1cbefae3-dd10-437c-960e-157259ccb926

This model is a fine-tuned version of bigscience/bloom-560m on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.1596

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: 0.000206
• train_batch_size: 4
• eval_batch_size: 4
• seed: 60
• 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	4.3682
5.0401	0.0116	50	3.1493
3.8837	0.0232	100	2.8177
4.2568	0.0349	150	2.6314
3.62	0.0465	200	2.4684
3.5098	0.0581	250	2.3860
3.1064	0.0697	300	2.3049
2.6914	0.0814	350	2.2421
2.5982	0.0930	400	2.2029
2.3915	0.1046	450	2.1755
2.876	0.1162	500	2.1596

Framework versions

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