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
Downloads last month
24
Safetensors
Model size
125M params
Tensor type
FP16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for pkarypis/opt-125m-sft

Base model

facebook/opt-125m
Finetuned
(48)
this model