llama_2_gsm8k_gold_answer

This model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.4465

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: 4
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• 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
• training_steps: 50

Training results

Training Loss	Epoch	Step	Validation Loss
3.5265	0.7692	5	2.7999
2.1262	1.5385	10	1.8010
1.5822	2.3077	15	1.5753
1.3955	3.0769	20	1.5030
1.2614	3.8462	25	1.4373
1.2132	4.6154	30	1.4229
1.0909	5.3846	35	1.4237
1.0842	6.1538	40	1.4348
1.0144	6.9231	45	1.4450
0.9903	7.6923	50	1.4465

Framework versions

• PEFT 0.12.0
• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.0
• Tokenizers 0.19.1