BigTMiami/dapt_plus_tapt_amazon_helpfulness_classification_v2

1---2license: mit3base_model: BigTMiami/dapt_plus_tapt_helpfulness_base_pretraining_model4tags:5- generated_from_trainer6metrics:7- accuracy8model-index:9- name: dapt_plus_tapt_amazon_helpfulness_classification_v210  results: []11---12 13<!-- This model card has been generated automatically according to the information the Trainer had access to. You14should probably proofread and complete it, then remove this comment. -->15 16# dapt_plus_tapt_amazon_helpfulness_classification_v217 18This model is a fine-tuned version of [BigTMiami/dapt_plus_tapt_helpfulness_base_pretraining_model](https://huggingface.co/BigTMiami/dapt_plus_tapt_helpfulness_base_pretraining_model) on an unknown dataset.19It achieves the following results on the evaluation set:20- Loss: 0.326721- Accuracy: 0.862822- F1 Macro: 0.689823 24## Model description25 26More information needed27 28## Intended uses & limitations29 30More information needed31 32## Training and evaluation data33 34More information needed35 36## Training procedure37 38### Training hyperparameters39 40The following hyperparameters were used during training:41- learning_rate: 2e-0542- train_batch_size: 1643- eval_batch_size: 1644- seed: 4245- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-0646- lr_scheduler_type: linear47- lr_scheduler_warmup_ratio: 0.0648- num_epochs: 1049 50### Training results51 52| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro |53|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|54| 0.3333        | 1.0   | 1563 | 0.3267          | 0.8628   | 0.6898   |55| 0.309         | 2.0   | 3126 | 0.3859          | 0.8696   | 0.6292   |56| 0.2443        | 3.0   | 4689 | 0.4222          | 0.8664   | 0.6222   |57| 0.1683        | 4.0   | 6252 | 0.5618          | 0.867    | 0.6315   |58| 0.1591        | 5.0   | 7815 | 0.6760          | 0.8668   | 0.6678   |59| 0.0877        | 6.0   | 9378 | 0.8763          | 0.8614   | 0.6678   |60 61 62### Framework versions63 64- Transformers 4.38.265- Pytorch 2.2.1+cu12166- Datasets 2.18.067- Tokenizers 0.15.268