Upload folder using huggingface_hub
Browse files- checkpoint-7623/config.json +124 -0
- checkpoint-7623/model.safetensors +3 -0
- checkpoint-7623/optimizer.pt +3 -0
- checkpoint-7623/preprocessor_config.json +22 -0
- checkpoint-7623/rng_state.pth +3 -0
- checkpoint-7623/scheduler.pt +3 -0
- checkpoint-7623/trainer_state.json +168 -0
- checkpoint-7623/training_args.bin +3 -0
- model.safetensors +1 -1
- training_args.bin +1 -1
checkpoint-7623/config.json
ADDED
@@ -0,0 +1,124 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dima806/cat_breed_image_detection",
|
3 |
+
"architectures": [
|
4 |
+
"ViTForImageClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"encoder_stride": 16,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.0,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "Abyssinian",
|
13 |
+
"1": "American Bobtail",
|
14 |
+
"2": "American Curl",
|
15 |
+
"3": "American Shorthair",
|
16 |
+
"4": "Applehead Siamese",
|
17 |
+
"5": "Balinese",
|
18 |
+
"6": "Bengal",
|
19 |
+
"7": "Birman",
|
20 |
+
"8": "Bombay",
|
21 |
+
"9": "British Shorthair",
|
22 |
+
"10": "Burmese",
|
23 |
+
"11": "Calico",
|
24 |
+
"12": "Cornish Rex",
|
25 |
+
"13": "Devon Rex",
|
26 |
+
"14": "Dilute Calico",
|
27 |
+
"15": "Dilute Tortoiseshell",
|
28 |
+
"16": "Domestic Long Hair",
|
29 |
+
"17": "Domestic Medium Hair",
|
30 |
+
"18": "Domestic Short Hair",
|
31 |
+
"19": "Egyptian Mau",
|
32 |
+
"20": "Exotic Shorthair",
|
33 |
+
"21": "Extra-Toes Cat - Hemingway Polydactyl",
|
34 |
+
"22": "Havana",
|
35 |
+
"23": "Himalayan",
|
36 |
+
"24": "Japanese Bobtail",
|
37 |
+
"25": "Maine Coon",
|
38 |
+
"26": "Manx",
|
39 |
+
"27": "Munchkin",
|
40 |
+
"28": "Nebelung",
|
41 |
+
"29": "Norwegian Forest",
|
42 |
+
"30": "Oriental Short Hair",
|
43 |
+
"31": "Persian",
|
44 |
+
"32": "Ragamuffin",
|
45 |
+
"33": "Ragdoll",
|
46 |
+
"34": "Russian Blue",
|
47 |
+
"35": "Scottish Fold",
|
48 |
+
"36": "Siamese",
|
49 |
+
"37": "Siberian",
|
50 |
+
"38": "Snowshoe",
|
51 |
+
"39": "Sphynx",
|
52 |
+
"40": "Tabby",
|
53 |
+
"41": "Tiger",
|
54 |
+
"42": "Tonkinese",
|
55 |
+
"43": "Torbie",
|
56 |
+
"44": "Tortoiseshell",
|
57 |
+
"45": "Turkish Angora",
|
58 |
+
"46": "Turkish Van",
|
59 |
+
"47": "Tuxedo"
|
60 |
+
},
|
61 |
+
"image_size": 224,
|
62 |
+
"initializer_range": 0.02,
|
63 |
+
"intermediate_size": 3072,
|
64 |
+
"label2id": {
|
65 |
+
"Abyssinian": 0,
|
66 |
+
"American Bobtail": 1,
|
67 |
+
"American Curl": 2,
|
68 |
+
"American Shorthair": 3,
|
69 |
+
"Applehead Siamese": 4,
|
70 |
+
"Balinese": 5,
|
71 |
+
"Bengal": 6,
|
72 |
+
"Birman": 7,
|
73 |
+
"Bombay": 8,
|
74 |
+
"British Shorthair": 9,
|
75 |
+
"Burmese": 10,
|
76 |
+
"Calico": 11,
|
77 |
+
"Cornish Rex": 12,
|
78 |
+
"Devon Rex": 13,
|
79 |
+
"Dilute Calico": 14,
|
80 |
+
"Dilute Tortoiseshell": 15,
|
81 |
+
"Domestic Long Hair": 16,
|
82 |
+
"Domestic Medium Hair": 17,
|
83 |
+
"Domestic Short Hair": 18,
|
84 |
+
"Egyptian Mau": 19,
|
85 |
+
"Exotic Shorthair": 20,
|
86 |
+
"Extra-Toes Cat - Hemingway Polydactyl": 21,
|
87 |
+
"Havana": 22,
|
88 |
+
"Himalayan": 23,
|
89 |
+
"Japanese Bobtail": 24,
|
90 |
+
"Maine Coon": 25,
|
91 |
+
"Manx": 26,
|
92 |
+
"Munchkin": 27,
|
93 |
+
"Nebelung": 28,
|
94 |
+
"Norwegian Forest": 29,
|
95 |
+
"Oriental Short Hair": 30,
|
96 |
+
"Persian": 31,
|
97 |
+
"Ragamuffin": 32,
|
98 |
+
"Ragdoll": 33,
|
99 |
+
"Russian Blue": 34,
|
100 |
+
"Scottish Fold": 35,
|
101 |
+
"Siamese": 36,
|
102 |
+
"Siberian": 37,
|
103 |
+
"Snowshoe": 38,
|
104 |
+
"Sphynx": 39,
|
105 |
+
"Tabby": 40,
|
106 |
+
"Tiger": 41,
|
107 |
+
"Tonkinese": 42,
|
108 |
+
"Torbie": 43,
|
109 |
+
"Tortoiseshell": 44,
|
110 |
+
"Turkish Angora": 45,
|
111 |
+
"Turkish Van": 46,
|
112 |
+
"Tuxedo": 47
|
113 |
+
},
|
114 |
+
"layer_norm_eps": 1e-12,
|
115 |
+
"model_type": "vit",
|
116 |
+
"num_attention_heads": 12,
|
117 |
+
"num_channels": 3,
|
118 |
+
"num_hidden_layers": 12,
|
119 |
+
"patch_size": 16,
|
120 |
+
"problem_type": "single_label_classification",
|
121 |
+
"qkv_bias": true,
|
122 |
+
"torch_dtype": "float32",
|
123 |
+
"transformers_version": "4.43.3"
|
124 |
+
}
|
checkpoint-7623/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cce8ab6dbce6287960ea5fdf6432aa92c141bb2348dd8f398cd88288f69143a4
|
3 |
+
size 343365480
|
checkpoint-7623/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d2d6db04e237478c0203eb0fc447ab351526e0c29985b727d7453dab5a5cad2
|
3 |
+
size 686851461
|
checkpoint-7623/preprocessor_config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"do_rescale": true,
|
4 |
+
"do_resize": true,
|
5 |
+
"image_mean": [
|
6 |
+
0.5,
|
7 |
+
0.5,
|
8 |
+
0.5
|
9 |
+
],
|
10 |
+
"image_processor_type": "ViTImageProcessor",
|
11 |
+
"image_std": [
|
12 |
+
0.5,
|
13 |
+
0.5,
|
14 |
+
0.5
|
15 |
+
],
|
16 |
+
"resample": 2,
|
17 |
+
"rescale_factor": 0.00392156862745098,
|
18 |
+
"size": {
|
19 |
+
"height": 224,
|
20 |
+
"width": 224
|
21 |
+
}
|
22 |
+
}
|
checkpoint-7623/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:993ea6245e253edfa8c23bc982cde0c4b23b0b26e82553342a493d0d0931cc05
|
3 |
+
size 14575
|
checkpoint-7623/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f696e75fe8786dd955df182ba81df65ab470f5e0a95e7c49ab1518f21aa6499f
|
3 |
+
size 627
|
checkpoint-7623/trainer_state.json
ADDED
@@ -0,0 +1,168 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.488718032836914,
|
3 |
+
"best_model_checkpoint": "cat_breed_image_detection/checkpoint-7623",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 7623,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.19677292404565133,
|
13 |
+
"grad_norm": 8.220705032348633,
|
14 |
+
"learning_rate": 8.465205334741845e-07,
|
15 |
+
"loss": 1.4752,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.39354584809130266,
|
20 |
+
"grad_norm": 7.696910858154297,
|
21 |
+
"learning_rate": 7.870989040010564e-07,
|
22 |
+
"loss": 1.4833,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.5903187721369539,
|
27 |
+
"grad_norm": 7.823228359222412,
|
28 |
+
"learning_rate": 7.276772745279281e-07,
|
29 |
+
"loss": 1.4728,
|
30 |
+
"step": 1500
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.7870916961826053,
|
34 |
+
"grad_norm": 6.080297946929932,
|
35 |
+
"learning_rate": 6.682556450547999e-07,
|
36 |
+
"loss": 1.4901,
|
37 |
+
"step": 2000
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.9838646202282566,
|
41 |
+
"grad_norm": 7.583363056182861,
|
42 |
+
"learning_rate": 6.088340155816718e-07,
|
43 |
+
"loss": 1.4755,
|
44 |
+
"step": 2500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.0,
|
48 |
+
"eval_accuracy": 0.6088537053439622,
|
49 |
+
"eval_loss": 1.5104930400848389,
|
50 |
+
"eval_model_preparation_time": 0.0053,
|
51 |
+
"eval_runtime": 1216.8858,
|
52 |
+
"eval_samples_per_second": 89.067,
|
53 |
+
"eval_steps_per_second": 2.783,
|
54 |
+
"step": 2541
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 1.1806375442739079,
|
58 |
+
"grad_norm": 9.293631553649902,
|
59 |
+
"learning_rate": 5.494123861085435e-07,
|
60 |
+
"loss": 1.4665,
|
61 |
+
"step": 3000
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"epoch": 1.3774104683195592,
|
65 |
+
"grad_norm": 8.063645362854004,
|
66 |
+
"learning_rate": 4.899907566354153e-07,
|
67 |
+
"loss": 1.4613,
|
68 |
+
"step": 3500
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 1.5741833923652107,
|
72 |
+
"grad_norm": 6.942551612854004,
|
73 |
+
"learning_rate": 4.3056912716228705e-07,
|
74 |
+
"loss": 1.4569,
|
75 |
+
"step": 4000
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 1.770956316410862,
|
79 |
+
"grad_norm": 11.436430931091309,
|
80 |
+
"learning_rate": 3.7114749768915883e-07,
|
81 |
+
"loss": 1.4412,
|
82 |
+
"step": 4500
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 1.9677292404565132,
|
86 |
+
"grad_norm": 6.971865177154541,
|
87 |
+
"learning_rate": 3.117258682160306e-07,
|
88 |
+
"loss": 1.4428,
|
89 |
+
"step": 5000
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 2.0,
|
93 |
+
"eval_accuracy": 0.6121660023619723,
|
94 |
+
"eval_loss": 1.4942480325698853,
|
95 |
+
"eval_model_preparation_time": 0.0053,
|
96 |
+
"eval_runtime": 1210.5473,
|
97 |
+
"eval_samples_per_second": 89.533,
|
98 |
+
"eval_steps_per_second": 2.798,
|
99 |
+
"step": 5082
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 2.1645021645021645,
|
103 |
+
"grad_norm": 7.25930643081665,
|
104 |
+
"learning_rate": 2.523042387429024e-07,
|
105 |
+
"loss": 1.4412,
|
106 |
+
"step": 5500
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"epoch": 2.3612750885478158,
|
110 |
+
"grad_norm": 8.07095718383789,
|
111 |
+
"learning_rate": 1.928826092697742e-07,
|
112 |
+
"loss": 1.4362,
|
113 |
+
"step": 6000
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 2.558048012593467,
|
117 |
+
"grad_norm": 8.908621788024902,
|
118 |
+
"learning_rate": 1.3346097979664598e-07,
|
119 |
+
"loss": 1.4375,
|
120 |
+
"step": 6500
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 2.7548209366391183,
|
124 |
+
"grad_norm": 8.16598129272461,
|
125 |
+
"learning_rate": 7.403935032351777e-08,
|
126 |
+
"loss": 1.4397,
|
127 |
+
"step": 7000
|
128 |
+
},
|
129 |
+
{
|
130 |
+
"epoch": 2.9515938606847696,
|
131 |
+
"grad_norm": 9.264542579650879,
|
132 |
+
"learning_rate": 1.4617720850389543e-08,
|
133 |
+
"loss": 1.437,
|
134 |
+
"step": 7500
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 3.0,
|
138 |
+
"eval_accuracy": 0.6130332890463537,
|
139 |
+
"eval_loss": 1.488718032836914,
|
140 |
+
"eval_model_preparation_time": 0.0053,
|
141 |
+
"eval_runtime": 1205.355,
|
142 |
+
"eval_samples_per_second": 89.919,
|
143 |
+
"eval_steps_per_second": 2.81,
|
144 |
+
"step": 7623
|
145 |
+
}
|
146 |
+
],
|
147 |
+
"logging_steps": 500,
|
148 |
+
"max_steps": 7623,
|
149 |
+
"num_input_tokens_seen": 0,
|
150 |
+
"num_train_epochs": 3,
|
151 |
+
"save_steps": 500,
|
152 |
+
"stateful_callbacks": {
|
153 |
+
"TrainerControl": {
|
154 |
+
"args": {
|
155 |
+
"should_epoch_stop": false,
|
156 |
+
"should_evaluate": false,
|
157 |
+
"should_log": false,
|
158 |
+
"should_save": true,
|
159 |
+
"should_training_stop": true
|
160 |
+
},
|
161 |
+
"attributes": {}
|
162 |
+
}
|
163 |
+
},
|
164 |
+
"total_flos": 3.781059536914691e+19,
|
165 |
+
"train_batch_size": 64,
|
166 |
+
"trial_name": null,
|
167 |
+
"trial_params": null
|
168 |
+
}
|
checkpoint-7623/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ddce706ee826114a81e5dc98c1b4a675a40b3cf07bb0062afea81a5ff747285
|
3 |
+
size 4667
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 343365480
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cce8ab6dbce6287960ea5fdf6432aa92c141bb2348dd8f398cd88288f69143a4
|
3 |
size 343365480
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4667
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ddce706ee826114a81e5dc98c1b4a675a40b3cf07bb0062afea81a5ff747285
|
3 |
size 4667
|