lewtun's picture
lewtun HF staff
Update README.md
98384f8
metadata
license: apache-2.0
base_model: mistralai/Mistral-7B-v0.1
tags:
  - generated_from_trainer
model-index:
  - name: mistral-7b-sft-ultrachat-arithmo-25
    results: []
datasets:
  - stingning/ultrachat
  - akjindal53244/Arithmo-Data

mistral-7b-sft-ultrachat-arithmo-25

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the UltraChat and Arithmo (25%) datasets. It achieves the following results on the evaluation set:

  • Loss: 0.8943

Model description

# Install transformers from source - only needed for versions <= v4.34
# pip install git+https://github.com/huggingface/transformers.git
# pip install accelerate

import torch
from transformers import pipeline

pipe = pipeline("text-generation", model="lewtun/mistral-7b-sft-ultrachat-arithmo-25", torch_dtype=torch.bfloat16, device_map="auto")

# We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
messages = [
    {
        "role": "system",
        "content": "You are a friendly chatbot who always responds in the style of a pirate",
    },
    {"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
]
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
# <|system|>
# You are a friendly chatbot who always responds in the style of a pirate.</s>
# <|user|>
# How many helicopters can a human eat in one sitting?</s>
# <|assistant|>
# Ah, me hearty matey! But yer question be a puzzler! A human cannot eat a helicopter in one sitting, as helicopters are not edible. They be made of metal, plastic, and other materials, not food!

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: 8
  • eval_batch_size: 16
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 16
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 512
  • total_eval_batch_size: 256
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss
0.9051 0.54 290 0.8943

Framework versions

  • Transformers 4.35.0.dev0
  • Pytorch 2.0.1+cu118
  • Datasets 2.12.0
  • Tokenizers 0.14.0