End of training
Browse files- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +271 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 3.4709447650818164,
|
| 4 |
+
"train_runtime": 56.0951,
|
| 5 |
+
"train_samples": 209,
|
| 6 |
+
"train_samples_per_second": 3.726,
|
| 7 |
+
"train_steps_per_second": 3.726
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 3.4709447650818164,
|
| 4 |
+
"train_runtime": 56.0951,
|
| 5 |
+
"train_samples": 209,
|
| 6 |
+
"train_samples_per_second": 3.726,
|
| 7 |
+
"train_steps_per_second": 3.726
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,271 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"global_step": 209,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.02,
|
| 12 |
+
"learning_rate": 0.0001339177033492823,
|
| 13 |
+
"loss": 4.9076,
|
| 14 |
+
"step": 5
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.05,
|
| 18 |
+
"learning_rate": 0.0001306354066985646,
|
| 19 |
+
"loss": 4.477,
|
| 20 |
+
"step": 10
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.07,
|
| 24 |
+
"learning_rate": 0.0001273531100478469,
|
| 25 |
+
"loss": 4.4198,
|
| 26 |
+
"step": 15
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.1,
|
| 30 |
+
"learning_rate": 0.0001240708133971292,
|
| 31 |
+
"loss": 4.2271,
|
| 32 |
+
"step": 20
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.12,
|
| 36 |
+
"learning_rate": 0.00012078851674641149,
|
| 37 |
+
"loss": 4.0551,
|
| 38 |
+
"step": 25
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.14,
|
| 42 |
+
"learning_rate": 0.00011750622009569378,
|
| 43 |
+
"loss": 3.9819,
|
| 44 |
+
"step": 30
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.17,
|
| 48 |
+
"learning_rate": 0.00011422392344497608,
|
| 49 |
+
"loss": 3.9541,
|
| 50 |
+
"step": 35
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.19,
|
| 54 |
+
"learning_rate": 0.00011094162679425838,
|
| 55 |
+
"loss": 3.9238,
|
| 56 |
+
"step": 40
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.22,
|
| 60 |
+
"learning_rate": 0.00010765933014354067,
|
| 61 |
+
"loss": 3.888,
|
| 62 |
+
"step": 45
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.24,
|
| 66 |
+
"learning_rate": 0.00010437703349282297,
|
| 67 |
+
"loss": 3.6435,
|
| 68 |
+
"step": 50
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.26,
|
| 72 |
+
"learning_rate": 0.00010109473684210525,
|
| 73 |
+
"loss": 3.548,
|
| 74 |
+
"step": 55
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.29,
|
| 78 |
+
"learning_rate": 9.781244019138755e-05,
|
| 79 |
+
"loss": 3.6575,
|
| 80 |
+
"step": 60
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.31,
|
| 84 |
+
"learning_rate": 9.453014354066986e-05,
|
| 85 |
+
"loss": 3.7024,
|
| 86 |
+
"step": 65
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.33,
|
| 90 |
+
"learning_rate": 9.124784688995216e-05,
|
| 91 |
+
"loss": 3.5278,
|
| 92 |
+
"step": 70
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.36,
|
| 96 |
+
"learning_rate": 8.796555023923445e-05,
|
| 97 |
+
"loss": 3.4996,
|
| 98 |
+
"step": 75
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.38,
|
| 102 |
+
"learning_rate": 8.468325358851675e-05,
|
| 103 |
+
"loss": 3.5006,
|
| 104 |
+
"step": 80
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.41,
|
| 108 |
+
"learning_rate": 8.140095693779905e-05,
|
| 109 |
+
"loss": 3.4716,
|
| 110 |
+
"step": 85
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.43,
|
| 114 |
+
"learning_rate": 7.811866028708133e-05,
|
| 115 |
+
"loss": 3.3409,
|
| 116 |
+
"step": 90
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.45,
|
| 120 |
+
"learning_rate": 7.483636363636363e-05,
|
| 121 |
+
"loss": 3.3467,
|
| 122 |
+
"step": 95
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.48,
|
| 126 |
+
"learning_rate": 7.155406698564593e-05,
|
| 127 |
+
"loss": 3.3855,
|
| 128 |
+
"step": 100
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.5,
|
| 132 |
+
"learning_rate": 6.827177033492822e-05,
|
| 133 |
+
"loss": 3.3672,
|
| 134 |
+
"step": 105
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.53,
|
| 138 |
+
"learning_rate": 6.498947368421052e-05,
|
| 139 |
+
"loss": 3.2343,
|
| 140 |
+
"step": 110
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.55,
|
| 144 |
+
"learning_rate": 6.170717703349283e-05,
|
| 145 |
+
"loss": 3.3405,
|
| 146 |
+
"step": 115
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.57,
|
| 150 |
+
"learning_rate": 5.842488038277512e-05,
|
| 151 |
+
"loss": 3.2181,
|
| 152 |
+
"step": 120
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.6,
|
| 156 |
+
"learning_rate": 5.5142583732057416e-05,
|
| 157 |
+
"loss": 3.2851,
|
| 158 |
+
"step": 125
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.62,
|
| 162 |
+
"learning_rate": 5.1860287081339706e-05,
|
| 163 |
+
"loss": 3.2362,
|
| 164 |
+
"step": 130
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.65,
|
| 168 |
+
"learning_rate": 4.857799043062201e-05,
|
| 169 |
+
"loss": 3.1771,
|
| 170 |
+
"step": 135
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.67,
|
| 174 |
+
"learning_rate": 4.529569377990431e-05,
|
| 175 |
+
"loss": 3.2146,
|
| 176 |
+
"step": 140
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.69,
|
| 180 |
+
"learning_rate": 4.2013397129186604e-05,
|
| 181 |
+
"loss": 3.2209,
|
| 182 |
+
"step": 145
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.72,
|
| 186 |
+
"learning_rate": 3.8731100478468894e-05,
|
| 187 |
+
"loss": 3.2406,
|
| 188 |
+
"step": 150
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.74,
|
| 192 |
+
"learning_rate": 3.54488038277512e-05,
|
| 193 |
+
"loss": 3.0664,
|
| 194 |
+
"step": 155
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.77,
|
| 198 |
+
"learning_rate": 3.2166507177033495e-05,
|
| 199 |
+
"loss": 3.0473,
|
| 200 |
+
"step": 160
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.79,
|
| 204 |
+
"learning_rate": 2.8884210526315788e-05,
|
| 205 |
+
"loss": 3.2034,
|
| 206 |
+
"step": 165
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.81,
|
| 210 |
+
"learning_rate": 2.5601913875598085e-05,
|
| 211 |
+
"loss": 3.1364,
|
| 212 |
+
"step": 170
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.84,
|
| 216 |
+
"learning_rate": 2.2319617224880382e-05,
|
| 217 |
+
"loss": 3.0634,
|
| 218 |
+
"step": 175
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.86,
|
| 222 |
+
"learning_rate": 1.903732057416268e-05,
|
| 223 |
+
"loss": 3.1028,
|
| 224 |
+
"step": 180
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.89,
|
| 228 |
+
"learning_rate": 1.5755023923444976e-05,
|
| 229 |
+
"loss": 3.0197,
|
| 230 |
+
"step": 185
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.91,
|
| 234 |
+
"learning_rate": 1.2472727272727273e-05,
|
| 235 |
+
"loss": 3.0413,
|
| 236 |
+
"step": 190
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.93,
|
| 240 |
+
"learning_rate": 9.19043062200957e-06,
|
| 241 |
+
"loss": 3.0188,
|
| 242 |
+
"step": 195
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.96,
|
| 246 |
+
"learning_rate": 5.908133971291866e-06,
|
| 247 |
+
"loss": 2.9653,
|
| 248 |
+
"step": 200
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.98,
|
| 252 |
+
"learning_rate": 2.6258373205741627e-06,
|
| 253 |
+
"loss": 3.063,
|
| 254 |
+
"step": 205
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.0,
|
| 258 |
+
"step": 209,
|
| 259 |
+
"total_flos": 109220069376000.0,
|
| 260 |
+
"train_loss": 3.4709447650818164,
|
| 261 |
+
"train_runtime": 56.0951,
|
| 262 |
+
"train_samples_per_second": 3.726,
|
| 263 |
+
"train_steps_per_second": 3.726
|
| 264 |
+
}
|
| 265 |
+
],
|
| 266 |
+
"max_steps": 209,
|
| 267 |
+
"num_train_epochs": 1,
|
| 268 |
+
"total_flos": 109220069376000.0,
|
| 269 |
+
"trial_name": null,
|
| 270 |
+
"trial_params": null
|
| 271 |
+
}
|