Upload folder using huggingface_hub
Browse files- config.json +4 -6
- optimizer.pt +2 -2
- pytorch_model.bin +2 -2
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +178 -79
- training_args.bin +1 -1
config.json
CHANGED
|
@@ -9,17 +9,15 @@
|
|
| 9 |
"hidden_dropout_prob": 0.0,
|
| 10 |
"hidden_size": 768,
|
| 11 |
"id2label": {
|
| 12 |
-
"0": "
|
| 13 |
-
"1": "
|
| 14 |
-
"2": "NoTumor"
|
| 15 |
},
|
| 16 |
"image_size": 224,
|
| 17 |
"initializer_range": 0.02,
|
| 18 |
"intermediate_size": 3072,
|
| 19 |
"label2id": {
|
| 20 |
-
"
|
| 21 |
-
"
|
| 22 |
-
"NoTumor": "2"
|
| 23 |
},
|
| 24 |
"layer_norm_eps": 1e-12,
|
| 25 |
"model_type": "vit",
|
|
|
|
| 9 |
"hidden_dropout_prob": 0.0,
|
| 10 |
"hidden_size": 768,
|
| 11 |
"id2label": {
|
| 12 |
+
"0": "no",
|
| 13 |
+
"1": "yes"
|
|
|
|
| 14 |
},
|
| 15 |
"image_size": 224,
|
| 16 |
"initializer_range": 0.02,
|
| 17 |
"intermediate_size": 3072,
|
| 18 |
"label2id": {
|
| 19 |
+
"no": "0",
|
| 20 |
+
"yes": "1"
|
|
|
|
| 21 |
},
|
| 22 |
"layer_norm_eps": 1e-12,
|
| 23 |
"model_type": "vit",
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97622a42fad17fda9f4e3e2968936f5d8154521765d06218209a3f8d57bf84f3
|
| 3 |
+
size 686518917
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed4a452acd361b9df965fa879ed0694bf5a220837b7a43535949173d7aef818e
|
| 3 |
+
size 343268717
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8bb3860d98363e44bc4704fb9458deec927fd96997d1d09c80639070db959d22
|
| 3 |
size 14575
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8a54c653e954cbfd76e7193d163778c2617b720e1d8c400bd852fdfbf02140d
|
| 3 |
size 627
|
trainer_state.json
CHANGED
|
@@ -1,148 +1,247 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "./vit-base-beans/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 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.
|
| 12 |
-
"learning_rate": 0.
|
| 13 |
-
"loss": 0.
|
| 14 |
"step": 10
|
| 15 |
},
|
| 16 |
{
|
| 17 |
-
"epoch": 0.
|
| 18 |
-
"learning_rate": 0.
|
| 19 |
-
"loss": 0.
|
| 20 |
"step": 20
|
| 21 |
},
|
| 22 |
{
|
| 23 |
-
"epoch": 0.
|
| 24 |
-
"learning_rate": 0.
|
| 25 |
-
"loss": 0.
|
| 26 |
"step": 30
|
| 27 |
},
|
| 28 |
{
|
| 29 |
-
"epoch": 0.
|
| 30 |
-
"learning_rate": 0.
|
| 31 |
-
"loss": 0.
|
| 32 |
"step": 40
|
| 33 |
},
|
| 34 |
{
|
| 35 |
-
"epoch": 0.
|
| 36 |
-
"eval_accuracy": 0.
|
| 37 |
-
"eval_loss": 0.
|
| 38 |
-
"eval_runtime":
|
| 39 |
-
"eval_samples_per_second":
|
| 40 |
-
"eval_steps_per_second":
|
| 41 |
"step": 40
|
| 42 |
},
|
| 43 |
{
|
| 44 |
-
"epoch": 0.
|
| 45 |
-
"learning_rate": 0.
|
| 46 |
-
"loss": 0.
|
| 47 |
"step": 50
|
| 48 |
},
|
| 49 |
{
|
| 50 |
-
"epoch": 0.
|
| 51 |
-
"learning_rate": 0.
|
| 52 |
-
"loss": 0.
|
| 53 |
"step": 60
|
| 54 |
},
|
| 55 |
{
|
| 56 |
-
"epoch": 0.
|
| 57 |
-
"learning_rate": 0.
|
| 58 |
-
"loss": 0.
|
| 59 |
"step": 70
|
| 60 |
},
|
| 61 |
{
|
| 62 |
-
"epoch": 0.
|
| 63 |
-
"learning_rate": 0.
|
| 64 |
-
"loss": 0.
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
-
"epoch": 0.
|
| 69 |
-
"eval_accuracy": 0.
|
| 70 |
-
"eval_loss": 0.
|
| 71 |
-
"eval_runtime":
|
| 72 |
-
"eval_samples_per_second":
|
| 73 |
-
"eval_steps_per_second":
|
| 74 |
"step": 80
|
| 75 |
},
|
| 76 |
{
|
| 77 |
-
"epoch": 0.
|
| 78 |
-
"learning_rate": 0.
|
| 79 |
-
"loss": 0.
|
| 80 |
"step": 90
|
| 81 |
},
|
| 82 |
{
|
| 83 |
-
"epoch": 0.
|
| 84 |
-
"learning_rate":
|
| 85 |
-
"loss": 0.
|
| 86 |
"step": 100
|
| 87 |
},
|
| 88 |
{
|
| 89 |
-
"epoch": 0.
|
| 90 |
-
"learning_rate":
|
| 91 |
-
"loss": 0.
|
| 92 |
"step": 110
|
| 93 |
},
|
| 94 |
{
|
| 95 |
-
"epoch": 0.
|
| 96 |
-
"learning_rate":
|
| 97 |
-
"loss": 0.
|
| 98 |
"step": 120
|
| 99 |
},
|
| 100 |
{
|
| 101 |
-
"epoch": 0.
|
| 102 |
-
"eval_accuracy": 0.
|
| 103 |
-
"eval_loss": 0.
|
| 104 |
-
"eval_runtime":
|
| 105 |
-
"eval_samples_per_second":
|
| 106 |
-
"eval_steps_per_second":
|
| 107 |
"step": 120
|
| 108 |
},
|
| 109 |
{
|
| 110 |
-
"epoch": 0.
|
| 111 |
-
"learning_rate":
|
| 112 |
-
"loss": 0.
|
| 113 |
"step": 130
|
| 114 |
},
|
| 115 |
{
|
| 116 |
-
"epoch": 0.
|
| 117 |
-
"learning_rate":
|
| 118 |
-
"loss": 0.
|
| 119 |
"step": 140
|
| 120 |
},
|
| 121 |
{
|
| 122 |
-
"epoch": 0
|
| 123 |
-
"learning_rate":
|
| 124 |
-
"loss": 0.
|
| 125 |
"step": 150
|
| 126 |
},
|
| 127 |
{
|
| 128 |
-
"epoch":
|
| 129 |
-
"learning_rate":
|
| 130 |
-
"loss": 0.
|
| 131 |
"step": 160
|
| 132 |
},
|
| 133 |
{
|
| 134 |
-
"epoch":
|
| 135 |
-
"eval_accuracy": 0.
|
| 136 |
-
"eval_loss": 0.
|
| 137 |
-
"eval_runtime":
|
| 138 |
-
"eval_samples_per_second":
|
| 139 |
-
"eval_steps_per_second":
|
| 140 |
"step": 160
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 141 |
}
|
| 142 |
],
|
| 143 |
-
"max_steps":
|
| 144 |
-
"num_train_epochs":
|
| 145 |
-
"total_flos":
|
| 146 |
"trial_name": null,
|
| 147 |
"trial_params": null
|
| 148 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.036450520157814026,
|
| 3 |
+
"best_model_checkpoint": "./vit-base-beans/checkpoint-280",
|
| 4 |
+
"epoch": 1.8666666666666667,
|
| 5 |
+
"global_step": 280,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
+
"epoch": 0.07,
|
| 12 |
+
"learning_rate": 0.00019333333333333333,
|
| 13 |
+
"loss": 0.5095,
|
| 14 |
"step": 10
|
| 15 |
},
|
| 16 |
{
|
| 17 |
+
"epoch": 0.13,
|
| 18 |
+
"learning_rate": 0.0001866666666666667,
|
| 19 |
+
"loss": 0.1264,
|
| 20 |
"step": 20
|
| 21 |
},
|
| 22 |
{
|
| 23 |
+
"epoch": 0.2,
|
| 24 |
+
"learning_rate": 0.00018,
|
| 25 |
+
"loss": 0.2591,
|
| 26 |
"step": 30
|
| 27 |
},
|
| 28 |
{
|
| 29 |
+
"epoch": 0.27,
|
| 30 |
+
"learning_rate": 0.00017333333333333334,
|
| 31 |
+
"loss": 0.2432,
|
| 32 |
"step": 40
|
| 33 |
},
|
| 34 |
{
|
| 35 |
+
"epoch": 0.27,
|
| 36 |
+
"eval_accuracy": 0.96,
|
| 37 |
+
"eval_loss": 0.1231376901268959,
|
| 38 |
+
"eval_runtime": 6.2617,
|
| 39 |
+
"eval_samples_per_second": 47.911,
|
| 40 |
+
"eval_steps_per_second": 6.069,
|
| 41 |
"step": 40
|
| 42 |
},
|
| 43 |
{
|
| 44 |
+
"epoch": 0.33,
|
| 45 |
+
"learning_rate": 0.0001666666666666667,
|
| 46 |
+
"loss": 0.0895,
|
| 47 |
"step": 50
|
| 48 |
},
|
| 49 |
{
|
| 50 |
+
"epoch": 0.4,
|
| 51 |
+
"learning_rate": 0.00016,
|
| 52 |
+
"loss": 0.0498,
|
| 53 |
"step": 60
|
| 54 |
},
|
| 55 |
{
|
| 56 |
+
"epoch": 0.47,
|
| 57 |
+
"learning_rate": 0.00015333333333333334,
|
| 58 |
+
"loss": 0.212,
|
| 59 |
"step": 70
|
| 60 |
},
|
| 61 |
{
|
| 62 |
+
"epoch": 0.53,
|
| 63 |
+
"learning_rate": 0.00014666666666666666,
|
| 64 |
+
"loss": 0.074,
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
+
"epoch": 0.53,
|
| 69 |
+
"eval_accuracy": 0.9833333333333333,
|
| 70 |
+
"eval_loss": 0.07364834100008011,
|
| 71 |
+
"eval_runtime": 5.1068,
|
| 72 |
+
"eval_samples_per_second": 58.745,
|
| 73 |
+
"eval_steps_per_second": 7.441,
|
| 74 |
"step": 80
|
| 75 |
},
|
| 76 |
{
|
| 77 |
+
"epoch": 0.6,
|
| 78 |
+
"learning_rate": 0.00014,
|
| 79 |
+
"loss": 0.0992,
|
| 80 |
"step": 90
|
| 81 |
},
|
| 82 |
{
|
| 83 |
+
"epoch": 0.67,
|
| 84 |
+
"learning_rate": 0.00013333333333333334,
|
| 85 |
+
"loss": 0.0764,
|
| 86 |
"step": 100
|
| 87 |
},
|
| 88 |
{
|
| 89 |
+
"epoch": 0.73,
|
| 90 |
+
"learning_rate": 0.00012666666666666666,
|
| 91 |
+
"loss": 0.0284,
|
| 92 |
"step": 110
|
| 93 |
},
|
| 94 |
{
|
| 95 |
+
"epoch": 0.8,
|
| 96 |
+
"learning_rate": 0.00012,
|
| 97 |
+
"loss": 0.0787,
|
| 98 |
"step": 120
|
| 99 |
},
|
| 100 |
{
|
| 101 |
+
"epoch": 0.8,
|
| 102 |
+
"eval_accuracy": 0.98,
|
| 103 |
+
"eval_loss": 0.08297358453273773,
|
| 104 |
+
"eval_runtime": 6.2497,
|
| 105 |
+
"eval_samples_per_second": 48.002,
|
| 106 |
+
"eval_steps_per_second": 6.08,
|
| 107 |
"step": 120
|
| 108 |
},
|
| 109 |
{
|
| 110 |
+
"epoch": 0.87,
|
| 111 |
+
"learning_rate": 0.00011333333333333334,
|
| 112 |
+
"loss": 0.0096,
|
| 113 |
"step": 130
|
| 114 |
},
|
| 115 |
{
|
| 116 |
+
"epoch": 0.93,
|
| 117 |
+
"learning_rate": 0.00010666666666666667,
|
| 118 |
+
"loss": 0.0387,
|
| 119 |
"step": 140
|
| 120 |
},
|
| 121 |
{
|
| 122 |
+
"epoch": 1.0,
|
| 123 |
+
"learning_rate": 0.0001,
|
| 124 |
+
"loss": 0.0246,
|
| 125 |
"step": 150
|
| 126 |
},
|
| 127 |
{
|
| 128 |
+
"epoch": 1.07,
|
| 129 |
+
"learning_rate": 9.333333333333334e-05,
|
| 130 |
+
"loss": 0.0132,
|
| 131 |
"step": 160
|
| 132 |
},
|
| 133 |
{
|
| 134 |
+
"epoch": 1.07,
|
| 135 |
+
"eval_accuracy": 0.9866666666666667,
|
| 136 |
+
"eval_loss": 0.04826768860220909,
|
| 137 |
+
"eval_runtime": 5.1012,
|
| 138 |
+
"eval_samples_per_second": 58.809,
|
| 139 |
+
"eval_steps_per_second": 7.449,
|
| 140 |
"step": 160
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.13,
|
| 144 |
+
"learning_rate": 8.666666666666667e-05,
|
| 145 |
+
"loss": 0.0056,
|
| 146 |
+
"step": 170
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 1.2,
|
| 150 |
+
"learning_rate": 8e-05,
|
| 151 |
+
"loss": 0.0379,
|
| 152 |
+
"step": 180
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.27,
|
| 156 |
+
"learning_rate": 7.333333333333333e-05,
|
| 157 |
+
"loss": 0.0277,
|
| 158 |
+
"step": 190
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.33,
|
| 162 |
+
"learning_rate": 6.666666666666667e-05,
|
| 163 |
+
"loss": 0.0305,
|
| 164 |
+
"step": 200
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.33,
|
| 168 |
+
"eval_accuracy": 0.9866666666666667,
|
| 169 |
+
"eval_loss": 0.05280878767371178,
|
| 170 |
+
"eval_runtime": 6.211,
|
| 171 |
+
"eval_samples_per_second": 48.301,
|
| 172 |
+
"eval_steps_per_second": 6.118,
|
| 173 |
+
"step": 200
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.4,
|
| 177 |
+
"learning_rate": 6e-05,
|
| 178 |
+
"loss": 0.0052,
|
| 179 |
+
"step": 210
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.47,
|
| 183 |
+
"learning_rate": 5.333333333333333e-05,
|
| 184 |
+
"loss": 0.0055,
|
| 185 |
+
"step": 220
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.53,
|
| 189 |
+
"learning_rate": 4.666666666666667e-05,
|
| 190 |
+
"loss": 0.0047,
|
| 191 |
+
"step": 230
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.6,
|
| 195 |
+
"learning_rate": 4e-05,
|
| 196 |
+
"loss": 0.0784,
|
| 197 |
+
"step": 240
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.6,
|
| 201 |
+
"eval_accuracy": 0.98,
|
| 202 |
+
"eval_loss": 0.066566601395607,
|
| 203 |
+
"eval_runtime": 5.7633,
|
| 204 |
+
"eval_samples_per_second": 52.053,
|
| 205 |
+
"eval_steps_per_second": 6.593,
|
| 206 |
+
"step": 240
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.67,
|
| 210 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 211 |
+
"loss": 0.0294,
|
| 212 |
+
"step": 250
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.73,
|
| 216 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 217 |
+
"loss": 0.036,
|
| 218 |
+
"step": 260
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.8,
|
| 222 |
+
"learning_rate": 2e-05,
|
| 223 |
+
"loss": 0.037,
|
| 224 |
+
"step": 270
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.87,
|
| 228 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 229 |
+
"loss": 0.006,
|
| 230 |
+
"step": 280
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.87,
|
| 234 |
+
"eval_accuracy": 0.99,
|
| 235 |
+
"eval_loss": 0.036450520157814026,
|
| 236 |
+
"eval_runtime": 5.101,
|
| 237 |
+
"eval_samples_per_second": 58.812,
|
| 238 |
+
"eval_steps_per_second": 7.45,
|
| 239 |
+
"step": 280
|
| 240 |
}
|
| 241 |
],
|
| 242 |
+
"max_steps": 300,
|
| 243 |
+
"num_train_epochs": 2,
|
| 244 |
+
"total_flos": 3.4716411347337216e+17,
|
| 245 |
"trial_name": null,
|
| 246 |
"trial_params": null
|
| 247 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3963
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6356fdac8f7ddf618557f635b47577515e3f93ecba50c63feb05831b44a3c970
|
| 3 |
size 3963
|