ruadapt_qwen2.5_3B_darulm_bpe_64000_full_lr3e4_bs256

This model is a fine-tuned version of RefalMachine/ruadapt_qwen2.5_3B_darulm_bpe_64000_mean_init on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.5169
• Accuracy: 0.4977

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: 0.0003
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• distributed_type: multi-GPU
• num_devices: 64
• gradient_accumulation_steps: 2
• total_train_batch_size: 256
• total_eval_batch_size: 128
• optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 100
• num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.0	1	6.3928	0.1604
2.7011	0.18	2000	2.5622	0.4925
2.673	0.35	4000	2.5308	0.4960
2.6503	0.53	6000	2.5210	0.4971
2.6557	0.7	8000	2.5176	0.4977
2.6422	0.88	10000	2.5169	0.4976

Framework versions

• Transformers 4.37.2
• Pytorch 2.3.0a0+6ddf5cf85e.nv24.04
• Datasets 2.18.0
• Tokenizers 0.15.2