0809_031041-google-gemma-2b

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: 0.3773
• Accuracy: 0.8239

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: 1e-05
• train_batch_size: 32
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.4824	0.3546	50	0.5036	0.7367
0.3486	0.7092	100	0.4458	0.7746
0.3555	1.0638	150	0.4337	0.8030
0.3447	1.4184	200	0.4066	0.8239
0.3008	1.7730	250	0.3979	0.8258
0.3857	2.1277	300	0.3888	0.8390
0.2754	2.4823	350	0.3760	0.8314
0.4746	2.8369	400	0.3798	0.8258
0.3281	3.1915	450	0.3734	0.8258
0.3149	3.5461	500	0.3827	0.8277
0.2695	3.9007	550	0.3720	0.8277
0.2524	4.2553	600	0.3758	0.8239
0.2197	4.6099	650	0.3768	0.8220
0.251	4.9645	700	0.3773	0.8239

Framework versions

• PEFT 0.12.0
• Transformers 4.44.0
• Pytorch 2.4.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1