qwen3-0.6b-vericava-posts-v3

This model is a fine-tuned version of Qwen/Qwen3-0.6B on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 6.9891

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: 0.0005
• train_batch_size: 128
• eval_batch_size: 128
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 1024
• optimizer: Use OptimizerNames.ADAMW_TORCH 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: 1000
• num_epochs: 150

Training results

Training Loss	Epoch	Step	Validation Loss
2.3084	11.1159	100	7.3315
1.5889	22.2319	200	5.7203
1.2512	33.3478	300	5.1681
0.9954	44.4638	400	5.3320
0.5796	55.5797	500	5.9040
0.2523	66.6957	600	6.3274
0.1139	77.8116	700	6.4830
0.0936	88.9275	800	6.5364
0.0715	100.0	900	6.6161
0.0478	111.1159	1000	6.7347
0.0371	122.2319	1100	6.8515
0.0143	133.3478	1200	6.9626
0.0076	144.4638	1300	6.9891

Framework versions

• Transformers 4.52.4
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.1