Upload trainer_state.json with huggingface_hub
Browse files- trainer_state.json +286 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,286 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.23450880873712818,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 3500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 3.3501258391018316e-05,
|
| 14 |
+
"grad_norm": 0.8195101618766785,
|
| 15 |
+
"learning_rate": 5e-05,
|
| 16 |
+
"loss": 14.0675,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.0033501258391018312,
|
| 21 |
+
"grad_norm": 0.6814610958099365,
|
| 22 |
+
"learning_rate": 4.999864297594039e-05,
|
| 23 |
+
"loss": 9.6991,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.0067002516782036625,
|
| 28 |
+
"grad_norm": 0.6981404423713684,
|
| 29 |
+
"learning_rate": 4.999451708687114e-05,
|
| 30 |
+
"loss": 5.8251,
|
| 31 |
+
"step": 200
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.010050377517305495,
|
| 35 |
+
"grad_norm": 0.71510249376297,
|
| 36 |
+
"learning_rate": 4.998762265134215e-05,
|
| 37 |
+
"loss": 4.8931,
|
| 38 |
+
"step": 300
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.013400503356407325,
|
| 42 |
+
"grad_norm": 0.7365719676017761,
|
| 43 |
+
"learning_rate": 4.9977960433023496e-05,
|
| 44 |
+
"loss": 3.7625,
|
| 45 |
+
"step": 400
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.016750629195509157,
|
| 49 |
+
"grad_norm": 0.7549176812171936,
|
| 50 |
+
"learning_rate": 4.9965531502161924e-05,
|
| 51 |
+
"loss": 2.5786,
|
| 52 |
+
"step": 500
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.02010075503461099,
|
| 56 |
+
"grad_norm": 0.7549782395362854,
|
| 57 |
+
"learning_rate": 4.995033723546226e-05,
|
| 58 |
+
"loss": 2.3343,
|
| 59 |
+
"step": 600
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.023450880873712818,
|
| 63 |
+
"grad_norm": 0.7549582123756409,
|
| 64 |
+
"learning_rate": 4.993237931593496e-05,
|
| 65 |
+
"loss": 2.3209,
|
| 66 |
+
"step": 700
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.02680100671281465,
|
| 70 |
+
"grad_norm": 0.754852831363678,
|
| 71 |
+
"learning_rate": 4.991165973270965e-05,
|
| 72 |
+
"loss": 2.3182,
|
| 73 |
+
"step": 800
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.030151132551916482,
|
| 77 |
+
"grad_norm": 0.7546794414520264,
|
| 78 |
+
"learning_rate": 4.988818078081481e-05,
|
| 79 |
+
"loss": 2.3295,
|
| 80 |
+
"step": 900
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.033501258391018314,
|
| 84 |
+
"grad_norm": 0.7546112537384033,
|
| 85 |
+
"learning_rate": 4.9861945060923584e-05,
|
| 86 |
+
"loss": 2.3221,
|
| 87 |
+
"step": 1000
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.036851384230120146,
|
| 91 |
+
"grad_norm": 0.7547661662101746,
|
| 92 |
+
"learning_rate": 4.983295547906569e-05,
|
| 93 |
+
"loss": 2.3251,
|
| 94 |
+
"step": 1100
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.04020151006922198,
|
| 98 |
+
"grad_norm": 0.7546742558479309,
|
| 99 |
+
"learning_rate": 4.980121524630554e-05,
|
| 100 |
+
"loss": 2.3214,
|
| 101 |
+
"step": 1200
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.0435516359083238,
|
| 105 |
+
"grad_norm": 0.7544980049133301,
|
| 106 |
+
"learning_rate": 4.976672787838654e-05,
|
| 107 |
+
"loss": 2.3259,
|
| 108 |
+
"step": 1300
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.046901761747425635,
|
| 112 |
+
"grad_norm": 0.7544678449630737,
|
| 113 |
+
"learning_rate": 4.9729497195341726e-05,
|
| 114 |
+
"loss": 2.3197,
|
| 115 |
+
"step": 1400
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.05025188758652747,
|
| 119 |
+
"grad_norm": 0.7546402215957642,
|
| 120 |
+
"learning_rate": 4.968952732107054e-05,
|
| 121 |
+
"loss": 2.3209,
|
| 122 |
+
"step": 1500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.0536020134256293,
|
| 126 |
+
"grad_norm": 0.754619300365448,
|
| 127 |
+
"learning_rate": 4.964682268288213e-05,
|
| 128 |
+
"loss": 2.3188,
|
| 129 |
+
"step": 1600
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.05695213926473113,
|
| 133 |
+
"grad_norm": 0.754672110080719,
|
| 134 |
+
"learning_rate": 4.9601388011004926e-05,
|
| 135 |
+
"loss": 2.3247,
|
| 136 |
+
"step": 1700
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.12060453020766593,
|
| 140 |
+
"grad_norm": 2.730647087097168,
|
| 141 |
+
"learning_rate": 4.822888174568335e-05,
|
| 142 |
+
"loss": 28.8747,
|
| 143 |
+
"step": 1800
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.12730478188586958,
|
| 147 |
+
"grad_norm": 2.763967275619507,
|
| 148 |
+
"learning_rate": 4.802920851560973e-05,
|
| 149 |
+
"loss": 17.4519,
|
| 150 |
+
"step": 1900
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.13400503356407326,
|
| 154 |
+
"grad_norm": 2.815877676010132,
|
| 155 |
+
"learning_rate": 4.7819332140911445e-05,
|
| 156 |
+
"loss": 15.0003,
|
| 157 |
+
"step": 2000
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.1407052852422769,
|
| 161 |
+
"grad_norm": 2.8834288120269775,
|
| 162 |
+
"learning_rate": 4.7599345607806536e-05,
|
| 163 |
+
"loss": 11.9449,
|
| 164 |
+
"step": 2100
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.14740553692048058,
|
| 168 |
+
"grad_norm": 2.9614415168762207,
|
| 169 |
+
"learning_rate": 4.7369346381842344e-05,
|
| 170 |
+
"loss": 8.1434,
|
| 171 |
+
"step": 2200
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.15410578859868423,
|
| 175 |
+
"grad_norm": 3.032062292098999,
|
| 176 |
+
"learning_rate": 4.7129436364713164e-05,
|
| 177 |
+
"loss": 3.7118,
|
| 178 |
+
"step": 2300
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.1608060402768879,
|
| 182 |
+
"grad_norm": 3.026526689529419,
|
| 183 |
+
"learning_rate": 4.687972184911246e-05,
|
| 184 |
+
"loss": 2.0568,
|
| 185 |
+
"step": 2400
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.16750629195509156,
|
| 189 |
+
"grad_norm": 3.0271811485290527,
|
| 190 |
+
"learning_rate": 4.6620313471639675e-05,
|
| 191 |
+
"loss": 1.9842,
|
| 192 |
+
"step": 2500
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.1742065436332952,
|
| 196 |
+
"grad_norm": 3.027158737182617,
|
| 197 |
+
"learning_rate": 4.635132616378236e-05,
|
| 198 |
+
"loss": 1.9426,
|
| 199 |
+
"step": 2600
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.1809067953114989,
|
| 203 |
+
"grad_norm": 3.0273852348327637,
|
| 204 |
+
"learning_rate": 4.607287910099557e-05,
|
| 205 |
+
"loss": 1.9186,
|
| 206 |
+
"step": 2700
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.18760704698970254,
|
| 210 |
+
"grad_norm": 3.0235822200775146,
|
| 211 |
+
"learning_rate": 4.578509564990087e-05,
|
| 212 |
+
"loss": 1.8787,
|
| 213 |
+
"step": 2800
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.19430729866790622,
|
| 217 |
+
"grad_norm": 3.0256638526916504,
|
| 218 |
+
"learning_rate": 4.5488103313628474e-05,
|
| 219 |
+
"loss": 1.8544,
|
| 220 |
+
"step": 2900
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.20100755034610987,
|
| 224 |
+
"grad_norm": 3.028939962387085,
|
| 225 |
+
"learning_rate": 4.5182033675326696e-05,
|
| 226 |
+
"loss": 1.8332,
|
| 227 |
+
"step": 3000
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.20770780202431355,
|
| 231 |
+
"grad_norm": 3.027080535888672,
|
| 232 |
+
"learning_rate": 4.4867022339863685e-05,
|
| 233 |
+
"loss": 1.81,
|
| 234 |
+
"step": 3100
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.2144080537025172,
|
| 238 |
+
"grad_norm": 3.0254549980163574,
|
| 239 |
+
"learning_rate": 4.454320887374743e-05,
|
| 240 |
+
"loss": 1.7835,
|
| 241 |
+
"step": 3200
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.22110830538072088,
|
| 245 |
+
"grad_norm": 3.025289535522461,
|
| 246 |
+
"learning_rate": 4.4210736743290485e-05,
|
| 247 |
+
"loss": 1.7494,
|
| 248 |
+
"step": 3300
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.22780855705892453,
|
| 252 |
+
"grad_norm": 3.02748441696167,
|
| 253 |
+
"learning_rate": 4.3869753251046806e-05,
|
| 254 |
+
"loss": 1.7233,
|
| 255 |
+
"step": 3400
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.23450880873712818,
|
| 259 |
+
"grad_norm": 3.0303146839141846,
|
| 260 |
+
"learning_rate": 4.352040947054912e-05,
|
| 261 |
+
"loss": 1.6755,
|
| 262 |
+
"step": 3500
|
| 263 |
+
}
|
| 264 |
+
],
|
| 265 |
+
"logging_steps": 100,
|
| 266 |
+
"max_steps": 14925,
|
| 267 |
+
"num_input_tokens_seen": 0,
|
| 268 |
+
"num_train_epochs": 1,
|
| 269 |
+
"save_steps": 100,
|
| 270 |
+
"stateful_callbacks": {
|
| 271 |
+
"TrainerControl": {
|
| 272 |
+
"args": {
|
| 273 |
+
"should_epoch_stop": false,
|
| 274 |
+
"should_evaluate": false,
|
| 275 |
+
"should_log": false,
|
| 276 |
+
"should_save": true,
|
| 277 |
+
"should_training_stop": false
|
| 278 |
+
},
|
| 279 |
+
"attributes": {}
|
| 280 |
+
}
|
| 281 |
+
},
|
| 282 |
+
"total_flos": 1.4305806868430477e+19,
|
| 283 |
+
"train_batch_size": 8,
|
| 284 |
+
"trial_name": null,
|
| 285 |
+
"trial_params": null
|
| 286 |
+
}
|