metadata

license: apache-2.0
base_model: BioMistral/BioMistral-7B
tags:
  - alignment-handbook
  - trl
  - sft
  - generated_from_trainer
  - trl
  - sft
  - generated_from_trainer
datasets:
  - HuggingFaceH4/deita-10k-v0-sft
model-index:
  - name: biomistral-7b-5e-6-wo-healthsearch_qa-iter-sft-step1_lr
    results: []

biomistral-7b-5e-6-wo-healthsearch_qa-iter-sft-step1_lr

This model is a fine-tuned version of BioMistral/BioMistral-7B on the HuggingFaceH4/deita-10k-v0-sft dataset. It achieves the following results on the evaluation set:

Loss: 1.5541

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-06
train_batch_size: 4
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 4
total_train_batch_size: 64
total_eval_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
2.0888	0.89	2	1.5769
2.0888	1.78	4	1.5594
1.8724	2.67	6	1.5541

Framework versions

Transformers 4.39.0.dev0
Pytorch 2.1.2
Datasets 2.14.6
Tokenizers 0.15.2