Upload folder using huggingface_hub
Browse files- checkpoint-3806/config.json +94 -0
- checkpoint-3806/model.safetensors +3 -0
- checkpoint-3806/optimizer.pt +3 -0
- checkpoint-3806/preprocessor_config.json +24 -0
- checkpoint-3806/rng_state.pth +3 -0
- checkpoint-3806/scheduler.pt +3 -0
- checkpoint-3806/trainer_state.json +93 -0
- checkpoint-3806/training_args.bin +3 -0
- config.json +94 -0
- model.safetensors +3 -0
- preprocessor_config.json +24 -0
- training_args.bin +3 -0
checkpoint-3806/config.json
ADDED
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"SiglipForImageClassification"
|
4 |
+
],
|
5 |
+
"id2label": {
|
6 |
+
"0": "A",
|
7 |
+
"1": "B",
|
8 |
+
"2": "C",
|
9 |
+
"3": "D",
|
10 |
+
"4": "E",
|
11 |
+
"5": "F",
|
12 |
+
"6": "G",
|
13 |
+
"7": "H",
|
14 |
+
"8": "I",
|
15 |
+
"9": "J",
|
16 |
+
"10": "K",
|
17 |
+
"11": "L",
|
18 |
+
"12": "M",
|
19 |
+
"13": "N",
|
20 |
+
"14": "O",
|
21 |
+
"15": "P",
|
22 |
+
"16": "Q",
|
23 |
+
"17": "R",
|
24 |
+
"18": "S",
|
25 |
+
"19": "T",
|
26 |
+
"20": "U",
|
27 |
+
"21": "V",
|
28 |
+
"22": "W",
|
29 |
+
"23": "X",
|
30 |
+
"24": "Y",
|
31 |
+
"25": "Z"
|
32 |
+
},
|
33 |
+
"initializer_factor": 1.0,
|
34 |
+
"label2id": {
|
35 |
+
"A": 0,
|
36 |
+
"B": 1,
|
37 |
+
"C": 2,
|
38 |
+
"D": 3,
|
39 |
+
"E": 4,
|
40 |
+
"F": 5,
|
41 |
+
"G": 6,
|
42 |
+
"H": 7,
|
43 |
+
"I": 8,
|
44 |
+
"J": 9,
|
45 |
+
"K": 10,
|
46 |
+
"L": 11,
|
47 |
+
"M": 12,
|
48 |
+
"N": 13,
|
49 |
+
"O": 14,
|
50 |
+
"P": 15,
|
51 |
+
"Q": 16,
|
52 |
+
"R": 17,
|
53 |
+
"S": 18,
|
54 |
+
"T": 19,
|
55 |
+
"U": 20,
|
56 |
+
"V": 21,
|
57 |
+
"W": 22,
|
58 |
+
"X": 23,
|
59 |
+
"Y": 24,
|
60 |
+
"Z": 25
|
61 |
+
},
|
62 |
+
"model_type": "siglip",
|
63 |
+
"problem_type": "single_label_classification",
|
64 |
+
"text_config": {
|
65 |
+
"attention_dropout": 0.0,
|
66 |
+
"hidden_act": "gelu_pytorch_tanh",
|
67 |
+
"hidden_size": 768,
|
68 |
+
"intermediate_size": 3072,
|
69 |
+
"layer_norm_eps": 1e-06,
|
70 |
+
"max_position_embeddings": 64,
|
71 |
+
"model_type": "siglip_text_model",
|
72 |
+
"num_attention_heads": 12,
|
73 |
+
"num_hidden_layers": 12,
|
74 |
+
"projection_size": 768,
|
75 |
+
"torch_dtype": "float32",
|
76 |
+
"vocab_size": 256000
|
77 |
+
},
|
78 |
+
"torch_dtype": "float32",
|
79 |
+
"transformers_version": "4.51.0.dev0",
|
80 |
+
"vision_config": {
|
81 |
+
"attention_dropout": 0.0,
|
82 |
+
"hidden_act": "gelu_pytorch_tanh",
|
83 |
+
"hidden_size": 768,
|
84 |
+
"image_size": 224,
|
85 |
+
"intermediate_size": 3072,
|
86 |
+
"layer_norm_eps": 1e-06,
|
87 |
+
"model_type": "siglip_vision_model",
|
88 |
+
"num_attention_heads": 12,
|
89 |
+
"num_channels": 3,
|
90 |
+
"num_hidden_layers": 12,
|
91 |
+
"patch_size": 16,
|
92 |
+
"torch_dtype": "float32"
|
93 |
+
}
|
94 |
+
}
|
checkpoint-3806/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4587facaf0b143a91070961f2c25fa4c99109cff99f178212e4408afe6c98be
|
3 |
+
size 371641824
|
checkpoint-3806/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c9fb67aa9ac490a53667f6057ab76e9ef0d2e0767932828ec725edb241b87bf
|
3 |
+
size 686703354
|
checkpoint-3806/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-3806/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab2fc19926ae2fb56788f4cb06febb63c3388b74df520678d8fd466f8a18ab49
|
3 |
+
size 14244
|
checkpoint-3806/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b560ef76704b06b8ae457fb1452fa10b2f86ddf16745b55b61b88edb8899516
|
3 |
+
size 1064
|
checkpoint-3806/trainer_state.json
ADDED
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_global_step": 3806,
|
3 |
+
"best_metric": 0.0015409403713420033,
|
4 |
+
"best_model_checkpoint": "Alphabetical-Sign-Language-Detection/checkpoint-3806",
|
5 |
+
"epoch": 1.0,
|
6 |
+
"eval_steps": 500,
|
7 |
+
"global_step": 3806,
|
8 |
+
"is_hyper_param_search": false,
|
9 |
+
"is_local_process_zero": true,
|
10 |
+
"is_world_process_zero": true,
|
11 |
+
"log_history": [
|
12 |
+
{
|
13 |
+
"epoch": 0.13137151865475566,
|
14 |
+
"grad_norm": 47.51639175415039,
|
15 |
+
"learning_rate": 1.7603833865814697e-06,
|
16 |
+
"loss": 1.4084,
|
17 |
+
"step": 500
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 0.2627430373095113,
|
21 |
+
"grad_norm": 36.14832305908203,
|
22 |
+
"learning_rate": 1.494142705005325e-06,
|
23 |
+
"loss": 0.0758,
|
24 |
+
"step": 1000
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.3941145559642669,
|
28 |
+
"grad_norm": 0.47897106409072876,
|
29 |
+
"learning_rate": 1.22790202342918e-06,
|
30 |
+
"loss": 0.0253,
|
31 |
+
"step": 1500
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.5254860746190226,
|
35 |
+
"grad_norm": 0.23500379920005798,
|
36 |
+
"learning_rate": 9.616613418530351e-07,
|
37 |
+
"loss": 0.0174,
|
38 |
+
"step": 2000
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.6568575932737782,
|
42 |
+
"grad_norm": 14.302626609802246,
|
43 |
+
"learning_rate": 6.954206602768902e-07,
|
44 |
+
"loss": 0.0099,
|
45 |
+
"step": 2500
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.7882291119285338,
|
49 |
+
"grad_norm": 0.023673132061958313,
|
50 |
+
"learning_rate": 4.2917997870074544e-07,
|
51 |
+
"loss": 0.0053,
|
52 |
+
"step": 3000
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 0.9196006305832896,
|
56 |
+
"grad_norm": 0.13073758780956268,
|
57 |
+
"learning_rate": 1.6293929712460063e-07,
|
58 |
+
"loss": 0.0038,
|
59 |
+
"step": 3500
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 1.0,
|
63 |
+
"eval_accuracy": 0.9995811741904754,
|
64 |
+
"eval_loss": 0.0015409403713420033,
|
65 |
+
"eval_model_preparation_time": 0.0024,
|
66 |
+
"eval_runtime": 1508.1295,
|
67 |
+
"eval_samples_per_second": 80.742,
|
68 |
+
"eval_steps_per_second": 10.093,
|
69 |
+
"step": 3806
|
70 |
+
}
|
71 |
+
],
|
72 |
+
"logging_steps": 500,
|
73 |
+
"max_steps": 3806,
|
74 |
+
"num_input_tokens_seen": 0,
|
75 |
+
"num_train_epochs": 1,
|
76 |
+
"save_steps": 500,
|
77 |
+
"stateful_callbacks": {
|
78 |
+
"TrainerControl": {
|
79 |
+
"args": {
|
80 |
+
"should_epoch_stop": false,
|
81 |
+
"should_evaluate": false,
|
82 |
+
"should_log": false,
|
83 |
+
"should_save": true,
|
84 |
+
"should_training_stop": true
|
85 |
+
},
|
86 |
+
"attributes": {}
|
87 |
+
}
|
88 |
+
},
|
89 |
+
"total_flos": 1.0200852722126868e+19,
|
90 |
+
"train_batch_size": 32,
|
91 |
+
"trial_name": null,
|
92 |
+
"trial_params": null
|
93 |
+
}
|
checkpoint-3806/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:20111e84a551ea8aa40b7c13479cf0a63c273323121e66cd5b3dd0143f930ed7
|
3 |
+
size 5304
|
config.json
ADDED
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"SiglipForImageClassification"
|
4 |
+
],
|
5 |
+
"id2label": {
|
6 |
+
"0": "A",
|
7 |
+
"1": "B",
|
8 |
+
"2": "C",
|
9 |
+
"3": "D",
|
10 |
+
"4": "E",
|
11 |
+
"5": "F",
|
12 |
+
"6": "G",
|
13 |
+
"7": "H",
|
14 |
+
"8": "I",
|
15 |
+
"9": "J",
|
16 |
+
"10": "K",
|
17 |
+
"11": "L",
|
18 |
+
"12": "M",
|
19 |
+
"13": "N",
|
20 |
+
"14": "O",
|
21 |
+
"15": "P",
|
22 |
+
"16": "Q",
|
23 |
+
"17": "R",
|
24 |
+
"18": "S",
|
25 |
+
"19": "T",
|
26 |
+
"20": "U",
|
27 |
+
"21": "V",
|
28 |
+
"22": "W",
|
29 |
+
"23": "X",
|
30 |
+
"24": "Y",
|
31 |
+
"25": "Z"
|
32 |
+
},
|
33 |
+
"initializer_factor": 1.0,
|
34 |
+
"label2id": {
|
35 |
+
"A": 0,
|
36 |
+
"B": 1,
|
37 |
+
"C": 2,
|
38 |
+
"D": 3,
|
39 |
+
"E": 4,
|
40 |
+
"F": 5,
|
41 |
+
"G": 6,
|
42 |
+
"H": 7,
|
43 |
+
"I": 8,
|
44 |
+
"J": 9,
|
45 |
+
"K": 10,
|
46 |
+
"L": 11,
|
47 |
+
"M": 12,
|
48 |
+
"N": 13,
|
49 |
+
"O": 14,
|
50 |
+
"P": 15,
|
51 |
+
"Q": 16,
|
52 |
+
"R": 17,
|
53 |
+
"S": 18,
|
54 |
+
"T": 19,
|
55 |
+
"U": 20,
|
56 |
+
"V": 21,
|
57 |
+
"W": 22,
|
58 |
+
"X": 23,
|
59 |
+
"Y": 24,
|
60 |
+
"Z": 25
|
61 |
+
},
|
62 |
+
"model_type": "siglip",
|
63 |
+
"problem_type": "single_label_classification",
|
64 |
+
"text_config": {
|
65 |
+
"attention_dropout": 0.0,
|
66 |
+
"hidden_act": "gelu_pytorch_tanh",
|
67 |
+
"hidden_size": 768,
|
68 |
+
"intermediate_size": 3072,
|
69 |
+
"layer_norm_eps": 1e-06,
|
70 |
+
"max_position_embeddings": 64,
|
71 |
+
"model_type": "siglip_text_model",
|
72 |
+
"num_attention_heads": 12,
|
73 |
+
"num_hidden_layers": 12,
|
74 |
+
"projection_size": 768,
|
75 |
+
"torch_dtype": "float32",
|
76 |
+
"vocab_size": 256000
|
77 |
+
},
|
78 |
+
"torch_dtype": "float32",
|
79 |
+
"transformers_version": "4.51.0.dev0",
|
80 |
+
"vision_config": {
|
81 |
+
"attention_dropout": 0.0,
|
82 |
+
"hidden_act": "gelu_pytorch_tanh",
|
83 |
+
"hidden_size": 768,
|
84 |
+
"image_size": 224,
|
85 |
+
"intermediate_size": 3072,
|
86 |
+
"layer_norm_eps": 1e-06,
|
87 |
+
"model_type": "siglip_vision_model",
|
88 |
+
"num_attention_heads": 12,
|
89 |
+
"num_channels": 3,
|
90 |
+
"num_hidden_layers": 12,
|
91 |
+
"patch_size": 16,
|
92 |
+
"torch_dtype": "float32"
|
93 |
+
}
|
94 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4587facaf0b143a91070961f2c25fa4c99109cff99f178212e4408afe6c98be
|
3 |
+
size 371641824
|
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 sha256:20111e84a551ea8aa40b7c13479cf0a63c273323121e66cd5b3dd0143f930ed7
|
3 |
+
size 5304
|