68d10e5d-937a-4363-bb4e-60fc8ac87ae7

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

• Loss: 6.7945

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: 0.000207
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• 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	0.0002	1	6.9331
6.8584	0.0118	50	6.8648
6.8127	0.0235	100	6.8334
6.7909	0.0353	150	6.8195
6.78	0.0471	200	6.8108
6.7829	0.0588	250	6.8048
6.772	0.0706	300	6.7998
6.7719	0.0823	350	6.7971
6.772	0.0941	400	6.7953
6.7661	0.1059	450	6.7943
6.7556	0.1176	500	6.7945

Framework versions

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