<!-- 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. -->
finetuning-sentiment-model-base-zero-shot
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5560
- Accuracy: 0.8015
- F1: 0.5511
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
---|---|---|---|---|---|
No log | 0.02 | 10 | 0.8518 | 0.6738 | 0.2684 |
No log | 0.03 | 20 | 0.7875 | 0.6738 | 0.2684 |
No log | 0.05 | 30 | 0.7443 | 0.6738 | 0.2684 |
No log | 0.07 | 40 | 0.7358 | 0.6746 | 0.2706 |
No log | 0.08 | 50 | 0.7233 | 0.6742 | 0.2695 |
No log | 0.1 | 60 | 0.6832 | 0.7148 | 0.3657 |
No log | 0.12 | 70 | 0.6272 | 0.7735 | 0.4807 |
No log | 0.13 | 80 | 0.5994 | 0.7910 | 0.4960 |
No log | 0.15 | 90 | 0.5908 | 0.7898 | 0.5113 |
No log | 0.17 | 100 | 0.5985 | 0.7982 | 0.5031 |
No log | 0.18 | 110 | 0.5920 | 0.7965 | 0.5006 |
No log | 0.2 | 120 | 0.5661 | 0.8053 | 0.5186 |
No log | 0.22 | 130 | 0.5900 | 0.8015 | 0.5092 |
No log | 0.23 | 140 | 0.5671 | 0.8023 | 0.5189 |
No log | 0.25 | 150 | 0.6000 | 0.8044 | 0.5114 |
No log | 0.27 | 160 | 0.5931 | 0.7785 | 0.5122 |
No log | 0.28 | 170 | 0.5477 | 0.8065 | 0.5220 |
No log | 0.3 | 180 | 0.5573 | 0.8107 | 0.5206 |
No log | 0.32 | 190 | 0.5586 | 0.7961 | 0.5206 |
No log | 0.34 | 200 | 0.5498 | 0.8107 | 0.5247 |
No log | 0.35 | 210 | 0.5829 | 0.8036 | 0.5082 |
No log | 0.37 | 220 | 0.5731 | 0.7843 | 0.5124 |
No log | 0.39 | 230 | 0.5704 | 0.7915 | 0.5179 |
No log | 0.4 | 240 | 0.5409 | 0.8070 | 0.5217 |
No log | 0.42 | 250 | 0.5486 | 0.8120 | 0.5237 |
No log | 0.44 | 260 | 0.5640 | 0.8082 | 0.5179 |
No log | 0.45 | 270 | 0.5525 | 0.8086 | 0.5182 |
No log | 0.47 | 280 | 0.5426 | 0.8086 | 0.5260 |
No log | 0.49 | 290 | 0.5599 | 0.8040 | 0.5090 |
No log | 0.5 | 300 | 0.5504 | 0.8124 | 0.5244 |
No log | 0.52 | 310 | 0.5561 | 0.8074 | 0.5149 |
No log | 0.54 | 320 | 0.5511 | 0.8061 | 0.5198 |
No log | 0.55 | 330 | 0.5574 | 0.8082 | 0.5194 |
No log | 0.57 | 340 | 0.5468 | 0.8099 | 0.5228 |
No log | 0.59 | 350 | 0.5518 | 0.7990 | 0.5262 |
No log | 0.6 | 360 | 0.5482 | 0.8099 | 0.5301 |
No log | 0.62 | 370 | 0.5409 | 0.8111 | 0.5364 |
No log | 0.64 | 380 | 0.5495 | 0.8103 | 0.5378 |
No log | 0.65 | 390 | 0.5508 | 0.8111 | 0.5362 |
No log | 0.67 | 400 | 0.5618 | 0.8011 | 0.5275 |
No log | 0.69 | 410 | 0.5490 | 0.8103 | 0.5306 |
No log | 0.7 | 420 | 0.5476 | 0.8116 | 0.5238 |
No log | 0.72 | 430 | 0.5414 | 0.8090 | 0.5306 |
No log | 0.74 | 440 | 0.5293 | 0.8153 | 0.5293 |
No log | 0.75 | 450 | 0.5595 | 0.8141 | 0.5339 |
No log | 0.77 | 460 | 0.5298 | 0.8132 | 0.5384 |
No log | 0.79 | 470 | 0.5309 | 0.8132 | 0.5359 |
No log | 0.8 | 480 | 0.5329 | 0.8132 | 0.5238 |
No log | 0.82 | 490 | 0.5305 | 0.8132 | 0.5314 |
0.5831 | 0.84 | 500 | 0.5560 | 0.8015 | 0.5511 |
0.5831 | 0.85 | 510 | 0.5207 | 0.8162 | 0.5393 |
0.5831 | 0.87 | 520 | 0.5607 | 0.8070 | 0.5481 |
0.5831 | 0.89 | 530 | 0.5321 | 0.8120 | 0.5317 |
Framework versions
- Transformers 4.29.2
- Pytorch 1.13.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3