mistral-7b-sft-ultrachat-arithmo-full
This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the UltraChat and Arithmo datasets.
It achieves the following results on the evaluation set:
Model description
import torch
from transformers import pipeline
pipe = pipeline("text-generation", model="lewtun/mistral-7b-sft-ultrachat-arithmo-full", torch_dtype=torch.bfloat16, device_map="auto")
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"])
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 |
0.8586 |
0.38 |
344 |
0.9133 |
Framework versions
- Transformers 4.35.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.14.0