Training in progress, step 2000
Browse files- added_tokens.json +0 -0
- config.json +3 -3
- last-checkpoint/added_tokens.json +0 -0
- last-checkpoint/config.json +3 -3
- last-checkpoint/optimizer.pt +2 -2
- last-checkpoint/pytorch_model.bin +2 -2
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/tokenizer.json +0 -0
- last-checkpoint/trainer_state.json +29 -482
- last-checkpoint/training_args.bin +2 -2
- pytorch_model.bin +2 -2
- runs/Jun05_10-45-59_0a95bf9de5ac/1685962630.6427722/events.out.tfevents.1685962630.0a95bf9de5ac.3272.1 +3 -0
- runs/Jun05_10-45-59_0a95bf9de5ac/events.out.tfevents.1685962630.0a95bf9de5ac.3272.0 +3 -0
- tokenizer.json +0 -0
- training_args.bin +2 -2
added_tokens.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
CHANGED
|
@@ -84,7 +84,7 @@
|
|
| 84 |
"typical_p": 1.0,
|
| 85 |
"use_bfloat16": false,
|
| 86 |
"use_cache": true,
|
| 87 |
-
"vocab_size":
|
| 88 |
},
|
| 89 |
"decoder_start_token_id": 101,
|
| 90 |
"early_stopping": true,
|
|
@@ -167,7 +167,7 @@
|
|
| 167 |
"typical_p": 1.0,
|
| 168 |
"use_bfloat16": false,
|
| 169 |
"use_cache": true,
|
| 170 |
-
"vocab_size":
|
| 171 |
},
|
| 172 |
"eos_token_id": 102,
|
| 173 |
"is_encoder_decoder": true,
|
|
@@ -178,5 +178,5 @@
|
|
| 178 |
"pad_token_id": 0,
|
| 179 |
"torch_dtype": "float32",
|
| 180 |
"transformers_version": null,
|
| 181 |
-
"vocab_size":
|
| 182 |
}
|
|
|
|
| 84 |
"typical_p": 1.0,
|
| 85 |
"use_bfloat16": false,
|
| 86 |
"use_cache": true,
|
| 87 |
+
"vocab_size": 32608
|
| 88 |
},
|
| 89 |
"decoder_start_token_id": 101,
|
| 90 |
"early_stopping": true,
|
|
|
|
| 167 |
"typical_p": 1.0,
|
| 168 |
"use_bfloat16": false,
|
| 169 |
"use_cache": true,
|
| 170 |
+
"vocab_size": 32608
|
| 171 |
},
|
| 172 |
"eos_token_id": 102,
|
| 173 |
"is_encoder_decoder": true,
|
|
|
|
| 178 |
"pad_token_id": 0,
|
| 179 |
"torch_dtype": "float32",
|
| 180 |
"transformers_version": null,
|
| 181 |
+
"vocab_size": 32608
|
| 182 |
}
|
last-checkpoint/added_tokens.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last-checkpoint/config.json
CHANGED
|
@@ -84,7 +84,7 @@
|
|
| 84 |
"typical_p": 1.0,
|
| 85 |
"use_bfloat16": false,
|
| 86 |
"use_cache": true,
|
| 87 |
-
"vocab_size":
|
| 88 |
},
|
| 89 |
"decoder_start_token_id": 101,
|
| 90 |
"early_stopping": true,
|
|
@@ -167,7 +167,7 @@
|
|
| 167 |
"typical_p": 1.0,
|
| 168 |
"use_bfloat16": false,
|
| 169 |
"use_cache": true,
|
| 170 |
-
"vocab_size":
|
| 171 |
},
|
| 172 |
"eos_token_id": 102,
|
| 173 |
"is_encoder_decoder": true,
|
|
@@ -178,5 +178,5 @@
|
|
| 178 |
"pad_token_id": 0,
|
| 179 |
"torch_dtype": "float32",
|
| 180 |
"transformers_version": null,
|
| 181 |
-
"vocab_size":
|
| 182 |
}
|
|
|
|
| 84 |
"typical_p": 1.0,
|
| 85 |
"use_bfloat16": false,
|
| 86 |
"use_cache": true,
|
| 87 |
+
"vocab_size": 32608
|
| 88 |
},
|
| 89 |
"decoder_start_token_id": 101,
|
| 90 |
"early_stopping": true,
|
|
|
|
| 167 |
"typical_p": 1.0,
|
| 168 |
"use_bfloat16": false,
|
| 169 |
"use_cache": true,
|
| 170 |
+
"vocab_size": 32608
|
| 171 |
},
|
| 172 |
"eos_token_id": 102,
|
| 173 |
"is_encoder_decoder": true,
|
|
|
|
| 178 |
"pad_token_id": 0,
|
| 179 |
"torch_dtype": "float32",
|
| 180 |
"transformers_version": null,
|
| 181 |
+
"vocab_size": 32608
|
| 182 |
}
|
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 sha256:95248b59e7dac0d789b6b077fbe09ce5175324e63b5e9cdd37a3a30c2cde9027
|
| 3 |
+
size 2000137067
|
last-checkpoint/pytorch_model.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 sha256:4238518d766751ead10635c197669c039a8c46869571a7f8fc96716f256600df
|
| 3 |
+
size 1002469625
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dda8e14cf65113c4145f87b0ecbda755c0d32ab5bbb56548e3c45d7ecd14a2c9
|
| 3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9c68e8f52d353c005549c69e33b5a29ace5f59d7300d7ea3a17b4a529d455d0
|
| 3 |
size 627
|
last-checkpoint/tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -10,591 +10,138 @@
|
|
| 10 |
{
|
| 11 |
"epoch": 0.07,
|
| 12 |
"learning_rate": 2.0000000000000003e-06,
|
| 13 |
-
"loss":
|
| 14 |
"step": 100
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.14,
|
| 18 |
"learning_rate": 4.000000000000001e-06,
|
| 19 |
-
"loss":
|
| 20 |
"step": 200
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.21,
|
| 24 |
"learning_rate": 6e-06,
|
| 25 |
-
"loss": 41.
|
| 26 |
"step": 300
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.28,
|
| 30 |
"learning_rate": 8.000000000000001e-06,
|
| 31 |
-
"loss": 36.
|
| 32 |
"step": 400
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 0.35,
|
| 36 |
"learning_rate": 1e-05,
|
| 37 |
-
"loss": 33.
|
| 38 |
"step": 500
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.42,
|
| 42 |
"learning_rate": 1.2e-05,
|
| 43 |
-
"loss":
|
| 44 |
"step": 600
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.49,
|
| 48 |
"learning_rate": 1.4000000000000001e-05,
|
| 49 |
-
"loss": 28.
|
| 50 |
"step": 700
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 0.56,
|
| 54 |
"learning_rate": 1.6000000000000003e-05,
|
| 55 |
-
"loss":
|
| 56 |
"step": 800
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 0.63,
|
| 60 |
"learning_rate": 1.8e-05,
|
| 61 |
-
"loss":
|
| 62 |
"step": 900
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 0.7,
|
| 66 |
"learning_rate": 2e-05,
|
| 67 |
-
"loss":
|
| 68 |
"step": 1000
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"epoch": 0.77,
|
| 72 |
"learning_rate": 2.2000000000000003e-05,
|
| 73 |
-
"loss":
|
| 74 |
"step": 1100
|
| 75 |
},
|
| 76 |
{
|
| 77 |
"epoch": 0.84,
|
| 78 |
"learning_rate": 2.4e-05,
|
| 79 |
-
"loss":
|
| 80 |
"step": 1200
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 0.91,
|
| 84 |
"learning_rate": 2.6000000000000002e-05,
|
| 85 |
-
"loss":
|
| 86 |
"step": 1300
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.98,
|
| 90 |
"learning_rate": 2.8000000000000003e-05,
|
| 91 |
-
"loss":
|
| 92 |
"step": 1400
|
| 93 |
},
|
| 94 |
{
|
| 95 |
"epoch": 1.05,
|
| 96 |
"learning_rate": 3e-05,
|
| 97 |
-
"loss":
|
| 98 |
"step": 1500
|
| 99 |
},
|
| 100 |
{
|
| 101 |
"epoch": 1.12,
|
| 102 |
"learning_rate": 3.2000000000000005e-05,
|
| 103 |
-
"loss":
|
| 104 |
"step": 1600
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"epoch": 1.19,
|
| 108 |
"learning_rate": 3.4000000000000007e-05,
|
| 109 |
-
"loss":
|
| 110 |
"step": 1700
|
| 111 |
},
|
| 112 |
{
|
| 113 |
"epoch": 1.26,
|
| 114 |
"learning_rate": 3.6e-05,
|
| 115 |
-
"loss": 9.
|
| 116 |
"step": 1800
|
| 117 |
},
|
| 118 |
{
|
| 119 |
"epoch": 1.33,
|
| 120 |
"learning_rate": 3.8e-05,
|
| 121 |
-
"loss":
|
| 122 |
"step": 1900
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 1.4,
|
| 126 |
"learning_rate": 4e-05,
|
| 127 |
-
"loss": 6.
|
| 128 |
"step": 2000
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 1.4,
|
| 132 |
-
"eval_bleu": 3.
|
| 133 |
"eval_em": 0.0,
|
| 134 |
-
"eval_gen_len":
|
| 135 |
-
"eval_loss": 6.
|
| 136 |
-
"eval_runtime":
|
| 137 |
-
"eval_samples_per_second": 0.
|
| 138 |
-
"eval_steps_per_second": 0.
|
| 139 |
"step": 2000
|
| 140 |
-
},
|
| 141 |
-
{
|
| 142 |
-
"epoch": 1.47,
|
| 143 |
-
"learning_rate": 4.2e-05,
|
| 144 |
-
"loss": 6.0941,
|
| 145 |
-
"step": 2100
|
| 146 |
-
},
|
| 147 |
-
{
|
| 148 |
-
"epoch": 1.54,
|
| 149 |
-
"learning_rate": 4.4000000000000006e-05,
|
| 150 |
-
"loss": 5.6741,
|
| 151 |
-
"step": 2200
|
| 152 |
-
},
|
| 153 |
-
{
|
| 154 |
-
"epoch": 1.61,
|
| 155 |
-
"learning_rate": 4.600000000000001e-05,
|
| 156 |
-
"loss": 5.4757,
|
| 157 |
-
"step": 2300
|
| 158 |
-
},
|
| 159 |
-
{
|
| 160 |
-
"epoch": 1.68,
|
| 161 |
-
"learning_rate": 4.8e-05,
|
| 162 |
-
"loss": 5.242,
|
| 163 |
-
"step": 2400
|
| 164 |
-
},
|
| 165 |
-
{
|
| 166 |
-
"epoch": 1.75,
|
| 167 |
-
"learning_rate": 5e-05,
|
| 168 |
-
"loss": 5.0108,
|
| 169 |
-
"step": 2500
|
| 170 |
-
},
|
| 171 |
-
{
|
| 172 |
-
"epoch": 1.82,
|
| 173 |
-
"learning_rate": 4.944121591417077e-05,
|
| 174 |
-
"loss": 4.8595,
|
| 175 |
-
"step": 2600
|
| 176 |
-
},
|
| 177 |
-
{
|
| 178 |
-
"epoch": 1.89,
|
| 179 |
-
"learning_rate": 4.888243182834153e-05,
|
| 180 |
-
"loss": 4.695,
|
| 181 |
-
"step": 2700
|
| 182 |
-
},
|
| 183 |
-
{
|
| 184 |
-
"epoch": 1.96,
|
| 185 |
-
"learning_rate": 4.8323647742512295e-05,
|
| 186 |
-
"loss": 4.5706,
|
| 187 |
-
"step": 2800
|
| 188 |
-
},
|
| 189 |
-
{
|
| 190 |
-
"epoch": 2.03,
|
| 191 |
-
"learning_rate": 4.776486365668306e-05,
|
| 192 |
-
"loss": 4.2498,
|
| 193 |
-
"step": 2900
|
| 194 |
-
},
|
| 195 |
-
{
|
| 196 |
-
"epoch": 2.1,
|
| 197 |
-
"learning_rate": 4.720607957085382e-05,
|
| 198 |
-
"loss": 4.1223,
|
| 199 |
-
"step": 3000
|
| 200 |
-
},
|
| 201 |
-
{
|
| 202 |
-
"epoch": 2.17,
|
| 203 |
-
"learning_rate": 4.664729548502459e-05,
|
| 204 |
-
"loss": 4.0181,
|
| 205 |
-
"step": 3100
|
| 206 |
-
},
|
| 207 |
-
{
|
| 208 |
-
"epoch": 2.24,
|
| 209 |
-
"learning_rate": 4.6088511399195353e-05,
|
| 210 |
-
"loss": 3.8722,
|
| 211 |
-
"step": 3200
|
| 212 |
-
},
|
| 213 |
-
{
|
| 214 |
-
"epoch": 2.31,
|
| 215 |
-
"learning_rate": 4.552972731336611e-05,
|
| 216 |
-
"loss": 3.7786,
|
| 217 |
-
"step": 3300
|
| 218 |
-
},
|
| 219 |
-
{
|
| 220 |
-
"epoch": 2.38,
|
| 221 |
-
"learning_rate": 4.497094322753688e-05,
|
| 222 |
-
"loss": 3.6403,
|
| 223 |
-
"step": 3400
|
| 224 |
-
},
|
| 225 |
-
{
|
| 226 |
-
"epoch": 2.45,
|
| 227 |
-
"learning_rate": 4.4412159141707646e-05,
|
| 228 |
-
"loss": 3.5437,
|
| 229 |
-
"step": 3500
|
| 230 |
-
},
|
| 231 |
-
{
|
| 232 |
-
"epoch": 2.52,
|
| 233 |
-
"learning_rate": 4.385337505587841e-05,
|
| 234 |
-
"loss": 3.389,
|
| 235 |
-
"step": 3600
|
| 236 |
-
},
|
| 237 |
-
{
|
| 238 |
-
"epoch": 2.59,
|
| 239 |
-
"learning_rate": 4.329459097004918e-05,
|
| 240 |
-
"loss": 3.2395,
|
| 241 |
-
"step": 3700
|
| 242 |
-
},
|
| 243 |
-
{
|
| 244 |
-
"epoch": 2.66,
|
| 245 |
-
"learning_rate": 4.2735806884219945e-05,
|
| 246 |
-
"loss": 3.1786,
|
| 247 |
-
"step": 3800
|
| 248 |
-
},
|
| 249 |
-
{
|
| 250 |
-
"epoch": 2.73,
|
| 251 |
-
"learning_rate": 4.2177022798390704e-05,
|
| 252 |
-
"loss": 3.0657,
|
| 253 |
-
"step": 3900
|
| 254 |
-
},
|
| 255 |
-
{
|
| 256 |
-
"epoch": 2.8,
|
| 257 |
-
"learning_rate": 4.161823871256147e-05,
|
| 258 |
-
"loss": 3.032,
|
| 259 |
-
"step": 4000
|
| 260 |
-
},
|
| 261 |
-
{
|
| 262 |
-
"epoch": 2.8,
|
| 263 |
-
"eval_bleu": 27.701,
|
| 264 |
-
"eval_em": 0.0,
|
| 265 |
-
"eval_gen_len": 33.9568,
|
| 266 |
-
"eval_loss": 2.904534339904785,
|
| 267 |
-
"eval_runtime": 297.5953,
|
| 268 |
-
"eval_samples_per_second": 4.049,
|
| 269 |
-
"eval_steps_per_second": 0.507,
|
| 270 |
-
"step": 4000
|
| 271 |
-
},
|
| 272 |
-
{
|
| 273 |
-
"epoch": 2.87,
|
| 274 |
-
"learning_rate": 4.105945462673223e-05,
|
| 275 |
-
"loss": 2.8755,
|
| 276 |
-
"step": 4100
|
| 277 |
-
},
|
| 278 |
-
{
|
| 279 |
-
"epoch": 2.94,
|
| 280 |
-
"learning_rate": 4.0500670540903e-05,
|
| 281 |
-
"loss": 2.8396,
|
| 282 |
-
"step": 4200
|
| 283 |
-
},
|
| 284 |
-
{
|
| 285 |
-
"epoch": 3.0,
|
| 286 |
-
"learning_rate": 3.994188645507376e-05,
|
| 287 |
-
"loss": 2.7454,
|
| 288 |
-
"step": 4300
|
| 289 |
-
},
|
| 290 |
-
{
|
| 291 |
-
"epoch": 3.07,
|
| 292 |
-
"learning_rate": 3.938310236924452e-05,
|
| 293 |
-
"loss": 2.5218,
|
| 294 |
-
"step": 4400
|
| 295 |
-
},
|
| 296 |
-
{
|
| 297 |
-
"epoch": 3.14,
|
| 298 |
-
"learning_rate": 3.882431828341529e-05,
|
| 299 |
-
"loss": 2.4895,
|
| 300 |
-
"step": 4500
|
| 301 |
-
},
|
| 302 |
-
{
|
| 303 |
-
"epoch": 3.21,
|
| 304 |
-
"learning_rate": 3.8265534197586055e-05,
|
| 305 |
-
"loss": 2.4554,
|
| 306 |
-
"step": 4600
|
| 307 |
-
},
|
| 308 |
-
{
|
| 309 |
-
"epoch": 3.28,
|
| 310 |
-
"learning_rate": 3.7706750111756815e-05,
|
| 311 |
-
"loss": 2.3573,
|
| 312 |
-
"step": 4700
|
| 313 |
-
},
|
| 314 |
-
{
|
| 315 |
-
"epoch": 3.35,
|
| 316 |
-
"learning_rate": 3.714796602592758e-05,
|
| 317 |
-
"loss": 2.2979,
|
| 318 |
-
"step": 4800
|
| 319 |
-
},
|
| 320 |
-
{
|
| 321 |
-
"epoch": 3.42,
|
| 322 |
-
"learning_rate": 3.658918194009835e-05,
|
| 323 |
-
"loss": 2.1874,
|
| 324 |
-
"step": 4900
|
| 325 |
-
},
|
| 326 |
-
{
|
| 327 |
-
"epoch": 3.49,
|
| 328 |
-
"learning_rate": 3.603039785426911e-05,
|
| 329 |
-
"loss": 2.1803,
|
| 330 |
-
"step": 5000
|
| 331 |
-
},
|
| 332 |
-
{
|
| 333 |
-
"epoch": 3.56,
|
| 334 |
-
"learning_rate": 3.5471613768439874e-05,
|
| 335 |
-
"loss": 2.1553,
|
| 336 |
-
"step": 5100
|
| 337 |
-
},
|
| 338 |
-
{
|
| 339 |
-
"epoch": 3.63,
|
| 340 |
-
"learning_rate": 3.491282968261064e-05,
|
| 341 |
-
"loss": 2.0567,
|
| 342 |
-
"step": 5200
|
| 343 |
-
},
|
| 344 |
-
{
|
| 345 |
-
"epoch": 3.7,
|
| 346 |
-
"learning_rate": 3.4354045596781406e-05,
|
| 347 |
-
"loss": 2.0147,
|
| 348 |
-
"step": 5300
|
| 349 |
-
},
|
| 350 |
-
{
|
| 351 |
-
"epoch": 3.77,
|
| 352 |
-
"learning_rate": 3.379526151095217e-05,
|
| 353 |
-
"loss": 1.9817,
|
| 354 |
-
"step": 5400
|
| 355 |
-
},
|
| 356 |
-
{
|
| 357 |
-
"epoch": 3.84,
|
| 358 |
-
"learning_rate": 3.323647742512294e-05,
|
| 359 |
-
"loss": 1.8843,
|
| 360 |
-
"step": 5500
|
| 361 |
-
},
|
| 362 |
-
{
|
| 363 |
-
"epoch": 3.91,
|
| 364 |
-
"learning_rate": 3.26776933392937e-05,
|
| 365 |
-
"loss": 1.8849,
|
| 366 |
-
"step": 5600
|
| 367 |
-
},
|
| 368 |
-
{
|
| 369 |
-
"epoch": 3.98,
|
| 370 |
-
"learning_rate": 3.2118909253464465e-05,
|
| 371 |
-
"loss": 1.8232,
|
| 372 |
-
"step": 5700
|
| 373 |
-
},
|
| 374 |
-
{
|
| 375 |
-
"epoch": 4.05,
|
| 376 |
-
"learning_rate": 3.156012516763523e-05,
|
| 377 |
-
"loss": 1.6714,
|
| 378 |
-
"step": 5800
|
| 379 |
-
},
|
| 380 |
-
{
|
| 381 |
-
"epoch": 4.12,
|
| 382 |
-
"learning_rate": 3.100134108180599e-05,
|
| 383 |
-
"loss": 1.6047,
|
| 384 |
-
"step": 5900
|
| 385 |
-
},
|
| 386 |
-
{
|
| 387 |
-
"epoch": 4.19,
|
| 388 |
-
"learning_rate": 3.0442556995976757e-05,
|
| 389 |
-
"loss": 1.5893,
|
| 390 |
-
"step": 6000
|
| 391 |
-
},
|
| 392 |
-
{
|
| 393 |
-
"epoch": 4.19,
|
| 394 |
-
"eval_bleu": 57.7509,
|
| 395 |
-
"eval_em": 0.0033,
|
| 396 |
-
"eval_gen_len": 44.132,
|
| 397 |
-
"eval_loss": 1.7326730489730835,
|
| 398 |
-
"eval_runtime": 426.2734,
|
| 399 |
-
"eval_samples_per_second": 2.827,
|
| 400 |
-
"eval_steps_per_second": 0.354,
|
| 401 |
-
"step": 6000
|
| 402 |
-
},
|
| 403 |
-
{
|
| 404 |
-
"epoch": 4.26,
|
| 405 |
-
"learning_rate": 2.9883772910147524e-05,
|
| 406 |
-
"loss": 1.5864,
|
| 407 |
-
"step": 6100
|
| 408 |
-
},
|
| 409 |
-
{
|
| 410 |
-
"epoch": 4.33,
|
| 411 |
-
"learning_rate": 2.9324988824318283e-05,
|
| 412 |
-
"loss": 1.5608,
|
| 413 |
-
"step": 6200
|
| 414 |
-
},
|
| 415 |
-
{
|
| 416 |
-
"epoch": 4.4,
|
| 417 |
-
"learning_rate": 2.876620473848905e-05,
|
| 418 |
-
"loss": 1.5144,
|
| 419 |
-
"step": 6300
|
| 420 |
-
},
|
| 421 |
-
{
|
| 422 |
-
"epoch": 4.47,
|
| 423 |
-
"learning_rate": 2.8207420652659816e-05,
|
| 424 |
-
"loss": 1.4582,
|
| 425 |
-
"step": 6400
|
| 426 |
-
},
|
| 427 |
-
{
|
| 428 |
-
"epoch": 4.54,
|
| 429 |
-
"learning_rate": 2.7648636566830576e-05,
|
| 430 |
-
"loss": 1.4793,
|
| 431 |
-
"step": 6500
|
| 432 |
-
},
|
| 433 |
-
{
|
| 434 |
-
"epoch": 4.61,
|
| 435 |
-
"learning_rate": 2.7089852481001342e-05,
|
| 436 |
-
"loss": 1.472,
|
| 437 |
-
"step": 6600
|
| 438 |
-
},
|
| 439 |
-
{
|
| 440 |
-
"epoch": 4.68,
|
| 441 |
-
"learning_rate": 2.653106839517211e-05,
|
| 442 |
-
"loss": 1.4424,
|
| 443 |
-
"step": 6700
|
| 444 |
-
},
|
| 445 |
-
{
|
| 446 |
-
"epoch": 4.75,
|
| 447 |
-
"learning_rate": 2.597228430934287e-05,
|
| 448 |
-
"loss": 1.3779,
|
| 449 |
-
"step": 6800
|
| 450 |
-
},
|
| 451 |
-
{
|
| 452 |
-
"epoch": 4.82,
|
| 453 |
-
"learning_rate": 2.5413500223513638e-05,
|
| 454 |
-
"loss": 1.3611,
|
| 455 |
-
"step": 6900
|
| 456 |
-
},
|
| 457 |
-
{
|
| 458 |
-
"epoch": 4.89,
|
| 459 |
-
"learning_rate": 2.48547161376844e-05,
|
| 460 |
-
"loss": 1.3311,
|
| 461 |
-
"step": 7000
|
| 462 |
-
},
|
| 463 |
-
{
|
| 464 |
-
"epoch": 4.96,
|
| 465 |
-
"learning_rate": 2.4295932051855164e-05,
|
| 466 |
-
"loss": 1.3164,
|
| 467 |
-
"step": 7100
|
| 468 |
-
},
|
| 469 |
-
{
|
| 470 |
-
"epoch": 5.03,
|
| 471 |
-
"learning_rate": 2.373714796602593e-05,
|
| 472 |
-
"loss": 1.2119,
|
| 473 |
-
"step": 7200
|
| 474 |
-
},
|
| 475 |
-
{
|
| 476 |
-
"epoch": 5.1,
|
| 477 |
-
"learning_rate": 2.3178363880196693e-05,
|
| 478 |
-
"loss": 1.1122,
|
| 479 |
-
"step": 7300
|
| 480 |
-
},
|
| 481 |
-
{
|
| 482 |
-
"epoch": 5.17,
|
| 483 |
-
"learning_rate": 2.2619579794367456e-05,
|
| 484 |
-
"loss": 1.1198,
|
| 485 |
-
"step": 7400
|
| 486 |
-
},
|
| 487 |
-
{
|
| 488 |
-
"epoch": 5.24,
|
| 489 |
-
"learning_rate": 2.206079570853822e-05,
|
| 490 |
-
"loss": 1.0416,
|
| 491 |
-
"step": 7500
|
| 492 |
-
},
|
| 493 |
-
{
|
| 494 |
-
"epoch": 5.31,
|
| 495 |
-
"learning_rate": 2.1502011622708985e-05,
|
| 496 |
-
"loss": 1.1042,
|
| 497 |
-
"step": 7600
|
| 498 |
-
},
|
| 499 |
-
{
|
| 500 |
-
"epoch": 5.38,
|
| 501 |
-
"learning_rate": 2.0943227536879752e-05,
|
| 502 |
-
"loss": 1.0715,
|
| 503 |
-
"step": 7700
|
| 504 |
-
},
|
| 505 |
-
{
|
| 506 |
-
"epoch": 5.45,
|
| 507 |
-
"learning_rate": 2.0384443451050515e-05,
|
| 508 |
-
"loss": 1.0815,
|
| 509 |
-
"step": 7800
|
| 510 |
-
},
|
| 511 |
-
{
|
| 512 |
-
"epoch": 5.52,
|
| 513 |
-
"learning_rate": 1.982565936522128e-05,
|
| 514 |
-
"loss": 1.0445,
|
| 515 |
-
"step": 7900
|
| 516 |
-
},
|
| 517 |
-
{
|
| 518 |
-
"epoch": 5.59,
|
| 519 |
-
"learning_rate": 1.9266875279392044e-05,
|
| 520 |
-
"loss": 1.0512,
|
| 521 |
-
"step": 8000
|
| 522 |
-
},
|
| 523 |
-
{
|
| 524 |
-
"epoch": 5.59,
|
| 525 |
-
"eval_bleu": 71.1272,
|
| 526 |
-
"eval_em": 0.0241,
|
| 527 |
-
"eval_gen_len": 46.0672,
|
| 528 |
-
"eval_loss": 1.2382431030273438,
|
| 529 |
-
"eval_runtime": 358.1089,
|
| 530 |
-
"eval_samples_per_second": 3.365,
|
| 531 |
-
"eval_steps_per_second": 0.422,
|
| 532 |
-
"step": 8000
|
| 533 |
-
},
|
| 534 |
-
{
|
| 535 |
-
"epoch": 5.66,
|
| 536 |
-
"learning_rate": 1.8708091193562807e-05,
|
| 537 |
-
"loss": 1.0201,
|
| 538 |
-
"step": 8100
|
| 539 |
-
},
|
| 540 |
-
{
|
| 541 |
-
"epoch": 5.73,
|
| 542 |
-
"learning_rate": 1.8149307107733573e-05,
|
| 543 |
-
"loss": 1.0377,
|
| 544 |
-
"step": 8200
|
| 545 |
-
},
|
| 546 |
-
{
|
| 547 |
-
"epoch": 5.8,
|
| 548 |
-
"learning_rate": 1.7590523021904336e-05,
|
| 549 |
-
"loss": 0.986,
|
| 550 |
-
"step": 8300
|
| 551 |
-
},
|
| 552 |
-
{
|
| 553 |
-
"epoch": 5.87,
|
| 554 |
-
"learning_rate": 1.70317389360751e-05,
|
| 555 |
-
"loss": 1.0244,
|
| 556 |
-
"step": 8400
|
| 557 |
-
},
|
| 558 |
-
{
|
| 559 |
-
"epoch": 5.94,
|
| 560 |
-
"learning_rate": 1.6472954850245866e-05,
|
| 561 |
-
"loss": 0.9654,
|
| 562 |
-
"step": 8500
|
| 563 |
-
},
|
| 564 |
-
{
|
| 565 |
-
"epoch": 6.01,
|
| 566 |
-
"learning_rate": 1.5914170764416632e-05,
|
| 567 |
-
"loss": 0.9454,
|
| 568 |
-
"step": 8600
|
| 569 |
-
},
|
| 570 |
-
{
|
| 571 |
-
"epoch": 6.08,
|
| 572 |
-
"learning_rate": 1.5355386678587395e-05,
|
| 573 |
-
"loss": 0.8179,
|
| 574 |
-
"step": 8700
|
| 575 |
-
},
|
| 576 |
-
{
|
| 577 |
-
"epoch": 6.15,
|
| 578 |
-
"learning_rate": 1.479660259275816e-05,
|
| 579 |
-
"loss": 0.8433,
|
| 580 |
-
"step": 8800
|
| 581 |
-
},
|
| 582 |
-
{
|
| 583 |
-
"epoch": 6.22,
|
| 584 |
-
"learning_rate": 1.4237818506928924e-05,
|
| 585 |
-
"loss": 0.8235,
|
| 586 |
-
"step": 8900
|
| 587 |
-
},
|
| 588 |
-
{
|
| 589 |
-
"epoch": 6.29,
|
| 590 |
-
"learning_rate": 1.3679034421099687e-05,
|
| 591 |
-
"loss": 0.832,
|
| 592 |
-
"step": 9000
|
| 593 |
}
|
| 594 |
],
|
| 595 |
"max_steps": 11448,
|
| 596 |
"num_train_epochs": 8,
|
| 597 |
-
"total_flos":
|
| 598 |
"trial_name": null,
|
| 599 |
"trial_params": null
|
| 600 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.397624039133473,
|
| 5 |
+
"global_step": 2000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 10 |
{
|
| 11 |
"epoch": 0.07,
|
| 12 |
"learning_rate": 2.0000000000000003e-06,
|
| 13 |
+
"loss": 87.2627,
|
| 14 |
"step": 100
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.14,
|
| 18 |
"learning_rate": 4.000000000000001e-06,
|
| 19 |
+
"loss": 52.4123,
|
| 20 |
"step": 200
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.21,
|
| 24 |
"learning_rate": 6e-06,
|
| 25 |
+
"loss": 41.3932,
|
| 26 |
"step": 300
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.28,
|
| 30 |
"learning_rate": 8.000000000000001e-06,
|
| 31 |
+
"loss": 36.7185,
|
| 32 |
"step": 400
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 0.35,
|
| 36 |
"learning_rate": 1e-05,
|
| 37 |
+
"loss": 33.4597,
|
| 38 |
"step": 500
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.42,
|
| 42 |
"learning_rate": 1.2e-05,
|
| 43 |
+
"loss": 31.1323,
|
| 44 |
"step": 600
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.49,
|
| 48 |
"learning_rate": 1.4000000000000001e-05,
|
| 49 |
+
"loss": 28.9204,
|
| 50 |
"step": 700
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 0.56,
|
| 54 |
"learning_rate": 1.6000000000000003e-05,
|
| 55 |
+
"loss": 27.0128,
|
| 56 |
"step": 800
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 0.63,
|
| 60 |
"learning_rate": 1.8e-05,
|
| 61 |
+
"loss": 25.1703,
|
| 62 |
"step": 900
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 0.7,
|
| 66 |
"learning_rate": 2e-05,
|
| 67 |
+
"loss": 23.5486,
|
| 68 |
"step": 1000
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"epoch": 0.77,
|
| 72 |
"learning_rate": 2.2000000000000003e-05,
|
| 73 |
+
"loss": 21.8419,
|
| 74 |
"step": 1100
|
| 75 |
},
|
| 76 |
{
|
| 77 |
"epoch": 0.84,
|
| 78 |
"learning_rate": 2.4e-05,
|
| 79 |
+
"loss": 20.3387,
|
| 80 |
"step": 1200
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 0.91,
|
| 84 |
"learning_rate": 2.6000000000000002e-05,
|
| 85 |
+
"loss": 18.7216,
|
| 86 |
"step": 1300
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.98,
|
| 90 |
"learning_rate": 2.8000000000000003e-05,
|
| 91 |
+
"loss": 16.7862,
|
| 92 |
"step": 1400
|
| 93 |
},
|
| 94 |
{
|
| 95 |
"epoch": 1.05,
|
| 96 |
"learning_rate": 3e-05,
|
| 97 |
+
"loss": 15.034,
|
| 98 |
"step": 1500
|
| 99 |
},
|
| 100 |
{
|
| 101 |
"epoch": 1.12,
|
| 102 |
"learning_rate": 3.2000000000000005e-05,
|
| 103 |
+
"loss": 13.3747,
|
| 104 |
"step": 1600
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"epoch": 1.19,
|
| 108 |
"learning_rate": 3.4000000000000007e-05,
|
| 109 |
+
"loss": 11.7581,
|
| 110 |
"step": 1700
|
| 111 |
},
|
| 112 |
{
|
| 113 |
"epoch": 1.26,
|
| 114 |
"learning_rate": 3.6e-05,
|
| 115 |
+
"loss": 9.9702,
|
| 116 |
"step": 1800
|
| 117 |
},
|
| 118 |
{
|
| 119 |
"epoch": 1.33,
|
| 120 |
"learning_rate": 3.8e-05,
|
| 121 |
+
"loss": 8.3363,
|
| 122 |
"step": 1900
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 1.4,
|
| 126 |
"learning_rate": 4e-05,
|
| 127 |
+
"loss": 6.9199,
|
| 128 |
"step": 2000
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 1.4,
|
| 132 |
+
"eval_bleu": 3.4801,
|
| 133 |
"eval_em": 0.0,
|
| 134 |
+
"eval_gen_len": 220.966,
|
| 135 |
+
"eval_loss": 6.3751444816589355,
|
| 136 |
+
"eval_runtime": 1604.7901,
|
| 137 |
+
"eval_samples_per_second": 0.751,
|
| 138 |
+
"eval_steps_per_second": 0.094,
|
| 139 |
"step": 2000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 140 |
}
|
| 141 |
],
|
| 142 |
"max_steps": 11448,
|
| 143 |
"num_train_epochs": 8,
|
| 144 |
+
"total_flos": 1328908826910720.0,
|
| 145 |
"trial_name": null,
|
| 146 |
"trial_params": null
|
| 147 |
}
|
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 sha256:0bb3fd12f0e9726bf97eb4344fe52ca7c4a117923bbaddabaa3847b6466f151f
|
| 3 |
+
size 4155
|
pytorch_model.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 sha256:4238518d766751ead10635c197669c039a8c46869571a7f8fc96716f256600df
|
| 3 |
+
size 1002469625
|
runs/Jun05_10-45-59_0a95bf9de5ac/1685962630.6427722/events.out.tfevents.1685962630.0a95bf9de5ac.3272.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:47943655f1ff4b3e0a5d8ce007bf952b1846b4f3695c5dcf053bdd1511d8da6e
|
| 3 |
+
size 6302
|
runs/Jun05_10-45-59_0a95bf9de5ac/events.out.tfevents.1685962630.0a95bf9de5ac.3272.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:098e0e6b4e1c013ebd1598cfcedd0c3450868df3bf0b760afd29eede229bcb12
|
| 3 |
+
size 12098
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
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 sha256:0bb3fd12f0e9726bf97eb4344fe52ca7c4a117923bbaddabaa3847b6466f151f
|
| 3 |
+
size 4155
|