ghc-google-t5-v1_1-large-intra_model-dataset-frequency-model_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
6.1892	1.0	345	6.6229
5.2951	2.0	690	5.5307
0.2702	3.0	1035	0.2511
0.2605	4.0	1380	0.2295
0.2635	5.0	1725	0.2378
0.2405	6.0	2070	0.2250
0.2605	7.0	2415	0.2226
0.2235	8.0	2760	0.2237
0.2303	9.0	3105	0.2199
0.2378	10.0	3450	0.2214
0.24	11.0	3795	0.2169
0.2236	12.0	4140	0.2183
0.2079	13.0	4485	0.2184
0.2594	14.0	4830	0.2159
0.2303	15.0	5175	0.2170
0.2238	16.0	5520	0.2146
0.2071	17.0	5865	0.2161
0.2129	18.0	6210	0.2130
0.2297	19.0	6555	0.2133
0.2434	20.0	6900	0.2158
0.2158	21.0	7245	0.2147
0.2222	22.0	7590	0.2166
0.2388	23.0	7935	0.2127
0.2132	24.0	8280	0.2123
0.2269	25.0	8625	0.2136
0.2237	26.0	8970	0.2142
0.2064	27.0	9315	0.2135
0.2329	28.0	9660	0.2140
0.2319	29.0	10005	0.2140

Framework versions

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