llama-3-8b-base-ultrachat-sft-4xh100/README.md

library_name, license, base_model, tags, datasets, model-index

library_name	license	base_model	tags	datasets	model-index
transformers	llama3	meta-llama/Meta-Llama-3-8B	alignment-handbook generated_from_trainer	HuggingFaceH4/ultrachat_200k	name results llama-3-8b-base-ultrachat-sft-4xh100

llama-3-8b-base-ultrachat-sft-4xh100

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on the HuggingFaceH4/ultrachat_200k dataset. It achieves the following results on the evaluation set:

• Loss: 1.0704

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: 2
• eval_batch_size: 2
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 16
• total_train_batch_size: 128
• total_eval_batch_size: 8
• 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
1.1457	0.2138	200	1.1342
1.0927	0.4276	400	1.1092
1.0811	0.6414	600	1.0847
1.0531	0.8552	800	1.0704

Framework versions

• Transformers 4.44.2
• Pytorch 2.3.1+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1