Upload folder using huggingface_hub
Browse files- checkpoint-556/config.json +50 -0
- checkpoint-556/model.safetensors +3 -0
- checkpoint-556/optimizer.pt +3 -0
- checkpoint-556/preprocessor_config.json +24 -0
- checkpoint-556/rng_state.pth +3 -0
- checkpoint-556/scheduler.pt +3 -0
- checkpoint-556/trainer_state.json +51 -0
- checkpoint-556/training_args.bin +3 -0
- config.json +50 -0
- model.safetensors +3 -0
- preprocessor_config.json +24 -0
- training_args.bin +3 -0
checkpoint-556/config.json
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"SiglipForImageClassification"
|
4 |
+
],
|
5 |
+
"id2label": {
|
6 |
+
"0": "Anime Portrait",
|
7 |
+
"1": "Cartoon Portrait",
|
8 |
+
"2": "Real Portrait",
|
9 |
+
"3": "Sketch Portrait"
|
10 |
+
},
|
11 |
+
"initializer_factor": 1.0,
|
12 |
+
"label2id": {
|
13 |
+
"Anime Portrait": 0,
|
14 |
+
"Cartoon Portrait": 1,
|
15 |
+
"Real Portrait": 2,
|
16 |
+
"Sketch Portrait": 3
|
17 |
+
},
|
18 |
+
"model_type": "siglip",
|
19 |
+
"problem_type": "single_label_classification",
|
20 |
+
"text_config": {
|
21 |
+
"attention_dropout": 0.0,
|
22 |
+
"hidden_act": "gelu_pytorch_tanh",
|
23 |
+
"hidden_size": 768,
|
24 |
+
"intermediate_size": 3072,
|
25 |
+
"layer_norm_eps": 1e-06,
|
26 |
+
"max_position_embeddings": 64,
|
27 |
+
"model_type": "siglip_text_model",
|
28 |
+
"num_attention_heads": 12,
|
29 |
+
"num_hidden_layers": 12,
|
30 |
+
"projection_size": 768,
|
31 |
+
"torch_dtype": "float32",
|
32 |
+
"vocab_size": 256000
|
33 |
+
},
|
34 |
+
"torch_dtype": "float32",
|
35 |
+
"transformers_version": "4.50.3",
|
36 |
+
"vision_config": {
|
37 |
+
"attention_dropout": 0.0,
|
38 |
+
"hidden_act": "gelu_pytorch_tanh",
|
39 |
+
"hidden_size": 768,
|
40 |
+
"image_size": 224,
|
41 |
+
"intermediate_size": 3072,
|
42 |
+
"layer_norm_eps": 1e-06,
|
43 |
+
"model_type": "siglip_vision_model",
|
44 |
+
"num_attention_heads": 12,
|
45 |
+
"num_channels": 3,
|
46 |
+
"num_hidden_layers": 12,
|
47 |
+
"patch_size": 16,
|
48 |
+
"torch_dtype": "float32"
|
49 |
+
}
|
50 |
+
}
|
checkpoint-556/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1364f1642175cfd4f7679aabac20bc65eb55ffdaa31ff2c441c9f668d7a9de1
|
3 |
+
size 371574144
|
checkpoint-556/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0d34855df5fd43a18cf6b12e503a0eb445813038330fae709e5c09ce3ab27d4
|
3 |
+
size 686568058
|
checkpoint-556/preprocessor_config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "SiglipImageProcessor",
|
12 |
+
"image_std": [
|
13 |
+
0.5,
|
14 |
+
0.5,
|
15 |
+
0.5
|
16 |
+
],
|
17 |
+
"processor_class": "SiglipProcessor",
|
18 |
+
"resample": 2,
|
19 |
+
"rescale_factor": 0.00392156862745098,
|
20 |
+
"size": {
|
21 |
+
"height": 224,
|
22 |
+
"width": 224
|
23 |
+
}
|
24 |
+
}
|
checkpoint-556/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:31ceb574d358fb0bc7675f0da40bab90e9214170e44128d4ddb3b3b39f42e425
|
3 |
+
size 14244
|
checkpoint-556/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dbed97058cc9728cf640945eda73cfa20bd3265a2cf129111caa60b73daea19f
|
3 |
+
size 1064
|
checkpoint-556/trainer_state.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_global_step": 556,
|
3 |
+
"best_metric": 0.013590352609753609,
|
4 |
+
"best_model_checkpoint": "siglip2-finetune-full/checkpoint-556",
|
5 |
+
"epoch": 1.0,
|
6 |
+
"eval_steps": 500,
|
7 |
+
"global_step": 556,
|
8 |
+
"is_hyper_param_search": false,
|
9 |
+
"is_local_process_zero": true,
|
10 |
+
"is_world_process_zero": true,
|
11 |
+
"log_history": [
|
12 |
+
{
|
13 |
+
"epoch": 0.8992805755395683,
|
14 |
+
"grad_norm": 0.036306124180555344,
|
15 |
+
"learning_rate": 2.213438735177866e-05,
|
16 |
+
"loss": 0.1388,
|
17 |
+
"step": 500
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 1.0,
|
21 |
+
"eval_accuracy": 0.9971872187218722,
|
22 |
+
"eval_loss": 0.013590352609753609,
|
23 |
+
"eval_model_preparation_time": 0.0023,
|
24 |
+
"eval_runtime": 396.8915,
|
25 |
+
"eval_samples_per_second": 44.788,
|
26 |
+
"eval_steps_per_second": 5.599,
|
27 |
+
"step": 556
|
28 |
+
}
|
29 |
+
],
|
30 |
+
"logging_steps": 500,
|
31 |
+
"max_steps": 556,
|
32 |
+
"num_input_tokens_seen": 0,
|
33 |
+
"num_train_epochs": 1,
|
34 |
+
"save_steps": 500,
|
35 |
+
"stateful_callbacks": {
|
36 |
+
"TrainerControl": {
|
37 |
+
"args": {
|
38 |
+
"should_epoch_stop": false,
|
39 |
+
"should_evaluate": false,
|
40 |
+
"should_log": false,
|
41 |
+
"should_save": true,
|
42 |
+
"should_training_stop": true
|
43 |
+
},
|
44 |
+
"attributes": {}
|
45 |
+
}
|
46 |
+
},
|
47 |
+
"total_flos": 1.48886238587034e+18,
|
48 |
+
"train_batch_size": 32,
|
49 |
+
"trial_name": null,
|
50 |
+
"trial_params": null
|
51 |
+
}
|
checkpoint-556/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d4c770425a87a246a23d3c502bf8f3c828b56b14006baa33b1dd089416ffc39
|
3 |
+
size 5304
|
config.json
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"SiglipForImageClassification"
|
4 |
+
],
|
5 |
+
"id2label": {
|
6 |
+
"0": "Anime Portrait",
|
7 |
+
"1": "Cartoon Portrait",
|
8 |
+
"2": "Real Portrait",
|
9 |
+
"3": "Sketch Portrait"
|
10 |
+
},
|
11 |
+
"initializer_factor": 1.0,
|
12 |
+
"label2id": {
|
13 |
+
"Anime Portrait": 0,
|
14 |
+
"Cartoon Portrait": 1,
|
15 |
+
"Real Portrait": 2,
|
16 |
+
"Sketch Portrait": 3
|
17 |
+
},
|
18 |
+
"model_type": "siglip",
|
19 |
+
"problem_type": "single_label_classification",
|
20 |
+
"text_config": {
|
21 |
+
"attention_dropout": 0.0,
|
22 |
+
"hidden_act": "gelu_pytorch_tanh",
|
23 |
+
"hidden_size": 768,
|
24 |
+
"intermediate_size": 3072,
|
25 |
+
"layer_norm_eps": 1e-06,
|
26 |
+
"max_position_embeddings": 64,
|
27 |
+
"model_type": "siglip_text_model",
|
28 |
+
"num_attention_heads": 12,
|
29 |
+
"num_hidden_layers": 12,
|
30 |
+
"projection_size": 768,
|
31 |
+
"torch_dtype": "float32",
|
32 |
+
"vocab_size": 256000
|
33 |
+
},
|
34 |
+
"torch_dtype": "float32",
|
35 |
+
"transformers_version": "4.50.3",
|
36 |
+
"vision_config": {
|
37 |
+
"attention_dropout": 0.0,
|
38 |
+
"hidden_act": "gelu_pytorch_tanh",
|
39 |
+
"hidden_size": 768,
|
40 |
+
"image_size": 224,
|
41 |
+
"intermediate_size": 3072,
|
42 |
+
"layer_norm_eps": 1e-06,
|
43 |
+
"model_type": "siglip_vision_model",
|
44 |
+
"num_attention_heads": 12,
|
45 |
+
"num_channels": 3,
|
46 |
+
"num_hidden_layers": 12,
|
47 |
+
"patch_size": 16,
|
48 |
+
"torch_dtype": "float32"
|
49 |
+
}
|
50 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1364f1642175cfd4f7679aabac20bc65eb55ffdaa31ff2c441c9f668d7a9de1
|
3 |
+
size 371574144
|
preprocessor_config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "SiglipImageProcessor",
|
12 |
+
"image_std": [
|
13 |
+
0.5,
|
14 |
+
0.5,
|
15 |
+
0.5
|
16 |
+
],
|
17 |
+
"processor_class": "SiglipProcessor",
|
18 |
+
"resample": 2,
|
19 |
+
"rescale_factor": 0.00392156862745098,
|
20 |
+
"size": {
|
21 |
+
"height": 224,
|
22 |
+
"width": 224
|
23 |
+
}
|
24 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d4c770425a87a246a23d3c502bf8f3c828b56b14006baa33b1dd089416ffc39
|
3 |
+
size 5304
|