gemma2-career-guidance

This model is a fine-tuned version of google/gemma-2b on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.1038

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: 3
• eval_batch_size: 3
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 6
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.2127	0.2331	100	1.2403
1.1809	0.4662	200	1.1635
1.1384	0.6993	300	1.1451
1.0805	0.9324	400	1.1187
0.8494	1.1655	500	1.1333
0.9014	1.3986	600	1.1291
0.8826	1.6317	700	1.1131
0.8646	1.8648	800	1.1001
0.619	2.0979	900	1.2390
0.5687	2.3310	1000	1.2335
0.582	2.5641	1100	1.2134
0.5543	2.7972	1200	1.2244
0.5199	3.0303	1300	1.3083

Framework versions

• PEFT 0.18.1
• Transformers 4.46.2
• Pytorch 2.5.1+cu124
• Datasets 4.5.0
• Tokenizers 0.20.3