pythia-410m-sft-full

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

• Loss: 1.5227

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: 0.0002
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 4
• total_train_batch_size: 256
• total_eval_batch_size: 32
• 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
1.5136	1.0	500	1.5227

Framework versions

• Transformers 4.36.2
• Pytorch 2.2.1
• Datasets 2.14.6
• Tokenizers 0.15.2

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	31.12
AI2 Reasoning Challenge (25-Shot)	26.54
HellaSwag (10-Shot)	40.00
MMLU (5-Shot)	25.49
TruthfulQA (0-shot)	40.21
Winogrande (5-shot)	53.43
GSM8k (5-shot)	1.06