llama-3b-bird-planner-fft

This model is a fine-tuned version of /home/datht/huggingface/meta-llama/Llama-3.2-3B-Instruct on the /home/datht/codes/data/multi-agents/planner/sft-gpt-4o-mini-planner_combine_with_true_sql_bird_062024_with_evidence_train/ dataset. It achieves the following results on the evaluation set:

• Loss: 0.0070

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: 4
• seed: 42
• distributed_type: multi-GPU
• gradient_accumulation_steps: 16
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss
0.0941	0.9956	57	0.0703
0.0599	1.9913	114	0.0384
0.0303	2.9869	171	0.0168
0.0125	3.9825	228	0.0070

Framework versions

• Transformers 4.44.0
• Pytorch 2.2.2+cu121
• Datasets 2.14.6
• Tokenizers 0.19.1