Llama-2-7b-chat-hf-formula-peft

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

• Loss: 2.1452

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: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss
4.1878	1.43	10	3.6596
2.8437	2.86	20	2.6466
1.8635	4.29	30	2.2266
1.4052	5.71	40	2.1136
1.2186	7.14	50	2.0805
0.8835	8.57	60	2.0733
0.6991	10.0	70	2.0809
0.5608	11.43	80	2.0862
0.4188	12.86	90	2.1078
0.3897	14.29	100	2.1089
0.2748	15.71	110	2.1333
0.2582	17.14	120	2.1383
0.2394	18.57	130	2.1440
0.2392	20.0	140	2.1452

Framework versions

• Transformers 4.34.1
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1