End of training
Browse files- all_results.json +8 -0
- test_results.json +8 -0
- trainer_state.json +404 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.08,
|
| 3 |
+
"eval_accuracy": 0.49866666666666665,
|
| 4 |
+
"eval_loss": 0.7278424501419067,
|
| 5 |
+
"eval_runtime": 236.8099,
|
| 6 |
+
"eval_samples_per_second": 3.167,
|
| 7 |
+
"eval_steps_per_second": 0.198
|
| 8 |
+
}
|
test_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.08,
|
| 3 |
+
"eval_accuracy": 0.49866666666666665,
|
| 4 |
+
"eval_loss": 0.7278424501419067,
|
| 5 |
+
"eval_runtime": 236.8099,
|
| 6 |
+
"eval_samples_per_second": 3.167,
|
| 7 |
+
"eval_steps_per_second": 0.198
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,404 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.507537688442211,
|
| 3 |
+
"best_model_checkpoint": "videomae-base-finetuned-ElderReact-Happiness11/checkpoint-156",
|
| 4 |
+
"epoch": 9.076315789473684,
|
| 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": 3.6178653240203857,
|
| 14 |
+
"learning_rate": 1.3157894736842106e-05,
|
| 15 |
+
"loss": 0.6756,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.05,
|
| 20 |
+
"grad_norm": 4.96007776260376,
|
| 21 |
+
"learning_rate": 2.6315789473684212e-05,
|
| 22 |
+
"loss": 0.6977,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.08,
|
| 27 |
+
"grad_norm": 2.377594470977783,
|
| 28 |
+
"learning_rate": 3.9473684210526316e-05,
|
| 29 |
+
"loss": 0.6977,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.1,
|
| 34 |
+
"eval_accuracy": 0.4635678391959799,
|
| 35 |
+
"eval_loss": 0.7047719359397888,
|
| 36 |
+
"eval_runtime": 261.9257,
|
| 37 |
+
"eval_samples_per_second": 3.039,
|
| 38 |
+
"eval_steps_per_second": 0.191,
|
| 39 |
+
"step": 39
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.0,
|
| 43 |
+
"grad_norm": 4.699587345123291,
|
| 44 |
+
"learning_rate": 4.970760233918128e-05,
|
| 45 |
+
"loss": 0.7053,
|
| 46 |
+
"step": 40
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 1.03,
|
| 50 |
+
"grad_norm": 6.8290114402771,
|
| 51 |
+
"learning_rate": 4.824561403508772e-05,
|
| 52 |
+
"loss": 0.665,
|
| 53 |
+
"step": 50
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 1.06,
|
| 57 |
+
"grad_norm": 2.537061929702759,
|
| 58 |
+
"learning_rate": 4.678362573099415e-05,
|
| 59 |
+
"loss": 0.7055,
|
| 60 |
+
"step": 60
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 1.08,
|
| 64 |
+
"grad_norm": 1.5095937252044678,
|
| 65 |
+
"learning_rate": 4.5321637426900585e-05,
|
| 66 |
+
"loss": 0.7198,
|
| 67 |
+
"step": 70
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 1.1,
|
| 71 |
+
"eval_accuracy": 0.47110552763819097,
|
| 72 |
+
"eval_loss": 0.7133272290229797,
|
| 73 |
+
"eval_runtime": 280.3033,
|
| 74 |
+
"eval_samples_per_second": 2.84,
|
| 75 |
+
"eval_steps_per_second": 0.178,
|
| 76 |
+
"step": 78
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 2.01,
|
| 80 |
+
"grad_norm": 2.1461029052734375,
|
| 81 |
+
"learning_rate": 4.3859649122807014e-05,
|
| 82 |
+
"loss": 0.6286,
|
| 83 |
+
"step": 80
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 2.03,
|
| 87 |
+
"grad_norm": 2.1844964027404785,
|
| 88 |
+
"learning_rate": 4.239766081871345e-05,
|
| 89 |
+
"loss": 0.6547,
|
| 90 |
+
"step": 90
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 2.06,
|
| 94 |
+
"grad_norm": 4.2716522216796875,
|
| 95 |
+
"learning_rate": 4.093567251461988e-05,
|
| 96 |
+
"loss": 0.6401,
|
| 97 |
+
"step": 100
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 2.08,
|
| 101 |
+
"grad_norm": 4.427234649658203,
|
| 102 |
+
"learning_rate": 3.9473684210526316e-05,
|
| 103 |
+
"loss": 0.639,
|
| 104 |
+
"step": 110
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 2.1,
|
| 108 |
+
"eval_accuracy": 0.40703517587939697,
|
| 109 |
+
"eval_loss": 0.8557814359664917,
|
| 110 |
+
"eval_runtime": 261.857,
|
| 111 |
+
"eval_samples_per_second": 3.04,
|
| 112 |
+
"eval_steps_per_second": 0.191,
|
| 113 |
+
"step": 117
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 3.01,
|
| 117 |
+
"grad_norm": 2.5250039100646973,
|
| 118 |
+
"learning_rate": 3.8011695906432746e-05,
|
| 119 |
+
"loss": 0.7011,
|
| 120 |
+
"step": 120
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 3.03,
|
| 124 |
+
"grad_norm": 4.220043659210205,
|
| 125 |
+
"learning_rate": 3.654970760233918e-05,
|
| 126 |
+
"loss": 0.602,
|
| 127 |
+
"step": 130
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 3.06,
|
| 131 |
+
"grad_norm": 7.634807109832764,
|
| 132 |
+
"learning_rate": 3.508771929824561e-05,
|
| 133 |
+
"loss": 0.6536,
|
| 134 |
+
"step": 140
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 3.09,
|
| 138 |
+
"grad_norm": 2.9651682376861572,
|
| 139 |
+
"learning_rate": 3.362573099415205e-05,
|
| 140 |
+
"loss": 0.664,
|
| 141 |
+
"step": 150
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 3.1,
|
| 145 |
+
"eval_accuracy": 0.507537688442211,
|
| 146 |
+
"eval_loss": 0.6846373081207275,
|
| 147 |
+
"eval_runtime": 252.5146,
|
| 148 |
+
"eval_samples_per_second": 3.152,
|
| 149 |
+
"eval_steps_per_second": 0.198,
|
| 150 |
+
"step": 156
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 4.01,
|
| 154 |
+
"grad_norm": 5.29097318649292,
|
| 155 |
+
"learning_rate": 3.216374269005848e-05,
|
| 156 |
+
"loss": 0.6102,
|
| 157 |
+
"step": 160
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 4.04,
|
| 161 |
+
"grad_norm": 4.258277416229248,
|
| 162 |
+
"learning_rate": 3.0701754385964913e-05,
|
| 163 |
+
"loss": 0.6022,
|
| 164 |
+
"step": 170
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 4.06,
|
| 168 |
+
"grad_norm": 2.0270493030548096,
|
| 169 |
+
"learning_rate": 2.9239766081871346e-05,
|
| 170 |
+
"loss": 0.6251,
|
| 171 |
+
"step": 180
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 4.09,
|
| 175 |
+
"grad_norm": 3.647946834564209,
|
| 176 |
+
"learning_rate": 2.777777777777778e-05,
|
| 177 |
+
"loss": 0.6217,
|
| 178 |
+
"step": 190
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 4.1,
|
| 182 |
+
"eval_accuracy": 0.41457286432160806,
|
| 183 |
+
"eval_loss": 0.8411366939544678,
|
| 184 |
+
"eval_runtime": 254.7722,
|
| 185 |
+
"eval_samples_per_second": 3.124,
|
| 186 |
+
"eval_steps_per_second": 0.196,
|
| 187 |
+
"step": 195
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 5.01,
|
| 191 |
+
"grad_norm": 5.861187934875488,
|
| 192 |
+
"learning_rate": 2.6315789473684212e-05,
|
| 193 |
+
"loss": 0.6029,
|
| 194 |
+
"step": 200
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 5.04,
|
| 198 |
+
"grad_norm": 4.177021026611328,
|
| 199 |
+
"learning_rate": 2.485380116959064e-05,
|
| 200 |
+
"loss": 0.5714,
|
| 201 |
+
"step": 210
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 5.07,
|
| 205 |
+
"grad_norm": 2.6523263454437256,
|
| 206 |
+
"learning_rate": 2.3391812865497074e-05,
|
| 207 |
+
"loss": 0.6066,
|
| 208 |
+
"step": 220
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 5.09,
|
| 212 |
+
"grad_norm": 8.681379318237305,
|
| 213 |
+
"learning_rate": 2.1929824561403507e-05,
|
| 214 |
+
"loss": 0.5826,
|
| 215 |
+
"step": 230
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 5.1,
|
| 219 |
+
"eval_accuracy": 0.42462311557788945,
|
| 220 |
+
"eval_loss": 0.8426756262779236,
|
| 221 |
+
"eval_runtime": 246.0667,
|
| 222 |
+
"eval_samples_per_second": 3.235,
|
| 223 |
+
"eval_steps_per_second": 0.203,
|
| 224 |
+
"step": 234
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 6.02,
|
| 228 |
+
"grad_norm": 5.220656871795654,
|
| 229 |
+
"learning_rate": 2.046783625730994e-05,
|
| 230 |
+
"loss": 0.5107,
|
| 231 |
+
"step": 240
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 6.04,
|
| 235 |
+
"grad_norm": 9.55013656616211,
|
| 236 |
+
"learning_rate": 1.9005847953216373e-05,
|
| 237 |
+
"loss": 0.4856,
|
| 238 |
+
"step": 250
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 6.07,
|
| 242 |
+
"grad_norm": 4.11871862411499,
|
| 243 |
+
"learning_rate": 1.7543859649122806e-05,
|
| 244 |
+
"loss": 0.5916,
|
| 245 |
+
"step": 260
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 6.09,
|
| 249 |
+
"grad_norm": 4.019587516784668,
|
| 250 |
+
"learning_rate": 1.608187134502924e-05,
|
| 251 |
+
"loss": 0.5881,
|
| 252 |
+
"step": 270
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 6.1,
|
| 256 |
+
"eval_accuracy": 0.435929648241206,
|
| 257 |
+
"eval_loss": 0.8049066662788391,
|
| 258 |
+
"eval_runtime": 263.5585,
|
| 259 |
+
"eval_samples_per_second": 3.02,
|
| 260 |
+
"eval_steps_per_second": 0.19,
|
| 261 |
+
"step": 273
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 7.02,
|
| 265 |
+
"grad_norm": 4.318753719329834,
|
| 266 |
+
"learning_rate": 1.4619883040935673e-05,
|
| 267 |
+
"loss": 0.5706,
|
| 268 |
+
"step": 280
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 7.04,
|
| 272 |
+
"grad_norm": 4.975842475891113,
|
| 273 |
+
"learning_rate": 1.3157894736842106e-05,
|
| 274 |
+
"loss": 0.5435,
|
| 275 |
+
"step": 290
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 7.07,
|
| 279 |
+
"grad_norm": 4.172918796539307,
|
| 280 |
+
"learning_rate": 1.1695906432748537e-05,
|
| 281 |
+
"loss": 0.575,
|
| 282 |
+
"step": 300
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 7.1,
|
| 286 |
+
"grad_norm": 4.347151279449463,
|
| 287 |
+
"learning_rate": 1.023391812865497e-05,
|
| 288 |
+
"loss": 0.421,
|
| 289 |
+
"step": 310
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 7.1,
|
| 293 |
+
"eval_accuracy": 0.5050251256281407,
|
| 294 |
+
"eval_loss": 0.778738796710968,
|
| 295 |
+
"eval_runtime": 244.8077,
|
| 296 |
+
"eval_samples_per_second": 3.252,
|
| 297 |
+
"eval_steps_per_second": 0.204,
|
| 298 |
+
"step": 312
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 8.02,
|
| 302 |
+
"grad_norm": 6.215036392211914,
|
| 303 |
+
"learning_rate": 8.771929824561403e-06,
|
| 304 |
+
"loss": 0.4506,
|
| 305 |
+
"step": 320
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 8.05,
|
| 309 |
+
"grad_norm": 6.92239236831665,
|
| 310 |
+
"learning_rate": 7.3099415204678366e-06,
|
| 311 |
+
"loss": 0.6033,
|
| 312 |
+
"step": 330
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 8.07,
|
| 316 |
+
"grad_norm": 2.6235239505767822,
|
| 317 |
+
"learning_rate": 5.8479532163742686e-06,
|
| 318 |
+
"loss": 0.4765,
|
| 319 |
+
"step": 340
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 8.1,
|
| 323 |
+
"grad_norm": 5.367151260375977,
|
| 324 |
+
"learning_rate": 4.3859649122807014e-06,
|
| 325 |
+
"loss": 0.4674,
|
| 326 |
+
"step": 350
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 8.1,
|
| 330 |
+
"eval_accuracy": 0.47361809045226133,
|
| 331 |
+
"eval_loss": 0.8280923962593079,
|
| 332 |
+
"eval_runtime": 266.1328,
|
| 333 |
+
"eval_samples_per_second": 2.991,
|
| 334 |
+
"eval_steps_per_second": 0.188,
|
| 335 |
+
"step": 351
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 9.02,
|
| 339 |
+
"grad_norm": 3.808866500854492,
|
| 340 |
+
"learning_rate": 2.9239766081871343e-06,
|
| 341 |
+
"loss": 0.5096,
|
| 342 |
+
"step": 360
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 9.05,
|
| 346 |
+
"grad_norm": 5.840443134307861,
|
| 347 |
+
"learning_rate": 1.4619883040935671e-06,
|
| 348 |
+
"loss": 0.4805,
|
| 349 |
+
"step": 370
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 9.08,
|
| 353 |
+
"grad_norm": 6.295402526855469,
|
| 354 |
+
"learning_rate": 0.0,
|
| 355 |
+
"loss": 0.4775,
|
| 356 |
+
"step": 380
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 9.08,
|
| 360 |
+
"eval_accuracy": 0.4434673366834171,
|
| 361 |
+
"eval_loss": 0.8615225553512573,
|
| 362 |
+
"eval_runtime": 248.7642,
|
| 363 |
+
"eval_samples_per_second": 3.2,
|
| 364 |
+
"eval_steps_per_second": 0.201,
|
| 365 |
+
"step": 380
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 9.08,
|
| 369 |
+
"step": 380,
|
| 370 |
+
"total_flos": 7.475141472240992e+18,
|
| 371 |
+
"train_loss": 0.5953672107897306,
|
| 372 |
+
"train_runtime": 4834.4844,
|
| 373 |
+
"train_samples_per_second": 1.258,
|
| 374 |
+
"train_steps_per_second": 0.079
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 9.08,
|
| 378 |
+
"eval_accuracy": 0.49866666666666665,
|
| 379 |
+
"eval_loss": 0.7278424501419067,
|
| 380 |
+
"eval_runtime": 243.6787,
|
| 381 |
+
"eval_samples_per_second": 3.078,
|
| 382 |
+
"eval_steps_per_second": 0.193,
|
| 383 |
+
"step": 380
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 9.08,
|
| 387 |
+
"eval_accuracy": 0.49866666666666665,
|
| 388 |
+
"eval_loss": 0.7278424501419067,
|
| 389 |
+
"eval_runtime": 236.8099,
|
| 390 |
+
"eval_samples_per_second": 3.167,
|
| 391 |
+
"eval_steps_per_second": 0.198,
|
| 392 |
+
"step": 380
|
| 393 |
+
}
|
| 394 |
+
],
|
| 395 |
+
"logging_steps": 10,
|
| 396 |
+
"max_steps": 380,
|
| 397 |
+
"num_input_tokens_seen": 0,
|
| 398 |
+
"num_train_epochs": 9223372036854775807,
|
| 399 |
+
"save_steps": 500,
|
| 400 |
+
"total_flos": 7.475141472240992e+18,
|
| 401 |
+
"train_batch_size": 16,
|
| 402 |
+
"trial_name": null,
|
| 403 |
+
"trial_params": null
|
| 404 |
+
}
|