gemma2b_quotes_v3

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

• Loss: 2.5712

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: 1
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 4
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• lr_scheduler_warmup_steps: 0.03
• training_steps: 50

Training results

Training Loss	Epoch	Step	Validation Loss
2.1771	0.0100	5	2.8362
2.55	0.0199	10	2.7224
2.4796	0.0299	15	2.7221
2.0271	0.0399	20	2.6961
1.8608	0.0499	25	2.6895
2.2195	0.0598	30	2.6817
1.9869	0.0698	35	2.6622
2.1826	0.0798	40	2.6511
1.8479	0.0897	45	2.6027
1.9439	0.0997	50	2.5712

Framework versions

• PEFT 0.11.1
• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1