Spaces:
Sleeping
Sleeping
EcoFriendlyWoodVerneer commited on
Commit ·
922d400
1
Parent(s): 8ccad0e
Remove training-only checkpoint files
Browse files- custom_t5_enzh/checkpoint-29688/optimizer.pt +0 -3
- custom_t5_enzh/checkpoint-29688/rng_state.pth +0 -3
- custom_t5_enzh/checkpoint-29688/scaler.pt +0 -3
- custom_t5_enzh/checkpoint-29688/scheduler.pt +0 -3
- custom_t5_enzh/checkpoint-29688/trainer_state.json +0 -1331
- custom_t5_enzh/checkpoint-29688/training_args.bin +0 -3
custom_t5_enzh/checkpoint-29688/optimizer.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:e64b45f39877c482632ccdd5afcca5030d58cd36d1527ca55c881a5455383a71
|
| 3 |
-
size 484048826
|
|
|
|
|
|
|
|
|
|
|
|
custom_t5_enzh/checkpoint-29688/rng_state.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:7959e86c1aa1b8eb7d94f513e7c9aed0577ed1a74cd7b9eaafc1fcdfdce76500
|
| 3 |
-
size 14244
|
|
|
|
|
|
|
|
|
|
|
|
custom_t5_enzh/checkpoint-29688/scaler.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:0fedd999e43515c9c2556ec2ff18a27b6972410a2706a52a92e0f127da24a309
|
| 3 |
-
size 988
|
|
|
|
|
|
|
|
|
|
|
|
custom_t5_enzh/checkpoint-29688/scheduler.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:eb53167c045732a134505f0578ddee8eefcd648eb6826870ef1abb00377ad4d1
|
| 3 |
-
size 1064
|
|
|
|
|
|
|
|
|
|
|
|
custom_t5_enzh/checkpoint-29688/trainer_state.json
DELETED
|
@@ -1,1331 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_global_step": null,
|
| 3 |
-
"best_metric": null,
|
| 4 |
-
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 1.0,
|
| 6 |
-
"eval_steps": 1000,
|
| 7 |
-
"global_step": 29688,
|
| 8 |
-
"is_hyper_param_search": false,
|
| 9 |
-
"is_local_process_zero": true,
|
| 10 |
-
"is_world_process_zero": true,
|
| 11 |
-
"log_history": [
|
| 12 |
-
{
|
| 13 |
-
"epoch": 0.006736842105263158,
|
| 14 |
-
"grad_norm": 4.254439830780029,
|
| 15 |
-
"learning_rate": 0.0004966484774993264,
|
| 16 |
-
"loss": 8.8092,
|
| 17 |
-
"step": 200
|
| 18 |
-
},
|
| 19 |
-
{
|
| 20 |
-
"epoch": 0.013473684210526317,
|
| 21 |
-
"grad_norm": 3.3755834102630615,
|
| 22 |
-
"learning_rate": 0.0004932801131770412,
|
| 23 |
-
"loss": 8.1379,
|
| 24 |
-
"step": 400
|
| 25 |
-
},
|
| 26 |
-
{
|
| 27 |
-
"epoch": 0.020210526315789474,
|
| 28 |
-
"grad_norm": 1.1486470699310303,
|
| 29 |
-
"learning_rate": 0.0004899285906763676,
|
| 30 |
-
"loss": 7.8786,
|
| 31 |
-
"step": 600
|
| 32 |
-
},
|
| 33 |
-
{
|
| 34 |
-
"epoch": 0.026947368421052633,
|
| 35 |
-
"grad_norm": 1.2390578985214233,
|
| 36 |
-
"learning_rate": 0.0004865602263540825,
|
| 37 |
-
"loss": 7.7022,
|
| 38 |
-
"step": 800
|
| 39 |
-
},
|
| 40 |
-
{
|
| 41 |
-
"epoch": 0.03368421052631579,
|
| 42 |
-
"grad_norm": 1.7450668811798096,
|
| 43 |
-
"learning_rate": 0.0004832087038534088,
|
| 44 |
-
"loss": 7.6146,
|
| 45 |
-
"step": 1000
|
| 46 |
-
},
|
| 47 |
-
{
|
| 48 |
-
"epoch": 0.03368421052631579,
|
| 49 |
-
"eval_chrf": 0.005726559318726246,
|
| 50 |
-
"eval_loss": 8.076652526855469,
|
| 51 |
-
"eval_runtime": 209.4663,
|
| 52 |
-
"eval_samples_per_second": 9.548,
|
| 53 |
-
"eval_steps_per_second": 0.597,
|
| 54 |
-
"step": 1000
|
| 55 |
-
},
|
| 56 |
-
{
|
| 57 |
-
"epoch": 0.04042105263157895,
|
| 58 |
-
"grad_norm": 2.2363343238830566,
|
| 59 |
-
"learning_rate": 0.0004798403395311237,
|
| 60 |
-
"loss": 7.5643,
|
| 61 |
-
"step": 1200
|
| 62 |
-
},
|
| 63 |
-
{
|
| 64 |
-
"epoch": 0.04715789473684211,
|
| 65 |
-
"grad_norm": 1.5633487701416016,
|
| 66 |
-
"learning_rate": 0.00047648881703045003,
|
| 67 |
-
"loss": 7.527,
|
| 68 |
-
"step": 1400
|
| 69 |
-
},
|
| 70 |
-
{
|
| 71 |
-
"epoch": 0.053894736842105266,
|
| 72 |
-
"grad_norm": 2.2892746925354004,
|
| 73 |
-
"learning_rate": 0.00047312045270816495,
|
| 74 |
-
"loss": 7.4918,
|
| 75 |
-
"step": 1600
|
| 76 |
-
},
|
| 77 |
-
{
|
| 78 |
-
"epoch": 0.06063157894736842,
|
| 79 |
-
"grad_norm": 1.7377341985702515,
|
| 80 |
-
"learning_rate": 0.00046976893020749124,
|
| 81 |
-
"loss": 7.4903,
|
| 82 |
-
"step": 1800
|
| 83 |
-
},
|
| 84 |
-
{
|
| 85 |
-
"epoch": 0.06736842105263158,
|
| 86 |
-
"grad_norm": 1.7025725841522217,
|
| 87 |
-
"learning_rate": 0.0004664005658852061,
|
| 88 |
-
"loss": 7.4449,
|
| 89 |
-
"step": 2000
|
| 90 |
-
},
|
| 91 |
-
{
|
| 92 |
-
"epoch": 0.06736842105263158,
|
| 93 |
-
"eval_chrf": 0.0019243755855956966,
|
| 94 |
-
"eval_loss": 8.043418884277344,
|
| 95 |
-
"eval_runtime": 210.6222,
|
| 96 |
-
"eval_samples_per_second": 9.496,
|
| 97 |
-
"eval_steps_per_second": 0.593,
|
| 98 |
-
"step": 2000
|
| 99 |
-
},
|
| 100 |
-
{
|
| 101 |
-
"epoch": 0.07410526315789474,
|
| 102 |
-
"grad_norm": 2.077467679977417,
|
| 103 |
-
"learning_rate": 0.000463032201562921,
|
| 104 |
-
"loss": 7.4266,
|
| 105 |
-
"step": 2200
|
| 106 |
-
},
|
| 107 |
-
{
|
| 108 |
-
"epoch": 0.0808421052631579,
|
| 109 |
-
"grad_norm": 1.6652511358261108,
|
| 110 |
-
"learning_rate": 0.00045966383724063594,
|
| 111 |
-
"loss": 7.4337,
|
| 112 |
-
"step": 2400
|
| 113 |
-
},
|
| 114 |
-
{
|
| 115 |
-
"epoch": 0.08757894736842105,
|
| 116 |
-
"grad_norm": 1.4601976871490479,
|
| 117 |
-
"learning_rate": 0.00045629547291835086,
|
| 118 |
-
"loss": 7.3881,
|
| 119 |
-
"step": 2600
|
| 120 |
-
},
|
| 121 |
-
{
|
| 122 |
-
"epoch": 0.09431578947368421,
|
| 123 |
-
"grad_norm": 2.035797595977783,
|
| 124 |
-
"learning_rate": 0.00045294395041767715,
|
| 125 |
-
"loss": 7.3976,
|
| 126 |
-
"step": 2800
|
| 127 |
-
},
|
| 128 |
-
{
|
| 129 |
-
"epoch": 0.10105263157894737,
|
| 130 |
-
"grad_norm": 11.324400901794434,
|
| 131 |
-
"learning_rate": 0.00044957558609539207,
|
| 132 |
-
"loss": 7.3977,
|
| 133 |
-
"step": 3000
|
| 134 |
-
},
|
| 135 |
-
{
|
| 136 |
-
"epoch": 0.10105263157894737,
|
| 137 |
-
"eval_chrf": 0.002352741368315669,
|
| 138 |
-
"eval_loss": 8.023853302001953,
|
| 139 |
-
"eval_runtime": 212.3438,
|
| 140 |
-
"eval_samples_per_second": 9.419,
|
| 141 |
-
"eval_steps_per_second": 0.589,
|
| 142 |
-
"step": 3000
|
| 143 |
-
},
|
| 144 |
-
{
|
| 145 |
-
"epoch": 0.10778947368421053,
|
| 146 |
-
"grad_norm": 3.328237533569336,
|
| 147 |
-
"learning_rate": 0.00044620722177310694,
|
| 148 |
-
"loss": 7.3749,
|
| 149 |
-
"step": 3200
|
| 150 |
-
},
|
| 151 |
-
{
|
| 152 |
-
"epoch": 0.11452631578947368,
|
| 153 |
-
"grad_norm": 4.6249189376831055,
|
| 154 |
-
"learning_rate": 0.00044283885745082186,
|
| 155 |
-
"loss": 7.3797,
|
| 156 |
-
"step": 3400
|
| 157 |
-
},
|
| 158 |
-
{
|
| 159 |
-
"epoch": 0.12126315789473684,
|
| 160 |
-
"grad_norm": 7.7165913581848145,
|
| 161 |
-
"learning_rate": 0.00043947049312853683,
|
| 162 |
-
"loss": 7.3639,
|
| 163 |
-
"step": 3600
|
| 164 |
-
},
|
| 165 |
-
{
|
| 166 |
-
"epoch": 0.128,
|
| 167 |
-
"grad_norm": 592.001220703125,
|
| 168 |
-
"learning_rate": 0.0004361189706278631,
|
| 169 |
-
"loss": 7.3774,
|
| 170 |
-
"step": 3800
|
| 171 |
-
},
|
| 172 |
-
{
|
| 173 |
-
"epoch": 0.13473684210526315,
|
| 174 |
-
"grad_norm": 10.053915023803711,
|
| 175 |
-
"learning_rate": 0.000432750606305578,
|
| 176 |
-
"loss": 7.3629,
|
| 177 |
-
"step": 4000
|
| 178 |
-
},
|
| 179 |
-
{
|
| 180 |
-
"epoch": 0.13473684210526315,
|
| 181 |
-
"eval_chrf": 0.0026428740107985933,
|
| 182 |
-
"eval_loss": 7.972915172576904,
|
| 183 |
-
"eval_runtime": 208.7087,
|
| 184 |
-
"eval_samples_per_second": 9.583,
|
| 185 |
-
"eval_steps_per_second": 0.599,
|
| 186 |
-
"step": 4000
|
| 187 |
-
},
|
| 188 |
-
{
|
| 189 |
-
"epoch": 0.1414736842105263,
|
| 190 |
-
"grad_norm": 12.676908493041992,
|
| 191 |
-
"learning_rate": 0.0004293822419832929,
|
| 192 |
-
"loss": 7.3723,
|
| 193 |
-
"step": 4200
|
| 194 |
-
},
|
| 195 |
-
{
|
| 196 |
-
"epoch": 0.1482105263157895,
|
| 197 |
-
"grad_norm": 3.955014228820801,
|
| 198 |
-
"learning_rate": 0.0004260138776610078,
|
| 199 |
-
"loss": 7.3371,
|
| 200 |
-
"step": 4400
|
| 201 |
-
},
|
| 202 |
-
{
|
| 203 |
-
"epoch": 0.15494736842105264,
|
| 204 |
-
"grad_norm": 7.863338470458984,
|
| 205 |
-
"learning_rate": 0.0004226455133387227,
|
| 206 |
-
"loss": 7.3359,
|
| 207 |
-
"step": 4600
|
| 208 |
-
},
|
| 209 |
-
{
|
| 210 |
-
"epoch": 0.1616842105263158,
|
| 211 |
-
"grad_norm": 1.5261688232421875,
|
| 212 |
-
"learning_rate": 0.00041927714901643766,
|
| 213 |
-
"loss": 7.3433,
|
| 214 |
-
"step": 4800
|
| 215 |
-
},
|
| 216 |
-
{
|
| 217 |
-
"epoch": 0.16842105263157894,
|
| 218 |
-
"grad_norm": 8.192843437194824,
|
| 219 |
-
"learning_rate": 0.00041590878469415253,
|
| 220 |
-
"loss": 7.3336,
|
| 221 |
-
"step": 5000
|
| 222 |
-
},
|
| 223 |
-
{
|
| 224 |
-
"epoch": 0.16842105263157894,
|
| 225 |
-
"eval_chrf": 0.002056091763873794,
|
| 226 |
-
"eval_loss": 7.981015682220459,
|
| 227 |
-
"eval_runtime": 210.934,
|
| 228 |
-
"eval_samples_per_second": 9.482,
|
| 229 |
-
"eval_steps_per_second": 0.593,
|
| 230 |
-
"step": 5000
|
| 231 |
-
},
|
| 232 |
-
{
|
| 233 |
-
"epoch": 0.1751578947368421,
|
| 234 |
-
"grad_norm": 7.735596179962158,
|
| 235 |
-
"learning_rate": 0.00041254042037186745,
|
| 236 |
-
"loss": 7.3357,
|
| 237 |
-
"step": 5200
|
| 238 |
-
},
|
| 239 |
-
{
|
| 240 |
-
"epoch": 0.18189473684210528,
|
| 241 |
-
"grad_norm": 3.6393988132476807,
|
| 242 |
-
"learning_rate": 0.00040917205604958237,
|
| 243 |
-
"loss": 7.3266,
|
| 244 |
-
"step": 5400
|
| 245 |
-
},
|
| 246 |
-
{
|
| 247 |
-
"epoch": 0.18863157894736843,
|
| 248 |
-
"grad_norm": 6.396200656890869,
|
| 249 |
-
"learning_rate": 0.00040580369172729723,
|
| 250 |
-
"loss": 7.339,
|
| 251 |
-
"step": 5600
|
| 252 |
-
},
|
| 253 |
-
{
|
| 254 |
-
"epoch": 0.19536842105263158,
|
| 255 |
-
"grad_norm": 2.8999171257019043,
|
| 256 |
-
"learning_rate": 0.00040243532740501215,
|
| 257 |
-
"loss": 7.2893,
|
| 258 |
-
"step": 5800
|
| 259 |
-
},
|
| 260 |
-
{
|
| 261 |
-
"epoch": 0.20210526315789473,
|
| 262 |
-
"grad_norm": 63.303401947021484,
|
| 263 |
-
"learning_rate": 0.0003991174885475613,
|
| 264 |
-
"loss": 7.3111,
|
| 265 |
-
"step": 6000
|
| 266 |
-
},
|
| 267 |
-
{
|
| 268 |
-
"epoch": 0.20210526315789473,
|
| 269 |
-
"eval_chrf": 0.004042745883260306,
|
| 270 |
-
"eval_loss": 7.9859795570373535,
|
| 271 |
-
"eval_runtime": 209.8571,
|
| 272 |
-
"eval_samples_per_second": 9.53,
|
| 273 |
-
"eval_steps_per_second": 0.596,
|
| 274 |
-
"step": 6000
|
| 275 |
-
},
|
| 276 |
-
{
|
| 277 |
-
"epoch": 0.20884210526315788,
|
| 278 |
-
"grad_norm": 5.230437755584717,
|
| 279 |
-
"learning_rate": 0.0003957491242252762,
|
| 280 |
-
"loss": 7.2863,
|
| 281 |
-
"step": 6200
|
| 282 |
-
},
|
| 283 |
-
{
|
| 284 |
-
"epoch": 0.21557894736842106,
|
| 285 |
-
"grad_norm": 29.289928436279297,
|
| 286 |
-
"learning_rate": 0.0003923807599029911,
|
| 287 |
-
"loss": 7.3219,
|
| 288 |
-
"step": 6400
|
| 289 |
-
},
|
| 290 |
-
{
|
| 291 |
-
"epoch": 0.22231578947368422,
|
| 292 |
-
"grad_norm": 161.98826599121094,
|
| 293 |
-
"learning_rate": 0.0003890292374023174,
|
| 294 |
-
"loss": 7.3044,
|
| 295 |
-
"step": 6600
|
| 296 |
-
},
|
| 297 |
-
{
|
| 298 |
-
"epoch": 0.22905263157894737,
|
| 299 |
-
"grad_norm": 137.97628784179688,
|
| 300 |
-
"learning_rate": 0.00038566087308003233,
|
| 301 |
-
"loss": 7.3067,
|
| 302 |
-
"step": 6800
|
| 303 |
-
},
|
| 304 |
-
{
|
| 305 |
-
"epoch": 0.23578947368421052,
|
| 306 |
-
"grad_norm": 11.88398265838623,
|
| 307 |
-
"learning_rate": 0.00038229250875774725,
|
| 308 |
-
"loss": 7.3083,
|
| 309 |
-
"step": 7000
|
| 310 |
-
},
|
| 311 |
-
{
|
| 312 |
-
"epoch": 0.23578947368421052,
|
| 313 |
-
"eval_chrf": 0.0052247493110234265,
|
| 314 |
-
"eval_loss": 7.974218845367432,
|
| 315 |
-
"eval_runtime": 209.3818,
|
| 316 |
-
"eval_samples_per_second": 9.552,
|
| 317 |
-
"eval_steps_per_second": 0.597,
|
| 318 |
-
"step": 7000
|
| 319 |
-
},
|
| 320 |
-
{
|
| 321 |
-
"epoch": 0.24252631578947367,
|
| 322 |
-
"grad_norm": 1372.63525390625,
|
| 323 |
-
"learning_rate": 0.0003789241444354621,
|
| 324 |
-
"loss": 7.287,
|
| 325 |
-
"step": 7200
|
| 326 |
-
},
|
| 327 |
-
{
|
| 328 |
-
"epoch": 0.24926315789473685,
|
| 329 |
-
"grad_norm": 4.1067352294921875,
|
| 330 |
-
"learning_rate": 0.00037555578011317704,
|
| 331 |
-
"loss": 7.3108,
|
| 332 |
-
"step": 7400
|
| 333 |
-
},
|
| 334 |
-
{
|
| 335 |
-
"epoch": 0.256,
|
| 336 |
-
"grad_norm": 16.280475616455078,
|
| 337 |
-
"learning_rate": 0.00037218741579089196,
|
| 338 |
-
"loss": 7.3079,
|
| 339 |
-
"step": 7600
|
| 340 |
-
},
|
| 341 |
-
{
|
| 342 |
-
"epoch": 0.26273684210526316,
|
| 343 |
-
"grad_norm": 5.811795234680176,
|
| 344 |
-
"learning_rate": 0.0003688190514686068,
|
| 345 |
-
"loss": 7.2741,
|
| 346 |
-
"step": 7800
|
| 347 |
-
},
|
| 348 |
-
{
|
| 349 |
-
"epoch": 0.2694736842105263,
|
| 350 |
-
"grad_norm": 12.810831069946289,
|
| 351 |
-
"learning_rate": 0.00036546752896793317,
|
| 352 |
-
"loss": 7.2951,
|
| 353 |
-
"step": 8000
|
| 354 |
-
},
|
| 355 |
-
{
|
| 356 |
-
"epoch": 0.2694736842105263,
|
| 357 |
-
"eval_chrf": 0.0018270964000608395,
|
| 358 |
-
"eval_loss": 7.971038341522217,
|
| 359 |
-
"eval_runtime": 208.8802,
|
| 360 |
-
"eval_samples_per_second": 9.575,
|
| 361 |
-
"eval_steps_per_second": 0.598,
|
| 362 |
-
"step": 8000
|
| 363 |
-
},
|
| 364 |
-
{
|
| 365 |
-
"epoch": 0.27621052631578946,
|
| 366 |
-
"grad_norm": 3.149369716644287,
|
| 367 |
-
"learning_rate": 0.0003620991646456481,
|
| 368 |
-
"loss": 7.276,
|
| 369 |
-
"step": 8200
|
| 370 |
-
},
|
| 371 |
-
{
|
| 372 |
-
"epoch": 0.2829473684210526,
|
| 373 |
-
"grad_norm": 8.988630294799805,
|
| 374 |
-
"learning_rate": 0.00035873080032336295,
|
| 375 |
-
"loss": 7.2858,
|
| 376 |
-
"step": 8400
|
| 377 |
-
},
|
| 378 |
-
{
|
| 379 |
-
"epoch": 0.28968421052631577,
|
| 380 |
-
"grad_norm": 3.606241464614868,
|
| 381 |
-
"learning_rate": 0.00035536243600107787,
|
| 382 |
-
"loss": 7.2752,
|
| 383 |
-
"step": 8600
|
| 384 |
-
},
|
| 385 |
-
{
|
| 386 |
-
"epoch": 0.296421052631579,
|
| 387 |
-
"grad_norm": 17.486343383789062,
|
| 388 |
-
"learning_rate": 0.0003519940716787928,
|
| 389 |
-
"loss": 7.2741,
|
| 390 |
-
"step": 8800
|
| 391 |
-
},
|
| 392 |
-
{
|
| 393 |
-
"epoch": 0.3031578947368421,
|
| 394 |
-
"grad_norm": 14.639832496643066,
|
| 395 |
-
"learning_rate": 0.00034862570735650765,
|
| 396 |
-
"loss": 7.2818,
|
| 397 |
-
"step": 9000
|
| 398 |
-
},
|
| 399 |
-
{
|
| 400 |
-
"epoch": 0.3031578947368421,
|
| 401 |
-
"eval_chrf": 0.0028106490006736635,
|
| 402 |
-
"eval_loss": 7.982977867126465,
|
| 403 |
-
"eval_runtime": 208.2552,
|
| 404 |
-
"eval_samples_per_second": 9.604,
|
| 405 |
-
"eval_steps_per_second": 0.6,
|
| 406 |
-
"step": 9000
|
| 407 |
-
},
|
| 408 |
-
{
|
| 409 |
-
"epoch": 0.3098947368421053,
|
| 410 |
-
"grad_norm": 26.35228157043457,
|
| 411 |
-
"learning_rate": 0.0003452573430342226,
|
| 412 |
-
"loss": 7.2879,
|
| 413 |
-
"step": 9200
|
| 414 |
-
},
|
| 415 |
-
{
|
| 416 |
-
"epoch": 0.31663157894736843,
|
| 417 |
-
"grad_norm": 521.87890625,
|
| 418 |
-
"learning_rate": 0.0003418889787119375,
|
| 419 |
-
"loss": 7.2615,
|
| 420 |
-
"step": 9400
|
| 421 |
-
},
|
| 422 |
-
{
|
| 423 |
-
"epoch": 0.3233684210526316,
|
| 424 |
-
"grad_norm": 11.705015182495117,
|
| 425 |
-
"learning_rate": 0.00033852061438965236,
|
| 426 |
-
"loss": 7.2654,
|
| 427 |
-
"step": 9600
|
| 428 |
-
},
|
| 429 |
-
{
|
| 430 |
-
"epoch": 0.33010526315789473,
|
| 431 |
-
"grad_norm": 165.28273010253906,
|
| 432 |
-
"learning_rate": 0.0003351522500673673,
|
| 433 |
-
"loss": 7.2716,
|
| 434 |
-
"step": 9800
|
| 435 |
-
},
|
| 436 |
-
{
|
| 437 |
-
"epoch": 0.3368421052631579,
|
| 438 |
-
"grad_norm": 3.113431215286255,
|
| 439 |
-
"learning_rate": 0.0003317838857450822,
|
| 440 |
-
"loss": 7.3123,
|
| 441 |
-
"step": 10000
|
| 442 |
-
},
|
| 443 |
-
{
|
| 444 |
-
"epoch": 0.3368421052631579,
|
| 445 |
-
"eval_chrf": 0.002015902006176986,
|
| 446 |
-
"eval_loss": 7.978994369506836,
|
| 447 |
-
"eval_runtime": 208.0446,
|
| 448 |
-
"eval_samples_per_second": 9.613,
|
| 449 |
-
"eval_steps_per_second": 0.601,
|
| 450 |
-
"step": 10000
|
| 451 |
-
},
|
| 452 |
-
{
|
| 453 |
-
"epoch": 0.34357894736842104,
|
| 454 |
-
"grad_norm": 21.174518585205078,
|
| 455 |
-
"learning_rate": 0.00032841552142279706,
|
| 456 |
-
"loss": 7.2841,
|
| 457 |
-
"step": 10200
|
| 458 |
-
},
|
| 459 |
-
{
|
| 460 |
-
"epoch": 0.3503157894736842,
|
| 461 |
-
"grad_norm": 6.507296562194824,
|
| 462 |
-
"learning_rate": 0.00032504715710051204,
|
| 463 |
-
"loss": 7.2824,
|
| 464 |
-
"step": 10400
|
| 465 |
-
},
|
| 466 |
-
{
|
| 467 |
-
"epoch": 0.35705263157894734,
|
| 468 |
-
"grad_norm": 8.37975025177002,
|
| 469 |
-
"learning_rate": 0.0003216787927782269,
|
| 470 |
-
"loss": 7.2624,
|
| 471 |
-
"step": 10600
|
| 472 |
-
},
|
| 473 |
-
{
|
| 474 |
-
"epoch": 0.36378947368421055,
|
| 475 |
-
"grad_norm": 6.058104038238525,
|
| 476 |
-
"learning_rate": 0.0003183104284559418,
|
| 477 |
-
"loss": 7.257,
|
| 478 |
-
"step": 10800
|
| 479 |
-
},
|
| 480 |
-
{
|
| 481 |
-
"epoch": 0.3705263157894737,
|
| 482 |
-
"grad_norm": 6.78323221206665,
|
| 483 |
-
"learning_rate": 0.00031494206413365674,
|
| 484 |
-
"loss": 7.2562,
|
| 485 |
-
"step": 11000
|
| 486 |
-
},
|
| 487 |
-
{
|
| 488 |
-
"epoch": 0.3705263157894737,
|
| 489 |
-
"eval_chrf": 0.002412227558600064,
|
| 490 |
-
"eval_loss": 7.9691162109375,
|
| 491 |
-
"eval_runtime": 206.8952,
|
| 492 |
-
"eval_samples_per_second": 9.667,
|
| 493 |
-
"eval_steps_per_second": 0.604,
|
| 494 |
-
"step": 11000
|
| 495 |
-
},
|
| 496 |
-
{
|
| 497 |
-
"epoch": 0.37726315789473686,
|
| 498 |
-
"grad_norm": 1.8443028926849365,
|
| 499 |
-
"learning_rate": 0.0003115736998113716,
|
| 500 |
-
"loss": 7.2435,
|
| 501 |
-
"step": 11200
|
| 502 |
-
},
|
| 503 |
-
{
|
| 504 |
-
"epoch": 0.384,
|
| 505 |
-
"grad_norm": 3.558148145675659,
|
| 506 |
-
"learning_rate": 0.0003082053354890865,
|
| 507 |
-
"loss": 7.2501,
|
| 508 |
-
"step": 11400
|
| 509 |
-
},
|
| 510 |
-
{
|
| 511 |
-
"epoch": 0.39073684210526316,
|
| 512 |
-
"grad_norm": 3.3841934204101562,
|
| 513 |
-
"learning_rate": 0.00030483697116680144,
|
| 514 |
-
"loss": 7.275,
|
| 515 |
-
"step": 11600
|
| 516 |
-
},
|
| 517 |
-
{
|
| 518 |
-
"epoch": 0.3974736842105263,
|
| 519 |
-
"grad_norm": 13.780865669250488,
|
| 520 |
-
"learning_rate": 0.0003014686068445163,
|
| 521 |
-
"loss": 7.2607,
|
| 522 |
-
"step": 11800
|
| 523 |
-
},
|
| 524 |
-
{
|
| 525 |
-
"epoch": 0.40421052631578946,
|
| 526 |
-
"grad_norm": 3.4634478092193604,
|
| 527 |
-
"learning_rate": 0.00029810024252223123,
|
| 528 |
-
"loss": 7.2695,
|
| 529 |
-
"step": 12000
|
| 530 |
-
},
|
| 531 |
-
{
|
| 532 |
-
"epoch": 0.40421052631578946,
|
| 533 |
-
"eval_chrf": 0.0018869151022955536,
|
| 534 |
-
"eval_loss": 7.95875358581543,
|
| 535 |
-
"eval_runtime": 207.586,
|
| 536 |
-
"eval_samples_per_second": 9.635,
|
| 537 |
-
"eval_steps_per_second": 0.602,
|
| 538 |
-
"step": 12000
|
| 539 |
-
},
|
| 540 |
-
{
|
| 541 |
-
"epoch": 0.4109473684210526,
|
| 542 |
-
"grad_norm": 13.57261848449707,
|
| 543 |
-
"learning_rate": 0.00029474872002155757,
|
| 544 |
-
"loss": 7.235,
|
| 545 |
-
"step": 12200
|
| 546 |
-
},
|
| 547 |
-
{
|
| 548 |
-
"epoch": 0.41768421052631577,
|
| 549 |
-
"grad_norm": 33.69303512573242,
|
| 550 |
-
"learning_rate": 0.00029138035569927244,
|
| 551 |
-
"loss": 7.2566,
|
| 552 |
-
"step": 12400
|
| 553 |
-
},
|
| 554 |
-
{
|
| 555 |
-
"epoch": 0.4244210526315789,
|
| 556 |
-
"grad_norm": 4.82642936706543,
|
| 557 |
-
"learning_rate": 0.00028801199137698736,
|
| 558 |
-
"loss": 7.2449,
|
| 559 |
-
"step": 12600
|
| 560 |
-
},
|
| 561 |
-
{
|
| 562 |
-
"epoch": 0.43115789473684213,
|
| 563 |
-
"grad_norm": 4.952188014984131,
|
| 564 |
-
"learning_rate": 0.0002846436270547023,
|
| 565 |
-
"loss": 7.256,
|
| 566 |
-
"step": 12800
|
| 567 |
-
},
|
| 568 |
-
{
|
| 569 |
-
"epoch": 0.4378947368421053,
|
| 570 |
-
"grad_norm": 9.873923301696777,
|
| 571 |
-
"learning_rate": 0.0002812921045540286,
|
| 572 |
-
"loss": 7.2354,
|
| 573 |
-
"step": 13000
|
| 574 |
-
},
|
| 575 |
-
{
|
| 576 |
-
"epoch": 0.4378947368421053,
|
| 577 |
-
"eval_chrf": 0.0038042034767471226,
|
| 578 |
-
"eval_loss": 7.933071613311768,
|
| 579 |
-
"eval_runtime": 206.7339,
|
| 580 |
-
"eval_samples_per_second": 9.674,
|
| 581 |
-
"eval_steps_per_second": 0.605,
|
| 582 |
-
"step": 13000
|
| 583 |
-
},
|
| 584 |
-
{
|
| 585 |
-
"epoch": 0.44463157894736843,
|
| 586 |
-
"grad_norm": 5.142228603363037,
|
| 587 |
-
"learning_rate": 0.00027794058205335485,
|
| 588 |
-
"loss": 7.2259,
|
| 589 |
-
"step": 13200
|
| 590 |
-
},
|
| 591 |
-
{
|
| 592 |
-
"epoch": 0.4513684210526316,
|
| 593 |
-
"grad_norm": 2.419574499130249,
|
| 594 |
-
"learning_rate": 0.00027457221773106977,
|
| 595 |
-
"loss": 7.2377,
|
| 596 |
-
"step": 13400
|
| 597 |
-
},
|
| 598 |
-
{
|
| 599 |
-
"epoch": 0.45810526315789474,
|
| 600 |
-
"grad_norm": 7.151025295257568,
|
| 601 |
-
"learning_rate": 0.0002712038534087847,
|
| 602 |
-
"loss": 7.2411,
|
| 603 |
-
"step": 13600
|
| 604 |
-
},
|
| 605 |
-
{
|
| 606 |
-
"epoch": 0.4648421052631579,
|
| 607 |
-
"grad_norm": 3.4384608268737793,
|
| 608 |
-
"learning_rate": 0.0002678354890864996,
|
| 609 |
-
"loss": 7.2342,
|
| 610 |
-
"step": 13800
|
| 611 |
-
},
|
| 612 |
-
{
|
| 613 |
-
"epoch": 0.47157894736842104,
|
| 614 |
-
"grad_norm": 16.630428314208984,
|
| 615 |
-
"learning_rate": 0.0002644839665858259,
|
| 616 |
-
"loss": 7.2102,
|
| 617 |
-
"step": 14000
|
| 618 |
-
},
|
| 619 |
-
{
|
| 620 |
-
"epoch": 0.47157894736842104,
|
| 621 |
-
"eval_chrf": 0.0,
|
| 622 |
-
"eval_loss": 7.95149040222168,
|
| 623 |
-
"eval_runtime": 207.8298,
|
| 624 |
-
"eval_samples_per_second": 9.623,
|
| 625 |
-
"eval_steps_per_second": 0.601,
|
| 626 |
-
"step": 14000
|
| 627 |
-
},
|
| 628 |
-
{
|
| 629 |
-
"epoch": 0.4783157894736842,
|
| 630 |
-
"grad_norm": 92.76679992675781,
|
| 631 |
-
"learning_rate": 0.0002611156022635408,
|
| 632 |
-
"loss": 7.2328,
|
| 633 |
-
"step": 14200
|
| 634 |
-
},
|
| 635 |
-
{
|
| 636 |
-
"epoch": 0.48505263157894735,
|
| 637 |
-
"grad_norm": 4.76525354385376,
|
| 638 |
-
"learning_rate": 0.0002577472379412557,
|
| 639 |
-
"loss": 7.2187,
|
| 640 |
-
"step": 14400
|
| 641 |
-
},
|
| 642 |
-
{
|
| 643 |
-
"epoch": 0.4917894736842105,
|
| 644 |
-
"grad_norm": 21.399099349975586,
|
| 645 |
-
"learning_rate": 0.00025439571544058203,
|
| 646 |
-
"loss": 7.2287,
|
| 647 |
-
"step": 14600
|
| 648 |
-
},
|
| 649 |
-
{
|
| 650 |
-
"epoch": 0.4985263157894737,
|
| 651 |
-
"grad_norm": 52.742637634277344,
|
| 652 |
-
"learning_rate": 0.00025102735111829695,
|
| 653 |
-
"loss": 7.2321,
|
| 654 |
-
"step": 14800
|
| 655 |
-
},
|
| 656 |
-
{
|
| 657 |
-
"epoch": 0.5052631578947369,
|
| 658 |
-
"grad_norm": 52.75876235961914,
|
| 659 |
-
"learning_rate": 0.00024765898679601187,
|
| 660 |
-
"loss": 7.1982,
|
| 661 |
-
"step": 15000
|
| 662 |
-
},
|
| 663 |
-
{
|
| 664 |
-
"epoch": 0.5052631578947369,
|
| 665 |
-
"eval_chrf": 0.08103163954254806,
|
| 666 |
-
"eval_loss": 7.952453136444092,
|
| 667 |
-
"eval_runtime": 208.516,
|
| 668 |
-
"eval_samples_per_second": 9.592,
|
| 669 |
-
"eval_steps_per_second": 0.599,
|
| 670 |
-
"step": 15000
|
| 671 |
-
},
|
| 672 |
-
{
|
| 673 |
-
"epoch": 0.512,
|
| 674 |
-
"grad_norm": 458.2991027832031,
|
| 675 |
-
"learning_rate": 0.0002442906224737268,
|
| 676 |
-
"loss": 7.2178,
|
| 677 |
-
"step": 15200
|
| 678 |
-
},
|
| 679 |
-
{
|
| 680 |
-
"epoch": 0.5187368421052632,
|
| 681 |
-
"grad_norm": 18.82977867126465,
|
| 682 |
-
"learning_rate": 0.00024092225815144168,
|
| 683 |
-
"loss": 7.2092,
|
| 684 |
-
"step": 15400
|
| 685 |
-
},
|
| 686 |
-
{
|
| 687 |
-
"epoch": 0.5254736842105263,
|
| 688 |
-
"grad_norm": 7.6946892738342285,
|
| 689 |
-
"learning_rate": 0.00023755389382915657,
|
| 690 |
-
"loss": 7.1814,
|
| 691 |
-
"step": 15600
|
| 692 |
-
},
|
| 693 |
-
{
|
| 694 |
-
"epoch": 0.5322105263157895,
|
| 695 |
-
"grad_norm": 75.808837890625,
|
| 696 |
-
"learning_rate": 0.00023418552950687146,
|
| 697 |
-
"loss": 7.198,
|
| 698 |
-
"step": 15800
|
| 699 |
-
},
|
| 700 |
-
{
|
| 701 |
-
"epoch": 0.5389473684210526,
|
| 702 |
-
"grad_norm": 6.179436683654785,
|
| 703 |
-
"learning_rate": 0.00023081716518458638,
|
| 704 |
-
"loss": 7.2108,
|
| 705 |
-
"step": 16000
|
| 706 |
-
},
|
| 707 |
-
{
|
| 708 |
-
"epoch": 0.5389473684210526,
|
| 709 |
-
"eval_chrf": 0.003132385941953158,
|
| 710 |
-
"eval_loss": 7.934022426605225,
|
| 711 |
-
"eval_runtime": 208.7048,
|
| 712 |
-
"eval_samples_per_second": 9.583,
|
| 713 |
-
"eval_steps_per_second": 0.599,
|
| 714 |
-
"step": 16000
|
| 715 |
-
},
|
| 716 |
-
{
|
| 717 |
-
"epoch": 0.5456842105263158,
|
| 718 |
-
"grad_norm": 11.434579849243164,
|
| 719 |
-
"learning_rate": 0.00022744880086230128,
|
| 720 |
-
"loss": 7.2084,
|
| 721 |
-
"step": 16200
|
| 722 |
-
},
|
| 723 |
-
{
|
| 724 |
-
"epoch": 0.5524210526315789,
|
| 725 |
-
"grad_norm": 8.820486068725586,
|
| 726 |
-
"learning_rate": 0.00022408043654001617,
|
| 727 |
-
"loss": 7.2035,
|
| 728 |
-
"step": 16400
|
| 729 |
-
},
|
| 730 |
-
{
|
| 731 |
-
"epoch": 0.5591578947368421,
|
| 732 |
-
"grad_norm": 152.7312469482422,
|
| 733 |
-
"learning_rate": 0.00022071207221773106,
|
| 734 |
-
"loss": 7.1938,
|
| 735 |
-
"step": 16600
|
| 736 |
-
},
|
| 737 |
-
{
|
| 738 |
-
"epoch": 0.5658947368421052,
|
| 739 |
-
"grad_norm": 25.932987213134766,
|
| 740 |
-
"learning_rate": 0.00021734370789544598,
|
| 741 |
-
"loss": 7.1847,
|
| 742 |
-
"step": 16800
|
| 743 |
-
},
|
| 744 |
-
{
|
| 745 |
-
"epoch": 0.5726315789473684,
|
| 746 |
-
"grad_norm": 2.2950472831726074,
|
| 747 |
-
"learning_rate": 0.00021397534357316087,
|
| 748 |
-
"loss": 7.1826,
|
| 749 |
-
"step": 17000
|
| 750 |
-
},
|
| 751 |
-
{
|
| 752 |
-
"epoch": 0.5726315789473684,
|
| 753 |
-
"eval_chrf": 0.0019444598388038512,
|
| 754 |
-
"eval_loss": 7.9318037033081055,
|
| 755 |
-
"eval_runtime": 209.2532,
|
| 756 |
-
"eval_samples_per_second": 9.558,
|
| 757 |
-
"eval_steps_per_second": 0.597,
|
| 758 |
-
"step": 17000
|
| 759 |
-
},
|
| 760 |
-
{
|
| 761 |
-
"epoch": 0.5793684210526315,
|
| 762 |
-
"grad_norm": 2.543137788772583,
|
| 763 |
-
"learning_rate": 0.00021060697925087576,
|
| 764 |
-
"loss": 7.2089,
|
| 765 |
-
"step": 17200
|
| 766 |
-
},
|
| 767 |
-
{
|
| 768 |
-
"epoch": 0.5861052631578947,
|
| 769 |
-
"grad_norm": 2.32310152053833,
|
| 770 |
-
"learning_rate": 0.0002072554567502021,
|
| 771 |
-
"loss": 7.1882,
|
| 772 |
-
"step": 17400
|
| 773 |
-
},
|
| 774 |
-
{
|
| 775 |
-
"epoch": 0.592842105263158,
|
| 776 |
-
"grad_norm": 4.159054279327393,
|
| 777 |
-
"learning_rate": 0.000203887092427917,
|
| 778 |
-
"loss": 7.1915,
|
| 779 |
-
"step": 17600
|
| 780 |
-
},
|
| 781 |
-
{
|
| 782 |
-
"epoch": 0.5995789473684211,
|
| 783 |
-
"grad_norm": 2.6347360610961914,
|
| 784 |
-
"learning_rate": 0.0002005187281056319,
|
| 785 |
-
"loss": 7.1964,
|
| 786 |
-
"step": 17800
|
| 787 |
-
},
|
| 788 |
-
{
|
| 789 |
-
"epoch": 0.6063157894736843,
|
| 790 |
-
"grad_norm": 30.20026969909668,
|
| 791 |
-
"learning_rate": 0.0001971503637833468,
|
| 792 |
-
"loss": 7.1968,
|
| 793 |
-
"step": 18000
|
| 794 |
-
},
|
| 795 |
-
{
|
| 796 |
-
"epoch": 0.6063157894736843,
|
| 797 |
-
"eval_chrf": 0.004562467509283169,
|
| 798 |
-
"eval_loss": 7.917642593383789,
|
| 799 |
-
"eval_runtime": 205.2953,
|
| 800 |
-
"eval_samples_per_second": 9.742,
|
| 801 |
-
"eval_steps_per_second": 0.609,
|
| 802 |
-
"step": 18000
|
| 803 |
-
},
|
| 804 |
-
{
|
| 805 |
-
"epoch": 0.6130526315789474,
|
| 806 |
-
"grad_norm": 14.687439918518066,
|
| 807 |
-
"learning_rate": 0.0001937819994610617,
|
| 808 |
-
"loss": 7.164,
|
| 809 |
-
"step": 18200
|
| 810 |
-
},
|
| 811 |
-
{
|
| 812 |
-
"epoch": 0.6197894736842106,
|
| 813 |
-
"grad_norm": 2.020901918411255,
|
| 814 |
-
"learning_rate": 0.0001904136351387766,
|
| 815 |
-
"loss": 7.1797,
|
| 816 |
-
"step": 18400
|
| 817 |
-
},
|
| 818 |
-
{
|
| 819 |
-
"epoch": 0.6265263157894737,
|
| 820 |
-
"grad_norm": 3.653233051300049,
|
| 821 |
-
"learning_rate": 0.00018704527081649152,
|
| 822 |
-
"loss": 7.1938,
|
| 823 |
-
"step": 18600
|
| 824 |
-
},
|
| 825 |
-
{
|
| 826 |
-
"epoch": 0.6332631578947369,
|
| 827 |
-
"grad_norm": 3.1946516036987305,
|
| 828 |
-
"learning_rate": 0.00018367690649420643,
|
| 829 |
-
"loss": 7.1726,
|
| 830 |
-
"step": 18800
|
| 831 |
-
},
|
| 832 |
-
{
|
| 833 |
-
"epoch": 0.64,
|
| 834 |
-
"grad_norm": 7.460574150085449,
|
| 835 |
-
"learning_rate": 0.00018030854217192133,
|
| 836 |
-
"loss": 7.1489,
|
| 837 |
-
"step": 19000
|
| 838 |
-
},
|
| 839 |
-
{
|
| 840 |
-
"epoch": 0.64,
|
| 841 |
-
"eval_chrf": 0.006730491793968211,
|
| 842 |
-
"eval_loss": 7.91720724105835,
|
| 843 |
-
"eval_runtime": 206.4462,
|
| 844 |
-
"eval_samples_per_second": 9.688,
|
| 845 |
-
"eval_steps_per_second": 0.605,
|
| 846 |
-
"step": 19000
|
| 847 |
-
},
|
| 848 |
-
{
|
| 849 |
-
"epoch": 0.6467368421052632,
|
| 850 |
-
"grad_norm": 3.547877311706543,
|
| 851 |
-
"learning_rate": 0.00017694017784963622,
|
| 852 |
-
"loss": 7.1717,
|
| 853 |
-
"step": 19200
|
| 854 |
-
},
|
| 855 |
-
{
|
| 856 |
-
"epoch": 0.6534736842105263,
|
| 857 |
-
"grad_norm": 6.870595932006836,
|
| 858 |
-
"learning_rate": 0.00017357181352735114,
|
| 859 |
-
"loss": 7.1649,
|
| 860 |
-
"step": 19400
|
| 861 |
-
},
|
| 862 |
-
{
|
| 863 |
-
"epoch": 0.6602105263157895,
|
| 864 |
-
"grad_norm": 30.911413192749023,
|
| 865 |
-
"learning_rate": 0.00017020344920506603,
|
| 866 |
-
"loss": 7.1932,
|
| 867 |
-
"step": 19600
|
| 868 |
-
},
|
| 869 |
-
{
|
| 870 |
-
"epoch": 0.6669473684210526,
|
| 871 |
-
"grad_norm": 27.14822769165039,
|
| 872 |
-
"learning_rate": 0.00016683508488278092,
|
| 873 |
-
"loss": 7.1748,
|
| 874 |
-
"step": 19800
|
| 875 |
-
},
|
| 876 |
-
{
|
| 877 |
-
"epoch": 0.6736842105263158,
|
| 878 |
-
"grad_norm": 6.460318565368652,
|
| 879 |
-
"learning_rate": 0.00016346672056049584,
|
| 880 |
-
"loss": 7.1696,
|
| 881 |
-
"step": 20000
|
| 882 |
-
},
|
| 883 |
-
{
|
| 884 |
-
"epoch": 0.6736842105263158,
|
| 885 |
-
"eval_chrf": 0.0110937211817252,
|
| 886 |
-
"eval_loss": 7.917947292327881,
|
| 887 |
-
"eval_runtime": 205.7528,
|
| 888 |
-
"eval_samples_per_second": 9.72,
|
| 889 |
-
"eval_steps_per_second": 0.608,
|
| 890 |
-
"step": 20000
|
| 891 |
-
},
|
| 892 |
-
{
|
| 893 |
-
"epoch": 0.6804210526315789,
|
| 894 |
-
"grad_norm": 27.423723220825195,
|
| 895 |
-
"learning_rate": 0.00016009835623821074,
|
| 896 |
-
"loss": 7.1587,
|
| 897 |
-
"step": 20200
|
| 898 |
-
},
|
| 899 |
-
{
|
| 900 |
-
"epoch": 0.6871578947368421,
|
| 901 |
-
"grad_norm": 36.06264114379883,
|
| 902 |
-
"learning_rate": 0.00015672999191592563,
|
| 903 |
-
"loss": 7.162,
|
| 904 |
-
"step": 20400
|
| 905 |
-
},
|
| 906 |
-
{
|
| 907 |
-
"epoch": 0.6938947368421052,
|
| 908 |
-
"grad_norm": 21.235185623168945,
|
| 909 |
-
"learning_rate": 0.00015336162759364052,
|
| 910 |
-
"loss": 7.1682,
|
| 911 |
-
"step": 20600
|
| 912 |
-
},
|
| 913 |
-
{
|
| 914 |
-
"epoch": 0.7006315789473684,
|
| 915 |
-
"grad_norm": 63.7025032043457,
|
| 916 |
-
"learning_rate": 0.00014999326327135544,
|
| 917 |
-
"loss": 7.1485,
|
| 918 |
-
"step": 20800
|
| 919 |
-
},
|
| 920 |
-
{
|
| 921 |
-
"epoch": 0.7073684210526315,
|
| 922 |
-
"grad_norm": 24.675535202026367,
|
| 923 |
-
"learning_rate": 0.00014662489894907033,
|
| 924 |
-
"loss": 7.1642,
|
| 925 |
-
"step": 21000
|
| 926 |
-
},
|
| 927 |
-
{
|
| 928 |
-
"epoch": 0.7073684210526315,
|
| 929 |
-
"eval_chrf": 0.001302284516081954,
|
| 930 |
-
"eval_loss": 7.913628101348877,
|
| 931 |
-
"eval_runtime": 206.9451,
|
| 932 |
-
"eval_samples_per_second": 9.664,
|
| 933 |
-
"eval_steps_per_second": 0.604,
|
| 934 |
-
"step": 21000
|
| 935 |
-
},
|
| 936 |
-
{
|
| 937 |
-
"epoch": 0.7141052631578947,
|
| 938 |
-
"grad_norm": 8.021008491516113,
|
| 939 |
-
"learning_rate": 0.00014325653462678522,
|
| 940 |
-
"loss": 7.1759,
|
| 941 |
-
"step": 21200
|
| 942 |
-
},
|
| 943 |
-
{
|
| 944 |
-
"epoch": 0.7208421052631578,
|
| 945 |
-
"grad_norm": 7.012975215911865,
|
| 946 |
-
"learning_rate": 0.00013988817030450012,
|
| 947 |
-
"loss": 7.1351,
|
| 948 |
-
"step": 21400
|
| 949 |
-
},
|
| 950 |
-
{
|
| 951 |
-
"epoch": 0.7275789473684211,
|
| 952 |
-
"grad_norm": 10.689805030822754,
|
| 953 |
-
"learning_rate": 0.00013651980598221504,
|
| 954 |
-
"loss": 7.1471,
|
| 955 |
-
"step": 21600
|
| 956 |
-
},
|
| 957 |
-
{
|
| 958 |
-
"epoch": 0.7343157894736843,
|
| 959 |
-
"grad_norm": 5.859151840209961,
|
| 960 |
-
"learning_rate": 0.00013315144165992993,
|
| 961 |
-
"loss": 7.1629,
|
| 962 |
-
"step": 21800
|
| 963 |
-
},
|
| 964 |
-
{
|
| 965 |
-
"epoch": 0.7410526315789474,
|
| 966 |
-
"grad_norm": 7.223715782165527,
|
| 967 |
-
"learning_rate": 0.00012978307733764485,
|
| 968 |
-
"loss": 7.1661,
|
| 969 |
-
"step": 22000
|
| 970 |
-
},
|
| 971 |
-
{
|
| 972 |
-
"epoch": 0.7410526315789474,
|
| 973 |
-
"eval_chrf": 0.0011799654844890197,
|
| 974 |
-
"eval_loss": 7.905208110809326,
|
| 975 |
-
"eval_runtime": 207.646,
|
| 976 |
-
"eval_samples_per_second": 9.632,
|
| 977 |
-
"eval_steps_per_second": 0.602,
|
| 978 |
-
"step": 22000
|
| 979 |
-
},
|
| 980 |
-
{
|
| 981 |
-
"epoch": 0.7477894736842106,
|
| 982 |
-
"grad_norm": 9.268714904785156,
|
| 983 |
-
"learning_rate": 0.00012641471301535977,
|
| 984 |
-
"loss": 7.157,
|
| 985 |
-
"step": 22200
|
| 986 |
-
},
|
| 987 |
-
{
|
| 988 |
-
"epoch": 0.7545263157894737,
|
| 989 |
-
"grad_norm": 12.853730201721191,
|
| 990 |
-
"learning_rate": 0.00012304634869307463,
|
| 991 |
-
"loss": 7.149,
|
| 992 |
-
"step": 22400
|
| 993 |
-
},
|
| 994 |
-
{
|
| 995 |
-
"epoch": 0.7612631578947369,
|
| 996 |
-
"grad_norm": 17.167985916137695,
|
| 997 |
-
"learning_rate": 0.00011967798437078954,
|
| 998 |
-
"loss": 7.1557,
|
| 999 |
-
"step": 22600
|
| 1000 |
-
},
|
| 1001 |
-
{
|
| 1002 |
-
"epoch": 0.768,
|
| 1003 |
-
"grad_norm": 2.593167543411255,
|
| 1004 |
-
"learning_rate": 0.00011630962004850446,
|
| 1005 |
-
"loss": 7.1546,
|
| 1006 |
-
"step": 22800
|
| 1007 |
-
},
|
| 1008 |
-
{
|
| 1009 |
-
"epoch": 0.7747368421052632,
|
| 1010 |
-
"grad_norm": 14.160483360290527,
|
| 1011 |
-
"learning_rate": 0.00011294125572621935,
|
| 1012 |
-
"loss": 7.1355,
|
| 1013 |
-
"step": 23000
|
| 1014 |
-
},
|
| 1015 |
-
{
|
| 1016 |
-
"epoch": 0.7747368421052632,
|
| 1017 |
-
"eval_chrf": 0.0041122119540037425,
|
| 1018 |
-
"eval_loss": 7.90371561050415,
|
| 1019 |
-
"eval_runtime": 207.9982,
|
| 1020 |
-
"eval_samples_per_second": 9.615,
|
| 1021 |
-
"eval_steps_per_second": 0.601,
|
| 1022 |
-
"step": 23000
|
| 1023 |
-
},
|
| 1024 |
-
{
|
| 1025 |
-
"epoch": 0.7814736842105263,
|
| 1026 |
-
"grad_norm": 10556.6650390625,
|
| 1027 |
-
"learning_rate": 0.00010957289140393426,
|
| 1028 |
-
"loss": 7.1865,
|
| 1029 |
-
"step": 23200
|
| 1030 |
-
},
|
| 1031 |
-
{
|
| 1032 |
-
"epoch": 0.7882105263157895,
|
| 1033 |
-
"grad_norm": 4.445006847381592,
|
| 1034 |
-
"learning_rate": 0.00010620452708164916,
|
| 1035 |
-
"loss": 7.1488,
|
| 1036 |
-
"step": 23400
|
| 1037 |
-
},
|
| 1038 |
-
{
|
| 1039 |
-
"epoch": 0.7949473684210526,
|
| 1040 |
-
"grad_norm": 85.52156829833984,
|
| 1041 |
-
"learning_rate": 0.00010283616275936405,
|
| 1042 |
-
"loss": 7.1588,
|
| 1043 |
-
"step": 23600
|
| 1044 |
-
},
|
| 1045 |
-
{
|
| 1046 |
-
"epoch": 0.8016842105263158,
|
| 1047 |
-
"grad_norm": 6.259866714477539,
|
| 1048 |
-
"learning_rate": 9.946779843707896e-05,
|
| 1049 |
-
"loss": 7.1447,
|
| 1050 |
-
"step": 23800
|
| 1051 |
-
},
|
| 1052 |
-
{
|
| 1053 |
-
"epoch": 0.8084210526315789,
|
| 1054 |
-
"grad_norm": 224.35865783691406,
|
| 1055 |
-
"learning_rate": 9.609943411479385e-05,
|
| 1056 |
-
"loss": 7.129,
|
| 1057 |
-
"step": 24000
|
| 1058 |
-
},
|
| 1059 |
-
{
|
| 1060 |
-
"epoch": 0.8084210526315789,
|
| 1061 |
-
"eval_chrf": 0.0,
|
| 1062 |
-
"eval_loss": 7.911408424377441,
|
| 1063 |
-
"eval_runtime": 207.0244,
|
| 1064 |
-
"eval_samples_per_second": 9.661,
|
| 1065 |
-
"eval_steps_per_second": 0.604,
|
| 1066 |
-
"step": 24000
|
| 1067 |
-
},
|
| 1068 |
-
{
|
| 1069 |
-
"epoch": 0.8151578947368421,
|
| 1070 |
-
"grad_norm": 23.08391571044922,
|
| 1071 |
-
"learning_rate": 9.273106979250876e-05,
|
| 1072 |
-
"loss": 7.1423,
|
| 1073 |
-
"step": 24200
|
| 1074 |
-
},
|
| 1075 |
-
{
|
| 1076 |
-
"epoch": 0.8218947368421052,
|
| 1077 |
-
"grad_norm": 245.7853546142578,
|
| 1078 |
-
"learning_rate": 8.937954729183509e-05,
|
| 1079 |
-
"loss": 7.1328,
|
| 1080 |
-
"step": 24400
|
| 1081 |
-
},
|
| 1082 |
-
{
|
| 1083 |
-
"epoch": 0.8286315789473684,
|
| 1084 |
-
"grad_norm": 15.29963493347168,
|
| 1085 |
-
"learning_rate": 8.601118296954999e-05,
|
| 1086 |
-
"loss": 7.129,
|
| 1087 |
-
"step": 24600
|
| 1088 |
-
},
|
| 1089 |
-
{
|
| 1090 |
-
"epoch": 0.8353684210526315,
|
| 1091 |
-
"grad_norm": 2.8458406925201416,
|
| 1092 |
-
"learning_rate": 8.264281864726489e-05,
|
| 1093 |
-
"loss": 7.1198,
|
| 1094 |
-
"step": 24800
|
| 1095 |
-
},
|
| 1096 |
-
{
|
| 1097 |
-
"epoch": 0.8421052631578947,
|
| 1098 |
-
"grad_norm": 13.018074035644531,
|
| 1099 |
-
"learning_rate": 7.927445432497979e-05,
|
| 1100 |
-
"loss": 7.1327,
|
| 1101 |
-
"step": 25000
|
| 1102 |
-
},
|
| 1103 |
-
{
|
| 1104 |
-
"epoch": 0.8421052631578947,
|
| 1105 |
-
"eval_chrf": 0.013941249868227827,
|
| 1106 |
-
"eval_loss": 7.8870368003845215,
|
| 1107 |
-
"eval_runtime": 207.43,
|
| 1108 |
-
"eval_samples_per_second": 9.642,
|
| 1109 |
-
"eval_steps_per_second": 0.603,
|
| 1110 |
-
"step": 25000
|
| 1111 |
-
},
|
| 1112 |
-
{
|
| 1113 |
-
"epoch": 0.8488421052631578,
|
| 1114 |
-
"grad_norm": 5.2148823738098145,
|
| 1115 |
-
"learning_rate": 7.590609000269468e-05,
|
| 1116 |
-
"loss": 7.1452,
|
| 1117 |
-
"step": 25200
|
| 1118 |
-
},
|
| 1119 |
-
{
|
| 1120 |
-
"epoch": 0.8555789473684211,
|
| 1121 |
-
"grad_norm": 19.233739852905273,
|
| 1122 |
-
"learning_rate": 7.253772568040959e-05,
|
| 1123 |
-
"loss": 7.1447,
|
| 1124 |
-
"step": 25400
|
| 1125 |
-
},
|
| 1126 |
-
{
|
| 1127 |
-
"epoch": 0.8623157894736843,
|
| 1128 |
-
"grad_norm": 14.095065116882324,
|
| 1129 |
-
"learning_rate": 6.916936135812451e-05,
|
| 1130 |
-
"loss": 7.1247,
|
| 1131 |
-
"step": 25600
|
| 1132 |
-
},
|
| 1133 |
-
{
|
| 1134 |
-
"epoch": 0.8690526315789474,
|
| 1135 |
-
"grad_norm": 7.621742248535156,
|
| 1136 |
-
"learning_rate": 6.58009970358394e-05,
|
| 1137 |
-
"loss": 7.1332,
|
| 1138 |
-
"step": 25800
|
| 1139 |
-
},
|
| 1140 |
-
{
|
| 1141 |
-
"epoch": 0.8757894736842106,
|
| 1142 |
-
"grad_norm": 29.361238479614258,
|
| 1143 |
-
"learning_rate": 6.243263271355431e-05,
|
| 1144 |
-
"loss": 7.1217,
|
| 1145 |
-
"step": 26000
|
| 1146 |
-
},
|
| 1147 |
-
{
|
| 1148 |
-
"epoch": 0.8757894736842106,
|
| 1149 |
-
"eval_chrf": 0.014676119312534507,
|
| 1150 |
-
"eval_loss": 7.898392200469971,
|
| 1151 |
-
"eval_runtime": 209.4371,
|
| 1152 |
-
"eval_samples_per_second": 9.549,
|
| 1153 |
-
"eval_steps_per_second": 0.597,
|
| 1154 |
-
"step": 26000
|
| 1155 |
-
},
|
| 1156 |
-
{
|
| 1157 |
-
"epoch": 0.8825263157894737,
|
| 1158 |
-
"grad_norm": 5.2996015548706055,
|
| 1159 |
-
"learning_rate": 5.90642683912692e-05,
|
| 1160 |
-
"loss": 7.1288,
|
| 1161 |
-
"step": 26200
|
| 1162 |
-
},
|
| 1163 |
-
{
|
| 1164 |
-
"epoch": 0.8892631578947369,
|
| 1165 |
-
"grad_norm": 11.741786003112793,
|
| 1166 |
-
"learning_rate": 5.56959040689841e-05,
|
| 1167 |
-
"loss": 7.1358,
|
| 1168 |
-
"step": 26400
|
| 1169 |
-
},
|
| 1170 |
-
{
|
| 1171 |
-
"epoch": 0.896,
|
| 1172 |
-
"grad_norm": 11.052619934082031,
|
| 1173 |
-
"learning_rate": 5.2327539746699005e-05,
|
| 1174 |
-
"loss": 7.1089,
|
| 1175 |
-
"step": 26600
|
| 1176 |
-
},
|
| 1177 |
-
{
|
| 1178 |
-
"epoch": 0.9027368421052632,
|
| 1179 |
-
"grad_norm": 43.7511100769043,
|
| 1180 |
-
"learning_rate": 4.895917542441391e-05,
|
| 1181 |
-
"loss": 7.1314,
|
| 1182 |
-
"step": 26800
|
| 1183 |
-
},
|
| 1184 |
-
{
|
| 1185 |
-
"epoch": 0.9094736842105263,
|
| 1186 |
-
"grad_norm": 3.492421865463257,
|
| 1187 |
-
"learning_rate": 4.559081110212881e-05,
|
| 1188 |
-
"loss": 7.1272,
|
| 1189 |
-
"step": 27000
|
| 1190 |
-
},
|
| 1191 |
-
{
|
| 1192 |
-
"epoch": 0.9094736842105263,
|
| 1193 |
-
"eval_chrf": 0.016404275037183086,
|
| 1194 |
-
"eval_loss": 7.888070106506348,
|
| 1195 |
-
"eval_runtime": 208.0677,
|
| 1196 |
-
"eval_samples_per_second": 9.612,
|
| 1197 |
-
"eval_steps_per_second": 0.601,
|
| 1198 |
-
"step": 27000
|
| 1199 |
-
},
|
| 1200 |
-
{
|
| 1201 |
-
"epoch": 0.9162105263157895,
|
| 1202 |
-
"grad_norm": 4.310942649841309,
|
| 1203 |
-
"learning_rate": 4.222244677984371e-05,
|
| 1204 |
-
"loss": 7.1517,
|
| 1205 |
-
"step": 27200
|
| 1206 |
-
},
|
| 1207 |
-
{
|
| 1208 |
-
"epoch": 0.9229473684210526,
|
| 1209 |
-
"grad_norm": 2.516460657119751,
|
| 1210 |
-
"learning_rate": 3.885408245755861e-05,
|
| 1211 |
-
"loss": 7.1274,
|
| 1212 |
-
"step": 27400
|
| 1213 |
-
},
|
| 1214 |
-
{
|
| 1215 |
-
"epoch": 0.9296842105263158,
|
| 1216 |
-
"grad_norm": 16.778484344482422,
|
| 1217 |
-
"learning_rate": 3.5485718135273514e-05,
|
| 1218 |
-
"loss": 7.1142,
|
| 1219 |
-
"step": 27600
|
| 1220 |
-
},
|
| 1221 |
-
{
|
| 1222 |
-
"epoch": 0.9364210526315789,
|
| 1223 |
-
"grad_norm": 12.279007911682129,
|
| 1224 |
-
"learning_rate": 3.211735381298841e-05,
|
| 1225 |
-
"loss": 7.1103,
|
| 1226 |
-
"step": 27800
|
| 1227 |
-
},
|
| 1228 |
-
{
|
| 1229 |
-
"epoch": 0.9431578947368421,
|
| 1230 |
-
"grad_norm": 17.17557716369629,
|
| 1231 |
-
"learning_rate": 2.876583131231474e-05,
|
| 1232 |
-
"loss": 7.1172,
|
| 1233 |
-
"step": 28000
|
| 1234 |
-
},
|
| 1235 |
-
{
|
| 1236 |
-
"epoch": 0.9431578947368421,
|
| 1237 |
-
"eval_chrf": 0.011932768282003571,
|
| 1238 |
-
"eval_loss": 7.885815143585205,
|
| 1239 |
-
"eval_runtime": 206.9267,
|
| 1240 |
-
"eval_samples_per_second": 9.665,
|
| 1241 |
-
"eval_steps_per_second": 0.604,
|
| 1242 |
-
"step": 28000
|
| 1243 |
-
},
|
| 1244 |
-
{
|
| 1245 |
-
"epoch": 0.9498947368421052,
|
| 1246 |
-
"grad_norm": 10.02868366241455,
|
| 1247 |
-
"learning_rate": 2.5414308811641068e-05,
|
| 1248 |
-
"loss": 7.125,
|
| 1249 |
-
"step": 28200
|
| 1250 |
-
},
|
| 1251 |
-
{
|
| 1252 |
-
"epoch": 0.9566315789473684,
|
| 1253 |
-
"grad_norm": 62.310943603515625,
|
| 1254 |
-
"learning_rate": 2.204594448935597e-05,
|
| 1255 |
-
"loss": 7.129,
|
| 1256 |
-
"step": 28400
|
| 1257 |
-
},
|
| 1258 |
-
{
|
| 1259 |
-
"epoch": 0.9633684210526315,
|
| 1260 |
-
"grad_norm": 15.6820068359375,
|
| 1261 |
-
"learning_rate": 1.867758016707087e-05,
|
| 1262 |
-
"loss": 7.1403,
|
| 1263 |
-
"step": 28600
|
| 1264 |
-
},
|
| 1265 |
-
{
|
| 1266 |
-
"epoch": 0.9701052631578947,
|
| 1267 |
-
"grad_norm": 29.801271438598633,
|
| 1268 |
-
"learning_rate": 1.5309215844785772e-05,
|
| 1269 |
-
"loss": 7.1221,
|
| 1270 |
-
"step": 28800
|
| 1271 |
-
},
|
| 1272 |
-
{
|
| 1273 |
-
"epoch": 0.9768421052631578,
|
| 1274 |
-
"grad_norm": 10.878236770629883,
|
| 1275 |
-
"learning_rate": 1.1940851522500673e-05,
|
| 1276 |
-
"loss": 7.117,
|
| 1277 |
-
"step": 29000
|
| 1278 |
-
},
|
| 1279 |
-
{
|
| 1280 |
-
"epoch": 0.9768421052631578,
|
| 1281 |
-
"eval_chrf": 0.007758678698519381,
|
| 1282 |
-
"eval_loss": 7.882614612579346,
|
| 1283 |
-
"eval_runtime": 206.9708,
|
| 1284 |
-
"eval_samples_per_second": 9.663,
|
| 1285 |
-
"eval_steps_per_second": 0.604,
|
| 1286 |
-
"step": 29000
|
| 1287 |
-
},
|
| 1288 |
-
{
|
| 1289 |
-
"epoch": 0.983578947368421,
|
| 1290 |
-
"grad_norm": 12.309194564819336,
|
| 1291 |
-
"learning_rate": 8.572487200215576e-06,
|
| 1292 |
-
"loss": 7.1325,
|
| 1293 |
-
"step": 29200
|
| 1294 |
-
},
|
| 1295 |
-
{
|
| 1296 |
-
"epoch": 0.9903157894736843,
|
| 1297 |
-
"grad_norm": 9.50011920928955,
|
| 1298 |
-
"learning_rate": 5.204122877930477e-06,
|
| 1299 |
-
"loss": 7.1155,
|
| 1300 |
-
"step": 29400
|
| 1301 |
-
},
|
| 1302 |
-
{
|
| 1303 |
-
"epoch": 0.9970526315789474,
|
| 1304 |
-
"grad_norm": 10.140064239501953,
|
| 1305 |
-
"learning_rate": 1.8357585556453785e-06,
|
| 1306 |
-
"loss": 7.1061,
|
| 1307 |
-
"step": 29600
|
| 1308 |
-
}
|
| 1309 |
-
],
|
| 1310 |
-
"logging_steps": 200,
|
| 1311 |
-
"max_steps": 29688,
|
| 1312 |
-
"num_input_tokens_seen": 0,
|
| 1313 |
-
"num_train_epochs": 1,
|
| 1314 |
-
"save_steps": 1000,
|
| 1315 |
-
"stateful_callbacks": {
|
| 1316 |
-
"TrainerControl": {
|
| 1317 |
-
"args": {
|
| 1318 |
-
"should_epoch_stop": false,
|
| 1319 |
-
"should_evaluate": false,
|
| 1320 |
-
"should_log": false,
|
| 1321 |
-
"should_save": true,
|
| 1322 |
-
"should_training_stop": true
|
| 1323 |
-
},
|
| 1324 |
-
"attributes": {}
|
| 1325 |
-
}
|
| 1326 |
-
},
|
| 1327 |
-
"total_flos": 1.1855167823020032e+16,
|
| 1328 |
-
"train_batch_size": 16,
|
| 1329 |
-
"trial_name": null,
|
| 1330 |
-
"trial_params": null
|
| 1331 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
custom_t5_enzh/checkpoint-29688/training_args.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:add135644272834a16fd6d191289d331be161e3f79fee156a1d67d95b81a509d
|
| 3 |
-
size 5432
|
|
|
|
|
|
|
|
|
|
|
|