./google-vit-base-patch16-224-in21k-9H
Browse files- README.md +1 -1
- all_results.json +9 -4
- eval_results.json +8 -0
- train_results.json +4 -4
- trainer_state.json +57 -0
README.md
CHANGED
|
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
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 None dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: 0.
|
| 21 |
- Accuracy: 0.9877
|
| 22 |
|
| 23 |
## Model description
|
|
|
|
| 17 |
|
| 18 |
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 None dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.8449
|
| 21 |
- Accuracy: 0.9877
|
| 22 |
|
| 23 |
## Model description
|
all_results.json
CHANGED
|
@@ -1,8 +1,13 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"total_flos": 1.6948561394167603e+17,
|
| 4 |
-
"train_loss":
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second": 13.
|
| 7 |
-
"train_steps_per_second": 1.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.9876543209876543,
|
| 4 |
+
"eval_loss": 0.8449140191078186,
|
| 5 |
+
"eval_runtime": 4.6209,
|
| 6 |
+
"eval_samples_per_second": 17.529,
|
| 7 |
+
"eval_steps_per_second": 4.545,
|
| 8 |
"total_flos": 1.6948561394167603e+17,
|
| 9 |
+
"train_loss": 0.7343477571391623,
|
| 10 |
+
"train_runtime": 162.6903,
|
| 11 |
+
"train_samples_per_second": 13.443,
|
| 12 |
+
"train_steps_per_second": 1.346
|
| 13 |
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.9876543209876543,
|
| 4 |
+
"eval_loss": 0.8449140191078186,
|
| 5 |
+
"eval_runtime": 4.6209,
|
| 6 |
+
"eval_samples_per_second": 17.529,
|
| 7 |
+
"eval_steps_per_second": 4.545
|
| 8 |
+
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
"total_flos": 1.6948561394167603e+17,
|
| 4 |
-
"train_loss":
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second": 13.
|
| 7 |
-
"train_steps_per_second": 1.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
"total_flos": 1.6948561394167603e+17,
|
| 4 |
+
"train_loss": 0.7343477571391623,
|
| 5 |
+
"train_runtime": 162.6903,
|
| 6 |
+
"train_samples_per_second": 13.443,
|
| 7 |
+
"train_steps_per_second": 1.346
|
| 8 |
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9876543209876543,
|
| 3 |
+
"best_model_checkpoint": "/content/drive/MyDrive/graduate_design/ViT_train_pictures/output_dir/checkpoint-73",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 219,
|
| 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": 0.9876543209876543,
|
| 14 |
+
"eval_loss": 0.8449140191078186,
|
| 15 |
+
"eval_runtime": 4.0408,
|
| 16 |
+
"eval_samples_per_second": 20.045,
|
| 17 |
+
"eval_steps_per_second": 5.197,
|
| 18 |
+
"step": 73
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 2.0,
|
| 22 |
+
"eval_accuracy": 0.9876543209876543,
|
| 23 |
+
"eval_loss": 0.5911225080490112,
|
| 24 |
+
"eval_runtime": 4.5389,
|
| 25 |
+
"eval_samples_per_second": 17.846,
|
| 26 |
+
"eval_steps_per_second": 4.627,
|
| 27 |
+
"step": 146
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 3.0,
|
| 31 |
+
"eval_accuracy": 0.9876543209876543,
|
| 32 |
+
"eval_loss": 0.5122054219245911,
|
| 33 |
+
"eval_runtime": 4.2151,
|
| 34 |
+
"eval_samples_per_second": 19.217,
|
| 35 |
+
"eval_steps_per_second": 4.982,
|
| 36 |
+
"step": 219
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 3.0,
|
| 40 |
+
"step": 219,
|
| 41 |
+
"total_flos": 1.6948561394167603e+17,
|
| 42 |
+
"train_loss": 0.7343477571391623,
|
| 43 |
+
"train_runtime": 162.6903,
|
| 44 |
+
"train_samples_per_second": 13.443,
|
| 45 |
+
"train_steps_per_second": 1.346
|
| 46 |
+
}
|
| 47 |
+
],
|
| 48 |
+
"logging_steps": 500,
|
| 49 |
+
"max_steps": 219,
|
| 50 |
+
"num_input_tokens_seen": 0,
|
| 51 |
+
"num_train_epochs": 3,
|
| 52 |
+
"save_steps": 500,
|
| 53 |
+
"total_flos": 1.6948561394167603e+17,
|
| 54 |
+
"train_batch_size": 10,
|
| 55 |
+
"trial_name": null,
|
| 56 |
+
"trial_params": null
|
| 57 |
+
}
|