bloomz-560m-mixed-detector / trainer_state.json
andreas122001's picture
Upload 10 files
8fad34c
raw
history blame
24.4 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"global_step": 2188,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 4.997714808043876e-05,
"loss": 5.5906,
"step": 1
},
{
"epoch": 0.02,
"learning_rate": 4.9017367458866546e-05,
"loss": 3.8301,
"step": 43
},
{
"epoch": 0.02,
"eval_accuracy": 0.7008,
"eval_f1": 0.7372365339578454,
"eval_loss": 1.7894935607910156,
"eval_precision": 0.6572025052192066,
"eval_recall": 0.8394666666666667,
"eval_runtime": 100.3646,
"eval_samples_per_second": 37.364,
"eval_steps_per_second": 4.673,
"step": 43
},
{
"epoch": 0.04,
"learning_rate": 4.8034734917733096e-05,
"loss": 1.7461,
"step": 86
},
{
"epoch": 0.04,
"eval_accuracy": 0.7669333333333334,
"eval_f1": 0.8065515714918104,
"eval_loss": 1.6799604892730713,
"eval_precision": 0.6893681422625804,
"eval_recall": 0.9717333333333333,
"eval_runtime": 100.5302,
"eval_samples_per_second": 37.302,
"eval_steps_per_second": 4.665,
"step": 86
},
{
"epoch": 0.06,
"learning_rate": 4.705210237659964e-05,
"loss": 1.5511,
"step": 129
},
{
"epoch": 0.06,
"eval_accuracy": 0.8925333333333333,
"eval_f1": 0.8882728028832826,
"eval_loss": 0.5680333375930786,
"eval_precision": 0.9249422632794457,
"eval_recall": 0.8544,
"eval_runtime": 100.4817,
"eval_samples_per_second": 37.32,
"eval_steps_per_second": 4.668,
"step": 129
},
{
"epoch": 0.08,
"learning_rate": 4.606946983546618e-05,
"loss": 1.2304,
"step": 172
},
{
"epoch": 0.08,
"eval_accuracy": 0.7061333333333333,
"eval_f1": 0.5838368580060423,
"eval_loss": 4.393102169036865,
"eval_precision": 1.0,
"eval_recall": 0.41226666666666667,
"eval_runtime": 100.2927,
"eval_samples_per_second": 37.391,
"eval_steps_per_second": 4.676,
"step": 172
},
{
"epoch": 0.1,
"learning_rate": 4.5086837294332726e-05,
"loss": 1.6111,
"step": 215
},
{
"epoch": 0.1,
"eval_accuracy": 0.7248,
"eval_f1": 0.7810776410691558,
"eval_loss": 1.275352954864502,
"eval_precision": 0.6484677703416696,
"eval_recall": 0.9818666666666667,
"eval_runtime": 100.7588,
"eval_samples_per_second": 37.218,
"eval_steps_per_second": 4.655,
"step": 215
},
{
"epoch": 0.12,
"learning_rate": 4.410420475319927e-05,
"loss": 1.1002,
"step": 258
},
{
"epoch": 0.12,
"eval_accuracy": 0.848,
"eval_f1": 0.8375142531356898,
"eval_loss": 0.5289755463600159,
"eval_precision": 0.8995713410900184,
"eval_recall": 0.7834666666666666,
"eval_runtime": 100.7268,
"eval_samples_per_second": 37.229,
"eval_steps_per_second": 4.656,
"step": 258
},
{
"epoch": 0.14,
"learning_rate": 4.312157221206581e-05,
"loss": 0.6462,
"step": 301
},
{
"epoch": 0.14,
"eval_accuracy": 0.864,
"eval_f1": 0.8452669902912622,
"eval_loss": 0.6743063926696777,
"eval_precision": 0.9802955665024631,
"eval_recall": 0.7429333333333333,
"eval_runtime": 100.4683,
"eval_samples_per_second": 37.325,
"eval_steps_per_second": 4.668,
"step": 301
},
{
"epoch": 0.16,
"learning_rate": 4.213893967093236e-05,
"loss": 0.6835,
"step": 344
},
{
"epoch": 0.16,
"eval_accuracy": 0.6992,
"eval_f1": 0.7657807308970099,
"eval_loss": 0.9862114787101746,
"eval_precision": 0.6269976198571914,
"eval_recall": 0.9834666666666667,
"eval_runtime": 100.9462,
"eval_samples_per_second": 37.148,
"eval_steps_per_second": 4.646,
"step": 344
},
{
"epoch": 0.18,
"learning_rate": 4.1156307129798905e-05,
"loss": 0.5506,
"step": 387
},
{
"epoch": 0.18,
"eval_accuracy": 0.7984,
"eval_f1": 0.7476635514018691,
"eval_loss": 1.4477732181549072,
"eval_precision": 0.9991079393398751,
"eval_recall": 0.5973333333333334,
"eval_runtime": 101.0116,
"eval_samples_per_second": 37.124,
"eval_steps_per_second": 4.643,
"step": 387
},
{
"epoch": 0.2,
"learning_rate": 4.017367458866545e-05,
"loss": 1.0906,
"step": 430
},
{
"epoch": 0.2,
"eval_accuracy": 0.9165333333333333,
"eval_f1": 0.9144575020497402,
"eval_loss": 0.2948032021522522,
"eval_precision": 0.9377802690582959,
"eval_recall": 0.8922666666666667,
"eval_runtime": 100.9951,
"eval_samples_per_second": 37.131,
"eval_steps_per_second": 4.644,
"step": 430
},
{
"epoch": 0.22,
"learning_rate": 3.919104204753199e-05,
"loss": 0.4459,
"step": 473
},
{
"epoch": 0.22,
"eval_accuracy": 0.9082666666666667,
"eval_f1": 0.9078242229367631,
"eval_loss": 0.5833027362823486,
"eval_precision": 0.9122240172320948,
"eval_recall": 0.9034666666666666,
"eval_runtime": 100.5094,
"eval_samples_per_second": 37.31,
"eval_steps_per_second": 4.666,
"step": 473
},
{
"epoch": 0.24,
"learning_rate": 3.820840950639854e-05,
"loss": 0.4996,
"step": 516
},
{
"epoch": 0.24,
"eval_accuracy": 0.9210666666666667,
"eval_f1": 0.9218172213417856,
"eval_loss": 0.6353188157081604,
"eval_precision": 0.913134484563056,
"eval_recall": 0.9306666666666666,
"eval_runtime": 100.6316,
"eval_samples_per_second": 37.265,
"eval_steps_per_second": 4.661,
"step": 516
},
{
"epoch": 0.26,
"learning_rate": 3.7225776965265085e-05,
"loss": 0.4613,
"step": 559
},
{
"epoch": 0.26,
"eval_accuracy": 0.9290666666666667,
"eval_f1": 0.926923076923077,
"eval_loss": 0.43136465549468994,
"eval_precision": 0.9558073654390935,
"eval_recall": 0.8997333333333334,
"eval_runtime": 100.9532,
"eval_samples_per_second": 37.146,
"eval_steps_per_second": 4.646,
"step": 559
},
{
"epoch": 0.28,
"learning_rate": 3.624314442413163e-05,
"loss": 0.3868,
"step": 602
},
{
"epoch": 0.28,
"eval_accuracy": 0.8997333333333334,
"eval_f1": 0.8932424758659853,
"eval_loss": 0.6684072017669678,
"eval_precision": 0.9550698239222829,
"eval_recall": 0.8389333333333333,
"eval_runtime": 100.7051,
"eval_samples_per_second": 37.237,
"eval_steps_per_second": 4.657,
"step": 602
},
{
"epoch": 0.29,
"learning_rate": 3.526051188299818e-05,
"loss": 0.3524,
"step": 645
},
{
"epoch": 0.29,
"eval_accuracy": 0.9269333333333334,
"eval_f1": 0.9261057173678533,
"eval_loss": 0.49305853247642517,
"eval_precision": 0.9367157665030006,
"eval_recall": 0.9157333333333333,
"eval_runtime": 101.0904,
"eval_samples_per_second": 37.096,
"eval_steps_per_second": 4.639,
"step": 645
},
{
"epoch": 0.31,
"learning_rate": 3.4277879341864715e-05,
"loss": 0.4739,
"step": 688
},
{
"epoch": 0.31,
"eval_accuracy": 0.9192,
"eval_f1": 0.9207428720899816,
"eval_loss": 0.4122666120529175,
"eval_precision": 0.9034907597535934,
"eval_recall": 0.9386666666666666,
"eval_runtime": 101.3837,
"eval_samples_per_second": 36.988,
"eval_steps_per_second": 4.626,
"step": 688
},
{
"epoch": 0.33,
"learning_rate": 3.329524680073126e-05,
"loss": 0.5484,
"step": 731
},
{
"epoch": 0.33,
"eval_accuracy": 0.6853333333333333,
"eval_f1": 0.7321833862914208,
"eval_loss": 0.6493818759918213,
"eval_precision": 0.6372975108652706,
"eval_recall": 0.8602666666666666,
"eval_runtime": 100.5978,
"eval_samples_per_second": 37.277,
"eval_steps_per_second": 4.662,
"step": 731
},
{
"epoch": 0.35,
"learning_rate": 3.231261425959781e-05,
"loss": 0.4939,
"step": 774
},
{
"epoch": 0.35,
"eval_accuracy": 0.8562666666666666,
"eval_f1": 0.8371109096403747,
"eval_loss": 0.43780916929244995,
"eval_precision": 0.9658298465829847,
"eval_recall": 0.7386666666666667,
"eval_runtime": 101.7646,
"eval_samples_per_second": 36.85,
"eval_steps_per_second": 4.609,
"step": 774
},
{
"epoch": 0.37,
"learning_rate": 3.132998171846435e-05,
"loss": 0.3646,
"step": 817
},
{
"epoch": 0.37,
"eval_accuracy": 0.9093333333333333,
"eval_f1": 0.9018475750577367,
"eval_loss": 0.5472243428230286,
"eval_precision": 0.9830081812460667,
"eval_recall": 0.8330666666666666,
"eval_runtime": 100.6656,
"eval_samples_per_second": 37.252,
"eval_steps_per_second": 4.659,
"step": 817
},
{
"epoch": 0.39,
"learning_rate": 3.03473491773309e-05,
"loss": 0.3954,
"step": 860
},
{
"epoch": 0.39,
"eval_accuracy": 0.9216,
"eval_f1": 0.9219330855018588,
"eval_loss": 0.3911387324333191,
"eval_precision": 0.9180327868852459,
"eval_recall": 0.9258666666666666,
"eval_runtime": 101.1862,
"eval_samples_per_second": 37.06,
"eval_steps_per_second": 4.635,
"step": 860
},
{
"epoch": 0.41,
"learning_rate": 2.9364716636197442e-05,
"loss": 0.3898,
"step": 903
},
{
"epoch": 0.41,
"eval_accuracy": 0.8677333333333334,
"eval_f1": 0.8485958485958486,
"eval_loss": 0.608423113822937,
"eval_precision": 0.9921484653818701,
"eval_recall": 0.7413333333333333,
"eval_runtime": 100.7786,
"eval_samples_per_second": 37.21,
"eval_steps_per_second": 4.654,
"step": 903
},
{
"epoch": 0.43,
"learning_rate": 2.838208409506399e-05,
"loss": 0.5361,
"step": 946
},
{
"epoch": 0.43,
"eval_accuracy": 0.9045333333333333,
"eval_f1": 0.8954439252336449,
"eval_loss": 0.5845316648483276,
"eval_precision": 0.9896707553260168,
"eval_recall": 0.8176,
"eval_runtime": 100.5268,
"eval_samples_per_second": 37.303,
"eval_steps_per_second": 4.665,
"step": 946
},
{
"epoch": 0.45,
"learning_rate": 2.739945155393053e-05,
"loss": 0.3488,
"step": 989
},
{
"epoch": 0.45,
"eval_accuracy": 0.9032,
"eval_f1": 0.90854119425548,
"eval_loss": 0.6275143027305603,
"eval_precision": 0.8610315186246418,
"eval_recall": 0.9616,
"eval_runtime": 100.5257,
"eval_samples_per_second": 37.304,
"eval_steps_per_second": 4.665,
"step": 989
},
{
"epoch": 0.47,
"learning_rate": 2.641681901279708e-05,
"loss": 0.6024,
"step": 1032
},
{
"epoch": 0.47,
"eval_accuracy": 0.7704,
"eval_f1": 0.8113910186199343,
"eval_loss": 1.486302375793457,
"eval_precision": 0.6884758364312268,
"eval_recall": 0.9877333333333334,
"eval_runtime": 100.9298,
"eval_samples_per_second": 37.155,
"eval_steps_per_second": 4.647,
"step": 1032
},
{
"epoch": 0.49,
"learning_rate": 2.5434186471663625e-05,
"loss": 0.6391,
"step": 1075
},
{
"epoch": 0.49,
"eval_accuracy": 0.9296,
"eval_f1": 0.9263803680981595,
"eval_loss": 0.47947388887405396,
"eval_precision": 0.9707773232028054,
"eval_recall": 0.8858666666666667,
"eval_runtime": 100.5142,
"eval_samples_per_second": 37.308,
"eval_steps_per_second": 4.666,
"step": 1075
},
{
"epoch": 0.51,
"learning_rate": 2.4451553930530165e-05,
"loss": 0.6603,
"step": 1118
},
{
"epoch": 0.51,
"eval_accuracy": 0.9266666666666666,
"eval_f1": 0.9240541286937309,
"eval_loss": 0.35503658652305603,
"eval_precision": 0.9581901489117984,
"eval_recall": 0.8922666666666667,
"eval_runtime": 100.9348,
"eval_samples_per_second": 37.153,
"eval_steps_per_second": 4.647,
"step": 1118
},
{
"epoch": 0.53,
"learning_rate": 2.346892138939671e-05,
"loss": 0.3186,
"step": 1161
},
{
"epoch": 0.53,
"eval_accuracy": 0.9317333333333333,
"eval_f1": 0.9288493607559756,
"eval_loss": 0.4835192561149597,
"eval_precision": 0.9698200812536274,
"eval_recall": 0.8912,
"eval_runtime": 100.4468,
"eval_samples_per_second": 37.333,
"eval_steps_per_second": 4.669,
"step": 1161
},
{
"epoch": 0.55,
"learning_rate": 2.2486288848263255e-05,
"loss": 0.3122,
"step": 1204
},
{
"epoch": 0.55,
"eval_accuracy": 0.9328,
"eval_f1": 0.9340314136125655,
"eval_loss": 0.31904712319374084,
"eval_precision": 0.9172236503856042,
"eval_recall": 0.9514666666666667,
"eval_runtime": 100.4601,
"eval_samples_per_second": 37.328,
"eval_steps_per_second": 4.669,
"step": 1204
},
{
"epoch": 0.57,
"learning_rate": 2.1503656307129798e-05,
"loss": 0.4917,
"step": 1247
},
{
"epoch": 0.57,
"eval_accuracy": 0.9192,
"eval_f1": 0.9151498179781573,
"eval_loss": 0.45495307445526123,
"eval_precision": 0.9634433962264151,
"eval_recall": 0.8714666666666666,
"eval_runtime": 100.5501,
"eval_samples_per_second": 37.295,
"eval_steps_per_second": 4.664,
"step": 1247
},
{
"epoch": 0.59,
"learning_rate": 2.0521023765996345e-05,
"loss": 0.448,
"step": 1290
},
{
"epoch": 0.59,
"eval_accuracy": 0.936,
"eval_f1": 0.9338113623827909,
"eval_loss": 0.18482676148414612,
"eval_precision": 0.9668760708166761,
"eval_recall": 0.9029333333333334,
"eval_runtime": 100.3779,
"eval_samples_per_second": 37.359,
"eval_steps_per_second": 4.672,
"step": 1290
},
{
"epoch": 0.61,
"learning_rate": 1.953839122486289e-05,
"loss": 0.3064,
"step": 1333
},
{
"epoch": 0.61,
"eval_accuracy": 0.9402666666666667,
"eval_f1": 0.9405204460966542,
"eval_loss": 0.23262375593185425,
"eval_precision": 0.9365415124272871,
"eval_recall": 0.9445333333333333,
"eval_runtime": 101.1761,
"eval_samples_per_second": 37.064,
"eval_steps_per_second": 4.635,
"step": 1333
},
{
"epoch": 0.63,
"learning_rate": 1.8555758683729435e-05,
"loss": 0.2274,
"step": 1376
},
{
"epoch": 0.63,
"eval_accuracy": 0.924,
"eval_f1": 0.9256844850065189,
"eval_loss": 0.28850072622299194,
"eval_precision": 0.9056122448979592,
"eval_recall": 0.9466666666666667,
"eval_runtime": 100.8319,
"eval_samples_per_second": 37.191,
"eval_steps_per_second": 4.651,
"step": 1376
},
{
"epoch": 0.65,
"learning_rate": 1.7573126142595978e-05,
"loss": 0.3728,
"step": 1419
},
{
"epoch": 0.65,
"eval_accuracy": 0.9301333333333334,
"eval_f1": 0.9273433166943982,
"eval_loss": 0.29230690002441406,
"eval_precision": 0.9659156556903524,
"eval_recall": 0.8917333333333334,
"eval_runtime": 100.785,
"eval_samples_per_second": 37.208,
"eval_steps_per_second": 4.653,
"step": 1419
},
{
"epoch": 0.67,
"learning_rate": 1.659049360146252e-05,
"loss": 0.5048,
"step": 1462
},
{
"epoch": 0.67,
"eval_accuracy": 0.9464,
"eval_f1": 0.9464713715046603,
"eval_loss": 0.2164454311132431,
"eval_precision": 0.9452127659574469,
"eval_recall": 0.9477333333333333,
"eval_runtime": 100.7467,
"eval_samples_per_second": 37.222,
"eval_steps_per_second": 4.655,
"step": 1462
},
{
"epoch": 0.69,
"learning_rate": 1.5607861060329068e-05,
"loss": 0.4483,
"step": 1505
},
{
"epoch": 0.69,
"eval_accuracy": 0.9250666666666667,
"eval_f1": 0.9274464239607538,
"eval_loss": 0.3050013482570648,
"eval_precision": 0.8988988988988988,
"eval_recall": 0.9578666666666666,
"eval_runtime": 100.8928,
"eval_samples_per_second": 37.168,
"eval_steps_per_second": 4.648,
"step": 1505
},
{
"epoch": 0.71,
"learning_rate": 1.4625228519195613e-05,
"loss": 0.3347,
"step": 1548
},
{
"epoch": 0.71,
"eval_accuracy": 0.9466666666666667,
"eval_f1": 0.9471179270227393,
"eval_loss": 0.22358763217926025,
"eval_precision": 0.9391714735186156,
"eval_recall": 0.9552,
"eval_runtime": 100.8242,
"eval_samples_per_second": 37.193,
"eval_steps_per_second": 4.652,
"step": 1548
},
{
"epoch": 0.73,
"learning_rate": 1.3642595978062158e-05,
"loss": 0.31,
"step": 1591
},
{
"epoch": 0.73,
"eval_accuracy": 0.9386666666666666,
"eval_f1": 0.9386011745862254,
"eval_loss": 0.18921497464179993,
"eval_precision": 0.9396044895777659,
"eval_recall": 0.9376,
"eval_runtime": 100.5904,
"eval_samples_per_second": 37.28,
"eval_steps_per_second": 4.662,
"step": 1591
},
{
"epoch": 0.75,
"learning_rate": 1.2659963436928701e-05,
"loss": 0.1936,
"step": 1634
},
{
"epoch": 0.75,
"eval_accuracy": 0.9424,
"eval_f1": 0.9430079155672824,
"eval_loss": 0.24673737585544586,
"eval_precision": 0.933159268929504,
"eval_recall": 0.9530666666666666,
"eval_runtime": 100.7748,
"eval_samples_per_second": 37.212,
"eval_steps_per_second": 4.654,
"step": 1634
},
{
"epoch": 0.77,
"learning_rate": 1.1677330895795248e-05,
"loss": 0.2855,
"step": 1677
},
{
"epoch": 0.77,
"eval_accuracy": 0.9384,
"eval_f1": 0.9391304347826087,
"eval_loss": 0.37995821237564087,
"eval_precision": 0.928125,
"eval_recall": 0.9504,
"eval_runtime": 100.6345,
"eval_samples_per_second": 37.264,
"eval_steps_per_second": 4.66,
"step": 1677
},
{
"epoch": 0.79,
"learning_rate": 1.0694698354661791e-05,
"loss": 0.2566,
"step": 1720
},
{
"epoch": 0.79,
"eval_accuracy": 0.9370666666666667,
"eval_f1": 0.9371671991480297,
"eval_loss": 0.38548287749290466,
"eval_precision": 0.935672514619883,
"eval_recall": 0.9386666666666666,
"eval_runtime": 101.0016,
"eval_samples_per_second": 37.128,
"eval_steps_per_second": 4.643,
"step": 1720
},
{
"epoch": 0.81,
"learning_rate": 9.712065813528338e-06,
"loss": 0.2966,
"step": 1763
},
{
"epoch": 0.81,
"eval_accuracy": 0.9512,
"eval_f1": 0.950068212824011,
"eval_loss": 0.28995445370674133,
"eval_precision": 0.9726256983240223,
"eval_recall": 0.9285333333333333,
"eval_runtime": 100.6179,
"eval_samples_per_second": 37.27,
"eval_steps_per_second": 4.661,
"step": 1763
},
{
"epoch": 0.83,
"learning_rate": 8.729433272394881e-06,
"loss": 0.2485,
"step": 1806
},
{
"epoch": 0.83,
"eval_accuracy": 0.9549333333333333,
"eval_f1": 0.9545087483176311,
"eval_loss": 0.24945972859859467,
"eval_precision": 0.9635869565217391,
"eval_recall": 0.9456,
"eval_runtime": 100.5538,
"eval_samples_per_second": 37.293,
"eval_steps_per_second": 4.664,
"step": 1806
},
{
"epoch": 0.85,
"learning_rate": 7.746800731261426e-06,
"loss": 0.2553,
"step": 1849
},
{
"epoch": 0.85,
"eval_accuracy": 0.9357333333333333,
"eval_f1": 0.9367620047231697,
"eval_loss": 0.394607812166214,
"eval_precision": 0.922004132231405,
"eval_recall": 0.952,
"eval_runtime": 100.5784,
"eval_samples_per_second": 37.284,
"eval_steps_per_second": 4.663,
"step": 1849
},
{
"epoch": 0.86,
"learning_rate": 6.764168190127972e-06,
"loss": 0.2719,
"step": 1892
},
{
"epoch": 0.86,
"eval_accuracy": 0.9533333333333334,
"eval_f1": 0.9524068534131085,
"eval_loss": 0.361551433801651,
"eval_precision": 0.9716981132075472,
"eval_recall": 0.9338666666666666,
"eval_runtime": 100.5791,
"eval_samples_per_second": 37.284,
"eval_steps_per_second": 4.663,
"step": 1892
},
{
"epoch": 0.88,
"learning_rate": 5.781535648994515e-06,
"loss": 0.2925,
"step": 1935
},
{
"epoch": 0.88,
"eval_accuracy": 0.9541333333333334,
"eval_f1": 0.9532862574687669,
"eval_loss": 0.30848976969718933,
"eval_precision": 0.9712230215827338,
"eval_recall": 0.936,
"eval_runtime": 100.6234,
"eval_samples_per_second": 37.268,
"eval_steps_per_second": 4.661,
"step": 1935
},
{
"epoch": 0.9,
"learning_rate": 4.798903107861061e-06,
"loss": 0.2477,
"step": 1978
},
{
"epoch": 0.9,
"eval_accuracy": 0.9544,
"eval_f1": 0.9536710918450284,
"eval_loss": 0.28153562545776367,
"eval_precision": 0.9691629955947136,
"eval_recall": 0.9386666666666666,
"eval_runtime": 100.4809,
"eval_samples_per_second": 37.321,
"eval_steps_per_second": 4.668,
"step": 1978
},
{
"epoch": 0.92,
"learning_rate": 3.816270566727605e-06,
"loss": 0.2164,
"step": 2021
},
{
"epoch": 0.92,
"eval_accuracy": 0.9568,
"eval_f1": 0.9560499186109603,
"eval_loss": 0.24747176468372345,
"eval_precision": 0.9729431253451132,
"eval_recall": 0.9397333333333333,
"eval_runtime": 100.5076,
"eval_samples_per_second": 37.311,
"eval_steps_per_second": 4.666,
"step": 2021
},
{
"epoch": 0.94,
"learning_rate": 2.83363802559415e-06,
"loss": 0.2816,
"step": 2064
},
{
"epoch": 0.94,
"eval_accuracy": 0.9570666666666666,
"eval_f1": 0.9563093622795115,
"eval_loss": 0.263465017080307,
"eval_precision": 0.9734806629834254,
"eval_recall": 0.9397333333333333,
"eval_runtime": 100.4934,
"eval_samples_per_second": 37.316,
"eval_steps_per_second": 4.667,
"step": 2064
},
{
"epoch": 0.96,
"learning_rate": 1.851005484460695e-06,
"loss": 0.351,
"step": 2107
},
{
"epoch": 0.96,
"eval_accuracy": 0.9573333333333334,
"eval_f1": 0.9566160520607375,
"eval_loss": 0.23055072128772736,
"eval_precision": 0.972972972972973,
"eval_recall": 0.9408,
"eval_runtime": 100.5497,
"eval_samples_per_second": 37.295,
"eval_steps_per_second": 4.664,
"step": 2107
},
{
"epoch": 0.98,
"learning_rate": 8.683729433272396e-07,
"loss": 0.2591,
"step": 2150
},
{
"epoch": 0.98,
"eval_accuracy": 0.9562666666666667,
"eval_f1": 0.955288985823337,
"eval_loss": 0.2391371726989746,
"eval_precision": 0.9771332961517011,
"eval_recall": 0.9344,
"eval_runtime": 100.6094,
"eval_samples_per_second": 37.273,
"eval_steps_per_second": 4.662,
"step": 2150
}
],
"max_steps": 2188,
"num_train_epochs": 1,
"total_flos": 1.62524823552e+16,
"trial_name": null,
"trial_params": null
}