Upload 24 files
Browse files- checkpoint-105/config.json +33 -0
- checkpoint-105/model.safetensors +3 -0
- checkpoint-105/optimizer.pt +3 -0
- checkpoint-105/rng_state.pth +3 -0
- checkpoint-105/scheduler.pt +3 -0
- checkpoint-105/trainer_state.json +104 -0
- checkpoint-105/training_args.bin +3 -0
- checkpoint-35/config.json +33 -0
- checkpoint-35/model.safetensors +3 -0
- checkpoint-35/optimizer.pt +3 -0
- checkpoint-35/rng_state.pth +3 -0
- checkpoint-35/scheduler.pt +3 -0
- checkpoint-35/trainer_state.json +55 -0
- checkpoint-35/training_args.bin +3 -0
- checkpoint-70/config.json +33 -0
- checkpoint-70/model.safetensors +3 -0
- checkpoint-70/optimizer.pt +3 -0
- checkpoint-70/rng_state.pth +3 -0
- checkpoint-70/scheduler.pt +3 -0
- checkpoint-70/trainer_state.json +83 -0
- checkpoint-70/training_args.bin +3 -0
- config.json +33 -33
- model.safetensors +1 -1
- preprocessor_config.json +23 -23
checkpoint-105/config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"ViTForImageClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.0,
|
| 6 |
+
"dtype": "float32",
|
| 7 |
+
"encoder_stride": 16,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.0,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "normal",
|
| 13 |
+
"1": "nsfw"
|
| 14 |
+
},
|
| 15 |
+
"image_size": 224,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 3072,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"normal": "0",
|
| 20 |
+
"nsfw": "1"
|
| 21 |
+
},
|
| 22 |
+
"layer_norm_eps": 1e-12,
|
| 23 |
+
"model_type": "vit",
|
| 24 |
+
"num_attention_heads": 12,
|
| 25 |
+
"num_channels": 3,
|
| 26 |
+
"num_hidden_layers": 12,
|
| 27 |
+
"patch_size": 16,
|
| 28 |
+
"pooler_act": "tanh",
|
| 29 |
+
"pooler_output_size": 768,
|
| 30 |
+
"problem_type": "single_label_classification",
|
| 31 |
+
"qkv_bias": true,
|
| 32 |
+
"transformers_version": "4.57.6"
|
| 33 |
+
}
|
checkpoint-105/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60e2fb8dc592b62760a79927d649b4a38f924ebe90ca0aaabb83589884c43430
|
| 3 |
+
size 343223968
|
checkpoint-105/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf906f097374bea01ec87d4d9711dfb3df62aef3c124ccb8619accd18ad4859c
|
| 3 |
+
size 686563723
|
checkpoint-105/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5564fcbf811625fd6d5252789722a2ca3ec1764e8d1a2d6bc90df7a2b5f7b9b
|
| 3 |
+
size 14391
|
checkpoint-105/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e49ac915fe173059ad0332c04ef46c53409c44f5c9709cd71748a9ec601be04
|
| 3 |
+
size 1465
|
checkpoint-105/trainer_state.json
ADDED
|
@@ -0,0 +1,104 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 105,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.2857142857142857,
|
| 14 |
+
"grad_norm": 6.8948283195495605,
|
| 15 |
+
"learning_rate": 2.7428571428571428e-05,
|
| 16 |
+
"loss": 1.44,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.5714285714285714,
|
| 21 |
+
"grad_norm": 5.060886383056641,
|
| 22 |
+
"learning_rate": 2.4571428571428572e-05,
|
| 23 |
+
"loss": 0.6458,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.8571428571428571,
|
| 28 |
+
"grad_norm": 5.317773342132568,
|
| 29 |
+
"learning_rate": 2.1714285714285715e-05,
|
| 30 |
+
"loss": 0.5486,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 1.1428571428571428,
|
| 35 |
+
"grad_norm": 1.5327340364456177,
|
| 36 |
+
"learning_rate": 1.8857142857142856e-05,
|
| 37 |
+
"loss": 0.2922,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.4285714285714286,
|
| 42 |
+
"grad_norm": 5.422910213470459,
|
| 43 |
+
"learning_rate": 1.6e-05,
|
| 44 |
+
"loss": 0.1456,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.7142857142857144,
|
| 49 |
+
"grad_norm": 6.254992961883545,
|
| 50 |
+
"learning_rate": 1.3142857142857143e-05,
|
| 51 |
+
"loss": 0.1324,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 2.0,
|
| 56 |
+
"grad_norm": 1.4883731603622437,
|
| 57 |
+
"learning_rate": 1.0285714285714286e-05,
|
| 58 |
+
"loss": 0.1583,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 2.2857142857142856,
|
| 63 |
+
"grad_norm": 0.4062122404575348,
|
| 64 |
+
"learning_rate": 7.428571428571429e-06,
|
| 65 |
+
"loss": 0.0331,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 2.571428571428571,
|
| 70 |
+
"grad_norm": 0.2686053514480591,
|
| 71 |
+
"learning_rate": 4.571428571428572e-06,
|
| 72 |
+
"loss": 0.0317,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 2.857142857142857,
|
| 77 |
+
"grad_norm": 0.3767339885234833,
|
| 78 |
+
"learning_rate": 1.7142857142857143e-06,
|
| 79 |
+
"loss": 0.0101,
|
| 80 |
+
"step": 100
|
| 81 |
+
}
|
| 82 |
+
],
|
| 83 |
+
"logging_steps": 10,
|
| 84 |
+
"max_steps": 105,
|
| 85 |
+
"num_input_tokens_seen": 0,
|
| 86 |
+
"num_train_epochs": 3,
|
| 87 |
+
"save_steps": 500,
|
| 88 |
+
"stateful_callbacks": {
|
| 89 |
+
"TrainerControl": {
|
| 90 |
+
"args": {
|
| 91 |
+
"should_epoch_stop": false,
|
| 92 |
+
"should_evaluate": false,
|
| 93 |
+
"should_log": false,
|
| 94 |
+
"should_save": true,
|
| 95 |
+
"should_training_stop": true
|
| 96 |
+
},
|
| 97 |
+
"attributes": {}
|
| 98 |
+
}
|
| 99 |
+
},
|
| 100 |
+
"total_flos": 6.369841546319462e+16,
|
| 101 |
+
"train_batch_size": 8,
|
| 102 |
+
"trial_name": null,
|
| 103 |
+
"trial_params": null
|
| 104 |
+
}
|
checkpoint-105/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d7c6fe48640fc2240f09e91591f89a93c23e9f1a84bff38a52fc6da5133acea2
|
| 3 |
+
size 5841
|
checkpoint-35/config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"ViTForImageClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.0,
|
| 6 |
+
"dtype": "float32",
|
| 7 |
+
"encoder_stride": 16,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.0,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "normal",
|
| 13 |
+
"1": "nsfw"
|
| 14 |
+
},
|
| 15 |
+
"image_size": 224,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 3072,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"normal": "0",
|
| 20 |
+
"nsfw": "1"
|
| 21 |
+
},
|
| 22 |
+
"layer_norm_eps": 1e-12,
|
| 23 |
+
"model_type": "vit",
|
| 24 |
+
"num_attention_heads": 12,
|
| 25 |
+
"num_channels": 3,
|
| 26 |
+
"num_hidden_layers": 12,
|
| 27 |
+
"patch_size": 16,
|
| 28 |
+
"pooler_act": "tanh",
|
| 29 |
+
"pooler_output_size": 768,
|
| 30 |
+
"problem_type": "single_label_classification",
|
| 31 |
+
"qkv_bias": true,
|
| 32 |
+
"transformers_version": "4.57.6"
|
| 33 |
+
}
|
checkpoint-35/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f08a91b468698c90a6dac176af009c41bf51b1fd5759336f42bcca798cdc4798
|
| 3 |
+
size 343223968
|
checkpoint-35/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:584232bf77d570e9bb0288d55c5918e06f6618e1e2ddadda5b21e07eacdf7546
|
| 3 |
+
size 686563723
|
checkpoint-35/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9492333f043fcb0e714313e810389b7109eb06011003261950b184ef9b60d26
|
| 3 |
+
size 14391
|
checkpoint-35/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48c9e5dbad548f6ad246659c82435983771da4ee4e744aaf0981623efeeab59c
|
| 3 |
+
size 1465
|
checkpoint-35/trainer_state.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 35,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.2857142857142857,
|
| 14 |
+
"grad_norm": 6.8948283195495605,
|
| 15 |
+
"learning_rate": 2.7428571428571428e-05,
|
| 16 |
+
"loss": 1.44,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.5714285714285714,
|
| 21 |
+
"grad_norm": 5.060886383056641,
|
| 22 |
+
"learning_rate": 2.4571428571428572e-05,
|
| 23 |
+
"loss": 0.6458,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.8571428571428571,
|
| 28 |
+
"grad_norm": 5.317773342132568,
|
| 29 |
+
"learning_rate": 2.1714285714285715e-05,
|
| 30 |
+
"loss": 0.5486,
|
| 31 |
+
"step": 30
|
| 32 |
+
}
|
| 33 |
+
],
|
| 34 |
+
"logging_steps": 10,
|
| 35 |
+
"max_steps": 105,
|
| 36 |
+
"num_input_tokens_seen": 0,
|
| 37 |
+
"num_train_epochs": 3,
|
| 38 |
+
"save_steps": 500,
|
| 39 |
+
"stateful_callbacks": {
|
| 40 |
+
"TrainerControl": {
|
| 41 |
+
"args": {
|
| 42 |
+
"should_epoch_stop": false,
|
| 43 |
+
"should_evaluate": false,
|
| 44 |
+
"should_log": false,
|
| 45 |
+
"should_save": true,
|
| 46 |
+
"should_training_stop": false
|
| 47 |
+
},
|
| 48 |
+
"attributes": {}
|
| 49 |
+
}
|
| 50 |
+
},
|
| 51 |
+
"total_flos": 2.123280515439821e+16,
|
| 52 |
+
"train_batch_size": 8,
|
| 53 |
+
"trial_name": null,
|
| 54 |
+
"trial_params": null
|
| 55 |
+
}
|
checkpoint-35/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d7c6fe48640fc2240f09e91591f89a93c23e9f1a84bff38a52fc6da5133acea2
|
| 3 |
+
size 5841
|
checkpoint-70/config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"ViTForImageClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.0,
|
| 6 |
+
"dtype": "float32",
|
| 7 |
+
"encoder_stride": 16,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.0,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "normal",
|
| 13 |
+
"1": "nsfw"
|
| 14 |
+
},
|
| 15 |
+
"image_size": 224,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 3072,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"normal": "0",
|
| 20 |
+
"nsfw": "1"
|
| 21 |
+
},
|
| 22 |
+
"layer_norm_eps": 1e-12,
|
| 23 |
+
"model_type": "vit",
|
| 24 |
+
"num_attention_heads": 12,
|
| 25 |
+
"num_channels": 3,
|
| 26 |
+
"num_hidden_layers": 12,
|
| 27 |
+
"patch_size": 16,
|
| 28 |
+
"pooler_act": "tanh",
|
| 29 |
+
"pooler_output_size": 768,
|
| 30 |
+
"problem_type": "single_label_classification",
|
| 31 |
+
"qkv_bias": true,
|
| 32 |
+
"transformers_version": "4.57.6"
|
| 33 |
+
}
|
checkpoint-70/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:291e44ae0dd733fd50195a2a8a7a82728a71e63e8a81f0d0bd82ecfed9140631
|
| 3 |
+
size 343223968
|
checkpoint-70/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e0592d39df3358621954701aaa9ed15e8c6ef8cea7a2a7f0a3df1765e023ed8
|
| 3 |
+
size 686563723
|
checkpoint-70/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af5222a7b879e3e79bce2a9b398df7898f0bf84f140d150ba1478ae072972a5a
|
| 3 |
+
size 14391
|
checkpoint-70/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0774b6bfaf45425427766979cfe59c29db934fd98dc5c88bf852de18b3e5d52
|
| 3 |
+
size 1465
|
checkpoint-70/trainer_state.json
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 70,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.2857142857142857,
|
| 14 |
+
"grad_norm": 6.8948283195495605,
|
| 15 |
+
"learning_rate": 2.7428571428571428e-05,
|
| 16 |
+
"loss": 1.44,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.5714285714285714,
|
| 21 |
+
"grad_norm": 5.060886383056641,
|
| 22 |
+
"learning_rate": 2.4571428571428572e-05,
|
| 23 |
+
"loss": 0.6458,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.8571428571428571,
|
| 28 |
+
"grad_norm": 5.317773342132568,
|
| 29 |
+
"learning_rate": 2.1714285714285715e-05,
|
| 30 |
+
"loss": 0.5486,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 1.1428571428571428,
|
| 35 |
+
"grad_norm": 1.5327340364456177,
|
| 36 |
+
"learning_rate": 1.8857142857142856e-05,
|
| 37 |
+
"loss": 0.2922,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.4285714285714286,
|
| 42 |
+
"grad_norm": 5.422910213470459,
|
| 43 |
+
"learning_rate": 1.6e-05,
|
| 44 |
+
"loss": 0.1456,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.7142857142857144,
|
| 49 |
+
"grad_norm": 6.254992961883545,
|
| 50 |
+
"learning_rate": 1.3142857142857143e-05,
|
| 51 |
+
"loss": 0.1324,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 2.0,
|
| 56 |
+
"grad_norm": 1.4883731603622437,
|
| 57 |
+
"learning_rate": 1.0285714285714286e-05,
|
| 58 |
+
"loss": 0.1583,
|
| 59 |
+
"step": 70
|
| 60 |
+
}
|
| 61 |
+
],
|
| 62 |
+
"logging_steps": 10,
|
| 63 |
+
"max_steps": 105,
|
| 64 |
+
"num_input_tokens_seen": 0,
|
| 65 |
+
"num_train_epochs": 3,
|
| 66 |
+
"save_steps": 500,
|
| 67 |
+
"stateful_callbacks": {
|
| 68 |
+
"TrainerControl": {
|
| 69 |
+
"args": {
|
| 70 |
+
"should_epoch_stop": false,
|
| 71 |
+
"should_evaluate": false,
|
| 72 |
+
"should_log": false,
|
| 73 |
+
"should_save": true,
|
| 74 |
+
"should_training_stop": false
|
| 75 |
+
},
|
| 76 |
+
"attributes": {}
|
| 77 |
+
}
|
| 78 |
+
},
|
| 79 |
+
"total_flos": 4.246561030879642e+16,
|
| 80 |
+
"train_batch_size": 8,
|
| 81 |
+
"trial_name": null,
|
| 82 |
+
"trial_params": null
|
| 83 |
+
}
|
checkpoint-70/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d7c6fe48640fc2240f09e91591f89a93c23e9f1a84bff38a52fc6da5133acea2
|
| 3 |
+
size 5841
|
config.json
CHANGED
|
@@ -1,33 +1,33 @@
|
|
| 1 |
-
{
|
| 2 |
-
"architectures": [
|
| 3 |
-
"ViTForImageClassification"
|
| 4 |
-
],
|
| 5 |
-
"attention_probs_dropout_prob": 0.0,
|
| 6 |
-
"dtype": "float32",
|
| 7 |
-
"encoder_stride": 16,
|
| 8 |
-
"hidden_act": "gelu",
|
| 9 |
-
"hidden_dropout_prob": 0.0,
|
| 10 |
-
"hidden_size": 768,
|
| 11 |
-
"id2label": {
|
| 12 |
-
"0": "normal",
|
| 13 |
-
"1": "nsfw"
|
| 14 |
-
},
|
| 15 |
-
"image_size": 224,
|
| 16 |
-
"initializer_range": 0.02,
|
| 17 |
-
"intermediate_size": 3072,
|
| 18 |
-
"label2id": {
|
| 19 |
-
"normal": "0",
|
| 20 |
-
"nsfw": "1"
|
| 21 |
-
},
|
| 22 |
-
"layer_norm_eps": 1e-12,
|
| 23 |
-
"model_type": "vit",
|
| 24 |
-
"num_attention_heads": 12,
|
| 25 |
-
"num_channels": 3,
|
| 26 |
-
"num_hidden_layers": 12,
|
| 27 |
-
"patch_size": 16,
|
| 28 |
-
"pooler_act": "tanh",
|
| 29 |
-
"pooler_output_size": 768,
|
| 30 |
-
"problem_type": "single_label_classification",
|
| 31 |
-
"qkv_bias": true,
|
| 32 |
-
"transformers_version": "4.57.
|
| 33 |
-
}
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"ViTForImageClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.0,
|
| 6 |
+
"dtype": "float32",
|
| 7 |
+
"encoder_stride": 16,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.0,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "normal",
|
| 13 |
+
"1": "nsfw"
|
| 14 |
+
},
|
| 15 |
+
"image_size": 224,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 3072,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"normal": "0",
|
| 20 |
+
"nsfw": "1"
|
| 21 |
+
},
|
| 22 |
+
"layer_norm_eps": 1e-12,
|
| 23 |
+
"model_type": "vit",
|
| 24 |
+
"num_attention_heads": 12,
|
| 25 |
+
"num_channels": 3,
|
| 26 |
+
"num_hidden_layers": 12,
|
| 27 |
+
"patch_size": 16,
|
| 28 |
+
"pooler_act": "tanh",
|
| 29 |
+
"pooler_output_size": 768,
|
| 30 |
+
"problem_type": "single_label_classification",
|
| 31 |
+
"qkv_bias": true,
|
| 32 |
+
"transformers_version": "4.57.6"
|
| 33 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 343223968
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60e2fb8dc592b62760a79927d649b4a38f924ebe90ca0aaabb83589884c43430
|
| 3 |
size 343223968
|
preprocessor_config.json
CHANGED
|
@@ -1,23 +1,23 @@
|
|
| 1 |
-
{
|
| 2 |
-
"do_convert_rgb": null,
|
| 3 |
-
"do_normalize": true,
|
| 4 |
-
"do_rescale": true,
|
| 5 |
-
"do_resize": true,
|
| 6 |
-
"image_mean": [
|
| 7 |
-
0.5,
|
| 8 |
-
0.5,
|
| 9 |
-
0.5
|
| 10 |
-
],
|
| 11 |
-
"image_processor_type": "ViTImageProcessor",
|
| 12 |
-
"image_std": [
|
| 13 |
-
0.5,
|
| 14 |
-
0.5,
|
| 15 |
-
0.5
|
| 16 |
-
],
|
| 17 |
-
"resample": 2,
|
| 18 |
-
"rescale_factor": 0.00392156862745098,
|
| 19 |
-
"size": {
|
| 20 |
-
"height": 224,
|
| 21 |
-
"width": 224
|
| 22 |
-
}
|
| 23 |
-
}
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": null,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.5,
|
| 8 |
+
0.5,
|
| 9 |
+
0.5
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "ViTImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.5,
|
| 14 |
+
0.5,
|
| 15 |
+
0.5
|
| 16 |
+
],
|
| 17 |
+
"resample": 2,
|
| 18 |
+
"rescale_factor": 0.00392156862745098,
|
| 19 |
+
"size": {
|
| 20 |
+
"height": 224,
|
| 21 |
+
"width": 224
|
| 22 |
+
}
|
| 23 |
+
}
|