Hugging Face's logo

rishiraj
/
bondhu-7b-alpha

Text Generation
Transformers
Safetensors
Bengali
mistral
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
bondhu-7b-alpha / README.md
rishiraj's picture
rishiraj
Update README.md
7d6ce98
preview code
|
raw
history blame contribute delete
1.45 kB
metadata
license: mit
base_model: HuggingFaceH4/zephyr-7b-beta
tags:
  - generated_from_trainer
model-index:
  - name: bondhu-7b-alpha
    results: []
datasets:
  - rishiraj/bengalichat
language:
  - bn

bondhu-7b-alpha

This model is a fine-tuned version of HuggingFaceH4/zephyr-7b-beta on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.4296

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: 2e-05
  • train_batch_size: 4
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • gradient_accumulation_steps: 128
  • total_train_batch_size: 512
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss
1.4503 0.65 12 1.4296

Framework versions

  • Transformers 4.35.0
  • Pytorch 2.1.1+cu121
  • Datasets 2.14.6
  • Tokenizers 0.14.1