File size: 6,244 Bytes
d3186b0 c98613b d3186b0 c98613b e9d9da3 c98613b |
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 |
---
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-0.10-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: 0.21 seconds.
Total parameters: 302,023,168
Verifying settings ...
Measured TFLOPs: 55520.94
Epoch 1 | iter 64 step 1 | loss train: 11.982, val: n/a | iter time: 409.55 ms (step) remaining time: 4 days, 17:45:21
Epoch 1 | iter 128 step 2 | loss train: 11.980, val: n/a | iter time: 354.46 ms (step) remaining time: 3 days, 15:01:16
Epoch 1 | iter 192 step 3 | loss train: 11.980, val: n/a | iter time: 353.67 ms (step) remaining time: 3 days, 5:46:03
Epoch 1 | iter 256 step 4 | loss train: 11.980, val: n/a | iter time: 354.11 ms (step) remaining time: 3 days, 1:05:26
Epoch 1 | iter 320 step 5 | loss train: 11.978, val: n/a | iter time: 358.28 ms (step) remaining time: 2 days, 22:21:45
Epoch 1 | iter 384 step 6 | loss train: 11.974, val: n/a | iter time: 356.21 ms (step) remaining time: 2 days, 20:33:55
Epoch 1 | iter 448 step 7 | loss train: 11.964, val: n/a | iter time: 357.42 ms (step) remaining time: 2 days, 19:15:59
Epoch 1 | iter 512 step 8 | loss train: 11.956, val: n/a | iter time: 355.74 ms (step) remaining time: 2 days, 18:16:43
Epoch 1 | iter 576 step 9 | loss train: 11.937, val: n/a | iter time: 356.05 ms (step) remaining time: 2 days, 17:28:34
Epoch 1 | iter 640 step 10 | loss train: 11.929, val: n/a | iter time: 356.68 ms (step) remaining time: 2 days, 16:49:58
# ...
```
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'
```
```
```
|