med_Mistral / README.md
joseagmz's picture
Upload folder using huggingface_hub
7549fb8 verified
metadata
license: apache-2.0
library_name: peft
tags:
  - generated_from_trainer
base_model: mistralai/Mistral-7B-v0.1
model-index:
  - name: med_Mistral
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.0

adapter: qlora
base_model: mistralai/Mistral-7B-v0.1
bf16: false
dataset_prepared_path: null
datasets:
- path: joseagmz/MedQnA_version3
  type: context_qa.load_v2
debug: null
deepspeed: null
early_stopping_patience: null
evals_per_epoch: null
flash_attention: false
fp16: true
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 1
gradient_checkpointing: true
group_by_length: false
is_llama_derived_model: true
learning_rate: 0.0002
load_in_4bit: true
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 16
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lora_target_modules: null
lr_scheduler: cosine
max_steps: 20
micro_batch_size: 1
mlflow_experiment_name: colab-example
model_type: MistralForCausalLM
num_epochs: 4
optimizer: paged_adamw_32bit
output_dir: ./med_Mistral
pad_to_sequence_len: true
resume_from_checkpoint: null
sample_packing: true
saves_per_epoch: null
sequence_len: 1096
special_tokens: null
strict: false
tf32: false
tokenizer_type: LlamaTokenizer
train_on_inputs: false
val_set_size: 0.05
wandb_entity: null
wandb_log_model: null
wandb_name: null
wandb_project: null
wandb_watch: null
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

med_Mistral

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.3152

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
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 10
  • training_steps: 20
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
1.9831 0.0 20 1.3152

Framework versions

  • PEFT 0.8.2
  • Transformers 4.38.0.dev0
  • Pytorch 2.1.2+cu121
  • Datasets 2.17.0
  • Tokenizers 0.15.0