Edit model card

Visualize in Weights & Biases

ERC_SUMMARY_gemma_peft

This model is a fine-tuned version of google/gemma-7b-it on the ArunaMak/ERC_summary dataset. It achieves the following results on the evaluation set:

  • Loss: 1.5364

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: 1e-05
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 4
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • num_epochs: 6

Training results

Training Loss Epoch Step Validation Loss
4.3768 0.9921 94 4.8155
1.6402 1.9947 189 1.6594
1.3945 2.9974 284 1.5666
1.3478 4.0 379 1.5460
1.3085 4.9921 473 1.5388
1.1856 5.9525 564 1.5364

Framework versions

  • PEFT 0.12.0
  • Transformers 4.43.0.dev0
  • Pytorch 2.3.1+cu118
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
3
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for ArunaMak/gemma_fine_tuned

Base model

google/gemma-7b
Finetuned
google/gemma-7b-it
Adapter
(73)
this model