End of training
Browse files- all_results.json +14 -0
- eval_results.json +9 -0
- train_results.json +8 -0
- trainer_state.json +304 -0
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.0,
|
| 3 |
+
"eval_f1": 0.6717231571462432,
|
| 4 |
+
"eval_loss": 0.21304987370967865,
|
| 5 |
+
"eval_runtime": 3.3638,
|
| 6 |
+
"eval_samples": 989,
|
| 7 |
+
"eval_samples_per_second": 294.016,
|
| 8 |
+
"eval_steps_per_second": 4.757,
|
| 9 |
+
"train_loss": 0.2572957956662742,
|
| 10 |
+
"train_runtime": 515.2049,
|
| 11 |
+
"train_samples": 7914,
|
| 12 |
+
"train_samples_per_second": 92.165,
|
| 13 |
+
"train_steps_per_second": 0.722
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.0,
|
| 3 |
+
"eval_f1": 0.6717231571462432,
|
| 4 |
+
"eval_loss": 0.21304987370967865,
|
| 5 |
+
"eval_runtime": 3.3638,
|
| 6 |
+
"eval_samples": 989,
|
| 7 |
+
"eval_samples_per_second": 294.016,
|
| 8 |
+
"eval_steps_per_second": 4.757
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.0,
|
| 3 |
+
"train_loss": 0.2572957956662742,
|
| 4 |
+
"train_runtime": 515.2049,
|
| 5 |
+
"train_samples": 7914,
|
| 6 |
+
"train_samples_per_second": 92.165,
|
| 7 |
+
"train_steps_per_second": 0.722
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,304 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 6.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 372,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.16,
|
| 13 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 14 |
+
"loss": 0.6871,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.32,
|
| 19 |
+
"learning_rate": 3.943977591036415e-05,
|
| 20 |
+
"loss": 0.506,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.48,
|
| 25 |
+
"learning_rate": 3.8319327731092444e-05,
|
| 26 |
+
"loss": 0.386,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.65,
|
| 31 |
+
"learning_rate": 3.719887955182073e-05,
|
| 32 |
+
"loss": 0.3467,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.81,
|
| 37 |
+
"learning_rate": 3.6078431372549025e-05,
|
| 38 |
+
"loss": 0.3235,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.97,
|
| 43 |
+
"learning_rate": 3.495798319327731e-05,
|
| 44 |
+
"loss": 0.3118,
|
| 45 |
+
"step": 60
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.0,
|
| 49 |
+
"eval_f1": 0.336166194523135,
|
| 50 |
+
"eval_loss": 0.2885044813156128,
|
| 51 |
+
"eval_runtime": 3.3771,
|
| 52 |
+
"eval_samples_per_second": 292.857,
|
| 53 |
+
"eval_steps_per_second": 4.738,
|
| 54 |
+
"step": 62
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.13,
|
| 58 |
+
"learning_rate": 3.383753501400561e-05,
|
| 59 |
+
"loss": 0.3046,
|
| 60 |
+
"step": 70
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 1.29,
|
| 64 |
+
"learning_rate": 3.2717086834733894e-05,
|
| 65 |
+
"loss": 0.2906,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 1.45,
|
| 70 |
+
"learning_rate": 3.159663865546219e-05,
|
| 71 |
+
"loss": 0.2896,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 1.61,
|
| 76 |
+
"learning_rate": 3.047619047619048e-05,
|
| 77 |
+
"loss": 0.2826,
|
| 78 |
+
"step": 100
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 1.77,
|
| 82 |
+
"learning_rate": 2.935574229691877e-05,
|
| 83 |
+
"loss": 0.2749,
|
| 84 |
+
"step": 110
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 1.94,
|
| 88 |
+
"learning_rate": 2.8235294117647063e-05,
|
| 89 |
+
"loss": 0.2676,
|
| 90 |
+
"step": 120
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 2.0,
|
| 94 |
+
"eval_f1": 0.4882154882154882,
|
| 95 |
+
"eval_loss": 0.25112977623939514,
|
| 96 |
+
"eval_runtime": 3.3888,
|
| 97 |
+
"eval_samples_per_second": 291.842,
|
| 98 |
+
"eval_steps_per_second": 4.721,
|
| 99 |
+
"step": 124
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.1,
|
| 103 |
+
"learning_rate": 2.7114845938375354e-05,
|
| 104 |
+
"loss": 0.2534,
|
| 105 |
+
"step": 130
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 2.26,
|
| 109 |
+
"learning_rate": 2.5994397759103644e-05,
|
| 110 |
+
"loss": 0.2491,
|
| 111 |
+
"step": 140
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 2.42,
|
| 115 |
+
"learning_rate": 2.4873949579831935e-05,
|
| 116 |
+
"loss": 0.2452,
|
| 117 |
+
"step": 150
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 2.58,
|
| 121 |
+
"learning_rate": 2.3753501400560226e-05,
|
| 122 |
+
"loss": 0.2373,
|
| 123 |
+
"step": 160
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 2.74,
|
| 127 |
+
"learning_rate": 2.2633053221288516e-05,
|
| 128 |
+
"loss": 0.2355,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 2.9,
|
| 133 |
+
"learning_rate": 2.1512605042016807e-05,
|
| 134 |
+
"loss": 0.2325,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 3.0,
|
| 139 |
+
"eval_f1": 0.6093467596178673,
|
| 140 |
+
"eval_loss": 0.22724518179893494,
|
| 141 |
+
"eval_runtime": 3.3851,
|
| 142 |
+
"eval_samples_per_second": 292.16,
|
| 143 |
+
"eval_steps_per_second": 4.727,
|
| 144 |
+
"step": 186
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.06,
|
| 148 |
+
"learning_rate": 2.0392156862745097e-05,
|
| 149 |
+
"loss": 0.231,
|
| 150 |
+
"step": 190
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 3.23,
|
| 154 |
+
"learning_rate": 1.927170868347339e-05,
|
| 155 |
+
"loss": 0.2195,
|
| 156 |
+
"step": 200
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 3.39,
|
| 160 |
+
"learning_rate": 1.8151260504201682e-05,
|
| 161 |
+
"loss": 0.2156,
|
| 162 |
+
"step": 210
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 3.55,
|
| 166 |
+
"learning_rate": 1.7030812324929973e-05,
|
| 167 |
+
"loss": 0.2184,
|
| 168 |
+
"step": 220
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 3.71,
|
| 172 |
+
"learning_rate": 1.5910364145658263e-05,
|
| 173 |
+
"loss": 0.2109,
|
| 174 |
+
"step": 230
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 3.87,
|
| 178 |
+
"learning_rate": 1.4789915966386557e-05,
|
| 179 |
+
"loss": 0.2127,
|
| 180 |
+
"step": 240
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 4.0,
|
| 184 |
+
"eval_f1": 0.6591346153846154,
|
| 185 |
+
"eval_loss": 0.21806256473064423,
|
| 186 |
+
"eval_runtime": 3.3784,
|
| 187 |
+
"eval_samples_per_second": 292.738,
|
| 188 |
+
"eval_steps_per_second": 4.736,
|
| 189 |
+
"step": 248
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 4.03,
|
| 193 |
+
"learning_rate": 1.3669467787114848e-05,
|
| 194 |
+
"loss": 0.2067,
|
| 195 |
+
"step": 250
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 4.19,
|
| 199 |
+
"learning_rate": 1.2549019607843138e-05,
|
| 200 |
+
"loss": 0.1984,
|
| 201 |
+
"step": 260
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 4.35,
|
| 205 |
+
"learning_rate": 1.1428571428571429e-05,
|
| 206 |
+
"loss": 0.1957,
|
| 207 |
+
"step": 270
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 4.52,
|
| 211 |
+
"learning_rate": 1.030812324929972e-05,
|
| 212 |
+
"loss": 0.1967,
|
| 213 |
+
"step": 280
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 4.68,
|
| 217 |
+
"learning_rate": 9.187675070028012e-06,
|
| 218 |
+
"loss": 0.1975,
|
| 219 |
+
"step": 290
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 4.84,
|
| 223 |
+
"learning_rate": 8.067226890756303e-06,
|
| 224 |
+
"loss": 0.194,
|
| 225 |
+
"step": 300
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 5.0,
|
| 229 |
+
"learning_rate": 6.946778711484594e-06,
|
| 230 |
+
"loss": 0.1978,
|
| 231 |
+
"step": 310
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 5.0,
|
| 235 |
+
"eval_f1": 0.6685687113647171,
|
| 236 |
+
"eval_loss": 0.2140355408191681,
|
| 237 |
+
"eval_runtime": 3.3785,
|
| 238 |
+
"eval_samples_per_second": 292.736,
|
| 239 |
+
"eval_steps_per_second": 4.736,
|
| 240 |
+
"step": 310
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 5.16,
|
| 244 |
+
"learning_rate": 5.826330532212886e-06,
|
| 245 |
+
"loss": 0.1877,
|
| 246 |
+
"step": 320
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 5.32,
|
| 250 |
+
"learning_rate": 4.705882352941177e-06,
|
| 251 |
+
"loss": 0.1877,
|
| 252 |
+
"step": 330
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 5.48,
|
| 256 |
+
"learning_rate": 3.585434173669468e-06,
|
| 257 |
+
"loss": 0.1803,
|
| 258 |
+
"step": 340
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 5.65,
|
| 262 |
+
"learning_rate": 2.4649859943977594e-06,
|
| 263 |
+
"loss": 0.1874,
|
| 264 |
+
"step": 350
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 5.81,
|
| 268 |
+
"learning_rate": 1.3445378151260504e-06,
|
| 269 |
+
"loss": 0.1911,
|
| 270 |
+
"step": 360
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 5.97,
|
| 274 |
+
"learning_rate": 2.2408963585434175e-07,
|
| 275 |
+
"loss": 0.1817,
|
| 276 |
+
"step": 370
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 6.0,
|
| 280 |
+
"eval_f1": 0.6717231571462432,
|
| 281 |
+
"eval_loss": 0.21304987370967865,
|
| 282 |
+
"eval_runtime": 3.3805,
|
| 283 |
+
"eval_samples_per_second": 292.556,
|
| 284 |
+
"eval_steps_per_second": 4.733,
|
| 285 |
+
"step": 372
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 6.0,
|
| 289 |
+
"step": 372,
|
| 290 |
+
"total_flos": 1.2495360147628032e+16,
|
| 291 |
+
"train_loss": 0.2572957956662742,
|
| 292 |
+
"train_runtime": 515.2049,
|
| 293 |
+
"train_samples_per_second": 92.165,
|
| 294 |
+
"train_steps_per_second": 0.722
|
| 295 |
+
}
|
| 296 |
+
],
|
| 297 |
+
"logging_steps": 10,
|
| 298 |
+
"max_steps": 372,
|
| 299 |
+
"num_train_epochs": 6,
|
| 300 |
+
"save_steps": 500,
|
| 301 |
+
"total_flos": 1.2495360147628032e+16,
|
| 302 |
+
"trial_name": null,
|
| 303 |
+
"trial_params": null
|
| 304 |
+
}
|