Jeevesh8_lecun_feather_berts-8-finetuned-lora-tweet_eval_irony
This model is a fine-tuned version of Jeevesh8/lecun_feather_berts-8 on the tweet_eval dataset. It achieves the following results on the evaluation set:
- accuracy: 0.6754
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: 0.0005
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
accuracy | train_loss | epoch |
---|---|---|
0.5225 | None | 0 |
0.5686 | 0.6970 | 0 |
0.6335 | 0.6577 | 1 |
0.6398 | 0.6249 | 2 |
0.6524 | 0.5972 | 3 |
0.6639 | 0.5727 | 4 |
0.6628 | 0.5588 | 5 |
0.6712 | 0.5402 | 6 |
0.6754 | 0.5356 | 7 |
Framework versions
- PEFT 0.8.2
- Transformers 4.37.2
- Pytorch 2.2.0
- Datasets 2.16.1
- Tokenizers 0.15.2
- Downloads last month
- 2
Inference API (serverless) does not yet support peft models for this pipeline type.
Model tree for TransferGraph/Jeevesh8_lecun_feather_berts-8-finetuned-lora-tweet_eval_irony
Base model
Jeevesh8/lecun_feather_berts-8Dataset used to train TransferGraph/Jeevesh8_lecun_feather_berts-8-finetuned-lora-tweet_eval_irony
Evaluation results
- accuracy on tweet_evalvalidation set self-reported0.675