metadata

license: llama2
library_name: peft
tags:
  - trl-sft
  - generated_from_trainer
datasets:
  - generator
base_model: sarvamai/OpenHathi-7B-Hi-v0.1-Base
model-index:
  - name: OpenHathi-7B-Hi-v0.1-Instruct
    results: []

OpenHathi-7B-Hi-v0.1-Instruct

This model is a fine-tuned version of sarvamai/OpenHathi-7B-Hi-v0.1-Base on the generator dataset. It achieves the following results on the evaluation set:

Loss: 0.9311

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: 0.0001
train_batch_size: 4
eval_batch_size: 4
seed: 100
gradient_accumulation_steps: 4
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.03
num_epochs: 3.0
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.5099	1.0	175	0.9747
1.4435	2.0	351	0.9363
1.4369	2.99	525	0.9311

Framework versions

PEFT 0.7.2.dev0
Transformers 4.37.0.dev0
Pytorch 2.1.0+cu121
Datasets 2.15.0
Tokenizers 0.15.0