lora-roberta-large-0927 / trainer_state.json
anniew666's picture
End of training
43a8173
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 25.0,
"eval_steps": 2092,
"global_step": 41825,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.25,
"learning_rate": 0.0001988527724665392,
"loss": 1.1848,
"step": 419
},
{
"epoch": 0.5,
"learning_rate": 0.00039913957934990444,
"loss": 0.8965,
"step": 838
},
{
"epoch": 0.75,
"learning_rate": 0.0005994263862332697,
"loss": 0.8659,
"step": 1257
},
{
"epoch": 1.0,
"learning_rate": 0.0007992351816443595,
"loss": 0.8381,
"step": 1676
},
{
"epoch": 1.25,
"eval_accuracy": 0.4471636546184739,
"eval_b_acc": 0.14285714285714285,
"eval_f1": 0.2763410114310333,
"eval_f1_anger": 0.0,
"eval_f1_disgust": 0.0,
"eval_f1_fear": 0.0,
"eval_f1_joy": 0.0,
"eval_f1_neutral": 0.6179862978059145,
"eval_f1_sadness": 0.0,
"eval_f1_surprise": 0.0,
"eval_loss": 1.541502594947815,
"eval_micro_f1": 0.4471636546184739,
"eval_prec": 0.1999553340117498,
"eval_prec_anger": 0.0,
"eval_prec_disgust": 0.0,
"eval_prec_fear": 0.0,
"eval_prec_joy": 0.0,
"eval_prec_neutral": 0.4471636546184739,
"eval_prec_sadness": 0.0,
"eval_prec_surprise": 0.0,
"eval_recall": 0.4471636546184739,
"eval_recall_anger": 0.0,
"eval_recall_disgust": 0.0,
"eval_recall_fear": 0.0,
"eval_recall_joy": 0.0,
"eval_recall_neutral": 1.0,
"eval_recall_sadness": 0.0,
"eval_recall_surprise": 0.0,
"eval_runtime": 53.3613,
"eval_samples_per_second": 447.965,
"eval_steps_per_second": 13.999,
"step": 2092
},
{
"epoch": 1.25,
"learning_rate": 0.0009995219885277247,
"loss": 0.9804,
"step": 2095
},
{
"epoch": 1.5,
"learning_rate": 0.000989479777514912,
"loss": 1.4905,
"step": 2514
},
{
"epoch": 1.75,
"learning_rate": 0.0009789343870334484,
"loss": 1.4837,
"step": 2933
},
{
"epoch": 2.0,
"learning_rate": 0.0009683889965519845,
"loss": 1.4851,
"step": 3352
},
{
"epoch": 2.25,
"learning_rate": 0.0009578436060705208,
"loss": 1.4866,
"step": 3771
},
{
"epoch": 2.5,
"eval_accuracy": 0.4471636546184739,
"eval_b_acc": 0.14285714285714285,
"eval_f1": 0.2763410114310333,
"eval_f1_anger": 0.0,
"eval_f1_disgust": 0.0,
"eval_f1_fear": 0.0,
"eval_f1_joy": 0.0,
"eval_f1_neutral": 0.6179862978059145,
"eval_f1_sadness": 0.0,
"eval_f1_surprise": 0.0,
"eval_loss": 1.5563576221466064,
"eval_micro_f1": 0.4471636546184739,
"eval_prec": 0.1999553340117498,
"eval_prec_anger": 0.0,
"eval_prec_disgust": 0.0,
"eval_prec_fear": 0.0,
"eval_prec_joy": 0.0,
"eval_prec_neutral": 0.4471636546184739,
"eval_prec_sadness": 0.0,
"eval_prec_surprise": 0.0,
"eval_recall": 0.4471636546184739,
"eval_recall_anger": 0.0,
"eval_recall_disgust": 0.0,
"eval_recall_fear": 0.0,
"eval_recall_joy": 0.0,
"eval_recall_neutral": 1.0,
"eval_recall_sadness": 0.0,
"eval_recall_surprise": 0.0,
"eval_runtime": 52.7331,
"eval_samples_per_second": 453.301,
"eval_steps_per_second": 14.166,
"step": 4184
},
{
"epoch": 2.5,
"learning_rate": 0.000947298215589057,
"loss": 1.4817,
"step": 4190
},
{
"epoch": 2.75,
"learning_rate": 0.0009367528251075931,
"loss": 1.4846,
"step": 4609
},
{
"epoch": 3.01,
"learning_rate": 0.0009262074346261294,
"loss": 1.4814,
"step": 5028
},
{
"epoch": 3.26,
"learning_rate": 0.0009156872121410415,
"loss": 1.4818,
"step": 5447
},
{
"epoch": 3.51,
"learning_rate": 0.0009051418216595777,
"loss": 1.4862,
"step": 5866
},
{
"epoch": 3.75,
"eval_accuracy": 0.4471636546184739,
"eval_b_acc": 0.14285714285714285,
"eval_f1": 0.2763410114310333,
"eval_f1_anger": 0.0,
"eval_f1_disgust": 0.0,
"eval_f1_fear": 0.0,
"eval_f1_joy": 0.0,
"eval_f1_neutral": 0.6179862978059145,
"eval_f1_sadness": 0.0,
"eval_f1_surprise": 0.0,
"eval_loss": 1.5699833631515503,
"eval_micro_f1": 0.4471636546184739,
"eval_prec": 0.1999553340117498,
"eval_prec_anger": 0.0,
"eval_prec_disgust": 0.0,
"eval_prec_fear": 0.0,
"eval_prec_joy": 0.0,
"eval_prec_neutral": 0.4471636546184739,
"eval_prec_sadness": 0.0,
"eval_prec_surprise": 0.0,
"eval_recall": 0.4471636546184739,
"eval_recall_anger": 0.0,
"eval_recall_disgust": 0.0,
"eval_recall_fear": 0.0,
"eval_recall_joy": 0.0,
"eval_recall_neutral": 1.0,
"eval_recall_sadness": 0.0,
"eval_recall_surprise": 0.0,
"eval_runtime": 52.9507,
"eval_samples_per_second": 451.439,
"eval_steps_per_second": 14.107,
"step": 6276
},
{
"epoch": 3.76,
"learning_rate": 0.0008945964311781139,
"loss": 1.482,
"step": 6285
},
{
"epoch": 4.01,
"learning_rate": 0.0008840510406966502,
"loss": 1.4793,
"step": 6704
},
{
"epoch": 4.26,
"learning_rate": 0.0008735056502151864,
"loss": 1.4753,
"step": 7123
},
{
"epoch": 4.51,
"learning_rate": 0.0008629854277300984,
"loss": 1.4905,
"step": 7542
},
{
"epoch": 4.76,
"learning_rate": 0.0008524400372486346,
"loss": 1.4762,
"step": 7961
},
{
"epoch": 5.0,
"eval_accuracy": 0.4471636546184739,
"eval_b_acc": 0.14285714285714285,
"eval_f1": 0.2763410114310333,
"eval_f1_anger": 0.0,
"eval_f1_disgust": 0.0,
"eval_f1_fear": 0.0,
"eval_f1_joy": 0.0,
"eval_f1_neutral": 0.6179862978059145,
"eval_f1_sadness": 0.0,
"eval_f1_surprise": 0.0,
"eval_loss": 1.5391422510147095,
"eval_micro_f1": 0.4471636546184739,
"eval_prec": 0.1999553340117498,
"eval_prec_anger": 0.0,
"eval_prec_disgust": 0.0,
"eval_prec_fear": 0.0,
"eval_prec_joy": 0.0,
"eval_prec_neutral": 0.4471636546184739,
"eval_prec_sadness": 0.0,
"eval_prec_surprise": 0.0,
"eval_recall": 0.4471636546184739,
"eval_recall_anger": 0.0,
"eval_recall_disgust": 0.0,
"eval_recall_fear": 0.0,
"eval_recall_joy": 0.0,
"eval_recall_neutral": 1.0,
"eval_recall_sadness": 0.0,
"eval_recall_surprise": 0.0,
"eval_runtime": 52.76,
"eval_samples_per_second": 453.07,
"eval_steps_per_second": 14.158,
"step": 8368
},
{
"epoch": 5.01,
"learning_rate": 0.0008418946467671709,
"loss": 1.4794,
"step": 8380
},
{
"epoch": 5.26,
"learning_rate": 0.0008313995922784587,
"loss": 1.48,
"step": 8799
},
{
"epoch": 5.51,
"learning_rate": 0.0008209045377897466,
"loss": 1.4795,
"step": 9218
},
{
"epoch": 5.76,
"learning_rate": 0.0008104094833010344,
"loss": 1.4815,
"step": 9637
},
{
"epoch": 6.01,
"learning_rate": 0.0007998640928195707,
"loss": 1.4765,
"step": 10056
},
{
"epoch": 6.25,
"eval_accuracy": 0.4471636546184739,
"eval_b_acc": 0.14285714285714285,
"eval_f1": 0.2763410114310333,
"eval_f1_anger": 0.0,
"eval_f1_disgust": 0.0,
"eval_f1_fear": 0.0,
"eval_f1_joy": 0.0,
"eval_f1_neutral": 0.6179862978059145,
"eval_f1_sadness": 0.0,
"eval_f1_surprise": 0.0,
"eval_loss": 1.5565674304962158,
"eval_micro_f1": 0.4471636546184739,
"eval_prec": 0.1999553340117498,
"eval_prec_anger": 0.0,
"eval_prec_disgust": 0.0,
"eval_prec_fear": 0.0,
"eval_prec_joy": 0.0,
"eval_prec_neutral": 0.4471636546184739,
"eval_prec_sadness": 0.0,
"eval_prec_surprise": 0.0,
"eval_recall": 0.4471636546184739,
"eval_recall_anger": 0.0,
"eval_recall_disgust": 0.0,
"eval_recall_fear": 0.0,
"eval_recall_joy": 0.0,
"eval_recall_neutral": 1.0,
"eval_recall_sadness": 0.0,
"eval_recall_surprise": 0.0,
"eval_runtime": 52.8225,
"eval_samples_per_second": 452.534,
"eval_steps_per_second": 14.142,
"step": 10460
},
{
"epoch": 6.26,
"learning_rate": 0.0007893187023381068,
"loss": 1.4785,
"step": 10475
},
{
"epoch": 6.51,
"learning_rate": 0.0007787733118566431,
"loss": 1.4841,
"step": 10894
},
{
"epoch": 6.76,
"learning_rate": 0.0007682279213751794,
"loss": 1.4815,
"step": 11313
},
{
"epoch": 7.01,
"learning_rate": 0.0007577328668864671,
"loss": 1.4808,
"step": 11732
},
{
"epoch": 7.26,
"learning_rate": 0.0007471874764050034,
"loss": 1.4848,
"step": 12151
},
{
"epoch": 7.5,
"eval_accuracy": 0.4471636546184739,
"eval_b_acc": 0.14285714285714285,
"eval_f1": 0.2763410114310333,
"eval_f1_anger": 0.0,
"eval_f1_disgust": 0.0,
"eval_f1_fear": 0.0,
"eval_f1_joy": 0.0,
"eval_f1_neutral": 0.6179862978059145,
"eval_f1_sadness": 0.0,
"eval_f1_surprise": 0.0,
"eval_loss": 1.5410676002502441,
"eval_micro_f1": 0.4471636546184739,
"eval_prec": 0.1999553340117498,
"eval_prec_anger": 0.0,
"eval_prec_disgust": 0.0,
"eval_prec_fear": 0.0,
"eval_prec_joy": 0.0,
"eval_prec_neutral": 0.4471636546184739,
"eval_prec_sadness": 0.0,
"eval_prec_surprise": 0.0,
"eval_recall": 0.4471636546184739,
"eval_recall_anger": 0.0,
"eval_recall_disgust": 0.0,
"eval_recall_fear": 0.0,
"eval_recall_joy": 0.0,
"eval_recall_neutral": 1.0,
"eval_recall_sadness": 0.0,
"eval_recall_surprise": 0.0,
"eval_runtime": 53.1004,
"eval_samples_per_second": 450.166,
"eval_steps_per_second": 14.068,
"step": 12552
},
{
"epoch": 7.51,
"learning_rate": 0.0007366420859235397,
"loss": 1.4779,
"step": 12570
},
{
"epoch": 7.76,
"learning_rate": 0.0007260966954420759,
"loss": 1.4833,
"step": 12989
},
{
"epoch": 8.01,
"learning_rate": 0.0007155764729569879,
"loss": 1.4759,
"step": 13408
},
{
"epoch": 8.26,
"learning_rate": 0.0007050310824755242,
"loss": 1.4763,
"step": 13827
},
{
"epoch": 8.52,
"learning_rate": 0.0006945611959831878,
"loss": 1.4782,
"step": 14246
},
{
"epoch": 8.75,
"eval_accuracy": 0.4471636546184739,
"eval_b_acc": 0.14285714285714285,
"eval_f1": 0.2763410114310333,
"eval_f1_anger": 0.0,
"eval_f1_disgust": 0.0,
"eval_f1_fear": 0.0,
"eval_f1_joy": 0.0,
"eval_f1_neutral": 0.6179862978059145,
"eval_f1_sadness": 0.0,
"eval_f1_surprise": 0.0,
"eval_loss": 1.5548430681228638,
"eval_micro_f1": 0.4471636546184739,
"eval_prec": 0.1999553340117498,
"eval_prec_anger": 0.0,
"eval_prec_disgust": 0.0,
"eval_prec_fear": 0.0,
"eval_prec_joy": 0.0,
"eval_prec_neutral": 0.4471636546184739,
"eval_prec_sadness": 0.0,
"eval_prec_surprise": 0.0,
"eval_recall": 0.4471636546184739,
"eval_recall_anger": 0.0,
"eval_recall_disgust": 0.0,
"eval_recall_fear": 0.0,
"eval_recall_joy": 0.0,
"eval_recall_neutral": 1.0,
"eval_recall_sadness": 0.0,
"eval_recall_surprise": 0.0,
"eval_runtime": 52.8918,
"eval_samples_per_second": 451.941,
"eval_steps_per_second": 14.123,
"step": 14644
},
{
"epoch": 8.77,
"learning_rate": 0.0006840158055017241,
"loss": 1.482,
"step": 14665
},
{
"epoch": 9.02,
"learning_rate": 0.0006734704150202603,
"loss": 1.4789,
"step": 15084
},
{
"epoch": 9.27,
"learning_rate": 0.0006629753605315481,
"loss": 1.4715,
"step": 15503
},
{
"epoch": 9.52,
"learning_rate": 0.0006524299700500843,
"loss": 1.4967,
"step": 15922
},
{
"epoch": 9.77,
"learning_rate": 0.0006418845795686205,
"loss": 1.4943,
"step": 16341
},
{
"epoch": 10.0,
"eval_accuracy": 0.4471636546184739,
"eval_b_acc": 0.14285714285714285,
"eval_f1": 0.2763410114310333,
"eval_f1_anger": 0.0,
"eval_f1_disgust": 0.0,
"eval_f1_fear": 0.0,
"eval_f1_joy": 0.0,
"eval_f1_neutral": 0.6179862978059145,
"eval_f1_sadness": 0.0,
"eval_f1_surprise": 0.0,
"eval_loss": 1.6114758253097534,
"eval_micro_f1": 0.4471636546184739,
"eval_prec": 0.1999553340117498,
"eval_prec_anger": 0.0,
"eval_prec_disgust": 0.0,
"eval_prec_fear": 0.0,
"eval_prec_joy": 0.0,
"eval_prec_neutral": 0.4471636546184739,
"eval_prec_sadness": 0.0,
"eval_prec_surprise": 0.0,
"eval_recall": 0.4471636546184739,
"eval_recall_anger": 0.0,
"eval_recall_disgust": 0.0,
"eval_recall_fear": 0.0,
"eval_recall_joy": 0.0,
"eval_recall_neutral": 1.0,
"eval_recall_sadness": 0.0,
"eval_recall_surprise": 0.0,
"eval_runtime": 53.2358,
"eval_samples_per_second": 449.021,
"eval_steps_per_second": 14.032,
"step": 16736
},
{
"epoch": 10.02,
"learning_rate": 0.0006313391890871568,
"loss": 1.4874,
"step": 16760
},
{
"epoch": 10.27,
"learning_rate": 0.000620793798605693,
"loss": 1.4877,
"step": 17179
},
{
"epoch": 10.52,
"learning_rate": 0.0006102484081242293,
"loss": 1.4833,
"step": 17598
},
{
"epoch": 10.77,
"learning_rate": 0.0005997281856391413,
"loss": 1.4796,
"step": 18017
},
{
"epoch": 11.02,
"learning_rate": 0.0005891827951576775,
"loss": 1.4801,
"step": 18436
},
{
"epoch": 11.25,
"eval_accuracy": 0.4471636546184739,
"eval_b_acc": 0.14285714285714285,
"eval_f1": 0.2763410114310333,
"eval_f1_anger": 0.0,
"eval_f1_disgust": 0.0,
"eval_f1_fear": 0.0,
"eval_f1_joy": 0.0,
"eval_f1_neutral": 0.6179862978059145,
"eval_f1_sadness": 0.0,
"eval_f1_surprise": 0.0,
"eval_loss": 1.5423938035964966,
"eval_micro_f1": 0.4471636546184739,
"eval_prec": 0.1999553340117498,
"eval_prec_anger": 0.0,
"eval_prec_disgust": 0.0,
"eval_prec_fear": 0.0,
"eval_prec_joy": 0.0,
"eval_prec_neutral": 0.4471636546184739,
"eval_prec_sadness": 0.0,
"eval_prec_surprise": 0.0,
"eval_recall": 0.4471636546184739,
"eval_recall_anger": 0.0,
"eval_recall_disgust": 0.0,
"eval_recall_fear": 0.0,
"eval_recall_joy": 0.0,
"eval_recall_neutral": 1.0,
"eval_recall_sadness": 0.0,
"eval_recall_surprise": 0.0,
"eval_runtime": 52.871,
"eval_samples_per_second": 452.119,
"eval_steps_per_second": 14.129,
"step": 18828
},
{
"epoch": 11.27,
"learning_rate": 0.0005786374046762138,
"loss": 1.4804,
"step": 18855
},
{
"epoch": 11.52,
"learning_rate": 0.0005680920141947499,
"loss": 1.4836,
"step": 19274
},
{
"epoch": 11.77,
"learning_rate": 0.0005575466237132862,
"loss": 1.4839,
"step": 19693
},
{
"epoch": 12.02,
"learning_rate": 0.0005470012332318224,
"loss": 1.4826,
"step": 20112
},
{
"epoch": 12.27,
"learning_rate": 0.0005365061787431102,
"loss": 1.4946,
"step": 20531
},
{
"epoch": 12.5,
"eval_accuracy": 0.4471636546184739,
"eval_b_acc": 0.14285714285714285,
"eval_f1": 0.2763410114310333,
"eval_f1_anger": 0.0,
"eval_f1_disgust": 0.0,
"eval_f1_fear": 0.0,
"eval_f1_joy": 0.0,
"eval_f1_neutral": 0.6179862978059145,
"eval_f1_sadness": 0.0,
"eval_f1_surprise": 0.0,
"eval_loss": 1.5636779069900513,
"eval_micro_f1": 0.4471636546184739,
"eval_prec": 0.1999553340117498,
"eval_prec_anger": 0.0,
"eval_prec_disgust": 0.0,
"eval_prec_fear": 0.0,
"eval_prec_joy": 0.0,
"eval_prec_neutral": 0.4471636546184739,
"eval_prec_sadness": 0.0,
"eval_prec_surprise": 0.0,
"eval_recall": 0.4471636546184739,
"eval_recall_anger": 0.0,
"eval_recall_disgust": 0.0,
"eval_recall_fear": 0.0,
"eval_recall_joy": 0.0,
"eval_recall_neutral": 1.0,
"eval_recall_sadness": 0.0,
"eval_recall_surprise": 0.0,
"eval_runtime": 52.887,
"eval_samples_per_second": 451.982,
"eval_steps_per_second": 14.124,
"step": 20920
},
{
"epoch": 12.52,
"learning_rate": 0.0005259859562580223,
"loss": 1.4926,
"step": 20950
},
{
"epoch": 12.77,
"learning_rate": 0.0005154405657765586,
"loss": 1.4868,
"step": 21369
},
{
"epoch": 13.02,
"learning_rate": 0.0005048951752950947,
"loss": 1.4776,
"step": 21788
},
{
"epoch": 13.27,
"learning_rate": 0.000494349784813631,
"loss": 1.4827,
"step": 22207
},
{
"epoch": 13.52,
"learning_rate": 0.00048380439433216724,
"loss": 1.4867,
"step": 22626
},
{
"epoch": 13.75,
"eval_accuracy": 0.4471636546184739,
"eval_b_acc": 0.14285714285714285,
"eval_f1": 0.2763410114310333,
"eval_f1_anger": 0.0,
"eval_f1_disgust": 0.0,
"eval_f1_fear": 0.0,
"eval_f1_joy": 0.0,
"eval_f1_neutral": 0.6179862978059145,
"eval_f1_sadness": 0.0,
"eval_f1_surprise": 0.0,
"eval_loss": 1.5492433309555054,
"eval_micro_f1": 0.4471636546184739,
"eval_prec": 0.1999553340117498,
"eval_prec_anger": 0.0,
"eval_prec_disgust": 0.0,
"eval_prec_fear": 0.0,
"eval_prec_joy": 0.0,
"eval_prec_neutral": 0.4471636546184739,
"eval_prec_sadness": 0.0,
"eval_prec_surprise": 0.0,
"eval_recall": 0.4471636546184739,
"eval_recall_anger": 0.0,
"eval_recall_disgust": 0.0,
"eval_recall_fear": 0.0,
"eval_recall_joy": 0.0,
"eval_recall_neutral": 1.0,
"eval_recall_sadness": 0.0,
"eval_recall_surprise": 0.0,
"eval_runtime": 53.2702,
"eval_samples_per_second": 448.731,
"eval_steps_per_second": 14.023,
"step": 23012
},
{
"epoch": 13.77,
"learning_rate": 0.00047325900385070346,
"loss": 1.4902,
"step": 23045
},
{
"epoch": 14.03,
"learning_rate": 0.0004627136133692397,
"loss": 1.4825,
"step": 23464
},
{
"epoch": 14.28,
"learning_rate": 0.0004521682228877759,
"loss": 1.4823,
"step": 23883
},
{
"epoch": 14.53,
"learning_rate": 0.00044162283240631214,
"loss": 1.4933,
"step": 24302
},
{
"epoch": 14.78,
"learning_rate": 0.0004311026099212242,
"loss": 1.4957,
"step": 24721
},
{
"epoch": 15.01,
"eval_accuracy": 0.4471636546184739,
"eval_b_acc": 0.14285714285714285,
"eval_f1": 0.2763410114310333,
"eval_f1_anger": 0.0,
"eval_f1_disgust": 0.0,
"eval_f1_fear": 0.0,
"eval_f1_joy": 0.0,
"eval_f1_neutral": 0.6179862978059145,
"eval_f1_sadness": 0.0,
"eval_f1_surprise": 0.0,
"eval_loss": 1.5811705589294434,
"eval_micro_f1": 0.4471636546184739,
"eval_prec": 0.1999553340117498,
"eval_prec_anger": 0.0,
"eval_prec_disgust": 0.0,
"eval_prec_fear": 0.0,
"eval_prec_joy": 0.0,
"eval_prec_neutral": 0.4471636546184739,
"eval_prec_sadness": 0.0,
"eval_prec_surprise": 0.0,
"eval_recall": 0.4471636546184739,
"eval_recall_anger": 0.0,
"eval_recall_disgust": 0.0,
"eval_recall_fear": 0.0,
"eval_recall_joy": 0.0,
"eval_recall_neutral": 1.0,
"eval_recall_sadness": 0.0,
"eval_recall_surprise": 0.0,
"eval_runtime": 52.7987,
"eval_samples_per_second": 452.739,
"eval_steps_per_second": 14.148,
"step": 25104
},
{
"epoch": 15.03,
"learning_rate": 0.00042055721943976037,
"loss": 1.4875,
"step": 25140
},
{
"epoch": 15.28,
"learning_rate": 0.00041001182895829665,
"loss": 1.4866,
"step": 25559
},
{
"epoch": 15.53,
"learning_rate": 0.00039946643847683287,
"loss": 1.4879,
"step": 25978
},
{
"epoch": 15.78,
"learning_rate": 0.0003889210479953691,
"loss": 1.4856,
"step": 26397
},
{
"epoch": 16.03,
"learning_rate": 0.00037840082551028115,
"loss": 1.4913,
"step": 26816
},
{
"epoch": 16.26,
"eval_accuracy": 0.4471636546184739,
"eval_b_acc": 0.14285714285714285,
"eval_f1": 0.2763410114310333,
"eval_f1_anger": 0.0,
"eval_f1_disgust": 0.0,
"eval_f1_fear": 0.0,
"eval_f1_joy": 0.0,
"eval_f1_neutral": 0.6179862978059145,
"eval_f1_sadness": 0.0,
"eval_f1_surprise": 0.0,
"eval_loss": 1.5424742698669434,
"eval_micro_f1": 0.4471636546184739,
"eval_prec": 0.1999553340117498,
"eval_prec_anger": 0.0,
"eval_prec_disgust": 0.0,
"eval_prec_fear": 0.0,
"eval_prec_joy": 0.0,
"eval_prec_neutral": 0.4471636546184739,
"eval_prec_sadness": 0.0,
"eval_prec_surprise": 0.0,
"eval_recall": 0.4471636546184739,
"eval_recall_anger": 0.0,
"eval_recall_disgust": 0.0,
"eval_recall_fear": 0.0,
"eval_recall_joy": 0.0,
"eval_recall_neutral": 1.0,
"eval_recall_sadness": 0.0,
"eval_recall_surprise": 0.0,
"eval_runtime": 53.2257,
"eval_samples_per_second": 449.106,
"eval_steps_per_second": 14.035,
"step": 27196
},
{
"epoch": 16.28,
"learning_rate": 0.000367905771021569,
"loss": 1.4935,
"step": 27235
},
{
"epoch": 16.53,
"learning_rate": 0.00035738554853648104,
"loss": 1.5047,
"step": 27654
},
{
"epoch": 16.78,
"learning_rate": 0.0003468401580550172,
"loss": 1.4959,
"step": 28073
},
{
"epoch": 17.03,
"learning_rate": 0.0003362947675735535,
"loss": 1.5074,
"step": 28492
},
{
"epoch": 17.28,
"learning_rate": 0.00032574937709208967,
"loss": 1.5007,
"step": 28911
},
{
"epoch": 17.51,
"eval_accuracy": 0.4471636546184739,
"eval_b_acc": 0.14285714285714285,
"eval_f1": 0.2763410114310333,
"eval_f1_anger": 0.0,
"eval_f1_disgust": 0.0,
"eval_f1_fear": 0.0,
"eval_f1_joy": 0.0,
"eval_f1_neutral": 0.6179862978059145,
"eval_f1_sadness": 0.0,
"eval_f1_surprise": 0.0,
"eval_loss": 1.5446112155914307,
"eval_micro_f1": 0.4471636546184739,
"eval_prec": 0.1999553340117498,
"eval_prec_anger": 0.0,
"eval_prec_disgust": 0.0,
"eval_prec_fear": 0.0,
"eval_prec_joy": 0.0,
"eval_prec_neutral": 0.4471636546184739,
"eval_prec_sadness": 0.0,
"eval_prec_surprise": 0.0,
"eval_recall": 0.4471636546184739,
"eval_recall_anger": 0.0,
"eval_recall_disgust": 0.0,
"eval_recall_fear": 0.0,
"eval_recall_joy": 0.0,
"eval_recall_neutral": 1.0,
"eval_recall_sadness": 0.0,
"eval_recall_surprise": 0.0,
"eval_runtime": 52.751,
"eval_samples_per_second": 453.148,
"eval_steps_per_second": 14.161,
"step": 29288
},
{
"epoch": 17.53,
"learning_rate": 0.00031520398661062594,
"loss": 1.5003,
"step": 29330
},
{
"epoch": 17.78,
"learning_rate": 0.00030465859612916217,
"loss": 1.5044,
"step": 29749
},
{
"epoch": 18.03,
"learning_rate": 0.0002941132056476984,
"loss": 1.4958,
"step": 30168
},
{
"epoch": 18.28,
"learning_rate": 0.0002835678151662346,
"loss": 1.5033,
"step": 30587
},
{
"epoch": 18.53,
"learning_rate": 0.00027302242468477085,
"loss": 1.4919,
"step": 31006
},
{
"epoch": 18.76,
"eval_accuracy": 0.4471636546184739,
"eval_b_acc": 0.14285714285714285,
"eval_f1": 0.2763410114310333,
"eval_f1_anger": 0.0,
"eval_f1_disgust": 0.0,
"eval_f1_fear": 0.0,
"eval_f1_joy": 0.0,
"eval_f1_neutral": 0.6179862978059145,
"eval_f1_sadness": 0.0,
"eval_f1_surprise": 0.0,
"eval_loss": 1.5616443157196045,
"eval_micro_f1": 0.4471636546184739,
"eval_prec": 0.1999553340117498,
"eval_prec_anger": 0.0,
"eval_prec_disgust": 0.0,
"eval_prec_fear": 0.0,
"eval_prec_joy": 0.0,
"eval_prec_neutral": 0.4471636546184739,
"eval_prec_sadness": 0.0,
"eval_prec_surprise": 0.0,
"eval_recall": 0.4471636546184739,
"eval_recall_anger": 0.0,
"eval_recall_disgust": 0.0,
"eval_recall_fear": 0.0,
"eval_recall_joy": 0.0,
"eval_recall_neutral": 1.0,
"eval_recall_sadness": 0.0,
"eval_recall_surprise": 0.0,
"eval_runtime": 53.1901,
"eval_samples_per_second": 449.407,
"eval_steps_per_second": 14.044,
"step": 31380
},
{
"epoch": 18.78,
"learning_rate": 0.00026247703420330707,
"loss": 1.4962,
"step": 31425
},
{
"epoch": 19.03,
"learning_rate": 0.0002519316437218433,
"loss": 1.4966,
"step": 31844
},
{
"epoch": 19.28,
"learning_rate": 0.00024138625324037955,
"loss": 1.4861,
"step": 32263
},
{
"epoch": 19.53,
"learning_rate": 0.00023084086275891577,
"loss": 1.4909,
"step": 32682
},
{
"epoch": 19.79,
"learning_rate": 0.000220295472277452,
"loss": 1.4895,
"step": 33101
},
{
"epoch": 20.01,
"eval_accuracy": 0.4471636546184739,
"eval_b_acc": 0.14285714285714285,
"eval_f1": 0.2763410114310333,
"eval_f1_anger": 0.0,
"eval_f1_disgust": 0.0,
"eval_f1_fear": 0.0,
"eval_f1_joy": 0.0,
"eval_f1_neutral": 0.6179862978059145,
"eval_f1_sadness": 0.0,
"eval_f1_surprise": 0.0,
"eval_loss": 1.5502026081085205,
"eval_micro_f1": 0.4471636546184739,
"eval_prec": 0.1999553340117498,
"eval_prec_anger": 0.0,
"eval_prec_disgust": 0.0,
"eval_prec_fear": 0.0,
"eval_prec_joy": 0.0,
"eval_prec_neutral": 0.4471636546184739,
"eval_prec_sadness": 0.0,
"eval_prec_surprise": 0.0,
"eval_recall": 0.4471636546184739,
"eval_recall_anger": 0.0,
"eval_recall_disgust": 0.0,
"eval_recall_fear": 0.0,
"eval_recall_joy": 0.0,
"eval_recall_neutral": 1.0,
"eval_recall_sadness": 0.0,
"eval_recall_surprise": 0.0,
"eval_runtime": 53.1794,
"eval_samples_per_second": 449.498,
"eval_steps_per_second": 14.047,
"step": 33472
},
{
"epoch": 20.04,
"learning_rate": 0.00020975008179598823,
"loss": 1.5021,
"step": 33520
},
{
"epoch": 20.29,
"learning_rate": 0.00019920469131452445,
"loss": 1.491,
"step": 33939
},
{
"epoch": 20.54,
"learning_rate": 0.00018865930083306068,
"loss": 1.4844,
"step": 34358
},
{
"epoch": 20.79,
"learning_rate": 0.0001781139103515969,
"loss": 1.4874,
"step": 34777
},
{
"epoch": 21.04,
"learning_rate": 0.00016756851987013313,
"loss": 1.4946,
"step": 35196
},
{
"epoch": 21.26,
"eval_accuracy": 0.4471636546184739,
"eval_b_acc": 0.14285714285714285,
"eval_f1": 0.2763410114310333,
"eval_f1_anger": 0.0,
"eval_f1_disgust": 0.0,
"eval_f1_fear": 0.0,
"eval_f1_joy": 0.0,
"eval_f1_neutral": 0.6179862978059145,
"eval_f1_sadness": 0.0,
"eval_f1_surprise": 0.0,
"eval_loss": 1.5398402214050293,
"eval_micro_f1": 0.4471636546184739,
"eval_prec": 0.1999553340117498,
"eval_prec_anger": 0.0,
"eval_prec_disgust": 0.0,
"eval_prec_fear": 0.0,
"eval_prec_joy": 0.0,
"eval_prec_neutral": 0.4471636546184739,
"eval_prec_sadness": 0.0,
"eval_prec_surprise": 0.0,
"eval_recall": 0.4471636546184739,
"eval_recall_anger": 0.0,
"eval_recall_disgust": 0.0,
"eval_recall_fear": 0.0,
"eval_recall_joy": 0.0,
"eval_recall_neutral": 1.0,
"eval_recall_sadness": 0.0,
"eval_recall_surprise": 0.0,
"eval_runtime": 53.2578,
"eval_samples_per_second": 448.836,
"eval_steps_per_second": 14.026,
"step": 35564
},
{
"epoch": 21.29,
"learning_rate": 0.00015702312938866935,
"loss": 1.4867,
"step": 35615
},
{
"epoch": 21.54,
"learning_rate": 0.00014647773890720558,
"loss": 1.4851,
"step": 36034
},
{
"epoch": 21.79,
"learning_rate": 0.00013595751642211766,
"loss": 1.4809,
"step": 36453
},
{
"epoch": 22.04,
"learning_rate": 0.00012541212594065389,
"loss": 1.4865,
"step": 36872
},
{
"epoch": 22.29,
"learning_rate": 0.0001148667354591901,
"loss": 1.4754,
"step": 37291
},
{
"epoch": 22.51,
"eval_accuracy": 0.4471636546184739,
"eval_b_acc": 0.14285714285714285,
"eval_f1": 0.2763410114310333,
"eval_f1_anger": 0.0,
"eval_f1_disgust": 0.0,
"eval_f1_fear": 0.0,
"eval_f1_joy": 0.0,
"eval_f1_neutral": 0.6179862978059145,
"eval_f1_sadness": 0.0,
"eval_f1_surprise": 0.0,
"eval_loss": 1.5307480096817017,
"eval_micro_f1": 0.4471636546184739,
"eval_prec": 0.1999553340117498,
"eval_prec_anger": 0.0,
"eval_prec_disgust": 0.0,
"eval_prec_fear": 0.0,
"eval_prec_joy": 0.0,
"eval_prec_neutral": 0.4471636546184739,
"eval_prec_sadness": 0.0,
"eval_prec_surprise": 0.0,
"eval_recall": 0.4471636546184739,
"eval_recall_anger": 0.0,
"eval_recall_disgust": 0.0,
"eval_recall_fear": 0.0,
"eval_recall_joy": 0.0,
"eval_recall_neutral": 1.0,
"eval_recall_sadness": 0.0,
"eval_recall_surprise": 0.0,
"eval_runtime": 53.2695,
"eval_samples_per_second": 448.737,
"eval_steps_per_second": 14.023,
"step": 37656
},
{
"epoch": 22.54,
"learning_rate": 0.00010432134497772632,
"loss": 1.4855,
"step": 37710
},
{
"epoch": 22.79,
"learning_rate": 9.380112249263837e-05,
"loss": 1.4831,
"step": 38129
},
{
"epoch": 23.04,
"learning_rate": 8.325573201117459e-05,
"loss": 1.4884,
"step": 38548
},
{
"epoch": 23.29,
"learning_rate": 7.271034152971082e-05,
"loss": 1.4794,
"step": 38967
},
{
"epoch": 23.54,
"learning_rate": 6.216495104824706e-05,
"loss": 1.4824,
"step": 39386
},
{
"epoch": 23.76,
"eval_accuracy": 0.4471636546184739,
"eval_b_acc": 0.14285714285714285,
"eval_f1": 0.2763410114310333,
"eval_f1_anger": 0.0,
"eval_f1_disgust": 0.0,
"eval_f1_fear": 0.0,
"eval_f1_joy": 0.0,
"eval_f1_neutral": 0.6179862978059145,
"eval_f1_sadness": 0.0,
"eval_f1_surprise": 0.0,
"eval_loss": 1.535596489906311,
"eval_micro_f1": 0.4471636546184739,
"eval_prec": 0.1999553340117498,
"eval_prec_anger": 0.0,
"eval_prec_disgust": 0.0,
"eval_prec_fear": 0.0,
"eval_prec_joy": 0.0,
"eval_prec_neutral": 0.4471636546184739,
"eval_prec_sadness": 0.0,
"eval_prec_surprise": 0.0,
"eval_recall": 0.4471636546184739,
"eval_recall_anger": 0.0,
"eval_recall_disgust": 0.0,
"eval_recall_fear": 0.0,
"eval_recall_joy": 0.0,
"eval_recall_neutral": 1.0,
"eval_recall_sadness": 0.0,
"eval_recall_surprise": 0.0,
"eval_runtime": 52.9319,
"eval_samples_per_second": 451.599,
"eval_steps_per_second": 14.112,
"step": 39748
},
{
"epoch": 23.79,
"learning_rate": 5.1619560566783274e-05,
"loss": 1.482,
"step": 39805
},
{
"epoch": 24.04,
"learning_rate": 4.1074170085319506e-05,
"loss": 1.4867,
"step": 40224
},
{
"epoch": 24.29,
"learning_rate": 3.052877960385574e-05,
"loss": 1.4839,
"step": 40643
},
{
"epoch": 24.54,
"learning_rate": 1.9983389122391967e-05,
"loss": 1.4788,
"step": 41062
},
{
"epoch": 24.79,
"learning_rate": 9.437998640928196e-06,
"loss": 1.4844,
"step": 41481
},
{
"epoch": 25.0,
"step": 41825,
"total_flos": 1.2547148116392576e+18,
"train_loss": 1.4594040881953265,
"train_runtime": 28719.4719,
"train_samples_per_second": 186.383,
"train_steps_per_second": 1.456
}
],
"logging_steps": 419,
"max_steps": 41825,
"num_train_epochs": 25,
"save_steps": 4183,
"total_flos": 1.2547148116392576e+18,
"trial_name": null,
"trial_params": null
}