Hugging Face's logo

emily49
/
mistral-7b-instruct-connections

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files Community
mistral-7b-instruct-connections / README.md
emily49's picture
emily49
End of training
636cff8 verified
preview code
|
raw
history blame
2.98 kB
metadata
license: apache-2.0
library_name: peft
tags:
  - trl
  - sft
  - generated_from_trainer
base_model: mistralai/Mistral-7B-Instruct-v0.1
model-index:
  - name: mistral-7b-instruct-connections
    results: []

Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases

mistral-7b-instruct-connections

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.1 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6526

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: 4
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: constant
  • lr_scheduler_warmup_ratio: 0.03
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss
No log 0.9855 17 0.5535
0.8187 1.9710 34 0.5099
0.4261 2.9565 51 0.5141
0.4261 4.0 69 0.5708
0.2769 4.9275 85 0.6526

Framework versions

  • PEFT 0.11.1
  • Transformers 4.42.0.dev0
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1