Downloads · 30 days
16
7% of all-time downloads
100M_low_0_6910
craa/100M_low_0_6910
100M_low_0_6910 is a text generation model from craa. Use it when you need the model to write or continue text. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
225
Public
Parameters
126M
45.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt11.1 GB · 65%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- gpt2
- Access
- Public
- Created
- Oct 31, 2024
- Updated
- Dec 17, 2024
- SHA
- f81ea385
Try a prompt
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
100M_low_0_6910
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.3041
- Accuracy: 0.3943
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0006
- train_batch_size: 32
- eval_batch_size: 16
- seed: 6910
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.98) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 5.1141 | 0.1078 | 1000 | 5.0241 | 0.2272 |
| 4.5896 | 0.2156 | 2000 | 4.5195 | 0.2690 |
| 4.3176 | 0.3235 | 3000 | 4.2406 | 0.2978 |
| 4.1612 | 0.4313 | 4000 | 4.0956 | 0.3116 |
| 4.0659 | 0.5391 | 5000 | 4.0039 | 0.3203 |
| 4.0073 | 0.6469 | 6000 | 3.9222 | 0.3275 |
| 3.9322 | 0.7547 | 7000 | 3.8701 | 0.3325 |
| 3.8887 | 0.8625 | 8000 | 3.8230 | 0.3371 |
| 3.8463 | 0.9704 | 9000 | 3.7831 | 0.3407 |
| 3.7831 | 1.0782 | 10000 | 3.7605 | 0.3441 |
| 3.7431 | 1.1860 | 11000 | 3.7287 | 0.3471 |
| 3.7399 | 1.2938 | 12000 | 3.7075 | 0.3487 |
| 3.7173 | 1.4016 | 13000 | 3.6832 | 0.3510 |
| 3.7049 | 1.5094 | 14000 | 3.6616 | 0.3530 |
| 3.6839 | 1.6173 | 15000 | 3.6434 | 0.3550 |
| 3.6832 | 1.7251 | 16000 | 3.6254 | 0.3564 |
| 3.6671 | 1.8329 | 17000 | 3.6116 | 0.3579 |
| 3.6482 | 1.9407 | 18000 | 3.5949 | 0.3596 |
| 3.5642 | 2.0485 | 19000 | 3.5868 | 0.3609 |
| 3.5635 | 2.1563 | 20000 | 3.5754 | 0.3625 |
| 3.5639 | 2.2642 | 21000 | 3.5689 | 0.3631 |
| 3.55 | 2.3720 | 22000 | 3.5548 | 0.3641 |
| 3.5579 | 2.4798 | 23000 | 3.5473 | 0.3651 |
| 3.5468 | 2.5876 | 24000 | 3.5359 | 0.3662 |
| 3.5317 | 2.6954 | 25000 | 3.5258 | 0.3674 |
| 3.543 | 2.8032 | 26000 | 3.5178 | 0.3682 |
| 3.5252 | 2.9111 | 27000 | 3.5079 | 0.3690 |
| 3.4506 | 3.0189 | 28000 | 3.5070 | 0.3699 |
| 3.4454 | 3.1267 | 29000 | 3.5001 | 0.3703 |
| 3.4743 | 3.2345 | 30000 | 3.4937 | 0.3715 |
| 3.48 | 3.3423 | 31000 | 3.4869 | 0.3721 |
| 3.4678 | 3.4501 | 32000 | 3.4801 | 0.3728 |
| 3.4589 | 3.5580 | 33000 | 3.4743 | 0.3729 |
| 3.457 | 3.6658 | 34000 | 3.4689 | 0.3740 |
| 3.4738 | 3.7736 | 35000 | 3.4627 | 0.3745 |
| 3.4416 | 3.8814 | 36000 | 3.4562 | 0.3750 |
| 3.423 | 3.9892 | 37000 | 3.4495 | 0.3757 |
| 3.3646 | 4.0970 | 38000 | 3.4522 | 0.3761 |
| 3.3902 | 4.2049 | 39000 | 3.4492 | 0.3764 |
| 3.4058 | 4.3127 | 40000 | 3.4436 | 0.3768 |
| 3.4198 | 4.4205 | 41000 | 3.4398 | 0.3776 |
| 3.3918 | 4.5283 | 42000 | 3.4331 | 0.3782 |
| 3.4122 | 4.6361 | 43000 | 3.4296 | 0.3786 |
| 3.396 | 4.7439 | 44000 | 3.4239 | 0.3791 |
| 3.3935 | 4.8518 | 45000 | 3.4178 | 0.3798 |
| 3.3924 | 4.9596 | 46000 | 3.4154 | 0.3801 |
| 3.3181 | 5.0674 | 47000 | 3.4168 | 0.3803 |
| 3.3111 | 5.1752 | 48000 | 3.4168 | 0.3804 |
| 3.3336 | 5.2830 | 49000 | 3.4130 | 0.3810 |
| 3.3466 | 5.3908 | 50000 | 3.4048 | 0.3813 |
| 3.3206 | 5.4987 | 51000 | 3.4028 | 0.3818 |
| 3.3324 | 5.6065 | 52000 | 3.3979 | 0.3822 |
| 3.3457 | 5.7143 | 53000 | 3.3935 | 0.3827 |
| 3.3306 | 5.8221 | 54000 | 3.3904 | 0.3831 |
| 3.3313 | 5.9299 | 55000 | 3.3839 | 0.3836 |
| 3.2433 | 6.0377 | 56000 | 3.3888 | 0.3834 |
| 3.2736 | 6.1456 | 57000 | 3.3873 | 0.3840 |
| 3.28 | 6.2534 | 58000 | 3.3847 | 0.3842 |
| 3.2965 | 6.3612 | 59000 | 3.3815 | 0.3845 |
| 3.2877 | 6.4690 | 60000 | 3.3767 | 0.3852 |
| 3.2805 | 6.5768 | 61000 | 3.3725 | 0.3854 |
| 3.2824 | 6.6846 | 62000 | 3.3696 | 0.3856 |
| 3.2914 | 6.7925 | 63000 | 3.3646 | 0.3863 |
| 3.3061 | 6.9003 | 64000 | 3.3604 | 0.3866 |
| 3.2147 | 7.0081 | 65000 | 3.3652 | 0.3865 |
| 3.2271 | 7.1159 | 66000 | 3.3639 | 0.3871 |
| 3.2382 | 7.2237 | 67000 | 3.3606 | 0.3872 |
| 3.2208 | 7.3315 | 68000 | 3.3588 | 0.3875 |
| 3.2531 | 7.4394 | 69000 | 3.3557 | 0.3877 |
| 3.2403 | 7.5472 | 70000 | 3.3506 | 0.3884 |
| 3.2398 | 7.6550 | 71000 | 3.3457 | 0.3888 |
| 3.2352 | 7.7628 | 72000 | 3.3442 | 0.3890 |
| 3.2342 | 7.8706 | 73000 | 3.3396 | 0.3893 |
| 3.2489 | 7.9784 | 74000 | 3.3357 | 0.3898 |
| 3.1622 | 8.0863 | 75000 | 3.3411 | 0.3896 |
| 3.1905 | 8.1941 | 76000 | 3.3404 | 0.3896 |
| 3.1792 | 8.3019 | 77000 | 3.3360 | 0.3902 |
| 3.1981 | 8.4097 | 78000 | 3.3326 | 0.3907 |
| 3.1843 | 8.5175 | 79000 | 3.3302 | 0.3908 |
| 3.1816 | 8.6253 | 80000 | 3.3269 | 0.3915 |
| 3.195 | 8.7332 | 81000 | 3.3220 | 0.3919 |
| 3.1996 | 8.8410 | 82000 | 3.3191 | 0.3922 |
| 3.1765 | 8.9488 | 83000 | 3.3175 | 0.3923 |
| 3.1116 | 9.0566 | 84000 | 3.3203 | 0.3923 |
| 3.1486 | 9.1644 | 85000 | 3.3185 | 0.3925 |
| 3.1375 | 9.2722 | 86000 | 3.3170 | 0.3929 |
| 3.1256 | 9.3801 | 87000 | 3.3150 | 0.3930 |
| 3.1403 | 9.4879 | 88000 | 3.3119 | 0.3935 |
| 3.1353 | 9.5957 | 89000 | 3.3095 | 0.3936 |
| 3.1371 | 9.7035 | 90000 | 3.3072 | 0.3939 |
| 3.1378 | 9.8113 | 91000 | 3.3057 | 0.3941 |
| 3.148 | 9.9191 | 92000 | 3.3041 | 0.3943 |
Framework versions
- Transformers 4.47.0.dev0
- Pytorch 2.5.0+cu124
- Datasets 3.0.2
- Tokenizers 0.20.1
- Task
- Text Generation
- Library
- transformers
- Type
- gpt2
- Created
- Oct 31, 2024
- Updated
- Dec 17, 2024