |
+
"eval_loss": 1.2193830013275146,
|
| 421 |
+
"eval_runtime": 0.1693,
|
| 422 |
+
"eval_samples_per_second": 64.983,
|
| 423 |
+
"eval_steps_per_second": 5.908,
|
| 424 |
+
"step": 43
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 44.0,
|
| 428 |
+
"eval_accuracy": 0.7272727272727273,
|
| 429 |
+
"eval_loss": 1.2879159450531006,
|
| 430 |
+
"eval_runtime": 0.1697,
|
| 431 |
+
"eval_samples_per_second": 64.802,
|
| 432 |
+
"eval_steps_per_second": 5.891,
|
| 433 |
+
"step": 44
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 45.0,
|
| 437 |
+
"eval_accuracy": 0.7272727272727273,
|
| 438 |
+
"eval_loss": 1.4545269012451172,
|
| 439 |
+
"eval_runtime": 0.1628,
|
| 440 |
+
"eval_samples_per_second": 67.576,
|
| 441 |
+
"eval_steps_per_second": 6.143,
|
| 442 |
+
"step": 45
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 46.0,
|
| 446 |
+
"eval_accuracy": 0.7272727272727273,
|
| 447 |
+
"eval_loss": 1.690229058265686,
|
| 448 |
+
"eval_runtime": 0.1655,
|
| 449 |
+
"eval_samples_per_second": 66.484,
|
| 450 |
+
"eval_steps_per_second": 6.044,
|
| 451 |
+
"step": 46
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 47.0,
|
| 455 |
+
"eval_accuracy": 0.7272727272727273,
|
| 456 |
+
"eval_loss": 1.841526746749878,
|
| 457 |
+
"eval_runtime": 0.1592,
|
| 458 |
+
"eval_samples_per_second": 69.109,
|
| 459 |
+
"eval_steps_per_second": 6.283,
|
| 460 |
+
"step": 47
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 48.0,
|
| 464 |
+
"eval_accuracy": 0.7272727272727273,
|
| 465 |
+
"eval_loss": 1.8891047239303589,
|
| 466 |
+
"eval_runtime": 0.1648,
|
| 467 |
+
"eval_samples_per_second": 66.73,
|
| 468 |
+
"eval_steps_per_second": 6.066,
|
| 469 |
+
"step": 48
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 49.0,
|
| 473 |
+
"eval_accuracy": 0.7272727272727273,
|
| 474 |
+
"eval_loss": 1.8338725566864014,
|
| 475 |
+
"eval_runtime": 0.1644,
|
| 476 |
+
"eval_samples_per_second": 66.92,
|
| 477 |
+
"eval_steps_per_second": 6.084,
|
| 478 |
+
"step": 49
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 50.0,
|
| 482 |
+
"grad_norm": 3.850102186203003,
|
| 483 |
+
"learning_rate": 2.777777777777778e-05,
|
| 484 |
+
"loss": 0.0551,
|
| 485 |
+
"step": 50
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 50.0,
|
| 489 |
+
"eval_accuracy": 0.7272727272727273,
|
| 490 |
+
"eval_loss": 1.8432774543762207,
|
| 491 |
+
"eval_runtime": 0.163,
|
| 492 |
+
"eval_samples_per_second": 67.484,
|
| 493 |
+
"eval_steps_per_second": 6.135,
|
| 494 |
+
"step": 50
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 51.0,
|
| 498 |
+
"eval_accuracy": 0.7272727272727273,
|
| 499 |
+
"eval_loss": 1.8432278633117676,
|
| 500 |
+
"eval_runtime": 0.2062,
|
| 501 |
+
"eval_samples_per_second": 53.334,
|
| 502 |
+
"eval_steps_per_second": 4.849,
|
| 503 |
+
"step": 51
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 52.0,
|
| 507 |
+
"eval_accuracy": 0.7272727272727273,
|
| 508 |
+
"eval_loss": 1.8002498149871826,
|
| 509 |
+
"eval_runtime": 0.1696,
|
| 510 |
+
"eval_samples_per_second": 64.874,
|
| 511 |
+
"eval_steps_per_second": 5.898,
|
| 512 |
+
"step": 52
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 53.0,
|
| 516 |
+
"eval_accuracy": 0.7272727272727273,
|
| 517 |
+
"eval_loss": 1.7276179790496826,
|
| 518 |
+
"eval_runtime": 0.1613,
|
| 519 |
+
"eval_samples_per_second": 68.189,
|
| 520 |
+
"eval_steps_per_second": 6.199,
|
| 521 |
+
"step": 53
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 54.0,
|
| 525 |
+
"eval_accuracy": 0.7272727272727273,
|
| 526 |
+
"eval_loss": 1.576358437538147,
|
| 527 |
+
"eval_runtime": 0.1619,
|
| 528 |
+
"eval_samples_per_second": 67.937,
|
| 529 |
+
"eval_steps_per_second": 6.176,
|
| 530 |
+
"step": 54
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 55.0,
|
| 534 |
+
"eval_accuracy": 0.7272727272727273,
|
| 535 |
+
"eval_loss": 1.3950941562652588,
|
| 536 |
+
"eval_runtime": 0.1733,
|
| 537 |
+
"eval_samples_per_second": 63.49,
|
| 538 |
+
"eval_steps_per_second": 5.772,
|
| 539 |
+
"step": 55
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 56.0,
|
| 543 |
+
"eval_accuracy": 0.7272727272727273,
|
| 544 |
+
"eval_loss": 1.4242897033691406,
|
| 545 |
+
"eval_runtime": 0.1672,
|
| 546 |
+
"eval_samples_per_second": 65.775,
|
| 547 |
+
"eval_steps_per_second": 5.98,
|
| 548 |
+
"step": 56
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 57.0,
|
| 552 |
+
"eval_accuracy": 0.7272727272727273,
|
| 553 |
+
"eval_loss": 1.5619553327560425,
|
| 554 |
+
"eval_runtime": 0.1633,
|
| 555 |
+
"eval_samples_per_second": 67.374,
|
| 556 |
+
"eval_steps_per_second": 6.125,
|
| 557 |
+
"step": 57
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 58.0,
|
| 561 |
+
"eval_accuracy": 0.7272727272727273,
|
| 562 |
+
"eval_loss": 1.6896965503692627,
|
| 563 |
+
"eval_runtime": 0.166,
|
| 564 |
+
"eval_samples_per_second": 66.266,
|
| 565 |
+
"eval_steps_per_second": 6.024,
|
| 566 |
+
"step": 58
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 59.0,
|
| 570 |
+
"eval_accuracy": 0.7272727272727273,
|
| 571 |
+
"eval_loss": 1.799486517906189,
|
| 572 |
+
"eval_runtime": 0.1705,
|
| 573 |
+
"eval_samples_per_second": 64.5,
|
| 574 |
+
"eval_steps_per_second": 5.864,
|
| 575 |
+
"step": 59
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 60.0,
|
| 579 |
+
"grad_norm": 0.7450773119926453,
|
| 580 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 581 |
+
"loss": 0.0413,
|
| 582 |
+
"step": 60
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 60.0,
|
| 586 |
+
"eval_accuracy": 0.7272727272727273,
|
| 587 |
+
"eval_loss": 1.873887300491333,
|
| 588 |
+
"eval_runtime": 0.1624,
|
| 589 |
+
"eval_samples_per_second": 67.749,
|
| 590 |
+
"eval_steps_per_second": 6.159,
|
| 591 |
+
"step": 60
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 61.0,
|
| 595 |
+
"eval_accuracy": 0.7272727272727273,
|
| 596 |
+
"eval_loss": 1.8485583066940308,
|
| 597 |
+
"eval_runtime": 0.1594,
|
| 598 |
+
"eval_samples_per_second": 69.026,
|
| 599 |
+
"eval_steps_per_second": 6.275,
|
| 600 |
+
"step": 61
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 62.0,
|
| 604 |
+
"eval_accuracy": 0.7272727272727273,
|
| 605 |
+
"eval_loss": 1.8072762489318848,
|
| 606 |
+
"eval_runtime": 0.1617,
|
| 607 |
+
"eval_samples_per_second": 68.035,
|
| 608 |
+
"eval_steps_per_second": 6.185,
|
| 609 |
+
"step": 62
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 63.0,
|
| 613 |
+
"eval_accuracy": 0.7272727272727273,
|
| 614 |
+
"eval_loss": 1.8192728757858276,
|
| 615 |
+
"eval_runtime": 0.166,
|
| 616 |
+
"eval_samples_per_second": 66.255,
|
| 617 |
+
"eval_steps_per_second": 6.023,
|
| 618 |
+
"step": 63
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 64.0,
|
| 622 |
+
"eval_accuracy": 0.7272727272727273,
|
| 623 |
+
"eval_loss": 1.760420560836792,
|
| 624 |
+
"eval_runtime": 0.1664,
|
| 625 |
+
"eval_samples_per_second": 66.12,
|
| 626 |
+
"eval_steps_per_second": 6.011,
|
| 627 |
+
"step": 64
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 65.0,
|
| 631 |
+
"eval_accuracy": 0.7272727272727273,
|
| 632 |
+
"eval_loss": 1.6326606273651123,
|
| 633 |
+
"eval_runtime": 0.1674,
|
| 634 |
+
"eval_samples_per_second": 65.711,
|
| 635 |
+
"eval_steps_per_second": 5.974,
|
| 636 |
+
"step": 65
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 66.0,
|
| 640 |
+
"eval_accuracy": 0.7272727272727273,
|
| 641 |
+
"eval_loss": 1.5446624755859375,
|
| 642 |
+
"eval_runtime": 0.1644,
|
| 643 |
+
"eval_samples_per_second": 66.898,
|
| 644 |
+
"eval_steps_per_second": 6.082,
|
| 645 |
+
"step": 66
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 67.0,
|
| 649 |
+
"eval_accuracy": 0.7272727272727273,
|
| 650 |
+
"eval_loss": 1.424346923828125,
|
| 651 |
+
"eval_runtime": 0.1647,
|
| 652 |
+
"eval_samples_per_second": 66.773,
|
| 653 |
+
"eval_steps_per_second": 6.07,
|
| 654 |
+
"step": 67
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 68.0,
|
| 658 |
+
"eval_accuracy": 0.7272727272727273,
|
| 659 |
+
"eval_loss": 1.3809901475906372,
|
| 660 |
+
"eval_runtime": 0.1629,
|
| 661 |
+
"eval_samples_per_second": 67.542,
|
| 662 |
+
"eval_steps_per_second": 6.14,
|
| 663 |
+
"step": 68
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 69.0,
|
| 667 |
+
"eval_accuracy": 0.7272727272727273,
|
| 668 |
+
"eval_loss": 1.3640745878219604,
|
| 669 |
+
"eval_runtime": 0.1716,
|
| 670 |
+
"eval_samples_per_second": 64.118,
|
| 671 |
+
"eval_steps_per_second": 5.829,
|
| 672 |
+
"step": 69
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 70.0,
|
| 676 |
+
"grad_norm": 1.508904218673706,
|
| 677 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 678 |
+
"loss": 0.038,
|
| 679 |
+
"step": 70
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 70.0,
|
| 683 |
+
"eval_accuracy": 0.7272727272727273,
|
| 684 |
+
"eval_loss": 1.4687689542770386,
|
| 685 |
+
"eval_runtime": 0.1619,
|
| 686 |
+
"eval_samples_per_second": 67.948,
|
| 687 |
+
"eval_steps_per_second": 6.177,
|
| 688 |
+
"step": 70
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 71.0,
|
| 692 |
+
"eval_accuracy": 0.7272727272727273,
|
| 693 |
+
"eval_loss": 1.5677317380905151,
|
| 694 |
+
"eval_runtime": 0.1666,
|
| 695 |
+
"eval_samples_per_second": 66.03,
|
| 696 |
+
"eval_steps_per_second": 6.003,
|
| 697 |
+
"step": 71
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 72.0,
|
| 701 |
+
"eval_accuracy": 0.7272727272727273,
|
| 702 |
+
"eval_loss": 1.717352271080017,
|
| 703 |
+
"eval_runtime": 0.1661,
|
| 704 |
+
"eval_samples_per_second": 66.219,
|
| 705 |
+
"eval_steps_per_second": 6.02,
|
| 706 |
+
"step": 72
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 73.0,
|
| 710 |
+
"eval_accuracy": 0.7272727272727273,
|
| 711 |
+
"eval_loss": 1.791959285736084,
|
| 712 |
+
"eval_runtime": 0.1623,
|
| 713 |
+
"eval_samples_per_second": 67.755,
|
| 714 |
+
"eval_steps_per_second": 6.16,
|
| 715 |
+
"step": 73
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 74.0,
|
| 719 |
+
"eval_accuracy": 0.7272727272727273,
|
| 720 |
+
"eval_loss": 1.8999717235565186,
|
| 721 |
+
"eval_runtime": 0.1611,
|
| 722 |
+
"eval_samples_per_second": 68.291,
|
| 723 |
+
"eval_steps_per_second": 6.208,
|
| 724 |
+
"step": 74
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 75.0,
|
| 728 |
+
"eval_accuracy": 0.7272727272727273,
|
| 729 |
+
"eval_loss": 1.9467865228652954,
|
| 730 |
+
"eval_runtime": 0.1648,
|
| 731 |
+
"eval_samples_per_second": 66.731,
|
| 732 |
+
"eval_steps_per_second": 6.066,
|
| 733 |
+
"step": 75
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 76.0,
|
| 737 |
+
"eval_accuracy": 0.7272727272727273,
|
| 738 |
+
"eval_loss": 1.9872097969055176,
|
| 739 |
+
"eval_runtime": 0.1646,
|
| 740 |
+
"eval_samples_per_second": 66.843,
|
| 741 |
+
"eval_steps_per_second": 6.077,
|
| 742 |
+
"step": 76
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 77.0,
|
| 746 |
+
"eval_accuracy": 0.7272727272727273,
|
| 747 |
+
"eval_loss": 2.0208170413970947,
|
| 748 |
+
"eval_runtime": 0.1631,
|
| 749 |
+
"eval_samples_per_second": 67.445,
|
| 750 |
+
"eval_steps_per_second": 6.131,
|
| 751 |
+
"step": 77
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 78.0,
|
| 755 |
+
"eval_accuracy": 0.7272727272727273,
|
| 756 |
+
"eval_loss": 2.0134825706481934,
|
| 757 |
+
"eval_runtime": 0.1701,
|
| 758 |
+
"eval_samples_per_second": 64.674,
|
| 759 |
+
"eval_steps_per_second": 5.879,
|
| 760 |
+
"step": 78
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 79.0,
|
| 764 |
+
"eval_accuracy": 0.7272727272727273,
|
| 765 |
+
"eval_loss": 1.9762377738952637,
|
| 766 |
+
"eval_runtime": 0.1647,
|
| 767 |
+
"eval_samples_per_second": 66.795,
|
| 768 |
+
"eval_steps_per_second": 6.072,
|
| 769 |
+
"step": 79
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 80.0,
|
| 773 |
+
"grad_norm": 1.9063314199447632,
|
| 774 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 775 |
+
"loss": 0.0365,
|
| 776 |
+
"step": 80
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 80.0,
|
| 780 |
+
"eval_accuracy": 0.7272727272727273,
|
| 781 |
+
"eval_loss": 1.9576034545898438,
|
| 782 |
+
"eval_runtime": 0.1617,
|
| 783 |
+
"eval_samples_per_second": 68.013,
|
| 784 |
+
"eval_steps_per_second": 6.183,
|
| 785 |
+
"step": 80
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 81.0,
|
| 789 |
+
"eval_accuracy": 0.7272727272727273,
|
| 790 |
+
"eval_loss": 1.931043267250061,
|
| 791 |
+
"eval_runtime": 0.1692,
|
| 792 |
+
"eval_samples_per_second": 65.005,
|
| 793 |
+
"eval_steps_per_second": 5.91,
|
| 794 |
+
"step": 81
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 82.0,
|
| 798 |
+
"eval_accuracy": 0.7272727272727273,
|
| 799 |
+
"eval_loss": 1.849521517753601,
|
| 800 |
+
"eval_runtime": 0.1653,
|
| 801 |
+
"eval_samples_per_second": 66.543,
|
| 802 |
+
"eval_steps_per_second": 6.049,
|
| 803 |
+
"step": 82
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 83.0,
|
| 807 |
+
"eval_accuracy": 0.7272727272727273,
|
| 808 |
+
"eval_loss": 1.7683414220809937,
|
| 809 |
+
"eval_runtime": 0.1658,
|
| 810 |
+
"eval_samples_per_second": 66.355,
|
| 811 |
+
"eval_steps_per_second": 6.032,
|
| 812 |
+
"step": 83
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 84.0,
|
| 816 |
+
"eval_accuracy": 0.7272727272727273,
|
| 817 |
+
"eval_loss": 1.710900902748108,
|
| 818 |
+
"eval_runtime": 0.1657,
|
| 819 |
+
"eval_samples_per_second": 66.404,
|
| 820 |
+
"eval_steps_per_second": 6.037,
|
| 821 |
+
"step": 84
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 85.0,
|
| 825 |
+
"eval_accuracy": 0.7272727272727273,
|
| 826 |
+
"eval_loss": 1.6437627077102661,
|
| 827 |
+
"eval_runtime": 0.1641,
|
| 828 |
+
"eval_samples_per_second": 67.039,
|
| 829 |
+
"eval_steps_per_second": 6.094,
|
| 830 |
+
"step": 85
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 86.0,
|
| 834 |
+
"eval_accuracy": 0.7272727272727273,
|
| 835 |
+
"eval_loss": 1.6153919696807861,
|
| 836 |
+
"eval_runtime": 0.1664,
|
| 837 |
+
"eval_samples_per_second": 66.115,
|
| 838 |
+
"eval_steps_per_second": 6.01,
|
| 839 |
+
"step": 86
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 87.0,
|
| 843 |
+
"eval_accuracy": 0.7272727272727273,
|
| 844 |
+
"eval_loss": 1.5714579820632935,
|
| 845 |
+
"eval_runtime": 0.1606,
|
| 846 |
+
"eval_samples_per_second": 68.51,
|
| 847 |
+
"eval_steps_per_second": 6.228,
|
| 848 |
+
"step": 87
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 88.0,
|
| 852 |
+
"eval_accuracy": 0.7272727272727273,
|
| 853 |
+
"eval_loss": 1.5428203344345093,
|
| 854 |
+
"eval_runtime": 0.1625,
|
| 855 |
+
"eval_samples_per_second": 67.699,
|
| 856 |
+
"eval_steps_per_second": 6.154,
|
| 857 |
+
"step": 88
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 89.0,
|
| 861 |
+
"eval_accuracy": 0.7272727272727273,
|
| 862 |
+
"eval_loss": 1.5164352655410767,
|
| 863 |
+
"eval_runtime": 0.1665,
|
| 864 |
+
"eval_samples_per_second": 66.086,
|
| 865 |
+
"eval_steps_per_second": 6.008,
|
| 866 |
+
"step": 89
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 90.0,
|
| 870 |
+
"grad_norm": 1.735504388809204,
|
| 871 |
+
"learning_rate": 5.555555555555556e-06,
|
| 872 |
+
"loss": 0.038,
|
| 873 |
+
"step": 90
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 90.0,
|
| 877 |
+
"eval_accuracy": 0.7272727272727273,
|
| 878 |
+
"eval_loss": 1.5007927417755127,
|
| 879 |
+
"eval_runtime": 0.1612,
|
| 880 |
+
"eval_samples_per_second": 68.243,
|
| 881 |
+
"eval_steps_per_second": 6.204,
|
| 882 |
+
"step": 90
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 91.0,
|
| 886 |
+
"eval_accuracy": 0.7272727272727273,
|
| 887 |
+
"eval_loss": 1.4729591608047485,
|
| 888 |
+
"eval_runtime": 0.1685,
|
| 889 |
+
"eval_samples_per_second": 65.283,
|
| 890 |
+
"eval_steps_per_second": 5.935,
|
| 891 |
+
"step": 91
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 92.0,
|
| 895 |
+
"eval_accuracy": 0.7272727272727273,
|
| 896 |
+
"eval_loss": 1.4492815732955933,
|
| 897 |
+
"eval_runtime": 0.1674,
|
| 898 |
+
"eval_samples_per_second": 65.72,
|
| 899 |
+
"eval_steps_per_second": 5.975,
|
| 900 |
+
"step": 92
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 93.0,
|
| 904 |
+
"eval_accuracy": 0.7272727272727273,
|
| 905 |
+
"eval_loss": 1.4728164672851562,
|
| 906 |
+
"eval_runtime": 0.1687,
|
| 907 |
+
"eval_samples_per_second": 65.196,
|
| 908 |
+
"eval_steps_per_second": 5.927,
|
| 909 |
+
"step": 93
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 94.0,
|
| 913 |
+
"eval_accuracy": 0.7272727272727273,
|
| 914 |
+
"eval_loss": 1.5032776594161987,
|
| 915 |
+
"eval_runtime": 0.1619,
|
| 916 |
+
"eval_samples_per_second": 67.93,
|
| 917 |
+
"eval_steps_per_second": 6.175,
|
| 918 |
+
"step": 94
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 95.0,
|
| 922 |
+
"eval_accuracy": 0.7272727272727273,
|
| 923 |
+
"eval_loss": 1.5345958471298218,
|
| 924 |
+
"eval_runtime": 0.1644,
|
| 925 |
+
"eval_samples_per_second": 66.89,
|
| 926 |
+
"eval_steps_per_second": 6.081,
|
| 927 |
+
"step": 95
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 96.0,
|
| 931 |
+
"eval_accuracy": 0.7272727272727273,
|
| 932 |
+
"eval_loss": 1.5555568933486938,
|
| 933 |
+
"eval_runtime": 0.1681,
|
| 934 |
+
"eval_samples_per_second": 65.45,
|
| 935 |
+
"eval_steps_per_second": 5.95,
|
| 936 |
+
"step": 96
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 97.0,
|
| 940 |
+
"eval_accuracy": 0.7272727272727273,
|
| 941 |
+
"eval_loss": 1.5642927885055542,
|
| 942 |
+
"eval_runtime": 0.1687,
|
| 943 |
+
"eval_samples_per_second": 65.192,
|
| 944 |
+
"eval_steps_per_second": 5.927,
|
| 945 |
+
"step": 97
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 98.0,
|
| 949 |
+
"eval_accuracy": 0.7272727272727273,
|
| 950 |
+
"eval_loss": 1.575886845588684,
|
| 951 |
+
"eval_runtime": 0.1637,
|
| 952 |
+
"eval_samples_per_second": 67.21,
|
| 953 |
+
"eval_steps_per_second": 6.11,
|
| 954 |
+
"step": 98
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 99.0,
|
| 958 |
+
"eval_accuracy": 0.7272727272727273,
|
| 959 |
+
"eval_loss": 1.5806941986083984,
|
| 960 |
+
"eval_runtime": 0.1619,
|
| 961 |
+
"eval_samples_per_second": 67.959,
|
| 962 |
+
"eval_steps_per_second": 6.178,
|
| 963 |
+
"step": 99
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 100.0,
|
| 967 |
+
"grad_norm": 2.8808040618896484,
|
| 968 |
+
"learning_rate": 0.0,
|
| 969 |
+
"loss": 0.0191,
|
| 970 |
+
"step": 100
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 100.0,
|
| 974 |
+
"eval_accuracy": 0.7272727272727273,
|
| 975 |
+
"eval_loss": 1.580631971359253,
|
| 976 |
+
"eval_runtime": 0.1593,
|
| 977 |
+
"eval_samples_per_second": 69.053,
|
| 978 |
+
"eval_steps_per_second": 6.278,
|
| 979 |
+
"step": 100
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"epoch": 100.0,
|
| 983 |
+
"step": 100,
|
| 984 |
+
"total_flos": 4.570114227259392e+17,
|
| 985 |
+
"train_loss": 0.09848821982741356,
|
| 986 |
+
"train_runtime": 419.3344,
|
| 987 |
+
"train_samples_per_second": 14.07,
|
| 988 |
+
"train_steps_per_second": 0.238
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 100.0,
|
| 992 |
+
"eval_accuracy": 0.7272727272727273,
|
| 993 |
+
"eval_loss": 0.9074404239654541,
|
| 994 |
+
"eval_runtime": 0.218,
|
| 995 |
+
"eval_samples_per_second": 50.454,
|
| 996 |
+
"eval_steps_per_second": 4.587,
|
| 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": 4.570114227259392e+17,
|
| 1018 |
+
"train_batch_size": 32,
|
| 1019 |
+
"trial_name": null,
|
| 1020 |
+
"trial_params": null
|
| 1021 |
+
}
|