twitter-roberta-base-CoNLL / trainer_state.json
emilys's picture
End of training
3158b6c
raw
history blame
8.44 kB
{
"best_metric": 0.6566383257030739,
"best_model_checkpoint": "twitter-roberta-base-CoNLL/checkpoint-500",
"epoch": 10.0,
"global_step": 540,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.46,
"eval_accuracy": 0.9230280302548782,
"eval_f1": 0.03744493392070484,
"eval_loss": 0.28825512528419495,
"eval_precision": 0.2361111111111111,
"eval_recall": 0.02033492822966507,
"eval_runtime": 1.8273,
"eval_samples_per_second": 552.196,
"eval_steps_per_second": 0.547,
"step": 25
},
{
"epoch": 0.93,
"eval_accuracy": 0.9474988876882985,
"eval_f1": 0.5355029585798816,
"eval_loss": 0.20930655300617218,
"eval_precision": 0.7015503875968992,
"eval_recall": 0.43301435406698563,
"eval_runtime": 1.5316,
"eval_samples_per_second": 658.776,
"eval_steps_per_second": 0.653,
"step": 50
},
{
"epoch": 1.39,
"eval_accuracy": 0.9579228373482489,
"eval_f1": 0.6288323548597522,
"eval_loss": 0.1807074397802353,
"eval_precision": 0.6915351506456241,
"eval_recall": 0.5765550239234449,
"eval_runtime": 1.5064,
"eval_samples_per_second": 669.792,
"eval_steps_per_second": 0.664,
"step": 75
},
{
"epoch": 1.85,
"eval_accuracy": 0.9608466281065277,
"eval_f1": 0.6203411244472521,
"eval_loss": 0.1702219694852829,
"eval_precision": 0.6572958500669344,
"eval_recall": 0.5873205741626795,
"eval_runtime": 1.5233,
"eval_samples_per_second": 662.362,
"eval_steps_per_second": 0.656,
"step": 100
},
{
"epoch": 2.31,
"eval_accuracy": 0.9616093561304265,
"eval_f1": 0.6293800539083557,
"eval_loss": 0.1766974776983261,
"eval_precision": 0.720679012345679,
"eval_recall": 0.5586124401913876,
"eval_runtime": 1.5236,
"eval_samples_per_second": 662.237,
"eval_steps_per_second": 0.656,
"step": 125
},
{
"epoch": 2.78,
"eval_accuracy": 0.9617364774677429,
"eval_f1": 0.6370860927152318,
"eval_loss": 0.17372390627861023,
"eval_precision": 0.7136498516320475,
"eval_recall": 0.5753588516746412,
"eval_runtime": 1.5265,
"eval_samples_per_second": 660.978,
"eval_steps_per_second": 0.655,
"step": 150
},
{
"epoch": 3.24,
"eval_accuracy": 0.9635161761901735,
"eval_f1": 0.6610279765777489,
"eval_loss": 0.1732863336801529,
"eval_precision": 0.724679029957204,
"eval_recall": 0.6076555023923444,
"eval_runtime": 1.6272,
"eval_samples_per_second": 620.089,
"eval_steps_per_second": 0.615,
"step": 175
},
{
"epoch": 3.7,
"eval_accuracy": 0.9644695862200471,
"eval_f1": 0.6645728643216081,
"eval_loss": 0.16830594837665558,
"eval_precision": 0.6997354497354498,
"eval_recall": 0.6327751196172249,
"eval_runtime": 1.5645,
"eval_samples_per_second": 644.943,
"eval_steps_per_second": 0.639,
"step": 200
},
{
"epoch": 4.17,
"eval_accuracy": 0.9647873895633382,
"eval_f1": 0.6692160611854684,
"eval_loss": 0.1790447235107422,
"eval_precision": 0.7162346521145976,
"eval_recall": 0.6279904306220095,
"eval_runtime": 1.5303,
"eval_samples_per_second": 659.327,
"eval_steps_per_second": 0.653,
"step": 225
},
{
"epoch": 4.63,
"eval_accuracy": 0.9645331468887053,
"eval_f1": 0.6596858638743455,
"eval_loss": 0.1847098022699356,
"eval_precision": 0.7283236994219653,
"eval_recall": 0.6028708133971292,
"eval_runtime": 1.5507,
"eval_samples_per_second": 650.675,
"eval_steps_per_second": 0.645,
"step": 250
},
{
"epoch": 5.09,
"eval_accuracy": 0.9638339795334647,
"eval_f1": 0.6632057105775471,
"eval_loss": 0.1948511302471161,
"eval_precision": 0.724822695035461,
"eval_recall": 0.611244019138756,
"eval_runtime": 1.7607,
"eval_samples_per_second": 573.054,
"eval_steps_per_second": 0.568,
"step": 275
},
{
"epoch": 5.56,
"eval_accuracy": 0.9647873895633382,
"eval_f1": 0.6649649010848755,
"eval_loss": 0.18528707325458527,
"eval_precision": 0.7127222982216143,
"eval_recall": 0.6232057416267942,
"eval_runtime": 1.5232,
"eval_samples_per_second": 662.408,
"eval_steps_per_second": 0.656,
"step": 300
},
{
"epoch": 6.02,
"eval_accuracy": 0.9644695862200471,
"eval_f1": 0.669172932330827,
"eval_loss": 0.18068380653858185,
"eval_precision": 0.7026315789473684,
"eval_recall": 0.638755980861244,
"eval_runtime": 1.5586,
"eval_samples_per_second": 647.372,
"eval_steps_per_second": 0.642,
"step": 325
},
{
"epoch": 6.48,
"eval_accuracy": 0.9641517828767558,
"eval_f1": 0.664951768488746,
"eval_loss": 0.20004822313785553,
"eval_precision": 0.7190542420027817,
"eval_recall": 0.618421052631579,
"eval_runtime": 1.5707,
"eval_samples_per_second": 642.403,
"eval_steps_per_second": 0.637,
"step": 350
},
{
"epoch": 6.94,
"eval_accuracy": 0.9638339795334647,
"eval_f1": 0.6614987080103358,
"eval_loss": 0.19970329105854034,
"eval_precision": 0.7191011235955056,
"eval_recall": 0.6124401913875598,
"eval_runtime": 1.5546,
"eval_samples_per_second": 649.03,
"eval_steps_per_second": 0.643,
"step": 375
},
{
"epoch": 7.41,
"eval_accuracy": 0.9640246615394394,
"eval_f1": 0.663659793814433,
"eval_loss": 0.2035072147846222,
"eval_precision": 0.7192737430167597,
"eval_recall": 0.6160287081339713,
"eval_runtime": 1.5893,
"eval_samples_per_second": 634.88,
"eval_steps_per_second": 0.629,
"step": 400
},
{
"epoch": 7.87,
"eval_accuracy": 0.9643424648827306,
"eval_f1": 0.6557169930511686,
"eval_loss": 0.19765512645244598,
"eval_precision": 0.6947791164658634,
"eval_recall": 0.6208133971291866,
"eval_runtime": 1.57,
"eval_samples_per_second": 642.691,
"eval_steps_per_second": 0.637,
"step": 425
},
{
"epoch": 8.33,
"eval_accuracy": 0.9645331468887053,
"eval_f1": 0.6683706070287541,
"eval_loss": 0.20478704571723938,
"eval_precision": 0.7174211248285323,
"eval_recall": 0.6255980861244019,
"eval_runtime": 1.58,
"eval_samples_per_second": 638.623,
"eval_steps_per_second": 0.633,
"step": 450
},
{
"epoch": 8.8,
"eval_accuracy": 0.964215343545414,
"eval_f1": 0.6610608020698577,
"eval_loss": 0.2073480784893036,
"eval_precision": 0.719718309859155,
"eval_recall": 0.611244019138756,
"eval_runtime": 1.6091,
"eval_samples_per_second": 627.07,
"eval_steps_per_second": 0.621,
"step": 475
},
{
"epoch": 9.26,
"learning_rate": 3.7037037037037037e-06,
"loss": 0.07,
"step": 500
},
{
"epoch": 9.26,
"eval_accuracy": 0.9638339795334647,
"eval_f1": 0.6566383257030739,
"eval_loss": 0.21393825113773346,
"eval_precision": 0.7243867243867244,
"eval_recall": 0.6004784688995215,
"eval_runtime": 1.5553,
"eval_samples_per_second": 648.763,
"eval_steps_per_second": 0.643,
"step": 500
},
{
"epoch": 9.72,
"eval_accuracy": 0.96472382889468,
"eval_f1": 0.663284717818643,
"eval_loss": 0.20485757291316986,
"eval_precision": 0.7058029689608637,
"eval_recall": 0.6255980861244019,
"eval_runtime": 1.544,
"eval_samples_per_second": 653.493,
"eval_steps_per_second": 0.648,
"step": 525
},
{
"epoch": 10.0,
"step": 540,
"total_flos": 1009327449452316.0,
"train_loss": 0.06530485324285648,
"train_runtime": 166.7998,
"train_samples_per_second": 203.477,
"train_steps_per_second": 3.237
}
],
"max_steps": 540,
"num_train_epochs": 10,
"total_flos": 1009327449452316.0,
"trial_name": null,
"trial_params": null
}