Upload folder using huggingface_hub
Browse files- checkpoint-157/config.json +46 -0
- checkpoint-157/model.safetensors +3 -0
- checkpoint-157/optimizer.pt +3 -0
- checkpoint-157/preprocessor_config.json +24 -0
- checkpoint-157/rng_state.pth +3 -0
- checkpoint-157/scheduler.pt +3 -0
- checkpoint-157/trainer_state.json +44 -0
- checkpoint-157/training_args.bin +3 -0
- checkpoint-314/config.json +46 -0
- checkpoint-314/model.safetensors +3 -0
- checkpoint-314/optimizer.pt +3 -0
- checkpoint-314/preprocessor_config.json +24 -0
- checkpoint-314/rng_state.pth +3 -0
- checkpoint-314/scheduler.pt +3 -0
- checkpoint-314/trainer_state.json +54 -0
- checkpoint-314/training_args.bin +3 -0
- config.json +46 -0
- model.safetensors +3 -0
- preprocessor_config.json +24 -0
- training_args.bin +3 -0
checkpoint-157/config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"SiglipForImageClassification"
|
4 |
+
],
|
5 |
+
"id2label": {
|
6 |
+
"0": "Female \u2640",
|
7 |
+
"1": "Male \u2642"
|
8 |
+
},
|
9 |
+
"initializer_factor": 1.0,
|
10 |
+
"label2id": {
|
11 |
+
"Female \u2640": 0,
|
12 |
+
"Male \u2642": 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": "4.51.0.dev0",
|
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-157/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b3c881ec1fe495b6b7b22e0736bb670c36abef535d9173a427e5cbe50ffb9eb
|
3 |
+
size 371567992
|
checkpoint-157/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e42ca61096460c1b7078d91e3d07d3c3b5ddc67fe516b44fdf9643760658696
|
3 |
+
size 686555770
|
checkpoint-157/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-157/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86d5603fb9476ef375dada75dcc320d16423a8b7cade08e44ab0230cd7431cd5
|
3 |
+
size 14244
|
checkpoint-157/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4e52ea243618241f112cfa55bc1203d9492a008fab26d507445786f4e9c80e8
|
3 |
+
size 1064
|
checkpoint-157/trainer_state.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_global_step": 157,
|
3 |
+
"best_metric": 0.11236772686243057,
|
4 |
+
"best_model_checkpoint": "siglip2-finetune-full/checkpoint-157",
|
5 |
+
"epoch": 1.0,
|
6 |
+
"eval_steps": 500,
|
7 |
+
"global_step": 157,
|
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": 0.9614,
|
15 |
+
"eval_loss": 0.11236772686243057,
|
16 |
+
"eval_model_preparation_time": 0.0024,
|
17 |
+
"eval_runtime": 61.0327,
|
18 |
+
"eval_samples_per_second": 81.923,
|
19 |
+
"eval_steps_per_second": 10.24,
|
20 |
+
"step": 157
|
21 |
+
}
|
22 |
+
],
|
23 |
+
"logging_steps": 500,
|
24 |
+
"max_steps": 314,
|
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": 4.1877747910656e+17,
|
41 |
+
"train_batch_size": 32,
|
42 |
+
"trial_name": null,
|
43 |
+
"trial_params": null
|
44 |
+
}
|
checkpoint-157/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60bfe4936cb8662967af80740b170b7ee49a77c617cfb4b4d72cb94fb4856548
|
3 |
+
size 5304
|
checkpoint-314/config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"SiglipForImageClassification"
|
4 |
+
],
|
5 |
+
"id2label": {
|
6 |
+
"0": "Female \u2640",
|
7 |
+
"1": "Male \u2642"
|
8 |
+
},
|
9 |
+
"initializer_factor": 1.0,
|
10 |
+
"label2id": {
|
11 |
+
"Female \u2640": 0,
|
12 |
+
"Male \u2642": 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": "4.51.0.dev0",
|
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-314/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:672245c638f4bced0d3d2c6dc3b4c8e1b936ad88259e443dfbe919a677d3bae3
|
3 |
+
size 371567992
|
checkpoint-314/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca2c61bce314c08c2c635e0305545daff08656f2025c9347f009aa9877b246e3
|
3 |
+
size 686555770
|
checkpoint-314/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-314/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d268ac255a6c083faad4615b0dc4cbdb3cece12ea20b61aa70a45e69eb36fdc
|
3 |
+
size 14244
|
checkpoint-314/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b7714de473690f533461a318746634bcf917a385380970c1b2a5fed17283c74
|
3 |
+
size 1064
|
checkpoint-314/trainer_state.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_global_step": 314,
|
3 |
+
"best_metric": 0.07697099447250366,
|
4 |
+
"best_model_checkpoint": "siglip2-finetune-full/checkpoint-314",
|
5 |
+
"epoch": 2.0,
|
6 |
+
"eval_steps": 500,
|
7 |
+
"global_step": 314,
|
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": 0.9614,
|
15 |
+
"eval_loss": 0.11236772686243057,
|
16 |
+
"eval_model_preparation_time": 0.0024,
|
17 |
+
"eval_runtime": 61.0327,
|
18 |
+
"eval_samples_per_second": 81.923,
|
19 |
+
"eval_steps_per_second": 10.24,
|
20 |
+
"step": 157
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 2.0,
|
24 |
+
"eval_accuracy": 0.972,
|
25 |
+
"eval_loss": 0.07697099447250366,
|
26 |
+
"eval_model_preparation_time": 0.0024,
|
27 |
+
"eval_runtime": 60.4043,
|
28 |
+
"eval_samples_per_second": 82.776,
|
29 |
+
"eval_steps_per_second": 10.347,
|
30 |
+
"step": 314
|
31 |
+
}
|
32 |
+
],
|
33 |
+
"logging_steps": 500,
|
34 |
+
"max_steps": 314,
|
35 |
+
"num_input_tokens_seen": 0,
|
36 |
+
"num_train_epochs": 2,
|
37 |
+
"save_steps": 500,
|
38 |
+
"stateful_callbacks": {
|
39 |
+
"TrainerControl": {
|
40 |
+
"args": {
|
41 |
+
"should_epoch_stop": false,
|
42 |
+
"should_evaluate": false,
|
43 |
+
"should_log": false,
|
44 |
+
"should_save": true,
|
45 |
+
"should_training_stop": true
|
46 |
+
},
|
47 |
+
"attributes": {}
|
48 |
+
}
|
49 |
+
},
|
50 |
+
"total_flos": 8.3755495821312e+17,
|
51 |
+
"train_batch_size": 32,
|
52 |
+
"trial_name": null,
|
53 |
+
"trial_params": null
|
54 |
+
}
|
checkpoint-314/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60bfe4936cb8662967af80740b170b7ee49a77c617cfb4b4d72cb94fb4856548
|
3 |
+
size 5304
|
config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"SiglipForImageClassification"
|
4 |
+
],
|
5 |
+
"id2label": {
|
6 |
+
"0": "Female \u2640",
|
7 |
+
"1": "Male \u2642"
|
8 |
+
},
|
9 |
+
"initializer_factor": 1.0,
|
10 |
+
"label2id": {
|
11 |
+
"Female \u2640": 0,
|
12 |
+
"Male \u2642": 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": "4.51.0.dev0",
|
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 sha256:672245c638f4bced0d3d2c6dc3b4c8e1b936ad88259e443dfbe919a677d3bae3
|
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 sha256:60bfe4936cb8662967af80740b170b7ee49a77c617cfb4b4d72cb94fb4856548
|
3 |
+
size 5304
|