Upload trainer_state.json with huggingface_hub
Browse files- trainer_state.json +393 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,393 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.9961448907852173,
|
| 3 |
+
"best_model_checkpoint": "models/dehanalkautsar/mbert-5-with-parallel-tokenizer-30k/checkpoint-48000",
|
| 4 |
+
"epoch": 19.99623562926035,
|
| 5 |
+
"eval_steps": 2000,
|
| 6 |
+
"global_step": 49140,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.8139179977617255,
|
| 13 |
+
"grad_norm": 12.944409370422363,
|
| 14 |
+
"learning_rate": 9.185999185999187e-05,
|
| 15 |
+
"loss": 6.4974,
|
| 16 |
+
"step": 2000
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.8139179977617255,
|
| 20 |
+
"eval_loss": 5.766712665557861,
|
| 21 |
+
"eval_runtime": 74.2223,
|
| 22 |
+
"eval_samples_per_second": 134.73,
|
| 23 |
+
"eval_steps_per_second": 2.115,
|
| 24 |
+
"step": 2000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 1.6275307762742903,
|
| 28 |
+
"grad_norm": 11.577170372009277,
|
| 29 |
+
"learning_rate": 8.371998371998372e-05,
|
| 30 |
+
"loss": 5.2766,
|
| 31 |
+
"step": 4000
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 1.6275307762742903,
|
| 35 |
+
"eval_loss": 4.884174823760986,
|
| 36 |
+
"eval_runtime": 74.2859,
|
| 37 |
+
"eval_samples_per_second": 134.615,
|
| 38 |
+
"eval_steps_per_second": 2.113,
|
| 39 |
+
"step": 4000
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 2.4411435547868554,
|
| 43 |
+
"grad_norm": 18.84739875793457,
|
| 44 |
+
"learning_rate": 7.557997557997558e-05,
|
| 45 |
+
"loss": 4.4979,
|
| 46 |
+
"step": 6000
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 2.4411435547868554,
|
| 50 |
+
"eval_loss": 3.7487125396728516,
|
| 51 |
+
"eval_runtime": 74.2668,
|
| 52 |
+
"eval_samples_per_second": 134.65,
|
| 53 |
+
"eval_steps_per_second": 2.114,
|
| 54 |
+
"step": 6000
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 3.25475633329942,
|
| 58 |
+
"grad_norm": 16.400541305541992,
|
| 59 |
+
"learning_rate": 6.743996743996744e-05,
|
| 60 |
+
"loss": 3.3089,
|
| 61 |
+
"step": 8000
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 3.25475633329942,
|
| 65 |
+
"eval_loss": 2.872248649597168,
|
| 66 |
+
"eval_runtime": 74.2418,
|
| 67 |
+
"eval_samples_per_second": 134.695,
|
| 68 |
+
"eval_steps_per_second": 2.115,
|
| 69 |
+
"step": 8000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 4.068369111811985,
|
| 73 |
+
"grad_norm": 15.022873878479004,
|
| 74 |
+
"learning_rate": 5.929995929995931e-05,
|
| 75 |
+
"loss": 2.8436,
|
| 76 |
+
"step": 10000
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 4.068369111811985,
|
| 80 |
+
"eval_loss": 2.6301286220550537,
|
| 81 |
+
"eval_runtime": 74.2596,
|
| 82 |
+
"eval_samples_per_second": 134.663,
|
| 83 |
+
"eval_steps_per_second": 2.114,
|
| 84 |
+
"step": 10000
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 4.882287109573711,
|
| 88 |
+
"grad_norm": 14.731890678405762,
|
| 89 |
+
"learning_rate": 5.115995115995116e-05,
|
| 90 |
+
"loss": 2.6498,
|
| 91 |
+
"step": 12000
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 4.882287109573711,
|
| 95 |
+
"eval_loss": 2.4912309646606445,
|
| 96 |
+
"eval_runtime": 74.2946,
|
| 97 |
+
"eval_samples_per_second": 134.599,
|
| 98 |
+
"eval_steps_per_second": 2.113,
|
| 99 |
+
"step": 12000
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 5.6958998880862755,
|
| 103 |
+
"grad_norm": 15.547078132629395,
|
| 104 |
+
"learning_rate": 4.301994301994302e-05,
|
| 105 |
+
"loss": 2.5281,
|
| 106 |
+
"step": 14000
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 5.6958998880862755,
|
| 110 |
+
"eval_loss": 2.4065146446228027,
|
| 111 |
+
"eval_runtime": 74.3674,
|
| 112 |
+
"eval_samples_per_second": 134.468,
|
| 113 |
+
"eval_steps_per_second": 2.111,
|
| 114 |
+
"step": 14000
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 6.50951266659884,
|
| 118 |
+
"grad_norm": 14.562560081481934,
|
| 119 |
+
"learning_rate": 3.487993487993488e-05,
|
| 120 |
+
"loss": 2.4394,
|
| 121 |
+
"step": 16000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 6.50951266659884,
|
| 125 |
+
"eval_loss": 2.3277714252471924,
|
| 126 |
+
"eval_runtime": 74.2604,
|
| 127 |
+
"eval_samples_per_second": 134.661,
|
| 128 |
+
"eval_steps_per_second": 2.114,
|
| 129 |
+
"step": 16000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 7.323125445111405,
|
| 133 |
+
"grad_norm": 14.990942001342773,
|
| 134 |
+
"learning_rate": 2.673992673992674e-05,
|
| 135 |
+
"loss": 2.3797,
|
| 136 |
+
"step": 18000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 7.323125445111405,
|
| 140 |
+
"eval_loss": 2.277052640914917,
|
| 141 |
+
"eval_runtime": 74.2753,
|
| 142 |
+
"eval_samples_per_second": 134.634,
|
| 143 |
+
"eval_steps_per_second": 2.114,
|
| 144 |
+
"step": 18000
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 8.13673822362397,
|
| 148 |
+
"grad_norm": 14.372356414794922,
|
| 149 |
+
"learning_rate": 1.85999185999186e-05,
|
| 150 |
+
"loss": 2.3303,
|
| 151 |
+
"step": 20000
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 8.13673822362397,
|
| 155 |
+
"eval_loss": 2.2430338859558105,
|
| 156 |
+
"eval_runtime": 74.2644,
|
| 157 |
+
"eval_samples_per_second": 134.654,
|
| 158 |
+
"eval_steps_per_second": 2.114,
|
| 159 |
+
"step": 20000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 8.950656221385696,
|
| 163 |
+
"grad_norm": 15.09987735748291,
|
| 164 |
+
"learning_rate": 1.045991045991046e-05,
|
| 165 |
+
"loss": 2.2974,
|
| 166 |
+
"step": 22000
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 8.950656221385696,
|
| 170 |
+
"eval_loss": 2.2221477031707764,
|
| 171 |
+
"eval_runtime": 74.2795,
|
| 172 |
+
"eval_samples_per_second": 134.627,
|
| 173 |
+
"eval_steps_per_second": 2.114,
|
| 174 |
+
"step": 22000
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 9.76426899989826,
|
| 178 |
+
"grad_norm": 14.753724098205566,
|
| 179 |
+
"learning_rate": 2.31990231990232e-06,
|
| 180 |
+
"loss": 2.272,
|
| 181 |
+
"step": 24000
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 9.76426899989826,
|
| 185 |
+
"eval_loss": 2.2013912200927734,
|
| 186 |
+
"eval_runtime": 74.2825,
|
| 187 |
+
"eval_samples_per_second": 134.621,
|
| 188 |
+
"eval_steps_per_second": 2.114,
|
| 189 |
+
"step": 24000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 10.581951368399634,
|
| 193 |
+
"grad_norm": 14.659090995788574,
|
| 194 |
+
"learning_rate": 4.708994708994709e-05,
|
| 195 |
+
"loss": 2.2996,
|
| 196 |
+
"step": 26000
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 10.581951368399634,
|
| 200 |
+
"eval_loss": 2.2351293563842773,
|
| 201 |
+
"eval_runtime": 74.3521,
|
| 202 |
+
"eval_samples_per_second": 134.495,
|
| 203 |
+
"eval_steps_per_second": 2.112,
|
| 204 |
+
"step": 26000
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 11.395564146912198,
|
| 208 |
+
"grad_norm": 14.084636688232422,
|
| 209 |
+
"learning_rate": 4.301994301994302e-05,
|
| 210 |
+
"loss": 2.2664,
|
| 211 |
+
"step": 28000
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 11.395564146912198,
|
| 215 |
+
"eval_loss": 2.174744129180908,
|
| 216 |
+
"eval_runtime": 74.3256,
|
| 217 |
+
"eval_samples_per_second": 134.543,
|
| 218 |
+
"eval_steps_per_second": 2.112,
|
| 219 |
+
"step": 28000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 12.209176925424764,
|
| 223 |
+
"grad_norm": 13.796431541442871,
|
| 224 |
+
"learning_rate": 3.8949938949938955e-05,
|
| 225 |
+
"loss": 2.2317,
|
| 226 |
+
"step": 30000
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 12.209176925424764,
|
| 230 |
+
"eval_loss": 2.150289535522461,
|
| 231 |
+
"eval_runtime": 74.3662,
|
| 232 |
+
"eval_samples_per_second": 134.47,
|
| 233 |
+
"eval_steps_per_second": 2.111,
|
| 234 |
+
"step": 30000
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 13.022789703937327,
|
| 238 |
+
"grad_norm": 14.407515525817871,
|
| 239 |
+
"learning_rate": 3.487993487993488e-05,
|
| 240 |
+
"loss": 2.1954,
|
| 241 |
+
"step": 32000
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 13.022789703937327,
|
| 245 |
+
"eval_loss": 2.1134209632873535,
|
| 246 |
+
"eval_runtime": 74.3327,
|
| 247 |
+
"eval_samples_per_second": 134.53,
|
| 248 |
+
"eval_steps_per_second": 2.112,
|
| 249 |
+
"step": 32000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 13.836707701699053,
|
| 253 |
+
"grad_norm": 15.40833854675293,
|
| 254 |
+
"learning_rate": 3.080993080993081e-05,
|
| 255 |
+
"loss": 2.1617,
|
| 256 |
+
"step": 34000
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 13.836707701699053,
|
| 260 |
+
"eval_loss": 2.069462299346924,
|
| 261 |
+
"eval_runtime": 74.3637,
|
| 262 |
+
"eval_samples_per_second": 134.474,
|
| 263 |
+
"eval_steps_per_second": 2.111,
|
| 264 |
+
"step": 34000
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 14.650320480211619,
|
| 268 |
+
"grad_norm": 15.9359130859375,
|
| 269 |
+
"learning_rate": 2.673992673992674e-05,
|
| 270 |
+
"loss": 2.1372,
|
| 271 |
+
"step": 36000
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 14.650320480211619,
|
| 275 |
+
"eval_loss": 2.0720558166503906,
|
| 276 |
+
"eval_runtime": 74.3125,
|
| 277 |
+
"eval_samples_per_second": 134.567,
|
| 278 |
+
"eval_steps_per_second": 2.113,
|
| 279 |
+
"step": 36000
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 15.463933258724184,
|
| 283 |
+
"grad_norm": 14.391825675964355,
|
| 284 |
+
"learning_rate": 2.2669922669922673e-05,
|
| 285 |
+
"loss": 2.1101,
|
| 286 |
+
"step": 38000
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 15.463933258724184,
|
| 290 |
+
"eval_loss": 2.0433037281036377,
|
| 291 |
+
"eval_runtime": 74.3291,
|
| 292 |
+
"eval_samples_per_second": 134.537,
|
| 293 |
+
"eval_steps_per_second": 2.112,
|
| 294 |
+
"step": 38000
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 16.27754603723675,
|
| 298 |
+
"grad_norm": 14.036117553710938,
|
| 299 |
+
"learning_rate": 1.85999185999186e-05,
|
| 300 |
+
"loss": 2.0897,
|
| 301 |
+
"step": 40000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 16.27754603723675,
|
| 305 |
+
"eval_loss": 2.0293655395507812,
|
| 306 |
+
"eval_runtime": 74.3236,
|
| 307 |
+
"eval_samples_per_second": 134.547,
|
| 308 |
+
"eval_steps_per_second": 2.112,
|
| 309 |
+
"step": 40000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 17.091158815749314,
|
| 313 |
+
"grad_norm": 14.702261924743652,
|
| 314 |
+
"learning_rate": 1.4529914529914531e-05,
|
| 315 |
+
"loss": 2.074,
|
| 316 |
+
"step": 42000
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 17.091158815749314,
|
| 320 |
+
"eval_loss": 2.007510185241699,
|
| 321 |
+
"eval_runtime": 74.3171,
|
| 322 |
+
"eval_samples_per_second": 134.559,
|
| 323 |
+
"eval_steps_per_second": 2.113,
|
| 324 |
+
"step": 42000
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 17.905076813511037,
|
| 328 |
+
"grad_norm": 22.03821563720703,
|
| 329 |
+
"learning_rate": 1.045991045991046e-05,
|
| 330 |
+
"loss": 2.0601,
|
| 331 |
+
"step": 44000
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 17.905076813511037,
|
| 335 |
+
"eval_loss": 1.9990129470825195,
|
| 336 |
+
"eval_runtime": 74.3189,
|
| 337 |
+
"eval_samples_per_second": 134.555,
|
| 338 |
+
"eval_steps_per_second": 2.113,
|
| 339 |
+
"step": 44000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 18.718689592023605,
|
| 343 |
+
"grad_norm": 14.990620613098145,
|
| 344 |
+
"learning_rate": 6.38990638990639e-06,
|
| 345 |
+
"loss": 2.0474,
|
| 346 |
+
"step": 46000
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 18.718689592023605,
|
| 350 |
+
"eval_loss": 2.0009329319000244,
|
| 351 |
+
"eval_runtime": 74.3384,
|
| 352 |
+
"eval_samples_per_second": 134.52,
|
| 353 |
+
"eval_steps_per_second": 2.112,
|
| 354 |
+
"step": 46000
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 19.53230237053617,
|
| 358 |
+
"grad_norm": 14.060431480407715,
|
| 359 |
+
"learning_rate": 2.31990231990232e-06,
|
| 360 |
+
"loss": 2.0354,
|
| 361 |
+
"step": 48000
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 19.53230237053617,
|
| 365 |
+
"eval_loss": 1.9961448907852173,
|
| 366 |
+
"eval_runtime": 74.3131,
|
| 367 |
+
"eval_samples_per_second": 134.566,
|
| 368 |
+
"eval_steps_per_second": 2.113,
|
| 369 |
+
"step": 48000
|
| 370 |
+
}
|
| 371 |
+
],
|
| 372 |
+
"logging_steps": 2000,
|
| 373 |
+
"max_steps": 49140,
|
| 374 |
+
"num_input_tokens_seen": 0,
|
| 375 |
+
"num_train_epochs": 20,
|
| 376 |
+
"save_steps": 2000,
|
| 377 |
+
"stateful_callbacks": {
|
| 378 |
+
"TrainerControl": {
|
| 379 |
+
"args": {
|
| 380 |
+
"should_epoch_stop": false,
|
| 381 |
+
"should_evaluate": false,
|
| 382 |
+
"should_log": false,
|
| 383 |
+
"should_save": true,
|
| 384 |
+
"should_training_stop": true
|
| 385 |
+
},
|
| 386 |
+
"attributes": {}
|
| 387 |
+
}
|
| 388 |
+
},
|
| 389 |
+
"total_flos": 3.3100605673150464e+18,
|
| 390 |
+
"train_batch_size": 32,
|
| 391 |
+
"trial_name": null,
|
| 392 |
+
"trial_params": null
|
| 393 |
+
}
|