Upload trainer_state.json with huggingface_hub
Browse files- trainer_state.json +336 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,336 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.87719298245614,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 420,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.23391812865497075,
|
| 13 |
+
"grad_norm": 0.36140677332878113,
|
| 14 |
+
"learning_rate": 4.77807122597034e-05,
|
| 15 |
+
"loss": 1.7972,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.4678362573099415,
|
| 20 |
+
"grad_norm": 0.33242133259773254,
|
| 21 |
+
"learning_rate": 3.232056928191376e-05,
|
| 22 |
+
"loss": 1.6893,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.7017543859649122,
|
| 27 |
+
"grad_norm": 0.2246789187192917,
|
| 28 |
+
"learning_rate": 1.1892317911069212e-05,
|
| 29 |
+
"loss": 1.6413,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.935672514619883,
|
| 34 |
+
"grad_norm": 0.2739926278591156,
|
| 35 |
+
"learning_rate": 8.066763266625282e-07,
|
| 36 |
+
"loss": 1.6134,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 1.1871345029239766,
|
| 41 |
+
"grad_norm": 0.37965312600135803,
|
| 42 |
+
"learning_rate": 3.848943205739711e-05,
|
| 43 |
+
"loss": 1.4769,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.4210526315789473,
|
| 48 |
+
"grad_norm": 0.3006901741027832,
|
| 49 |
+
"learning_rate": 3.219473788427984e-05,
|
| 50 |
+
"loss": 1.4539,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.654970760233918,
|
| 55 |
+
"grad_norm": 0.27228423953056335,
|
| 56 |
+
"learning_rate": 2.604226177226137e-05,
|
| 57 |
+
"loss": 1.5344,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.8888888888888888,
|
| 62 |
+
"grad_norm": 0.26753801107406616,
|
| 63 |
+
"learning_rate": 1.9146971351147655e-05,
|
| 64 |
+
"loss": 1.4816,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 2.1228070175438596,
|
| 69 |
+
"grad_norm": 0.266255259513855,
|
| 70 |
+
"learning_rate": 1.270117540713368e-05,
|
| 71 |
+
"loss": 1.4132,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 2.3567251461988303,
|
| 76 |
+
"grad_norm": 0.3016515076160431,
|
| 77 |
+
"learning_rate": 7.1998911101617575e-06,
|
| 78 |
+
"loss": 1.3255,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 2.590643274853801,
|
| 83 |
+
"grad_norm": 0.27352389693260193,
|
| 84 |
+
"learning_rate": 3.0656000602372558e-06,
|
| 85 |
+
"loss": 1.3132,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 2.824561403508772,
|
| 90 |
+
"grad_norm": 0.27444812655448914,
|
| 91 |
+
"learning_rate": 6.158030087068001e-07,
|
| 92 |
+
"loss": 1.3476,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 3.0935672514619883,
|
| 97 |
+
"grad_norm": 0.3967718183994293,
|
| 98 |
+
"learning_rate": 4.388136440446337e-05,
|
| 99 |
+
"loss": 1.1837,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 3.327485380116959,
|
| 104 |
+
"grad_norm": 0.4026094377040863,
|
| 105 |
+
"learning_rate": 4.245592045215182e-05,
|
| 106 |
+
"loss": 1.3114,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 3.56140350877193,
|
| 111 |
+
"grad_norm": 0.3775029182434082,
|
| 112 |
+
"learning_rate": 4.0909970437009096e-05,
|
| 113 |
+
"loss": 1.2437,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 3.7953216374269005,
|
| 118 |
+
"grad_norm": 0.40222153067588806,
|
| 119 |
+
"learning_rate": 3.925418674667405e-05,
|
| 120 |
+
"loss": 1.2936,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 4.029239766081871,
|
| 125 |
+
"grad_norm": 0.4361186921596527,
|
| 126 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 127 |
+
"loss": 1.3328,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 4.2631578947368425,
|
| 132 |
+
"grad_norm": 0.4647097885608673,
|
| 133 |
+
"learning_rate": 3.565952013635635e-05,
|
| 134 |
+
"loss": 1.1235,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 4.497076023391813,
|
| 139 |
+
"grad_norm": 0.417835533618927,
|
| 140 |
+
"learning_rate": 3.374545281527538e-05,
|
| 141 |
+
"loss": 1.0464,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 4.730994152046784,
|
| 146 |
+
"grad_norm": 0.42690905928611755,
|
| 147 |
+
"learning_rate": 3.177101170357513e-05,
|
| 148 |
+
"loss": 1.1242,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 4.964912280701754,
|
| 153 |
+
"grad_norm": 0.4406892955303192,
|
| 154 |
+
"learning_rate": 2.9749827255479755e-05,
|
| 155 |
+
"loss": 1.0463,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 5.1988304093567255,
|
| 160 |
+
"grad_norm": 0.4422934353351593,
|
| 161 |
+
"learning_rate": 2.769585261546897e-05,
|
| 162 |
+
"loss": 0.9407,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 5.432748538011696,
|
| 167 |
+
"grad_norm": 0.46315091848373413,
|
| 168 |
+
"learning_rate": 2.5623267293451826e-05,
|
| 169 |
+
"loss": 0.8377,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 5.666666666666667,
|
| 174 |
+
"grad_norm": 0.5057820081710815,
|
| 175 |
+
"learning_rate": 2.3546379277238107e-05,
|
| 176 |
+
"loss": 0.9125,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 5.900584795321637,
|
| 181 |
+
"grad_norm": 0.5013360381126404,
|
| 182 |
+
"learning_rate": 2.1479526258069087e-05,
|
| 183 |
+
"loss": 0.9502,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 6.1345029239766085,
|
| 188 |
+
"grad_norm": 0.7791084051132202,
|
| 189 |
+
"learning_rate": 1.9436976651092144e-05,
|
| 190 |
+
"loss": 0.8194,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 6.368421052631579,
|
| 195 |
+
"grad_norm": 0.4837506115436554,
|
| 196 |
+
"learning_rate": 1.7432831094079355e-05,
|
| 197 |
+
"loss": 0.7167,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 6.60233918128655,
|
| 202 |
+
"grad_norm": 0.5172699689865112,
|
| 203 |
+
"learning_rate": 1.5480925104388762e-05,
|
| 204 |
+
"loss": 0.7622,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 6.83625730994152,
|
| 209 |
+
"grad_norm": 0.5458669662475586,
|
| 210 |
+
"learning_rate": 1.3594733566170926e-05,
|
| 211 |
+
"loss": 0.767,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 7.0701754385964914,
|
| 216 |
+
"grad_norm": 0.46376243233680725,
|
| 217 |
+
"learning_rate": 1.1787277707188616e-05,
|
| 218 |
+
"loss": 0.7493,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 7.304093567251462,
|
| 223 |
+
"grad_norm": 0.5310298800468445,
|
| 224 |
+
"learning_rate": 1.0071035207430352e-05,
|
| 225 |
+
"loss": 0.6112,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 7.538011695906433,
|
| 230 |
+
"grad_norm": 0.49246639013290405,
|
| 231 |
+
"learning_rate": 8.45785406007852e-06,
|
| 232 |
+
"loss": 0.6109,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 7.771929824561403,
|
| 237 |
+
"grad_norm": 0.5299611687660217,
|
| 238 |
+
"learning_rate": 6.958870779488447e-06,
|
| 239 |
+
"loss": 0.6453,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 8.005847953216374,
|
| 244 |
+
"grad_norm": 0.4647846519947052,
|
| 245 |
+
"learning_rate": 5.584433520825541e-06,
|
| 246 |
+
"loss": 0.6664,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 8.239766081871345,
|
| 251 |
+
"grad_norm": 0.4858466386795044,
|
| 252 |
+
"learning_rate": 4.344030642100133e-06,
|
| 253 |
+
"loss": 0.5755,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 8.473684210526315,
|
| 258 |
+
"grad_norm": 0.4467305839061737,
|
| 259 |
+
"learning_rate": 3.2462252017684797e-06,
|
| 260 |
+
"loss": 0.5977,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 8.707602339181287,
|
| 265 |
+
"grad_norm": 0.47269728779792786,
|
| 266 |
+
"learning_rate": 2.298595844092377e-06,
|
| 267 |
+
"loss": 0.5428,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 8.941520467836257,
|
| 272 |
+
"grad_norm": 0.4306669235229492,
|
| 273 |
+
"learning_rate": 1.5076844803522922e-06,
|
| 274 |
+
"loss": 0.5528,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 9.175438596491228,
|
| 279 |
+
"grad_norm": 0.42190077900886536,
|
| 280 |
+
"learning_rate": 8.78951127094127e-07,
|
| 281 |
+
"loss": 0.5825,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 9.409356725146198,
|
| 286 |
+
"grad_norm": 0.4262978434562683,
|
| 287 |
+
"learning_rate": 4.16736213181515e-07,
|
| 288 |
+
"loss": 0.5498,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 9.64327485380117,
|
| 293 |
+
"grad_norm": 0.4205697774887085,
|
| 294 |
+
"learning_rate": 1.2423061586496477e-07,
|
| 295 |
+
"loss": 0.5318,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 9.87719298245614,
|
| 300 |
+
"grad_norm": 0.4037964940071106,
|
| 301 |
+
"learning_rate": 3.453632722358324e-09,
|
| 302 |
+
"loss": 0.5299,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 9.87719298245614,
|
| 307 |
+
"step": 420,
|
| 308 |
+
"total_flos": 6.211299136336036e+17,
|
| 309 |
+
"train_loss": 0.5820885260899862,
|
| 310 |
+
"train_runtime": 3633.6741,
|
| 311 |
+
"train_samples_per_second": 3.762,
|
| 312 |
+
"train_steps_per_second": 0.116
|
| 313 |
+
}
|
| 314 |
+
],
|
| 315 |
+
"logging_steps": 10,
|
| 316 |
+
"max_steps": 420,
|
| 317 |
+
"num_input_tokens_seen": 0,
|
| 318 |
+
"num_train_epochs": 10,
|
| 319 |
+
"save_steps": 1000,
|
| 320 |
+
"stateful_callbacks": {
|
| 321 |
+
"TrainerControl": {
|
| 322 |
+
"args": {
|
| 323 |
+
"should_epoch_stop": false,
|
| 324 |
+
"should_evaluate": false,
|
| 325 |
+
"should_log": false,
|
| 326 |
+
"should_save": true,
|
| 327 |
+
"should_training_stop": true
|
| 328 |
+
},
|
| 329 |
+
"attributes": {}
|
| 330 |
+
}
|
| 331 |
+
},
|
| 332 |
+
"total_flos": 6.211299136336036e+17,
|
| 333 |
+
"train_batch_size": 8,
|
| 334 |
+
"trial_name": null,
|
| 335 |
+
"trial_params": null
|
| 336 |
+
}
|