End of training
Browse files- all_results.json +8 -0
- test_results.json +8 -0
- trainer_state.json +479 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.5,
|
| 3 |
+
"eval_accuracy": 1.0,
|
| 4 |
+
"eval_loss": 0.002725747646763921,
|
| 5 |
+
"eval_runtime": 663.5855,
|
| 6 |
+
"eval_samples_per_second": 0.211,
|
| 7 |
+
"eval_steps_per_second": 0.105
|
| 8 |
+
}
|
test_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.5,
|
| 3 |
+
"eval_accuracy": 1.0,
|
| 4 |
+
"eval_loss": 0.002725747646763921,
|
| 5 |
+
"eval_runtime": 663.5855,
|
| 6 |
+
"eval_samples_per_second": 0.211,
|
| 7 |
+
"eval_steps_per_second": 0.105
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,479 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.0,
|
| 3 |
+
"best_model_checkpoint": "YAHIA/ViViT-b-16x2-ShopLifting-Dataset\\checkpoint-596",
|
| 4 |
+
"epoch": 1.4983221476510067,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 596,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02,
|
| 13 |
+
"grad_norm": 10.692367553710938,
|
| 14 |
+
"learning_rate": 8.333333333333334e-06,
|
| 15 |
+
"loss": 0.7508,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.03,
|
| 20 |
+
"grad_norm": 15.156712532043457,
|
| 21 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 22 |
+
"loss": 0.5978,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.05,
|
| 27 |
+
"grad_norm": 1.6303211450576782,
|
| 28 |
+
"learning_rate": 2.5e-05,
|
| 29 |
+
"loss": 0.6351,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.07,
|
| 34 |
+
"grad_norm": 41.47138214111328,
|
| 35 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 36 |
+
"loss": 0.9622,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.08,
|
| 41 |
+
"grad_norm": 1.7870268821716309,
|
| 42 |
+
"learning_rate": 4.166666666666667e-05,
|
| 43 |
+
"loss": 0.3437,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.1,
|
| 48 |
+
"grad_norm": 0.17213623225688934,
|
| 49 |
+
"learning_rate": 5e-05,
|
| 50 |
+
"loss": 0.4405,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.12,
|
| 55 |
+
"grad_norm": 0.06276705861091614,
|
| 56 |
+
"learning_rate": 4.906716417910448e-05,
|
| 57 |
+
"loss": 0.2694,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.13,
|
| 62 |
+
"grad_norm": 1.269716501235962,
|
| 63 |
+
"learning_rate": 4.813432835820896e-05,
|
| 64 |
+
"loss": 0.6896,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.15,
|
| 69 |
+
"grad_norm": 30.071969985961914,
|
| 70 |
+
"learning_rate": 4.7201492537313436e-05,
|
| 71 |
+
"loss": 1.224,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.17,
|
| 76 |
+
"grad_norm": 11.760859489440918,
|
| 77 |
+
"learning_rate": 4.626865671641791e-05,
|
| 78 |
+
"loss": 0.6247,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.18,
|
| 83 |
+
"grad_norm": 0.22317390143871307,
|
| 84 |
+
"learning_rate": 4.5335820895522394e-05,
|
| 85 |
+
"loss": 0.2921,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.2,
|
| 90 |
+
"grad_norm": 27.252477645874023,
|
| 91 |
+
"learning_rate": 4.440298507462687e-05,
|
| 92 |
+
"loss": 0.6916,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.22,
|
| 97 |
+
"grad_norm": 0.2607596814632416,
|
| 98 |
+
"learning_rate": 4.3470149253731345e-05,
|
| 99 |
+
"loss": 0.2637,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.23,
|
| 104 |
+
"grad_norm": 25.883403778076172,
|
| 105 |
+
"learning_rate": 4.253731343283582e-05,
|
| 106 |
+
"loss": 0.3661,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.25,
|
| 111 |
+
"grad_norm": 0.009978611953556538,
|
| 112 |
+
"learning_rate": 4.16044776119403e-05,
|
| 113 |
+
"loss": 0.2078,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.27,
|
| 118 |
+
"grad_norm": 28.141712188720703,
|
| 119 |
+
"learning_rate": 4.067164179104478e-05,
|
| 120 |
+
"loss": 0.4631,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.29,
|
| 125 |
+
"grad_norm": 0.08477218449115753,
|
| 126 |
+
"learning_rate": 3.9738805970149254e-05,
|
| 127 |
+
"loss": 0.7177,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.3,
|
| 132 |
+
"grad_norm": 0.6206006407737732,
|
| 133 |
+
"learning_rate": 3.8805970149253736e-05,
|
| 134 |
+
"loss": 0.0064,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.32,
|
| 139 |
+
"grad_norm": 22.071073532104492,
|
| 140 |
+
"learning_rate": 3.787313432835821e-05,
|
| 141 |
+
"loss": 0.7343,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.34,
|
| 146 |
+
"grad_norm": 134.8112335205078,
|
| 147 |
+
"learning_rate": 3.694029850746269e-05,
|
| 148 |
+
"loss": 0.1803,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.35,
|
| 153 |
+
"grad_norm": 54.530120849609375,
|
| 154 |
+
"learning_rate": 3.600746268656717e-05,
|
| 155 |
+
"loss": 0.135,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.37,
|
| 160 |
+
"grad_norm": 0.017338775098323822,
|
| 161 |
+
"learning_rate": 3.5074626865671645e-05,
|
| 162 |
+
"loss": 0.0485,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.39,
|
| 167 |
+
"grad_norm": 0.008222455158829689,
|
| 168 |
+
"learning_rate": 3.414179104477612e-05,
|
| 169 |
+
"loss": 0.311,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.4,
|
| 174 |
+
"grad_norm": 0.012648209929466248,
|
| 175 |
+
"learning_rate": 3.32089552238806e-05,
|
| 176 |
+
"loss": 0.253,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.42,
|
| 181 |
+
"grad_norm": 0.00926213525235653,
|
| 182 |
+
"learning_rate": 3.227611940298508e-05,
|
| 183 |
+
"loss": 0.0245,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.44,
|
| 188 |
+
"grad_norm": 1.1042240858078003,
|
| 189 |
+
"learning_rate": 3.1343283582089554e-05,
|
| 190 |
+
"loss": 0.2106,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.45,
|
| 195 |
+
"grad_norm": 0.034143492579460144,
|
| 196 |
+
"learning_rate": 3.0410447761194033e-05,
|
| 197 |
+
"loss": 0.268,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.47,
|
| 202 |
+
"grad_norm": 0.12180909514427185,
|
| 203 |
+
"learning_rate": 2.9477611940298512e-05,
|
| 204 |
+
"loss": 0.0042,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.49,
|
| 209 |
+
"grad_norm": 0.00459245964884758,
|
| 210 |
+
"learning_rate": 2.8544776119402988e-05,
|
| 211 |
+
"loss": 0.0004,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.5,
|
| 216 |
+
"eval_accuracy": 0.952755905511811,
|
| 217 |
+
"eval_loss": 0.26606377959251404,
|
| 218 |
+
"eval_runtime": 510.7369,
|
| 219 |
+
"eval_samples_per_second": 0.249,
|
| 220 |
+
"eval_steps_per_second": 0.125,
|
| 221 |
+
"step": 299
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.0,
|
| 225 |
+
"grad_norm": 0.006104098167270422,
|
| 226 |
+
"learning_rate": 2.7611940298507467e-05,
|
| 227 |
+
"loss": 0.0002,
|
| 228 |
+
"step": 300
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 1.02,
|
| 232 |
+
"grad_norm": 37.364593505859375,
|
| 233 |
+
"learning_rate": 2.6679104477611942e-05,
|
| 234 |
+
"loss": 0.046,
|
| 235 |
+
"step": 310
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 1.04,
|
| 239 |
+
"grad_norm": 0.030606430023908615,
|
| 240 |
+
"learning_rate": 2.574626865671642e-05,
|
| 241 |
+
"loss": 0.0002,
|
| 242 |
+
"step": 320
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.05,
|
| 246 |
+
"grad_norm": 0.3013696074485779,
|
| 247 |
+
"learning_rate": 2.4813432835820897e-05,
|
| 248 |
+
"loss": 0.5804,
|
| 249 |
+
"step": 330
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.07,
|
| 253 |
+
"grad_norm": 0.003663327544927597,
|
| 254 |
+
"learning_rate": 2.3880597014925373e-05,
|
| 255 |
+
"loss": 0.0001,
|
| 256 |
+
"step": 340
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.09,
|
| 260 |
+
"grad_norm": 0.004311152268201113,
|
| 261 |
+
"learning_rate": 2.294776119402985e-05,
|
| 262 |
+
"loss": 0.0004,
|
| 263 |
+
"step": 350
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 1.1,
|
| 267 |
+
"grad_norm": 0.04659305512905121,
|
| 268 |
+
"learning_rate": 2.201492537313433e-05,
|
| 269 |
+
"loss": 0.0002,
|
| 270 |
+
"step": 360
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 1.12,
|
| 274 |
+
"grad_norm": 0.037149786949157715,
|
| 275 |
+
"learning_rate": 2.1082089552238806e-05,
|
| 276 |
+
"loss": 0.001,
|
| 277 |
+
"step": 370
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 1.14,
|
| 281 |
+
"grad_norm": 0.03413153439760208,
|
| 282 |
+
"learning_rate": 2.0149253731343285e-05,
|
| 283 |
+
"loss": 0.0004,
|
| 284 |
+
"step": 380
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.15,
|
| 288 |
+
"grad_norm": 0.041676830500364304,
|
| 289 |
+
"learning_rate": 1.921641791044776e-05,
|
| 290 |
+
"loss": 0.0056,
|
| 291 |
+
"step": 390
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 1.17,
|
| 295 |
+
"grad_norm": 0.0016505724051967263,
|
| 296 |
+
"learning_rate": 1.828358208955224e-05,
|
| 297 |
+
"loss": 0.0002,
|
| 298 |
+
"step": 400
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 1.19,
|
| 302 |
+
"grad_norm": 0.0031964355148375034,
|
| 303 |
+
"learning_rate": 1.735074626865672e-05,
|
| 304 |
+
"loss": 0.0001,
|
| 305 |
+
"step": 410
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 1.2,
|
| 309 |
+
"grad_norm": 0.004493652377277613,
|
| 310 |
+
"learning_rate": 1.6417910447761194e-05,
|
| 311 |
+
"loss": 0.0001,
|
| 312 |
+
"step": 420
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 1.22,
|
| 316 |
+
"grad_norm": 0.0042636813595891,
|
| 317 |
+
"learning_rate": 1.5485074626865673e-05,
|
| 318 |
+
"loss": 0.0001,
|
| 319 |
+
"step": 430
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 1.24,
|
| 323 |
+
"grad_norm": 0.028110649436712265,
|
| 324 |
+
"learning_rate": 1.455223880597015e-05,
|
| 325 |
+
"loss": 0.0003,
|
| 326 |
+
"step": 440
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 1.25,
|
| 330 |
+
"grad_norm": 0.0027514537796378136,
|
| 331 |
+
"learning_rate": 1.3619402985074628e-05,
|
| 332 |
+
"loss": 0.0001,
|
| 333 |
+
"step": 450
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 1.27,
|
| 337 |
+
"grad_norm": 0.003923814278095961,
|
| 338 |
+
"learning_rate": 1.2686567164179105e-05,
|
| 339 |
+
"loss": 0.0013,
|
| 340 |
+
"step": 460
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 1.29,
|
| 344 |
+
"grad_norm": 0.001681660651229322,
|
| 345 |
+
"learning_rate": 1.1753731343283584e-05,
|
| 346 |
+
"loss": 0.1662,
|
| 347 |
+
"step": 470
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 1.3,
|
| 351 |
+
"grad_norm": 0.00280452030710876,
|
| 352 |
+
"learning_rate": 1.082089552238806e-05,
|
| 353 |
+
"loss": 0.0037,
|
| 354 |
+
"step": 480
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.32,
|
| 358 |
+
"grad_norm": 0.03961377218365669,
|
| 359 |
+
"learning_rate": 9.888059701492537e-06,
|
| 360 |
+
"loss": 0.0002,
|
| 361 |
+
"step": 490
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 1.34,
|
| 365 |
+
"grad_norm": 0.0012254673056304455,
|
| 366 |
+
"learning_rate": 8.955223880597016e-06,
|
| 367 |
+
"loss": 0.0076,
|
| 368 |
+
"step": 500
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 1.35,
|
| 372 |
+
"grad_norm": 0.0026522520929574966,
|
| 373 |
+
"learning_rate": 8.022388059701493e-06,
|
| 374 |
+
"loss": 0.0003,
|
| 375 |
+
"step": 510
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 1.37,
|
| 379 |
+
"grad_norm": 0.017898578196763992,
|
| 380 |
+
"learning_rate": 7.08955223880597e-06,
|
| 381 |
+
"loss": 0.0005,
|
| 382 |
+
"step": 520
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 1.39,
|
| 386 |
+
"grad_norm": 0.001244415994733572,
|
| 387 |
+
"learning_rate": 6.156716417910448e-06,
|
| 388 |
+
"loss": 0.0002,
|
| 389 |
+
"step": 530
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 1.4,
|
| 393 |
+
"grad_norm": 0.0038874938618391752,
|
| 394 |
+
"learning_rate": 5.2238805970149255e-06,
|
| 395 |
+
"loss": 0.0001,
|
| 396 |
+
"step": 540
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 1.42,
|
| 400 |
+
"grad_norm": 0.0015441217692568898,
|
| 401 |
+
"learning_rate": 4.291044776119403e-06,
|
| 402 |
+
"loss": 0.0001,
|
| 403 |
+
"step": 550
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 1.44,
|
| 407 |
+
"grad_norm": 0.002049211412668228,
|
| 408 |
+
"learning_rate": 3.358208955223881e-06,
|
| 409 |
+
"loss": 0.0001,
|
| 410 |
+
"step": 560
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 1.45,
|
| 414 |
+
"grad_norm": 0.09079094976186752,
|
| 415 |
+
"learning_rate": 2.4253731343283585e-06,
|
| 416 |
+
"loss": 0.0004,
|
| 417 |
+
"step": 570
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 1.47,
|
| 421 |
+
"grad_norm": 0.00330289825797081,
|
| 422 |
+
"learning_rate": 1.4925373134328358e-06,
|
| 423 |
+
"loss": 0.0001,
|
| 424 |
+
"step": 580
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 1.49,
|
| 428 |
+
"grad_norm": 0.002893247874453664,
|
| 429 |
+
"learning_rate": 5.597014925373135e-07,
|
| 430 |
+
"loss": 0.0001,
|
| 431 |
+
"step": 590
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 1.5,
|
| 435 |
+
"eval_accuracy": 1.0,
|
| 436 |
+
"eval_loss": 0.00015069438086356968,
|
| 437 |
+
"eval_runtime": 601.9366,
|
| 438 |
+
"eval_samples_per_second": 0.211,
|
| 439 |
+
"eval_steps_per_second": 0.106,
|
| 440 |
+
"step": 596
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 1.5,
|
| 444 |
+
"step": 596,
|
| 445 |
+
"total_flos": 3.0513984388253614e+18,
|
| 446 |
+
"train_loss": 0.21028166316409014,
|
| 447 |
+
"train_runtime": 8990.1785,
|
| 448 |
+
"train_samples_per_second": 0.133,
|
| 449 |
+
"train_steps_per_second": 0.066
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 1.5,
|
| 453 |
+
"eval_accuracy": 1.0,
|
| 454 |
+
"eval_loss": 0.0027257483452558517,
|
| 455 |
+
"eval_runtime": 678.7878,
|
| 456 |
+
"eval_samples_per_second": 0.206,
|
| 457 |
+
"eval_steps_per_second": 0.103,
|
| 458 |
+
"step": 596
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.5,
|
| 462 |
+
"eval_accuracy": 1.0,
|
| 463 |
+
"eval_loss": 0.002725747646763921,
|
| 464 |
+
"eval_runtime": 663.5855,
|
| 465 |
+
"eval_samples_per_second": 0.211,
|
| 466 |
+
"eval_steps_per_second": 0.105,
|
| 467 |
+
"step": 596
|
| 468 |
+
}
|
| 469 |
+
],
|
| 470 |
+
"logging_steps": 10,
|
| 471 |
+
"max_steps": 596,
|
| 472 |
+
"num_input_tokens_seen": 0,
|
| 473 |
+
"num_train_epochs": 9223372036854775807,
|
| 474 |
+
"save_steps": 500,
|
| 475 |
+
"total_flos": 3.0513984388253614e+18,
|
| 476 |
+
"train_batch_size": 2,
|
| 477 |
+
"trial_name": null,
|
| 478 |
+
"trial_params": null
|
| 479 |
+
}
|