thenlpresearcher/mistral_sequence_classification

1---2library_name: peft3license: apache-2.04base_model: mistralai/Mistral-7B-v0.35tags:6- generated_from_trainer7model-index:8- name: mistral_sequence_classification9  results: []10---11 12<!-- This model card has been generated automatically according to the information the Trainer had access to. You13should probably proofread and complete it, then remove this comment. -->14 15# mistral_sequence_classification16 17This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on the None dataset.18It achieves the following results on the evaluation set:19- Loss: 0.266720- Pearson: 0.970421 22## Model description23 24More information needed25 26## Intended uses & limitations27 28More information needed29 30## Training and evaluation data31 32More information needed33 34## Training procedure35 36### Training hyperparameters37 38The following hyperparameters were used during training:39- learning_rate: 0.000140- train_batch_size: 3241- eval_batch_size: 842- seed: 4243- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0844- lr_scheduler_type: linear45- num_epochs: 546 47### Training results48 49| Training Loss | Epoch | Step | Validation Loss | Pearson |50|:-------------:|:-----:|:----:|:---------------:|:-------:|51| No log        | 1.0   | 206  | 0.3305          | 0.9028  |52| No log        | 2.0   | 412  | 0.2609          | 0.9532  |53| 0.4868        | 3.0   | 618  | 0.2432          | 0.9611  |54| 0.4868        | 4.0   | 824  | 0.2611          | 0.9639  |55| 0.0417        | 5.0   | 1030 | 0.2667          | 0.9704  |56 57 58### Framework versions59 60- PEFT 0.14.061- Transformers 4.45.262- Pytorch 2.4.0a0+f70bd71a48.nv24.0663- Datasets 3.2.064- Tokenizers 0.20.3