Gemma-2-2B_task-2_120-samples_config-2_full

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

• Loss: 0.8742

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
1.356	0.9091	5	1.3237
1.3153	2.0	11	1.2306
1.1344	2.9091	16	1.1313
1.0582	4.0	22	1.0518
0.9757	4.9091	27	0.9752
0.8903	6.0	33	0.9265
0.8676	6.9091	38	0.9079
0.8368	8.0	44	0.8935
0.8107	8.9091	49	0.8845
0.8061	10.0	55	0.8781
0.7712	10.9091	60	0.8747
0.747	12.0	66	0.8742
0.7182	12.9091	71	0.8779
0.7025	14.0	77	0.8851
0.626	14.9091	82	0.8947
0.633	16.0	88	0.9076
0.583	16.9091	93	0.9299
0.5357	18.0	99	0.9467
0.5232	18.9091	104	0.9674

Framework versions

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