Commit
•
4c6bd8d
1
Parent(s):
0054227
huggingartists
Browse files- README.md +3 -3
- config.json +1 -1
- evaluation.txt +1 -1
- flax_model.msgpack +1 -1
- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- rng_state.pth +2 -2
- scheduler.pt +1 -1
- trainer_state.json +34 -734
- training_args.bin +2 -2
README.md
CHANGED
|
@@ -45,15 +45,15 @@ from datasets import load_dataset
|
|
| 45 |
dataset = load_dataset("huggingartists/the-king-and-the-jester")
|
| 46 |
```
|
| 47 |
|
| 48 |
-
[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/
|
| 49 |
|
| 50 |
## Training procedure
|
| 51 |
|
| 52 |
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on Король и Шут (The King and the Jester)'s lyrics.
|
| 53 |
|
| 54 |
-
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/
|
| 55 |
|
| 56 |
-
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/
|
| 57 |
|
| 58 |
## How to use
|
| 59 |
|
|
|
|
| 45 |
dataset = load_dataset("huggingartists/the-king-and-the-jester")
|
| 46 |
```
|
| 47 |
|
| 48 |
+
[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/1qw2ic95/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
|
| 49 |
|
| 50 |
## Training procedure
|
| 51 |
|
| 52 |
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on Король и Шут (The King and the Jester)'s lyrics.
|
| 53 |
|
| 54 |
+
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/hhhj9047) for full transparency and reproducibility.
|
| 55 |
|
| 56 |
+
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/hhhj9047/artifacts) is logged and versioned.
|
| 57 |
|
| 58 |
## How to use
|
| 59 |
|
config.json
CHANGED
|
@@ -35,7 +35,7 @@
|
|
| 35 |
}
|
| 36 |
},
|
| 37 |
"torch_dtype": "float32",
|
| 38 |
-
"transformers_version": "4.
|
| 39 |
"use_cache": true,
|
| 40 |
"vocab_size": 50257
|
| 41 |
}
|
|
|
|
| 35 |
}
|
| 36 |
},
|
| 37 |
"torch_dtype": "float32",
|
| 38 |
+
"transformers_version": "4.11.0",
|
| 39 |
"use_cache": true,
|
| 40 |
"vocab_size": 50257
|
| 41 |
}
|
evaluation.txt
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"eval_loss": 1.
|
|
|
|
| 1 |
+
{"eval_loss": 1.3811118602752686, "eval_runtime": 2.7029, "eval_samples_per_second": 20.718, "eval_steps_per_second": 2.59, "epoch": 14.0}
|
flax_model.msgpack
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 497764120
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9e175838bcefc314abb41ccdc056d9ec76d3c23ec1913aad2c1bc8121080c50
|
| 3 |
size 497764120
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 995604017
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cea581dc317000974b4d217190f003bf615040e9e1598ac287c37ef42026ad10
|
| 3 |
size 995604017
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 510403817
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf9401ee76bd94fd951f38fc8ff5e2041ba8e3f26386f718b133a47a8e011f93
|
| 3 |
size 510403817
|
rng_state.pth
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 sha256:677e090106eb423c84d903f7625e7b33fd588c14e0966b2dcb8739ccb436b9cf
|
| 3 |
+
size 14567
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 623
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:428d2db0a08ed1ac463b6b8c47d9f8227cfb86b90836ee74abface2c5812275a
|
| 3 |
size 623
|
trainer_state.json
CHANGED
|
@@ -1,772 +1,72 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 3 |
-
"best_model_checkpoint": "output/the-king-and-the-jester/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 0.12,
|
| 12 |
-
"learning_rate": 0.
|
| 13 |
-
"loss":
|
| 14 |
"step": 5
|
| 15 |
},
|
| 16 |
{
|
| 17 |
-
"epoch": 0.
|
| 18 |
-
"learning_rate": 0.
|
| 19 |
-
"loss":
|
| 20 |
"step": 10
|
| 21 |
},
|
| 22 |
{
|
| 23 |
-
"epoch": 0.
|
| 24 |
-
"learning_rate": 9.
|
| 25 |
-
"loss":
|
| 26 |
"step": 15
|
| 27 |
},
|
| 28 |
{
|
| 29 |
-
"epoch": 0.
|
| 30 |
-
"learning_rate":
|
| 31 |
-
"loss":
|
| 32 |
"step": 20
|
| 33 |
},
|
| 34 |
{
|
| 35 |
-
"epoch": 0.
|
| 36 |
-
"learning_rate": 4.
|
| 37 |
-
"loss":
|
| 38 |
"step": 25
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch": 0.
|
| 42 |
-
"learning_rate": 2.
|
| 43 |
-
"loss":
|
| 44 |
"step": 30
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch": 0.
|
| 48 |
-
"learning_rate":
|
| 49 |
-
"loss":
|
| 50 |
"step": 35
|
| 51 |
},
|
| 52 |
{
|
| 53 |
-
"epoch":
|
| 54 |
-
"learning_rate":
|
| 55 |
-
"loss":
|
| 56 |
-
"step": 40
|
| 57 |
-
},
|
| 58 |
-
{
|
| 59 |
-
"epoch": 1.0,
|
| 60 |
-
"eval_loss": 2.0384345054626465,
|
| 61 |
-
"eval_runtime": 3.02,
|
| 62 |
-
"eval_samples_per_second": 22.848,
|
| 63 |
-
"eval_steps_per_second": 2.98,
|
| 64 |
"step": 40
|
| 65 |
},
|
| 66 |
{
|
| 67 |
"epoch": 1.0,
|
| 68 |
-
"eval_loss":
|
| 69 |
-
"eval_runtime": 2.7482,
|
| 70 |
-
"eval_samples_per_second": 21.833,
|
| 71 |
-
"eval_steps_per_second": 2.911,
|
| 72 |
-
"step": 41
|
| 73 |
-
},
|
| 74 |
-
{
|
| 75 |
-
"epoch": 1.1,
|
| 76 |
-
"learning_rate": 3.197007505031765e-06,
|
| 77 |
-
"loss": 2.0701,
|
| 78 |
-
"step": 45
|
| 79 |
-
},
|
| 80 |
-
{
|
| 81 |
-
"epoch": 1.22,
|
| 82 |
-
"learning_rate": 1.5675842264214697e-05,
|
| 83 |
-
"loss": 2.1089,
|
| 84 |
-
"step": 50
|
| 85 |
-
},
|
| 86 |
-
{
|
| 87 |
-
"epoch": 1.34,
|
| 88 |
-
"learning_rate": 3.58284204500588e-05,
|
| 89 |
-
"loss": 2.1069,
|
| 90 |
-
"step": 55
|
| 91 |
-
},
|
| 92 |
-
{
|
| 93 |
-
"epoch": 1.46,
|
| 94 |
-
"learning_rate": 6.0732717017669706e-05,
|
| 95 |
-
"loss": 2.1029,
|
| 96 |
-
"step": 60
|
| 97 |
-
},
|
| 98 |
-
{
|
| 99 |
-
"epoch": 1.59,
|
| 100 |
-
"learning_rate": 8.677773105069102e-05,
|
| 101 |
-
"loss": 2.0072,
|
| 102 |
-
"step": 65
|
| 103 |
-
},
|
| 104 |
-
{
|
| 105 |
-
"epoch": 1.71,
|
| 106 |
-
"learning_rate": 0.00011018706319231134,
|
| 107 |
-
"loss": 2.0136,
|
| 108 |
-
"step": 70
|
| 109 |
-
},
|
| 110 |
-
{
|
| 111 |
-
"epoch": 1.83,
|
| 112 |
-
"learning_rate": 0.00012756647503932202,
|
| 113 |
-
"loss": 1.9948,
|
| 114 |
-
"step": 75
|
| 115 |
-
},
|
| 116 |
-
{
|
| 117 |
-
"epoch": 1.95,
|
| 118 |
-
"learning_rate": 0.0001363960370713319,
|
| 119 |
-
"loss": 2.0721,
|
| 120 |
-
"step": 80
|
| 121 |
-
},
|
| 122 |
-
{
|
| 123 |
-
"epoch": 2.0,
|
| 124 |
-
"eval_loss": 1.9534873962402344,
|
| 125 |
-
"eval_runtime": 2.6646,
|
| 126 |
-
"eval_samples_per_second": 22.517,
|
| 127 |
-
"eval_steps_per_second": 3.002,
|
| 128 |
-
"step": 82
|
| 129 |
-
},
|
| 130 |
-
{
|
| 131 |
-
"epoch": 2.07,
|
| 132 |
-
"learning_rate": 0.00013539550607801564,
|
| 133 |
-
"loss": 1.954,
|
| 134 |
-
"step": 85
|
| 135 |
-
},
|
| 136 |
-
{
|
| 137 |
-
"epoch": 2.2,
|
| 138 |
-
"learning_rate": 0.00012470995414859683,
|
| 139 |
-
"loss": 1.9953,
|
| 140 |
-
"step": 90
|
| 141 |
-
},
|
| 142 |
-
{
|
| 143 |
-
"epoch": 2.32,
|
| 144 |
-
"learning_rate": 0.00010588873393008382,
|
| 145 |
-
"loss": 1.942,
|
| 146 |
-
"step": 95
|
| 147 |
-
},
|
| 148 |
-
{
|
| 149 |
-
"epoch": 2.44,
|
| 150 |
-
"learning_rate": 8.16608300886963e-05,
|
| 151 |
-
"loss": 1.9347,
|
| 152 |
-
"step": 100
|
| 153 |
-
},
|
| 154 |
-
{
|
| 155 |
-
"epoch": 2.56,
|
| 156 |
-
"learning_rate": 5.553916991130374e-05,
|
| 157 |
-
"loss": 1.9066,
|
| 158 |
-
"step": 105
|
| 159 |
-
},
|
| 160 |
-
{
|
| 161 |
-
"epoch": 2.68,
|
| 162 |
-
"learning_rate": 3.131126606991618e-05,
|
| 163 |
-
"loss": 1.8905,
|
| 164 |
-
"step": 110
|
| 165 |
-
},
|
| 166 |
-
{
|
| 167 |
-
"epoch": 2.8,
|
| 168 |
-
"learning_rate": 1.249004585140324e-05,
|
| 169 |
-
"loss": 1.9008,
|
| 170 |
-
"step": 115
|
| 171 |
-
},
|
| 172 |
-
{
|
| 173 |
-
"epoch": 2.93,
|
| 174 |
-
"learning_rate": 1.8044939219843706e-06,
|
| 175 |
-
"loss": 1.9337,
|
| 176 |
-
"step": 120
|
| 177 |
-
},
|
| 178 |
-
{
|
| 179 |
-
"epoch": 3.0,
|
| 180 |
-
"eval_loss": 1.8858658075332642,
|
| 181 |
-
"eval_runtime": 2.6819,
|
| 182 |
-
"eval_samples_per_second": 22.372,
|
| 183 |
-
"eval_steps_per_second": 2.983,
|
| 184 |
-
"step": 123
|
| 185 |
-
},
|
| 186 |
-
{
|
| 187 |
-
"epoch": 3.05,
|
| 188 |
-
"learning_rate": 8.03962928668091e-07,
|
| 189 |
-
"loss": 1.8946,
|
| 190 |
-
"step": 125
|
| 191 |
-
},
|
| 192 |
-
{
|
| 193 |
-
"epoch": 3.17,
|
| 194 |
-
"learning_rate": 9.633524960678029e-06,
|
| 195 |
-
"loss": 1.8829,
|
| 196 |
-
"step": 130
|
| 197 |
-
},
|
| 198 |
-
{
|
| 199 |
-
"epoch": 3.29,
|
| 200 |
-
"learning_rate": 2.7012936807688628e-05,
|
| 201 |
-
"loss": 1.8463,
|
| 202 |
-
"step": 135
|
| 203 |
-
},
|
| 204 |
-
{
|
| 205 |
-
"epoch": 3.41,
|
| 206 |
-
"learning_rate": 5.042226894930894e-05,
|
| 207 |
-
"loss": 1.8504,
|
| 208 |
-
"step": 140
|
| 209 |
-
},
|
| 210 |
-
{
|
| 211 |
-
"epoch": 3.54,
|
| 212 |
-
"learning_rate": 7.646728298233026e-05,
|
| 213 |
-
"loss": 1.8816,
|
| 214 |
-
"step": 145
|
| 215 |
-
},
|
| 216 |
-
{
|
| 217 |
-
"epoch": 3.66,
|
| 218 |
-
"learning_rate": 0.00010137157954994128,
|
| 219 |
-
"loss": 1.8994,
|
| 220 |
-
"step": 150
|
| 221 |
-
},
|
| 222 |
-
{
|
| 223 |
-
"epoch": 3.78,
|
| 224 |
-
"learning_rate": 0.00012152415773578527,
|
| 225 |
-
"loss": 1.8732,
|
| 226 |
-
"step": 155
|
| 227 |
-
},
|
| 228 |
-
{
|
| 229 |
-
"epoch": 3.9,
|
| 230 |
-
"learning_rate": 0.00013400299249496822,
|
| 231 |
-
"loss": 1.8941,
|
| 232 |
-
"step": 160
|
| 233 |
-
},
|
| 234 |
-
{
|
| 235 |
-
"epoch": 4.0,
|
| 236 |
-
"eval_loss": 1.875728726387024,
|
| 237 |
-
"eval_runtime": 2.6807,
|
| 238 |
-
"eval_samples_per_second": 22.383,
|
| 239 |
-
"eval_steps_per_second": 2.984,
|
| 240 |
-
"step": 164
|
| 241 |
-
},
|
| 242 |
-
{
|
| 243 |
-
"epoch": 4.02,
|
| 244 |
-
"learning_rate": 0.00013699871396120457,
|
| 245 |
-
"loss": 1.7863,
|
| 246 |
-
"step": 165
|
| 247 |
-
},
|
| 248 |
-
{
|
| 249 |
-
"epoch": 4.15,
|
| 250 |
-
"learning_rate": 0.0001300769572075284,
|
| 251 |
-
"loss": 1.7972,
|
| 252 |
-
"step": 170
|
| 253 |
-
},
|
| 254 |
-
{
|
| 255 |
-
"epoch": 4.27,
|
| 256 |
-
"learning_rate": 0.0001142413430313578,
|
| 257 |
-
"loss": 1.8453,
|
| 258 |
-
"step": 175
|
| 259 |
-
},
|
| 260 |
-
{
|
| 261 |
-
"epoch": 4.39,
|
| 262 |
-
"learning_rate": 9.178795785882326e-05,
|
| 263 |
-
"loss": 1.7723,
|
| 264 |
-
"step": 180
|
| 265 |
-
},
|
| 266 |
-
{
|
| 267 |
-
"epoch": 4.51,
|
| 268 |
-
"learning_rate": 6.597243246886372e-05,
|
| 269 |
-
"loss": 1.7477,
|
| 270 |
-
"step": 185
|
| 271 |
-
},
|
| 272 |
-
{
|
| 273 |
-
"epoch": 4.63,
|
| 274 |
-
"learning_rate": 4.0537891490046174e-05,
|
| 275 |
-
"loss": 1.8018,
|
| 276 |
-
"step": 190
|
| 277 |
-
},
|
| 278 |
-
{
|
| 279 |
-
"epoch": 4.76,
|
| 280 |
-
"learning_rate": 1.917221867898604e-05,
|
| 281 |
-
"loss": 1.8131,
|
| 282 |
-
"step": 195
|
| 283 |
-
},
|
| 284 |
-
{
|
| 285 |
-
"epoch": 4.88,
|
| 286 |
-
"learning_rate": 4.9733318543963394e-06,
|
| 287 |
-
"loss": 1.838,
|
| 288 |
-
"step": 200
|
| 289 |
-
},
|
| 290 |
-
{
|
| 291 |
-
"epoch": 5.0,
|
| 292 |
-
"learning_rate": 0.0,
|
| 293 |
-
"loss": 1.7917,
|
| 294 |
-
"step": 205
|
| 295 |
-
},
|
| 296 |
-
{
|
| 297 |
-
"epoch": 5.0,
|
| 298 |
-
"eval_loss": 1.8161486387252808,
|
| 299 |
-
"eval_runtime": 2.661,
|
| 300 |
-
"eval_samples_per_second": 22.548,
|
| 301 |
-
"eval_steps_per_second": 3.006,
|
| 302 |
-
"step": 205
|
| 303 |
-
},
|
| 304 |
-
{
|
| 305 |
-
"epoch": 5.12,
|
| 306 |
-
"learning_rate": 4.973331854396309e-06,
|
| 307 |
-
"loss": 1.7952,
|
| 308 |
-
"step": 210
|
| 309 |
-
},
|
| 310 |
-
{
|
| 311 |
-
"epoch": 5.24,
|
| 312 |
-
"learning_rate": 1.917221867898606e-05,
|
| 313 |
-
"loss": 1.7604,
|
| 314 |
-
"step": 215
|
| 315 |
-
},
|
| 316 |
-
{
|
| 317 |
-
"epoch": 5.37,
|
| 318 |
-
"learning_rate": 4.053789149004621e-05,
|
| 319 |
-
"loss": 1.7446,
|
| 320 |
-
"step": 220
|
| 321 |
-
},
|
| 322 |
-
{
|
| 323 |
-
"epoch": 5.49,
|
| 324 |
-
"learning_rate": 6.597243246886352e-05,
|
| 325 |
-
"loss": 1.6903,
|
| 326 |
-
"step": 225
|
| 327 |
-
},
|
| 328 |
-
{
|
| 329 |
-
"epoch": 5.61,
|
| 330 |
-
"learning_rate": 9.178795785882305e-05,
|
| 331 |
-
"loss": 1.7928,
|
| 332 |
-
"step": 230
|
| 333 |
-
},
|
| 334 |
-
{
|
| 335 |
-
"epoch": 5.73,
|
| 336 |
-
"learning_rate": 0.00011424134303135765,
|
| 337 |
-
"loss": 1.6792,
|
| 338 |
-
"step": 235
|
| 339 |
-
},
|
| 340 |
-
{
|
| 341 |
-
"epoch": 5.85,
|
| 342 |
-
"learning_rate": 0.00013007695720752838,
|
| 343 |
-
"loss": 1.8006,
|
| 344 |
-
"step": 240
|
| 345 |
-
},
|
| 346 |
-
{
|
| 347 |
-
"epoch": 5.98,
|
| 348 |
-
"learning_rate": 0.00013699871396120457,
|
| 349 |
-
"loss": 1.7115,
|
| 350 |
-
"step": 245
|
| 351 |
-
},
|
| 352 |
-
{
|
| 353 |
-
"epoch": 6.0,
|
| 354 |
-
"eval_loss": 1.8405648469924927,
|
| 355 |
-
"eval_runtime": 2.6612,
|
| 356 |
-
"eval_samples_per_second": 22.546,
|
| 357 |
-
"eval_steps_per_second": 3.006,
|
| 358 |
-
"step": 246
|
| 359 |
-
},
|
| 360 |
-
{
|
| 361 |
-
"epoch": 6.1,
|
| 362 |
-
"learning_rate": 0.00013400299249496822,
|
| 363 |
-
"loss": 1.6111,
|
| 364 |
-
"step": 250
|
| 365 |
-
},
|
| 366 |
-
{
|
| 367 |
-
"epoch": 6.22,
|
| 368 |
-
"learning_rate": 0.00012152415773578526,
|
| 369 |
-
"loss": 1.7498,
|
| 370 |
-
"step": 255
|
| 371 |
-
},
|
| 372 |
-
{
|
| 373 |
-
"epoch": 6.34,
|
| 374 |
-
"learning_rate": 0.00010137157954994115,
|
| 375 |
-
"loss": 1.7173,
|
| 376 |
-
"step": 260
|
| 377 |
-
},
|
| 378 |
-
{
|
| 379 |
-
"epoch": 6.46,
|
| 380 |
-
"learning_rate": 7.646728298233034e-05,
|
| 381 |
-
"loss": 1.6387,
|
| 382 |
-
"step": 265
|
| 383 |
-
},
|
| 384 |
-
{
|
| 385 |
-
"epoch": 6.59,
|
| 386 |
-
"learning_rate": 5.0422268949309024e-05,
|
| 387 |
-
"loss": 1.7363,
|
| 388 |
-
"step": 270
|
| 389 |
-
},
|
| 390 |
-
{
|
| 391 |
-
"epoch": 6.71,
|
| 392 |
-
"learning_rate": 2.7012936807688787e-05,
|
| 393 |
-
"loss": 1.6338,
|
| 394 |
-
"step": 275
|
| 395 |
-
},
|
| 396 |
-
{
|
| 397 |
-
"epoch": 6.83,
|
| 398 |
-
"learning_rate": 9.633524960678075e-06,
|
| 399 |
-
"loss": 1.6839,
|
| 400 |
-
"step": 280
|
| 401 |
-
},
|
| 402 |
-
{
|
| 403 |
-
"epoch": 6.95,
|
| 404 |
-
"learning_rate": 8.039629286681063e-07,
|
| 405 |
-
"loss": 1.6574,
|
| 406 |
-
"step": 285
|
| 407 |
-
},
|
| 408 |
-
{
|
| 409 |
-
"epoch": 7.0,
|
| 410 |
-
"eval_loss": 1.7874430418014526,
|
| 411 |
-
"eval_runtime": 2.6845,
|
| 412 |
-
"eval_samples_per_second": 22.35,
|
| 413 |
-
"eval_steps_per_second": 2.98,
|
| 414 |
-
"step": 287
|
| 415 |
-
},
|
| 416 |
-
{
|
| 417 |
-
"epoch": 7.07,
|
| 418 |
-
"learning_rate": 1.8044939219843553e-06,
|
| 419 |
-
"loss": 1.7106,
|
| 420 |
-
"step": 290
|
| 421 |
-
},
|
| 422 |
-
{
|
| 423 |
-
"epoch": 7.2,
|
| 424 |
-
"learning_rate": 1.2490045851403185e-05,
|
| 425 |
-
"loss": 1.651,
|
| 426 |
-
"step": 295
|
| 427 |
-
},
|
| 428 |
-
{
|
| 429 |
-
"epoch": 7.32,
|
| 430 |
-
"learning_rate": 3.131126606991631e-05,
|
| 431 |
-
"loss": 1.6335,
|
| 432 |
-
"step": 300
|
| 433 |
-
},
|
| 434 |
-
{
|
| 435 |
-
"epoch": 7.44,
|
| 436 |
-
"learning_rate": 5.553916991130366e-05,
|
| 437 |
-
"loss": 1.6561,
|
| 438 |
-
"step": 305
|
| 439 |
-
},
|
| 440 |
-
{
|
| 441 |
-
"epoch": 7.56,
|
| 442 |
-
"learning_rate": 8.166083008869623e-05,
|
| 443 |
-
"loss": 1.6365,
|
| 444 |
-
"step": 310
|
| 445 |
-
},
|
| 446 |
-
{
|
| 447 |
-
"epoch": 7.68,
|
| 448 |
-
"learning_rate": 0.00010588873393008359,
|
| 449 |
-
"loss": 1.5825,
|
| 450 |
-
"step": 315
|
| 451 |
-
},
|
| 452 |
-
{
|
| 453 |
-
"epoch": 7.8,
|
| 454 |
-
"learning_rate": 0.00012470995414859675,
|
| 455 |
-
"loss": 1.6183,
|
| 456 |
-
"step": 320
|
| 457 |
-
},
|
| 458 |
-
{
|
| 459 |
-
"epoch": 7.93,
|
| 460 |
-
"learning_rate": 0.00013539550607801564,
|
| 461 |
-
"loss": 1.6877,
|
| 462 |
-
"step": 325
|
| 463 |
-
},
|
| 464 |
-
{
|
| 465 |
-
"epoch": 8.0,
|
| 466 |
-
"eval_loss": 1.809894323348999,
|
| 467 |
-
"eval_runtime": 2.6825,
|
| 468 |
-
"eval_samples_per_second": 22.367,
|
| 469 |
-
"eval_steps_per_second": 2.982,
|
| 470 |
-
"step": 328
|
| 471 |
-
},
|
| 472 |
-
{
|
| 473 |
-
"epoch": 8.05,
|
| 474 |
-
"learning_rate": 0.00013639603707133193,
|
| 475 |
-
"loss": 1.6439,
|
| 476 |
-
"step": 330
|
| 477 |
-
},
|
| 478 |
-
{
|
| 479 |
-
"epoch": 8.17,
|
| 480 |
-
"learning_rate": 0.0001275664750393221,
|
| 481 |
-
"loss": 1.5897,
|
| 482 |
-
"step": 335
|
| 483 |
-
},
|
| 484 |
-
{
|
| 485 |
-
"epoch": 8.29,
|
| 486 |
-
"learning_rate": 0.00011018706319231131,
|
| 487 |
-
"loss": 1.5505,
|
| 488 |
-
"step": 340
|
| 489 |
-
},
|
| 490 |
-
{
|
| 491 |
-
"epoch": 8.41,
|
| 492 |
-
"learning_rate": 8.67777310506911e-05,
|
| 493 |
-
"loss": 1.6075,
|
| 494 |
-
"step": 345
|
| 495 |
-
},
|
| 496 |
-
{
|
| 497 |
-
"epoch": 8.54,
|
| 498 |
-
"learning_rate": 6.073271701766978e-05,
|
| 499 |
-
"loss": 1.6166,
|
| 500 |
-
"step": 350
|
| 501 |
-
},
|
| 502 |
-
{
|
| 503 |
-
"epoch": 8.66,
|
| 504 |
-
"learning_rate": 3.5828420450058975e-05,
|
| 505 |
-
"loss": 1.5752,
|
| 506 |
-
"step": 355
|
| 507 |
-
},
|
| 508 |
-
{
|
| 509 |
-
"epoch": 8.78,
|
| 510 |
-
"learning_rate": 1.5675842264214674e-05,
|
| 511 |
-
"loss": 1.5862,
|
| 512 |
-
"step": 360
|
| 513 |
-
},
|
| 514 |
-
{
|
| 515 |
-
"epoch": 8.9,
|
| 516 |
-
"learning_rate": 3.1970075050318028e-06,
|
| 517 |
-
"loss": 1.6337,
|
| 518 |
-
"step": 365
|
| 519 |
-
},
|
| 520 |
-
{
|
| 521 |
-
"epoch": 9.0,
|
| 522 |
-
"eval_loss": 1.7743412256240845,
|
| 523 |
-
"eval_runtime": 2.6816,
|
| 524 |
-
"eval_samples_per_second": 22.374,
|
| 525 |
-
"eval_steps_per_second": 2.983,
|
| 526 |
-
"step": 369
|
| 527 |
-
},
|
| 528 |
-
{
|
| 529 |
-
"epoch": 9.02,
|
| 530 |
-
"learning_rate": 2.012860387953829e-07,
|
| 531 |
-
"loss": 1.571,
|
| 532 |
-
"step": 370
|
| 533 |
-
},
|
| 534 |
-
{
|
| 535 |
-
"epoch": 9.15,
|
| 536 |
-
"learning_rate": 7.123042792471586e-06,
|
| 537 |
-
"loss": 1.5196,
|
| 538 |
-
"step": 375
|
| 539 |
-
},
|
| 540 |
-
{
|
| 541 |
-
"epoch": 9.27,
|
| 542 |
-
"learning_rate": 2.295865696864207e-05,
|
| 543 |
-
"loss": 1.5784,
|
| 544 |
-
"step": 380
|
| 545 |
-
},
|
| 546 |
-
{
|
| 547 |
-
"epoch": 9.39,
|
| 548 |
-
"learning_rate": 4.541204214117682e-05,
|
| 549 |
-
"loss": 1.4763,
|
| 550 |
-
"step": 385
|
| 551 |
-
},
|
| 552 |
-
{
|
| 553 |
-
"epoch": 9.51,
|
| 554 |
-
"learning_rate": 7.122756753113636e-05,
|
| 555 |
-
"loss": 1.5361,
|
| 556 |
-
"step": 390
|
| 557 |
-
},
|
| 558 |
-
{
|
| 559 |
-
"epoch": 9.63,
|
| 560 |
-
"learning_rate": 9.66621085099539e-05,
|
| 561 |
-
"loss": 1.5069,
|
| 562 |
-
"step": 395
|
| 563 |
-
},
|
| 564 |
-
{
|
| 565 |
-
"epoch": 9.76,
|
| 566 |
-
"learning_rate": 0.00011802778132101384,
|
| 567 |
-
"loss": 1.4928,
|
| 568 |
-
"step": 400
|
| 569 |
-
},
|
| 570 |
-
{
|
| 571 |
-
"epoch": 9.88,
|
| 572 |
-
"learning_rate": 0.00013222666814560375,
|
| 573 |
-
"loss": 1.5968,
|
| 574 |
-
"step": 405
|
| 575 |
-
},
|
| 576 |
-
{
|
| 577 |
-
"epoch": 10.0,
|
| 578 |
-
"learning_rate": 0.0001372,
|
| 579 |
-
"loss": 1.5821,
|
| 580 |
-
"step": 410
|
| 581 |
-
},
|
| 582 |
-
{
|
| 583 |
-
"epoch": 10.0,
|
| 584 |
-
"eval_loss": 1.8010404109954834,
|
| 585 |
-
"eval_runtime": 2.6585,
|
| 586 |
-
"eval_samples_per_second": 22.569,
|
| 587 |
-
"eval_steps_per_second": 3.009,
|
| 588 |
-
"step": 410
|
| 589 |
-
},
|
| 590 |
-
{
|
| 591 |
-
"epoch": 10.12,
|
| 592 |
-
"learning_rate": 0.0001322266681456038,
|
| 593 |
-
"loss": 1.5347,
|
| 594 |
-
"step": 415
|
| 595 |
-
},
|
| 596 |
-
{
|
| 597 |
-
"epoch": 10.24,
|
| 598 |
-
"learning_rate": 0.00011802778132101396,
|
| 599 |
-
"loss": 1.4811,
|
| 600 |
-
"step": 420
|
| 601 |
-
},
|
| 602 |
-
{
|
| 603 |
-
"epoch": 10.37,
|
| 604 |
-
"learning_rate": 9.666210850995405e-05,
|
| 605 |
-
"loss": 1.5224,
|
| 606 |
-
"step": 425
|
| 607 |
-
},
|
| 608 |
-
{
|
| 609 |
-
"epoch": 10.49,
|
| 610 |
-
"learning_rate": 7.122756753113628e-05,
|
| 611 |
-
"loss": 1.5008,
|
| 612 |
-
"step": 430
|
| 613 |
-
},
|
| 614 |
-
{
|
| 615 |
-
"epoch": 10.61,
|
| 616 |
-
"learning_rate": 4.541204214117674e-05,
|
| 617 |
-
"loss": 1.5444,
|
| 618 |
-
"step": 435
|
| 619 |
-
},
|
| 620 |
-
{
|
| 621 |
-
"epoch": 10.73,
|
| 622 |
-
"learning_rate": 2.2958656968642017e-05,
|
| 623 |
-
"loss": 1.4584,
|
| 624 |
-
"step": 440
|
| 625 |
-
},
|
| 626 |
-
{
|
| 627 |
-
"epoch": 10.85,
|
| 628 |
-
"learning_rate": 7.123042792471548e-06,
|
| 629 |
-
"loss": 1.5025,
|
| 630 |
-
"step": 445
|
| 631 |
-
},
|
| 632 |
-
{
|
| 633 |
-
"epoch": 10.98,
|
| 634 |
-
"learning_rate": 2.0128603879541336e-07,
|
| 635 |
-
"loss": 1.4657,
|
| 636 |
-
"step": 450
|
| 637 |
-
},
|
| 638 |
-
{
|
| 639 |
-
"epoch": 11.0,
|
| 640 |
-
"eval_loss": 1.7706276178359985,
|
| 641 |
"eval_runtime": 2.6826,
|
| 642 |
-
"eval_samples_per_second":
|
| 643 |
-
"eval_steps_per_second": 2.
|
| 644 |
-
"step":
|
| 645 |
-
},
|
| 646 |
-
{
|
| 647 |
-
"epoch": 11.38,
|
| 648 |
-
"learning_rate": 4.234791653975473e-05,
|
| 649 |
-
"loss": 1.6323,
|
| 650 |
-
"step": 455
|
| 651 |
-
},
|
| 652 |
-
{
|
| 653 |
-
"epoch": 11.5,
|
| 654 |
-
"learning_rate": 6.859999999999978e-05,
|
| 655 |
-
"loss": 1.5573,
|
| 656 |
-
"step": 460
|
| 657 |
-
},
|
| 658 |
-
{
|
| 659 |
-
"epoch": 11.62,
|
| 660 |
-
"learning_rate": 9.485208346024488e-05,
|
| 661 |
-
"loss": 1.5613,
|
| 662 |
-
"step": 465
|
| 663 |
-
},
|
| 664 |
-
{
|
| 665 |
-
"epoch": 11.75,
|
| 666 |
-
"learning_rate": 0.00011710752518939722,
|
| 667 |
-
"loss": 1.5808,
|
| 668 |
-
"step": 470
|
| 669 |
-
},
|
| 670 |
-
{
|
| 671 |
-
"epoch": 11.88,
|
| 672 |
-
"learning_rate": 0.00013197813593027427,
|
| 673 |
-
"loss": 1.5626,
|
| 674 |
-
"step": 475
|
| 675 |
-
},
|
| 676 |
-
{
|
| 677 |
-
"epoch": 12.0,
|
| 678 |
-
"learning_rate": 0.0001372,
|
| 679 |
-
"loss": 1.5582,
|
| 680 |
-
"step": 480
|
| 681 |
-
},
|
| 682 |
-
{
|
| 683 |
-
"epoch": 12.0,
|
| 684 |
-
"eval_loss": 1.4257222414016724,
|
| 685 |
-
"eval_runtime": 2.9531,
|
| 686 |
-
"eval_samples_per_second": 22.688,
|
| 687 |
-
"eval_steps_per_second": 3.048,
|
| 688 |
-
"step": 480
|
| 689 |
-
},
|
| 690 |
-
{
|
| 691 |
-
"epoch": 11.83,
|
| 692 |
-
"learning_rate": 0.00012756647503932202,
|
| 693 |
-
"loss": 1.532,
|
| 694 |
-
"step": 485
|
| 695 |
-
},
|
| 696 |
-
{
|
| 697 |
-
"epoch": 11.95,
|
| 698 |
-
"learning_rate": 0.0001363960370713319,
|
| 699 |
-
"loss": 1.6289,
|
| 700 |
-
"step": 490
|
| 701 |
-
},
|
| 702 |
-
{
|
| 703 |
-
"epoch": 12.0,
|
| 704 |
-
"eval_loss": 1.3016469478607178,
|
| 705 |
-
"eval_runtime": 2.8272,
|
| 706 |
-
"eval_samples_per_second": 21.222,
|
| 707 |
-
"eval_steps_per_second": 2.83,
|
| 708 |
-
"step": 492
|
| 709 |
-
},
|
| 710 |
-
{
|
| 711 |
-
"epoch": 12.07,
|
| 712 |
-
"learning_rate": 0.00013539550607801572,
|
| 713 |
-
"loss": 1.5711,
|
| 714 |
-
"step": 495
|
| 715 |
-
},
|
| 716 |
-
{
|
| 717 |
-
"epoch": 12.2,
|
| 718 |
-
"learning_rate": 0.00012470995414859683,
|
| 719 |
-
"loss": 1.5507,
|
| 720 |
-
"step": 500
|
| 721 |
-
},
|
| 722 |
-
{
|
| 723 |
-
"epoch": 12.32,
|
| 724 |
-
"learning_rate": 0.00010588873393008394,
|
| 725 |
-
"loss": 1.5444,
|
| 726 |
-
"step": 505
|
| 727 |
-
},
|
| 728 |
-
{
|
| 729 |
-
"epoch": 12.44,
|
| 730 |
-
"learning_rate": 8.166083008869614e-05,
|
| 731 |
-
"loss": 1.5625,
|
| 732 |
-
"step": 510
|
| 733 |
-
},
|
| 734 |
-
{
|
| 735 |
-
"epoch": 12.56,
|
| 736 |
-
"learning_rate": 5.553916991130382e-05,
|
| 737 |
-
"loss": 1.523,
|
| 738 |
-
"step": 515
|
| 739 |
-
},
|
| 740 |
-
{
|
| 741 |
-
"epoch": 12.68,
|
| 742 |
-
"learning_rate": 3.131126606991604e-05,
|
| 743 |
-
"loss": 1.5342,
|
| 744 |
-
"step": 520
|
| 745 |
-
},
|
| 746 |
-
{
|
| 747 |
-
"epoch": 12.8,
|
| 748 |
-
"learning_rate": 1.2490045851403148e-05,
|
| 749 |
-
"loss": 1.4935,
|
| 750 |
-
"step": 525
|
| 751 |
-
},
|
| 752 |
-
{
|
| 753 |
-
"epoch": 12.93,
|
| 754 |
-
"learning_rate": 1.8044939219843934e-06,
|
| 755 |
-
"loss": 1.5076,
|
| 756 |
-
"step": 530
|
| 757 |
-
},
|
| 758 |
-
{
|
| 759 |
-
"epoch": 13.0,
|
| 760 |
-
"eval_loss": 1.288225769996643,
|
| 761 |
-
"eval_runtime": 2.8008,
|
| 762 |
-
"eval_samples_per_second": 21.423,
|
| 763 |
-
"eval_steps_per_second": 2.856,
|
| 764 |
-
"step": 533
|
| 765 |
}
|
| 766 |
],
|
| 767 |
-
"max_steps":
|
| 768 |
-
"num_train_epochs":
|
| 769 |
-
"total_flos":
|
| 770 |
"trial_name": null,
|
| 771 |
"trial_params": null
|
| 772 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.3811118602752686,
|
| 3 |
+
"best_model_checkpoint": "output/the-king-and-the-jester/checkpoint-41",
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"global_step": 41,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 0.12,
|
| 12 |
+
"learning_rate": 0.0001322266681456038,
|
| 13 |
+
"loss": 1.4322,
|
| 14 |
"step": 5
|
| 15 |
},
|
| 16 |
{
|
| 17 |
+
"epoch": 0.24,
|
| 18 |
+
"learning_rate": 0.00011802778132101399,
|
| 19 |
+
"loss": 1.3789,
|
| 20 |
"step": 10
|
| 21 |
},
|
| 22 |
{
|
| 23 |
+
"epoch": 0.37,
|
| 24 |
+
"learning_rate": 9.666210850995409e-05,
|
| 25 |
+
"loss": 1.4705,
|
| 26 |
"step": 15
|
| 27 |
},
|
| 28 |
{
|
| 29 |
+
"epoch": 0.49,
|
| 30 |
+
"learning_rate": 7.12275675311363e-05,
|
| 31 |
+
"loss": 1.3895,
|
| 32 |
"step": 20
|
| 33 |
},
|
| 34 |
{
|
| 35 |
+
"epoch": 0.61,
|
| 36 |
+
"learning_rate": 4.541204214117678e-05,
|
| 37 |
+
"loss": 1.4426,
|
| 38 |
"step": 25
|
| 39 |
},
|
| 40 |
{
|
| 41 |
+
"epoch": 0.73,
|
| 42 |
+
"learning_rate": 2.295865696864204e-05,
|
| 43 |
+
"loss": 1.4315,
|
| 44 |
"step": 30
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.85,
|
| 48 |
+
"learning_rate": 7.123042792471563e-06,
|
| 49 |
+
"loss": 1.3887,
|
| 50 |
"step": 35
|
| 51 |
},
|
| 52 |
{
|
| 53 |
+
"epoch": 0.98,
|
| 54 |
+
"learning_rate": 2.0128603879541336e-07,
|
| 55 |
+
"loss": 1.4529,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 56 |
"step": 40
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 1.0,
|
| 60 |
+
"eval_loss": 1.3811118602752686,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 61 |
"eval_runtime": 2.6826,
|
| 62 |
+
"eval_samples_per_second": 20.875,
|
| 63 |
+
"eval_steps_per_second": 2.609,
|
| 64 |
+
"step": 41
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 65 |
}
|
| 66 |
],
|
| 67 |
+
"max_steps": 574,
|
| 68 |
+
"num_train_epochs": 14,
|
| 69 |
+
"total_flos": 42590601216000.0,
|
| 70 |
"trial_name": null,
|
| 71 |
"trial_params": null
|
| 72 |
}
|
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:d62e5f9b8962b5980207df52958a170de8d798048c5b53d9e689844dc14eb9fb
|
| 3 |
+
size 2863
|