Upload folder using huggingface_hub
Browse files- checkpoint-4500/config.json +31 -0
- checkpoint-4500/model.safetensors +3 -0
- checkpoint-4500/optimizer.pt +3 -0
- checkpoint-4500/preprocessor_config.json +27 -0
- checkpoint-4500/rng_state.pth +3 -0
- checkpoint-4500/scheduler.pt +3 -0
- checkpoint-4500/trainer_state.json +126 -0
- checkpoint-4500/training_args.bin +3 -0
- config.json +31 -0
- model.safetensors +3 -0
- preprocessor_config.json +27 -0
- training_args.bin +3 -0
checkpoint-4500/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "openai/clip-vit-base-patch32",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"CLIPForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"id2label": {
|
| 7 |
+
"0": "REAL",
|
| 8 |
+
"1": "FAKE"
|
| 9 |
+
},
|
| 10 |
+
"initializer_factor": 1.0,
|
| 11 |
+
"label2id": {
|
| 12 |
+
"FAKE": 1,
|
| 13 |
+
"REAL": 0
|
| 14 |
+
},
|
| 15 |
+
"logit_scale_init_value": 2.6592,
|
| 16 |
+
"model_type": "clip",
|
| 17 |
+
"problem_type": "single_label_classification",
|
| 18 |
+
"projection_dim": 512,
|
| 19 |
+
"text_config": {
|
| 20 |
+
"bos_token_id": 0,
|
| 21 |
+
"dropout": 0.0,
|
| 22 |
+
"eos_token_id": 2,
|
| 23 |
+
"model_type": "clip_text_model"
|
| 24 |
+
},
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.46.2",
|
| 27 |
+
"vision_config": {
|
| 28 |
+
"dropout": 0.0,
|
| 29 |
+
"model_type": "clip_vision_model"
|
| 30 |
+
}
|
| 31 |
+
}
|
checkpoint-4500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c3a66129ec79a95e5fca7bd96dbdf75bc52c6aa928bbb51b28c77f3ca0c0996
|
| 3 |
+
size 349854120
|
checkpoint-4500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:43894160de083217dfe6270264c9780588096e61e1b63960ad9a9433c46af05d
|
| 3 |
+
size 699814021
|
checkpoint-4500/preprocessor_config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": {
|
| 3 |
+
"height": 224,
|
| 4 |
+
"width": 224
|
| 5 |
+
},
|
| 6 |
+
"do_center_crop": true,
|
| 7 |
+
"do_convert_rgb": true,
|
| 8 |
+
"do_normalize": true,
|
| 9 |
+
"do_rescale": true,
|
| 10 |
+
"do_resize": true,
|
| 11 |
+
"image_mean": [
|
| 12 |
+
0.48145466,
|
| 13 |
+
0.4578275,
|
| 14 |
+
0.40821073
|
| 15 |
+
],
|
| 16 |
+
"image_processor_type": "CLIPImageProcessor",
|
| 17 |
+
"image_std": [
|
| 18 |
+
0.26862954,
|
| 19 |
+
0.26130258,
|
| 20 |
+
0.27577711
|
| 21 |
+
],
|
| 22 |
+
"resample": 3,
|
| 23 |
+
"rescale_factor": 0.00392156862745098,
|
| 24 |
+
"size": {
|
| 25 |
+
"shortest_edge": 224
|
| 26 |
+
}
|
| 27 |
+
}
|
checkpoint-4500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93a3fcabe0b2ff3b3ec81f1f69c8ef8e49fff07b7cc7afe8359bd022cd30d871
|
| 3 |
+
size 14575
|
checkpoint-4500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:718c85711d9802299e409bb13f1ec6bd8a44411fb3eb4222a4620eaccb9d086e
|
| 3 |
+
size 627
|
checkpoint-4500/trainer_state.json
ADDED
|
@@ -0,0 +1,126 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.10008788853883743,
|
| 3 |
+
"best_model_checkpoint": "clip_base_noaug/checkpoint-4500",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 4500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.3333333333333333,
|
| 13 |
+
"grad_norm": 34.92070007324219,
|
| 14 |
+
"learning_rate": 8.988764044943819e-07,
|
| 15 |
+
"loss": 0.2967,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.6666666666666666,
|
| 20 |
+
"grad_norm": 45.73786163330078,
|
| 21 |
+
"learning_rate": 7.865168539325843e-07,
|
| 22 |
+
"loss": 0.1592,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 1.0,
|
| 27 |
+
"grad_norm": 26.203510284423828,
|
| 28 |
+
"learning_rate": 6.741573033707865e-07,
|
| 29 |
+
"loss": 0.1429,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 1.0,
|
| 34 |
+
"eval_accuracy": 0.94675,
|
| 35 |
+
"eval_loss": 0.14425331354141235,
|
| 36 |
+
"eval_model_preparation_time": 0.004,
|
| 37 |
+
"eval_runtime": 87.8205,
|
| 38 |
+
"eval_samples_per_second": 273.285,
|
| 39 |
+
"eval_steps_per_second": 8.54,
|
| 40 |
+
"step": 1500
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 1.3333333333333333,
|
| 44 |
+
"grad_norm": 42.80449676513672,
|
| 45 |
+
"learning_rate": 5.617977528089887e-07,
|
| 46 |
+
"loss": 0.123,
|
| 47 |
+
"step": 2000
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 1.6666666666666665,
|
| 51 |
+
"grad_norm": 37.18833541870117,
|
| 52 |
+
"learning_rate": 4.4943820224719097e-07,
|
| 53 |
+
"loss": 0.1134,
|
| 54 |
+
"step": 2500
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 2.0,
|
| 58 |
+
"grad_norm": 57.78050231933594,
|
| 59 |
+
"learning_rate": 3.3707865168539325e-07,
|
| 60 |
+
"loss": 0.1023,
|
| 61 |
+
"step": 3000
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 2.0,
|
| 65 |
+
"eval_accuracy": 0.9605833333333333,
|
| 66 |
+
"eval_loss": 0.10788565874099731,
|
| 67 |
+
"eval_model_preparation_time": 0.004,
|
| 68 |
+
"eval_runtime": 101.8398,
|
| 69 |
+
"eval_samples_per_second": 235.664,
|
| 70 |
+
"eval_steps_per_second": 7.365,
|
| 71 |
+
"step": 3000
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 2.3333333333333335,
|
| 75 |
+
"grad_norm": 44.27554702758789,
|
| 76 |
+
"learning_rate": 2.2471910112359549e-07,
|
| 77 |
+
"loss": 0.0957,
|
| 78 |
+
"step": 3500
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 2.6666666666666665,
|
| 82 |
+
"grad_norm": 29.09344482421875,
|
| 83 |
+
"learning_rate": 1.1235955056179774e-07,
|
| 84 |
+
"loss": 0.0897,
|
| 85 |
+
"step": 4000
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 3.0,
|
| 89 |
+
"grad_norm": 18.151649475097656,
|
| 90 |
+
"learning_rate": 0.0,
|
| 91 |
+
"loss": 0.0888,
|
| 92 |
+
"step": 4500
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 3.0,
|
| 96 |
+
"eval_accuracy": 0.962375,
|
| 97 |
+
"eval_loss": 0.10008788853883743,
|
| 98 |
+
"eval_model_preparation_time": 0.004,
|
| 99 |
+
"eval_runtime": 88.2967,
|
| 100 |
+
"eval_samples_per_second": 271.811,
|
| 101 |
+
"eval_steps_per_second": 8.494,
|
| 102 |
+
"step": 4500
|
| 103 |
+
}
|
| 104 |
+
],
|
| 105 |
+
"logging_steps": 500,
|
| 106 |
+
"max_steps": 4500,
|
| 107 |
+
"num_input_tokens_seen": 0,
|
| 108 |
+
"num_train_epochs": 3,
|
| 109 |
+
"save_steps": 500,
|
| 110 |
+
"stateful_callbacks": {
|
| 111 |
+
"TrainerControl": {
|
| 112 |
+
"args": {
|
| 113 |
+
"should_epoch_stop": false,
|
| 114 |
+
"should_evaluate": false,
|
| 115 |
+
"should_log": false,
|
| 116 |
+
"should_save": true,
|
| 117 |
+
"should_training_stop": true
|
| 118 |
+
},
|
| 119 |
+
"attributes": {}
|
| 120 |
+
}
|
| 121 |
+
},
|
| 122 |
+
"total_flos": 2.273880039240499e+19,
|
| 123 |
+
"train_batch_size": 64,
|
| 124 |
+
"trial_name": null,
|
| 125 |
+
"trial_params": null
|
| 126 |
+
}
|
checkpoint-4500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:731ba7bae80b0e3f5033ff382c0d76ccb018cc6f7a928bffa7f2131c1573fe30
|
| 3 |
+
size 4795
|
config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "openai/clip-vit-base-patch32",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"CLIPForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"id2label": {
|
| 7 |
+
"0": "REAL",
|
| 8 |
+
"1": "FAKE"
|
| 9 |
+
},
|
| 10 |
+
"initializer_factor": 1.0,
|
| 11 |
+
"label2id": {
|
| 12 |
+
"FAKE": 1,
|
| 13 |
+
"REAL": 0
|
| 14 |
+
},
|
| 15 |
+
"logit_scale_init_value": 2.6592,
|
| 16 |
+
"model_type": "clip",
|
| 17 |
+
"problem_type": "single_label_classification",
|
| 18 |
+
"projection_dim": 512,
|
| 19 |
+
"text_config": {
|
| 20 |
+
"bos_token_id": 0,
|
| 21 |
+
"dropout": 0.0,
|
| 22 |
+
"eos_token_id": 2,
|
| 23 |
+
"model_type": "clip_text_model"
|
| 24 |
+
},
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.46.2",
|
| 27 |
+
"vision_config": {
|
| 28 |
+
"dropout": 0.0,
|
| 29 |
+
"model_type": "clip_vision_model"
|
| 30 |
+
}
|
| 31 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c3a66129ec79a95e5fca7bd96dbdf75bc52c6aa928bbb51b28c77f3ca0c0996
|
| 3 |
+
size 349854120
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": {
|
| 3 |
+
"height": 224,
|
| 4 |
+
"width": 224
|
| 5 |
+
},
|
| 6 |
+
"do_center_crop": true,
|
| 7 |
+
"do_convert_rgb": true,
|
| 8 |
+
"do_normalize": true,
|
| 9 |
+
"do_rescale": true,
|
| 10 |
+
"do_resize": true,
|
| 11 |
+
"image_mean": [
|
| 12 |
+
0.48145466,
|
| 13 |
+
0.4578275,
|
| 14 |
+
0.40821073
|
| 15 |
+
],
|
| 16 |
+
"image_processor_type": "CLIPImageProcessor",
|
| 17 |
+
"image_std": [
|
| 18 |
+
0.26862954,
|
| 19 |
+
0.26130258,
|
| 20 |
+
0.27577711
|
| 21 |
+
],
|
| 22 |
+
"resample": 3,
|
| 23 |
+
"rescale_factor": 0.00392156862745098,
|
| 24 |
+
"size": {
|
| 25 |
+
"shortest_edge": 224
|
| 26 |
+
}
|
| 27 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:731ba7bae80b0e3f5033ff382c0d76ccb018cc6f7a928bffa7f2131c1573fe30
|
| 3 |
+
size 4795
|