code-1b-chat-v2/README.md

library_name, license, base_model, tags, model-index

library_name	license	base_model	tags	model-index
transformers	apache-2.0	rovdetection/code-1b-pretrain-v3	generated_from_trainer	name results code-1b-chat-v2

code-1b-chat-v2

This model is a fine-tuned version of rovdetection/code-1b-pretrain-v3 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.9919

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: 2e-05
• train_batch_size: 1
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 32
• total_train_batch_size: 32
• 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: 100
• training_steps: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.0509	0.8840	500	1.0258
0.6652	1.7673	1000	0.9919

Framework versions

• Transformers 5.9.0
• Pytorch 2.10.0+cu128
• Datasets 4.8.5
• Tokenizers 0.22.2