Upload folder using huggingface_hub
Browse files- checkpoint-369/config.json +46 -0
- checkpoint-369/model.safetensors +3 -0
- checkpoint-369/optimizer.pt +3 -0
- checkpoint-369/preprocessor_config.json +24 -0
- checkpoint-369/rng_state.pth +3 -0
- checkpoint-369/scheduler.pt +3 -0
- checkpoint-369/trainer_state.json +44 -0
- checkpoint-369/training_args.bin +3 -0
- checkpoint-738/config.json +46 -0
- checkpoint-738/model.safetensors +3 -0
- checkpoint-738/optimizer.pt +3 -0
- checkpoint-738/preprocessor_config.json +24 -0
- checkpoint-738/rng_state.pth +3 -0
- checkpoint-738/scheduler.pt +3 -0
- checkpoint-738/trainer_state.json +61 -0
- checkpoint-738/training_args.bin +3 -0
- config.json +46 -0
- model.safetensors +3 -0
- preprocessor_config.json +24 -0
- training_args.bin +3 -0
checkpoint-369/config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"SiglipForImageClassification"
|
4 |
+
],
|
5 |
+
"id2label": {
|
6 |
+
"0": "Face_Mask Found",
|
7 |
+
"1": "Face_Mask Not_Found"
|
8 |
+
},
|
9 |
+
"initializer_factor": 1.0,
|
10 |
+
"label2id": {
|
11 |
+
"Face_Mask Found": 0,
|
12 |
+
"Face_Mask Not_Found": 1
|
13 |
+
},
|
14 |
+
"model_type": "siglip",
|
15 |
+
"problem_type": "single_label_classification",
|
16 |
+
"text_config": {
|
17 |
+
"attention_dropout": 0.0,
|
18 |
+
"hidden_act": "gelu_pytorch_tanh",
|
19 |
+
"hidden_size": 768,
|
20 |
+
"intermediate_size": 3072,
|
21 |
+
"layer_norm_eps": 1e-06,
|
22 |
+
"max_position_embeddings": 64,
|
23 |
+
"model_type": "siglip_text_model",
|
24 |
+
"num_attention_heads": 12,
|
25 |
+
"num_hidden_layers": 12,
|
26 |
+
"projection_size": 768,
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"vocab_size": 256000
|
29 |
+
},
|
30 |
+
"torch_dtype": "float32",
|
31 |
+
"transformers_version": "4.50.0",
|
32 |
+
"vision_config": {
|
33 |
+
"attention_dropout": 0.0,
|
34 |
+
"hidden_act": "gelu_pytorch_tanh",
|
35 |
+
"hidden_size": 768,
|
36 |
+
"image_size": 224,
|
37 |
+
"intermediate_size": 3072,
|
38 |
+
"layer_norm_eps": 1e-06,
|
39 |
+
"model_type": "siglip_vision_model",
|
40 |
+
"num_attention_heads": 12,
|
41 |
+
"num_channels": 3,
|
42 |
+
"num_hidden_layers": 12,
|
43 |
+
"patch_size": 16,
|
44 |
+
"torch_dtype": "float32"
|
45 |
+
}
|
46 |
+
}
|
checkpoint-369/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b4991dd5ba6a0e06008bedbfaeb6207db9ade853a870204ac5146bcf6060f93
|
3 |
+
size 371567992
|
checkpoint-369/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e607fbcc63973d66aea2bbe1393dd442e4e6a36bf048c85901418fb2ff76d446
|
3 |
+
size 686555770
|
checkpoint-369/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-369/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e5efde2046afd61240470db72c8cbef39bbda7a6fcf1c8af7fa102a21eb25a5
|
3 |
+
size 14244
|
checkpoint-369/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c1072f5d575f49f060858e14dd3d01072cbd8cdbc2c3608b972cb436acb3eab
|
3 |
+
size 1064
|
checkpoint-369/trainer_state.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_global_step": 369,
|
3 |
+
"best_metric": 0.2595628798007965,
|
4 |
+
"best_model_checkpoint": "siglip2-finetune-full/checkpoint-369",
|
5 |
+
"epoch": 1.0,
|
6 |
+
"eval_steps": 500,
|
7 |
+
"global_step": 369,
|
8 |
+
"is_hyper_param_search": false,
|
9 |
+
"is_local_process_zero": true,
|
10 |
+
"is_world_process_zero": true,
|
11 |
+
"log_history": [
|
12 |
+
{
|
13 |
+
"epoch": 1.0,
|
14 |
+
"eval_accuracy": 0.9029850746268657,
|
15 |
+
"eval_loss": 0.2595628798007965,
|
16 |
+
"eval_model_preparation_time": 0.0022,
|
17 |
+
"eval_runtime": 150.3008,
|
18 |
+
"eval_samples_per_second": 78.456,
|
19 |
+
"eval_steps_per_second": 9.807,
|
20 |
+
"step": 369
|
21 |
+
}
|
22 |
+
],
|
23 |
+
"logging_steps": 500,
|
24 |
+
"max_steps": 738,
|
25 |
+
"num_input_tokens_seen": 0,
|
26 |
+
"num_train_epochs": 2,
|
27 |
+
"save_steps": 500,
|
28 |
+
"stateful_callbacks": {
|
29 |
+
"TrainerControl": {
|
30 |
+
"args": {
|
31 |
+
"should_epoch_stop": false,
|
32 |
+
"should_evaluate": false,
|
33 |
+
"should_log": false,
|
34 |
+
"should_save": true,
|
35 |
+
"should_training_stop": false
|
36 |
+
},
|
37 |
+
"attributes": {}
|
38 |
+
}
|
39 |
+
},
|
40 |
+
"total_flos": 9.876448067249111e+17,
|
41 |
+
"train_batch_size": 32,
|
42 |
+
"trial_name": null,
|
43 |
+
"trial_params": null
|
44 |
+
}
|
checkpoint-369/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9615cd46396eb75d8e897bc9c7ffa0c7648b70f2a0388208e84c8dbe1846b2a
|
3 |
+
size 5304
|
checkpoint-738/config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"SiglipForImageClassification"
|
4 |
+
],
|
5 |
+
"id2label": {
|
6 |
+
"0": "Face_Mask Found",
|
7 |
+
"1": "Face_Mask Not_Found"
|
8 |
+
},
|
9 |
+
"initializer_factor": 1.0,
|
10 |
+
"label2id": {
|
11 |
+
"Face_Mask Found": 0,
|
12 |
+
"Face_Mask Not_Found": 1
|
13 |
+
},
|
14 |
+
"model_type": "siglip",
|
15 |
+
"problem_type": "single_label_classification",
|
16 |
+
"text_config": {
|
17 |
+
"attention_dropout": 0.0,
|
18 |
+
"hidden_act": "gelu_pytorch_tanh",
|
19 |
+
"hidden_size": 768,
|
20 |
+
"intermediate_size": 3072,
|
21 |
+
"layer_norm_eps": 1e-06,
|
22 |
+
"max_position_embeddings": 64,
|
23 |
+
"model_type": "siglip_text_model",
|
24 |
+
"num_attention_heads": 12,
|
25 |
+
"num_hidden_layers": 12,
|
26 |
+
"projection_size": 768,
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"vocab_size": 256000
|
29 |
+
},
|
30 |
+
"torch_dtype": "float32",
|
31 |
+
"transformers_version": "4.50.0",
|
32 |
+
"vision_config": {
|
33 |
+
"attention_dropout": 0.0,
|
34 |
+
"hidden_act": "gelu_pytorch_tanh",
|
35 |
+
"hidden_size": 768,
|
36 |
+
"image_size": 224,
|
37 |
+
"intermediate_size": 3072,
|
38 |
+
"layer_norm_eps": 1e-06,
|
39 |
+
"model_type": "siglip_vision_model",
|
40 |
+
"num_attention_heads": 12,
|
41 |
+
"num_channels": 3,
|
42 |
+
"num_hidden_layers": 12,
|
43 |
+
"patch_size": 16,
|
44 |
+
"torch_dtype": "float32"
|
45 |
+
}
|
46 |
+
}
|
checkpoint-738/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1aef3979ebaef6a3b90709e4e39114cb3e8ff0d9029fdc4e3f422167c7161062
|
3 |
+
size 371567992
|
checkpoint-738/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f1c9af80eb7375b91002bea98001e5648eeb2eb25fead0bd253a3fb554fdd89
|
3 |
+
size 686555770
|
checkpoint-738/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-738/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05dea197a4ce3ab3e3334423d94cc1080aa17c5ef4c8feb0dfc8acce91ec6c40
|
3 |
+
size 14244
|
checkpoint-738/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57908b47145d8c90eb6016da4d169848a9e88a762b3ea9cb1286106f82a2870c
|
3 |
+
size 1064
|
checkpoint-738/trainer_state.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_global_step": 738,
|
3 |
+
"best_metric": 0.10818483680486679,
|
4 |
+
"best_model_checkpoint": "siglip2-finetune-full/checkpoint-738",
|
5 |
+
"epoch": 2.0,
|
6 |
+
"eval_steps": 500,
|
7 |
+
"global_step": 738,
|
8 |
+
"is_hyper_param_search": false,
|
9 |
+
"is_local_process_zero": true,
|
10 |
+
"is_world_process_zero": true,
|
11 |
+
"log_history": [
|
12 |
+
{
|
13 |
+
"epoch": 1.0,
|
14 |
+
"eval_accuracy": 0.9029850746268657,
|
15 |
+
"eval_loss": 0.2595628798007965,
|
16 |
+
"eval_model_preparation_time": 0.0022,
|
17 |
+
"eval_runtime": 150.3008,
|
18 |
+
"eval_samples_per_second": 78.456,
|
19 |
+
"eval_steps_per_second": 9.807,
|
20 |
+
"step": 369
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 1.3550135501355014,
|
24 |
+
"grad_norm": 0.6212332248687744,
|
25 |
+
"learning_rate": 0.00017296511627906978,
|
26 |
+
"loss": 0.3415,
|
27 |
+
"step": 500
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 2.0,
|
31 |
+
"eval_accuracy": 0.9614145183175034,
|
32 |
+
"eval_loss": 0.10818483680486679,
|
33 |
+
"eval_model_preparation_time": 0.0022,
|
34 |
+
"eval_runtime": 149.8409,
|
35 |
+
"eval_samples_per_second": 78.697,
|
36 |
+
"eval_steps_per_second": 9.837,
|
37 |
+
"step": 738
|
38 |
+
}
|
39 |
+
],
|
40 |
+
"logging_steps": 500,
|
41 |
+
"max_steps": 738,
|
42 |
+
"num_input_tokens_seen": 0,
|
43 |
+
"num_train_epochs": 2,
|
44 |
+
"save_steps": 500,
|
45 |
+
"stateful_callbacks": {
|
46 |
+
"TrainerControl": {
|
47 |
+
"args": {
|
48 |
+
"should_epoch_stop": false,
|
49 |
+
"should_evaluate": false,
|
50 |
+
"should_log": false,
|
51 |
+
"should_save": true,
|
52 |
+
"should_training_stop": true
|
53 |
+
},
|
54 |
+
"attributes": {}
|
55 |
+
}
|
56 |
+
},
|
57 |
+
"total_flos": 1.9752896134498222e+18,
|
58 |
+
"train_batch_size": 32,
|
59 |
+
"trial_name": null,
|
60 |
+
"trial_params": null
|
61 |
+
}
|
checkpoint-738/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9615cd46396eb75d8e897bc9c7ffa0c7648b70f2a0388208e84c8dbe1846b2a
|
3 |
+
size 5304
|
config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"SiglipForImageClassification"
|
4 |
+
],
|
5 |
+
"id2label": {
|
6 |
+
"0": "Face_Mask Found",
|
7 |
+
"1": "Face_Mask Not_Found"
|
8 |
+
},
|
9 |
+
"initializer_factor": 1.0,
|
10 |
+
"label2id": {
|
11 |
+
"Face_Mask Found": 0,
|
12 |
+
"Face_Mask Not_Found": 1
|
13 |
+
},
|
14 |
+
"model_type": "siglip",
|
15 |
+
"problem_type": "single_label_classification",
|
16 |
+
"text_config": {
|
17 |
+
"attention_dropout": 0.0,
|
18 |
+
"hidden_act": "gelu_pytorch_tanh",
|
19 |
+
"hidden_size": 768,
|
20 |
+
"intermediate_size": 3072,
|
21 |
+
"layer_norm_eps": 1e-06,
|
22 |
+
"max_position_embeddings": 64,
|
23 |
+
"model_type": "siglip_text_model",
|
24 |
+
"num_attention_heads": 12,
|
25 |
+
"num_hidden_layers": 12,
|
26 |
+
"projection_size": 768,
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"vocab_size": 256000
|
29 |
+
},
|
30 |
+
"torch_dtype": "float32",
|
31 |
+
"transformers_version": "4.50.0",
|
32 |
+
"vision_config": {
|
33 |
+
"attention_dropout": 0.0,
|
34 |
+
"hidden_act": "gelu_pytorch_tanh",
|
35 |
+
"hidden_size": 768,
|
36 |
+
"image_size": 224,
|
37 |
+
"intermediate_size": 3072,
|
38 |
+
"layer_norm_eps": 1e-06,
|
39 |
+
"model_type": "siglip_vision_model",
|
40 |
+
"num_attention_heads": 12,
|
41 |
+
"num_channels": 3,
|
42 |
+
"num_hidden_layers": 12,
|
43 |
+
"patch_size": 16,
|
44 |
+
"torch_dtype": "float32"
|
45 |
+
}
|
46 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1aef3979ebaef6a3b90709e4e39114cb3e8ff0d9029fdc4e3f422167c7161062
|
3 |
+
size 371567992
|
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:e9615cd46396eb75d8e897bc9c7ffa0c7648b70f2a0388208e84c8dbe1846b2a
|
3 |
+
size 5304
|