Gemma-2-2B_task-1_180-samples_config-1_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: 0.9279

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: 8
• total_train_batch_size: 8
• 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
2.1329	1.0	17	2.0792
1.45	2.0	34	1.3699
1.025	3.0	51	1.0322
0.8935	4.0	68	0.9611
0.827	5.0	85	0.9339
0.7407	6.0	102	0.9279
0.5958	7.0	119	0.9795
0.4738	8.0	136	1.0905
0.3328	9.0	153	1.3366
0.2352	10.0	170	1.5625
0.1754	11.0	187	1.6811
0.1229	12.0	204	1.8215
0.1126	13.0	221	1.8674

Framework versions

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