0bb1d60b-6e76-4bfd-9832-1645de905a7d

This model is a fine-tuned version of fxmarty/tiny-random-GemmaForCausalLM on the None dataset. It achieves the following results on the evaluation set:

• Loss: 12.3976

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: 0.000213
• train_batch_size: 4
• eval_batch_size: 4
• seed: 130
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 50
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0003	1	12.4576
12.4551	0.0173	50	12.4492
12.4007	0.0346	100	12.4022
12.3946	0.0518	150	12.3999
12.3969	0.0691	200	12.3992
12.3972	0.0864	250	12.3982
12.3973	0.1037	300	12.3984
12.3925	0.1209	350	12.3979
12.392	0.1382	400	12.3977
12.3941	0.1555	450	12.3978
12.3949	0.1728	500	12.3976

Framework versions

• PEFT 0.13.2
• Transformers 4.46.0
• Pytorch 2.5.0+cu124
• Datasets 3.0.1
• Tokenizers 0.20.1