Training in progress, step 50, checkpoint
Browse files- last-checkpoint/model-00001-of-00002.safetensors +1 -1
- last-checkpoint/model-00002-of-00002.safetensors +1 -1
- last-checkpoint/optimizer.pt +2 -2
- last-checkpoint/rng_state_0.pth +3 -0
- last-checkpoint/rng_state_1.pth +3 -0
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +38 -291
- last-checkpoint/training_args.bin +2 -2
last-checkpoint/model-00001-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4972163696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:826e66b930379b9b17d06e3e36abceae89de64258529cf378786e7914578f2d6
|
| 3 |
size 4972163696
|
last-checkpoint/model-00002-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2669366920
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e2037f966379e933b0ee4ec2c31021e10d1bac8c66ea2bd6a5ed50ad79df2c79
|
| 3 |
size 2669366920
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:35811abfb416c04cf69a2ba0e185844b311fd958ed4b56f97e8f58a9aea3a136
|
| 3 |
+
size 7762295162
|
last-checkpoint/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2667eee8d875561f6539074432e0dd0e4895799b436b03ff4f88447a79b23c54
|
| 3 |
+
size 14512
|
last-checkpoint/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f453d97040b5753e846b52c3f3f2ec936ae564e3d843c2334ebea047a9d227d
|
| 3 |
+
size 14512
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aefbcebbcca874264bb329f31301bfa219bc90bffbd18b02b072517f20157778
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,323 +1,70 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
-
"eval_steps":
|
| 6 |
-
"global_step":
|
| 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.
|
| 13 |
-
"eval_loss": 2.
|
| 14 |
-
"eval_runtime":
|
| 15 |
-
"eval_samples_per_second":
|
| 16 |
-
"eval_steps_per_second":
|
| 17 |
"step": 1
|
| 18 |
},
|
| 19 |
{
|
| 20 |
-
"epoch": 0.
|
| 21 |
-
"grad_norm":
|
| 22 |
-
"learning_rate":
|
| 23 |
-
"loss": 1.
|
| 24 |
"step": 10
|
| 25 |
},
|
| 26 |
{
|
| 27 |
-
"epoch": 0.
|
| 28 |
-
"grad_norm":
|
| 29 |
-
"learning_rate":
|
| 30 |
-
"loss": 1.
|
| 31 |
"step": 20
|
| 32 |
},
|
| 33 |
{
|
| 34 |
-
"epoch": 0.
|
| 35 |
-
"grad_norm":
|
| 36 |
-
"learning_rate":
|
| 37 |
-
"loss": 1.
|
| 38 |
"step": 30
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch": 0.
|
| 42 |
-
"grad_norm":
|
| 43 |
-
"learning_rate":
|
| 44 |
-
"loss": 1.
|
| 45 |
"step": 40
|
| 46 |
},
|
| 47 |
{
|
| 48 |
-
"epoch": 0.
|
| 49 |
-
"grad_norm":
|
| 50 |
-
"learning_rate":
|
| 51 |
-
"loss": 1.
|
| 52 |
"step": 50
|
| 53 |
},
|
| 54 |
{
|
| 55 |
-
"epoch": 0.
|
| 56 |
-
"
|
| 57 |
-
"
|
| 58 |
-
"
|
| 59 |
-
"
|
| 60 |
-
|
| 61 |
-
{
|
| 62 |
-
"epoch": 0.020716188221367268,
|
| 63 |
-
"grad_norm": 7.3125,
|
| 64 |
-
"learning_rate": 0.00011200000000000001,
|
| 65 |
-
"loss": 1.5509,
|
| 66 |
-
"step": 70
|
| 67 |
-
},
|
| 68 |
-
{
|
| 69 |
-
"epoch": 0.02367564368156259,
|
| 70 |
-
"grad_norm": 9.75,
|
| 71 |
-
"learning_rate": 0.00012800000000000002,
|
| 72 |
-
"loss": 1.5801,
|
| 73 |
-
"step": 80
|
| 74 |
-
},
|
| 75 |
-
{
|
| 76 |
-
"epoch": 0.026635099141757917,
|
| 77 |
-
"grad_norm": 13.4375,
|
| 78 |
-
"learning_rate": 0.000144,
|
| 79 |
-
"loss": 1.5691,
|
| 80 |
-
"step": 90
|
| 81 |
-
},
|
| 82 |
-
{
|
| 83 |
-
"epoch": 0.02959455460195324,
|
| 84 |
-
"grad_norm": 64.0,
|
| 85 |
-
"learning_rate": 0.00016,
|
| 86 |
-
"loss": 1.9617,
|
| 87 |
-
"step": 100
|
| 88 |
-
},
|
| 89 |
-
{
|
| 90 |
-
"epoch": 0.032554010062148565,
|
| 91 |
-
"grad_norm": 8.125,
|
| 92 |
-
"learning_rate": 0.00017600000000000002,
|
| 93 |
-
"loss": 2.1875,
|
| 94 |
-
"step": 110
|
| 95 |
-
},
|
| 96 |
-
{
|
| 97 |
-
"epoch": 0.03551346552234389,
|
| 98 |
-
"grad_norm": 7.125,
|
| 99 |
-
"learning_rate": 0.000192,
|
| 100 |
-
"loss": 1.9646,
|
| 101 |
-
"step": 120
|
| 102 |
-
},
|
| 103 |
-
{
|
| 104 |
-
"epoch": 0.03847292098253921,
|
| 105 |
-
"grad_norm": 12.4375,
|
| 106 |
-
"learning_rate": 0.0001999978128380225,
|
| 107 |
-
"loss": 2.0544,
|
| 108 |
-
"step": 130
|
| 109 |
-
},
|
| 110 |
-
{
|
| 111 |
-
"epoch": 0.041432376442734536,
|
| 112 |
-
"grad_norm": 29.125,
|
| 113 |
-
"learning_rate": 0.0001999803161162393,
|
| 114 |
-
"loss": 2.2508,
|
| 115 |
-
"step": 140
|
| 116 |
-
},
|
| 117 |
-
{
|
| 118 |
-
"epoch": 0.04439183190292986,
|
| 119 |
-
"grad_norm": 19.25,
|
| 120 |
-
"learning_rate": 0.00019994532573409262,
|
| 121 |
-
"loss": 2.3878,
|
| 122 |
-
"step": 150
|
| 123 |
-
},
|
| 124 |
-
{
|
| 125 |
-
"epoch": 0.04735128736312518,
|
| 126 |
-
"grad_norm": 5.59375,
|
| 127 |
-
"learning_rate": 0.00019989284781388617,
|
| 128 |
-
"loss": 2.3223,
|
| 129 |
-
"step": 160
|
| 130 |
-
},
|
| 131 |
-
{
|
| 132 |
-
"epoch": 0.05031074282332051,
|
| 133 |
-
"grad_norm": 9.5625,
|
| 134 |
-
"learning_rate": 0.00019982289153773646,
|
| 135 |
-
"loss": 2.2869,
|
| 136 |
-
"step": 170
|
| 137 |
-
},
|
| 138 |
-
{
|
| 139 |
-
"epoch": 0.053270198283515834,
|
| 140 |
-
"grad_norm": 9.875,
|
| 141 |
-
"learning_rate": 0.00019973546914596623,
|
| 142 |
-
"loss": 2.2861,
|
| 143 |
-
"step": 180
|
| 144 |
-
},
|
| 145 |
-
{
|
| 146 |
-
"epoch": 0.05622965374371116,
|
| 147 |
-
"grad_norm": 27.5,
|
| 148 |
-
"learning_rate": 0.00019963059593496268,
|
| 149 |
-
"loss": 2.4016,
|
| 150 |
-
"step": 190
|
| 151 |
-
},
|
| 152 |
-
{
|
| 153 |
-
"epoch": 0.05918910920390648,
|
| 154 |
-
"grad_norm": 24.0,
|
| 155 |
-
"learning_rate": 0.00019950829025450114,
|
| 156 |
-
"loss": 2.8436,
|
| 157 |
-
"step": 200
|
| 158 |
-
},
|
| 159 |
-
{
|
| 160 |
-
"epoch": 0.05918910920390648,
|
| 161 |
-
"eval_loss": 2.5731241703033447,
|
| 162 |
-
"eval_runtime": 121.8212,
|
| 163 |
-
"eval_samples_per_second": 12.33,
|
| 164 |
-
"eval_steps_per_second": 3.086,
|
| 165 |
-
"step": 200
|
| 166 |
-
},
|
| 167 |
-
{
|
| 168 |
-
"epoch": 0.062148564664101805,
|
| 169 |
-
"grad_norm": 6.03125,
|
| 170 |
-
"learning_rate": 0.0001993685735045343,
|
| 171 |
-
"loss": 2.4605,
|
| 172 |
-
"step": 210
|
| 173 |
-
},
|
| 174 |
-
{
|
| 175 |
-
"epoch": 0.06510802012429713,
|
| 176 |
-
"grad_norm": 10.1875,
|
| 177 |
-
"learning_rate": 0.0001992114701314478,
|
| 178 |
-
"loss": 2.3989,
|
| 179 |
-
"step": 220
|
| 180 |
-
},
|
| 181 |
-
{
|
| 182 |
-
"epoch": 0.06806747558449246,
|
| 183 |
-
"grad_norm": 7.625,
|
| 184 |
-
"learning_rate": 0.000199037007623783,
|
| 185 |
-
"loss": 2.5254,
|
| 186 |
-
"step": 230
|
| 187 |
-
},
|
| 188 |
-
{
|
| 189 |
-
"epoch": 0.07102693104468778,
|
| 190 |
-
"grad_norm": 10.0,
|
| 191 |
-
"learning_rate": 0.00019884521650742715,
|
| 192 |
-
"loss": 2.4139,
|
| 193 |
-
"step": 240
|
| 194 |
-
},
|
| 195 |
-
{
|
| 196 |
-
"epoch": 0.0739863865048831,
|
| 197 |
-
"grad_norm": 62.0,
|
| 198 |
-
"learning_rate": 0.00019863613034027224,
|
| 199 |
-
"loss": 2.7548,
|
| 200 |
-
"step": 250
|
| 201 |
-
},
|
| 202 |
-
{
|
| 203 |
-
"epoch": 0.07694584196507842,
|
| 204 |
-
"grad_norm": 6.8125,
|
| 205 |
-
"learning_rate": 0.0001984097857063434,
|
| 206 |
-
"loss": 2.512,
|
| 207 |
-
"step": 260
|
| 208 |
-
},
|
| 209 |
-
{
|
| 210 |
-
"epoch": 0.07990529742527375,
|
| 211 |
-
"grad_norm": 5.9375,
|
| 212 |
-
"learning_rate": 0.0001981662222093976,
|
| 213 |
-
"loss": 2.5735,
|
| 214 |
-
"step": 270
|
| 215 |
-
},
|
| 216 |
-
{
|
| 217 |
-
"epoch": 0.08286475288546907,
|
| 218 |
-
"grad_norm": 10.75,
|
| 219 |
-
"learning_rate": 0.00019790548246599447,
|
| 220 |
-
"loss": 2.4225,
|
| 221 |
-
"step": 280
|
| 222 |
-
},
|
| 223 |
-
{
|
| 224 |
-
"epoch": 0.0858242083456644,
|
| 225 |
-
"grad_norm": 40.25,
|
| 226 |
-
"learning_rate": 0.00019762761209803927,
|
| 227 |
-
"loss": 2.6627,
|
| 228 |
-
"step": 290
|
| 229 |
-
},
|
| 230 |
-
{
|
| 231 |
-
"epoch": 0.08878366380585972,
|
| 232 |
-
"grad_norm": 34.5,
|
| 233 |
-
"learning_rate": 0.0001973326597248006,
|
| 234 |
-
"loss": 2.8292,
|
| 235 |
-
"step": 300
|
| 236 |
-
},
|
| 237 |
-
{
|
| 238 |
-
"epoch": 0.09174311926605505,
|
| 239 |
-
"grad_norm": 5.3125,
|
| 240 |
-
"learning_rate": 0.00019702067695440332,
|
| 241 |
-
"loss": 2.6395,
|
| 242 |
-
"step": 310
|
| 243 |
-
},
|
| 244 |
-
{
|
| 245 |
-
"epoch": 0.09470257472625036,
|
| 246 |
-
"grad_norm": 5.28125,
|
| 247 |
-
"learning_rate": 0.00019669171837479873,
|
| 248 |
-
"loss": 2.3439,
|
| 249 |
-
"step": 320
|
| 250 |
-
},
|
| 251 |
-
{
|
| 252 |
-
"epoch": 0.09766203018644569,
|
| 253 |
-
"grad_norm": 6.34375,
|
| 254 |
-
"learning_rate": 0.00019634584154421317,
|
| 255 |
-
"loss": 2.518,
|
| 256 |
-
"step": 330
|
| 257 |
-
},
|
| 258 |
-
{
|
| 259 |
-
"epoch": 0.10062148564664102,
|
| 260 |
-
"grad_norm": 11.125,
|
| 261 |
-
"learning_rate": 0.00019598310698107702,
|
| 262 |
-
"loss": 2.5213,
|
| 263 |
-
"step": 340
|
| 264 |
-
},
|
| 265 |
-
{
|
| 266 |
-
"epoch": 0.10358094110683634,
|
| 267 |
-
"grad_norm": 21.375,
|
| 268 |
-
"learning_rate": 0.00019560357815343577,
|
| 269 |
-
"loss": 2.4462,
|
| 270 |
-
"step": 350
|
| 271 |
-
},
|
| 272 |
-
{
|
| 273 |
-
"epoch": 0.10654039656703167,
|
| 274 |
-
"grad_norm": 5.625,
|
| 275 |
-
"learning_rate": 0.00019520732146784491,
|
| 276 |
-
"loss": 2.7193,
|
| 277 |
-
"step": 360
|
| 278 |
-
},
|
| 279 |
-
{
|
| 280 |
-
"epoch": 0.109499852027227,
|
| 281 |
-
"grad_norm": 6.96875,
|
| 282 |
-
"learning_rate": 0.0001947944062577507,
|
| 283 |
-
"loss": 2.3469,
|
| 284 |
-
"step": 370
|
| 285 |
-
},
|
| 286 |
-
{
|
| 287 |
-
"epoch": 0.11245930748742232,
|
| 288 |
-
"grad_norm": 12.6875,
|
| 289 |
-
"learning_rate": 0.00019436490477135878,
|
| 290 |
-
"loss": 2.7748,
|
| 291 |
-
"step": 380
|
| 292 |
-
},
|
| 293 |
-
{
|
| 294 |
-
"epoch": 0.11541876294761765,
|
| 295 |
-
"grad_norm": 7.84375,
|
| 296 |
-
"learning_rate": 0.00019391889215899299,
|
| 297 |
-
"loss": 2.6912,
|
| 298 |
-
"step": 390
|
| 299 |
-
},
|
| 300 |
-
{
|
| 301 |
-
"epoch": 0.11837821840781296,
|
| 302 |
-
"grad_norm": 22.875,
|
| 303 |
-
"learning_rate": 0.0001934564464599461,
|
| 304 |
-
"loss": 2.0167,
|
| 305 |
-
"step": 400
|
| 306 |
-
},
|
| 307 |
-
{
|
| 308 |
-
"epoch": 0.11837821840781296,
|
| 309 |
-
"eval_loss": 3.1852574348449707,
|
| 310 |
-
"eval_runtime": 121.7205,
|
| 311 |
-
"eval_samples_per_second": 12.34,
|
| 312 |
-
"eval_steps_per_second": 3.089,
|
| 313 |
-
"step": 400
|
| 314 |
}
|
| 315 |
],
|
| 316 |
"logging_steps": 10,
|
| 317 |
-
"max_steps":
|
| 318 |
"num_input_tokens_seen": 0,
|
| 319 |
-
"num_train_epochs":
|
| 320 |
-
"save_steps":
|
| 321 |
"stateful_callbacks": {
|
| 322 |
"TrainerControl": {
|
| 323 |
"args": {
|
|
@@ -330,7 +77,7 @@
|
|
| 330 |
"attributes": {}
|
| 331 |
}
|
| 332 |
},
|
| 333 |
-
"total_flos":
|
| 334 |
"train_batch_size": 4,
|
| 335 |
"trial_name": null,
|
| 336 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.4716981132075472,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 50,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.009433962264150943,
|
| 13 |
+
"eval_loss": 2.0827555656433105,
|
| 14 |
+
"eval_runtime": 40.6076,
|
| 15 |
+
"eval_samples_per_second": 36.963,
|
| 16 |
+
"eval_steps_per_second": 4.63,
|
| 17 |
"step": 1
|
| 18 |
},
|
| 19 |
{
|
| 20 |
+
"epoch": 0.09433962264150944,
|
| 21 |
+
"grad_norm": 2.671875,
|
| 22 |
+
"learning_rate": 3.0769230769230774e-05,
|
| 23 |
+
"loss": 1.8571,
|
| 24 |
"step": 10
|
| 25 |
},
|
| 26 |
{
|
| 27 |
+
"epoch": 0.18867924528301888,
|
| 28 |
+
"grad_norm": 1.4609375,
|
| 29 |
+
"learning_rate": 6.153846153846155e-05,
|
| 30 |
+
"loss": 1.6978,
|
| 31 |
"step": 20
|
| 32 |
},
|
| 33 |
{
|
| 34 |
+
"epoch": 0.2830188679245283,
|
| 35 |
+
"grad_norm": 1.65625,
|
| 36 |
+
"learning_rate": 9.230769230769232e-05,
|
| 37 |
+
"loss": 1.6459,
|
| 38 |
"step": 30
|
| 39 |
},
|
| 40 |
{
|
| 41 |
+
"epoch": 0.37735849056603776,
|
| 42 |
+
"grad_norm": 1.4296875,
|
| 43 |
+
"learning_rate": 0.0001230769230769231,
|
| 44 |
+
"loss": 1.6934,
|
| 45 |
"step": 40
|
| 46 |
},
|
| 47 |
{
|
| 48 |
+
"epoch": 0.4716981132075472,
|
| 49 |
+
"grad_norm": 1.5,
|
| 50 |
+
"learning_rate": 0.00015384615384615385,
|
| 51 |
+
"loss": 1.8091,
|
| 52 |
"step": 50
|
| 53 |
},
|
| 54 |
{
|
| 55 |
+
"epoch": 0.4716981132075472,
|
| 56 |
+
"eval_loss": 1.5812501907348633,
|
| 57 |
+
"eval_runtime": 39.1264,
|
| 58 |
+
"eval_samples_per_second": 38.363,
|
| 59 |
+
"eval_steps_per_second": 4.805,
|
| 60 |
+
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 61 |
}
|
| 62 |
],
|
| 63 |
"logging_steps": 10,
|
| 64 |
+
"max_steps": 1300,
|
| 65 |
"num_input_tokens_seen": 0,
|
| 66 |
+
"num_train_epochs": 13,
|
| 67 |
+
"save_steps": 50,
|
| 68 |
"stateful_callbacks": {
|
| 69 |
"TrainerControl": {
|
| 70 |
"args": {
|
|
|
|
| 77 |
"attributes": {}
|
| 78 |
}
|
| 79 |
},
|
| 80 |
+
"total_flos": 1.82964197523456e+16,
|
| 81 |
"train_batch_size": 4,
|
| 82 |
"trial_name": null,
|
| 83 |
"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
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e4320434255846d7d3d8916bcc913b473a3b0890bc89a39d373bf3ce9e989285
|
| 3 |
+
size 7096
|