TransferGraph/Capreolus_bert-base-msmarco-finetuned-lora-tweet_eval_hate

1---2library_name: peft3tags:4- parquet5- text-classification6datasets:7- tweet_eval8metrics:9- accuracy10base_model: Capreolus/bert-base-msmarco11model-index:12- name: Capreolus_bert-base-msmarco-finetuned-lora-tweet_eval_hate13  results:14  - task:15      type: text-classification16      name: Text Classification17    dataset:18      name: tweet_eval19      type: tweet_eval20      config: hate21      split: validation22      args: hate23    metrics:24    - type: accuracy25      value: 0.72926      name: accuracy27---28 29<!-- This model card has been generated automatically according to the information the Trainer had access to. You30should probably proofread and complete it, then remove this comment. -->31 32# Capreolus_bert-base-msmarco-finetuned-lora-tweet_eval_hate33 34This model is a fine-tuned version of [Capreolus/bert-base-msmarco](https://huggingface.co/Capreolus/bert-base-msmarco) on the tweet_eval dataset.35It achieves the following results on the evaluation set:36- accuracy: 0.72937 38## Model description39 40More information needed41 42## Intended uses & limitations43 44More information needed45 46## Training and evaluation data47 48More information needed49 50## Training procedure51 52### Training hyperparameters53 54The following hyperparameters were used during training:55- learning_rate: 0.000456- train_batch_size: 3257- eval_batch_size: 3258- seed: 4259- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0860- lr_scheduler_type: linear61- num_epochs: 462 63### Training results64 65| accuracy | train_loss | epoch |66|:--------:|:----------:|:-----:|67| 0.574    | None       | 0     |68| 0.701    | 0.7621     | 0     |69| 0.717    | 0.5213     | 1     |70| 0.723    | 0.4752     | 2     |71| 0.729    | 0.4514     | 3     |72 73 74### Framework versions75 76- PEFT 0.8.277- Transformers 4.37.278- Pytorch 2.2.079- Datasets 2.16.180- Tokenizers 0.15.2