End of training
Browse files- README.md +1 -0
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +88 -0
README.md
CHANGED
|
@@ -2,6 +2,7 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: google/vit-base-patch16-224
|
| 4 |
tags:
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
- imagefolder
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: google/vit-base-patch16-224
|
| 4 |
tags:
|
| 5 |
+
- image-classification
|
| 6 |
- generated_from_trainer
|
| 7 |
datasets:
|
| 8 |
- imagefolder
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 1.772241802485719e+18,
|
| 4 |
+
"train_loss": 0.1194506121081347,
|
| 5 |
+
"train_runtime": 815.7328,
|
| 6 |
+
"train_samples_per_second": 28.036,
|
| 7 |
+
"train_steps_per_second": 0.439
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 1.772241802485719e+18,
|
| 4 |
+
"train_loss": 0.1194506121081347,
|
| 5 |
+
"train_runtime": 815.7328,
|
| 6 |
+
"train_samples_per_second": 28.036,
|
| 7 |
+
"train_steps_per_second": 0.439
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.11141396313905716,
|
| 3 |
+
"best_model_checkpoint": "./vit-spam/checkpoint-358",
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 358,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.13966480446927373,
|
| 13 |
+
"grad_norm": 1.035046935081482,
|
| 14 |
+
"learning_rate": 4.301675977653631e-05,
|
| 15 |
+
"loss": 0.2956,
|
| 16 |
+
"step": 50
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.27932960893854747,
|
| 20 |
+
"grad_norm": 2.2606287002563477,
|
| 21 |
+
"learning_rate": 3.603351955307263e-05,
|
| 22 |
+
"loss": 0.1171,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.41899441340782123,
|
| 27 |
+
"grad_norm": 1.3705707788467407,
|
| 28 |
+
"learning_rate": 2.9050279329608944e-05,
|
| 29 |
+
"loss": 0.1116,
|
| 30 |
+
"step": 150
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.5586592178770949,
|
| 34 |
+
"grad_norm": 1.3012491464614868,
|
| 35 |
+
"learning_rate": 2.206703910614525e-05,
|
| 36 |
+
"loss": 0.0839,
|
| 37 |
+
"step": 200
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.6983240223463687,
|
| 41 |
+
"grad_norm": 0.7185125350952148,
|
| 42 |
+
"learning_rate": 1.5083798882681566e-05,
|
| 43 |
+
"loss": 0.069,
|
| 44 |
+
"step": 250
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.8379888268156425,
|
| 48 |
+
"grad_norm": 0.9136179685592651,
|
| 49 |
+
"learning_rate": 8.100558659217877e-06,
|
| 50 |
+
"loss": 0.0885,
|
| 51 |
+
"step": 300
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.9776536312849162,
|
| 55 |
+
"grad_norm": 0.8141963481903076,
|
| 56 |
+
"learning_rate": 1.11731843575419e-06,
|
| 57 |
+
"loss": 0.0785,
|
| 58 |
+
"step": 350
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.0,
|
| 62 |
+
"eval_loss": 0.11141396313905716,
|
| 63 |
+
"eval_roc_auc": 0.9529222871380703,
|
| 64 |
+
"eval_runtime": 162.1567,
|
| 65 |
+
"eval_samples_per_second": 34.553,
|
| 66 |
+
"eval_steps_per_second": 0.543,
|
| 67 |
+
"step": 358
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 1.0,
|
| 71 |
+
"step": 358,
|
| 72 |
+
"total_flos": 1.772241802485719e+18,
|
| 73 |
+
"train_loss": 0.1194506121081347,
|
| 74 |
+
"train_runtime": 815.7328,
|
| 75 |
+
"train_samples_per_second": 28.036,
|
| 76 |
+
"train_steps_per_second": 0.439
|
| 77 |
+
}
|
| 78 |
+
],
|
| 79 |
+
"logging_steps": 50,
|
| 80 |
+
"max_steps": 358,
|
| 81 |
+
"num_input_tokens_seen": 0,
|
| 82 |
+
"num_train_epochs": 1,
|
| 83 |
+
"save_steps": 500,
|
| 84 |
+
"total_flos": 1.772241802485719e+18,
|
| 85 |
+
"train_batch_size": 64,
|
| 86 |
+
"trial_name": null,
|
| 87 |
+
"trial_params": null
|
| 88 |
+
}
|