This model is a fine-tuned version of FacebookAI/roberta-large on the None dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.3577 | 0.0962 | 10 | 1.2713 |
| 1.3243 | 0.1923 | 20 | 1.2728 |
| 1.3107 | 0.2885 | 30 | 1.2959 |
| 1.312 | 0.3846 | 40 | 1.2748 |
| 1.3671 | 0.4808 | 50 | 1.3367 |
| 1.3327 | 0.5769 | 60 | 1.3070 |
| 1.3419 | 0.6731 | 70 | 1.3431 |
| 1.3405 | 0.7692 | 80 | 1.2734 |
| 1.2465 | 0.8654 | 90 | 1.2881 |
| 1.3376 | 0.9615 | 100 | 1.2953 |
| 1.2883 | 1.0577 | 110 | 1.2678 |
| 1.3219 | 1.1538 | 120 | 1.2775 |
| 1.2754 | 1.25 | 130 | 1.2876 |
| 1.293 | 1.3462 | 140 | 1.2705 |
| 1.2848 | 1.4423 | 150 | 1.2747 |
| 1.3346 | 1.5385 | 160 | 1.2852 |
| 1.3195 | 1.6346 | 170 | 1.2678 |
| 1.3516 | 1.7308 | 180 | 1.3041 |
| 1.3072 | 1.8269 | 190 | 1.2718 |
| 1.3103 | 1.9231 | 200 | 1.3155 |
| 1.338 | 2.0192 | 210 | 1.2849 |
| 1.3551 | 2.1154 | 220 | 1.2753 |
| 1.3342 | 2.2115 | 230 | 1.3073 |
| 1.3228 | 2.3077 | 240 | 1.2871 |
| 1.335 | 2.4038 | 250 | 1.2732 |
| 1.3218 | 2.5 | 260 | 1.2806 |
| 1.2967 | 2.5962 | 270 | 1.2738 |
| 1.2826 | 2.6923 | 280 | 1.2746 |
| 1.2718 | 2.7885 | 290 | 1.2680 |
| 1.2969 | 2.8846 | 300 | 1.2714 |
| 1.3147 | 2.9808 | 310 | 1.2699 |
| 1.253 | 3.0769 | 320 | 1.2703 |
| 1.3062 | 3.1731 | 330 | 1.2714 |
| 1.303 | 3.2692 | 340 | 1.2708 |
| 1.3001 | 3.3654 | 350 | 1.2814 |
| 1.3067 | 3.4615 | 360 | 1.2780 |
| 1.2818 | 3.5577 | 370 | 1.2708 |
| 1.3128 | 3.6538 | 380 | 1.2702 |
| 1.2715 | 3.75 | 390 | 1.2761 |
| 1.3178 | 3.8462 | 400 | 1.2673 |
| 1.2829 | 3.9423 | 410 | 1.2697 |
| 1.3103 | 4.0385 | 420 | 1.2723 |
| 1.3009 | 4.1346 | 430 | 1.2728 |
| 1.2902 | 4.2308 | 440 | 1.2697 |
| 1.3163 | 4.3269 | 450 | 1.2690 |
| 1.3005 | 4.4231 | 460 | 1.2689 |
| 1.3083 | 4.5192 | 470 | 1.2693 |
| 1.2759 | 4.6154 | 480 | 1.2690 |
| 1.2771 | 4.7115 | 490 | 1.2690 |
| 1.2882 | 4.8077 | 500 | 1.2691 |
| 1.2749 | 4.9038 | 510 | 1.2692 |
| 1.2892 | 5.0 | 520 | 1.2692 |
Released freely — support more experiments like it:
model.safetensors 1.4 GBtraining_args.bin 5.4 kBHave the files? Submit a torrent.
Submit a torrentHave the complete files and permission to share them? Replace the example folder path. The script checks the files, makes a torrent and submits its magnet and checksums. Keep your torrent client seeding. Get your community key from your settings, and read the script before running it.
curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo YuvrajSingh9886/roberta-base-Maradona ./model-folder