66f38a3b1589c02e6371f5707d3a106c

This model is a fine-tuned version of deepseek-ai/DeepSeek-R1-Distill-Qwen-7B on the fancyzhx/dbpedia_14 dataset. It achieves the following results on the evaluation set:

• Loss: 0.3213
• Data Size: 1.0
• Epoch Runtime: 17258.9539
• Accuracy: 0.9883
• F1 Macro: 0.9883
• Rouge1: 0.9883
• Rouge2: 0.0
• Rougel: 0.9883
• Rougelsum: 0.9883

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-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• total_train_batch_size: 32
• total_eval_batch_size: 32
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: constant
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Data Size	Epoch Runtime	Accuracy	F1 Macro	Rouge1	Rouge2	Rougel	Rougelsum
No log	0	0	31.6545	0	267.2952	0.0966	0.0393	0.0965	0.0	0.0965	0.0967
0.9544	1	17500	1.1678	0.0078	396.9469	0.9582	0.9580	0.9582	0.0	0.9582	0.9583
0.5234	2	35000	0.5709	0.0156	534.0985	0.9735	0.9736	0.9735	0.0	0.9735	0.9735
0.4576	3	52500	0.4903	0.0312	810.5504	0.9836	0.9835	0.9836	0.0	0.9836	0.9836
0.3233	4	70000	0.4092	0.0625	1338.8806	0.9797	0.9798	0.9798	0.0	0.9797	0.9797
0.2983	5	87500	0.3439	0.125	2402.1746	0.9845	0.9845	0.9845	0.0	0.9845	0.9845
0.3199	6	105000	0.2991	0.25	4501.2012	0.9839	0.9840	0.9839	0.0	0.9839	0.9839
0.0018	7	122500	0.2544	0.5	8744.8150	0.9866	0.9866	0.9866	0.0	0.9866	0.9866
0.1702	8.0	140000	0.2525	1.0	17214.3393	0.9881	0.9881	0.9881	0.0	0.9881	0.9881
0.0731	9.0	157500	0.2546	1.0	17199.1036	0.9887	0.9887	0.9887	0.0	0.9887	0.9887
0.0525	10.0	175000	0.2983	1.0	17220.8883	0.9875	0.9875	0.9875	0.0	0.9875	0.9875
0.0431	11.0	192500	0.3369	1.0	17223.4248	0.9889	0.9889	0.9889	0.0	0.9889	0.9889
0.0553	12.0	210000	0.3213	1.0	17258.9539	0.9883	0.9883	0.9883	0.0	0.9883	0.9883

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.1