Upload folder using huggingface_hub
Browse files- checkpoint-10164/config.json +124 -0
- checkpoint-10164/model.safetensors +3 -0
- checkpoint-10164/optimizer.pt +3 -0
- checkpoint-10164/preprocessor_config.json +22 -0
- checkpoint-10164/rng_state.pth +3 -0
- checkpoint-10164/scheduler.pt +3 -0
- checkpoint-10164/trainer_state.json +209 -0
- checkpoint-10164/training_args.bin +3 -0
- model.safetensors +1 -1
- training_args.bin +1 -1
checkpoint-10164/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": "4.42.4"
|
124 |
+
}
|
checkpoint-10164/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b0df2157bb08488aa22ecdae7586ea53776b24c55d50814bb23e8501642c21d9
|
3 |
+
size 343365480
|
checkpoint-10164/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba4909a0590746ef607d7f9766d9278c841123132ced95fa2d0a5ce64601e496
|
3 |
+
size 686851461
|
checkpoint-10164/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-10164/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:649ec9a1c287c7ff5853257363d0ac083dd3e9b3fef0e21e79976fb03006194f
|
3 |
+
size 14575
|
checkpoint-10164/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bcb792081ca522b9358c97c5042f0451bc7ca5061290fca5dd43951effffcca4
|
3 |
+
size 627
|
checkpoint-10164/trainer_state.json
ADDED
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.572628378868103,
|
3 |
+
"best_model_checkpoint": "cat_breed_image_detection/checkpoint-10164",
|
4 |
+
"epoch": 4.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 10164,
|
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": 8.132095336914062,
|
14 |
+
"learning_rate": 8.599564959462131e-07,
|
15 |
+
"loss": 1.6107,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.39354584809130266,
|
20 |
+
"grad_norm": 6.708084583282471,
|
21 |
+
"learning_rate": 8.154637136642278e-07,
|
22 |
+
"loss": 1.5888,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.5903187721369539,
|
27 |
+
"grad_norm": 7.669999122619629,
|
28 |
+
"learning_rate": 7.709709313822424e-07,
|
29 |
+
"loss": 1.5734,
|
30 |
+
"step": 1500
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.7870916961826053,
|
34 |
+
"grad_norm": 8.473257064819336,
|
35 |
+
"learning_rate": 7.26478149100257e-07,
|
36 |
+
"loss": 1.5921,
|
37 |
+
"step": 2000
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.9838646202282566,
|
41 |
+
"grad_norm": 7.519883155822754,
|
42 |
+
"learning_rate": 6.819853668182716e-07,
|
43 |
+
"loss": 1.5814,
|
44 |
+
"step": 2500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.0,
|
48 |
+
"eval_accuracy": 0.583766976675524,
|
49 |
+
"eval_loss": 1.6136096715927124,
|
50 |
+
"eval_runtime": 1206.4218,
|
51 |
+
"eval_samples_per_second": 89.839,
|
52 |
+
"eval_steps_per_second": 2.807,
|
53 |
+
"step": 2541
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 1.1806375442739079,
|
57 |
+
"grad_norm": 6.776809215545654,
|
58 |
+
"learning_rate": 6.374925845362863e-07,
|
59 |
+
"loss": 1.5698,
|
60 |
+
"step": 3000
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 1.3774104683195592,
|
64 |
+
"grad_norm": 5.961708068847656,
|
65 |
+
"learning_rate": 5.929998022543009e-07,
|
66 |
+
"loss": 1.5564,
|
67 |
+
"step": 3500
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"epoch": 1.5741833923652107,
|
71 |
+
"grad_norm": 7.470553398132324,
|
72 |
+
"learning_rate": 5.485070199723155e-07,
|
73 |
+
"loss": 1.5616,
|
74 |
+
"step": 4000
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 1.770956316410862,
|
78 |
+
"grad_norm": 6.852038383483887,
|
79 |
+
"learning_rate": 5.040142376903302e-07,
|
80 |
+
"loss": 1.5534,
|
81 |
+
"step": 4500
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 1.9677292404565132,
|
85 |
+
"grad_norm": 8.469923973083496,
|
86 |
+
"learning_rate": 4.5952145540834485e-07,
|
87 |
+
"loss": 1.5467,
|
88 |
+
"step": 5000
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 2.0,
|
92 |
+
"eval_accuracy": 0.5894412459403602,
|
93 |
+
"eval_loss": 1.5893911123275757,
|
94 |
+
"eval_runtime": 1210.5447,
|
95 |
+
"eval_samples_per_second": 89.533,
|
96 |
+
"eval_steps_per_second": 2.798,
|
97 |
+
"step": 5082
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 2.1645021645021645,
|
101 |
+
"grad_norm": 6.9930195808410645,
|
102 |
+
"learning_rate": 4.150286731263595e-07,
|
103 |
+
"loss": 1.5455,
|
104 |
+
"step": 5500
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 2.3612750885478158,
|
108 |
+
"grad_norm": 8.173332214355469,
|
109 |
+
"learning_rate": 3.705358908443741e-07,
|
110 |
+
"loss": 1.5393,
|
111 |
+
"step": 6000
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 2.558048012593467,
|
115 |
+
"grad_norm": 5.5481767654418945,
|
116 |
+
"learning_rate": 3.2604310856238877e-07,
|
117 |
+
"loss": 1.5412,
|
118 |
+
"step": 6500
|
119 |
+
},
|
120 |
+
{
|
121 |
+
"epoch": 2.7548209366391183,
|
122 |
+
"grad_norm": 6.221193313598633,
|
123 |
+
"learning_rate": 2.815503262804034e-07,
|
124 |
+
"loss": 1.531,
|
125 |
+
"step": 7000
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 2.9515938606847696,
|
129 |
+
"grad_norm": 6.431015968322754,
|
130 |
+
"learning_rate": 2.37057543998418e-07,
|
131 |
+
"loss": 1.5297,
|
132 |
+
"step": 7500
|
133 |
+
},
|
134 |
+
{
|
135 |
+
"epoch": 3.0,
|
136 |
+
"eval_accuracy": 0.5934916592855034,
|
137 |
+
"eval_loss": 1.5773507356643677,
|
138 |
+
"eval_runtime": 1196.383,
|
139 |
+
"eval_samples_per_second": 90.593,
|
140 |
+
"eval_steps_per_second": 2.831,
|
141 |
+
"step": 7623
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 3.1483667847304213,
|
145 |
+
"grad_norm": 10.443075180053711,
|
146 |
+
"learning_rate": 1.9256476171643265e-07,
|
147 |
+
"loss": 1.5376,
|
148 |
+
"step": 8000
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"epoch": 3.3451397087760726,
|
152 |
+
"grad_norm": 6.658329010009766,
|
153 |
+
"learning_rate": 1.4807197943444728e-07,
|
154 |
+
"loss": 1.5207,
|
155 |
+
"step": 8500
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 3.541912632821724,
|
159 |
+
"grad_norm": 6.124561786651611,
|
160 |
+
"learning_rate": 1.0357919715246192e-07,
|
161 |
+
"loss": 1.5225,
|
162 |
+
"step": 9000
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 3.738685556867375,
|
166 |
+
"grad_norm": 7.456569194793701,
|
167 |
+
"learning_rate": 5.9086414870476566e-08,
|
168 |
+
"loss": 1.5198,
|
169 |
+
"step": 9500
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"epoch": 3.9354584809130264,
|
173 |
+
"grad_norm": 6.399494647979736,
|
174 |
+
"learning_rate": 1.4593632588491198e-08,
|
175 |
+
"loss": 1.5279,
|
176 |
+
"step": 10000
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 4.0,
|
180 |
+
"eval_accuracy": 0.5949955713020372,
|
181 |
+
"eval_loss": 1.572628378868103,
|
182 |
+
"eval_runtime": 1198.3774,
|
183 |
+
"eval_samples_per_second": 90.442,
|
184 |
+
"eval_steps_per_second": 2.826,
|
185 |
+
"step": 10164
|
186 |
+
}
|
187 |
+
],
|
188 |
+
"logging_steps": 500,
|
189 |
+
"max_steps": 10164,
|
190 |
+
"num_input_tokens_seen": 0,
|
191 |
+
"num_train_epochs": 4,
|
192 |
+
"save_steps": 500,
|
193 |
+
"stateful_callbacks": {
|
194 |
+
"TrainerControl": {
|
195 |
+
"args": {
|
196 |
+
"should_epoch_stop": false,
|
197 |
+
"should_evaluate": false,
|
198 |
+
"should_log": false,
|
199 |
+
"should_save": true,
|
200 |
+
"should_training_stop": true
|
201 |
+
},
|
202 |
+
"attributes": {}
|
203 |
+
}
|
204 |
+
},
|
205 |
+
"total_flos": 5.0414127158862545e+19,
|
206 |
+
"train_batch_size": 64,
|
207 |
+
"trial_name": null,
|
208 |
+
"trial_params": null
|
209 |
+
}
|
checkpoint-10164/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7038f06b241e4c336bbada2433c50f59bc04ec8c51993fbe3e8837885274dc54
|
3 |
+
size 4603
|
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:b0df2157bb08488aa22ecdae7586ea53776b24c55d50814bb23e8501642c21d9
|
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 4603
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7038f06b241e4c336bbada2433c50f59bc04ec8c51993fbe3e8837885274dc54
|
3 |
size 4603
|