GaetanMichelet's picture
End of training
e5aca1e verified
metadata
base_model: mistralai/Mistral-7B-Instruct-v0.3
datasets:
  - GaetanMichelet/chat-60_ft_task-3
  - GaetanMichelet/chat-120_ft_task-3
  - GaetanMichelet/chat-180_ft_task-3
library_name: peft
license: apache-2.0
tags:
  - alignment-handbook
  - trl
  - sft
  - generated_from_trainer
model-index:
  - name: Mistral-7B_task-3_180-samples_config-2_full
    results: []

Mistral-7B_task-3_180-samples_config-2_full

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.3 on the GaetanMichelet/chat-60_ft_task-3, the GaetanMichelet/chat-120_ft_task-3 and the GaetanMichelet/chat-180_ft_task-3 datasets. It achieves the following results on the evaluation set:

  • Loss: 0.8614

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
1.224 0.9412 8 1.1846
1.0894 2.0 17 1.0561
0.9794 2.9412 25 0.9392
0.8318 4.0 34 0.8909
0.8075 4.9412 42 0.8741
0.8096 6.0 51 0.8642
0.7922 6.9412 59 0.8614
0.7089 8.0 68 0.8719
0.6122 8.9412 76 0.8933
0.569 10.0 85 0.9316
0.508 10.9412 93 0.9548
0.4196 12.0 102 0.9916
0.389 12.9412 110 1.0309
0.3283 14.0 119 1.1282

Framework versions

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