llama2-7b-dolly-15k-japanese-brainstorming

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

• Loss: 1.0642
• Rouge Scores: {'rouge1': 0.9653633690526473, 'rouge2': 0.9344851380895685, 'rougeL': 0.9554449155418876, 'rougeLsum': 0.9653412268073773}
• Bleu Scores: [0.900726205206837, 0.8659579174904524, 0.8282110782853057, 0.788805544882148]
• Gen Len: 467.6554

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
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge Scores	Bleu Scores	Gen Len
0.9844	1.0	398	0.9678	{'rouge1': 0.9691461778318393, 'rouge2': 0.9382969684393989, 'rougeL': 0.9578632643524403, 'rougeLsum': 0.9690528081779507}	[0.9044212000231915, 0.86963718873592, 0.8320476513312739, 0.7928883742871506]	467.6554
0.6979	2.0	796	0.9827	{'rouge1': 0.9660674664057384, 'rouge2': 0.935760349759682, 'rougeL': 0.9563208459437473, 'rougeLsum': 0.9658214441757752}	[0.9032042405966677, 0.8700278506363877, 0.8335211486398665, 0.7953375975436736]	467.6554
0.4532	3.0	1194	1.0642	{'rouge1': 0.9653633690526473, 'rouge2': 0.9344851380895685, 'rougeL': 0.9554449155418876, 'rougeLsum': 0.9653412268073773}	[0.900726205206837, 0.8659579174904524, 0.8282110782853057, 0.788805544882148]	467.6554

Framework versions

• PEFT 0.8.2
• Transformers 4.39.0.dev0
• Pytorch 2.1.0+cu121
• Datasets 2.17.2.dev0
• Tokenizers 0.15.2