End of training
Browse files- README.md +2 -2
- all_results.json +8 -0
- runs/Feb07_21-32-38_c86197ac4896/events.out.tfevents.1707352373.c86197ac4896.199.1 +3 -0
- test_results.json +8 -0
- trainer_state.json +285 -0
README.md
CHANGED
|
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [Tommidi/st_vit_untrained](https://huggingface.co/Tommidi/st_vit_untrained) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 0.
|
| 20 |
-
- Accuracy: 0.
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [Tommidi/st_vit_untrained](https://huggingface.co/Tommidi/st_vit_untrained) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.0648
|
| 20 |
+
- Accuracy: 0.9733
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 7.1,
|
| 3 |
+
"eval_accuracy": 0.9733333333333334,
|
| 4 |
+
"eval_loss": 0.06482689082622528,
|
| 5 |
+
"eval_runtime": 274.5585,
|
| 6 |
+
"eval_samples_per_second": 0.273,
|
| 7 |
+
"eval_steps_per_second": 0.036
|
| 8 |
+
}
|
runs/Feb07_21-32-38_c86197ac4896/events.out.tfevents.1707352373.c86197ac4896.199.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52800926d580431acc40641a538eba815a58fbdfc4eaa4fc66b728a5fc97cb47
|
| 3 |
+
size 411
|
test_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 7.1,
|
| 3 |
+
"eval_accuracy": 0.9733333333333334,
|
| 4 |
+
"eval_loss": 0.06482689082622528,
|
| 5 |
+
"eval_runtime": 274.5585,
|
| 6 |
+
"eval_samples_per_second": 0.273,
|
| 7 |
+
"eval_steps_per_second": 0.036
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,285 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.0,
|
| 3 |
+
"best_model_checkpoint": "st_vit_trained-8epoch-ucf101-subset/checkpoint-76",
|
| 4 |
+
"epoch": 7.101351351351352,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 296,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 14 |
+
"loss": 2.1556,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.07,
|
| 19 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 20 |
+
"loss": 0.6436,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.1,
|
| 25 |
+
"learning_rate": 5e-05,
|
| 26 |
+
"loss": 0.6314,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.13,
|
| 31 |
+
"eval_accuracy": 0.9333333333333333,
|
| 32 |
+
"eval_loss": 0.12640628218650818,
|
| 33 |
+
"eval_runtime": 107.3422,
|
| 34 |
+
"eval_samples_per_second": 0.279,
|
| 35 |
+
"eval_steps_per_second": 0.037,
|
| 36 |
+
"step": 38
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 1.01,
|
| 40 |
+
"learning_rate": 4.81203007518797e-05,
|
| 41 |
+
"loss": 0.2368,
|
| 42 |
+
"step": 40
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 1.04,
|
| 46 |
+
"learning_rate": 4.62406015037594e-05,
|
| 47 |
+
"loss": 0.2077,
|
| 48 |
+
"step": 50
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 1.07,
|
| 52 |
+
"learning_rate": 4.43609022556391e-05,
|
| 53 |
+
"loss": 0.4179,
|
| 54 |
+
"step": 60
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.11,
|
| 58 |
+
"learning_rate": 4.24812030075188e-05,
|
| 59 |
+
"loss": 0.3547,
|
| 60 |
+
"step": 70
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 1.13,
|
| 64 |
+
"eval_accuracy": 1.0,
|
| 65 |
+
"eval_loss": 0.007708676625043154,
|
| 66 |
+
"eval_runtime": 109.7958,
|
| 67 |
+
"eval_samples_per_second": 0.273,
|
| 68 |
+
"eval_steps_per_second": 0.036,
|
| 69 |
+
"step": 76
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 2.01,
|
| 73 |
+
"learning_rate": 4.0601503759398494e-05,
|
| 74 |
+
"loss": 0.2593,
|
| 75 |
+
"step": 80
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 2.05,
|
| 79 |
+
"learning_rate": 3.87218045112782e-05,
|
| 80 |
+
"loss": 0.1361,
|
| 81 |
+
"step": 90
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 2.08,
|
| 85 |
+
"learning_rate": 3.6842105263157895e-05,
|
| 86 |
+
"loss": 0.079,
|
| 87 |
+
"step": 100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 2.11,
|
| 91 |
+
"learning_rate": 3.49624060150376e-05,
|
| 92 |
+
"loss": 0.0189,
|
| 93 |
+
"step": 110
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 2.13,
|
| 97 |
+
"eval_accuracy": 0.9333333333333333,
|
| 98 |
+
"eval_loss": 0.510276734828949,
|
| 99 |
+
"eval_runtime": 110.2619,
|
| 100 |
+
"eval_samples_per_second": 0.272,
|
| 101 |
+
"eval_steps_per_second": 0.036,
|
| 102 |
+
"step": 114
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 3.02,
|
| 106 |
+
"learning_rate": 3.3082706766917295e-05,
|
| 107 |
+
"loss": 0.0021,
|
| 108 |
+
"step": 120
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 3.05,
|
| 112 |
+
"learning_rate": 3.120300751879699e-05,
|
| 113 |
+
"loss": 0.0596,
|
| 114 |
+
"step": 130
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 3.09,
|
| 118 |
+
"learning_rate": 2.9323308270676693e-05,
|
| 119 |
+
"loss": 0.0554,
|
| 120 |
+
"step": 140
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 3.12,
|
| 124 |
+
"learning_rate": 2.7443609022556393e-05,
|
| 125 |
+
"loss": 0.0611,
|
| 126 |
+
"step": 150
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 3.13,
|
| 130 |
+
"eval_accuracy": 0.9333333333333333,
|
| 131 |
+
"eval_loss": 0.15075534582138062,
|
| 132 |
+
"eval_runtime": 110.9545,
|
| 133 |
+
"eval_samples_per_second": 0.27,
|
| 134 |
+
"eval_steps_per_second": 0.036,
|
| 135 |
+
"step": 152
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 4.03,
|
| 139 |
+
"learning_rate": 2.556390977443609e-05,
|
| 140 |
+
"loss": 0.219,
|
| 141 |
+
"step": 160
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 4.06,
|
| 145 |
+
"learning_rate": 2.368421052631579e-05,
|
| 146 |
+
"loss": 0.1464,
|
| 147 |
+
"step": 170
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 4.09,
|
| 151 |
+
"learning_rate": 2.1804511278195487e-05,
|
| 152 |
+
"loss": 0.0131,
|
| 153 |
+
"step": 180
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 4.13,
|
| 157 |
+
"learning_rate": 1.9924812030075188e-05,
|
| 158 |
+
"loss": 0.0027,
|
| 159 |
+
"step": 190
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 4.13,
|
| 163 |
+
"eval_accuracy": 1.0,
|
| 164 |
+
"eval_loss": 0.0017944329883903265,
|
| 165 |
+
"eval_runtime": 111.261,
|
| 166 |
+
"eval_samples_per_second": 0.27,
|
| 167 |
+
"eval_steps_per_second": 0.036,
|
| 168 |
+
"step": 190
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 5.03,
|
| 172 |
+
"learning_rate": 1.8045112781954888e-05,
|
| 173 |
+
"loss": 0.0291,
|
| 174 |
+
"step": 200
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 5.07,
|
| 178 |
+
"learning_rate": 1.6165413533834585e-05,
|
| 179 |
+
"loss": 0.0183,
|
| 180 |
+
"step": 210
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 5.1,
|
| 184 |
+
"learning_rate": 1.4285714285714285e-05,
|
| 185 |
+
"loss": 0.0812,
|
| 186 |
+
"step": 220
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 5.13,
|
| 190 |
+
"eval_accuracy": 0.9333333333333333,
|
| 191 |
+
"eval_loss": 0.0942629873752594,
|
| 192 |
+
"eval_runtime": 110.723,
|
| 193 |
+
"eval_samples_per_second": 0.271,
|
| 194 |
+
"eval_steps_per_second": 0.036,
|
| 195 |
+
"step": 228
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 6.01,
|
| 199 |
+
"learning_rate": 1.2406015037593984e-05,
|
| 200 |
+
"loss": 0.0072,
|
| 201 |
+
"step": 230
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 6.04,
|
| 205 |
+
"learning_rate": 1.0526315789473684e-05,
|
| 206 |
+
"loss": 0.1462,
|
| 207 |
+
"step": 240
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 6.07,
|
| 211 |
+
"learning_rate": 8.646616541353383e-06,
|
| 212 |
+
"loss": 0.1258,
|
| 213 |
+
"step": 250
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 6.11,
|
| 217 |
+
"learning_rate": 6.766917293233083e-06,
|
| 218 |
+
"loss": 0.0005,
|
| 219 |
+
"step": 260
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 6.13,
|
| 223 |
+
"eval_accuracy": 0.9666666666666667,
|
| 224 |
+
"eval_loss": 0.06345120072364807,
|
| 225 |
+
"eval_runtime": 111.1102,
|
| 226 |
+
"eval_samples_per_second": 0.27,
|
| 227 |
+
"eval_steps_per_second": 0.036,
|
| 228 |
+
"step": 266
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 7.01,
|
| 232 |
+
"learning_rate": 4.887218045112782e-06,
|
| 233 |
+
"loss": 0.0017,
|
| 234 |
+
"step": 270
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 7.05,
|
| 238 |
+
"learning_rate": 3.007518796992481e-06,
|
| 239 |
+
"loss": 0.0004,
|
| 240 |
+
"step": 280
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 7.08,
|
| 244 |
+
"learning_rate": 1.1278195488721805e-06,
|
| 245 |
+
"loss": 0.3035,
|
| 246 |
+
"step": 290
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 7.1,
|
| 250 |
+
"eval_accuracy": 0.9666666666666667,
|
| 251 |
+
"eval_loss": 0.05302112549543381,
|
| 252 |
+
"eval_runtime": 111.2744,
|
| 253 |
+
"eval_samples_per_second": 0.27,
|
| 254 |
+
"eval_steps_per_second": 0.036,
|
| 255 |
+
"step": 296
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 7.1,
|
| 259 |
+
"step": 296,
|
| 260 |
+
"total_flos": 0.0,
|
| 261 |
+
"train_loss": 0.21684430856918413,
|
| 262 |
+
"train_runtime": 10490.4185,
|
| 263 |
+
"train_samples_per_second": 0.226,
|
| 264 |
+
"train_steps_per_second": 0.028
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 7.1,
|
| 268 |
+
"eval_accuracy": 0.9733333333333334,
|
| 269 |
+
"eval_loss": 0.06482689082622528,
|
| 270 |
+
"eval_runtime": 274.5585,
|
| 271 |
+
"eval_samples_per_second": 0.273,
|
| 272 |
+
"eval_steps_per_second": 0.036,
|
| 273 |
+
"step": 296
|
| 274 |
+
}
|
| 275 |
+
],
|
| 276 |
+
"logging_steps": 10,
|
| 277 |
+
"max_steps": 296,
|
| 278 |
+
"num_input_tokens_seen": 0,
|
| 279 |
+
"num_train_epochs": 9223372036854775807,
|
| 280 |
+
"save_steps": 500,
|
| 281 |
+
"total_flos": 0.0,
|
| 282 |
+
"train_batch_size": 8,
|
| 283 |
+
"trial_name": null,
|
| 284 |
+
"trial_params": null
|
| 285 |
+
}
|