End of training
Browse files- all_results.json +8 -0
- test_results.json +8 -0
- trainer_state.json +359 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.19,
|
| 3 |
+
"eval_f1": 0.0,
|
| 4 |
+
"eval_loss": 0.5602522492408752,
|
| 5 |
+
"eval_runtime": 1096.1841,
|
| 6 |
+
"eval_samples_per_second": 0.684,
|
| 7 |
+
"eval_steps_per_second": 0.086
|
| 8 |
+
}
|
test_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.19,
|
| 3 |
+
"eval_f1": 0.0,
|
| 4 |
+
"eval_loss": 0.5602522492408752,
|
| 5 |
+
"eval_runtime": 1096.1841,
|
| 6 |
+
"eval_samples_per_second": 0.684,
|
| 7 |
+
"eval_steps_per_second": 0.086
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,359 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.0,
|
| 3 |
+
"best_model_checkpoint": "videomae-base-finetuned-ElderReact-Sadness/checkpoint-77",
|
| 4 |
+
"epoch": 4.189473684210526,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 380,
|
| 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": 8.733156204223633,
|
| 14 |
+
"learning_rate": 1.3157894736842106e-05,
|
| 15 |
+
"loss": 0.8614,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.05,
|
| 20 |
+
"grad_norm": 2.5065677165985107,
|
| 21 |
+
"learning_rate": 2.6315789473684212e-05,
|
| 22 |
+
"loss": 0.4565,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.08,
|
| 27 |
+
"grad_norm": 3.9178378582000732,
|
| 28 |
+
"learning_rate": 3.9473684210526316e-05,
|
| 29 |
+
"loss": 0.6916,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.11,
|
| 34 |
+
"grad_norm": 3.131615161895752,
|
| 35 |
+
"learning_rate": 4.970760233918128e-05,
|
| 36 |
+
"loss": 0.4775,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.13,
|
| 41 |
+
"grad_norm": 2.4320406913757324,
|
| 42 |
+
"learning_rate": 4.824561403508772e-05,
|
| 43 |
+
"loss": 0.5228,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.16,
|
| 48 |
+
"grad_norm": 3.9200363159179688,
|
| 49 |
+
"learning_rate": 4.678362573099415e-05,
|
| 50 |
+
"loss": 0.543,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.18,
|
| 55 |
+
"grad_norm": 5.265003204345703,
|
| 56 |
+
"learning_rate": 4.5321637426900585e-05,
|
| 57 |
+
"loss": 0.4849,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.2,
|
| 62 |
+
"eval_f1": 0.0,
|
| 63 |
+
"eval_loss": 0.562191903591156,
|
| 64 |
+
"eval_runtime": 1559.6394,
|
| 65 |
+
"eval_samples_per_second": 0.51,
|
| 66 |
+
"eval_steps_per_second": 0.064,
|
| 67 |
+
"step": 77
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 1.01,
|
| 71 |
+
"grad_norm": 7.044685363769531,
|
| 72 |
+
"learning_rate": 4.3859649122807014e-05,
|
| 73 |
+
"loss": 0.484,
|
| 74 |
+
"step": 80
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.03,
|
| 78 |
+
"grad_norm": 5.2160563468933105,
|
| 79 |
+
"learning_rate": 4.239766081871345e-05,
|
| 80 |
+
"loss": 0.5683,
|
| 81 |
+
"step": 90
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.06,
|
| 85 |
+
"grad_norm": 4.619358539581299,
|
| 86 |
+
"learning_rate": 4.093567251461988e-05,
|
| 87 |
+
"loss": 0.4599,
|
| 88 |
+
"step": 100
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.09,
|
| 92 |
+
"grad_norm": 1.9805103540420532,
|
| 93 |
+
"learning_rate": 3.9473684210526316e-05,
|
| 94 |
+
"loss": 0.4367,
|
| 95 |
+
"step": 110
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.11,
|
| 99 |
+
"grad_norm": 8.803659439086914,
|
| 100 |
+
"learning_rate": 3.8011695906432746e-05,
|
| 101 |
+
"loss": 0.5594,
|
| 102 |
+
"step": 120
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.14,
|
| 106 |
+
"grad_norm": 2.0656039714813232,
|
| 107 |
+
"learning_rate": 3.654970760233918e-05,
|
| 108 |
+
"loss": 0.4642,
|
| 109 |
+
"step": 130
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.17,
|
| 113 |
+
"grad_norm": 3.4128127098083496,
|
| 114 |
+
"learning_rate": 3.508771929824561e-05,
|
| 115 |
+
"loss": 0.4347,
|
| 116 |
+
"step": 140
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.19,
|
| 120 |
+
"grad_norm": 1.4679104089736938,
|
| 121 |
+
"learning_rate": 3.362573099415205e-05,
|
| 122 |
+
"loss": 0.6142,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.2,
|
| 127 |
+
"eval_f1": 0.0,
|
| 128 |
+
"eval_loss": 0.5103093385696411,
|
| 129 |
+
"eval_runtime": 1584.0126,
|
| 130 |
+
"eval_samples_per_second": 0.503,
|
| 131 |
+
"eval_steps_per_second": 0.063,
|
| 132 |
+
"step": 154
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 2.02,
|
| 136 |
+
"grad_norm": 2.87197208404541,
|
| 137 |
+
"learning_rate": 3.216374269005848e-05,
|
| 138 |
+
"loss": 0.386,
|
| 139 |
+
"step": 160
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 2.04,
|
| 143 |
+
"grad_norm": 3.87532901763916,
|
| 144 |
+
"learning_rate": 3.0701754385964913e-05,
|
| 145 |
+
"loss": 0.4474,
|
| 146 |
+
"step": 170
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.07,
|
| 150 |
+
"grad_norm": 2.707888603210449,
|
| 151 |
+
"learning_rate": 2.9239766081871346e-05,
|
| 152 |
+
"loss": 0.5089,
|
| 153 |
+
"step": 180
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 2.09,
|
| 157 |
+
"grad_norm": 2.239783525466919,
|
| 158 |
+
"learning_rate": 2.777777777777778e-05,
|
| 159 |
+
"loss": 0.5545,
|
| 160 |
+
"step": 190
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 2.12,
|
| 164 |
+
"grad_norm": 5.229273796081543,
|
| 165 |
+
"learning_rate": 2.6315789473684212e-05,
|
| 166 |
+
"loss": 0.5179,
|
| 167 |
+
"step": 200
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 2.15,
|
| 171 |
+
"grad_norm": 5.174344062805176,
|
| 172 |
+
"learning_rate": 2.485380116959064e-05,
|
| 173 |
+
"loss": 0.4611,
|
| 174 |
+
"step": 210
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 2.17,
|
| 178 |
+
"grad_norm": 8.643746376037598,
|
| 179 |
+
"learning_rate": 2.3391812865497074e-05,
|
| 180 |
+
"loss": 0.5094,
|
| 181 |
+
"step": 220
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 2.2,
|
| 185 |
+
"grad_norm": 2.9545063972473145,
|
| 186 |
+
"learning_rate": 2.1929824561403507e-05,
|
| 187 |
+
"loss": 0.3716,
|
| 188 |
+
"step": 230
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.2,
|
| 192 |
+
"eval_f1": 0.0,
|
| 193 |
+
"eval_loss": 0.5194397568702698,
|
| 194 |
+
"eval_runtime": 1491.9026,
|
| 195 |
+
"eval_samples_per_second": 0.534,
|
| 196 |
+
"eval_steps_per_second": 0.067,
|
| 197 |
+
"step": 231
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 3.02,
|
| 201 |
+
"grad_norm": 1.3416327238082886,
|
| 202 |
+
"learning_rate": 2.046783625730994e-05,
|
| 203 |
+
"loss": 0.3645,
|
| 204 |
+
"step": 240
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 3.05,
|
| 208 |
+
"grad_norm": 3.5003273487091064,
|
| 209 |
+
"learning_rate": 1.9005847953216373e-05,
|
| 210 |
+
"loss": 0.4325,
|
| 211 |
+
"step": 250
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 3.08,
|
| 215 |
+
"grad_norm": 2.262181043624878,
|
| 216 |
+
"learning_rate": 1.7543859649122806e-05,
|
| 217 |
+
"loss": 0.4698,
|
| 218 |
+
"step": 260
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 3.1,
|
| 222 |
+
"grad_norm": 4.914053916931152,
|
| 223 |
+
"learning_rate": 1.608187134502924e-05,
|
| 224 |
+
"loss": 0.4821,
|
| 225 |
+
"step": 270
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 3.13,
|
| 229 |
+
"grad_norm": 1.7723067998886108,
|
| 230 |
+
"learning_rate": 1.4619883040935673e-05,
|
| 231 |
+
"loss": 0.5028,
|
| 232 |
+
"step": 280
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 3.16,
|
| 236 |
+
"grad_norm": 2.144120454788208,
|
| 237 |
+
"learning_rate": 1.3157894736842106e-05,
|
| 238 |
+
"loss": 0.4522,
|
| 239 |
+
"step": 290
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 3.18,
|
| 243 |
+
"grad_norm": 8.266680717468262,
|
| 244 |
+
"learning_rate": 1.1695906432748537e-05,
|
| 245 |
+
"loss": 0.5747,
|
| 246 |
+
"step": 300
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 3.2,
|
| 250 |
+
"eval_f1": 0.0,
|
| 251 |
+
"eval_loss": 0.5140724778175354,
|
| 252 |
+
"eval_runtime": 1509.3663,
|
| 253 |
+
"eval_samples_per_second": 0.527,
|
| 254 |
+
"eval_steps_per_second": 0.066,
|
| 255 |
+
"step": 308
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 4.01,
|
| 259 |
+
"grad_norm": 1.3488402366638184,
|
| 260 |
+
"learning_rate": 1.023391812865497e-05,
|
| 261 |
+
"loss": 0.4201,
|
| 262 |
+
"step": 310
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 4.03,
|
| 266 |
+
"grad_norm": 5.935779094696045,
|
| 267 |
+
"learning_rate": 8.771929824561403e-06,
|
| 268 |
+
"loss": 0.4379,
|
| 269 |
+
"step": 320
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 4.06,
|
| 273 |
+
"grad_norm": 5.667685508728027,
|
| 274 |
+
"learning_rate": 7.3099415204678366e-06,
|
| 275 |
+
"loss": 0.5889,
|
| 276 |
+
"step": 330
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 4.08,
|
| 280 |
+
"grad_norm": 2.8014166355133057,
|
| 281 |
+
"learning_rate": 5.8479532163742686e-06,
|
| 282 |
+
"loss": 0.3455,
|
| 283 |
+
"step": 340
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 4.11,
|
| 287 |
+
"grad_norm": 2.801328659057617,
|
| 288 |
+
"learning_rate": 4.3859649122807014e-06,
|
| 289 |
+
"loss": 0.4534,
|
| 290 |
+
"step": 350
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 4.14,
|
| 294 |
+
"grad_norm": 1.3298965692520142,
|
| 295 |
+
"learning_rate": 2.9239766081871343e-06,
|
| 296 |
+
"loss": 0.3722,
|
| 297 |
+
"step": 360
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 4.16,
|
| 301 |
+
"grad_norm": 1.345963716506958,
|
| 302 |
+
"learning_rate": 1.4619883040935671e-06,
|
| 303 |
+
"loss": 0.5017,
|
| 304 |
+
"step": 370
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 4.19,
|
| 308 |
+
"grad_norm": 3.070298671722412,
|
| 309 |
+
"learning_rate": 0.0,
|
| 310 |
+
"loss": 0.5651,
|
| 311 |
+
"step": 380
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 4.19,
|
| 315 |
+
"eval_f1": 0.0,
|
| 316 |
+
"eval_loss": 0.5184840559959412,
|
| 317 |
+
"eval_runtime": 1440.3381,
|
| 318 |
+
"eval_samples_per_second": 0.553,
|
| 319 |
+
"eval_steps_per_second": 0.069,
|
| 320 |
+
"step": 380
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 4.19,
|
| 324 |
+
"step": 380,
|
| 325 |
+
"total_flos": 3.783052093636215e+18,
|
| 326 |
+
"train_loss": 0.4941942767093056,
|
| 327 |
+
"train_runtime": 18908.6056,
|
| 328 |
+
"train_samples_per_second": 0.161,
|
| 329 |
+
"train_steps_per_second": 0.02
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 4.19,
|
| 333 |
+
"eval_f1": 0.0,
|
| 334 |
+
"eval_loss": 0.5602521896362305,
|
| 335 |
+
"eval_runtime": 1292.4629,
|
| 336 |
+
"eval_samples_per_second": 0.58,
|
| 337 |
+
"eval_steps_per_second": 0.073,
|
| 338 |
+
"step": 380
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 4.19,
|
| 342 |
+
"eval_f1": 0.0,
|
| 343 |
+
"eval_loss": 0.5602522492408752,
|
| 344 |
+
"eval_runtime": 1096.1841,
|
| 345 |
+
"eval_samples_per_second": 0.684,
|
| 346 |
+
"eval_steps_per_second": 0.086,
|
| 347 |
+
"step": 380
|
| 348 |
+
}
|
| 349 |
+
],
|
| 350 |
+
"logging_steps": 10,
|
| 351 |
+
"max_steps": 380,
|
| 352 |
+
"num_input_tokens_seen": 0,
|
| 353 |
+
"num_train_epochs": 9223372036854775807,
|
| 354 |
+
"save_steps": 500,
|
| 355 |
+
"total_flos": 3.783052093636215e+18,
|
| 356 |
+
"train_batch_size": 8,
|
| 357 |
+
"trial_name": null,
|
| 358 |
+
"trial_params": null
|
| 359 |
+
}
|