Upload folder using huggingface_hub
Browse files- checkpoint-208/config.json +46 -0
- checkpoint-208/model.safetensors +3 -0
- checkpoint-208/optimizer.pt +3 -0
- checkpoint-208/preprocessor_config.json +24 -0
- checkpoint-208/rng_state.pth +3 -0
- checkpoint-208/scheduler.pt +3 -0
- checkpoint-208/trainer_state.json +44 -0
- checkpoint-208/training_args.bin +3 -0
- checkpoint-416/config.json +46 -0
- checkpoint-416/model.safetensors +3 -0
- checkpoint-416/optimizer.pt +3 -0
- checkpoint-416/preprocessor_config.json +24 -0
- checkpoint-416/rng_state.pth +3 -0
- checkpoint-416/scheduler.pt +3 -0
- checkpoint-416/trainer_state.json +54 -0
- checkpoint-416/training_args.bin +3 -0
- config.json +46 -0
- model.safetensors +3 -0
- preprocessor_config.json +24 -0
- training_args.bin +3 -0
checkpoint-208/config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"SiglipForImageClassification"
|
4 |
+
],
|
5 |
+
"id2label": {
|
6 |
+
"0": "biting",
|
7 |
+
"1": "no biting"
|
8 |
+
},
|
9 |
+
"initializer_factor": 1.0,
|
10 |
+
"label2id": {
|
11 |
+
"biting": 0,
|
12 |
+
"no biting": 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-208/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c79539e2675d963f19f5b13b97ea51aa8246945944db27db4c43075a11c3db12
|
3 |
+
size 371567992
|
checkpoint-208/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b75992c64e9911fe9db9fcaaa016594acd72d5e5b41317cc961e27b87e4bdd7f
|
3 |
+
size 686555770
|
checkpoint-208/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-208/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56713906e50cc3640058ecf67a107854792fddb56442162f65b434bf2918fc19
|
3 |
+
size 14244
|
checkpoint-208/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3a12c5a7d9b870b80abfdb55c5a66a3fb21e649b6dc60c3d4829d8c6526c235
|
3 |
+
size 1064
|
checkpoint-208/trainer_state.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_global_step": 208,
|
3 |
+
"best_metric": 0.7102543711662292,
|
4 |
+
"best_model_checkpoint": "siglip2-finetune-full/checkpoint-208",
|
5 |
+
"epoch": 1.0,
|
6 |
+
"eval_steps": 500,
|
7 |
+
"global_step": 208,
|
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": 0.5183285563433399,
|
15 |
+
"eval_loss": 0.7102543711662292,
|
16 |
+
"eval_model_preparation_time": 0.0025,
|
17 |
+
"eval_runtime": 83.451,
|
18 |
+
"eval_samples_per_second": 79.436,
|
19 |
+
"eval_steps_per_second": 9.934,
|
20 |
+
"step": 208
|
21 |
+
}
|
22 |
+
],
|
23 |
+
"logging_steps": 500,
|
24 |
+
"max_steps": 416,
|
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": 5.5521518179947725e+17,
|
41 |
+
"train_batch_size": 32,
|
42 |
+
"trial_name": null,
|
43 |
+
"trial_params": null
|
44 |
+
}
|
checkpoint-208/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:206d195b28a5a4e1f61804a2eec06b109a4be9fa8d841f4d552fca404cebe15f
|
3 |
+
size 5304
|
checkpoint-416/config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"SiglipForImageClassification"
|
4 |
+
],
|
5 |
+
"id2label": {
|
6 |
+
"0": "biting",
|
7 |
+
"1": "no biting"
|
8 |
+
},
|
9 |
+
"initializer_factor": 1.0,
|
10 |
+
"label2id": {
|
11 |
+
"biting": 0,
|
12 |
+
"no biting": 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-416/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e60b72a9ca548a7b2207a5618b15766b5533715e777938dbedbfd571dff8400
|
3 |
+
size 371567992
|
checkpoint-416/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e1477880d5768ebc9a43cd4d2feae1d3d52df7b3baea3632d621c23ae4f902f
|
3 |
+
size 686555770
|
checkpoint-416/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-416/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30128f956ffacadb88f7cf5618fe0a2146045314e2a02bde7eca56205a9a67c7
|
3 |
+
size 14244
|
checkpoint-416/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bdc263a9f9611b19bd5578692a89cdfab97826a1462e341c1f06283240becc2b
|
3 |
+
size 1064
|
checkpoint-416/trainer_state.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_global_step": 416,
|
3 |
+
"best_metric": 0.28768205642700195,
|
4 |
+
"best_model_checkpoint": "siglip2-finetune-full/checkpoint-416",
|
5 |
+
"epoch": 2.0,
|
6 |
+
"eval_steps": 500,
|
7 |
+
"global_step": 416,
|
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": 0.5183285563433399,
|
15 |
+
"eval_loss": 0.7102543711662292,
|
16 |
+
"eval_model_preparation_time": 0.0025,
|
17 |
+
"eval_runtime": 83.451,
|
18 |
+
"eval_samples_per_second": 79.436,
|
19 |
+
"eval_steps_per_second": 9.934,
|
20 |
+
"step": 208
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 2.0,
|
24 |
+
"eval_accuracy": 0.887615024890632,
|
25 |
+
"eval_loss": 0.28768205642700195,
|
26 |
+
"eval_model_preparation_time": 0.0025,
|
27 |
+
"eval_runtime": 84.0354,
|
28 |
+
"eval_samples_per_second": 78.883,
|
29 |
+
"eval_steps_per_second": 9.865,
|
30 |
+
"step": 416
|
31 |
+
}
|
32 |
+
],
|
33 |
+
"logging_steps": 500,
|
34 |
+
"max_steps": 416,
|
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": 1.1104303635989545e+18,
|
51 |
+
"train_batch_size": 32,
|
52 |
+
"trial_name": null,
|
53 |
+
"trial_params": null
|
54 |
+
}
|
checkpoint-416/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:206d195b28a5a4e1f61804a2eec06b109a4be9fa8d841f4d552fca404cebe15f
|
3 |
+
size 5304
|
config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"SiglipForImageClassification"
|
4 |
+
],
|
5 |
+
"id2label": {
|
6 |
+
"0": "biting",
|
7 |
+
"1": "no biting"
|
8 |
+
},
|
9 |
+
"initializer_factor": 1.0,
|
10 |
+
"label2id": {
|
11 |
+
"biting": 0,
|
12 |
+
"no biting": 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 sha256:9e60b72a9ca548a7b2207a5618b15766b5533715e777938dbedbfd571dff8400
|
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 sha256:206d195b28a5a4e1f61804a2eec06b109a4be9fa8d841f4d552fca404cebe15f
|
3 |
+
size 5304
|