Hugging Face's logo

pkarypis
/
opt-125m-sft

Text Generation
Transformers
TensorBoard
Safetensors
opt
trl
sft
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
opt-125m-sft / README.md
pkarypis's picture
pkarypis
Model save
db9e4d7
preview code
|
raw
history blame contribute delete
No virus
1.46 kB
metadata
license: other
base_model: facebook/opt-125m
tags:
  - trl
  - sft
  - generated_from_trainer
datasets:
  - generator
model-index:
  - name: opt-125m-sft
    results: []

opt-125m-sft

This model is a fine-tuned version of facebook/opt-125m on the generator dataset. It achieves the following results on the evaluation set:

  • Loss: 1.9307

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: 16
  • eval_batch_size: 16
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 32
  • total_train_batch_size: 512
  • total_eval_batch_size: 512
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • num_epochs: 1.0
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
2.5574 1.0 253 1.9307

Framework versions

  • Transformers 4.36.2
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.5
  • Tokenizers 0.15.0