m-a-p/CriticLeanGPT-Qwen2.5-14B-Instruct-SFT

Qwen2.5-14B-Instruct-critic_lean_mix_48k

This model is a fine-tuned version of Qwen2.5-14B-Instruct on the critic_lean_mix_48k dataset. It achieves the following results on the evaluation set:

• Loss: 0.2970

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: 5e-06
• train_batch_size: 2
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 16
• total_train_batch_size: 32
• total_eval_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.348	1.0	1485	0.2822
0.2655	2.0	2970	0.2750
0.1382	3.0	4455	0.2970

Framework versions

• Transformers 4.44.2
• Pytorch 2.2.1+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1