HFShishir's picture
Release BanglaFast-500M-Instruct v1.0
367cc32 verified
|
Raw History Blame Contribute Delete
1.71 kB
metadata
library_name: transformers
license: apache-2.0
base_model: HFShishir/BanglaFast-500M-Foundation-SLM
tags:
  - generated_from_trainer
model-index:
  - name: BanglaFast-500M-Instruct
    results: []

BanglaFast-500M-Instruct

This model is a fine-tuned version of HFShishir/BanglaFast-500M-Foundation-SLM on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0433

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: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 32
  • optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 50
  • num_epochs: 3
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.0512 1.0 179 0.0491
0.0440 2.0 358 0.0437
0.0427 3.0 537 0.0433

Framework versions

  • Transformers 5.22.1
  • Pytorch 2.14.1+cu130
  • Datasets 4.8.5
  • Tokenizers 0.23.3