30ee322a0e99ffd4dc6e70c8e217affb

This model is a fine-tuned version of google-bert/bert-large-cased-whole-word-masking-finetuned-squad on the nyu-mll/glue [sst2] dataset. It achieves the following results on the evaluation set:

• Loss: 0.7060
• Data Size: 1.0
• Epoch Runtime: 194.1826
• Accuracy: 0.5093
• F1 Macro: 0.3374
• Rouge1: 0.5093
• Rouge2: 0.0
• Rougel: 0.5093
• Rougelsum: 0.5081

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	0.8228	0	1.2522	0.4907	0.3292	0.4907	0.0	0.4907	0.4919
No log	1	2104	0.7346	0.0078	2.9680	0.7130	0.6942	0.7130	0.0	0.7130	0.7141
No log	2	4208	0.3238	0.0156	4.9893	0.8808	0.8805	0.8819	0.0	0.8819	0.8808
0.0096	3	6312	0.2622	0.0312	8.5079	0.8866	0.8864	0.8866	0.0	0.8866	0.8866
0.3273	4	8416	0.2424	0.0625	14.9652	0.9086	0.9086	0.9086	0.0	0.9086	0.9086
0.2692	5	10520	0.3801	0.125	27.0948	0.8519	0.8491	0.8519	0.0	0.8519	0.8519
0.2656	6	12624	0.2490	0.25	52.2349	0.9028	0.9027	0.9028	0.0	0.9028	0.9028
0.2593	7	14728	0.3277	0.5	100.0042	0.8854	0.8849	0.8854	0.0	0.8854	0.8848
0.693	8.0	16832	0.7060	1.0	194.1826	0.5093	0.3374	0.5093	0.0	0.5093	0.5081

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu128
• Datasets 4.3.0
• Tokenizers 0.22.1