3c7e1bd3dc07cfbed338e80dad831be2

This model is a fine-tuned version of Qwen/Qwen2.5-0.5B on the google/boolq dataset. It achieves the following results on the evaluation set:

• Loss: 7.9243
• Data Size: 1.0
• Epoch Runtime: 57.8806
• Accuracy: 0.6636
• F1 Macro: 0.6234
• Rouge1: 0.6636
• Rouge2: 0.0
• Rougel: 0.6633
• Rougelsum: 0.6636

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	13.8651	0	6.8162	0.3891	0.3391	0.3888	0.0	0.3891	0.3885
No log	1	294	19.2783	0.0078	7.0421	0.6192	0.3854	0.6189	0.0	0.6186	0.6189
No log	2	588	16.3539	0.0156	7.6380	0.3897	0.3032	0.3894	0.0	0.3900	0.3899
No log	3	882	2.8784	0.0312	9.1390	0.6210	0.3854	0.6210	0.0	0.6207	0.6210
0.3917	4	1176	2.9268	0.0625	11.3439	0.3787	0.2747	0.3787	0.0	0.3793	0.3790
0.2226	5	1470	2.7311	0.125	14.2140	0.5362	0.5197	0.5357	0.0	0.5362	0.5365
0.416	6	1764	2.6649	0.25	20.0703	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
2.679	7	2058	2.6945	0.5	31.9367	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
2.684	8.0	2352	2.5542	1.0	58.6421	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
2.0627	9.0	2646	2.4724	1.0	57.9752	0.6694	0.6175	0.6697	0.0	0.6694	0.6697
1.1534	10.0	2940	3.6267	1.0	57.8401	0.6661	0.6170	0.6661	0.0	0.6664	0.6661
0.8405	11.0	3234	3.8913	1.0	58.8240	0.6581	0.6069	0.6581	0.0	0.6581	0.6581
0.5462	12.0	3528	3.7149	1.0	57.2843	0.6403	0.6192	0.6403	0.0	0.6400	0.6406
0.4319	13.0	3822	7.9243	1.0	57.8806	0.6636	0.6234	0.6636	0.0	0.6633	0.6636

Framework versions

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