roberta-academic-detector / trainer_state.json
andreas122001's picture
Upload 12 files
3220104
raw
history blame
24 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"global_step": 1750,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 4.9971428571428576e-05,
"loss": 0.6862,
"step": 1
},
{
"epoch": 0.02,
"learning_rate": 4.9e-05,
"loss": 0.4775,
"step": 35
},
{
"epoch": 0.02,
"eval_accuracy": 0.857,
"eval_f1": 0.8737864077669902,
"eval_loss": 0.40033745765686035,
"eval_precision": 0.7819905213270142,
"eval_recall": 0.99,
"eval_runtime": 39.2752,
"eval_samples_per_second": 76.384,
"eval_steps_per_second": 9.548,
"step": 35
},
{
"epoch": 0.04,
"learning_rate": 4.8e-05,
"loss": 0.3051,
"step": 70
},
{
"epoch": 0.04,
"eval_accuracy": 0.8823333333333333,
"eval_f1": 0.8942163620017981,
"eval_loss": 0.6440998911857605,
"eval_precision": 0.8121937942297224,
"eval_recall": 0.9946666666666667,
"eval_runtime": 37.422,
"eval_samples_per_second": 80.167,
"eval_steps_per_second": 10.021,
"step": 70
},
{
"epoch": 0.06,
"learning_rate": 4.7e-05,
"loss": 0.492,
"step": 105
},
{
"epoch": 0.06,
"eval_accuracy": 0.8696666666666667,
"eval_f1": 0.8846947803007963,
"eval_loss": 0.6633870601654053,
"eval_precision": 0.7932310946589106,
"eval_recall": 1.0,
"eval_runtime": 36.0985,
"eval_samples_per_second": 83.106,
"eval_steps_per_second": 10.388,
"step": 105
},
{
"epoch": 0.08,
"learning_rate": 4.600000000000001e-05,
"loss": 0.2019,
"step": 140
},
{
"epoch": 0.08,
"eval_accuracy": 0.9256666666666666,
"eval_f1": 0.9306376360808709,
"eval_loss": 0.46288976073265076,
"eval_precision": 0.8723032069970845,
"eval_recall": 0.9973333333333333,
"eval_runtime": 36.0593,
"eval_samples_per_second": 83.196,
"eval_steps_per_second": 10.4,
"step": 140
},
{
"epoch": 0.1,
"learning_rate": 4.5e-05,
"loss": 0.2224,
"step": 175
},
{
"epoch": 0.1,
"eval_accuracy": 0.9183333333333333,
"eval_f1": 0.9243126351560087,
"eval_loss": 0.34658756852149963,
"eval_precision": 0.8612550374208405,
"eval_recall": 0.9973333333333333,
"eval_runtime": 36.7878,
"eval_samples_per_second": 81.549,
"eval_steps_per_second": 10.194,
"step": 175
},
{
"epoch": 0.12,
"learning_rate": 4.4000000000000006e-05,
"loss": 0.1034,
"step": 210
},
{
"epoch": 0.12,
"eval_accuracy": 0.9716666666666667,
"eval_f1": 0.9722312969617772,
"eval_loss": 0.12845683097839355,
"eval_precision": 0.9532351057014734,
"eval_recall": 0.992,
"eval_runtime": 37.1714,
"eval_samples_per_second": 80.707,
"eval_steps_per_second": 10.088,
"step": 210
},
{
"epoch": 0.14,
"learning_rate": 4.3e-05,
"loss": 0.0783,
"step": 245
},
{
"epoch": 0.14,
"eval_accuracy": 0.98,
"eval_f1": 0.9803149606299214,
"eval_loss": 0.09441035240888596,
"eval_precision": 0.9651162790697675,
"eval_recall": 0.996,
"eval_runtime": 37.1535,
"eval_samples_per_second": 80.746,
"eval_steps_per_second": 10.093,
"step": 245
},
{
"epoch": 0.16,
"learning_rate": 4.2e-05,
"loss": 0.2329,
"step": 280
},
{
"epoch": 0.16,
"eval_accuracy": 0.91,
"eval_f1": 0.9173806609547123,
"eval_loss": 0.33303627371788025,
"eval_precision": 0.8478506787330317,
"eval_recall": 0.9993333333333333,
"eval_runtime": 37.5239,
"eval_samples_per_second": 79.949,
"eval_steps_per_second": 9.994,
"step": 280
},
{
"epoch": 0.18,
"learning_rate": 4.1e-05,
"loss": 0.0883,
"step": 315
},
{
"epoch": 0.18,
"eval_accuracy": 0.9436666666666667,
"eval_f1": 0.946603475513428,
"eval_loss": 0.32765254378318787,
"eval_precision": 0.8996996996996997,
"eval_recall": 0.9986666666666667,
"eval_runtime": 36.0524,
"eval_samples_per_second": 83.212,
"eval_steps_per_second": 10.402,
"step": 315
},
{
"epoch": 0.2,
"learning_rate": 4e-05,
"loss": 0.1818,
"step": 350
},
{
"epoch": 0.2,
"eval_accuracy": 0.9783333333333334,
"eval_f1": 0.9786535303776683,
"eval_loss": 0.06494130194187164,
"eval_precision": 0.9644012944983819,
"eval_recall": 0.9933333333333333,
"eval_runtime": 37.1476,
"eval_samples_per_second": 80.759,
"eval_steps_per_second": 10.095,
"step": 350
},
{
"epoch": 0.22,
"learning_rate": 3.9000000000000006e-05,
"loss": 0.1854,
"step": 385
},
{
"epoch": 0.22,
"eval_accuracy": 0.9913333333333333,
"eval_f1": 0.991315965263861,
"eval_loss": 0.04114186391234398,
"eval_precision": 0.9933065595716198,
"eval_recall": 0.9893333333333333,
"eval_runtime": 37.1144,
"eval_samples_per_second": 80.831,
"eval_steps_per_second": 10.104,
"step": 385
},
{
"epoch": 0.24,
"learning_rate": 3.8e-05,
"loss": 0.085,
"step": 420
},
{
"epoch": 0.24,
"eval_accuracy": 0.988,
"eval_f1": 0.9879437374413931,
"eval_loss": 0.05784890055656433,
"eval_precision": 0.9925975773889637,
"eval_recall": 0.9833333333333333,
"eval_runtime": 35.9925,
"eval_samples_per_second": 83.351,
"eval_steps_per_second": 10.419,
"step": 420
},
{
"epoch": 0.26,
"learning_rate": 3.7e-05,
"loss": 0.1281,
"step": 455
},
{
"epoch": 0.26,
"eval_accuracy": 0.963,
"eval_f1": 0.9642281662906864,
"eval_loss": 0.23219378292560577,
"eval_precision": 0.9332501559575795,
"eval_recall": 0.9973333333333333,
"eval_runtime": 36.1167,
"eval_samples_per_second": 83.064,
"eval_steps_per_second": 10.383,
"step": 455
},
{
"epoch": 0.28,
"learning_rate": 3.6e-05,
"loss": 0.155,
"step": 490
},
{
"epoch": 0.28,
"eval_accuracy": 0.9793333333333333,
"eval_f1": 0.9795783926218709,
"eval_loss": 0.0876053124666214,
"eval_precision": 0.9680989583333334,
"eval_recall": 0.9913333333333333,
"eval_runtime": 37.4935,
"eval_samples_per_second": 80.014,
"eval_steps_per_second": 10.002,
"step": 490
},
{
"epoch": 0.3,
"learning_rate": 3.5e-05,
"loss": 0.1536,
"step": 525
},
{
"epoch": 0.3,
"eval_accuracy": 0.98,
"eval_f1": 0.98022412656559,
"eval_loss": 0.08141922205686569,
"eval_precision": 0.969361147327249,
"eval_recall": 0.9913333333333333,
"eval_runtime": 36.207,
"eval_samples_per_second": 82.857,
"eval_steps_per_second": 10.357,
"step": 525
},
{
"epoch": 0.32,
"learning_rate": 3.4000000000000007e-05,
"loss": 0.0686,
"step": 560
},
{
"epoch": 0.32,
"eval_accuracy": 0.8446666666666667,
"eval_f1": 0.8654734411085451,
"eval_loss": 0.7843948602676392,
"eval_precision": 0.7632382892057027,
"eval_recall": 0.9993333333333333,
"eval_runtime": 37.456,
"eval_samples_per_second": 80.094,
"eval_steps_per_second": 10.012,
"step": 560
},
{
"epoch": 0.34,
"learning_rate": 3.3e-05,
"loss": 0.0569,
"step": 595
},
{
"epoch": 0.34,
"eval_accuracy": 0.99,
"eval_f1": 0.99,
"eval_loss": 0.04974000155925751,
"eval_precision": 0.99,
"eval_recall": 0.99,
"eval_runtime": 36.1808,
"eval_samples_per_second": 82.917,
"eval_steps_per_second": 10.365,
"step": 595
},
{
"epoch": 0.36,
"learning_rate": 3.2000000000000005e-05,
"loss": 0.0951,
"step": 630
},
{
"epoch": 0.36,
"eval_accuracy": 0.9733333333333334,
"eval_f1": 0.9739243807040417,
"eval_loss": 0.14421893656253815,
"eval_precision": 0.9528061224489796,
"eval_recall": 0.996,
"eval_runtime": 36.1151,
"eval_samples_per_second": 83.068,
"eval_steps_per_second": 10.383,
"step": 630
},
{
"epoch": 0.38,
"learning_rate": 3.1e-05,
"loss": 0.0434,
"step": 665
},
{
"epoch": 0.38,
"eval_accuracy": 0.9026666666666666,
"eval_f1": 0.9111922141119222,
"eval_loss": 0.6636046767234802,
"eval_precision": 0.8378076062639821,
"eval_recall": 0.9986666666666667,
"eval_runtime": 37.4412,
"eval_samples_per_second": 80.126,
"eval_steps_per_second": 10.016,
"step": 665
},
{
"epoch": 0.4,
"learning_rate": 3e-05,
"loss": 0.1023,
"step": 700
},
{
"epoch": 0.4,
"eval_accuracy": 0.9653333333333334,
"eval_f1": 0.9664082687338501,
"eval_loss": 0.17706581950187683,
"eval_precision": 0.9373433583959899,
"eval_recall": 0.9973333333333333,
"eval_runtime": 36.7932,
"eval_samples_per_second": 81.537,
"eval_steps_per_second": 10.192,
"step": 700
},
{
"epoch": 0.42,
"learning_rate": 2.9e-05,
"loss": 0.0619,
"step": 735
},
{
"epoch": 0.42,
"eval_accuracy": 0.9893333333333333,
"eval_f1": 0.9893617021276595,
"eval_loss": 0.051007628440856934,
"eval_precision": 0.986737400530504,
"eval_recall": 0.992,
"eval_runtime": 36.0289,
"eval_samples_per_second": 83.267,
"eval_steps_per_second": 10.408,
"step": 735
},
{
"epoch": 0.44,
"learning_rate": 2.8000000000000003e-05,
"loss": 0.0367,
"step": 770
},
{
"epoch": 0.44,
"eval_accuracy": 0.9913333333333333,
"eval_f1": 0.9913275517011341,
"eval_loss": 0.04358353838324547,
"eval_precision": 0.9919893190921228,
"eval_recall": 0.9906666666666667,
"eval_runtime": 36.0918,
"eval_samples_per_second": 83.121,
"eval_steps_per_second": 10.39,
"step": 770
},
{
"epoch": 0.46,
"learning_rate": 2.7000000000000002e-05,
"loss": 0.0011,
"step": 805
},
{
"epoch": 0.46,
"eval_accuracy": 0.9896666666666667,
"eval_f1": 0.9896355733868272,
"eval_loss": 0.06585267186164856,
"eval_precision": 0.9926224010731053,
"eval_recall": 0.9866666666666667,
"eval_runtime": 36.0308,
"eval_samples_per_second": 83.262,
"eval_steps_per_second": 10.408,
"step": 805
},
{
"epoch": 0.48,
"learning_rate": 2.6000000000000002e-05,
"loss": 0.0241,
"step": 840
},
{
"epoch": 0.48,
"eval_accuracy": 0.976,
"eval_f1": 0.9764705882352941,
"eval_loss": 0.1684291660785675,
"eval_precision": 0.9576923076923077,
"eval_recall": 0.996,
"eval_runtime": 37.039,
"eval_samples_per_second": 80.996,
"eval_steps_per_second": 10.124,
"step": 840
},
{
"epoch": 0.5,
"learning_rate": 2.5e-05,
"loss": 0.1195,
"step": 875
},
{
"epoch": 0.5,
"eval_accuracy": 0.9793333333333333,
"eval_f1": 0.9797120418848168,
"eval_loss": 0.12230364978313446,
"eval_precision": 0.962082262210797,
"eval_recall": 0.998,
"eval_runtime": 36.0431,
"eval_samples_per_second": 83.234,
"eval_steps_per_second": 10.404,
"step": 875
},
{
"epoch": 0.52,
"learning_rate": 2.4e-05,
"loss": 0.0557,
"step": 910
},
{
"epoch": 0.52,
"eval_accuracy": 0.9916666666666667,
"eval_f1": 0.9916805324459235,
"eval_loss": 0.04335600137710571,
"eval_precision": 0.9900332225913622,
"eval_recall": 0.9933333333333333,
"eval_runtime": 36.1241,
"eval_samples_per_second": 83.047,
"eval_steps_per_second": 10.381,
"step": 910
},
{
"epoch": 0.54,
"learning_rate": 2.3000000000000003e-05,
"loss": 0.054,
"step": 945
},
{
"epoch": 0.54,
"eval_accuracy": 0.9913333333333333,
"eval_f1": 0.9913563829787235,
"eval_loss": 0.03961500525474548,
"eval_precision": 0.9887267904509284,
"eval_recall": 0.994,
"eval_runtime": 36.0623,
"eval_samples_per_second": 83.189,
"eval_steps_per_second": 10.399,
"step": 945
},
{
"epoch": 0.56,
"learning_rate": 2.2000000000000003e-05,
"loss": 0.0345,
"step": 980
},
{
"epoch": 0.56,
"eval_accuracy": 0.991,
"eval_f1": 0.9909426366990942,
"eval_loss": 0.05297405645251274,
"eval_precision": 0.9972991222147198,
"eval_recall": 0.9846666666666667,
"eval_runtime": 36.0625,
"eval_samples_per_second": 83.189,
"eval_steps_per_second": 10.399,
"step": 980
},
{
"epoch": 0.58,
"learning_rate": 2.1e-05,
"loss": 0.0582,
"step": 1015
},
{
"epoch": 0.58,
"eval_accuracy": 0.9636666666666667,
"eval_f1": 0.9648953301127215,
"eval_loss": 0.23049569129943848,
"eval_precision": 0.9333333333333333,
"eval_recall": 0.9986666666666667,
"eval_runtime": 36.0114,
"eval_samples_per_second": 83.307,
"eval_steps_per_second": 10.413,
"step": 1015
},
{
"epoch": 0.6,
"learning_rate": 2e-05,
"loss": 0.0451,
"step": 1050
},
{
"epoch": 0.6,
"eval_accuracy": 0.954,
"eval_f1": 0.9559948979591837,
"eval_loss": 0.2961997985839844,
"eval_precision": 0.9162591687041565,
"eval_recall": 0.9993333333333333,
"eval_runtime": 36.0251,
"eval_samples_per_second": 83.275,
"eval_steps_per_second": 10.409,
"step": 1050
},
{
"epoch": 0.62,
"learning_rate": 1.9e-05,
"loss": 0.134,
"step": 1085
},
{
"epoch": 0.62,
"eval_accuracy": 0.9836666666666667,
"eval_f1": 0.9839080459770116,
"eval_loss": 0.08320324122905731,
"eval_precision": 0.96957928802589,
"eval_recall": 0.9986666666666667,
"eval_runtime": 36.0675,
"eval_samples_per_second": 83.177,
"eval_steps_per_second": 10.397,
"step": 1085
},
{
"epoch": 0.64,
"learning_rate": 1.8e-05,
"loss": 0.0852,
"step": 1120
},
{
"epoch": 0.64,
"eval_accuracy": 0.987,
"eval_f1": 0.9871329594193335,
"eval_loss": 0.06261658668518066,
"eval_precision": 0.977139124755062,
"eval_recall": 0.9973333333333333,
"eval_runtime": 36.0739,
"eval_samples_per_second": 83.163,
"eval_steps_per_second": 10.395,
"step": 1120
},
{
"epoch": 0.66,
"learning_rate": 1.7000000000000003e-05,
"loss": 0.1262,
"step": 1155
},
{
"epoch": 0.66,
"eval_accuracy": 0.9516666666666667,
"eval_f1": 0.9538363578478192,
"eval_loss": 0.21791885793209076,
"eval_precision": 0.9128580134064594,
"eval_recall": 0.9986666666666667,
"eval_runtime": 36.0083,
"eval_samples_per_second": 83.314,
"eval_steps_per_second": 10.414,
"step": 1155
},
{
"epoch": 0.68,
"learning_rate": 1.6000000000000003e-05,
"loss": 0.0167,
"step": 1190
},
{
"epoch": 0.68,
"eval_accuracy": 0.9873333333333333,
"eval_f1": 0.9874587458745875,
"eval_loss": 0.060804687440395355,
"eval_precision": 0.9777777777777777,
"eval_recall": 0.9973333333333333,
"eval_runtime": 37.0856,
"eval_samples_per_second": 80.894,
"eval_steps_per_second": 10.112,
"step": 1190
},
{
"epoch": 0.7,
"learning_rate": 1.5e-05,
"loss": 0.1207,
"step": 1225
},
{
"epoch": 0.7,
"eval_accuracy": 0.993,
"eval_f1": 0.993025572899369,
"eval_loss": 0.025707580149173737,
"eval_precision": 0.9894109861019192,
"eval_recall": 0.9966666666666667,
"eval_runtime": 36.8077,
"eval_samples_per_second": 81.505,
"eval_steps_per_second": 10.188,
"step": 1225
},
{
"epoch": 0.72,
"learning_rate": 1.4000000000000001e-05,
"loss": 0.033,
"step": 1260
},
{
"epoch": 0.72,
"eval_accuracy": 0.994,
"eval_f1": 0.9940159574468085,
"eval_loss": 0.029781479388475418,
"eval_precision": 0.9913793103448276,
"eval_recall": 0.9966666666666667,
"eval_runtime": 36.0985,
"eval_samples_per_second": 83.106,
"eval_steps_per_second": 10.388,
"step": 1260
},
{
"epoch": 0.74,
"learning_rate": 1.3000000000000001e-05,
"loss": 0.0403,
"step": 1295
},
{
"epoch": 0.74,
"eval_accuracy": 0.97,
"eval_f1": 0.9708360337005832,
"eval_loss": 0.17279422283172607,
"eval_precision": 0.9445145018915511,
"eval_recall": 0.9986666666666667,
"eval_runtime": 36.0515,
"eval_samples_per_second": 83.214,
"eval_steps_per_second": 10.402,
"step": 1295
},
{
"epoch": 0.76,
"learning_rate": 1.2e-05,
"loss": 0.0554,
"step": 1330
},
{
"epoch": 0.76,
"eval_accuracy": 0.9866666666666667,
"eval_f1": 0.98681608437706,
"eval_loss": 0.0723133310675621,
"eval_precision": 0.9758800521512386,
"eval_recall": 0.998,
"eval_runtime": 36.0327,
"eval_samples_per_second": 83.258,
"eval_steps_per_second": 10.407,
"step": 1330
},
{
"epoch": 0.78,
"learning_rate": 1.1000000000000001e-05,
"loss": 0.0443,
"step": 1365
},
{
"epoch": 0.78,
"eval_accuracy": 0.9916666666666667,
"eval_f1": 0.99171362280411,
"eval_loss": 0.04444814473390579,
"eval_precision": 0.986156888595913,
"eval_recall": 0.9973333333333333,
"eval_runtime": 36.8515,
"eval_samples_per_second": 81.408,
"eval_steps_per_second": 10.176,
"step": 1365
},
{
"epoch": 0.8,
"learning_rate": 1e-05,
"loss": 0.0308,
"step": 1400
},
{
"epoch": 0.8,
"eval_accuracy": 0.9773333333333334,
"eval_f1": 0.9778067885117493,
"eval_loss": 0.1104651615023613,
"eval_precision": 0.9578005115089514,
"eval_recall": 0.9986666666666667,
"eval_runtime": 37.2021,
"eval_samples_per_second": 80.641,
"eval_steps_per_second": 10.08,
"step": 1400
},
{
"epoch": 0.82,
"learning_rate": 9e-06,
"loss": 0.0519,
"step": 1435
},
{
"epoch": 0.82,
"eval_accuracy": 0.9946666666666667,
"eval_f1": 0.9946559786239145,
"eval_loss": 0.023080775514245033,
"eval_precision": 0.9966532797858099,
"eval_recall": 0.9926666666666667,
"eval_runtime": 36.06,
"eval_samples_per_second": 83.195,
"eval_steps_per_second": 10.399,
"step": 1435
},
{
"epoch": 0.84,
"learning_rate": 8.000000000000001e-06,
"loss": 0.0007,
"step": 1470
},
{
"epoch": 0.84,
"eval_accuracy": 0.9856666666666667,
"eval_f1": 0.9858506087528792,
"eval_loss": 0.08097357302904129,
"eval_precision": 0.9733593242365172,
"eval_recall": 0.9986666666666667,
"eval_runtime": 35.9829,
"eval_samples_per_second": 83.373,
"eval_steps_per_second": 10.422,
"step": 1470
},
{
"epoch": 0.86,
"learning_rate": 7.000000000000001e-06,
"loss": 0.0167,
"step": 1505
},
{
"epoch": 0.86,
"eval_accuracy": 0.9883333333333333,
"eval_f1": 0.9884526558891455,
"eval_loss": 0.05811823159456253,
"eval_precision": 0.9784454604833442,
"eval_recall": 0.9986666666666667,
"eval_runtime": 37.0549,
"eval_samples_per_second": 80.961,
"eval_steps_per_second": 10.12,
"step": 1505
},
{
"epoch": 0.88,
"learning_rate": 6e-06,
"loss": 0.0514,
"step": 1540
},
{
"epoch": 0.88,
"eval_accuracy": 0.995,
"eval_f1": 0.995008319467554,
"eval_loss": 0.024803927168250084,
"eval_precision": 0.9933554817275747,
"eval_recall": 0.9966666666666667,
"eval_runtime": 36.1623,
"eval_samples_per_second": 82.959,
"eval_steps_per_second": 10.37,
"step": 1540
},
{
"epoch": 0.9,
"learning_rate": 5e-06,
"loss": 0.0005,
"step": 1575
},
{
"epoch": 0.9,
"eval_accuracy": 0.9943333333333333,
"eval_f1": 0.994354035204251,
"eval_loss": 0.03251485526561737,
"eval_precision": 0.9907346128391793,
"eval_recall": 0.998,
"eval_runtime": 36.0076,
"eval_samples_per_second": 83.316,
"eval_steps_per_second": 10.414,
"step": 1575
},
{
"epoch": 0.92,
"learning_rate": 4.000000000000001e-06,
"loss": 0.0003,
"step": 1610
},
{
"epoch": 0.92,
"eval_accuracy": 0.992,
"eval_f1": 0.9920477137176937,
"eval_loss": 0.04252306744456291,
"eval_precision": 0.9861660079051383,
"eval_recall": 0.998,
"eval_runtime": 36.1851,
"eval_samples_per_second": 82.907,
"eval_steps_per_second": 10.363,
"step": 1610
},
{
"epoch": 0.94,
"learning_rate": 3e-06,
"loss": 0.0688,
"step": 1645
},
{
"epoch": 0.94,
"eval_accuracy": 0.9903333333333333,
"eval_f1": 0.9904132231404958,
"eval_loss": 0.054892849177122116,
"eval_precision": 0.9822950819672132,
"eval_recall": 0.9986666666666667,
"eval_runtime": 36.0592,
"eval_samples_per_second": 83.197,
"eval_steps_per_second": 10.4,
"step": 1645
},
{
"epoch": 0.96,
"learning_rate": 2.0000000000000003e-06,
"loss": 0.0289,
"step": 1680
},
{
"epoch": 0.96,
"eval_accuracy": 0.987,
"eval_f1": 0.9871499176276771,
"eval_loss": 0.07362984865903854,
"eval_precision": 0.9758957654723127,
"eval_recall": 0.9986666666666667,
"eval_runtime": 36.8485,
"eval_samples_per_second": 81.415,
"eval_steps_per_second": 10.177,
"step": 1680
},
{
"epoch": 0.98,
"learning_rate": 1.0000000000000002e-06,
"loss": 0.0291,
"step": 1715
},
{
"epoch": 0.98,
"eval_accuracy": 0.9856666666666667,
"eval_f1": 0.9858506087528792,
"eval_loss": 0.07627929002046585,
"eval_precision": 0.9733593242365172,
"eval_recall": 0.9986666666666667,
"eval_runtime": 37.3831,
"eval_samples_per_second": 80.25,
"eval_steps_per_second": 10.031,
"step": 1715
},
{
"epoch": 1.0,
"learning_rate": 0.0,
"loss": 0.0004,
"step": 1750
},
{
"epoch": 1.0,
"eval_accuracy": 0.987,
"eval_f1": 0.9871499176276771,
"eval_loss": 0.07068450003862381,
"eval_precision": 0.9758957654723127,
"eval_recall": 0.9986666666666667,
"eval_runtime": 36.1142,
"eval_samples_per_second": 83.07,
"eval_steps_per_second": 10.384,
"step": 1750
}
],
"max_steps": 1750,
"num_train_epochs": 1,
"total_flos": 3683554775040000.0,
"trial_name": null,
"trial_params": null
}