End of training
Browse files- all_results.json +8 -0
- test_results.json +8 -0
- trainer_state.json +311 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.44,
|
| 3 |
+
"eval_accuracy": 0.16911764705882354,
|
| 4 |
+
"eval_loss": 1.9171618223190308,
|
| 5 |
+
"eval_runtime": 34.3798,
|
| 6 |
+
"eval_samples_per_second": 3.956,
|
| 7 |
+
"eval_steps_per_second": 1.978
|
| 8 |
+
}
|
test_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.44,
|
| 3 |
+
"eval_accuracy": 0.16911764705882354,
|
| 4 |
+
"eval_loss": 1.9171618223190308,
|
| 5 |
+
"eval_runtime": 34.3798,
|
| 6 |
+
"eval_samples_per_second": 3.956,
|
| 7 |
+
"eval_steps_per_second": 1.978
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,311 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.14545454545454545,
|
| 3 |
+
"best_model_checkpoint": "videomae-base-finetuned-kinetics-finetuned-caer-subset\\checkpoint-350",
|
| 4 |
+
"epoch": 1.44,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 350,
|
| 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 |
+
"grad_norm": 10.89427661895752,
|
| 14 |
+
"learning_rate": 1.4285714285714285e-05,
|
| 15 |
+
"loss": 1.9195,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.06,
|
| 20 |
+
"grad_norm": 9.84024715423584,
|
| 21 |
+
"learning_rate": 2.857142857142857e-05,
|
| 22 |
+
"loss": 1.9823,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.09,
|
| 27 |
+
"grad_norm": 15.709190368652344,
|
| 28 |
+
"learning_rate": 4.2857142857142856e-05,
|
| 29 |
+
"loss": 1.9911,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.11,
|
| 34 |
+
"grad_norm": 17.095855712890625,
|
| 35 |
+
"learning_rate": 4.9206349206349204e-05,
|
| 36 |
+
"loss": 2.0181,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.14,
|
| 41 |
+
"grad_norm": 10.043827056884766,
|
| 42 |
+
"learning_rate": 4.761904761904762e-05,
|
| 43 |
+
"loss": 1.9888,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.17,
|
| 48 |
+
"grad_norm": 10.363592147827148,
|
| 49 |
+
"learning_rate": 4.603174603174603e-05,
|
| 50 |
+
"loss": 1.937,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.2,
|
| 55 |
+
"grad_norm": 9.244985580444336,
|
| 56 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 57 |
+
"loss": 1.9099,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.23,
|
| 62 |
+
"grad_norm": 6.264003753662109,
|
| 63 |
+
"learning_rate": 4.2857142857142856e-05,
|
| 64 |
+
"loss": 2.0108,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.26,
|
| 69 |
+
"grad_norm": 7.295020580291748,
|
| 70 |
+
"learning_rate": 4.126984126984127e-05,
|
| 71 |
+
"loss": 1.8789,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.29,
|
| 76 |
+
"grad_norm": 5.525545120239258,
|
| 77 |
+
"learning_rate": 3.968253968253968e-05,
|
| 78 |
+
"loss": 1.9794,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.31,
|
| 83 |
+
"grad_norm": 5.664557456970215,
|
| 84 |
+
"learning_rate": 3.809523809523809e-05,
|
| 85 |
+
"loss": 2.0856,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.34,
|
| 90 |
+
"grad_norm": 6.291672706604004,
|
| 91 |
+
"learning_rate": 3.650793650793651e-05,
|
| 92 |
+
"loss": 2.0504,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.37,
|
| 97 |
+
"grad_norm": 9.917661666870117,
|
| 98 |
+
"learning_rate": 3.492063492063492e-05,
|
| 99 |
+
"loss": 1.902,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.4,
|
| 104 |
+
"grad_norm": 8.238541603088379,
|
| 105 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 106 |
+
"loss": 1.9035,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.43,
|
| 111 |
+
"grad_norm": 11.320600509643555,
|
| 112 |
+
"learning_rate": 3.1746031746031745e-05,
|
| 113 |
+
"loss": 1.951,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.46,
|
| 118 |
+
"grad_norm": 8.543054580688477,
|
| 119 |
+
"learning_rate": 3.0158730158730158e-05,
|
| 120 |
+
"loss": 1.9308,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.49,
|
| 125 |
+
"grad_norm": 8.997832298278809,
|
| 126 |
+
"learning_rate": 2.857142857142857e-05,
|
| 127 |
+
"loss": 1.9112,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.51,
|
| 132 |
+
"grad_norm": 7.9026713371276855,
|
| 133 |
+
"learning_rate": 2.6984126984126984e-05,
|
| 134 |
+
"loss": 1.9884,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.54,
|
| 139 |
+
"grad_norm": 4.980269908905029,
|
| 140 |
+
"learning_rate": 2.5396825396825397e-05,
|
| 141 |
+
"loss": 2.0268,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.56,
|
| 146 |
+
"eval_accuracy": 0.10909090909090909,
|
| 147 |
+
"eval_loss": 2.038116931915283,
|
| 148 |
+
"eval_runtime": 13.0712,
|
| 149 |
+
"eval_samples_per_second": 4.208,
|
| 150 |
+
"eval_steps_per_second": 2.142,
|
| 151 |
+
"step": 196
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.01,
|
| 155 |
+
"grad_norm": 5.153656959533691,
|
| 156 |
+
"learning_rate": 2.380952380952381e-05,
|
| 157 |
+
"loss": 1.9254,
|
| 158 |
+
"step": 200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.04,
|
| 162 |
+
"grad_norm": 5.691870212554932,
|
| 163 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 164 |
+
"loss": 2.0473,
|
| 165 |
+
"step": 210
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.07,
|
| 169 |
+
"grad_norm": 3.863321304321289,
|
| 170 |
+
"learning_rate": 2.0634920634920636e-05,
|
| 171 |
+
"loss": 2.0271,
|
| 172 |
+
"step": 220
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.1,
|
| 176 |
+
"grad_norm": 3.6589486598968506,
|
| 177 |
+
"learning_rate": 1.9047619047619046e-05,
|
| 178 |
+
"loss": 1.8714,
|
| 179 |
+
"step": 230
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.13,
|
| 183 |
+
"grad_norm": 4.852847576141357,
|
| 184 |
+
"learning_rate": 1.746031746031746e-05,
|
| 185 |
+
"loss": 2.0027,
|
| 186 |
+
"step": 240
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.15,
|
| 190 |
+
"grad_norm": 3.800025463104248,
|
| 191 |
+
"learning_rate": 1.5873015873015872e-05,
|
| 192 |
+
"loss": 1.9541,
|
| 193 |
+
"step": 250
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.18,
|
| 197 |
+
"grad_norm": 3.3564181327819824,
|
| 198 |
+
"learning_rate": 1.4285714285714285e-05,
|
| 199 |
+
"loss": 1.9262,
|
| 200 |
+
"step": 260
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.21,
|
| 204 |
+
"grad_norm": 4.314349174499512,
|
| 205 |
+
"learning_rate": 1.2698412698412699e-05,
|
| 206 |
+
"loss": 2.0122,
|
| 207 |
+
"step": 270
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.24,
|
| 211 |
+
"grad_norm": 3.4683678150177,
|
| 212 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 213 |
+
"loss": 2.0268,
|
| 214 |
+
"step": 280
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.27,
|
| 218 |
+
"grad_norm": 5.209654808044434,
|
| 219 |
+
"learning_rate": 9.523809523809523e-06,
|
| 220 |
+
"loss": 1.8604,
|
| 221 |
+
"step": 290
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.3,
|
| 225 |
+
"grad_norm": 7.990084171295166,
|
| 226 |
+
"learning_rate": 7.936507936507936e-06,
|
| 227 |
+
"loss": 1.9207,
|
| 228 |
+
"step": 300
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 1.33,
|
| 232 |
+
"grad_norm": 7.0981950759887695,
|
| 233 |
+
"learning_rate": 6.349206349206349e-06,
|
| 234 |
+
"loss": 1.8903,
|
| 235 |
+
"step": 310
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 1.35,
|
| 239 |
+
"grad_norm": 11.933561325073242,
|
| 240 |
+
"learning_rate": 4.7619047619047615e-06,
|
| 241 |
+
"loss": 1.8676,
|
| 242 |
+
"step": 320
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.38,
|
| 246 |
+
"grad_norm": 9.403660774230957,
|
| 247 |
+
"learning_rate": 3.1746031746031746e-06,
|
| 248 |
+
"loss": 1.9368,
|
| 249 |
+
"step": 330
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.41,
|
| 253 |
+
"grad_norm": 7.650759696960449,
|
| 254 |
+
"learning_rate": 1.5873015873015873e-06,
|
| 255 |
+
"loss": 1.7748,
|
| 256 |
+
"step": 340
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.44,
|
| 260 |
+
"grad_norm": 8.465459823608398,
|
| 261 |
+
"learning_rate": 0.0,
|
| 262 |
+
"loss": 1.8411,
|
| 263 |
+
"step": 350
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 1.44,
|
| 267 |
+
"eval_accuracy": 0.14545454545454545,
|
| 268 |
+
"eval_loss": 1.8625677824020386,
|
| 269 |
+
"eval_runtime": 13.2287,
|
| 270 |
+
"eval_samples_per_second": 4.158,
|
| 271 |
+
"eval_steps_per_second": 2.117,
|
| 272 |
+
"step": 350
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.44,
|
| 276 |
+
"step": 350,
|
| 277 |
+
"total_flos": 8.710379865046057e+17,
|
| 278 |
+
"train_loss": 1.9500097220284598,
|
| 279 |
+
"train_runtime": 289.2328,
|
| 280 |
+
"train_samples_per_second": 2.42,
|
| 281 |
+
"train_steps_per_second": 1.21
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.44,
|
| 285 |
+
"eval_accuracy": 0.16911764705882354,
|
| 286 |
+
"eval_loss": 1.9171618223190308,
|
| 287 |
+
"eval_runtime": 33.8698,
|
| 288 |
+
"eval_samples_per_second": 4.015,
|
| 289 |
+
"eval_steps_per_second": 2.008,
|
| 290 |
+
"step": 350
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.44,
|
| 294 |
+
"eval_accuracy": 0.16911764705882354,
|
| 295 |
+
"eval_loss": 1.9171618223190308,
|
| 296 |
+
"eval_runtime": 34.3798,
|
| 297 |
+
"eval_samples_per_second": 3.956,
|
| 298 |
+
"eval_steps_per_second": 1.978,
|
| 299 |
+
"step": 350
|
| 300 |
+
}
|
| 301 |
+
],
|
| 302 |
+
"logging_steps": 10,
|
| 303 |
+
"max_steps": 350,
|
| 304 |
+
"num_input_tokens_seen": 0,
|
| 305 |
+
"num_train_epochs": 9223372036854775807,
|
| 306 |
+
"save_steps": 500,
|
| 307 |
+
"total_flos": 8.710379865046057e+17,
|
| 308 |
+
"train_batch_size": 2,
|
| 309 |
+
"trial_name": null,
|
| 310 |
+
"trial_params": null
|
| 311 |
+
}
|