prec_240807_llama2

This model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on the perception_240723 dataset. It achieves the following results on the evaluation set:

• Loss: 0.8686

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: 1e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• gradient_accumulation_steps: 2
• total_train_batch_size: 4
• total_eval_batch_size: 2
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.9956	0.1111	50	0.9926
0.9989	0.2222	100	0.9736
0.9373	0.3333	150	0.9539
1.0155	0.4444	200	0.9442
0.9273	0.5556	250	0.9123
0.8789	0.6667	300	0.8964
0.871	0.7778	350	0.8800
0.8756	0.8889	400	0.8700
0.9423	1.0	450	0.8686

Framework versions

• Transformers 4.43.3
• Pytorch 2.4.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1