<!-- 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. -->
dialogpt-medium-no_ear
This model is a fine-tuned version of microsoft/DialoGPT-medium on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5659
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: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 21
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3.0
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
9.109 | 0.01 | 10 | 9.8250 |
8.6669 | 0.02 | 20 | 8.9632 |
5.0713 | 0.03 | 30 | 4.2372 |
1.5919 | 0.04 | 40 | 1.2643 |
0.957 | 0.05 | 50 | 1.0243 |
1.0602 | 0.06 | 60 | 0.9280 |
0.9131 | 0.07 | 70 | 0.8479 |
0.8981 | 0.08 | 80 | 0.7994 |
0.6697 | 0.09 | 90 | 0.7674 |
0.9282 | 0.1 | 100 | 0.7433 |
0.9447 | 0.11 | 110 | 0.7271 |
0.7462 | 0.12 | 120 | 0.7156 |
0.7161 | 0.13 | 130 | 0.7040 |
0.8005 | 0.14 | 140 | 0.6934 |
0.579 | 0.15 | 150 | 0.6848 |
0.8563 | 0.16 | 160 | 0.6770 |
0.6635 | 0.17 | 170 | 0.6692 |
0.8981 | 0.18 | 180 | 0.6613 |
0.731 | 0.19 | 190 | 0.6552 |
0.9141 | 0.2 | 200 | 0.6492 |
0.5798 | 0.21 | 210 | 0.6446 |
0.6765 | 0.22 | 220 | 0.6400 |
0.621 | 0.23 | 230 | 0.6356 |
0.601 | 0.24 | 240 | 0.6330 |
0.5373 | 0.25 | 250 | 0.6301 |
0.64 | 0.26 | 260 | 0.6261 |
0.6474 | 0.27 | 270 | 0.6224 |
0.6433 | 0.28 | 280 | 0.6197 |
0.604 | 0.29 | 290 | 0.6167 |
0.6947 | 0.3 | 300 | 0.6143 |
0.606 | 0.31 | 310 | 0.6116 |
0.6329 | 0.32 | 320 | 0.6103 |
0.5827 | 0.33 | 330 | 0.6086 |
0.5401 | 0.34 | 340 | 0.6074 |
0.6682 | 0.35 | 350 | 0.6066 |
0.6235 | 0.36 | 360 | 0.6039 |
0.6753 | 0.37 | 370 | 0.6018 |
0.6582 | 0.38 | 380 | 0.6001 |
0.5886 | 0.39 | 390 | 0.5995 |
0.6826 | 0.4 | 400 | 0.5983 |
0.5701 | 0.41 | 410 | 0.5973 |
0.7211 | 0.42 | 420 | 0.5962 |
0.6857 | 0.43 | 430 | 0.5944 |
0.6894 | 0.44 | 440 | 0.5922 |
0.6034 | 0.45 | 450 | 0.5920 |
0.6199 | 0.46 | 460 | 0.5925 |
0.6487 | 0.47 | 470 | 0.5904 |
0.5674 | 0.48 | 480 | 0.5884 |
0.4604 | 0.49 | 490 | 0.5876 |
0.5617 | 0.5 | 500 | 0.5865 |
0.5553 | 0.51 | 510 | 0.5852 |
0.6245 | 0.52 | 520 | 0.5846 |
0.5015 | 0.53 | 530 | 0.5837 |
0.6115 | 0.54 | 540 | 0.5836 |
0.5197 | 0.55 | 550 | 0.5831 |
0.6451 | 0.56 | 560 | 0.5820 |
0.6348 | 0.57 | 570 | 0.5817 |
0.5413 | 0.58 | 580 | 0.5803 |
0.6283 | 0.59 | 590 | 0.5795 |
0.5502 | 0.6 | 600 | 0.5789 |
0.6853 | 0.61 | 610 | 0.5776 |
0.5457 | 0.62 | 620 | 0.5770 |
0.6369 | 0.63 | 630 | 0.5762 |
0.7152 | 0.64 | 640 | 0.5756 |
0.534 | 0.65 | 650 | 0.5759 |
0.5276 | 0.66 | 660 | 0.5753 |
0.6566 | 0.67 | 670 | 0.5750 |
0.504 | 0.68 | 680 | 0.5746 |
0.5552 | 0.69 | 690 | 0.5740 |
0.4891 | 0.7 | 700 | 0.5746 |
0.6463 | 0.71 | 710 | 0.5743 |
0.5943 | 0.72 | 720 | 0.5732 |
0.5833 | 0.73 | 730 | 0.5726 |
0.5904 | 0.74 | 740 | 0.5719 |
0.5971 | 0.75 | 750 | 0.5718 |
0.5906 | 0.76 | 760 | 0.5710 |
0.6268 | 0.77 | 770 | 0.5701 |
0.5872 | 0.78 | 780 | 0.5698 |
0.571 | 0.79 | 790 | 0.5690 |
0.6224 | 0.8 | 800 | 0.5686 |
0.5397 | 0.81 | 810 | 0.5683 |
0.5658 | 0.82 | 820 | 0.5683 |
0.4248 | 0.83 | 830 | 0.5680 |
0.5334 | 0.84 | 840 | 0.5674 |
0.5338 | 0.85 | 850 | 0.5672 |
0.641 | 0.86 | 860 | 0.5669 |
0.5601 | 0.87 | 870 | 0.5660 |
0.6031 | 0.88 | 880 | 0.5654 |
0.5738 | 0.89 | 890 | 0.5652 |
0.5619 | 0.9 | 900 | 0.5655 |
0.4863 | 0.91 | 910 | 0.5667 |
0.5421 | 0.92 | 920 | 0.5659 |
Framework versions
- Transformers 4.27.4
- Pytorch 1.11.0+cu113
- Datasets 2.11.0
- Tokenizers 0.12.1