1a134dc2eb3bce07c9a7936c27c0d2c8

This model is a fine-tuned version of Qwen/Qwen2.5-3B on the google/boolq dataset. It achieves the following results on the evaluation set:

• Loss: 7.3683
• Data Size: 1.0
• Epoch Runtime: 131.7022
• Accuracy: 0.6532
• F1 Macro: 0.6246
• Rouge1: 0.6532
• Rouge2: 0.0
• Rougel: 0.6529
• Rougelsum: 0.6529

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	7.5316	0	11.7479	0.6167	0.4064	0.6170	0.0	0.6161	0.6164
No log	1	294	50.8245	0.0078	13.2546	0.3811	0.2806	0.3811	0.0	0.3814	0.3814
No log	2	588	4.1720	0.0156	16.9468	0.6155	0.4104	0.6155	0.0	0.6152	0.6150
No log	3	882	4.2681	0.0312	21.3451	0.6232	0.3937	0.6235	0.0	0.6222	0.6232
0.3005	4	1176	2.8119	0.0625	27.4886	0.6222	0.3859	0.6222	0.0	0.6216	0.6222
0.2866	5	1470	2.8051	0.125	36.9648	0.6066	0.4119	0.6066	0.0	0.6060	0.6060
0.46	6	1764	3.0223	0.25	49.3831	0.3799	0.2788	0.3799	0.0	0.3802	0.3802
2.7997	7	2058	2.6535	0.5	77.6294	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
2.6791	8.0	2352	2.6546	1.0	135.9464	0.5885	0.5764	0.5888	0.0	0.5885	0.5888
2.2742	9.0	2646	2.5097	1.0	133.1889	0.6498	0.6244	0.6495	0.0	0.6498	0.6495
2.2826	10.0	2940	3.2409	1.0	133.3433	0.6590	0.5421	0.6590	0.0	0.6587	0.6590
1.4271	11.0	3234	3.1746	1.0	132.3281	0.6575	0.6029	0.6575	0.0	0.6573	0.6575
0.6124	12.0	3528	6.3895	1.0	131.8055	0.6752	0.6043	0.6752	0.0	0.6749	0.6752
0.4867	13.0	3822	7.3683	1.0	131.7022	0.6532	0.6246	0.6532	0.0	0.6529	0.6529

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu128
• Datasets 4.2.0
• Tokenizers 0.22.1