d83aaa5b9a19335e8c48f538131e6744

This model is a fine-tuned version of deepseek-ai/DeepSeek-R1-Distill-Qwen-7B on the nyu-mll/glue [wnli] dataset. It achieves the following results on the evaluation set:

• Loss: 3.2279
• Data Size: 1.0
• Epoch Runtime: 41.2389
• Accuracy: 0.3281
• F1 Macro: 0.3200
• Rouge1: 0.3281
• Rouge2: 0.0
• Rougel: 0.3281
• Rougelsum: 0.3281

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	19.2359	0	1.0677	0.4375	0.3043	0.4375	0.0	0.4375	0.4375
No log	1	19	53.5196	0.0078	1.8650	0.5625	0.36	0.5625	0.0	0.5625	0.5625
No log	2	38	7.8009	0.0156	13.1051	0.5625	0.36	0.5625	0.0	0.5625	0.5625
No log	3	57	50.2539	0.0312	22.4758	0.4375	0.3043	0.4375	0.0	0.4375	0.4375
No log	4	76	21.3439	0.0625	31.9284	0.4375	0.3043	0.4375	0.0	0.4375	0.4375
No log	5	95	10.0790	0.125	41.0658	0.5625	0.36	0.5625	0.0	0.5625	0.5625
1.9862	6	114	5.8955	0.25	48.4514	0.5469	0.3535	0.5469	0.0	0.5469	0.5469
1.9862	7	133	2.9724	0.5	59.5660	0.5469	0.3535	0.5469	0.0	0.5469	0.5469
2.5225	8.0	152	3.1456	1.0	78.5581	0.5625	0.36	0.5625	0.0	0.5625	0.5625
2.5225	9.0	171	2.8076	1.0	73.2145	0.4375	0.3263	0.4375	0.0	0.4375	0.4375
2.5225	10.0	190	2.8134	1.0	84.0226	0.5625	0.36	0.5625	0.0	0.5625	0.5625
2.9932	11.0	209	2.8068	1.0	89.4419	0.5625	0.36	0.5625	0.0	0.5625	0.5625
2.9932	12.0	228	3.1002	1.0	75.1912	0.4375	0.3043	0.4375	0.0	0.4375	0.4375
2.9932	13.0	247	2.8943	1.0	24.3643	0.4375	0.3043	0.4375	0.0	0.4375	0.4375
2.981	14.0	266	3.0679	1.0	35.2033	0.5625	0.36	0.5625	0.0	0.5625	0.5625
2.981	15.0	285	3.2279	1.0	41.2389	0.3281	0.3200	0.3281	0.0	0.3281	0.3281

Framework versions

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