mubi commited on
Training in progress, step 300, checkpoint
Browse files- last-checkpoint/adapter_config.json +4 -4
- last-checkpoint/adapter_model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +9 -324
- last-checkpoint/training_args.bin +1 -1
last-checkpoint/adapter_config.json
CHANGED
|
@@ -34,12 +34,12 @@
|
|
| 34 |
"revision": null,
|
| 35 |
"target_modules": [
|
| 36 |
"k_proj",
|
| 37 |
-
"
|
|
|
|
| 38 |
"down_proj",
|
| 39 |
-
"v_proj",
|
| 40 |
"gate_proj",
|
| 41 |
-
"
|
| 42 |
-
"
|
| 43 |
],
|
| 44 |
"target_parameters": null,
|
| 45 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 34 |
"revision": null,
|
| 35 |
"target_modules": [
|
| 36 |
"k_proj",
|
| 37 |
+
"q_proj",
|
| 38 |
+
"up_proj",
|
| 39 |
"down_proj",
|
|
|
|
| 40 |
"gate_proj",
|
| 41 |
+
"o_proj",
|
| 42 |
+
"v_proj"
|
| 43 |
],
|
| 44 |
"target_parameters": null,
|
| 45 |
"task_type": "CAUSAL_LM",
|
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 119597408
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:957b1d6cd03c133280dcffffb39454c963dfa646010078dee1ad5b855fabb8e0
|
| 3 |
size 119597408
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 61232293
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8139c246b94eedf9c59349dc6ef47dcb2abd3c670c6732349a61ef5d72f7bd1
|
| 3 |
size 61232293
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
|
| 3 |
size 14645
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1383
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30af866df24edce708e1eb20700878b402fa05707fa9bc5f332496baf440dbbb
|
| 3 |
size 1383
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7442deb0c3e03c328c05262c8906396ab48f1a3e5d9ba4630479c1996a028545
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,348 +2,33 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
"epoch": 0.05333333333333334,
|
| 14 |
-
"grad_norm": 0.
|
| 15 |
"learning_rate": 0.00019996188073020713,
|
| 16 |
-
"loss": 0.
|
| 17 |
"step": 100
|
| 18 |
},
|
| 19 |
{
|
| 20 |
"epoch": 0.10666666666666667,
|
| 21 |
-
"grad_norm": 0.
|
| 22 |
"learning_rate": 0.00019964771237806272,
|
| 23 |
-
"loss": 0.
|
| 24 |
"step": 200
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 0.16,
|
| 28 |
-
"grad_norm": 0.
|
| 29 |
"learning_rate": 0.0001990171979823181,
|
| 30 |
-
"loss": 0.
|
| 31 |
"step": 300
|
| 32 |
-
},
|
| 33 |
-
{
|
| 34 |
-
"epoch": 0.21333333333333335,
|
| 35 |
-
"grad_norm": 0.18324309587478638,
|
| 36 |
-
"learning_rate": 0.00019807233920191516,
|
| 37 |
-
"loss": 0.5441,
|
| 38 |
-
"step": 400
|
| 39 |
-
},
|
| 40 |
-
{
|
| 41 |
-
"epoch": 0.26666666666666666,
|
| 42 |
-
"grad_norm": 0.20826920866966248,
|
| 43 |
-
"learning_rate": 0.00019681613562740963,
|
| 44 |
-
"loss": 0.5466,
|
| 45 |
-
"step": 500
|
| 46 |
-
},
|
| 47 |
-
{
|
| 48 |
-
"epoch": 0.32,
|
| 49 |
-
"grad_norm": 0.209468275308609,
|
| 50 |
-
"learning_rate": 0.00019525257525833772,
|
| 51 |
-
"loss": 0.5744,
|
| 52 |
-
"step": 600
|
| 53 |
-
},
|
| 54 |
-
{
|
| 55 |
-
"epoch": 0.37333333333333335,
|
| 56 |
-
"grad_norm": 0.2050088346004486,
|
| 57 |
-
"learning_rate": 0.00019338662184273617,
|
| 58 |
-
"loss": 0.5383,
|
| 59 |
-
"step": 700
|
| 60 |
-
},
|
| 61 |
-
{
|
| 62 |
-
"epoch": 0.4266666666666667,
|
| 63 |
-
"grad_norm": 0.18242451548576355,
|
| 64 |
-
"learning_rate": 0.0001912241991190079,
|
| 65 |
-
"loss": 0.5563,
|
| 66 |
-
"step": 800
|
| 67 |
-
},
|
| 68 |
-
{
|
| 69 |
-
"epoch": 0.48,
|
| 70 |
-
"grad_norm": 0.2052665799856186,
|
| 71 |
-
"learning_rate": 0.0001887721720101592,
|
| 72 |
-
"loss": 0.5705,
|
| 73 |
-
"step": 900
|
| 74 |
-
},
|
| 75 |
-
{
|
| 76 |
-
"epoch": 0.5333333333333333,
|
| 77 |
-
"grad_norm": 0.27574437856674194,
|
| 78 |
-
"learning_rate": 0.00018603832483011145,
|
| 79 |
-
"loss": 0.5505,
|
| 80 |
-
"step": 1000
|
| 81 |
-
},
|
| 82 |
-
{
|
| 83 |
-
"epoch": 0.5866666666666667,
|
| 84 |
-
"grad_norm": 0.30421534180641174,
|
| 85 |
-
"learning_rate": 0.00018303133657127273,
|
| 86 |
-
"loss": 0.5265,
|
| 87 |
-
"step": 1100
|
| 88 |
-
},
|
| 89 |
-
{
|
| 90 |
-
"epoch": 0.64,
|
| 91 |
-
"grad_norm": 0.2369503527879715,
|
| 92 |
-
"learning_rate": 0.00017976075335182407,
|
| 93 |
-
"loss": 0.5407,
|
| 94 |
-
"step": 1200
|
| 95 |
-
},
|
| 96 |
-
{
|
| 97 |
-
"epoch": 0.6933333333333334,
|
| 98 |
-
"grad_norm": 0.29343071579933167,
|
| 99 |
-
"learning_rate": 0.0001762369581101898,
|
| 100 |
-
"loss": 0.5366,
|
| 101 |
-
"step": 1300
|
| 102 |
-
},
|
| 103 |
-
{
|
| 104 |
-
"epoch": 0.7466666666666667,
|
| 105 |
-
"grad_norm": 0.1794026792049408,
|
| 106 |
-
"learning_rate": 0.00017247113764290082,
|
| 107 |
-
"loss": 0.5745,
|
| 108 |
-
"step": 1400
|
| 109 |
-
},
|
| 110 |
-
{
|
| 111 |
-
"epoch": 0.8,
|
| 112 |
-
"grad_norm": 0.2688276469707489,
|
| 113 |
-
"learning_rate": 0.00016847524709049475,
|
| 114 |
-
"loss": 0.4972,
|
| 115 |
-
"step": 1500
|
| 116 |
-
},
|
| 117 |
-
{
|
| 118 |
-
"epoch": 0.8533333333333334,
|
| 119 |
-
"grad_norm": 0.17949211597442627,
|
| 120 |
-
"learning_rate": 0.0001642619719841971,
|
| 121 |
-
"loss": 0.543,
|
| 122 |
-
"step": 1600
|
| 123 |
-
},
|
| 124 |
-
{
|
| 125 |
-
"epoch": 0.9066666666666666,
|
| 126 |
-
"grad_norm": 0.24293017387390137,
|
| 127 |
-
"learning_rate": 0.0001598446879738714,
|
| 128 |
-
"loss": 0.5566,
|
| 129 |
-
"step": 1700
|
| 130 |
-
},
|
| 131 |
-
{
|
| 132 |
-
"epoch": 0.96,
|
| 133 |
-
"grad_norm": 0.17684029042720795,
|
| 134 |
-
"learning_rate": 0.00015523741836508866,
|
| 135 |
-
"loss": 0.5058,
|
| 136 |
-
"step": 1800
|
| 137 |
-
},
|
| 138 |
-
{
|
| 139 |
-
"epoch": 1.0133333333333334,
|
| 140 |
-
"grad_norm": 0.2043057680130005,
|
| 141 |
-
"learning_rate": 0.00015045478960011983,
|
| 142 |
-
"loss": 0.5232,
|
| 143 |
-
"step": 1900
|
| 144 |
-
},
|
| 145 |
-
{
|
| 146 |
-
"epoch": 1.0666666666666667,
|
| 147 |
-
"grad_norm": 0.21241049468517303,
|
| 148 |
-
"learning_rate": 0.00014551198482418425,
|
| 149 |
-
"loss": 0.4672,
|
| 150 |
-
"step": 2000
|
| 151 |
-
},
|
| 152 |
-
{
|
| 153 |
-
"epoch": 1.12,
|
| 154 |
-
"grad_norm": 0.2556317150592804,
|
| 155 |
-
"learning_rate": 0.00014042469568436382,
|
| 156 |
-
"loss": 0.4465,
|
| 157 |
-
"step": 2100
|
| 158 |
-
},
|
| 159 |
-
{
|
| 160 |
-
"epoch": 1.1733333333333333,
|
| 161 |
-
"grad_norm": 0.26184341311454773,
|
| 162 |
-
"learning_rate": 0.00013520907251420486,
|
| 163 |
-
"loss": 0.4223,
|
| 164 |
-
"step": 2200
|
| 165 |
-
},
|
| 166 |
-
{
|
| 167 |
-
"epoch": 1.2266666666666666,
|
| 168 |
-
"grad_norm": 0.39901483058929443,
|
| 169 |
-
"learning_rate": 0.00012988167306215355,
|
| 170 |
-
"loss": 0.4134,
|
| 171 |
-
"step": 2300
|
| 172 |
-
},
|
| 173 |
-
{
|
| 174 |
-
"epoch": 1.28,
|
| 175 |
-
"grad_norm": 0.2483246624469757,
|
| 176 |
-
"learning_rate": 0.00012445940992659383,
|
| 177 |
-
"loss": 0.4383,
|
| 178 |
-
"step": 2400
|
| 179 |
-
},
|
| 180 |
-
{
|
| 181 |
-
"epoch": 1.3333333333333333,
|
| 182 |
-
"grad_norm": 0.30793285369873047,
|
| 183 |
-
"learning_rate": 0.00011895949686436324,
|
| 184 |
-
"loss": 0.4512,
|
| 185 |
-
"step": 2500
|
| 186 |
-
},
|
| 187 |
-
{
|
| 188 |
-
"epoch": 1.3866666666666667,
|
| 189 |
-
"grad_norm": 0.21273203194141388,
|
| 190 |
-
"learning_rate": 0.00011339939414319763,
|
| 191 |
-
"loss": 0.4043,
|
| 192 |
-
"step": 2600
|
| 193 |
-
},
|
| 194 |
-
{
|
| 195 |
-
"epoch": 1.44,
|
| 196 |
-
"grad_norm": 0.21911175549030304,
|
| 197 |
-
"learning_rate": 0.00010779675311159134,
|
| 198 |
-
"loss": 0.4142,
|
| 199 |
-
"step": 2700
|
| 200 |
-
},
|
| 201 |
-
{
|
| 202 |
-
"epoch": 1.4933333333333334,
|
| 203 |
-
"grad_norm": 0.18140286207199097,
|
| 204 |
-
"learning_rate": 0.00010216936016204415,
|
| 205 |
-
"loss": 0.4625,
|
| 206 |
-
"step": 2800
|
| 207 |
-
},
|
| 208 |
-
{
|
| 209 |
-
"epoch": 1.5466666666666666,
|
| 210 |
-
"grad_norm": 0.26568442583084106,
|
| 211 |
-
"learning_rate": 9.653508026559144e-05,
|
| 212 |
-
"loss": 0.4615,
|
| 213 |
-
"step": 2900
|
| 214 |
-
},
|
| 215 |
-
{
|
| 216 |
-
"epoch": 1.6,
|
| 217 |
-
"grad_norm": 0.2561465799808502,
|
| 218 |
-
"learning_rate": 9.091180025687534e-05,
|
| 219 |
-
"loss": 0.4113,
|
| 220 |
-
"step": 3000
|
| 221 |
-
},
|
| 222 |
-
{
|
| 223 |
-
"epoch": 1.6533333333333333,
|
| 224 |
-
"grad_norm": 0.3138136565685272,
|
| 225 |
-
"learning_rate": 8.531737204980706e-05,
|
| 226 |
-
"loss": 0.4099,
|
| 227 |
-
"step": 3100
|
| 228 |
-
},
|
| 229 |
-
{
|
| 230 |
-
"epoch": 1.7066666666666666,
|
| 231 |
-
"grad_norm": 0.3352762758731842,
|
| 232 |
-
"learning_rate": 7.976955596408955e-05,
|
| 233 |
-
"loss": 0.4565,
|
| 234 |
-
"step": 3200
|
| 235 |
-
},
|
| 236 |
-
{
|
| 237 |
-
"epoch": 1.76,
|
| 238 |
-
"grad_norm": 0.26667091250419617,
|
| 239 |
-
"learning_rate": 7.428596434251988e-05,
|
| 240 |
-
"loss": 0.3972,
|
| 241 |
-
"step": 3300
|
| 242 |
-
},
|
| 243 |
-
{
|
| 244 |
-
"epoch": 1.8133333333333335,
|
| 245 |
-
"grad_norm": 0.31186443567276,
|
| 246 |
-
"learning_rate": 6.8884005638065e-05,
|
| 247 |
-
"loss": 0.3727,
|
| 248 |
-
"step": 3400
|
| 249 |
-
},
|
| 250 |
-
{
|
| 251 |
-
"epoch": 1.8666666666666667,
|
| 252 |
-
"grad_norm": 0.38279128074645996,
|
| 253 |
-
"learning_rate": 6.358082914821574e-05,
|
| 254 |
-
"loss": 0.4563,
|
| 255 |
-
"step": 3500
|
| 256 |
-
},
|
| 257 |
-
{
|
| 258 |
-
"epoch": 1.92,
|
| 259 |
-
"grad_norm": 0.27467605471611023,
|
| 260 |
-
"learning_rate": 5.839327057206678e-05,
|
| 261 |
-
"loss": 0.4258,
|
| 262 |
-
"step": 3600
|
| 263 |
-
},
|
| 264 |
-
{
|
| 265 |
-
"epoch": 1.9733333333333334,
|
| 266 |
-
"grad_norm": 0.2837699055671692,
|
| 267 |
-
"learning_rate": 5.33377985629605e-05,
|
| 268 |
-
"loss": 0.4553,
|
| 269 |
-
"step": 3700
|
| 270 |
-
},
|
| 271 |
-
{
|
| 272 |
-
"epoch": 2.026666666666667,
|
| 273 |
-
"grad_norm": 0.2614632844924927,
|
| 274 |
-
"learning_rate": 4.843046244637005e-05,
|
| 275 |
-
"loss": 0.374,
|
| 276 |
-
"step": 3800
|
| 277 |
-
},
|
| 278 |
-
{
|
| 279 |
-
"epoch": 2.08,
|
| 280 |
-
"grad_norm": 0.3883622884750366,
|
| 281 |
-
"learning_rate": 4.368684126899957e-05,
|
| 282 |
-
"loss": 0.3362,
|
| 283 |
-
"step": 3900
|
| 284 |
-
},
|
| 285 |
-
{
|
| 286 |
-
"epoch": 2.1333333333333333,
|
| 287 |
-
"grad_norm": 0.31639665365219116,
|
| 288 |
-
"learning_rate": 3.912199434085212e-05,
|
| 289 |
-
"loss": 0.327,
|
| 290 |
-
"step": 4000
|
| 291 |
-
},
|
| 292 |
-
{
|
| 293 |
-
"epoch": 2.1866666666666665,
|
| 294 |
-
"grad_norm": 0.361616313457489,
|
| 295 |
-
"learning_rate": 3.475041342727693e-05,
|
| 296 |
-
"loss": 0.3119,
|
| 297 |
-
"step": 4100
|
| 298 |
-
},
|
| 299 |
-
{
|
| 300 |
-
"epoch": 2.24,
|
| 301 |
-
"grad_norm": 0.2547502815723419,
|
| 302 |
-
"learning_rate": 3.0585976742768554e-05,
|
| 303 |
-
"loss": 0.3271,
|
| 304 |
-
"step": 4200
|
| 305 |
-
},
|
| 306 |
-
{
|
| 307 |
-
"epoch": 2.2933333333333334,
|
| 308 |
-
"grad_norm": 0.2862648367881775,
|
| 309 |
-
"learning_rate": 2.6641904892572556e-05,
|
| 310 |
-
"loss": 0.3443,
|
| 311 |
-
"step": 4300
|
| 312 |
-
},
|
| 313 |
-
{
|
| 314 |
-
"epoch": 2.3466666666666667,
|
| 315 |
-
"grad_norm": 0.3456701338291168,
|
| 316 |
-
"learning_rate": 2.2930718901966042e-05,
|
| 317 |
-
"loss": 0.3044,
|
| 318 |
-
"step": 4400
|
| 319 |
-
},
|
| 320 |
-
{
|
| 321 |
-
"epoch": 2.4,
|
| 322 |
-
"grad_norm": 0.44919243454933167,
|
| 323 |
-
"learning_rate": 1.946420046645574e-05,
|
| 324 |
-
"loss": 0.34,
|
| 325 |
-
"step": 4500
|
| 326 |
-
},
|
| 327 |
-
{
|
| 328 |
-
"epoch": 2.453333333333333,
|
| 329 |
-
"grad_norm": 0.2444528192281723,
|
| 330 |
-
"learning_rate": 1.625335454908574e-05,
|
| 331 |
-
"loss": 0.3477,
|
| 332 |
-
"step": 4600
|
| 333 |
-
},
|
| 334 |
-
{
|
| 335 |
-
"epoch": 2.506666666666667,
|
| 336 |
-
"grad_norm": 0.24498413503170013,
|
| 337 |
-
"learning_rate": 1.3308374443593851e-05,
|
| 338 |
-
"loss": 0.3403,
|
| 339 |
-
"step": 4700
|
| 340 |
-
},
|
| 341 |
-
{
|
| 342 |
-
"epoch": 2.56,
|
| 343 |
-
"grad_norm": 0.4272463321685791,
|
| 344 |
-
"learning_rate": 1.0638609414329625e-05,
|
| 345 |
-
"loss": 0.2954,
|
| 346 |
-
"step": 4800
|
| 347 |
}
|
| 348 |
],
|
| 349 |
"logging_steps": 100,
|
|
@@ -363,7 +48,7 @@
|
|
| 363 |
"attributes": {}
|
| 364 |
}
|
| 365 |
},
|
| 366 |
-
"total_flos":
|
| 367 |
"train_batch_size": 2,
|
| 368 |
"trial_name": null,
|
| 369 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.16,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 300,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
"epoch": 0.05333333333333334,
|
| 14 |
+
"grad_norm": 0.23234646022319794,
|
| 15 |
"learning_rate": 0.00019996188073020713,
|
| 16 |
+
"loss": 0.712,
|
| 17 |
"step": 100
|
| 18 |
},
|
| 19 |
{
|
| 20 |
"epoch": 0.10666666666666667,
|
| 21 |
+
"grad_norm": 0.2066359966993332,
|
| 22 |
"learning_rate": 0.00019964771237806272,
|
| 23 |
+
"loss": 0.5661,
|
| 24 |
"step": 200
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 0.16,
|
| 28 |
+
"grad_norm": 0.14829668402671814,
|
| 29 |
"learning_rate": 0.0001990171979823181,
|
| 30 |
+
"loss": 0.5721,
|
| 31 |
"step": 300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
}
|
| 33 |
],
|
| 34 |
"logging_steps": 100,
|
|
|
|
| 48 |
"attributes": {}
|
| 49 |
}
|
| 50 |
},
|
| 51 |
+
"total_flos": 3.106400242323456e+16,
|
| 52 |
"train_batch_size": 2,
|
| 53 |
"trial_name": null,
|
| 54 |
"trial_params": null
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6097
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a586cb12f3d9ab0c60acbb1fea8c67cedd0908b4df110bb2a98fc6c01da2716c
|
| 3 |
size 6097
|