README.md

metadata

license: apache-2.0
base_model: EleutherAI/pythia-410m-deduped-v0
tags:
  - alignment-handbook
  - trl
  - sft
  - generated_from_trainer
  - trl
  - sft
  - generated_from_trainer
datasets:
  - HuggingFaceH4/ultrachat_200k
model-index:
  - name: pythia-410m-sft-full
    results: []

pythia-410m-sft-full

This model is a fine-tuned version of EleutherAI/pythia-410m-deduped-v0 on the HuggingFaceH4/ultrachat_200k dataset. It achieves the following results on the evaluation set:

• Loss: 1.6286

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
• distributed_type: multi-GPU
• num_devices: 2
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• total_eval_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
1.5669	1.0	3982	1.6286

Framework versions

• Transformers 4.39.3
• Pytorch 2.1.2+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2