Gemma-2-2B_task-1_180-samples_config-2_full_auto

This model is a fine-tuned version of google/gemma-2-2b-it on the GaetanMichelet/chat-60_ft_task-1_auto, the GaetanMichelet/chat-120_ft_task-1_auto and the GaetanMichelet/chat-180_ft_task-1_auto datasets. It achieves the following results on the evaluation set:

• Loss: 0.9375

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: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• gradient_accumulation_steps: 16
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss
2.2783	0.9412	8	2.2320
1.8925	2.0	17	1.7374
1.479	2.9412	25	1.3322
1.0469	4.0	34	1.0631
0.962	4.9412	42	0.9939
0.9343	6.0	51	0.9545
0.8325	6.9412	59	0.9375
0.7698	8.0	68	0.9379
0.6897	8.9412	76	0.9577
0.5925	10.0	85	1.0182
0.506	10.9412	93	1.1055
0.3319	12.0	102	1.2682
0.2649	12.9412	110	1.4429
0.2121	14.0	119	1.6486

Framework versions

• PEFT 0.12.0
• Transformers 4.44.0
• Pytorch 2.1.2+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1