Edit model card

PointCon-vigogne-2-70b-chat-3

This model is a fine-tuned version of bofenghuang/vigogne-2-70b-chat on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.5719

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: 5e-05
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 1
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
1.8556 0.05 30 1.7646
1.6805 0.1 60 1.6982
1.646 0.15 90 1.6679
1.5978 0.19 120 1.6567
1.6003 0.24 150 1.6437
1.5975 0.29 180 1.6339
1.5917 0.34 210 1.6264
1.5579 0.39 240 1.6111
1.5888 0.44 270 1.6022
1.5763 0.49 300 1.5966
1.5102 0.54 330 1.5938
1.5611 0.58 360 1.5877
1.6063 0.63 390 1.5869
1.5641 0.68 420 1.5870
1.5615 0.73 450 1.5808
1.4644 0.78 480 1.5761
1.4924 0.83 510 1.5750
1.5644 0.88 540 1.5735
1.5498 0.93 570 1.5726
1.5179 0.97 600 1.5719

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu118
  • Datasets 2.15.0
  • Tokenizers 0.15.0
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference API
Unable to determine this model's library. Check the docs .

Model tree for IUseAMouse/PointCon-Vigogne-70B-QLoRA

Finetuned
(2)
this model