cot-trainset-ft-transduction-v4-lora-train

This model is a fine-tuned version of barc0/cot-transduction-arc-heavy on the barc0/cot_train_dataset_960_ms10_v2, the barc0/cot_rearc_dataset_100_ms10 and the barc0/seeds_cot datasets. It achieves the following results on the evaluation set:

• Loss: 0.1497

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: 0.0002
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• total_eval_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
0.103	0.9983	287	0.1445
0.0874	1.9965	574	0.1497

Framework versions

• PEFT 0.12.0
• Transformers 4.45.0.dev0
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1