o1_sft_all_abla_numina_oly_orca

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

all_abla_numina_oly_orca

This model is a fine-tuned version of /home/test/testdata/models/Meta-Llama-3.1-8B-Instruct on the codefeedback-o1, the magicoder-o1, the magicoder-oss-o1, the mathinstruct-MATH-o1, the mathinstruct-augmented-o1, the numina-cn-k12-o1, the numina-not-cn-k12-o1, the reasoning-001-o1 and the ultramedical_mc_o1 datasets. It achieves the following results on the evaluation set:

• Loss: 0.2059
• Accuracy: 0.9286

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: 1e-05
• train_batch_size: 4
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 32
• gradient_accumulation_steps: 2
• total_train_batch_size: 256
• total_eval_batch_size: 32
• 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

Framework versions

• Transformers 4.43.4
• Pytorch 2.4.0
• Datasets 2.20.0
• Tokenizers 0.19.1