🍻 cheers
Browse files- README.md +3 -2
- all_results.json +13 -0
- eval_results.json +8 -0
- runs/Mar29_04-16-17_e4da807b6953/events.out.tfevents.1743222906.e4da807b6953.31.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +1011 -0
README.md
CHANGED
|
@@ -3,6 +3,7 @@ library_name: transformers
|
|
| 3 |
license: apache-2.0
|
| 4 |
base_model: google/vit-base-patch16-224-in21k
|
| 5 |
tags:
|
|
|
|
| 6 |
- generated_from_trainer
|
| 7 |
metrics:
|
| 8 |
- accuracy
|
|
@@ -16,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
# vit-4-veggies
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss: 0.
|
| 22 |
- Accuracy: 0.9879
|
| 23 |
|
| 24 |
## Model description
|
|
|
|
| 3 |
license: apache-2.0
|
| 4 |
base_model: google/vit-base-patch16-224-in21k
|
| 5 |
tags:
|
| 6 |
+
- image-classification
|
| 7 |
- generated_from_trainer
|
| 8 |
metrics:
|
| 9 |
- accuracy
|
|
|
|
| 17 |
|
| 18 |
# vit-4-veggies
|
| 19 |
|
| 20 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the darthraider/fruit-ripeness-detection-dataset dataset.
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.0606
|
| 23 |
- Accuracy: 0.9879
|
| 24 |
|
| 25 |
## Model description
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 8.0,
|
| 3 |
+
"eval_accuracy": 0.9878836833602584,
|
| 4 |
+
"eval_loss": 0.06056738272309303,
|
| 5 |
+
"eval_runtime": 12.7331,
|
| 6 |
+
"eval_samples_per_second": 97.227,
|
| 7 |
+
"eval_steps_per_second": 6.126,
|
| 8 |
+
"total_flos": 3.0452071013776097e+18,
|
| 9 |
+
"train_loss": 0.09478302804823865,
|
| 10 |
+
"train_runtime": 1093.0198,
|
| 11 |
+
"train_samples_per_second": 35.952,
|
| 12 |
+
"train_steps_per_second": 1.127
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 8.0,
|
| 3 |
+
"eval_accuracy": 0.9878836833602584,
|
| 4 |
+
"eval_loss": 0.06056738272309303,
|
| 5 |
+
"eval_runtime": 12.7331,
|
| 6 |
+
"eval_samples_per_second": 97.227,
|
| 7 |
+
"eval_steps_per_second": 6.126
|
| 8 |
+
}
|
runs/Mar29_04-16-17_e4da807b6953/events.out.tfevents.1743222906.e4da807b6953.31.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44fed8c7e33867ebeb41e0a4bda8c40929b11eda00a21f2c5dd774d26a35276d
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 8.0,
|
| 3 |
+
"total_flos": 3.0452071013776097e+18,
|
| 4 |
+
"train_loss": 0.09478302804823865,
|
| 5 |
+
"train_runtime": 1093.0198,
|
| 6 |
+
"train_samples_per_second": 35.952,
|
| 7 |
+
"train_steps_per_second": 1.127
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1011 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.06056738272309303,
|
| 3 |
+
"best_model_checkpoint": "./vit-4-veggies/checkpoint-600",
|
| 4 |
+
"epoch": 8.0,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 1232,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.06493506493506493,
|
| 13 |
+
"grad_norm": 98652.796875,
|
| 14 |
+
"learning_rate": 4.959415584415585e-05,
|
| 15 |
+
"loss": 1.4476,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.12987012987012986,
|
| 20 |
+
"grad_norm": 94436.625,
|
| 21 |
+
"learning_rate": 4.918831168831169e-05,
|
| 22 |
+
"loss": 1.136,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.19480519480519481,
|
| 27 |
+
"grad_norm": 101840.984375,
|
| 28 |
+
"learning_rate": 4.8782467532467536e-05,
|
| 29 |
+
"loss": 0.9244,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.2597402597402597,
|
| 34 |
+
"grad_norm": 114599.859375,
|
| 35 |
+
"learning_rate": 4.8376623376623384e-05,
|
| 36 |
+
"loss": 0.6615,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.3246753246753247,
|
| 41 |
+
"grad_norm": 83704.421875,
|
| 42 |
+
"learning_rate": 4.797077922077922e-05,
|
| 43 |
+
"loss": 0.6185,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.38961038961038963,
|
| 48 |
+
"grad_norm": 78849.09375,
|
| 49 |
+
"learning_rate": 4.756493506493507e-05,
|
| 50 |
+
"loss": 0.4871,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.45454545454545453,
|
| 55 |
+
"grad_norm": 99447.1015625,
|
| 56 |
+
"learning_rate": 4.715909090909091e-05,
|
| 57 |
+
"loss": 0.4844,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.5194805194805194,
|
| 62 |
+
"grad_norm": 157846.703125,
|
| 63 |
+
"learning_rate": 4.675324675324675e-05,
|
| 64 |
+
"loss": 0.4082,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.5844155844155844,
|
| 69 |
+
"grad_norm": 131451.96875,
|
| 70 |
+
"learning_rate": 4.63474025974026e-05,
|
| 71 |
+
"loss": 0.3779,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.6493506493506493,
|
| 76 |
+
"grad_norm": 107052.734375,
|
| 77 |
+
"learning_rate": 4.5941558441558444e-05,
|
| 78 |
+
"loss": 0.3154,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.6493506493506493,
|
| 83 |
+
"eval_accuracy": 0.9434571890145396,
|
| 84 |
+
"eval_loss": 0.3097687065601349,
|
| 85 |
+
"eval_runtime": 12.2238,
|
| 86 |
+
"eval_samples_per_second": 101.278,
|
| 87 |
+
"eval_steps_per_second": 6.381,
|
| 88 |
+
"step": 100
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.7142857142857143,
|
| 92 |
+
"grad_norm": 383554.3125,
|
| 93 |
+
"learning_rate": 4.5535714285714286e-05,
|
| 94 |
+
"loss": 0.2848,
|
| 95 |
+
"step": 110
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.7792207792207793,
|
| 99 |
+
"grad_norm": 261821.75,
|
| 100 |
+
"learning_rate": 4.5129870129870135e-05,
|
| 101 |
+
"loss": 0.2766,
|
| 102 |
+
"step": 120
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.8441558441558441,
|
| 106 |
+
"grad_norm": 116962.8203125,
|
| 107 |
+
"learning_rate": 4.472402597402598e-05,
|
| 108 |
+
"loss": 0.2735,
|
| 109 |
+
"step": 130
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.9090909090909091,
|
| 113 |
+
"grad_norm": 126778.890625,
|
| 114 |
+
"learning_rate": 4.431818181818182e-05,
|
| 115 |
+
"loss": 0.2426,
|
| 116 |
+
"step": 140
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.974025974025974,
|
| 120 |
+
"grad_norm": 41615.3984375,
|
| 121 |
+
"learning_rate": 4.391233766233767e-05,
|
| 122 |
+
"loss": 0.2355,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.0389610389610389,
|
| 127 |
+
"grad_norm": 41465.8828125,
|
| 128 |
+
"learning_rate": 4.3506493506493503e-05,
|
| 129 |
+
"loss": 0.2035,
|
| 130 |
+
"step": 160
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.103896103896104,
|
| 134 |
+
"grad_norm": 336415.25,
|
| 135 |
+
"learning_rate": 4.310064935064935e-05,
|
| 136 |
+
"loss": 0.2156,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.1688311688311688,
|
| 141 |
+
"grad_norm": 49056.53125,
|
| 142 |
+
"learning_rate": 4.26948051948052e-05,
|
| 143 |
+
"loss": 0.2044,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.2337662337662338,
|
| 148 |
+
"grad_norm": 122884.6171875,
|
| 149 |
+
"learning_rate": 4.228896103896104e-05,
|
| 150 |
+
"loss": 0.2539,
|
| 151 |
+
"step": 190
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.2987012987012987,
|
| 155 |
+
"grad_norm": 128831.859375,
|
| 156 |
+
"learning_rate": 4.1883116883116886e-05,
|
| 157 |
+
"loss": 0.1446,
|
| 158 |
+
"step": 200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.2987012987012987,
|
| 162 |
+
"eval_accuracy": 0.9434571890145396,
|
| 163 |
+
"eval_loss": 0.2216598242521286,
|
| 164 |
+
"eval_runtime": 12.6893,
|
| 165 |
+
"eval_samples_per_second": 97.563,
|
| 166 |
+
"eval_steps_per_second": 6.147,
|
| 167 |
+
"step": 200
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.3636363636363638,
|
| 171 |
+
"grad_norm": 46098.05078125,
|
| 172 |
+
"learning_rate": 4.1477272727272734e-05,
|
| 173 |
+
"loss": 0.1041,
|
| 174 |
+
"step": 210
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.4285714285714286,
|
| 178 |
+
"grad_norm": 81511.2109375,
|
| 179 |
+
"learning_rate": 4.107142857142857e-05,
|
| 180 |
+
"loss": 0.1112,
|
| 181 |
+
"step": 220
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 1.4935064935064934,
|
| 185 |
+
"grad_norm": 324834.40625,
|
| 186 |
+
"learning_rate": 4.066558441558442e-05,
|
| 187 |
+
"loss": 0.14,
|
| 188 |
+
"step": 230
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.5584415584415585,
|
| 192 |
+
"grad_norm": 143048.796875,
|
| 193 |
+
"learning_rate": 4.025974025974026e-05,
|
| 194 |
+
"loss": 0.2534,
|
| 195 |
+
"step": 240
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.6233766233766234,
|
| 199 |
+
"grad_norm": 39697.8828125,
|
| 200 |
+
"learning_rate": 3.98538961038961e-05,
|
| 201 |
+
"loss": 0.1718,
|
| 202 |
+
"step": 250
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.6883116883116882,
|
| 206 |
+
"grad_norm": 32256.904296875,
|
| 207 |
+
"learning_rate": 3.944805194805195e-05,
|
| 208 |
+
"loss": 0.1571,
|
| 209 |
+
"step": 260
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.7532467532467533,
|
| 213 |
+
"grad_norm": 19842.701171875,
|
| 214 |
+
"learning_rate": 3.9042207792207794e-05,
|
| 215 |
+
"loss": 0.0853,
|
| 216 |
+
"step": 270
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.8181818181818183,
|
| 220 |
+
"grad_norm": 12634.58984375,
|
| 221 |
+
"learning_rate": 3.8636363636363636e-05,
|
| 222 |
+
"loss": 0.0671,
|
| 223 |
+
"step": 280
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 1.883116883116883,
|
| 227 |
+
"grad_norm": 37113.8984375,
|
| 228 |
+
"learning_rate": 3.8230519480519485e-05,
|
| 229 |
+
"loss": 0.0523,
|
| 230 |
+
"step": 290
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.948051948051948,
|
| 234 |
+
"grad_norm": 11151.8271484375,
|
| 235 |
+
"learning_rate": 3.782467532467533e-05,
|
| 236 |
+
"loss": 0.0814,
|
| 237 |
+
"step": 300
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.948051948051948,
|
| 241 |
+
"eval_accuracy": 0.9717285945072698,
|
| 242 |
+
"eval_loss": 0.1310429573059082,
|
| 243 |
+
"eval_runtime": 12.6419,
|
| 244 |
+
"eval_samples_per_second": 97.928,
|
| 245 |
+
"eval_steps_per_second": 6.17,
|
| 246 |
+
"step": 300
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 2.012987012987013,
|
| 250 |
+
"grad_norm": 22527.939453125,
|
| 251 |
+
"learning_rate": 3.741883116883117e-05,
|
| 252 |
+
"loss": 0.0838,
|
| 253 |
+
"step": 310
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 2.0779220779220777,
|
| 257 |
+
"grad_norm": 56426.72265625,
|
| 258 |
+
"learning_rate": 3.701298701298702e-05,
|
| 259 |
+
"loss": 0.0836,
|
| 260 |
+
"step": 320
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.142857142857143,
|
| 264 |
+
"grad_norm": 175356.546875,
|
| 265 |
+
"learning_rate": 3.6607142857142853e-05,
|
| 266 |
+
"loss": 0.0688,
|
| 267 |
+
"step": 330
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 2.207792207792208,
|
| 271 |
+
"grad_norm": 347378.875,
|
| 272 |
+
"learning_rate": 3.62012987012987e-05,
|
| 273 |
+
"loss": 0.07,
|
| 274 |
+
"step": 340
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 2.2727272727272725,
|
| 278 |
+
"grad_norm": 12468.73828125,
|
| 279 |
+
"learning_rate": 3.579545454545455e-05,
|
| 280 |
+
"loss": 0.0364,
|
| 281 |
+
"step": 350
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 2.3376623376623376,
|
| 285 |
+
"grad_norm": 6203.49267578125,
|
| 286 |
+
"learning_rate": 3.5389610389610387e-05,
|
| 287 |
+
"loss": 0.0303,
|
| 288 |
+
"step": 360
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 2.4025974025974026,
|
| 292 |
+
"grad_norm": 5669.07568359375,
|
| 293 |
+
"learning_rate": 3.4983766233766235e-05,
|
| 294 |
+
"loss": 0.0258,
|
| 295 |
+
"step": 370
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 2.4675324675324677,
|
| 299 |
+
"grad_norm": 6123.68603515625,
|
| 300 |
+
"learning_rate": 3.4577922077922084e-05,
|
| 301 |
+
"loss": 0.0664,
|
| 302 |
+
"step": 380
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.5324675324675323,
|
| 306 |
+
"grad_norm": 4741.46435546875,
|
| 307 |
+
"learning_rate": 3.417207792207792e-05,
|
| 308 |
+
"loss": 0.0371,
|
| 309 |
+
"step": 390
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 2.5974025974025974,
|
| 313 |
+
"grad_norm": 5111.3154296875,
|
| 314 |
+
"learning_rate": 3.376623376623377e-05,
|
| 315 |
+
"loss": 0.0438,
|
| 316 |
+
"step": 400
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 2.5974025974025974,
|
| 320 |
+
"eval_accuracy": 0.9830371567043619,
|
| 321 |
+
"eval_loss": 0.08745533972978592,
|
| 322 |
+
"eval_runtime": 12.6006,
|
| 323 |
+
"eval_samples_per_second": 98.25,
|
| 324 |
+
"eval_steps_per_second": 6.19,
|
| 325 |
+
"step": 400
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 2.6623376623376624,
|
| 329 |
+
"grad_norm": 6704.41015625,
|
| 330 |
+
"learning_rate": 3.336038961038961e-05,
|
| 331 |
+
"loss": 0.0687,
|
| 332 |
+
"step": 410
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.7272727272727275,
|
| 336 |
+
"grad_norm": 5477.58544921875,
|
| 337 |
+
"learning_rate": 3.295454545454545e-05,
|
| 338 |
+
"loss": 0.0178,
|
| 339 |
+
"step": 420
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.792207792207792,
|
| 343 |
+
"grad_norm": 3572.594970703125,
|
| 344 |
+
"learning_rate": 3.25487012987013e-05,
|
| 345 |
+
"loss": 0.0581,
|
| 346 |
+
"step": 430
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 2.857142857142857,
|
| 350 |
+
"grad_norm": 3537.077880859375,
|
| 351 |
+
"learning_rate": 3.2142857142857144e-05,
|
| 352 |
+
"loss": 0.0337,
|
| 353 |
+
"step": 440
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 2.9220779220779223,
|
| 357 |
+
"grad_norm": 247302.34375,
|
| 358 |
+
"learning_rate": 3.1737012987012986e-05,
|
| 359 |
+
"loss": 0.032,
|
| 360 |
+
"step": 450
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 2.987012987012987,
|
| 364 |
+
"grad_norm": 3149.987548828125,
|
| 365 |
+
"learning_rate": 3.1331168831168835e-05,
|
| 366 |
+
"loss": 0.0395,
|
| 367 |
+
"step": 460
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 3.051948051948052,
|
| 371 |
+
"grad_norm": 2695.8544921875,
|
| 372 |
+
"learning_rate": 3.092532467532468e-05,
|
| 373 |
+
"loss": 0.0112,
|
| 374 |
+
"step": 470
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 3.116883116883117,
|
| 378 |
+
"grad_norm": 3298.885986328125,
|
| 379 |
+
"learning_rate": 3.051948051948052e-05,
|
| 380 |
+
"loss": 0.0131,
|
| 381 |
+
"step": 480
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 3.1818181818181817,
|
| 385 |
+
"grad_norm": 2481.77685546875,
|
| 386 |
+
"learning_rate": 3.0113636363636365e-05,
|
| 387 |
+
"loss": 0.0201,
|
| 388 |
+
"step": 490
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 3.2467532467532467,
|
| 392 |
+
"grad_norm": 1988.6038818359375,
|
| 393 |
+
"learning_rate": 2.9707792207792207e-05,
|
| 394 |
+
"loss": 0.0212,
|
| 395 |
+
"step": 500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 3.2467532467532467,
|
| 399 |
+
"eval_accuracy": 0.9765751211631664,
|
| 400 |
+
"eval_loss": 0.11985456198453903,
|
| 401 |
+
"eval_runtime": 12.9037,
|
| 402 |
+
"eval_samples_per_second": 95.941,
|
| 403 |
+
"eval_steps_per_second": 6.045,
|
| 404 |
+
"step": 500
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 3.311688311688312,
|
| 408 |
+
"grad_norm": 2029.4908447265625,
|
| 409 |
+
"learning_rate": 2.9301948051948052e-05,
|
| 410 |
+
"loss": 0.0123,
|
| 411 |
+
"step": 510
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 3.3766233766233764,
|
| 415 |
+
"grad_norm": 1813.953125,
|
| 416 |
+
"learning_rate": 2.8896103896103898e-05,
|
| 417 |
+
"loss": 0.0072,
|
| 418 |
+
"step": 520
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 3.4415584415584415,
|
| 422 |
+
"grad_norm": 1632.518310546875,
|
| 423 |
+
"learning_rate": 2.849025974025974e-05,
|
| 424 |
+
"loss": 0.0187,
|
| 425 |
+
"step": 530
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 3.5064935064935066,
|
| 429 |
+
"grad_norm": 11811.1875,
|
| 430 |
+
"learning_rate": 2.8084415584415585e-05,
|
| 431 |
+
"loss": 0.0063,
|
| 432 |
+
"step": 540
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 3.571428571428571,
|
| 436 |
+
"grad_norm": 21330.248046875,
|
| 437 |
+
"learning_rate": 2.767857142857143e-05,
|
| 438 |
+
"loss": 0.0273,
|
| 439 |
+
"step": 550
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 3.6363636363636362,
|
| 443 |
+
"grad_norm": 4902.02587890625,
|
| 444 |
+
"learning_rate": 2.7272727272727273e-05,
|
| 445 |
+
"loss": 0.0261,
|
| 446 |
+
"step": 560
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 3.7012987012987013,
|
| 450 |
+
"grad_norm": 1297.66162109375,
|
| 451 |
+
"learning_rate": 2.686688311688312e-05,
|
| 452 |
+
"loss": 0.0051,
|
| 453 |
+
"step": 570
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 3.7662337662337664,
|
| 457 |
+
"grad_norm": 1216.2420654296875,
|
| 458 |
+
"learning_rate": 2.6461038961038964e-05,
|
| 459 |
+
"loss": 0.0046,
|
| 460 |
+
"step": 580
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 3.8311688311688314,
|
| 464 |
+
"grad_norm": 997.738525390625,
|
| 465 |
+
"learning_rate": 2.6055194805194806e-05,
|
| 466 |
+
"loss": 0.004,
|
| 467 |
+
"step": 590
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 3.896103896103896,
|
| 471 |
+
"grad_norm": 998.6089477539062,
|
| 472 |
+
"learning_rate": 2.5649350649350652e-05,
|
| 473 |
+
"loss": 0.0212,
|
| 474 |
+
"step": 600
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 3.896103896103896,
|
| 478 |
+
"eval_accuracy": 0.9878836833602584,
|
| 479 |
+
"eval_loss": 0.06056738272309303,
|
| 480 |
+
"eval_runtime": 12.5878,
|
| 481 |
+
"eval_samples_per_second": 98.349,
|
| 482 |
+
"eval_steps_per_second": 6.196,
|
| 483 |
+
"step": 600
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 3.961038961038961,
|
| 487 |
+
"grad_norm": 1652.7265625,
|
| 488 |
+
"learning_rate": 2.5243506493506497e-05,
|
| 489 |
+
"loss": 0.0088,
|
| 490 |
+
"step": 610
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 4.025974025974026,
|
| 494 |
+
"grad_norm": 921.3099365234375,
|
| 495 |
+
"learning_rate": 2.483766233766234e-05,
|
| 496 |
+
"loss": 0.026,
|
| 497 |
+
"step": 620
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 4.090909090909091,
|
| 501 |
+
"grad_norm": 873.7997436523438,
|
| 502 |
+
"learning_rate": 2.4431818181818185e-05,
|
| 503 |
+
"loss": 0.0226,
|
| 504 |
+
"step": 630
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 4.1558441558441555,
|
| 508 |
+
"grad_norm": 843.581298828125,
|
| 509 |
+
"learning_rate": 2.4025974025974027e-05,
|
| 510 |
+
"loss": 0.0033,
|
| 511 |
+
"step": 640
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 4.220779220779221,
|
| 515 |
+
"grad_norm": 681.9098510742188,
|
| 516 |
+
"learning_rate": 2.362012987012987e-05,
|
| 517 |
+
"loss": 0.003,
|
| 518 |
+
"step": 650
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 4.285714285714286,
|
| 522 |
+
"grad_norm": 644.044921875,
|
| 523 |
+
"learning_rate": 2.3214285714285715e-05,
|
| 524 |
+
"loss": 0.0028,
|
| 525 |
+
"step": 660
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 4.35064935064935,
|
| 529 |
+
"grad_norm": 717.3087158203125,
|
| 530 |
+
"learning_rate": 2.280844155844156e-05,
|
| 531 |
+
"loss": 0.0026,
|
| 532 |
+
"step": 670
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 4.415584415584416,
|
| 536 |
+
"grad_norm": 587.276611328125,
|
| 537 |
+
"learning_rate": 2.2402597402597402e-05,
|
| 538 |
+
"loss": 0.0023,
|
| 539 |
+
"step": 680
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 4.48051948051948,
|
| 543 |
+
"grad_norm": 533.31494140625,
|
| 544 |
+
"learning_rate": 2.1996753246753248e-05,
|
| 545 |
+
"loss": 0.0021,
|
| 546 |
+
"step": 690
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 4.545454545454545,
|
| 550 |
+
"grad_norm": 525.0987548828125,
|
| 551 |
+
"learning_rate": 2.1590909090909093e-05,
|
| 552 |
+
"loss": 0.002,
|
| 553 |
+
"step": 700
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 4.545454545454545,
|
| 557 |
+
"eval_accuracy": 0.9862681744749596,
|
| 558 |
+
"eval_loss": 0.08030502498149872,
|
| 559 |
+
"eval_runtime": 12.9251,
|
| 560 |
+
"eval_samples_per_second": 95.782,
|
| 561 |
+
"eval_steps_per_second": 6.035,
|
| 562 |
+
"step": 700
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 4.6103896103896105,
|
| 566 |
+
"grad_norm": 519.3194580078125,
|
| 567 |
+
"learning_rate": 2.1185064935064935e-05,
|
| 568 |
+
"loss": 0.0257,
|
| 569 |
+
"step": 710
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 4.675324675324675,
|
| 573 |
+
"grad_norm": 507.4796142578125,
|
| 574 |
+
"learning_rate": 2.077922077922078e-05,
|
| 575 |
+
"loss": 0.0018,
|
| 576 |
+
"step": 720
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 4.740259740259741,
|
| 580 |
+
"grad_norm": 425.1520080566406,
|
| 581 |
+
"learning_rate": 2.0373376623376626e-05,
|
| 582 |
+
"loss": 0.0017,
|
| 583 |
+
"step": 730
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 4.805194805194805,
|
| 587 |
+
"grad_norm": 393.7642517089844,
|
| 588 |
+
"learning_rate": 1.996753246753247e-05,
|
| 589 |
+
"loss": 0.0015,
|
| 590 |
+
"step": 740
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 4.87012987012987,
|
| 594 |
+
"grad_norm": 377.76678466796875,
|
| 595 |
+
"learning_rate": 1.956168831168831e-05,
|
| 596 |
+
"loss": 0.0016,
|
| 597 |
+
"step": 750
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 4.935064935064935,
|
| 601 |
+
"grad_norm": 422.4974670410156,
|
| 602 |
+
"learning_rate": 1.9155844155844156e-05,
|
| 603 |
+
"loss": 0.026,
|
| 604 |
+
"step": 760
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 5.0,
|
| 608 |
+
"grad_norm": 381.5065002441406,
|
| 609 |
+
"learning_rate": 1.8750000000000002e-05,
|
| 610 |
+
"loss": 0.0014,
|
| 611 |
+
"step": 770
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 5.064935064935065,
|
| 615 |
+
"grad_norm": 336.5712890625,
|
| 616 |
+
"learning_rate": 1.8344155844155844e-05,
|
| 617 |
+
"loss": 0.0012,
|
| 618 |
+
"step": 780
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 5.12987012987013,
|
| 622 |
+
"grad_norm": 320.25439453125,
|
| 623 |
+
"learning_rate": 1.793831168831169e-05,
|
| 624 |
+
"loss": 0.0012,
|
| 625 |
+
"step": 790
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 5.194805194805195,
|
| 629 |
+
"grad_norm": 326.00421142578125,
|
| 630 |
+
"learning_rate": 1.7532467532467535e-05,
|
| 631 |
+
"loss": 0.0011,
|
| 632 |
+
"step": 800
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 5.194805194805195,
|
| 636 |
+
"eval_accuracy": 0.9870759289176091,
|
| 637 |
+
"eval_loss": 0.07453276216983795,
|
| 638 |
+
"eval_runtime": 12.6647,
|
| 639 |
+
"eval_samples_per_second": 97.752,
|
| 640 |
+
"eval_steps_per_second": 6.159,
|
| 641 |
+
"step": 800
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 5.259740259740259,
|
| 645 |
+
"grad_norm": 403.37353515625,
|
| 646 |
+
"learning_rate": 1.7126623376623377e-05,
|
| 647 |
+
"loss": 0.0012,
|
| 648 |
+
"step": 810
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 5.324675324675325,
|
| 652 |
+
"grad_norm": 306.0226745605469,
|
| 653 |
+
"learning_rate": 1.672077922077922e-05,
|
| 654 |
+
"loss": 0.0011,
|
| 655 |
+
"step": 820
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 5.3896103896103895,
|
| 659 |
+
"grad_norm": 282.32855224609375,
|
| 660 |
+
"learning_rate": 1.6314935064935065e-05,
|
| 661 |
+
"loss": 0.001,
|
| 662 |
+
"step": 830
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 5.454545454545454,
|
| 666 |
+
"grad_norm": 67814.4609375,
|
| 667 |
+
"learning_rate": 1.590909090909091e-05,
|
| 668 |
+
"loss": 0.0255,
|
| 669 |
+
"step": 840
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 5.51948051948052,
|
| 673 |
+
"grad_norm": 242.10775756835938,
|
| 674 |
+
"learning_rate": 1.5503246753246752e-05,
|
| 675 |
+
"loss": 0.001,
|
| 676 |
+
"step": 850
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 5.584415584415584,
|
| 680 |
+
"grad_norm": 226.62974548339844,
|
| 681 |
+
"learning_rate": 1.50974025974026e-05,
|
| 682 |
+
"loss": 0.0432,
|
| 683 |
+
"step": 860
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 5.64935064935065,
|
| 687 |
+
"grad_norm": 225.47959899902344,
|
| 688 |
+
"learning_rate": 1.4691558441558442e-05,
|
| 689 |
+
"loss": 0.0008,
|
| 690 |
+
"step": 870
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 5.714285714285714,
|
| 694 |
+
"grad_norm": 216.57928466796875,
|
| 695 |
+
"learning_rate": 1.4285714285714285e-05,
|
| 696 |
+
"loss": 0.0008,
|
| 697 |
+
"step": 880
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 5.779220779220779,
|
| 701 |
+
"grad_norm": 239.439208984375,
|
| 702 |
+
"learning_rate": 1.3879870129870131e-05,
|
| 703 |
+
"loss": 0.0008,
|
| 704 |
+
"step": 890
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 5.8441558441558445,
|
| 708 |
+
"grad_norm": 247.78924560546875,
|
| 709 |
+
"learning_rate": 1.3474025974025975e-05,
|
| 710 |
+
"loss": 0.0008,
|
| 711 |
+
"step": 900
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 5.8441558441558445,
|
| 715 |
+
"eval_accuracy": 0.9878836833602584,
|
| 716 |
+
"eval_loss": 0.08090992271900177,
|
| 717 |
+
"eval_runtime": 12.58,
|
| 718 |
+
"eval_samples_per_second": 98.41,
|
| 719 |
+
"eval_steps_per_second": 6.2,
|
| 720 |
+
"step": 900
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 5.909090909090909,
|
| 724 |
+
"grad_norm": 208.6429901123047,
|
| 725 |
+
"learning_rate": 1.3068181818181819e-05,
|
| 726 |
+
"loss": 0.0008,
|
| 727 |
+
"step": 910
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 5.974025974025974,
|
| 731 |
+
"grad_norm": 235.62033081054688,
|
| 732 |
+
"learning_rate": 1.2662337662337662e-05,
|
| 733 |
+
"loss": 0.0007,
|
| 734 |
+
"step": 920
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 6.038961038961039,
|
| 738 |
+
"grad_norm": 183.11407470703125,
|
| 739 |
+
"learning_rate": 1.2256493506493508e-05,
|
| 740 |
+
"loss": 0.0007,
|
| 741 |
+
"step": 930
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 6.103896103896104,
|
| 745 |
+
"grad_norm": 161.49224853515625,
|
| 746 |
+
"learning_rate": 1.1850649350649352e-05,
|
| 747 |
+
"loss": 0.0104,
|
| 748 |
+
"step": 940
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 6.1688311688311686,
|
| 752 |
+
"grad_norm": 180.62030029296875,
|
| 753 |
+
"learning_rate": 1.1444805194805196e-05,
|
| 754 |
+
"loss": 0.0007,
|
| 755 |
+
"step": 950
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 6.233766233766234,
|
| 759 |
+
"grad_norm": 197.23057556152344,
|
| 760 |
+
"learning_rate": 1.103896103896104e-05,
|
| 761 |
+
"loss": 0.0006,
|
| 762 |
+
"step": 960
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 6.298701298701299,
|
| 766 |
+
"grad_norm": 148.50794982910156,
|
| 767 |
+
"learning_rate": 1.0633116883116883e-05,
|
| 768 |
+
"loss": 0.0206,
|
| 769 |
+
"step": 970
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 6.363636363636363,
|
| 773 |
+
"grad_norm": 142.77064514160156,
|
| 774 |
+
"learning_rate": 1.0227272727272729e-05,
|
| 775 |
+
"loss": 0.0006,
|
| 776 |
+
"step": 980
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 6.428571428571429,
|
| 780 |
+
"grad_norm": 655451.4375,
|
| 781 |
+
"learning_rate": 9.821428571428573e-06,
|
| 782 |
+
"loss": 0.0027,
|
| 783 |
+
"step": 990
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 6.4935064935064934,
|
| 787 |
+
"grad_norm": 140.66160583496094,
|
| 788 |
+
"learning_rate": 9.415584415584416e-06,
|
| 789 |
+
"loss": 0.0005,
|
| 790 |
+
"step": 1000
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 6.4935064935064934,
|
| 794 |
+
"eval_accuracy": 0.9886914378029079,
|
| 795 |
+
"eval_loss": 0.0861237570643425,
|
| 796 |
+
"eval_runtime": 12.6203,
|
| 797 |
+
"eval_samples_per_second": 98.096,
|
| 798 |
+
"eval_steps_per_second": 6.181,
|
| 799 |
+
"step": 1000
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 6.558441558441558,
|
| 803 |
+
"grad_norm": 159.91189575195312,
|
| 804 |
+
"learning_rate": 9.00974025974026e-06,
|
| 805 |
+
"loss": 0.0006,
|
| 806 |
+
"step": 1010
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 6.623376623376624,
|
| 810 |
+
"grad_norm": 141.53871154785156,
|
| 811 |
+
"learning_rate": 8.603896103896104e-06,
|
| 812 |
+
"loss": 0.0005,
|
| 813 |
+
"step": 1020
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 6.688311688311688,
|
| 817 |
+
"grad_norm": 156.2162322998047,
|
| 818 |
+
"learning_rate": 8.19805194805195e-06,
|
| 819 |
+
"loss": 0.0005,
|
| 820 |
+
"step": 1030
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 6.753246753246753,
|
| 824 |
+
"grad_norm": 141.82945251464844,
|
| 825 |
+
"learning_rate": 7.792207792207792e-06,
|
| 826 |
+
"loss": 0.0005,
|
| 827 |
+
"step": 1040
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 6.818181818181818,
|
| 831 |
+
"grad_norm": 172.6562957763672,
|
| 832 |
+
"learning_rate": 7.386363636363637e-06,
|
| 833 |
+
"loss": 0.0005,
|
| 834 |
+
"step": 1050
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 6.883116883116883,
|
| 838 |
+
"grad_norm": 118.13848876953125,
|
| 839 |
+
"learning_rate": 6.98051948051948e-06,
|
| 840 |
+
"loss": 0.0005,
|
| 841 |
+
"step": 1060
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 6.948051948051948,
|
| 845 |
+
"grad_norm": 119.30269622802734,
|
| 846 |
+
"learning_rate": 6.574675324675325e-06,
|
| 847 |
+
"loss": 0.0005,
|
| 848 |
+
"step": 1070
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 7.012987012987013,
|
| 852 |
+
"grad_norm": 120.57817840576172,
|
| 853 |
+
"learning_rate": 6.168831168831169e-06,
|
| 854 |
+
"loss": 0.0004,
|
| 855 |
+
"step": 1080
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 7.077922077922078,
|
| 859 |
+
"grad_norm": 117.14134979248047,
|
| 860 |
+
"learning_rate": 5.762987012987013e-06,
|
| 861 |
+
"loss": 0.0005,
|
| 862 |
+
"step": 1090
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 7.142857142857143,
|
| 866 |
+
"grad_norm": 130.8657989501953,
|
| 867 |
+
"learning_rate": 5.357142857142857e-06,
|
| 868 |
+
"loss": 0.0005,
|
| 869 |
+
"step": 1100
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 7.142857142857143,
|
| 873 |
+
"eval_accuracy": 0.9878836833602584,
|
| 874 |
+
"eval_loss": 0.08649223297834396,
|
| 875 |
+
"eval_runtime": 12.5975,
|
| 876 |
+
"eval_samples_per_second": 98.273,
|
| 877 |
+
"eval_steps_per_second": 6.192,
|
| 878 |
+
"step": 1100
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 7.207792207792208,
|
| 882 |
+
"grad_norm": 134.7167510986328,
|
| 883 |
+
"learning_rate": 4.951298701298702e-06,
|
| 884 |
+
"loss": 0.0005,
|
| 885 |
+
"step": 1110
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 7.2727272727272725,
|
| 889 |
+
"grad_norm": 117.66633605957031,
|
| 890 |
+
"learning_rate": 4.5454545454545455e-06,
|
| 891 |
+
"loss": 0.0004,
|
| 892 |
+
"step": 1120
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 7.337662337662338,
|
| 896 |
+
"grad_norm": 129.73902893066406,
|
| 897 |
+
"learning_rate": 4.13961038961039e-06,
|
| 898 |
+
"loss": 0.0004,
|
| 899 |
+
"step": 1130
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 7.402597402597403,
|
| 903 |
+
"grad_norm": 112.13995361328125,
|
| 904 |
+
"learning_rate": 3.733766233766234e-06,
|
| 905 |
+
"loss": 0.0004,
|
| 906 |
+
"step": 1140
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 7.467532467532467,
|
| 910 |
+
"grad_norm": 135.0137939453125,
|
| 911 |
+
"learning_rate": 3.327922077922078e-06,
|
| 912 |
+
"loss": 0.0005,
|
| 913 |
+
"step": 1150
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 7.532467532467533,
|
| 917 |
+
"grad_norm": 115.70610046386719,
|
| 918 |
+
"learning_rate": 2.922077922077922e-06,
|
| 919 |
+
"loss": 0.0004,
|
| 920 |
+
"step": 1160
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 7.597402597402597,
|
| 924 |
+
"grad_norm": 136.4860076904297,
|
| 925 |
+
"learning_rate": 2.5162337662337663e-06,
|
| 926 |
+
"loss": 0.0004,
|
| 927 |
+
"step": 1170
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 7.662337662337662,
|
| 931 |
+
"grad_norm": 107.2647705078125,
|
| 932 |
+
"learning_rate": 2.1103896103896105e-06,
|
| 933 |
+
"loss": 0.0004,
|
| 934 |
+
"step": 1180
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 7.7272727272727275,
|
| 938 |
+
"grad_norm": 121.89676666259766,
|
| 939 |
+
"learning_rate": 1.7045454545454546e-06,
|
| 940 |
+
"loss": 0.0005,
|
| 941 |
+
"step": 1190
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 7.792207792207792,
|
| 945 |
+
"grad_norm": 149.9101104736328,
|
| 946 |
+
"learning_rate": 1.2987012987012988e-06,
|
| 947 |
+
"loss": 0.0004,
|
| 948 |
+
"step": 1200
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 7.792207792207792,
|
| 952 |
+
"eval_accuracy": 0.9878836833602584,
|
| 953 |
+
"eval_loss": 0.07882251590490341,
|
| 954 |
+
"eval_runtime": 12.5777,
|
| 955 |
+
"eval_samples_per_second": 98.428,
|
| 956 |
+
"eval_steps_per_second": 6.201,
|
| 957 |
+
"step": 1200
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 7.857142857142857,
|
| 961 |
+
"grad_norm": 118.61868286132812,
|
| 962 |
+
"learning_rate": 8.928571428571428e-07,
|
| 963 |
+
"loss": 0.0004,
|
| 964 |
+
"step": 1210
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 7.922077922077922,
|
| 968 |
+
"grad_norm": 108.26444244384766,
|
| 969 |
+
"learning_rate": 4.87012987012987e-07,
|
| 970 |
+
"loss": 0.0004,
|
| 971 |
+
"step": 1220
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 7.987012987012987,
|
| 975 |
+
"grad_norm": 101.61443328857422,
|
| 976 |
+
"learning_rate": 8.116883116883118e-08,
|
| 977 |
+
"loss": 0.0004,
|
| 978 |
+
"step": 1230
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 8.0,
|
| 982 |
+
"step": 1232,
|
| 983 |
+
"total_flos": 3.0452071013776097e+18,
|
| 984 |
+
"train_loss": 0.09478302804823865,
|
| 985 |
+
"train_runtime": 1093.0198,
|
| 986 |
+
"train_samples_per_second": 35.952,
|
| 987 |
+
"train_steps_per_second": 1.127
|
| 988 |
+
}
|
| 989 |
+
],
|
| 990 |
+
"logging_steps": 10,
|
| 991 |
+
"max_steps": 1232,
|
| 992 |
+
"num_input_tokens_seen": 0,
|
| 993 |
+
"num_train_epochs": 8,
|
| 994 |
+
"save_steps": 100,
|
| 995 |
+
"stateful_callbacks": {
|
| 996 |
+
"TrainerControl": {
|
| 997 |
+
"args": {
|
| 998 |
+
"should_epoch_stop": false,
|
| 999 |
+
"should_evaluate": false,
|
| 1000 |
+
"should_log": false,
|
| 1001 |
+
"should_save": true,
|
| 1002 |
+
"should_training_stop": true
|
| 1003 |
+
},
|
| 1004 |
+
"attributes": {}
|
| 1005 |
+
}
|
| 1006 |
+
},
|
| 1007 |
+
"total_flos": 3.0452071013776097e+18,
|
| 1008 |
+
"train_batch_size": 32,
|
| 1009 |
+
"trial_name": null,
|
| 1010 |
+
"trial_params": null
|
| 1011 |
+
}
|