---
library_name: peft
license: apache-2.0
base_model: humain-ai/ALLaM-7B-Instruct-preview
tags:
- base_model:adapter:humain-ai/ALLaM-7B-Instruct-preview
- lora
- transformers
pipeline_tag: text-generation
model-index:
- name: mcq-lora-out3
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# mcq-lora-out3

This model is a fine-tuned version of [humain-ai/ALLaM-7B-Instruct-preview](https://huggingface.co/humain-ai/ALLaM-7B-Instruct-preview) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0316

## 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: 0.0002
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 32
- total_train_batch_size: 32
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 3

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 0.6249        | 0.5735 | 50   | 0.7174          |
| 0.116         | 1.1376 | 100  | 1.0316          |


### Framework versions

- PEFT 0.17.1
- Transformers 4.56.2
- Pytorch 2.8.0+cu128
- Datasets 4.1.1
- Tokenizers 0.22.1