End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.326530612244898,
|
| 3 |
+
"eval_accuracy": 0.8075,
|
| 4 |
+
"eval_loss": 0.47592803835868835,
|
| 5 |
+
"eval_runtime": 236.8069,
|
| 6 |
+
"eval_samples_per_second": 3.378,
|
| 7 |
+
"eval_steps_per_second": 0.211
|
| 8 |
+
}
|
runs/Nov18_14-14-28_ml-server03/events.out.tfevents.1731962748.ml-server03.3189854.1
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 sha256:817c4904f887a16ea341b724d7cf65892c876dc1ea44d98e2cfac3c621b963ac
|
| 3 |
+
size 686
|
trainer_state.json
ADDED
|
@@ -0,0 +1,290 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8075,
|
| 3 |
+
"best_model_checkpoint": "videomae-base-finetuned-rwf2000-subset/checkpoint-99",
|
| 4 |
+
"epoch": 2.326530612244898,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 294,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.034013605442176874,
|
| 13 |
+
"grad_norm": 4.7393035888671875,
|
| 14 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 15 |
+
"loss": 0.6905,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.06802721088435375,
|
| 20 |
+
"grad_norm": 7.800499439239502,
|
| 21 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 22 |
+
"loss": 0.683,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.10204081632653061,
|
| 27 |
+
"grad_norm": 4.713344097137451,
|
| 28 |
+
"learning_rate": 5e-05,
|
| 29 |
+
"loss": 0.6734,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.1360544217687075,
|
| 34 |
+
"grad_norm": 4.479344367980957,
|
| 35 |
+
"learning_rate": 4.810606060606061e-05,
|
| 36 |
+
"loss": 0.5734,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.17006802721088435,
|
| 41 |
+
"grad_norm": 12.256854057312012,
|
| 42 |
+
"learning_rate": 4.621212121212121e-05,
|
| 43 |
+
"loss": 0.5376,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.20408163265306123,
|
| 48 |
+
"grad_norm": 3.8227643966674805,
|
| 49 |
+
"learning_rate": 4.431818181818182e-05,
|
| 50 |
+
"loss": 0.6064,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.23809523809523808,
|
| 55 |
+
"grad_norm": 3.2429208755493164,
|
| 56 |
+
"learning_rate": 4.242424242424243e-05,
|
| 57 |
+
"loss": 0.5943,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.272108843537415,
|
| 62 |
+
"grad_norm": 2.612661361694336,
|
| 63 |
+
"learning_rate": 4.053030303030303e-05,
|
| 64 |
+
"loss": 0.5576,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.30612244897959184,
|
| 69 |
+
"grad_norm": 11.458771705627441,
|
| 70 |
+
"learning_rate": 3.8636363636363636e-05,
|
| 71 |
+
"loss": 0.4016,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.336734693877551,
|
| 76 |
+
"eval_accuracy": 0.8075,
|
| 77 |
+
"eval_loss": 0.47592800855636597,
|
| 78 |
+
"eval_runtime": 226.6726,
|
| 79 |
+
"eval_samples_per_second": 3.529,
|
| 80 |
+
"eval_steps_per_second": 0.221,
|
| 81 |
+
"step": 99
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.0034013605442176,
|
| 85 |
+
"grad_norm": 8.344210624694824,
|
| 86 |
+
"learning_rate": 3.6742424242424246e-05,
|
| 87 |
+
"loss": 0.5466,
|
| 88 |
+
"step": 100
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.0374149659863945,
|
| 92 |
+
"grad_norm": 3.3535470962524414,
|
| 93 |
+
"learning_rate": 3.484848484848485e-05,
|
| 94 |
+
"loss": 0.5042,
|
| 95 |
+
"step": 110
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.0714285714285714,
|
| 99 |
+
"grad_norm": 7.865573883056641,
|
| 100 |
+
"learning_rate": 3.295454545454545e-05,
|
| 101 |
+
"loss": 0.4416,
|
| 102 |
+
"step": 120
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.1054421768707483,
|
| 106 |
+
"grad_norm": 2.2295467853546143,
|
| 107 |
+
"learning_rate": 3.106060606060606e-05,
|
| 108 |
+
"loss": 0.4595,
|
| 109 |
+
"step": 130
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.1394557823129252,
|
| 113 |
+
"grad_norm": 7.118393421173096,
|
| 114 |
+
"learning_rate": 2.916666666666667e-05,
|
| 115 |
+
"loss": 0.4775,
|
| 116 |
+
"step": 140
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.1734693877551021,
|
| 120 |
+
"grad_norm": 8.748396873474121,
|
| 121 |
+
"learning_rate": 2.7272727272727273e-05,
|
| 122 |
+
"loss": 0.4132,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.2074829931972788,
|
| 127 |
+
"grad_norm": 6.271174430847168,
|
| 128 |
+
"learning_rate": 2.537878787878788e-05,
|
| 129 |
+
"loss": 0.4926,
|
| 130 |
+
"step": 160
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.2414965986394557,
|
| 134 |
+
"grad_norm": 7.936441898345947,
|
| 135 |
+
"learning_rate": 2.3484848484848487e-05,
|
| 136 |
+
"loss": 0.4532,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.2755102040816326,
|
| 141 |
+
"grad_norm": 3.373074531555176,
|
| 142 |
+
"learning_rate": 2.1590909090909093e-05,
|
| 143 |
+
"loss": 0.5067,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.3095238095238095,
|
| 148 |
+
"grad_norm": 2.5091629028320312,
|
| 149 |
+
"learning_rate": 1.9696969696969697e-05,
|
| 150 |
+
"loss": 0.2963,
|
| 151 |
+
"step": 190
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.336734693877551,
|
| 155 |
+
"eval_accuracy": 0.72,
|
| 156 |
+
"eval_loss": 0.691987156867981,
|
| 157 |
+
"eval_runtime": 248.5517,
|
| 158 |
+
"eval_samples_per_second": 3.219,
|
| 159 |
+
"eval_steps_per_second": 0.201,
|
| 160 |
+
"step": 198
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 2.006802721088435,
|
| 164 |
+
"grad_norm": 3.1143054962158203,
|
| 165 |
+
"learning_rate": 1.7803030303030303e-05,
|
| 166 |
+
"loss": 0.336,
|
| 167 |
+
"step": 200
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 2.0408163265306123,
|
| 171 |
+
"grad_norm": 7.136720180511475,
|
| 172 |
+
"learning_rate": 1.590909090909091e-05,
|
| 173 |
+
"loss": 0.3749,
|
| 174 |
+
"step": 210
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 2.074829931972789,
|
| 178 |
+
"grad_norm": 4.782387733459473,
|
| 179 |
+
"learning_rate": 1.4015151515151515e-05,
|
| 180 |
+
"loss": 0.3953,
|
| 181 |
+
"step": 220
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 2.108843537414966,
|
| 185 |
+
"grad_norm": 5.702661514282227,
|
| 186 |
+
"learning_rate": 1.2121212121212122e-05,
|
| 187 |
+
"loss": 0.3348,
|
| 188 |
+
"step": 230
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.142857142857143,
|
| 192 |
+
"grad_norm": 7.018678665161133,
|
| 193 |
+
"learning_rate": 1.0227272727272729e-05,
|
| 194 |
+
"loss": 0.3232,
|
| 195 |
+
"step": 240
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 2.17687074829932,
|
| 199 |
+
"grad_norm": 3.7905936241149902,
|
| 200 |
+
"learning_rate": 8.333333333333334e-06,
|
| 201 |
+
"loss": 0.3215,
|
| 202 |
+
"step": 250
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 2.2108843537414966,
|
| 206 |
+
"grad_norm": 3.4865996837615967,
|
| 207 |
+
"learning_rate": 6.43939393939394e-06,
|
| 208 |
+
"loss": 0.4199,
|
| 209 |
+
"step": 260
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 2.2448979591836733,
|
| 213 |
+
"grad_norm": 4.849910259246826,
|
| 214 |
+
"learning_rate": 4.5454545454545455e-06,
|
| 215 |
+
"loss": 0.2796,
|
| 216 |
+
"step": 270
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 2.2789115646258504,
|
| 220 |
+
"grad_norm": 6.265749931335449,
|
| 221 |
+
"learning_rate": 2.651515151515152e-06,
|
| 222 |
+
"loss": 0.4186,
|
| 223 |
+
"step": 280
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 2.312925170068027,
|
| 227 |
+
"grad_norm": 5.316267013549805,
|
| 228 |
+
"learning_rate": 7.575757575757576e-07,
|
| 229 |
+
"loss": 0.3408,
|
| 230 |
+
"step": 290
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.326530612244898,
|
| 234 |
+
"eval_accuracy": 0.7875,
|
| 235 |
+
"eval_loss": 0.45441704988479614,
|
| 236 |
+
"eval_runtime": 261.2996,
|
| 237 |
+
"eval_samples_per_second": 3.062,
|
| 238 |
+
"eval_steps_per_second": 0.191,
|
| 239 |
+
"step": 294
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 2.326530612244898,
|
| 243 |
+
"step": 294,
|
| 244 |
+
"total_flos": 5.841550795443536e+18,
|
| 245 |
+
"train_loss": 0.46131317631727986,
|
| 246 |
+
"train_runtime": 2481.7838,
|
| 247 |
+
"train_samples_per_second": 1.895,
|
| 248 |
+
"train_steps_per_second": 0.118
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.326530612244898,
|
| 252 |
+
"eval_accuracy": 0.8075,
|
| 253 |
+
"eval_loss": 0.47592803835868835,
|
| 254 |
+
"eval_runtime": 242.7873,
|
| 255 |
+
"eval_samples_per_second": 3.295,
|
| 256 |
+
"eval_steps_per_second": 0.206,
|
| 257 |
+
"step": 294
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 2.326530612244898,
|
| 261 |
+
"eval_accuracy": 0.8075,
|
| 262 |
+
"eval_loss": 0.47592803835868835,
|
| 263 |
+
"eval_runtime": 236.8069,
|
| 264 |
+
"eval_samples_per_second": 3.378,
|
| 265 |
+
"eval_steps_per_second": 0.211,
|
| 266 |
+
"step": 294
|
| 267 |
+
}
|
| 268 |
+
],
|
| 269 |
+
"logging_steps": 10,
|
| 270 |
+
"max_steps": 294,
|
| 271 |
+
"num_input_tokens_seen": 0,
|
| 272 |
+
"num_train_epochs": 9223372036854775807,
|
| 273 |
+
"save_steps": 500,
|
| 274 |
+
"stateful_callbacks": {
|
| 275 |
+
"TrainerControl": {
|
| 276 |
+
"args": {
|
| 277 |
+
"should_epoch_stop": false,
|
| 278 |
+
"should_evaluate": false,
|
| 279 |
+
"should_log": false,
|
| 280 |
+
"should_save": true,
|
| 281 |
+
"should_training_stop": true
|
| 282 |
+
},
|
| 283 |
+
"attributes": {}
|
| 284 |
+
}
|
| 285 |
+
},
|
| 286 |
+
"total_flos": 5.841550795443536e+18,
|
| 287 |
+
"train_batch_size": 16,
|
| 288 |
+
"trial_name": null,
|
| 289 |
+
"trial_params": null
|
| 290 |
+
}
|
val_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.326530612244898,
|
| 3 |
+
"eval_accuracy": 0.8075,
|
| 4 |
+
"eval_loss": 0.47592803835868835,
|
| 5 |
+
"eval_runtime": 236.8069,
|
| 6 |
+
"eval_samples_per_second": 3.378,
|
| 7 |
+
"eval_steps_per_second": 0.211
|
| 8 |
+
}
|