agent_instruct_llama2_fullsft_agentinst_sharegpt_20240628

This model is a fine-tuned version of /home/ubuntu/bill/model/Llama-2-7b-chat-hf on the agent_instruct_mix_sharegpt dataset. It achieves the following results on the evaluation set:

• Loss: 0.7350

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: 5e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• 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: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.9302	0.4398	500	0.8788
0.8481	0.8795	1000	0.8225
0.4477	1.3193	1500	0.7884
0.4438	1.7590	2000	0.7362
0.2391	2.1988	2500	0.7423
0.2133	2.6385	3000	0.7365

Framework versions

• Transformers 4.41.2
• Pytorch 2.2.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1