File size: 5,309 Bytes
eee83ca d8b273d eee83ca d8b273d ebc900d cdeea60 ebc900d cdeea60 d8b273d |
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 |
---
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-0.2-core
```bash
time python -B prepare_core_datasets.py
```
```
Progress: 100%|████████| 220/220 [23:15<00:00, 6.34s/it]
Workers are finished.██| 220/220 [23:15<00:00, 6.34s/it]
Finished data processing!
i=0, block_size=8192, chunk_size=16384000, len(dataset)=893355, len(dataset) * block_size=7318364160
Total number of tokens in the optimized dataset '../core-data-0-8192-2000' is 7318364160
```
```bash
CUDA_VISIBLE_DEVICES=0 CUDA_LAUNCH_BLOCKING=0 PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True litgpt pretrain --config pretrain-core-model.yaml
```
```
Seed set to 23
Time to instantiate model: 0.32 seconds.
Total parameters: 217,088,512
Verifying settings ...
Measured TFLOPs: 3548.40
Epoch 1 | iter 256 step 1 | loss train: 11.716, val: n/a | iter time: 1735.26 ms (step) remaining time: 4 days, 11:06:29
Epoch 1 | iter 512 step 2 | loss train: 11.534, val: n/a | iter time: 1102.77 ms (step) remaining time: 4 days, 2:31:30
Epoch 1 | iter 768 step 3 | loss train: 11.356, val: n/a | iter time: 1095.87 ms (step) remaining time: 3 days, 23:44:12
Epoch 1 | iter 1024 step 4 | loss train: 11.162, val: n/a | iter time: 1099.92 ms (step) remaining time: 3 days, 22:18:27
Epoch 1 | iter 1280 step 5 | loss train: 11.018, val: n/a | iter time: 1096.45 ms (step) remaining time: 3 days, 21:24:35
Epoch 1 | iter 1536 step 6 | loss train: 10.901, val: n/a | iter time: 1093.65 ms (step) remaining time: 3 days, 20:48:11
Epoch 1 | iter 1792 step 7 | loss train: 10.850, val: n/a | iter time: 1100.16 ms (step) remaining time: 3 days, 20:22:00
Epoch 1 | iter 2048 step 8 | loss train: 10.780, val: n/a | iter time: 1092.67 ms (step) remaining time: 3 days, 20:01:57
Epoch 1 | iter 2304 step 9 | loss train: 10.692, val: n/a | iter time: 1095.77 ms (step) remaining time: 3 days, 19:45:57
Epoch 1 | iter 2560 step 10 | loss train: 10.678, val: n/a | iter time: 1092.12 ms (step) remaining time: 3 days, 19:32:43
Epoch 1 | iter 2816 step 11 | loss train: 10.619, val: n/a | iter time: 1094.44 ms (step) remaining time: 3 days, 19:21:32
Epoch 1 | iter 3072 step 12 | loss train: 10.588, val: n/a | iter time: 1102.51 ms (step) remaining time: 3 days, 19:12:30
Epoch 1 | iter 3328 step 13 | loss train: 10.514, val: n/a | iter time: 1095.57 ms (step) remaining time: 3 days, 19:04:07
Epoch 1 | iter 3584 step 14 | loss train: 10.472, val: n/a | iter time: 1104.00 ms (step) remaining time: 3 days, 18:56:56
Epoch 1 | iter 3840 step 15 | loss train: 10.431, val: n/a | iter time: 1096.00 ms (step) remaining time: 3 days, 18:50:21
Epoch 1 | iter 4096 step 16 | loss train: 10.392, val: n/a | iter time: 1098.34 ms (step) remaining time: 3 days, 18:44:25
Epoch 1 | iter 4352 step 17 | loss train: 10.360, val: n/a | iter time: 1106.53 ms (step) remaining time: 3 days, 18:38:58
Epoch 1 | iter 4608 step 18 | loss train: 10.329, val: n/a | iter time: 1084.95 ms (step) remaining time: 3 days, 18:33:58
Epoch 1 | iter 4864 step 19 | loss train: 10.296, val: n/a | iter time: 1096.22 ms (step) remaining time: 3 days, 18:29:12
Epoch 1 | iter 5120 step 20 | loss train: 10.236, val: n/a | iter time: 1093.39 ms (step) remaining time: 3 days, 18:24:51
# ...
```
Backup `wandb`:
```bash
mv wandb wandb-pretrain-core
```
Chat with model:
```bash
CUDA_VISIBLE_DEVICES=0 CUDA_LAUNCH_BLOCKING=0 PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True litgpt chat ../out/pretrain-core/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/leaderboard/' --batch_size 1 --dtype 'bfloat16' '../out/pretrain-core/final'
```
```
# ...
```
|