hos_sentiment_bert

This model is a fine-tuned version of google-bert/bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

Model description

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 3e-05
train_batch_size: 64
eval_batch_size: 64
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 40.0

Training Loss	Epoch	Step	Validation Loss	F1
No log	1.0	331	0.2183	0.9258
0.239	2.0	662	0.2168	0.9326
0.239	3.0	993	0.2527	0.9282
0.1255	4.0	1324	0.2896	0.9288
0.0662	5.0	1655	0.3389	0.9266
0.0662	6.0	1986	0.3793	0.9294
0.0453	7.0	2317	0.4110	0.9252
0.0257	8.0	2648	0.4656	0.9205
0.0257	9.0	2979	0.4953	0.9263
0.0196	10.0	3310	0.5412	0.9265
0.0125	11.0	3641	0.5528	0.9245
0.0125	12.0	3972	0.5527	0.9262
0.0141	13.0	4303	0.5683	0.9276
0.0097	14.0	4634	0.5835	0.9239
0.0097	15.0	4965	0.5905	0.9280
0.0107	16.0	5296	0.5799	0.9298
0.009	17.0	5627	0.6127	0.9266
0.009	18.0	5958	0.5911	0.9284
0.0084	19.0	6289	0.5900	0.9303
0.008	20.0	6620	0.5923	0.9283
0.008	21.0	6951	0.6186	0.9305
0.0068	22.0	7282	0.6076	0.9292
0.0064	23.0	7613	0.5782	0.9303
0.0064	24.0	7944	0.6077	0.9320
0.0048	25.0	8275	0.6446	0.9282
0.0046	26.0	8606	0.6417	0.9315
0.0046	27.0	8937	0.6656	0.9283
0.0053	28.0	9268	0.6541	0.9288
0.0043	29.0	9599	0.6703	0.9277
0.0043	30.0	9930	0.6871	0.9252
0.0041	31.0	10261	0.6735	0.9286
0.0034	32.0	10592	0.6651	0.9306
0.0034	33.0	10923	0.6799	0.9305
0.0032	34.0	11254	0.6753	0.9297
0.0031	35.0	11585	0.6855	0.9310
0.0031	36.0	11916	0.6885	0.9306
0.003	37.0	12247	0.6960	0.9293
0.0026	38.0	12578	0.6950	0.9292
0.0026	39.0	12909	0.6964	0.9297
0.0033	40.0	13240	0.6954	0.9290