Upload trainer_state.json with huggingface_hub
Browse files- trainer_state.json +423 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,423 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9826119126896042,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 504,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.059193488716241215,
|
| 13 |
+
"grad_norm": 0.19465851783752441,
|
| 14 |
+
"learning_rate": 2e-05,
|
| 15 |
+
"loss": 1.1117,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.11838697743248243,
|
| 20 |
+
"grad_norm": 0.21135994791984558,
|
| 21 |
+
"learning_rate": 4e-05,
|
| 22 |
+
"loss": 1.1022,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.17758046614872364,
|
| 27 |
+
"grad_norm": 0.2708509862422943,
|
| 28 |
+
"learning_rate": 6e-05,
|
| 29 |
+
"loss": 1.0546,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.23677395486496486,
|
| 34 |
+
"grad_norm": 0.21392174065113068,
|
| 35 |
+
"learning_rate": 8e-05,
|
| 36 |
+
"loss": 0.94,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.2959674435812061,
|
| 41 |
+
"grad_norm": 0.17460189759731293,
|
| 42 |
+
"learning_rate": 0.0001,
|
| 43 |
+
"loss": 0.8246,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.3551609322974473,
|
| 48 |
+
"grad_norm": 0.16554006934165955,
|
| 49 |
+
"learning_rate": 0.00012,
|
| 50 |
+
"loss": 0.7437,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.41435442101368847,
|
| 55 |
+
"grad_norm": 0.16454806923866272,
|
| 56 |
+
"learning_rate": 0.00014,
|
| 57 |
+
"loss": 0.6901,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.4735479097299297,
|
| 62 |
+
"grad_norm": 0.1758105754852295,
|
| 63 |
+
"learning_rate": 0.00016,
|
| 64 |
+
"loss": 0.6429,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.532741398446171,
|
| 69 |
+
"grad_norm": 0.1696159690618515,
|
| 70 |
+
"learning_rate": 0.00018,
|
| 71 |
+
"loss": 0.6319,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.5919348871624122,
|
| 76 |
+
"grad_norm": 0.17172178626060486,
|
| 77 |
+
"learning_rate": 0.0002,
|
| 78 |
+
"loss": 0.5995,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.5919348871624122,
|
| 83 |
+
"eval_loss": 0.5879706740379333,
|
| 84 |
+
"eval_runtime": 186.3324,
|
| 85 |
+
"eval_samples_per_second": 3.687,
|
| 86 |
+
"eval_steps_per_second": 0.462,
|
| 87 |
+
"step": 100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.6511283758786534,
|
| 91 |
+
"grad_norm": 0.16957880556583405,
|
| 92 |
+
"learning_rate": 0.00019504950495049505,
|
| 93 |
+
"loss": 0.5913,
|
| 94 |
+
"step": 110
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.7103218645948945,
|
| 98 |
+
"grad_norm": 0.17516390979290009,
|
| 99 |
+
"learning_rate": 0.0001900990099009901,
|
| 100 |
+
"loss": 0.5803,
|
| 101 |
+
"step": 120
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.7695153533111357,
|
| 105 |
+
"grad_norm": 0.18869660794734955,
|
| 106 |
+
"learning_rate": 0.00018514851485148517,
|
| 107 |
+
"loss": 0.5631,
|
| 108 |
+
"step": 130
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.8287088420273769,
|
| 112 |
+
"grad_norm": 0.18655870854854584,
|
| 113 |
+
"learning_rate": 0.00018019801980198022,
|
| 114 |
+
"loss": 0.5538,
|
| 115 |
+
"step": 140
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.8879023307436182,
|
| 119 |
+
"grad_norm": 0.18268819153308868,
|
| 120 |
+
"learning_rate": 0.00017524752475247526,
|
| 121 |
+
"loss": 0.5475,
|
| 122 |
+
"step": 150
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.9470958194598594,
|
| 126 |
+
"grad_norm": 0.1926167607307434,
|
| 127 |
+
"learning_rate": 0.0001702970297029703,
|
| 128 |
+
"loss": 0.5462,
|
| 129 |
+
"step": 160
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.005919348871624,
|
| 133 |
+
"grad_norm": 0.19758427143096924,
|
| 134 |
+
"learning_rate": 0.00016534653465346535,
|
| 135 |
+
"loss": 0.5375,
|
| 136 |
+
"step": 170
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 1.0651128375878653,
|
| 140 |
+
"grad_norm": 0.19379234313964844,
|
| 141 |
+
"learning_rate": 0.00016039603960396042,
|
| 142 |
+
"loss": 0.5234,
|
| 143 |
+
"step": 180
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.1243063263041067,
|
| 147 |
+
"grad_norm": 0.19841700792312622,
|
| 148 |
+
"learning_rate": 0.00015544554455445547,
|
| 149 |
+
"loss": 0.5336,
|
| 150 |
+
"step": 190
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1.1834998150203477,
|
| 154 |
+
"grad_norm": 0.19659265875816345,
|
| 155 |
+
"learning_rate": 0.00015049504950495051,
|
| 156 |
+
"loss": 0.5265,
|
| 157 |
+
"step": 200
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 1.1834998150203477,
|
| 161 |
+
"eval_loss": 0.5296523571014404,
|
| 162 |
+
"eval_runtime": 186.0309,
|
| 163 |
+
"eval_samples_per_second": 3.693,
|
| 164 |
+
"eval_steps_per_second": 0.462,
|
| 165 |
+
"step": 200
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.242693303736589,
|
| 169 |
+
"grad_norm": 0.2189786285161972,
|
| 170 |
+
"learning_rate": 0.00014554455445544556,
|
| 171 |
+
"loss": 0.5228,
|
| 172 |
+
"step": 210
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.3018867924528301,
|
| 176 |
+
"grad_norm": 0.2317192554473877,
|
| 177 |
+
"learning_rate": 0.0001405940594059406,
|
| 178 |
+
"loss": 0.5219,
|
| 179 |
+
"step": 220
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.3610802811690714,
|
| 183 |
+
"grad_norm": 0.20830461382865906,
|
| 184 |
+
"learning_rate": 0.00013564356435643565,
|
| 185 |
+
"loss": 0.5095,
|
| 186 |
+
"step": 230
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.4202737698853127,
|
| 190 |
+
"grad_norm": 0.2214994877576828,
|
| 191 |
+
"learning_rate": 0.0001306930693069307,
|
| 192 |
+
"loss": 0.5192,
|
| 193 |
+
"step": 240
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.4794672586015538,
|
| 197 |
+
"grad_norm": 0.21869614720344543,
|
| 198 |
+
"learning_rate": 0.00012574257425742574,
|
| 199 |
+
"loss": 0.5031,
|
| 200 |
+
"step": 250
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.538660747317795,
|
| 204 |
+
"grad_norm": 0.21614821255207062,
|
| 205 |
+
"learning_rate": 0.0001207920792079208,
|
| 206 |
+
"loss": 0.5177,
|
| 207 |
+
"step": 260
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.5978542360340362,
|
| 211 |
+
"grad_norm": 0.2306758016347885,
|
| 212 |
+
"learning_rate": 0.00011584158415841584,
|
| 213 |
+
"loss": 0.5124,
|
| 214 |
+
"step": 270
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.6570477247502775,
|
| 218 |
+
"grad_norm": 0.22710908949375153,
|
| 219 |
+
"learning_rate": 0.0001108910891089109,
|
| 220 |
+
"loss": 0.5025,
|
| 221 |
+
"step": 280
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.7162412134665188,
|
| 225 |
+
"grad_norm": 0.22501707077026367,
|
| 226 |
+
"learning_rate": 0.00010594059405940595,
|
| 227 |
+
"loss": 0.5048,
|
| 228 |
+
"step": 290
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 1.77543470218276,
|
| 232 |
+
"grad_norm": 0.22507990896701813,
|
| 233 |
+
"learning_rate": 0.00010099009900990099,
|
| 234 |
+
"loss": 0.5009,
|
| 235 |
+
"step": 300
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 1.77543470218276,
|
| 239 |
+
"eval_loss": 0.508837103843689,
|
| 240 |
+
"eval_runtime": 185.3987,
|
| 241 |
+
"eval_samples_per_second": 3.706,
|
| 242 |
+
"eval_steps_per_second": 0.464,
|
| 243 |
+
"step": 300
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 1.834628190899001,
|
| 247 |
+
"grad_norm": 0.22626681625843048,
|
| 248 |
+
"learning_rate": 9.603960396039604e-05,
|
| 249 |
+
"loss": 0.5045,
|
| 250 |
+
"step": 310
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 1.8938216796152423,
|
| 254 |
+
"grad_norm": 0.21802489459514618,
|
| 255 |
+
"learning_rate": 9.10891089108911e-05,
|
| 256 |
+
"loss": 0.5087,
|
| 257 |
+
"step": 320
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.9530151683314836,
|
| 261 |
+
"grad_norm": 0.2331380993127823,
|
| 262 |
+
"learning_rate": 8.613861386138614e-05,
|
| 263 |
+
"loss": 0.5038,
|
| 264 |
+
"step": 330
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 2.011838697743248,
|
| 268 |
+
"grad_norm": 0.21599650382995605,
|
| 269 |
+
"learning_rate": 8.11881188118812e-05,
|
| 270 |
+
"loss": 0.4912,
|
| 271 |
+
"step": 340
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 2.0710321864594894,
|
| 275 |
+
"grad_norm": 0.24118073284626007,
|
| 276 |
+
"learning_rate": 7.623762376237625e-05,
|
| 277 |
+
"loss": 0.4842,
|
| 278 |
+
"step": 350
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 2.1302256751757307,
|
| 282 |
+
"grad_norm": 0.232917919754982,
|
| 283 |
+
"learning_rate": 7.128712871287129e-05,
|
| 284 |
+
"loss": 0.4835,
|
| 285 |
+
"step": 360
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 2.189419163891972,
|
| 289 |
+
"grad_norm": 0.23639123141765594,
|
| 290 |
+
"learning_rate": 6.633663366336635e-05,
|
| 291 |
+
"loss": 0.4786,
|
| 292 |
+
"step": 370
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 2.2486126526082133,
|
| 296 |
+
"grad_norm": 0.2632993161678314,
|
| 297 |
+
"learning_rate": 6.13861386138614e-05,
|
| 298 |
+
"loss": 0.4824,
|
| 299 |
+
"step": 380
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 2.307806141324454,
|
| 303 |
+
"grad_norm": 0.2573336064815521,
|
| 304 |
+
"learning_rate": 5.643564356435643e-05,
|
| 305 |
+
"loss": 0.4771,
|
| 306 |
+
"step": 390
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 2.3669996300406955,
|
| 310 |
+
"grad_norm": 0.24001090228557587,
|
| 311 |
+
"learning_rate": 5.148514851485149e-05,
|
| 312 |
+
"loss": 0.4848,
|
| 313 |
+
"step": 400
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 2.3669996300406955,
|
| 317 |
+
"eval_loss": 0.4998326301574707,
|
| 318 |
+
"eval_runtime": 186.3844,
|
| 319 |
+
"eval_samples_per_second": 3.686,
|
| 320 |
+
"eval_steps_per_second": 0.461,
|
| 321 |
+
"step": 400
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 2.4261931187569368,
|
| 325 |
+
"grad_norm": 0.2617679834365845,
|
| 326 |
+
"learning_rate": 4.653465346534654e-05,
|
| 327 |
+
"loss": 0.4854,
|
| 328 |
+
"step": 410
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 2.485386607473178,
|
| 332 |
+
"grad_norm": 0.2378547489643097,
|
| 333 |
+
"learning_rate": 4.158415841584158e-05,
|
| 334 |
+
"loss": 0.4848,
|
| 335 |
+
"step": 420
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 2.544580096189419,
|
| 339 |
+
"grad_norm": 0.2498575747013092,
|
| 340 |
+
"learning_rate": 3.6633663366336634e-05,
|
| 341 |
+
"loss": 0.4768,
|
| 342 |
+
"step": 430
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 2.6037735849056602,
|
| 346 |
+
"grad_norm": 0.2568998336791992,
|
| 347 |
+
"learning_rate": 3.1683168316831686e-05,
|
| 348 |
+
"loss": 0.4863,
|
| 349 |
+
"step": 440
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 2.6629670736219015,
|
| 353 |
+
"grad_norm": 0.25008225440979004,
|
| 354 |
+
"learning_rate": 2.6732673267326734e-05,
|
| 355 |
+
"loss": 0.4747,
|
| 356 |
+
"step": 450
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 2.722160562338143,
|
| 360 |
+
"grad_norm": 0.24171195924282074,
|
| 361 |
+
"learning_rate": 2.1782178217821783e-05,
|
| 362 |
+
"loss": 0.4736,
|
| 363 |
+
"step": 460
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 2.781354051054384,
|
| 367 |
+
"grad_norm": 0.2468671202659607,
|
| 368 |
+
"learning_rate": 1.6831683168316834e-05,
|
| 369 |
+
"loss": 0.4894,
|
| 370 |
+
"step": 470
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 2.8405475397706255,
|
| 374 |
+
"grad_norm": 0.2496197372674942,
|
| 375 |
+
"learning_rate": 1.1881188118811881e-05,
|
| 376 |
+
"loss": 0.4798,
|
| 377 |
+
"step": 480
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 2.8997410284868663,
|
| 381 |
+
"grad_norm": 0.24788333475589752,
|
| 382 |
+
"learning_rate": 6.9306930693069314e-06,
|
| 383 |
+
"loss": 0.4739,
|
| 384 |
+
"step": 490
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 2.9589345172031076,
|
| 388 |
+
"grad_norm": 0.2498323768377304,
|
| 389 |
+
"learning_rate": 1.9801980198019803e-06,
|
| 390 |
+
"loss": 0.4718,
|
| 391 |
+
"step": 500
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 2.9589345172031076,
|
| 395 |
+
"eval_loss": 0.49539193511009216,
|
| 396 |
+
"eval_runtime": 185.1827,
|
| 397 |
+
"eval_samples_per_second": 3.71,
|
| 398 |
+
"eval_steps_per_second": 0.464,
|
| 399 |
+
"step": 500
|
| 400 |
+
}
|
| 401 |
+
],
|
| 402 |
+
"logging_steps": 10,
|
| 403 |
+
"max_steps": 504,
|
| 404 |
+
"num_input_tokens_seen": 0,
|
| 405 |
+
"num_train_epochs": 3,
|
| 406 |
+
"save_steps": 500,
|
| 407 |
+
"stateful_callbacks": {
|
| 408 |
+
"TrainerControl": {
|
| 409 |
+
"args": {
|
| 410 |
+
"should_epoch_stop": false,
|
| 411 |
+
"should_evaluate": false,
|
| 412 |
+
"should_log": false,
|
| 413 |
+
"should_save": true,
|
| 414 |
+
"should_training_stop": true
|
| 415 |
+
},
|
| 416 |
+
"attributes": {}
|
| 417 |
+
}
|
| 418 |
+
},
|
| 419 |
+
"total_flos": 9.23509345222656e+16,
|
| 420 |
+
"train_batch_size": 1,
|
| 421 |
+
"trial_name": null,
|
| 422 |
+
"trial_params": null
|
| 423 |
+
}
|