a70ce691-11de-43c1-ab45-07ed90ac8013

This model is a fine-tuned version of tlphams/gollm-12.8b-instruct-v2.3 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0030

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: 0.000204
• 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	0.0000	1	0.4987
0.0434	0.0020	50	0.0249
0.0225	0.0040	100	0.0119
0.0104	0.0060	150	0.0088
0.0189	0.0081	200	0.0066
0.0093	0.0101	250	0.0057
0.0157	0.0121	300	0.0044
0.0015	0.0141	350	0.0039
0.003	0.0161	400	0.0032
0.0112	0.0181	450	0.0030
0.0126	0.0201	500	0.0030

Framework versions

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