Commit
·
6498a09
1
Parent(s):
e7c3284
Training in progress, step 24576
Browse files- checkpoint-114688/config.json +0 -32
- checkpoint-114688/optimizer.pt +0 -3
- checkpoint-114688/pytorch_model.bin +0 -3
- checkpoint-114688/rng_state.pth +0 -3
- checkpoint-114688/scaler.pt +0 -3
- checkpoint-114688/scheduler.pt +0 -3
- checkpoint-114688/trainer_state.json +0 -800
- checkpoint-114688/training_args.bin +0 -3
- pytorch_model.bin +1 -1
checkpoint-114688/config.json
DELETED
|
@@ -1,32 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"activation_function": "gelu_new",
|
| 3 |
-
"architectures": [
|
| 4 |
-
"GPT2LMHeadModel"
|
| 5 |
-
],
|
| 6 |
-
"attn_pdrop": 0.1,
|
| 7 |
-
"bos_token_id": 50256,
|
| 8 |
-
"embd_pdrop": 0.1,
|
| 9 |
-
"eos_token_id": 50256,
|
| 10 |
-
"initializer_range": 0.02,
|
| 11 |
-
"layer_norm_epsilon": 1e-05,
|
| 12 |
-
"model_type": "gpt2",
|
| 13 |
-
"n_embd": 512,
|
| 14 |
-
"n_head": 8,
|
| 15 |
-
"n_inner": null,
|
| 16 |
-
"n_layer": 8,
|
| 17 |
-
"n_positions": 2048,
|
| 18 |
-
"pad_token_id": 1,
|
| 19 |
-
"reorder_and_upcast_attn": false,
|
| 20 |
-
"resid_pdrop": 0.1,
|
| 21 |
-
"scale_attn_by_inverse_layer_idx": false,
|
| 22 |
-
"scale_attn_weights": true,
|
| 23 |
-
"summary_activation": null,
|
| 24 |
-
"summary_first_dropout": 0.1,
|
| 25 |
-
"summary_proj_to_labels": true,
|
| 26 |
-
"summary_type": "cls_index",
|
| 27 |
-
"summary_use_proj": true,
|
| 28 |
-
"torch_dtype": "float32",
|
| 29 |
-
"transformers_version": "4.26.0.dev0",
|
| 30 |
-
"use_cache": true,
|
| 31 |
-
"vocab_size": 299
|
| 32 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-114688/optimizer.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:b68c6edb60414cfe637e2ec074a5f4acec75f5337e31730978b158998228eac5
|
| 3 |
-
size 211432837
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-114688/pytorch_model.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:6849dc98fcc9e4181c102fa0bb6dd1d70c54edae9d1a8440b604c6f98ba117b4
|
| 3 |
-
size 139279005
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-114688/rng_state.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:dc866ce242256f98027b6016930d35e9d45293516285c23fdbadea7b58591d8a
|
| 3 |
-
size 15597
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-114688/scaler.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:9778e4932801d6fcefc7836eddd9fd5635b262a07b6eb7a75700d5c35643bb19
|
| 3 |
-
size 557
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-114688/scheduler.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:2fa9e591dbfa043fe5b9503f81bacab889f557e7055edb15e3594fae6f28701b
|
| 3 |
-
size 627
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-114688/trainer_state.json
DELETED
|
@@ -1,800 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_metric": null,
|
| 3 |
-
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 7.735599622285175,
|
| 5 |
-
"global_step": 114688,
|
| 6 |
-
"is_hyper_param_search": false,
|
| 7 |
-
"is_local_process_zero": true,
|
| 8 |
-
"is_world_process_zero": true,
|
| 9 |
-
"log_history": [
|
| 10 |
-
{
|
| 11 |
-
"epoch": 0.14,
|
| 12 |
-
"learning_rate": 0.00020480000000000002,
|
| 13 |
-
"loss": 2.1719,
|
| 14 |
-
"step": 2048
|
| 15 |
-
},
|
| 16 |
-
{
|
| 17 |
-
"epoch": 0.14,
|
| 18 |
-
"eval_loss": 1.0833024978637695,
|
| 19 |
-
"eval_runtime": 15.7887,
|
| 20 |
-
"eval_samples_per_second": 132.5,
|
| 21 |
-
"eval_steps_per_second": 8.297,
|
| 22 |
-
"step": 2048
|
| 23 |
-
},
|
| 24 |
-
{
|
| 25 |
-
"epoch": 0.28,
|
| 26 |
-
"learning_rate": 0.00040960000000000004,
|
| 27 |
-
"loss": 0.9468,
|
| 28 |
-
"step": 4096
|
| 29 |
-
},
|
| 30 |
-
{
|
| 31 |
-
"epoch": 0.28,
|
| 32 |
-
"eval_loss": 0.8000818490982056,
|
| 33 |
-
"eval_runtime": 17.2632,
|
| 34 |
-
"eval_samples_per_second": 121.183,
|
| 35 |
-
"eval_steps_per_second": 7.588,
|
| 36 |
-
"step": 4096
|
| 37 |
-
},
|
| 38 |
-
{
|
| 39 |
-
"epoch": 0.41,
|
| 40 |
-
"learning_rate": 0.0004998749142723946,
|
| 41 |
-
"loss": 0.7542,
|
| 42 |
-
"step": 6144
|
| 43 |
-
},
|
| 44 |
-
{
|
| 45 |
-
"epoch": 0.41,
|
| 46 |
-
"eval_loss": 0.7439925074577332,
|
| 47 |
-
"eval_runtime": 17.4134,
|
| 48 |
-
"eval_samples_per_second": 120.138,
|
| 49 |
-
"eval_steps_per_second": 7.523,
|
| 50 |
-
"step": 6144
|
| 51 |
-
},
|
| 52 |
-
{
|
| 53 |
-
"epoch": 0.55,
|
| 54 |
-
"learning_rate": 0.0004990273340312486,
|
| 55 |
-
"loss": 0.6756,
|
| 56 |
-
"step": 8192
|
| 57 |
-
},
|
| 58 |
-
{
|
| 59 |
-
"epoch": 0.55,
|
| 60 |
-
"eval_loss": 0.7018134593963623,
|
| 61 |
-
"eval_runtime": 15.8601,
|
| 62 |
-
"eval_samples_per_second": 131.904,
|
| 63 |
-
"eval_steps_per_second": 8.26,
|
| 64 |
-
"step": 8192
|
| 65 |
-
},
|
| 66 |
-
{
|
| 67 |
-
"epoch": 0.69,
|
| 68 |
-
"learning_rate": 0.0004973820371438889,
|
| 69 |
-
"loss": 0.631,
|
| 70 |
-
"step": 10240
|
| 71 |
-
},
|
| 72 |
-
{
|
| 73 |
-
"epoch": 0.69,
|
| 74 |
-
"eval_loss": 0.684688925743103,
|
| 75 |
-
"eval_runtime": 18.0314,
|
| 76 |
-
"eval_samples_per_second": 116.02,
|
| 77 |
-
"eval_steps_per_second": 7.265,
|
| 78 |
-
"step": 10240
|
| 79 |
-
},
|
| 80 |
-
{
|
| 81 |
-
"epoch": 0.83,
|
| 82 |
-
"learning_rate": 0.0004949442940386407,
|
| 83 |
-
"loss": 0.5989,
|
| 84 |
-
"step": 12288
|
| 85 |
-
},
|
| 86 |
-
{
|
| 87 |
-
"epoch": 0.83,
|
| 88 |
-
"eval_loss": 0.6822534203529358,
|
| 89 |
-
"eval_runtime": 17.4182,
|
| 90 |
-
"eval_samples_per_second": 120.104,
|
| 91 |
-
"eval_steps_per_second": 7.521,
|
| 92 |
-
"step": 12288
|
| 93 |
-
},
|
| 94 |
-
{
|
| 95 |
-
"epoch": 0.97,
|
| 96 |
-
"learning_rate": 0.0004917201492451735,
|
| 97 |
-
"loss": 0.5776,
|
| 98 |
-
"step": 14336
|
| 99 |
-
},
|
| 100 |
-
{
|
| 101 |
-
"epoch": 0.97,
|
| 102 |
-
"eval_loss": 0.6674544215202332,
|
| 103 |
-
"eval_runtime": 17.7487,
|
| 104 |
-
"eval_samples_per_second": 117.868,
|
| 105 |
-
"eval_steps_per_second": 7.381,
|
| 106 |
-
"step": 14336
|
| 107 |
-
},
|
| 108 |
-
{
|
| 109 |
-
"epoch": 1.11,
|
| 110 |
-
"learning_rate": 0.0004877230785006913,
|
| 111 |
-
"loss": 0.5525,
|
| 112 |
-
"step": 16384
|
| 113 |
-
},
|
| 114 |
-
{
|
| 115 |
-
"epoch": 1.11,
|
| 116 |
-
"eval_loss": 0.6640163660049438,
|
| 117 |
-
"eval_runtime": 15.8951,
|
| 118 |
-
"eval_samples_per_second": 131.613,
|
| 119 |
-
"eval_steps_per_second": 8.242,
|
| 120 |
-
"step": 16384
|
| 121 |
-
},
|
| 122 |
-
{
|
| 123 |
-
"epoch": 1.24,
|
| 124 |
-
"learning_rate": 0.0004829670105577666,
|
| 125 |
-
"loss": 0.5373,
|
| 126 |
-
"step": 18432
|
| 127 |
-
},
|
| 128 |
-
{
|
| 129 |
-
"epoch": 1.24,
|
| 130 |
-
"eval_loss": 0.6663170456886292,
|
| 131 |
-
"eval_runtime": 17.5,
|
| 132 |
-
"eval_samples_per_second": 119.543,
|
| 133 |
-
"eval_steps_per_second": 7.486,
|
| 134 |
-
"step": 18432
|
| 135 |
-
},
|
| 136 |
-
{
|
| 137 |
-
"epoch": 1.38,
|
| 138 |
-
"learning_rate": 0.0004774596641323791,
|
| 139 |
-
"loss": 0.5261,
|
| 140 |
-
"step": 20480
|
| 141 |
-
},
|
| 142 |
-
{
|
| 143 |
-
"epoch": 1.38,
|
| 144 |
-
"eval_loss": 0.6518951654434204,
|
| 145 |
-
"eval_runtime": 17.1326,
|
| 146 |
-
"eval_samples_per_second": 122.107,
|
| 147 |
-
"eval_steps_per_second": 7.646,
|
| 148 |
-
"step": 20480
|
| 149 |
-
},
|
| 150 |
-
{
|
| 151 |
-
"epoch": 1.52,
|
| 152 |
-
"learning_rate": 0.0004712261976082475,
|
| 153 |
-
"loss": 0.5115,
|
| 154 |
-
"step": 22528
|
| 155 |
-
},
|
| 156 |
-
{
|
| 157 |
-
"epoch": 1.52,
|
| 158 |
-
"eval_loss": 0.6658991575241089,
|
| 159 |
-
"eval_runtime": 17.6874,
|
| 160 |
-
"eval_samples_per_second": 118.277,
|
| 161 |
-
"eval_steps_per_second": 7.406,
|
| 162 |
-
"step": 22528
|
| 163 |
-
},
|
| 164 |
-
{
|
| 165 |
-
"epoch": 1.66,
|
| 166 |
-
"learning_rate": 0.00046428407064289515,
|
| 167 |
-
"loss": 0.5033,
|
| 168 |
-
"step": 24576
|
| 169 |
-
},
|
| 170 |
-
{
|
| 171 |
-
"epoch": 1.66,
|
| 172 |
-
"eval_loss": 0.6602604389190674,
|
| 173 |
-
"eval_runtime": 15.8845,
|
| 174 |
-
"eval_samples_per_second": 131.701,
|
| 175 |
-
"eval_steps_per_second": 8.247,
|
| 176 |
-
"step": 24576
|
| 177 |
-
},
|
| 178 |
-
{
|
| 179 |
-
"epoch": 1.8,
|
| 180 |
-
"learning_rate": 0.00045665163060732317,
|
| 181 |
-
"loss": 0.4925,
|
| 182 |
-
"step": 26624
|
| 183 |
-
},
|
| 184 |
-
{
|
| 185 |
-
"epoch": 1.8,
|
| 186 |
-
"eval_loss": 0.6551440954208374,
|
| 187 |
-
"eval_runtime": 17.7902,
|
| 188 |
-
"eval_samples_per_second": 117.593,
|
| 189 |
-
"eval_steps_per_second": 7.364,
|
| 190 |
-
"step": 26624
|
| 191 |
-
},
|
| 192 |
-
{
|
| 193 |
-
"epoch": 1.93,
|
| 194 |
-
"learning_rate": 0.000448360778288479,
|
| 195 |
-
"loss": 0.4868,
|
| 196 |
-
"step": 28672
|
| 197 |
-
},
|
| 198 |
-
{
|
| 199 |
-
"epoch": 1.93,
|
| 200 |
-
"eval_loss": 0.6580803394317627,
|
| 201 |
-
"eval_runtime": 15.7841,
|
| 202 |
-
"eval_samples_per_second": 132.538,
|
| 203 |
-
"eval_steps_per_second": 8.299,
|
| 204 |
-
"step": 28672
|
| 205 |
-
},
|
| 206 |
-
{
|
| 207 |
-
"epoch": 2.07,
|
| 208 |
-
"learning_rate": 0.00043942999964293453,
|
| 209 |
-
"loss": 0.4741,
|
| 210 |
-
"step": 30720
|
| 211 |
-
},
|
| 212 |
-
{
|
| 213 |
-
"epoch": 2.07,
|
| 214 |
-
"eval_loss": 0.661230742931366,
|
| 215 |
-
"eval_runtime": 18.015,
|
| 216 |
-
"eval_samples_per_second": 116.126,
|
| 217 |
-
"eval_steps_per_second": 7.272,
|
| 218 |
-
"step": 30720
|
| 219 |
-
},
|
| 220 |
-
{
|
| 221 |
-
"epoch": 2.21,
|
| 222 |
-
"learning_rate": 0.0004298966220346151,
|
| 223 |
-
"loss": 0.4632,
|
| 224 |
-
"step": 32768
|
| 225 |
-
},
|
| 226 |
-
{
|
| 227 |
-
"epoch": 2.21,
|
| 228 |
-
"eval_loss": 0.6618030071258545,
|
| 229 |
-
"eval_runtime": 17.9073,
|
| 230 |
-
"eval_samples_per_second": 116.824,
|
| 231 |
-
"eval_steps_per_second": 7.315,
|
| 232 |
-
"step": 32768
|
| 233 |
-
},
|
| 234 |
-
{
|
| 235 |
-
"epoch": 2.35,
|
| 236 |
-
"learning_rate": 0.00041978697624050446,
|
| 237 |
-
"loss": 0.4584,
|
| 238 |
-
"step": 34816
|
| 239 |
-
},
|
| 240 |
-
{
|
| 241 |
-
"epoch": 2.35,
|
| 242 |
-
"eval_loss": 0.6579039096832275,
|
| 243 |
-
"eval_runtime": 17.8241,
|
| 244 |
-
"eval_samples_per_second": 117.369,
|
| 245 |
-
"eval_steps_per_second": 7.35,
|
| 246 |
-
"step": 34816
|
| 247 |
-
},
|
| 248 |
-
{
|
| 249 |
-
"epoch": 2.49,
|
| 250 |
-
"learning_rate": 0.0004091334467888659,
|
| 251 |
-
"loss": 0.451,
|
| 252 |
-
"step": 36864
|
| 253 |
-
},
|
| 254 |
-
{
|
| 255 |
-
"epoch": 2.49,
|
| 256 |
-
"eval_loss": 0.6627541780471802,
|
| 257 |
-
"eval_runtime": 17.6822,
|
| 258 |
-
"eval_samples_per_second": 118.311,
|
| 259 |
-
"eval_steps_per_second": 7.409,
|
| 260 |
-
"step": 36864
|
| 261 |
-
},
|
| 262 |
-
{
|
| 263 |
-
"epoch": 2.62,
|
| 264 |
-
"learning_rate": 0.00039796458815002033,
|
| 265 |
-
"loss": 0.445,
|
| 266 |
-
"step": 38912
|
| 267 |
-
},
|
| 268 |
-
{
|
| 269 |
-
"epoch": 2.62,
|
| 270 |
-
"eval_loss": 0.656867265701294,
|
| 271 |
-
"eval_runtime": 15.8659,
|
| 272 |
-
"eval_samples_per_second": 131.855,
|
| 273 |
-
"eval_steps_per_second": 8.257,
|
| 274 |
-
"step": 38912
|
| 275 |
-
},
|
| 276 |
-
{
|
| 277 |
-
"epoch": 2.76,
|
| 278 |
-
"learning_rate": 0.0003863212870708643,
|
| 279 |
-
"loss": 0.4404,
|
| 280 |
-
"step": 40960
|
| 281 |
-
},
|
| 282 |
-
{
|
| 283 |
-
"epoch": 2.76,
|
| 284 |
-
"eval_loss": 0.6653844118118286,
|
| 285 |
-
"eval_runtime": 17.9192,
|
| 286 |
-
"eval_samples_per_second": 116.747,
|
| 287 |
-
"eval_steps_per_second": 7.311,
|
| 288 |
-
"step": 40960
|
| 289 |
-
},
|
| 290 |
-
{
|
| 291 |
-
"epoch": 2.9,
|
| 292 |
-
"learning_rate": 0.00037424687637876156,
|
| 293 |
-
"loss": 0.4334,
|
| 294 |
-
"step": 43008
|
| 295 |
-
},
|
| 296 |
-
{
|
| 297 |
-
"epoch": 2.9,
|
| 298 |
-
"eval_loss": 0.6553301811218262,
|
| 299 |
-
"eval_runtime": 15.9304,
|
| 300 |
-
"eval_samples_per_second": 131.321,
|
| 301 |
-
"eval_steps_per_second": 8.223,
|
| 302 |
-
"step": 43008
|
| 303 |
-
},
|
| 304 |
-
{
|
| 305 |
-
"epoch": 3.04,
|
| 306 |
-
"learning_rate": 0.00036178064571954134,
|
| 307 |
-
"loss": 0.4278,
|
| 308 |
-
"step": 45056
|
| 309 |
-
},
|
| 310 |
-
{
|
| 311 |
-
"epoch": 3.04,
|
| 312 |
-
"eval_loss": 0.6766741871833801,
|
| 313 |
-
"eval_runtime": 16.9834,
|
| 314 |
-
"eval_samples_per_second": 123.179,
|
| 315 |
-
"eval_steps_per_second": 7.713,
|
| 316 |
-
"step": 45056
|
| 317 |
-
},
|
| 318 |
-
{
|
| 319 |
-
"epoch": 3.18,
|
| 320 |
-
"learning_rate": 0.0003489439971353363,
|
| 321 |
-
"loss": 0.4152,
|
| 322 |
-
"step": 47104
|
| 323 |
-
},
|
| 324 |
-
{
|
| 325 |
-
"epoch": 3.18,
|
| 326 |
-
"eval_loss": 0.6645193696022034,
|
| 327 |
-
"eval_runtime": 15.816,
|
| 328 |
-
"eval_samples_per_second": 132.271,
|
| 329 |
-
"eval_steps_per_second": 8.283,
|
| 330 |
-
"step": 47104
|
| 331 |
-
},
|
| 332 |
-
{
|
| 333 |
-
"epoch": 3.32,
|
| 334 |
-
"learning_rate": 0.0003357965820476752,
|
| 335 |
-
"loss": 0.411,
|
| 336 |
-
"step": 49152
|
| 337 |
-
},
|
| 338 |
-
{
|
| 339 |
-
"epoch": 3.32,
|
| 340 |
-
"eval_loss": 0.6748972535133362,
|
| 341 |
-
"eval_runtime": 17.7507,
|
| 342 |
-
"eval_samples_per_second": 117.855,
|
| 343 |
-
"eval_steps_per_second": 7.38,
|
| 344 |
-
"step": 49152
|
| 345 |
-
},
|
| 346 |
-
{
|
| 347 |
-
"epoch": 3.45,
|
| 348 |
-
"learning_rate": 0.0003223743322236833,
|
| 349 |
-
"loss": 0.4085,
|
| 350 |
-
"step": 51200
|
| 351 |
-
},
|
| 352 |
-
{
|
| 353 |
-
"epoch": 3.45,
|
| 354 |
-
"eval_loss": 0.6703893542289734,
|
| 355 |
-
"eval_runtime": 17.341,
|
| 356 |
-
"eval_samples_per_second": 120.639,
|
| 357 |
-
"eval_steps_per_second": 7.554,
|
| 358 |
-
"step": 51200
|
| 359 |
-
},
|
| 360 |
-
{
|
| 361 |
-
"epoch": 3.59,
|
| 362 |
-
"learning_rate": 0.0003087269633577651,
|
| 363 |
-
"loss": 0.4037,
|
| 364 |
-
"step": 53248
|
| 365 |
-
},
|
| 366 |
-
{
|
| 367 |
-
"epoch": 3.59,
|
| 368 |
-
"eval_loss": 0.6561577916145325,
|
| 369 |
-
"eval_runtime": 15.9295,
|
| 370 |
-
"eval_samples_per_second": 131.329,
|
| 371 |
-
"eval_steps_per_second": 8.224,
|
| 372 |
-
"step": 53248
|
| 373 |
-
},
|
| 374 |
-
{
|
| 375 |
-
"epoch": 3.73,
|
| 376 |
-
"learning_rate": 0.0002948780545870247,
|
| 377 |
-
"loss": 0.3975,
|
| 378 |
-
"step": 55296
|
| 379 |
-
},
|
| 380 |
-
{
|
| 381 |
-
"epoch": 3.73,
|
| 382 |
-
"eval_loss": 0.6698916554450989,
|
| 383 |
-
"eval_runtime": 17.9008,
|
| 384 |
-
"eval_samples_per_second": 116.866,
|
| 385 |
-
"eval_steps_per_second": 7.318,
|
| 386 |
-
"step": 55296
|
| 387 |
-
},
|
| 388 |
-
{
|
| 389 |
-
"epoch": 3.87,
|
| 390 |
-
"learning_rate": 0.0002808921064161573,
|
| 391 |
-
"loss": 0.3917,
|
| 392 |
-
"step": 57344
|
| 393 |
-
},
|
| 394 |
-
{
|
| 395 |
-
"epoch": 3.87,
|
| 396 |
-
"eval_loss": 0.7029281854629517,
|
| 397 |
-
"eval_runtime": 17.8146,
|
| 398 |
-
"eval_samples_per_second": 117.432,
|
| 399 |
-
"eval_steps_per_second": 7.354,
|
| 400 |
-
"step": 57344
|
| 401 |
-
},
|
| 402 |
-
{
|
| 403 |
-
"epoch": 4.01,
|
| 404 |
-
"learning_rate": 0.00026680720064442787,
|
| 405 |
-
"loss": 0.3876,
|
| 406 |
-
"step": 59392
|
| 407 |
-
},
|
| 408 |
-
{
|
| 409 |
-
"epoch": 4.01,
|
| 410 |
-
"eval_loss": 0.6837398409843445,
|
| 411 |
-
"eval_runtime": 17.4354,
|
| 412 |
-
"eval_samples_per_second": 119.986,
|
| 413 |
-
"eval_steps_per_second": 7.513,
|
| 414 |
-
"step": 59392
|
| 415 |
-
},
|
| 416 |
-
{
|
| 417 |
-
"epoch": 4.14,
|
| 418 |
-
"learning_rate": 0.00025266845586830784,
|
| 419 |
-
"loss": 0.3751,
|
| 420 |
-
"step": 61440
|
| 421 |
-
},
|
| 422 |
-
{
|
| 423 |
-
"epoch": 4.14,
|
| 424 |
-
"eval_loss": 0.690500795841217,
|
| 425 |
-
"eval_runtime": 17.8964,
|
| 426 |
-
"eval_samples_per_second": 116.895,
|
| 427 |
-
"eval_steps_per_second": 7.32,
|
| 428 |
-
"step": 61440
|
| 429 |
-
},
|
| 430 |
-
{
|
| 431 |
-
"epoch": 4.28,
|
| 432 |
-
"learning_rate": 0.00023851425721450398,
|
| 433 |
-
"loss": 0.3719,
|
| 434 |
-
"step": 63488
|
| 435 |
-
},
|
| 436 |
-
{
|
| 437 |
-
"epoch": 4.28,
|
| 438 |
-
"eval_loss": 0.6938452124595642,
|
| 439 |
-
"eval_runtime": 15.7962,
|
| 440 |
-
"eval_samples_per_second": 132.437,
|
| 441 |
-
"eval_steps_per_second": 8.293,
|
| 442 |
-
"step": 63488
|
| 443 |
-
},
|
| 444 |
-
{
|
| 445 |
-
"epoch": 4.42,
|
| 446 |
-
"learning_rate": 0.0002244106409269819,
|
| 447 |
-
"loss": 0.3644,
|
| 448 |
-
"step": 65536
|
| 449 |
-
},
|
| 450 |
-
{
|
| 451 |
-
"epoch": 4.42,
|
| 452 |
-
"eval_loss": 0.6987010836601257,
|
| 453 |
-
"eval_runtime": 15.9556,
|
| 454 |
-
"eval_samples_per_second": 131.114,
|
| 455 |
-
"eval_steps_per_second": 8.21,
|
| 456 |
-
"step": 65536
|
| 457 |
-
},
|
| 458 |
-
{
|
| 459 |
-
"epoch": 4.56,
|
| 460 |
-
"learning_rate": 0.00021037526400320187,
|
| 461 |
-
"loss": 0.357,
|
| 462 |
-
"step": 67584
|
| 463 |
-
},
|
| 464 |
-
{
|
| 465 |
-
"epoch": 4.56,
|
| 466 |
-
"eval_loss": 0.6973423957824707,
|
| 467 |
-
"eval_runtime": 15.8273,
|
| 468 |
-
"eval_samples_per_second": 132.177,
|
| 469 |
-
"eval_steps_per_second": 8.277,
|
| 470 |
-
"step": 67584
|
| 471 |
-
},
|
| 472 |
-
{
|
| 473 |
-
"epoch": 4.7,
|
| 474 |
-
"learning_rate": 0.0001964736950807942,
|
| 475 |
-
"loss": 0.357,
|
| 476 |
-
"step": 69632
|
| 477 |
-
},
|
| 478 |
-
{
|
| 479 |
-
"epoch": 4.7,
|
| 480 |
-
"eval_loss": 0.6949540972709656,
|
| 481 |
-
"eval_runtime": 16.1065,
|
| 482 |
-
"eval_samples_per_second": 129.885,
|
| 483 |
-
"eval_steps_per_second": 8.133,
|
| 484 |
-
"step": 69632
|
| 485 |
-
},
|
| 486 |
-
{
|
| 487 |
-
"epoch": 4.83,
|
| 488 |
-
"learning_rate": 0.00018274358855873096,
|
| 489 |
-
"loss": 0.3502,
|
| 490 |
-
"step": 71680
|
| 491 |
-
},
|
| 492 |
-
{
|
| 493 |
-
"epoch": 4.83,
|
| 494 |
-
"eval_loss": 0.6959769129753113,
|
| 495 |
-
"eval_runtime": 16.2001,
|
| 496 |
-
"eval_samples_per_second": 129.135,
|
| 497 |
-
"eval_steps_per_second": 8.086,
|
| 498 |
-
"step": 71680
|
| 499 |
-
},
|
| 500 |
-
{
|
| 501 |
-
"epoch": 4.97,
|
| 502 |
-
"learning_rate": 0.00016922892649452222,
|
| 503 |
-
"loss": 0.3458,
|
| 504 |
-
"step": 73728
|
| 505 |
-
},
|
| 506 |
-
{
|
| 507 |
-
"epoch": 4.97,
|
| 508 |
-
"eval_loss": 0.7017838358879089,
|
| 509 |
-
"eval_runtime": 18.0467,
|
| 510 |
-
"eval_samples_per_second": 115.922,
|
| 511 |
-
"eval_steps_per_second": 7.259,
|
| 512 |
-
"step": 73728
|
| 513 |
-
},
|
| 514 |
-
{
|
| 515 |
-
"epoch": 5.11,
|
| 516 |
-
"learning_rate": 0.00015597300080605504,
|
| 517 |
-
"loss": 0.3302,
|
| 518 |
-
"step": 75776
|
| 519 |
-
},
|
| 520 |
-
{
|
| 521 |
-
"epoch": 5.11,
|
| 522 |
-
"eval_loss": 0.7075567841529846,
|
| 523 |
-
"eval_runtime": 16.7136,
|
| 524 |
-
"eval_samples_per_second": 125.168,
|
| 525 |
-
"eval_steps_per_second": 7.838,
|
| 526 |
-
"step": 75776
|
| 527 |
-
},
|
| 528 |
-
{
|
| 529 |
-
"epoch": 5.25,
|
| 530 |
-
"learning_rate": 0.0001430182745933093,
|
| 531 |
-
"loss": 0.3278,
|
| 532 |
-
"step": 77824
|
| 533 |
-
},
|
| 534 |
-
{
|
| 535 |
-
"epoch": 5.25,
|
| 536 |
-
"eval_loss": 0.7178707718849182,
|
| 537 |
-
"eval_runtime": 15.7714,
|
| 538 |
-
"eval_samples_per_second": 132.645,
|
| 539 |
-
"eval_steps_per_second": 8.306,
|
| 540 |
-
"step": 77824
|
| 541 |
-
},
|
| 542 |
-
{
|
| 543 |
-
"epoch": 5.39,
|
| 544 |
-
"learning_rate": 0.00013040017526934073,
|
| 545 |
-
"loss": 0.3224,
|
| 546 |
-
"step": 79872
|
| 547 |
-
},
|
| 548 |
-
{
|
| 549 |
-
"epoch": 5.39,
|
| 550 |
-
"eval_loss": 0.725006639957428,
|
| 551 |
-
"eval_runtime": 15.8618,
|
| 552 |
-
"eval_samples_per_second": 131.889,
|
| 553 |
-
"eval_steps_per_second": 8.259,
|
| 554 |
-
"step": 79872
|
| 555 |
-
},
|
| 556 |
-
{
|
| 557 |
-
"epoch": 5.53,
|
| 558 |
-
"learning_rate": 0.00011817144183980649,
|
| 559 |
-
"loss": 0.3181,
|
| 560 |
-
"step": 81920
|
| 561 |
-
},
|
| 562 |
-
{
|
| 563 |
-
"epoch": 5.53,
|
| 564 |
-
"eval_loss": 0.7247176766395569,
|
| 565 |
-
"eval_runtime": 17.8123,
|
| 566 |
-
"eval_samples_per_second": 117.447,
|
| 567 |
-
"eval_steps_per_second": 7.354,
|
| 568 |
-
"step": 81920
|
| 569 |
-
},
|
| 570 |
-
{
|
| 571 |
-
"epoch": 5.66,
|
| 572 |
-
"learning_rate": 0.00010636499874117036,
|
| 573 |
-
"loss": 0.3154,
|
| 574 |
-
"step": 83968
|
| 575 |
-
},
|
| 576 |
-
{
|
| 577 |
-
"epoch": 5.66,
|
| 578 |
-
"eval_loss": 0.7248900532722473,
|
| 579 |
-
"eval_runtime": 17.751,
|
| 580 |
-
"eval_samples_per_second": 117.852,
|
| 581 |
-
"eval_steps_per_second": 7.38,
|
| 582 |
-
"step": 83968
|
| 583 |
-
},
|
| 584 |
-
{
|
| 585 |
-
"epoch": 5.8,
|
| 586 |
-
"learning_rate": 9.501866590283475e-05,
|
| 587 |
-
"loss": 0.3105,
|
| 588 |
-
"step": 86016
|
| 589 |
-
},
|
| 590 |
-
{
|
| 591 |
-
"epoch": 5.8,
|
| 592 |
-
"eval_loss": 0.7352888584136963,
|
| 593 |
-
"eval_runtime": 18.0338,
|
| 594 |
-
"eval_samples_per_second": 116.004,
|
| 595 |
-
"eval_steps_per_second": 7.264,
|
| 596 |
-
"step": 86016
|
| 597 |
-
},
|
| 598 |
-
{
|
| 599 |
-
"epoch": 5.94,
|
| 600 |
-
"learning_rate": 8.416361604489855e-05,
|
| 601 |
-
"loss": 0.3035,
|
| 602 |
-
"step": 88064
|
| 603 |
-
},
|
| 604 |
-
{
|
| 605 |
-
"epoch": 5.94,
|
| 606 |
-
"eval_loss": 0.7256708741188049,
|
| 607 |
-
"eval_runtime": 15.94,
|
| 608 |
-
"eval_samples_per_second": 131.242,
|
| 609 |
-
"eval_steps_per_second": 8.218,
|
| 610 |
-
"step": 88064
|
| 611 |
-
},
|
| 612 |
-
{
|
| 613 |
-
"epoch": 6.08,
|
| 614 |
-
"learning_rate": 7.384521927589935e-05,
|
| 615 |
-
"loss": 0.294,
|
| 616 |
-
"step": 90112
|
| 617 |
-
},
|
| 618 |
-
{
|
| 619 |
-
"epoch": 6.08,
|
| 620 |
-
"eval_loss": 0.7387065291404724,
|
| 621 |
-
"eval_runtime": 16.8562,
|
| 622 |
-
"eval_samples_per_second": 124.109,
|
| 623 |
-
"eval_steps_per_second": 7.772,
|
| 624 |
-
"step": 90112
|
| 625 |
-
},
|
| 626 |
-
{
|
| 627 |
-
"epoch": 6.22,
|
| 628 |
-
"learning_rate": 6.409110434142392e-05,
|
| 629 |
-
"loss": 0.2866,
|
| 630 |
-
"step": 92160
|
| 631 |
-
},
|
| 632 |
-
{
|
| 633 |
-
"epoch": 6.22,
|
| 634 |
-
"eval_loss": 0.7492235898971558,
|
| 635 |
-
"eval_runtime": 17.2872,
|
| 636 |
-
"eval_samples_per_second": 121.015,
|
| 637 |
-
"eval_steps_per_second": 7.578,
|
| 638 |
-
"step": 92160
|
| 639 |
-
},
|
| 640 |
-
{
|
| 641 |
-
"epoch": 6.35,
|
| 642 |
-
"learning_rate": 5.492819313147518e-05,
|
| 643 |
-
"loss": 0.2836,
|
| 644 |
-
"step": 94208
|
| 645 |
-
},
|
| 646 |
-
{
|
| 647 |
-
"epoch": 6.35,
|
| 648 |
-
"eval_loss": 0.7440558671951294,
|
| 649 |
-
"eval_runtime": 17.5257,
|
| 650 |
-
"eval_samples_per_second": 119.367,
|
| 651 |
-
"eval_steps_per_second": 7.475,
|
| 652 |
-
"step": 94208
|
| 653 |
-
},
|
| 654 |
-
{
|
| 655 |
-
"epoch": 6.49,
|
| 656 |
-
"learning_rate": 4.6394783238561305e-05,
|
| 657 |
-
"loss": 0.2811,
|
| 658 |
-
"step": 96256
|
| 659 |
-
},
|
| 660 |
-
{
|
| 661 |
-
"epoch": 6.49,
|
| 662 |
-
"eval_loss": 0.7577848434448242,
|
| 663 |
-
"eval_runtime": 15.8536,
|
| 664 |
-
"eval_samples_per_second": 131.957,
|
| 665 |
-
"eval_steps_per_second": 8.263,
|
| 666 |
-
"step": 96256
|
| 667 |
-
},
|
| 668 |
-
{
|
| 669 |
-
"epoch": 6.63,
|
| 670 |
-
"learning_rate": 3.851358797621554e-05,
|
| 671 |
-
"loss": 0.2774,
|
| 672 |
-
"step": 98304
|
| 673 |
-
},
|
| 674 |
-
{
|
| 675 |
-
"epoch": 6.63,
|
| 676 |
-
"eval_loss": 0.7483424544334412,
|
| 677 |
-
"eval_runtime": 15.8485,
|
| 678 |
-
"eval_samples_per_second": 132.0,
|
| 679 |
-
"eval_steps_per_second": 8.266,
|
| 680 |
-
"step": 98304
|
| 681 |
-
},
|
| 682 |
-
{
|
| 683 |
-
"epoch": 6.77,
|
| 684 |
-
"learning_rate": 3.130985341100834e-05,
|
| 685 |
-
"loss": 0.2736,
|
| 686 |
-
"step": 100352
|
| 687 |
-
},
|
| 688 |
-
{
|
| 689 |
-
"epoch": 6.77,
|
| 690 |
-
"eval_loss": 0.7481484413146973,
|
| 691 |
-
"eval_runtime": 17.9168,
|
| 692 |
-
"eval_samples_per_second": 116.762,
|
| 693 |
-
"eval_steps_per_second": 7.312,
|
| 694 |
-
"step": 100352
|
| 695 |
-
},
|
| 696 |
-
{
|
| 697 |
-
"epoch": 6.91,
|
| 698 |
-
"learning_rate": 2.4803653223119228e-05,
|
| 699 |
-
"loss": 0.27,
|
| 700 |
-
"step": 102400
|
| 701 |
-
},
|
| 702 |
-
{
|
| 703 |
-
"epoch": 6.91,
|
| 704 |
-
"eval_loss": 0.7659121751785278,
|
| 705 |
-
"eval_runtime": 15.8798,
|
| 706 |
-
"eval_samples_per_second": 131.739,
|
| 707 |
-
"eval_steps_per_second": 8.249,
|
| 708 |
-
"step": 102400
|
| 709 |
-
},
|
| 710 |
-
{
|
| 711 |
-
"epoch": 7.04,
|
| 712 |
-
"learning_rate": 1.902218093192909e-05,
|
| 713 |
-
"loss": 0.2636,
|
| 714 |
-
"step": 104448
|
| 715 |
-
},
|
| 716 |
-
{
|
| 717 |
-
"epoch": 7.04,
|
| 718 |
-
"eval_loss": 0.7734333276748657,
|
| 719 |
-
"eval_runtime": 17.8497,
|
| 720 |
-
"eval_samples_per_second": 117.201,
|
| 721 |
-
"eval_steps_per_second": 7.339,
|
| 722 |
-
"step": 104448
|
| 723 |
-
},
|
| 724 |
-
{
|
| 725 |
-
"epoch": 7.18,
|
| 726 |
-
"learning_rate": 1.398060674025281e-05,
|
| 727 |
-
"loss": 0.2583,
|
| 728 |
-
"step": 106496
|
| 729 |
-
},
|
| 730 |
-
{
|
| 731 |
-
"epoch": 7.18,
|
| 732 |
-
"eval_loss": 0.7774596810340881,
|
| 733 |
-
"eval_runtime": 17.9006,
|
| 734 |
-
"eval_samples_per_second": 116.868,
|
| 735 |
-
"eval_steps_per_second": 7.318,
|
| 736 |
-
"step": 106496
|
| 737 |
-
},
|
| 738 |
-
{
|
| 739 |
-
"epoch": 7.32,
|
| 740 |
-
"learning_rate": 9.695080472251094e-06,
|
| 741 |
-
"loss": 0.2577,
|
| 742 |
-
"step": 108544
|
| 743 |
-
},
|
| 744 |
-
{
|
| 745 |
-
"epoch": 7.32,
|
| 746 |
-
"eval_loss": 0.7828282117843628,
|
| 747 |
-
"eval_runtime": 15.9506,
|
| 748 |
-
"eval_samples_per_second": 131.155,
|
| 749 |
-
"eval_steps_per_second": 8.213,
|
| 750 |
-
"step": 108544
|
| 751 |
-
},
|
| 752 |
-
{
|
| 753 |
-
"epoch": 7.46,
|
| 754 |
-
"learning_rate": 6.177802621565725e-06,
|
| 755 |
-
"loss": 0.2553,
|
| 756 |
-
"step": 110592
|
| 757 |
-
},
|
| 758 |
-
{
|
| 759 |
-
"epoch": 7.46,
|
| 760 |
-
"eval_loss": 0.7818995714187622,
|
| 761 |
-
"eval_runtime": 15.975,
|
| 762 |
-
"eval_samples_per_second": 130.955,
|
| 763 |
-
"eval_steps_per_second": 8.2,
|
| 764 |
-
"step": 110592
|
| 765 |
-
},
|
| 766 |
-
{
|
| 767 |
-
"epoch": 7.6,
|
| 768 |
-
"learning_rate": 3.4434741135661028e-06,
|
| 769 |
-
"loss": 0.2545,
|
| 770 |
-
"step": 112640
|
| 771 |
-
},
|
| 772 |
-
{
|
| 773 |
-
"epoch": 7.6,
|
| 774 |
-
"eval_loss": 0.7817807197570801,
|
| 775 |
-
"eval_runtime": 15.9873,
|
| 776 |
-
"eval_samples_per_second": 130.854,
|
| 777 |
-
"eval_steps_per_second": 8.194,
|
| 778 |
-
"step": 112640
|
| 779 |
-
},
|
| 780 |
-
{
|
| 781 |
-
"epoch": 7.74,
|
| 782 |
-
"learning_rate": 1.498947438756143e-06,
|
| 783 |
-
"loss": 0.2536,
|
| 784 |
-
"step": 114688
|
| 785 |
-
},
|
| 786 |
-
{
|
| 787 |
-
"epoch": 7.74,
|
| 788 |
-
"eval_loss": 0.7830276489257812,
|
| 789 |
-
"eval_runtime": 17.6639,
|
| 790 |
-
"eval_samples_per_second": 118.434,
|
| 791 |
-
"eval_steps_per_second": 7.416,
|
| 792 |
-
"step": 114688
|
| 793 |
-
}
|
| 794 |
-
],
|
| 795 |
-
"max_steps": 118608,
|
| 796 |
-
"num_train_epochs": 8,
|
| 797 |
-
"total_flos": 4.702934009537618e+17,
|
| 798 |
-
"trial_name": null,
|
| 799 |
-
"trial_params": null
|
| 800 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-114688/training_args.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:0200139492e444a9d322a4f90a96e6dde09c7a882f05b816c2345dade5ea0f98
|
| 3 |
-
size 3515
|
|
|
|
|
|
|
|
|
|
|
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 139279005
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:319da55f7bdc14e455deb61ce68f9663cffd4b765a97952f7c04b2708e957075
|
| 3 |
size 139279005
|