Gemma-2-2B_task-2_60-samples_config-1_full

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

Loss: 0.8953

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
1.2928	0.8696	5	1.3069
1.2992	1.9130	11	1.2225
1.1839	2.9565	17	1.1170
1.0415	4.0	23	1.0408
0.9451	4.8696	28	0.9726
0.8679	5.9130	34	0.9312
0.8006	6.9565	40	0.9111
0.7924	8.0	46	0.9005
0.7768	8.8696	51	0.8965
0.7665	9.9130	57	0.8953
0.6893	10.9565	63	0.9024
0.6515	12.0	69	0.9145
0.6535	12.8696	74	0.9321
0.5737	13.9130	80	0.9723
0.5352	14.9565	86	0.9994
0.5419	16.0	92	1.0520
0.3587	16.8696	97	1.1345