README.md

metadata

library_name: transformers
license: mit
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - rouge
model-index:
  - name: bbfc8e75dac0d6ea1ca69ac37ff5beaa
    results: []

bbfc8e75dac0d6ea1ca69ac37ff5beaa

This model is a fine-tuned version of deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B on the nyu-mll/glue dataset. It achieves the following results on the evaluation set:

• Loss: 5.0891
• Data Size: 1.0
• Epoch Runtime: 33.8007
• Accuracy: 0.8149
• F1 Macro: 0.7728
• Rouge1: 0.8149
• Rouge2: 0.0
• Rougel: 0.8149
• Rougelsum: 0.8154

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	7.0905	0	4.4920	0.3544	0.2989	0.3538	0.0	0.3538	0.3544
No log	1	114	7.6449	0.0078	4.3656	0.6639	0.4121	0.6645	0.0	0.6639	0.6639
No log	2	228	3.1042	0.0156	7.0459	0.5731	0.5525	0.5725	0.0	0.5728	0.5731
No log	3	342	2.7720	0.0312	10.1902	0.6769	0.5282	0.6769	0.0	0.6763	0.6763
0.1341	4	456	2.3659	0.0625	12.0846	0.6881	0.6353	0.6881	0.0	0.6881	0.6881
0.1341	5	570	2.1620	0.125	14.6870	0.7488	0.6646	0.7482	0.0	0.7488	0.7494
0.1341	6	684	1.7724	0.25	19.3808	0.8013	0.7475	0.8019	0.0	0.8019	0.8013
0.4926	7	798	1.5741	0.5	21.4771	0.8261	0.8001	0.8255	0.0	0.8261	0.8261
0.9023	8.0	912	1.7902	1.0	32.0793	0.8090	0.7649	0.8093	0.0	0.8090	0.8096
0.5336	9.0	1026	3.7415	1.0	32.3208	0.7995	0.7667	0.7989	0.0	0.8001	0.7995
0.4963	10.0	1140	4.2174	1.0	31.7095	0.8160	0.7719	0.8160	0.0	0.8166	0.8166
0.1717	11.0	1254	5.0891	1.0	33.8007	0.8149	0.7728	0.8149	0.0	0.8149	0.8154

Framework versions

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