<!-- 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-ear_1-hs_cn
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: 0.5765
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 |
---|---|---|---|
6.3026 | 0.01 | 10 | 9.8250 |
5.7238 | 0.02 | 20 | 8.9634 |
2.2859 | 0.03 | 30 | 4.2371 |
-1.2255 | 0.04 | 40 | 1.2646 |
-1.8713 | 0.05 | 50 | 1.0242 |
-1.694 | 0.06 | 60 | 0.9279 |
-1.8816 | 0.07 | 70 | 0.8478 |
-1.8973 | 0.08 | 80 | 0.7993 |
-2.0091 | 0.09 | 90 | 0.7673 |
-1.977 | 0.1 | 100 | 0.7432 |
-1.8075 | 0.11 | 110 | 0.7269 |
-1.9108 | 0.12 | 120 | 0.7154 |
-2.0062 | 0.13 | 130 | 0.7037 |
-1.9097 | 0.14 | 140 | 0.6932 |
-2.1621 | 0.15 | 150 | 0.6846 |
-1.8851 | 0.16 | 160 | 0.6769 |
-2.194 | 0.17 | 170 | 0.6691 |
-2.0428 | 0.18 | 180 | 0.6612 |
-1.9283 | 0.19 | 190 | 0.6551 |
-1.9743 | 0.2 | 200 | 0.6492 |
-2.2554 | 0.21 | 210 | 0.6447 |
-2.1644 | 0.22 | 220 | 0.6401 |
-2.1329 | 0.23 | 230 | 0.6359 |
-2.1015 | 0.24 | 240 | 0.6335 |
-2.2095 | 0.25 | 250 | 0.6306 |
-2.1004 | 0.26 | 260 | 0.6265 |
-2.161 | 0.27 | 270 | 0.6226 |
-2.262 | 0.28 | 280 | 0.6199 |
-2.2931 | 0.29 | 290 | 0.6171 |
-2.0241 | 0.3 | 300 | 0.6145 |
-2.1599 | 0.31 | 310 | 0.6119 |
-2.2971 | 0.32 | 320 | 0.6108 |
-2.167 | 0.33 | 330 | 0.6092 |
-2.1164 | 0.34 | 340 | 0.6080 |
-2.1552 | 0.35 | 350 | 0.6072 |
-2.1538 | 0.36 | 360 | 0.6046 |
-2.0819 | 0.37 | 370 | 0.6030 |
-2.1029 | 0.38 | 380 | 0.6009 |
-2.3315 | 0.39 | 390 | 0.6007 |
-2.1264 | 0.4 | 400 | 0.5993 |
-2.1951 | 0.41 | 410 | 0.5982 |
-2.1331 | 0.42 | 420 | 0.5970 |
-2.0456 | 0.43 | 430 | 0.5950 |
-2.0306 | 0.44 | 440 | 0.5931 |
-2.1779 | 0.45 | 450 | 0.5931 |
-2.3273 | 0.46 | 460 | 0.5939 |
-2.1638 | 0.47 | 470 | 0.5912 |
-2.319 | 0.48 | 480 | 0.5897 |
-2.3439 | 0.49 | 490 | 0.5891 |
-2.1683 | 0.5 | 500 | 0.5877 |
-2.2591 | 0.51 | 510 | 0.5862 |
-2.2144 | 0.52 | 520 | 0.5857 |
-2.2421 | 0.53 | 530 | 0.5850 |
-2.1114 | 0.54 | 540 | 0.5849 |
-2.3897 | 0.55 | 550 | 0.5844 |
-2.0635 | 0.56 | 560 | 0.5835 |
-2.027 | 0.57 | 570 | 0.5832 |
-2.3047 | 0.58 | 580 | 0.5820 |
-2.1517 | 0.59 | 590 | 0.5811 |
-2.3209 | 0.6 | 600 | 0.5804 |
-2.1742 | 0.61 | 610 | 0.5786 |
-2.1789 | 0.62 | 620 | 0.5781 |
-2.1169 | 0.63 | 630 | 0.5771 |
-1.9847 | 0.64 | 640 | 0.5766 |
-2.2595 | 0.65 | 650 | 0.5774 |
-2.3232 | 0.66 | 660 | 0.5769 |
-2.1872 | 0.67 | 670 | 0.5765 |
Framework versions
- Transformers 4.27.4
- Pytorch 1.11.0+cu113
- Datasets 2.11.0
- Tokenizers 0.12.1