SBIC-google-t5-v1_1-large-intra_model-dataset-frequency-human_annots_str

This model is a fine-tuned version of google/t5-v1_1-large on the None dataset. It achieves the following results on the evaluation set:

• Loss: nan

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: 0.0001
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 200

Training results

Training Loss	Epoch	Step	Validation Loss
7.5892	1.0	392	8.1616
0.6051	2.0	784	0.4203
0.4096	3.0	1176	0.3717
0.4094	4.0	1568	0.3578
0.3419	5.0	1960	0.3266
0.3587	6.0	2352	0.3206
0.3431	7.0	2744	0.3057
0.355	8.0	3136	0.3103
0.3327	9.0	3528	0.3023
0.3089	10.0	3920	0.2948
0.2803	11.0	4312	0.3010
0.3204	12.0	4704	0.2951
0.3148	13.0	5096	0.2864
0.2896	14.0	5488	0.2830
0.3081	15.0	5880	0.2825
0.3012	16.0	6272	0.2808
0.2788	17.0	6664	0.2814
0.288	18.0	7056	0.2770
0.2648	19.0	7448	0.2697
0.3098	20.0	7840	0.2662
0.2592	21.0	8232	0.2651
0.2394	22.0	8624	0.2675
0.2716	23.0	9016	0.2617
0.2684	24.0	9408	0.2638
0.2729	25.0	9800	0.2627
0.2896	26.0	10192	0.2625
0.2652	27.0	10584	0.2625
0.2611	28.0	10976	0.2625

Framework versions

• Transformers 4.34.0
• Pytorch 2.1.0+cu121
• Datasets 2.14.5
• Tokenizers 0.14.1