Gemma-2b-MultiCap

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

• Loss: 0.5983

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: 0.0001
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.03
• training_steps: 600

Training results

Training Loss	Epoch	Step	Validation Loss
0.8045	0.0564	50	0.8067
0.7271	0.1128	100	0.6777
0.688	0.1692	150	0.6309
0.6268	0.2256	200	0.6176
0.572	0.2820	250	0.6118
0.5864	0.3384	300	0.6065
0.5528	0.3948	350	0.6030
0.5396	0.4512	400	0.6015
0.5726	0.5076	450	0.6005
0.5655	0.5640	500	0.5997
0.5712	0.6204	550	0.5988
0.5213	0.6768	600	0.5983

Framework versions

• PEFT 0.12.0
• Transformers 4.44.2
• Pytorch 2.4.0+cu124
• Datasets 2.21.0
• Tokenizers 0.19.1