File size: 25,073 Bytes
ac1ec4d 20261c8 ac1ec4d 20261c8 9f5b8d0 b71ffb9 1280a74 20261c8 b71ffb9 cc63ed3 20261c8 ef05d5a 1280a74 ef05d5a 20261c8 1280a74 20261c8 1280a74 20261c8 18f918f ef18151 91d88a3 c65045f 91d88a3 1f19c01 988877d 1aece92 988877d 1f19c01 9a4f571 54daf0f 9a4f571 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 |
---
license: mit
pipeline_tag: text-generation
library_name: transformers
language: [
'en', 'am', 'ar', 'as', 'az', 'be', 'bg', 'bn', 'br', 'bs', 'ca', 'cs', 'cy', 'da', 'de', 'el',
'eo', 'es', 'et', 'eu', 'fa', 'ff', 'fi', 'fr', 'fy', 'ga', 'gd', 'gl', 'gn', 'gu', 'ha', 'he',
'hi', 'hr', 'ht', 'hu', 'hy', 'id', 'ig', 'is', 'it', 'ja', 'jv', 'ka', 'kk', 'km', 'kn', 'ko',
'ku', 'ky', 'la', 'lg', 'li', 'ln', 'lo', 'lt', 'lv', 'mg', 'mk', 'ml', 'mn', 'mr', 'ms', 'my',
'ne', 'nl', 'no', 'ns', 'om', 'or', 'pa', 'pl', 'ps', 'pt', 'qu', 'rm', 'ro', 'ru', 'sa', 'si',
'sc', 'sd', 'sk', 'sl', 'so', 'sq', 'sr', 'ss', 'su', 'sv', 'sw', 'ta', 'te', 'th', 'tl', 'tn',
'tr', 'ug', 'uk', 'ur', 'uz', 'vi', 'wo', 'xh', 'yi', 'yo', 'zu',
]
datasets:
# core - base
- ontocord/fineweb-permissive-multilingual-2m
- distily/c4_multilingual_1M
- data-silence/sumnews
- xu-song/cc100-samples
- badrex/llm-emoji-dataset
- fblgit/simple-math
- Gusarich/math-expressions-1m
- neuralwork/arxiver
- christopher/rosetta-code
- nampdn-ai/tiny-codes
- JeanKaddour/minipile
# core - instruct
- NousResearch/hermes-function-calling-v1
- simplescaling/s1K-1.1
# base - instruct
- mlabonne/open-perfectblend
- allenai/tulu-3-sft-mixture
- rombodawg/Everything_Instruct_Multilingual
# base - reason
- open-r1/OpenR1-Math-220k
- open-thoughts/OpenThoughts-114k
- cognitivecomputations/dolphin-r1
- simplescaling/s1K-1.1
tags:
- chat
- core
- base
- instruct
- reason
---
# tangled-alpha-0.9-core
```bash
time python -B prepare_core_datasets.py
```
```
i=0, min_len=0, max_len=1073741824, block_size=1025, chunk_size=16400000, len(dataset)=5146620, len(dataset) * block_size=5275285500
Total number of tokens in the optimized dataset '../core-data-0-0-1073741824-1025-16000' is 5275285500
i=1, min_len=1025, max_len=2049, block_size=2049, chunk_size=16392000, len(dataset)=309838, len(dataset) * block_size=634858062
Total number of tokens in the optimized dataset '../core-data-1-1025-2049-2049-8000' is 634858062
i=2, min_len=2049, max_len=4097, block_size=4097, chunk_size=16388000, len(dataset)=113843, len(dataset) * block_size=466414771
Total number of tokens in the optimized dataset '../core-data-2-2049-4097-4097-4000' is 466414771
i=3, min_len=4097, max_len=8193, block_size=8193, chunk_size=16386000, len(dataset)=56713, len(dataset) * block_size=464649609
Total number of tokens in the optimized dataset '../core-data-3-4097-8193-8193-2000' is 464649609
i=4, min_len=8193, max_len=16385, block_size=16385, chunk_size=16385000, len(dataset)=37406, len(dataset) * block_size=612897310
Total number of tokens in the optimized dataset '../core-data-4-8193-16385-16385-1000' is 612897310
i=5, min_len=16385, max_len=32769, block_size=32769, chunk_size=16384500, len(dataset)=12737, len(dataset) * block_size=417378753
Total number of tokens in the optimized dataset '../core-data-5-16385-32769-32769-500' is 417378753
i=6, min_len=32769, max_len=65537, block_size=65537, chunk_size=16384250, len(dataset)=2824, len(dataset) * block_size=185076488
Total number of tokens in the optimized dataset '../core-data-6-32769-65537-65537-250' is 185076488
i=7, min_len=65537, max_len=131073, block_size=131073, chunk_size=16384125, len(dataset)=634, len(dataset) * block_size=83100282
Total number of tokens in the optimized dataset '../core-data-7-65537-131073-131073-125' is 83100282
real 292m54.341s
user 2118m1.154s
sys 12m2.746s
20G tangled-alpha-0.9-core/core-data-0-0-1073741824-1025-16000
2.4G tangled-alpha-0.9-core/core-data-1-1025-2049-2049-8000
1.8G tangled-alpha-0.9-core/core-data-2-2049-4097-4097-4000
1.8G tangled-alpha-0.9-core/core-data-3-4097-8193-8193-2000
2.3G tangled-alpha-0.9-core/core-data-4-8193-16385-16385-1000
1.6G tangled-alpha-0.9-core/core-data-5-16385-32769-32769-500
709M tangled-alpha-0.9-core/core-data-6-32769-65537-65537-250
321M tangled-alpha-0.9-core/core-data-7-65537-131073-131073-125
```
```bash
CUDA_VISIBLE_DEVICES=0 CUDA_LAUNCH_BLOCKING=0 PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True litgpt pretrain --config pretrain_core_model_0.yaml
```
```
Seed set to 23
Time to instantiate model: 0.44 seconds.
Total parameters: 234,914,304
Verifying settings ...
Measured TFLOPs: 55520.94
Epoch 1 | iter 64 step 1 | loss train: 11.977, val: n/a | iter time: 490.27 ms (step) remaining time: 6 days, 22:47:04
Epoch 1 | iter 128 step 2 | loss train: 11.970, val: n/a | iter time: 351.11 ms (step) remaining time: 4 days, 16:53:01
Epoch 1 | iter 192 step 3 | loss train: 11.971, val: n/a | iter time: 353.74 ms (step) remaining time: 3 days, 23:43:23
Epoch 1 | iter 256 step 4 | loss train: 11.974, val: n/a | iter time: 355.03 ms (step) remaining time: 3 days, 14:41:57
Epoch 1 | iter 320 step 5 | loss train: 11.964, val: n/a | iter time: 357.36 ms (step) remaining time: 3 days, 9:21:54
Epoch 1 | iter 384 step 6 | loss train: 11.957, val: n/a | iter time: 362.27 ms (step) remaining time: 3 days, 5:53:20
Epoch 1 | iter 448 step 7 | loss train: 11.948, val: n/a | iter time: 359.89 ms (step) remaining time: 3 days, 3:26:34
Epoch 1 | iter 512 step 8 | loss train: 11.938, val: n/a | iter time: 363.84 ms (step) remaining time: 3 days, 1:37:54
Epoch 1 | iter 576 step 9 | loss train: 11.920, val: n/a | iter time: 362.75 ms (step) remaining time: 3 days, 0:13:59
Epoch 1 | iter 640 step 10 | loss train: 11.900, val: n/a | iter time: 363.46 ms (step) remaining time: 2 days, 23:07:06
# ...
Epoch 1 | iter 643264 step 10051 | loss train: 2.834, val: 2.669 | iter time: 360.50 ms (step) remaining time: 0:03:59
Epoch 2 | iter 643328 step 10052 | loss train: 2.837, val: 2.669 | iter time: 359.53 ms (step) remaining time: 0:03:37
Epoch 2 | iter 643392 step 10053 | loss train: 2.768, val: 2.669 | iter time: 362.83 ms (step) remaining time: 0:03:15
Epoch 2 | iter 643456 step 10054 | loss train: 2.695, val: 2.669 | iter time: 363.85 ms (step) remaining time: 0:02:53
Epoch 2 | iter 643520 step 10055 | loss train: 2.768, val: 2.669 | iter time: 365.40 ms (step) remaining time: 0:02:30
Epoch 2 | iter 643584 step 10056 | loss train: 2.710, val: 2.669 | iter time: 364.72 ms (step) remaining time: 0:02:08
Epoch 2 | iter 643648 step 10057 | loss train: 2.749, val: 2.669 | iter time: 365.00 ms (step) remaining time: 0:01:46
Epoch 2 | iter 643712 step 10058 | loss train: 2.748, val: 2.669 | iter time: 363.42 ms (step) remaining time: 0:01:24
Epoch 2 | iter 643776 step 10059 | loss train: 2.710, val: 2.669 | iter time: 364.49 ms (step) remaining time: 0:01:02
Epoch 2 | iter 643840 step 10060 | loss train: 2.738, val: 2.669 | iter time: 364.43 ms (step) remaining time: 0:00:39
Epoch 2 | iter 643904 step 10061 | loss train: 2.734, val: 2.669 | iter time: 364.94 ms (step) remaining time: 0:00:17
Validating ...
Final evaluation | val loss: 2.669 | val ppl: 14.422
Saving checkpoint to '../out/pretrain-core-0/final/lit_model.pth'
----------------------------------------
| Performance
| - Total tokens : 5,275,279,360
| - Training Time : 223314.37 s
| - Tok/sec : 5541.09 tok/s
| ----------------------------------------
| Memory Usage
| - Memory Used : 22.33 GB
----------------------------------------
```
Backup `wandb`:
```bash
mv wandb wandb-pretrain-core-0
```
Copy config:
```bash
cp ../config-0.json ../out/pretrain-core-0/final/config.json
```
Chat with model:
```bash
CUDA_VISIBLE_DEVICES=0 CUDA_LAUNCH_BLOCKING=0 PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True litgpt chat ../out/pretrain-core-0/final
```
```bash
CUDA_VISIBLE_DEVICES=0 CUDA_LAUNCH_BLOCKING=0 PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True time litgpt evaluate --tasks 'leaderboard' --out_dir '../evaluate/pretrain-core-0/leaderboard/' --batch_size '4' --dtype 'bfloat16' '../out/pretrain-core-0/final'
```
```
| Tasks |Version|Filter|n-shot| Metric | |Value | |Stderr|
|-----------------------------------------------------------|-------|------|-----:|-----------------------|---|-----:|---|------|
|leaderboard | N/A| | | | | | | |
| - leaderboard_bbh | N/A| | | | | | | |
| - leaderboard_bbh_boolean_expressions | 1|none | 3|acc_norm |↑ |0.4600|± |0.0316|
| - leaderboard_bbh_causal_judgement | 1|none | 3|acc_norm |↑ |0.5134|± |0.0366|
| - leaderboard_bbh_date_understanding | 1|none | 3|acc_norm |↑ |0.1960|± |0.0252|
| - leaderboard_bbh_disambiguation_qa | 1|none | 3|acc_norm |↑ |0.3320|± |0.0298|
| - leaderboard_bbh_formal_fallacies | 1|none | 3|acc_norm |↑ |0.4680|± |0.0316|
| - leaderboard_bbh_geometric_shapes | 1|none | 3|acc_norm |↑ |0.2400|± |0.0271|
| - leaderboard_bbh_hyperbaton | 1|none | 3|acc_norm |↑ |0.5160|± |0.0317|
| - leaderboard_bbh_logical_deduction_five_objects | 1|none | 3|acc_norm |↑ |0.2040|± |0.0255|
| - leaderboard_bbh_logical_deduction_seven_objects | 1|none | 3|acc_norm |↑ |0.1320|± |0.0215|
| - leaderboard_bbh_logical_deduction_three_objects | 1|none | 3|acc_norm |↑ |0.3440|± |0.0301|
| - leaderboard_bbh_movie_recommendation | 1|none | 3|acc_norm |↑ |0.2680|± |0.0281|
| - leaderboard_bbh_navigate | 1|none | 3|acc_norm |↑ |0.5720|± |0.0314|
| - leaderboard_bbh_object_counting | 1|none | 3|acc_norm |↑ |0.0680|± |0.0160|
| - leaderboard_bbh_penguins_in_a_table | 1|none | 3|acc_norm |↑ |0.2055|± |0.0336|
| - leaderboard_bbh_reasoning_about_colored_objects | 1|none | 3|acc_norm |↑ |0.1760|± |0.0241|
| - leaderboard_bbh_ruin_names | 1|none | 3|acc_norm |↑ |0.2120|± |0.0259|
| - leaderboard_bbh_salient_translation_error_detection | 1|none | 3|acc_norm |↑ |0.2240|± |0.0264|
| - leaderboard_bbh_snarks | 1|none | 3|acc_norm |↑ |0.5393|± |0.0375|
| - leaderboard_bbh_sports_understanding | 1|none | 3|acc_norm |↑ |0.4600|± |0.0316|
| - leaderboard_bbh_temporal_sequences | 1|none | 3|acc_norm |↑ |0.2760|± |0.0283|
| - leaderboard_bbh_tracking_shuffled_objects_five_objects | 1|none | 3|acc_norm |↑ |0.1720|± |0.0239|
| - leaderboard_bbh_tracking_shuffled_objects_seven_objects| 1|none | 3|acc_norm |↑ |0.1360|± |0.0217|
| - leaderboard_bbh_tracking_shuffled_objects_three_objects| 1|none | 3|acc_norm |↑ |0.3320|± |0.0298|
| - leaderboard_bbh_web_of_lies | 1|none | 3|acc_norm |↑ |0.4880|± |0.0317|
| - leaderboard_gpqa | N/A| | | | | | | |
| - leaderboard_gpqa_diamond | 1|none | 0|acc_norm |↑ |0.2071|± |0.0289|
| - leaderboard_gpqa_extended | 1|none | 0|acc_norm |↑ |0.2637|± |0.0189|
| - leaderboard_gpqa_main | 1|none | 0|acc_norm |↑ |0.2612|± |0.0208|
| - leaderboard_ifeval | 3|none | 0|inst_level_loose_acc |↑ |0.2770|± | N/A|
| | |none | 0|inst_level_strict_acc |↑ |0.2710|± | N/A|
| | |none | 0|prompt_level_loose_acc |↑ |0.1534|± |0.0155|
| | |none | 0|prompt_level_strict_acc|↑ |0.1497|± |0.0154|
| - leaderboard_math_hard | N/A| | | | | | | |
| - leaderboard_math_algebra_hard | 2|none | 4|exact_match |↑ |0.0017|± |0.0012|
| - leaderboard_math_counting_and_prob_hard | 2|none | 4|exact_match |↑ |0.0000|± | 0|
| - leaderboard_math_geometry_hard | 2|none | 4|exact_match |↑ |0.0000|± | 0|
| - leaderboard_math_intermediate_algebra_hard | 2|none | 4|exact_match |↑ |0.0033|± |0.0019|
| - leaderboard_math_num_theory_hard | 2|none | 4|exact_match |↑ |0.0037|± |0.0026|
| - leaderboard_math_prealgebra_hard | 2|none | 4|exact_match |↑ |0.0046|± |0.0023|
| - leaderboard_math_precalculus_hard | 2|none | 4|exact_match |↑ |0.0000|± | 0|
| - leaderboard_mmlu_pro | 0.1|none | 5|acc |↑ |0.1068|± |0.0028|
| - leaderboard_musr | N/A| | | | | | | |
| - leaderboard_musr_murder_mysteries | 1|none | 0|acc_norm |↑ |0.5160|± |0.0317|
| - leaderboard_musr_object_placements | 1|none | 0|acc_norm |↑ |0.2344|± |0.0265|
| - leaderboard_musr_team_allocation | 1|none | 0|acc_norm |↑ |0.3200|± |0.0296|
```
```bash
litgpt convert_pretrained_checkpoint ../out/pretrain-core-0/final ../out/pretrain-core-0/checkpoint
```
```bash
CUDA_VISIBLE_DEVICES=0 CUDA_LAUNCH_BLOCKING=0 PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True litgpt pretrain --config pretrain_core_model_1.yaml
```
```
Seed set to 23
Time to instantiate model: 0.32 seconds.
Total parameters: 234,914,304
Validating ...
Measured TFLOPs: 27760.47
Epoch 1 | iter 128 step 1 | loss train: 3.205, val: 3.457 | iter time: 450.87 ms (step) remaining time: 10:13:33
Epoch 1 | iter 256 step 2 | loss train: 3.175, val: 3.457 | iter time: 386.03 ms (step) remaining time: 9:00:10
Epoch 1 | iter 384 step 3 | loss train: 3.144, val: 3.457 | iter time: 388.88 ms (step) remaining time: 8:35:53
Epoch 1 | iter 512 step 4 | loss train: 3.260, val: 3.457 | iter time: 390.66 ms (step) remaining time: 8:24:17
Epoch 1 | iter 640 step 5 | loss train: 3.247, val: 3.457 | iter time: 392.99 ms (step) remaining time: 8:17:54
Epoch 1 | iter 768 step 6 | loss train: 3.264, val: 3.457 | iter time: 397.01 ms (step) remaining time: 8:13:51
Epoch 1 | iter 896 step 7 | loss train: 3.232, val: 3.457 | iter time: 396.00 ms (step) remaining time: 8:11:00
Epoch 1 | iter 1024 step 8 | loss train: 3.287, val: 3.457 | iter time: 396.93 ms (step) remaining time: 8:08:43
Epoch 1 | iter 1152 step 9 | loss train: 3.236, val: 3.457 | iter time: 398.67 ms (step) remaining time: 8:06:49
Epoch 1 | iter 1280 step 10 | loss train: 3.274, val: 3.457 | iter time: 399.49 ms (step) remaining time: 8:05:09
# ...
Epoch 1 | iter 76928 step 601 | loss train: 3.177, val: 3.304 | iter time: 400.61 ms (step) remaining time: 0:03:35
Epoch 1 | iter 77056 step 602 | loss train: 3.191, val: 3.304 | iter time: 396.14 ms (step) remaining time: 0:02:46
Epoch 1 | iter 77184 step 603 | loss train: 3.173, val: 3.304 | iter time: 399.39 ms (step) remaining time: 0:01:58
Epoch 1 | iter 77312 step 604 | loss train: 3.211, val: 3.304 | iter time: 398.61 ms (step) remaining time: 0:01:09
Epoch 1 | iter 77440 step 605 | loss train: 3.203, val: 3.304 | iter time: 399.31 ms (step) remaining time: 0:00:21
Validating ...
Final evaluation | val loss: 3.304 | val ppl: 27.217
Saving checkpoint to '../out/pretrain-core-1/final/lit_model.pth'
----------------------------------------
| Performance
| - Total tokens : 634,855,424
| - Training Time : 29361.39 s
| - Tok/sec : 524.18 tok/s
| ----------------------------------------
| Memory Usage
| - Memory Used : 22.33 GB
----------------------------------------
```
```bash
mv wandb wandb-pretrain-core-1
```
```bash
cp ../config-1.json ../out/pretrain-core-1/final/config.json
```
```bash
CUDA_VISIBLE_DEVICES=0 CUDA_LAUNCH_BLOCKING=0 PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True litgpt chat ../out/pretrain-core-1/final
```
```bash
litgpt convert_pretrained_checkpoint ../out/pretrain-core-1/final ../out/pretrain-core-1/checkpoint
```
```bash
CUDA_VISIBLE_DEVICES=0 CUDA_LAUNCH_BLOCKING=0 PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True litgpt pretrain --config pretrain_core_model_2.yaml
```
```
Seed set to 23
Time to instantiate model: 0.30 seconds.
Total parameters: 234,914,304
Validating ...
Measured TFLOPs: 13880.23
Epoch 1 | iter 256 step 1 | loss train: 2.857, val: 3.078 | iter time: 518.53 ms (step) remaining time: 8:49:46
Epoch 1 | iter 512 step 2 | loss train: 2.839, val: 3.078 | iter time: 461.04 ms (step) remaining time: 7:47:05
Epoch 1 | iter 768 step 3 | loss train: 2.835, val: 3.078 | iter time: 462.82 ms (step) remaining time: 7:27:16
Epoch 1 | iter 1024 step 4 | loss train: 2.872, val: 3.078 | iter time: 464.55 ms (step) remaining time: 7:16:22
Epoch 1 | iter 1280 step 5 | loss train: 2.867, val: 3.078 | iter time: 462.06 ms (step) remaining time: 7:09:02
Epoch 1 | iter 1536 step 6 | loss train: 2.899, val: 3.078 | iter time: 465.26 ms (step) remaining time: 7:03:30
Epoch 1 | iter 1792 step 7 | loss train: 2.878, val: 3.078 | iter time: 465.57 ms (step) remaining time: 6:59:00
Epoch 1 | iter 2048 step 8 | loss train: 2.919, val: 3.078 | iter time: 464.37 ms (step) remaining time: 6:55:10
Epoch 1 | iter 2304 step 9 | loss train: 2.922, val: 3.078 | iter time: 464.24 ms (step) remaining time: 6:51:45
Epoch 1 | iter 2560 step 10 | loss train: 2.924, val: 3.078 | iter time: 464.71 ms (step) remaining time: 6:48:39
# ...
Epoch 1 | iter 53760 step 210 | loss train: 2.904, val: 3.013 | iter time: 468.66 ms (step) remaining time: 0:23:26
Epoch 1 | iter 54016 step 211 | loss train: 2.903, val: 3.013 | iter time: 468.81 ms (step) remaining time: 0:21:32
Epoch 1 | iter 54272 step 212 | loss train: 2.951, val: 3.013 | iter time: 463.52 ms (step) remaining time: 0:19:39
Epoch 1 | iter 54528 step 213 | loss train: 2.941, val: 3.013 | iter time: 466.12 ms (step) remaining time: 0:17:45
Epoch 1 | iter 54784 step 214 | loss train: 2.950, val: 3.013 | iter time: 468.24 ms (step) remaining time: 0:15:52
Epoch 1 | iter 55040 step 215 | loss train: 2.943, val: 3.013 | iter time: 466.65 ms (step) remaining time: 0:13:59
Epoch 1 | iter 55296 step 216 | loss train: 2.903, val: 3.013 | iter time: 464.44 ms (step) remaining time: 0:12:05
Epoch 1 | iter 55552 step 217 | loss train: 2.954, val: 3.013 | iter time: 465.12 ms (step) remaining time: 0:10:12
Epoch 1 | iter 55808 step 218 | loss train: 2.907, val: 3.013 | iter time: 464.96 ms (step) remaining time: 0:08:19
Epoch 1 | iter 56064 step 219 | loss train: 2.909, val: 3.013 | iter time: 467.12 ms (step) remaining time: 0:06:25
Epoch 1 | iter 56320 step 220 | loss train: 2.908, val: 3.013 | iter time: 466.43 ms (step) remaining time: 0:04:32
Epoch 1 | iter 56576 step 221 | loss train: 2.894, val: 3.013 | iter time: 469.70 ms (step) remaining time: 0:02:38
Epoch 1 | iter 56832 step 222 | loss train: 2.809, val: 3.013 | iter time: 463.88 ms (step) remaining time: 0:00:45
Validating ...
Final evaluation | val loss: 3.011 | val ppl: 20.306
Saving checkpoint to '../out/pretrain-core-1/final/lit_model.pth'
----------------------------------------
| Performance
| - Total tokens : 466,411,520
| - Training Time : 25263.31 s
| - Tok/sec : 371.33 tok/s
| ----------------------------------------
| Memory Usage
| - Memory Used : 22.33 GB
----------------------------------------
```
```bash
cp ../config-2.json ../out/pretrain-core-2/final/config.json
```
```bash
mv wandb wandb-pretrain-core-2
```
```bash
CUDA_VISIBLE_DEVICES=0 CUDA_LAUNCH_BLOCKING=0 PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True litgpt chat ../out/pretrain-core-2/final
```
```bash
litgpt convert_pretrained_checkpoint ../out/pretrain-core-2/final ../out/pretrain-core-2/checkpoint
```
```bash
CUDA_VISIBLE_DEVICES=0 CUDA_LAUNCH_BLOCKING=0 PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True litgpt pretrain --config pretrain_core_model_3.yaml
```
```
Seed set to 23
Time to instantiate model: 0.30 seconds.
Total parameters: 234,914,304
Validating ...
Measured TFLOPs: 6940.12
Epoch 1 | iter 512 step 1 | loss train: 2.698, val: 2.522 | iter time: 675.96 ms (step) remaining time: 9:49:31
Epoch 1 | iter 1024 step 2 | loss train: 2.627, val: 2.522 | iter time: 603.66 ms (step) remaining time: 9:19:41
Epoch 1 | iter 1536 step 3 | loss train: 2.653, val: 2.522 | iter time: 604.66 ms (step) remaining time: 9:06:15
Epoch 1 | iter 2048 step 4 | loss train: 2.608, val: 2.522 | iter time: 606.23 ms (step) remaining time: 8:57:08
Epoch 1 | iter 2560 step 5 | loss train: 2.604, val: 2.522 | iter time: 605.04 ms (step) remaining time: 8:49:43
Epoch 1 | iter 3072 step 6 | loss train: 2.578, val: 2.522 | iter time: 606.32 ms (step) remaining time: 8:43:08
Epoch 1 | iter 3584 step 7 | loss train: 2.692, val: 2.522 | iter time: 605.08 ms (step) remaining time: 8:37:01
Epoch 1 | iter 4096 step 8 | loss train: 2.570, val: 2.522 | iter time: 607.54 ms (step) remaining time: 8:31:20
Epoch 1 | iter 4608 step 9 | loss train: 2.646, val: 2.522 | iter time: 607.19 ms (step) remaining time: 8:25:47
Epoch 1 | iter 5120 step 10 | loss train: 2.565, val: 2.522 | iter time: 604.76 ms (step) remaining time: 8:20:23
# ...
Epoch 1 | iter 51712 step 101 | loss train: 2.562, val: 2.453 | iter time: 607.12 ms (step) remaining time: 0:48:29
Epoch 1 | iter 52224 step 102 | loss train: 2.637, val: 2.453 | iter time: 605.46 ms (step) remaining time: 0:43:31
Epoch 1 | iter 52736 step 103 | loss train: 2.629, val: 2.453 | iter time: 604.15 ms (step) remaining time: 0:38:34
Epoch 1 | iter 53248 step 104 | loss train: 2.629, val: 2.453 | iter time: 605.92 ms (step) remaining time: 0:33:36
Epoch 1 | iter 53760 step 105 | loss train: 2.606, val: 2.453 | iter time: 604.48 ms (step) remaining time: 0:28:38
Epoch 1 | iter 54272 step 106 | loss train: 2.581, val: 2.453 | iter time: 603.78 ms (step) remaining time: 0:23:41
Epoch 1 | iter 54784 step 107 | loss train: 2.580, val: 2.453 | iter time: 605.41 ms (step) remaining time: 0:18:43
Epoch 1 | iter 55296 step 108 | loss train: 2.602, val: 2.453 | iter time: 607.38 ms (step) remaining time: 0:13:46
Epoch 1 | iter 55808 step 109 | loss train: 2.633, val: 2.453 | iter time: 606.06 ms (step) remaining time: 0:08:49
Epoch 1 | iter 56320 step 110 | loss train: 2.631, val: 2.453 | iter time: 608.68 ms (step) remaining time: 0:03:51
Validating ...
iter 56320: val loss 2.4515, val time: 19303.40 ms
Saving checkpoint to '../out/pretrain-core-3/step-00000110/lit_model.pth'
Validating ...
Final evaluation | val loss: 2.451 | val ppl: 11.605
Saving checkpoint to '../out/pretrain-core-3/final/lit_model.pth'
----------------------------------------
| Performance
| - Total tokens : 464,642,048
| - Training Time : 33018.19 s
| - Tok/sec : 362.46 tok/s
| ----------------------------------------
| Memory Usage
| - Memory Used : 22.33 GB
----------------------------------------
```
```bash
cp ../config-3.json ../out/pretrain-core-3/final/config.json
```
```bash
mv wandb wandb-pretrain-core-3
```
```bash
CUDA_VISIBLE_DEVICES=0 CUDA_LAUNCH_BLOCKING=0 PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True litgpt chat ../out/pretrain-core-3/final
```
```bash
litgpt convert_pretrained_checkpoint ../out/pretrain-core-3/final ../out/pretrain-core-3/checkpoint
```
```bash
CUDA_VISIBLE_DEVICES=0 CUDA_LAUNCH_BLOCKING=0 PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True litgpt pretrain --config pretrain_core_model_4.yaml
```
```
# ...
```
|