GaetanMichelet's picture
End of training
662e2be verified
metadata
base_model: mistralai/Mistral-7B-Instruct-v0.3
datasets:
  - GaetanMichelet/chat-60_ft_task-1
  - GaetanMichelet/chat-120_ft_task-1
library_name: peft
license: apache-2.0
tags:
  - alignment-handbook
  - trl
  - sft
  - generated_from_trainer
model-index:
  - name: Mistral-7B_task-1_120-samples_config-2
    results: []

Mistral-7B_task-1_120-samples_config-2

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.3 on the GaetanMichelet/chat-60_ft_task-1 and the GaetanMichelet/chat-120_ft_task-1 datasets. It achieves the following results on the evaluation set:

  • Loss: 1.1563

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: 0.0001
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • gradient_accumulation_steps: 16
  • total_train_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: 50

Training results

Training Loss Epoch Step Validation Loss
2.2934 0.9091 5 2.0668
1.592 2.0 11 1.4282
1.2147 2.9091 16 1.2907
1.0354 4.0 22 1.1563
0.907 4.9091 27 1.1639
0.6665 6.0 33 1.2559
0.3785 6.9091 38 1.4904
0.1927 8.0 44 1.8472
0.0701 8.9091 49 2.0194
0.0521 10.0 55 2.1609
0.0379 10.9091 60 2.1465

Framework versions

  • PEFT 0.12.0
  • Transformers 4.44.0
  • Pytorch 2.1.2+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1