Downloads · 30 days
3
14% of all-time downloads
distilbert-sentiment-imdb-sft-cft
wsklee/distilbert-sentiment-imdb-sft-cft
distilbert-sentiment-imdb-sft-cft is a machine learning model from wsklee. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
21
Public
Parameters
66.4M
265 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors265 MB · 100%
At a glance
- Library
- transformers
- License
- apache-2.0
- Model type
- distilbert
- Access
- Public
- Created
- Nov 15, 2024
- Updated
- Nov 15, 2024
- SHA
- 1a46a61f
Base models
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. -->
distilbert-sentiment-imdb-sft-cft
This model is a fine-tuned version of wsklee/distilbert-sentiment-imdb-sft on the None dataset. It achieves the following results on the evaluation set:
- Accuracy: 0.9928
- Pos Similarity: 0.9601
- Neg Similarity: 0.1017
- F1: 0.9964
- Precision: 1.0
- Recall: 0.9928
- Loss: 3.4752
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine_with_restarts
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Accuracy | Pos Similarity | Neg Similarity | F1 | Precision | Recall | Validation Loss |
|---|---|---|---|---|---|---|---|---|---|
| 3.7349 | 0.5682 | 200 | 0.9912 | 0.9842 | 0.1435 | 0.9956 | 1.0 | 0.9912 | 3.4856 |
| 3.5495 | 1.1364 | 400 | 0.9952 | 0.9878 | 0.3020 | 0.9976 | 1.0 | 0.9952 | 3.4340 |
| 3.5023 | 1.7045 | 600 | 0.9944 | 0.9873 | 0.2135 | 0.9972 | 1.0 | 0.9944 | 3.4313 |
| 3.482 | 2.2727 | 800 | 0.9952 | 0.9862 | 0.1837 | 0.9976 | 1.0 | 0.9952 | 3.4293 |
| 3.4751 | 2.8409 | 1000 | 0.9952 | 0.9825 | 0.1738 | 0.9976 | 1.0 | 0.9952 | 3.4279 |
| 3.4557 | 3.4091 | 1200 | 0.9936 | 0.9719 | 0.1230 | 0.9968 | 1.0 | 0.9936 | 3.4516 |
| 3.4481 | 3.9773 | 1400 | 0.9952 | 0.9678 | 0.1074 | 0.9976 | 1.0 | 0.9952 | 3.4556 |
| 3.4256 | 4.5455 | 1600 | 0.9928 | 0.9601 | 0.1017 | 0.9964 | 1.0 | 0.9928 | 3.4752 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1
- Datasets 3.1.0
- Tokenizers 0.20.3
- Library
- transformers
- Type
- distilbert
- License
- apache-2.0
- Created
- Nov 15, 2024
- Updated
- Nov 15, 2024