Hugging Face's logo

astroa7m
/
Jais-AOU

Text Generation
Transformers
Safetensors
jais
trl
sft
Generated from Trainer
conversational
custom_code
Model card Files Community
Jais-AOU / README.md
astroa7m's picture
astroa7m
Jais_AOU
2157911 verified
preview code
|
raw
history blame contribute delete
1.75 kB
metadata
library_name: transformers
license: apache-2.0
base_model: inceptionai/jais-family-590m-chat
tags:
  - trl
  - sft
  - generated_from_trainer
model-index:
  - name: Jais-AOU
    results: []

Jais-AOU

This model is a fine-tuned version of inceptionai/jais-family-590m-chat on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7540

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: 2e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 50
  • num_epochs: 12
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
1.1215 1.7699 50 1.1407
0.5782 3.5398 100 0.8883
0.3542 5.3097 150 0.7643
0.2372 7.0796 200 0.7418
0.203 8.8496 250 0.7372
0.1891 10.6195 300 0.7540

Framework versions

  • Transformers 4.45.2
  • Pytorch 2.4.0
  • Datasets 3.0.1
  • Tokenizers 0.20.0