Upload folder using huggingface_hub
Browse files- checkpoint-300/config.json +46 -0
- checkpoint-300/optimizer.pt +3 -0
- checkpoint-300/preprocessor_config.json +22 -0
- checkpoint-300/pytorch_model.bin +3 -0
- checkpoint-300/rng_state.pth +3 -0
- checkpoint-300/scheduler.pt +3 -0
- checkpoint-300/trainer_state.json +232 -0
- checkpoint-300/training_args.bin +3 -0
checkpoint-300/config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/vit-large-patch16-224-in21k",
|
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": 1024,
|
11 |
+
"id2label": {
|
12 |
+
"0": "actinic keratosis",
|
13 |
+
"1": "basal cell carcinoma",
|
14 |
+
"2": "dermatofibroma",
|
15 |
+
"3": "melanoma",
|
16 |
+
"4": "nevus",
|
17 |
+
"5": "pigmented benign keratosis",
|
18 |
+
"6": "seborrheic keratosis",
|
19 |
+
"7": "squamous cell carcinoma",
|
20 |
+
"8": "vascular lesion"
|
21 |
+
},
|
22 |
+
"image_size": 224,
|
23 |
+
"initializer_range": 0.02,
|
24 |
+
"intermediate_size": 4096,
|
25 |
+
"label2id": {
|
26 |
+
"actinic keratosis": "0",
|
27 |
+
"basal cell carcinoma": "1",
|
28 |
+
"dermatofibroma": "2",
|
29 |
+
"melanoma": "3",
|
30 |
+
"nevus": "4",
|
31 |
+
"pigmented benign keratosis": "5",
|
32 |
+
"seborrheic keratosis": "6",
|
33 |
+
"squamous cell carcinoma": "7",
|
34 |
+
"vascular lesion": "8"
|
35 |
+
},
|
36 |
+
"layer_norm_eps": 1e-12,
|
37 |
+
"model_type": "vit",
|
38 |
+
"num_attention_heads": 16,
|
39 |
+
"num_channels": 3,
|
40 |
+
"num_hidden_layers": 24,
|
41 |
+
"patch_size": 16,
|
42 |
+
"problem_type": "single_label_classification",
|
43 |
+
"qkv_bias": true,
|
44 |
+
"torch_dtype": "float32",
|
45 |
+
"transformers_version": "4.31.0"
|
46 |
+
}
|
checkpoint-300/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:31720d3722a87bfa3576024552988f138da5919984477b6e88689cde3882a16c
|
3 |
+
size 2426717125
|
checkpoint-300/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": "ViTFeatureExtractor",
|
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-300/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dbc9dc4d0a05ea336343875a05c16f1ed334a312449829c63fa4f661f41b67bb
|
3 |
+
size 1213377325
|
checkpoint-300/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6162bb9db25c89c41e126a7a00a5d0695219447bff9b18d08731531620758440
|
3 |
+
size 14575
|
checkpoint-300/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:721830e5aa293c6d5e8210c5c6712d564a0d312fdcc1bf185213903cbfdcaafd
|
3 |
+
size 627
|
checkpoint-300/trainer_state.json
ADDED
@@ -0,0 +1,232 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.703125,
|
3 |
+
"best_model_checkpoint": "/content/20epcoh1/checkpoint-300",
|
4 |
+
"epoch": 4.0,
|
5 |
+
"global_step": 300,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.13,
|
12 |
+
"learning_rate": 1.2e-05,
|
13 |
+
"loss": 2.1242,
|
14 |
+
"step": 10
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.27,
|
18 |
+
"learning_rate": 2.5333333333333337e-05,
|
19 |
+
"loss": 1.8392,
|
20 |
+
"step": 20
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.4,
|
24 |
+
"learning_rate": 3.866666666666667e-05,
|
25 |
+
"loss": 1.5371,
|
26 |
+
"step": 30
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.53,
|
30 |
+
"learning_rate": 5.2000000000000004e-05,
|
31 |
+
"loss": 1.3264,
|
32 |
+
"step": 40
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.67,
|
36 |
+
"learning_rate": 6.533333333333334e-05,
|
37 |
+
"loss": 1.1148,
|
38 |
+
"step": 50
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.8,
|
42 |
+
"learning_rate": 7.866666666666666e-05,
|
43 |
+
"loss": 0.9979,
|
44 |
+
"step": 60
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.93,
|
48 |
+
"learning_rate": 9.200000000000001e-05,
|
49 |
+
"loss": 1.053,
|
50 |
+
"step": 70
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 1.0,
|
54 |
+
"eval_accuracy": 0.6160714285714286,
|
55 |
+
"eval_loss": 1.0581690073013306,
|
56 |
+
"eval_runtime": 14.56,
|
57 |
+
"eval_samples_per_second": 30.769,
|
58 |
+
"eval_steps_per_second": 3.846,
|
59 |
+
"step": 75
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 1.07,
|
63 |
+
"learning_rate": 0.00010533333333333332,
|
64 |
+
"loss": 0.8613,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 1.2,
|
69 |
+
"learning_rate": 0.00011866666666666669,
|
70 |
+
"loss": 0.9467,
|
71 |
+
"step": 90
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 1.33,
|
75 |
+
"learning_rate": 0.000132,
|
76 |
+
"loss": 0.8097,
|
77 |
+
"step": 100
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"epoch": 1.47,
|
81 |
+
"learning_rate": 0.00014533333333333333,
|
82 |
+
"loss": 0.8538,
|
83 |
+
"step": 110
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 1.6,
|
87 |
+
"learning_rate": 0.00015866666666666668,
|
88 |
+
"loss": 0.887,
|
89 |
+
"step": 120
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 1.73,
|
93 |
+
"learning_rate": 0.000172,
|
94 |
+
"loss": 1.0396,
|
95 |
+
"step": 130
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"epoch": 1.87,
|
99 |
+
"learning_rate": 0.00018533333333333333,
|
100 |
+
"loss": 0.8933,
|
101 |
+
"step": 140
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 2.0,
|
105 |
+
"learning_rate": 0.00019866666666666668,
|
106 |
+
"loss": 1.026,
|
107 |
+
"step": 150
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 2.0,
|
111 |
+
"eval_accuracy": 0.6584821428571429,
|
112 |
+
"eval_loss": 0.9405480623245239,
|
113 |
+
"eval_runtime": 14.9426,
|
114 |
+
"eval_samples_per_second": 29.981,
|
115 |
+
"eval_steps_per_second": 3.748,
|
116 |
+
"step": 150
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 2.13,
|
120 |
+
"learning_rate": 0.00019866666666666668,
|
121 |
+
"loss": 0.78,
|
122 |
+
"step": 160
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 2.27,
|
126 |
+
"learning_rate": 0.0001971851851851852,
|
127 |
+
"loss": 0.6783,
|
128 |
+
"step": 170
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 2.4,
|
132 |
+
"learning_rate": 0.0001957037037037037,
|
133 |
+
"loss": 0.7991,
|
134 |
+
"step": 180
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 2.53,
|
138 |
+
"learning_rate": 0.00019422222222222223,
|
139 |
+
"loss": 0.7667,
|
140 |
+
"step": 190
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 2.67,
|
144 |
+
"learning_rate": 0.00019274074074074075,
|
145 |
+
"loss": 0.7979,
|
146 |
+
"step": 200
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 2.8,
|
150 |
+
"learning_rate": 0.00019125925925925926,
|
151 |
+
"loss": 0.8502,
|
152 |
+
"step": 210
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 2.93,
|
156 |
+
"learning_rate": 0.00018977777777777778,
|
157 |
+
"loss": 0.7942,
|
158 |
+
"step": 220
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 3.0,
|
162 |
+
"eval_accuracy": 0.6339285714285714,
|
163 |
+
"eval_loss": 0.9822031855583191,
|
164 |
+
"eval_runtime": 19.6852,
|
165 |
+
"eval_samples_per_second": 22.758,
|
166 |
+
"eval_steps_per_second": 2.845,
|
167 |
+
"step": 225
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 3.07,
|
171 |
+
"learning_rate": 0.0001882962962962963,
|
172 |
+
"loss": 0.5113,
|
173 |
+
"step": 230
|
174 |
+
},
|
175 |
+
{
|
176 |
+
"epoch": 3.2,
|
177 |
+
"learning_rate": 0.0001868148148148148,
|
178 |
+
"loss": 0.659,
|
179 |
+
"step": 240
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 3.33,
|
183 |
+
"learning_rate": 0.00018533333333333333,
|
184 |
+
"loss": 0.5285,
|
185 |
+
"step": 250
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 3.47,
|
189 |
+
"learning_rate": 0.00018385185185185185,
|
190 |
+
"loss": 0.5316,
|
191 |
+
"step": 260
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 3.6,
|
195 |
+
"learning_rate": 0.00018237037037037036,
|
196 |
+
"loss": 0.5804,
|
197 |
+
"step": 270
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"epoch": 3.73,
|
201 |
+
"learning_rate": 0.0001808888888888889,
|
202 |
+
"loss": 0.6496,
|
203 |
+
"step": 280
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 3.87,
|
207 |
+
"learning_rate": 0.00017940740740740742,
|
208 |
+
"loss": 0.5075,
|
209 |
+
"step": 290
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 4.0,
|
213 |
+
"learning_rate": 0.00017792592592592594,
|
214 |
+
"loss": 0.4856,
|
215 |
+
"step": 300
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 4.0,
|
219 |
+
"eval_accuracy": 0.703125,
|
220 |
+
"eval_loss": 0.831343948841095,
|
221 |
+
"eval_runtime": 16.0292,
|
222 |
+
"eval_samples_per_second": 27.949,
|
223 |
+
"eval_steps_per_second": 3.494,
|
224 |
+
"step": 300
|
225 |
+
}
|
226 |
+
],
|
227 |
+
"max_steps": 1500,
|
228 |
+
"num_train_epochs": 20,
|
229 |
+
"total_flos": 1.962510888920408e+18,
|
230 |
+
"trial_name": null,
|
231 |
+
"trial_params": null
|
232 |
+
}
|
checkpoint-300/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bcc6635480980fd135dda8f3b75ff6d865400187841ae3ab2b75105d55109a44
|
3 |
+
size 3963
|