You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

politicalbias-2label-c09_lib01-model

This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 8
eval_batch_size: 16
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 10
num_epochs: 30
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
3.6674	1.0	29	2.8958
2.5275	2.0	58	2.4339
2.0891	3.0	87	2.1958
1.8554	4.0	116	2.0607
1.6775	5.0	145	1.9778
1.6552	6.0	174	1.8975
1.4718	7.0	203	1.8459
1.3608	8.0	232	1.8309
1.3041	9.0	261	1.8116
1.1661	10.0	290	1.8149
1.1402	11.0	319	1.8201
1.1035	12.0	348	1.7746
1.0536	13.0	377	1.7806
0.9668	14.0	406	1.7962
0.929	15.0	435	1.7799
0.9476	16.0	464	1.7816
0.9111	17.0	493	1.7952
0.8337	18.0	522	1.8019
0.8791	19.0	551	1.8276
0.8861	20.0	580	1.8185
0.7128	21.0	609	1.8327
0.7104	22.0	638	1.8420
0.8054	23.0	667	1.8565
0.7625	24.0	696	1.8557
0.7074	25.0	725	1.8533
0.7603	26.0	754	1.8685
0.73	27.0	783	1.8639
0.6895	28.0	812	1.8629
0.7133	29.0	841	1.8625
0.7613	30.0	870	1.8627

Safetensors

Model size

0.1B params

Tensor type

F32

Base model

Finetuned

(2078)

this model