metadata
library_name: peft
tags:
- generated_from_trainer
- unsloth
- chatalpaca
- mistral
- conversational
base_model: unsloth/mistral-7b-instruct-v0.2-bnb-4bit
model-index:
- name: Mistral-Instruct-7B-v0.2-ChatAlpacaV2
results: []
license: apache-2.0
datasets:
- robinsmits/ChatAlpaca-20K
language:
- en
inference: false
pipeline_tag: text-generation
Mistral-Instruct-7B-v0.2-ChatAlpacaV2
This model is a fine-tuned version of unsloth/mistral-7b-instruct-v0.2-bnb-4bit on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8439
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: 5e-05
- train_batch_size: 2
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.8801 | 0.2 | 120 | 0.8756 |
| 0.8498 | 0.39 | 240 | 0.8553 |
| 0.8515 | 0.59 | 360 | 0.8475 |
| 0.8313 | 0.78 | 480 | 0.8445 |
| 0.857 | 0.98 | 600 | 0.8439 |
Framework versions
- PEFT 0.8.2
- Transformers 4.37.1
- Pytorch 2.1.1+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1