Hugging Face's logo

rishisuresh
/
T5-large-Lora-0913

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
T5-large-Lora-0913 / README.md
rishisuresh's picture
rishisuresh
End of training
7e2b7b6 verified
preview code
|
raw
history blame contribute delete
1.64 kB
metadata
base_model: google/flan-t5-large
library_name: peft
license: apache-2.0
tags:
  - generated_from_trainer
model-index:
  - name: T5-large-Lora-0913
    results: []

T5-large-Lora-0913

This model is a fine-tuned version of google/flan-t5-large on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0263

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: 2
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 4
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 6

Training results

Training Loss Epoch Step Validation Loss
No log 1.0 90 0.1420
No log 2.0 180 0.0555
No log 3.0 270 0.0394
No log 4.0 360 0.0317
No log 5.0 450 0.0276
0.2952 6.0 540 0.0263

Framework versions

  • PEFT 0.12.0
  • Transformers 4.44.2
  • Pytorch 2.4.1+cu121
  • Datasets 3.0.0
  • Tokenizers 0.19.1