dialochess-v4

This model is a fine-tuned version of microsoft/DialoGPT-small 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: 5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
num_epochs: 6
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.3141	0.1616	200	1.1921	0.0002
1.194	0.3231	400	1.0974	0.0003
1.118	0.4847	600	1.0425	0.0
1.0767	0.6462	800	1.0071	0.0
1.0414	0.8078	1000	0.9825	0.0005
1.0158	0.9693	1200	0.9601	0.0002
1.0035	1.1309	1400	0.9427	0.0001
0.9715	1.2924	1600	0.9300	0.0002
0.9745	1.4540	1800	0.9193	0.0002
0.9447	1.6155	2000	0.9063	0.0002
0.9573	1.7771	2200	0.8980	0.0005
0.9386	1.9386	2400	0.8893	0.0003
0.9204	2.1002	2600	0.8786	0.0003
0.9128	2.2617	2800	0.8732	0.0003
0.9079	2.4233	3000	0.8670	0.0002
0.9073	2.5848	3200	0.8603	0.0002
0.8938	2.7464	3400	0.8532	0.0004
0.8899	2.9079	3600	0.8501	0.0002
0.8834	3.0695	3800	0.8426	0.0002
0.8693	3.2310	4000	0.8416	0.0003
0.8808	3.3926	4200	0.8335	0.0002
0.872	3.5541	4400	0.8297	0.0003
0.8689	3.7157	4600	0.8296	0.0003
0.8607	3.8772	4800	0.8237	0.0002
0.8516	4.0388	5000	0.8246	0.0004
0.8652	4.2003	5200	0.8210	0.0004
0.8522	4.3619	5400	0.8192	0.0003
0.8466	4.5234	5600	0.8181	0.0002
0.8525	4.6850	5800	0.8163	0.0004
0.8485	4.8465	6000	0.8163	0.0004
0.8444	5.0081	6200	0.8144	0.0003
0.8512	5.1696	6400	0.8141	0.0004
0.8405	5.3312	6600	0.8135	0.0004
0.8337	5.4927	6800	0.8124	0.0004
0.8601	5.6543	7000	0.8125	0.0004
0.8506	5.8158	7200	0.8124	0.0004
0.8562	5.9774	7400	0.8124	0.0004