Edit model card

saiga13summary_v20

This model is a fine-tuned version of meta-llama/Llama-2-13b-hf on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.1252

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: 0.0003
  • train_batch_size: 2
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 10
  • total_train_batch_size: 20
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • training_steps: 200

Training results

Training Loss Epoch Step Validation Loss
1.5622 0.8621 20 1.5155
1.2731 1.7241 40 1.3525
1.0342 2.5862 60 1.2242
0.8946 3.4483 80 1.1574
0.765 4.3103 100 1.1336
0.7816 5.1724 120 1.1239
0.728 6.0345 140 1.1192
0.705 6.8966 160 1.1205
0.6746 7.7586 180 1.1217
0.6631 8.6207 200 1.1252

Framework versions

  • PEFT 0.12.1.dev0
  • Transformers 4.45.0.dev0
  • Pytorch 2.3.0+cu121
  • Datasets 2.17.1
  • Tokenizers 0.19.1
Downloads last month
0
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for marcus2000/saiga13summary_v20

Adapter
(125)
this model