| { | |
| "best_metric": 1.322691559791565, | |
| "best_model_checkpoint": "distilbert_sa_pre-training-complete/checkpoint-293068", | |
| "epoch": 167.87912702853944, | |
| "global_step": 300000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.9719239746582195e-05, | |
| "loss": 1.8819, | |
| "step": 1787 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6569985974754559, | |
| "eval_loss": 1.634997844696045, | |
| "eval_runtime": 1.7494, | |
| "eval_samples_per_second": 273.804, | |
| "eval_steps_per_second": 2.286, | |
| "step": 1787 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 4.942130710236746e-05, | |
| "loss": 1.7699, | |
| "step": 3574 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.666442067435919, | |
| "eval_loss": 1.5847446918487549, | |
| "eval_runtime": 1.6443, | |
| "eval_samples_per_second": 291.312, | |
| "eval_steps_per_second": 2.433, | |
| "step": 3574 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 4.912337445815272e-05, | |
| "loss": 1.7308, | |
| "step": 5361 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.6677533506088217, | |
| "eval_loss": 1.5856640338897705, | |
| "eval_runtime": 1.5899, | |
| "eval_samples_per_second": 301.279, | |
| "eval_steps_per_second": 2.516, | |
| "step": 5361 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.882544181393798e-05, | |
| "loss": 1.7062, | |
| "step": 7148 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.6683528823169714, | |
| "eval_loss": 1.5678603649139404, | |
| "eval_runtime": 1.7076, | |
| "eval_samples_per_second": 280.506, | |
| "eval_steps_per_second": 2.342, | |
| "step": 7148 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 4.852750916972325e-05, | |
| "loss": 1.6858, | |
| "step": 8935 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.6689400715563506, | |
| "eval_loss": 1.557257056236267, | |
| "eval_runtime": 1.6041, | |
| "eval_samples_per_second": 298.603, | |
| "eval_steps_per_second": 2.494, | |
| "step": 8935 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.822974324774925e-05, | |
| "loss": 1.6684, | |
| "step": 10722 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.6686847832152224, | |
| "eval_loss": 1.5590558052062988, | |
| "eval_runtime": 1.6561, | |
| "eval_samples_per_second": 289.241, | |
| "eval_steps_per_second": 2.415, | |
| "step": 10722 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 4.793181060353452e-05, | |
| "loss": 1.6545, | |
| "step": 12509 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.6756023841134431, | |
| "eval_loss": 1.525283694267273, | |
| "eval_runtime": 1.6268, | |
| "eval_samples_per_second": 294.451, | |
| "eval_steps_per_second": 2.459, | |
| "step": 12509 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 4.763387795931978e-05, | |
| "loss": 1.6438, | |
| "step": 14296 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.6748053099797688, | |
| "eval_loss": 1.5303529500961304, | |
| "eval_runtime": 1.6169, | |
| "eval_samples_per_second": 296.24, | |
| "eval_steps_per_second": 2.474, | |
| "step": 14296 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 4.7336112037345786e-05, | |
| "loss": 1.631, | |
| "step": 16083 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.6805022280765674, | |
| "eval_loss": 1.4976379871368408, | |
| "eval_runtime": 1.865, | |
| "eval_samples_per_second": 256.834, | |
| "eval_steps_per_second": 2.145, | |
| "step": 16083 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 4.7038179393131046e-05, | |
| "loss": 1.6236, | |
| "step": 17870 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.677310686482661, | |
| "eval_loss": 1.5153287649154663, | |
| "eval_runtime": 1.6084, | |
| "eval_samples_per_second": 297.811, | |
| "eval_steps_per_second": 2.487, | |
| "step": 17870 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 4.6740413471157055e-05, | |
| "loss": 1.613, | |
| "step": 19657 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.6785895056521005, | |
| "eval_loss": 1.5010405778884888, | |
| "eval_runtime": 1.613, | |
| "eval_samples_per_second": 296.958, | |
| "eval_steps_per_second": 2.48, | |
| "step": 19657 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 4.6442480826942315e-05, | |
| "loss": 1.6046, | |
| "step": 21444 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.6817956622261367, | |
| "eval_loss": 1.5068795680999756, | |
| "eval_runtime": 1.617, | |
| "eval_samples_per_second": 296.234, | |
| "eval_steps_per_second": 2.474, | |
| "step": 21444 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 4.6144714904968324e-05, | |
| "loss": 1.5963, | |
| "step": 23231 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.6804745455575061, | |
| "eval_loss": 1.4795995950698853, | |
| "eval_runtime": 1.5836, | |
| "eval_samples_per_second": 302.481, | |
| "eval_steps_per_second": 2.526, | |
| "step": 23231 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 4.5846948982994333e-05, | |
| "loss": 1.5906, | |
| "step": 25018 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.6809435655783687, | |
| "eval_loss": 1.485795497894287, | |
| "eval_runtime": 1.6062, | |
| "eval_samples_per_second": 298.221, | |
| "eval_steps_per_second": 2.49, | |
| "step": 25018 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 4.554918306102034e-05, | |
| "loss": 1.5833, | |
| "step": 26805 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.6805767364480798, | |
| "eval_loss": 1.496237874031067, | |
| "eval_runtime": 1.5896, | |
| "eval_samples_per_second": 301.324, | |
| "eval_steps_per_second": 2.516, | |
| "step": 26805 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 4.52512504168056e-05, | |
| "loss": 1.5771, | |
| "step": 28592 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.6826146494145264, | |
| "eval_loss": 1.4748649597167969, | |
| "eval_runtime": 1.5864, | |
| "eval_samples_per_second": 301.949, | |
| "eval_steps_per_second": 2.521, | |
| "step": 28592 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 4.495365121707236e-05, | |
| "loss": 1.5703, | |
| "step": 30379 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.6873812451100928, | |
| "eval_loss": 1.4724414348602295, | |
| "eval_runtime": 1.6157, | |
| "eval_samples_per_second": 296.46, | |
| "eval_steps_per_second": 2.476, | |
| "step": 30379 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 4.465571857285762e-05, | |
| "loss": 1.5663, | |
| "step": 32166 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.6826915033044254, | |
| "eval_loss": 1.4945769309997559, | |
| "eval_runtime": 1.6046, | |
| "eval_samples_per_second": 298.512, | |
| "eval_steps_per_second": 2.493, | |
| "step": 32166 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 4.435795265088363e-05, | |
| "loss": 1.5614, | |
| "step": 33953 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.6798307475317349, | |
| "eval_loss": 1.493360161781311, | |
| "eval_runtime": 1.5976, | |
| "eval_samples_per_second": 299.828, | |
| "eval_steps_per_second": 2.504, | |
| "step": 33953 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 4.406002000666889e-05, | |
| "loss": 1.5558, | |
| "step": 35740 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.6893048578564813, | |
| "eval_loss": 1.4512126445770264, | |
| "eval_runtime": 1.5875, | |
| "eval_samples_per_second": 301.731, | |
| "eval_steps_per_second": 2.52, | |
| "step": 35740 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "learning_rate": 4.37622540846949e-05, | |
| "loss": 1.5508, | |
| "step": 37527 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.6920911905432029, | |
| "eval_loss": 1.4417309761047363, | |
| "eval_runtime": 1.5842, | |
| "eval_samples_per_second": 302.355, | |
| "eval_steps_per_second": 2.525, | |
| "step": 37527 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "learning_rate": 4.346448816272091e-05, | |
| "loss": 1.5466, | |
| "step": 39314 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.683659548403263, | |
| "eval_loss": 1.4744044542312622, | |
| "eval_runtime": 1.688, | |
| "eval_samples_per_second": 283.775, | |
| "eval_steps_per_second": 2.37, | |
| "step": 39314 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "learning_rate": 4.316672224074692e-05, | |
| "loss": 1.5427, | |
| "step": 41101 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.6903853118992561, | |
| "eval_loss": 1.4530385732650757, | |
| "eval_runtime": 1.5701, | |
| "eval_samples_per_second": 305.072, | |
| "eval_steps_per_second": 2.548, | |
| "step": 41101 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 4.286878959653218e-05, | |
| "loss": 1.5382, | |
| "step": 42888 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.6900174638048561, | |
| "eval_loss": 1.4377799034118652, | |
| "eval_runtime": 1.5785, | |
| "eval_samples_per_second": 303.458, | |
| "eval_steps_per_second": 2.534, | |
| "step": 42888 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 4.257119039679893e-05, | |
| "loss": 1.5342, | |
| "step": 44675 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.6820495514497034, | |
| "eval_loss": 1.4731613397598267, | |
| "eval_runtime": 1.5702, | |
| "eval_samples_per_second": 305.059, | |
| "eval_steps_per_second": 2.547, | |
| "step": 44675 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "learning_rate": 4.2273257752584196e-05, | |
| "loss": 1.5293, | |
| "step": 46462 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.6865246225483279, | |
| "eval_loss": 1.460905909538269, | |
| "eval_runtime": 1.5669, | |
| "eval_samples_per_second": 305.693, | |
| "eval_steps_per_second": 2.553, | |
| "step": 46462 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "learning_rate": 4.1975491830610205e-05, | |
| "loss": 1.5259, | |
| "step": 48249 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.6942026931254429, | |
| "eval_loss": 1.4399933815002441, | |
| "eval_runtime": 1.5672, | |
| "eval_samples_per_second": 305.645, | |
| "eval_steps_per_second": 2.552, | |
| "step": 48249 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 4.1677559186395465e-05, | |
| "loss": 1.5223, | |
| "step": 50036 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.6879446584741712, | |
| "eval_loss": 1.458624243736267, | |
| "eval_runtime": 1.6351, | |
| "eval_samples_per_second": 292.944, | |
| "eval_steps_per_second": 2.446, | |
| "step": 50036 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "learning_rate": 4.1379793264421474e-05, | |
| "loss": 1.5197, | |
| "step": 51823 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.6906005955390753, | |
| "eval_loss": 1.437148094177246, | |
| "eval_runtime": 1.5725, | |
| "eval_samples_per_second": 304.606, | |
| "eval_steps_per_second": 2.544, | |
| "step": 51823 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 4.1082194064688226e-05, | |
| "loss": 1.5161, | |
| "step": 53610 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.6908153728511145, | |
| "eval_loss": 1.4334877729415894, | |
| "eval_runtime": 1.5744, | |
| "eval_samples_per_second": 304.247, | |
| "eval_steps_per_second": 2.541, | |
| "step": 53610 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "learning_rate": 4.078426142047349e-05, | |
| "loss": 1.5126, | |
| "step": 55397 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.6977723406071297, | |
| "eval_loss": 1.4158803224563599, | |
| "eval_runtime": 1.576, | |
| "eval_samples_per_second": 303.927, | |
| "eval_steps_per_second": 2.538, | |
| "step": 55397 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "learning_rate": 4.048632877625875e-05, | |
| "loss": 1.5087, | |
| "step": 57184 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.6858260773724236, | |
| "eval_loss": 1.4411636590957642, | |
| "eval_runtime": 1.6849, | |
| "eval_samples_per_second": 284.296, | |
| "eval_steps_per_second": 2.374, | |
| "step": 57184 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "learning_rate": 4.018856285428476e-05, | |
| "loss": 1.5061, | |
| "step": 58971 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.6957515878616796, | |
| "eval_loss": 1.418090581893921, | |
| "eval_runtime": 1.5743, | |
| "eval_samples_per_second": 304.26, | |
| "eval_steps_per_second": 2.541, | |
| "step": 58971 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "learning_rate": 3.989079693231077e-05, | |
| "loss": 1.5035, | |
| "step": 60758 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.6902565822572531, | |
| "eval_loss": 1.4357043504714966, | |
| "eval_runtime": 1.5776, | |
| "eval_samples_per_second": 303.629, | |
| "eval_steps_per_second": 2.536, | |
| "step": 60758 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "learning_rate": 3.959319773257753e-05, | |
| "loss": 1.5011, | |
| "step": 62545 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.6913778077647522, | |
| "eval_loss": 1.4147114753723145, | |
| "eval_runtime": 1.7484, | |
| "eval_samples_per_second": 273.959, | |
| "eval_steps_per_second": 2.288, | |
| "step": 62545 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "learning_rate": 3.929526508836279e-05, | |
| "loss": 1.4967, | |
| "step": 64332 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.6931245246880545, | |
| "eval_loss": 1.4251492023468018, | |
| "eval_runtime": 1.567, | |
| "eval_samples_per_second": 305.681, | |
| "eval_steps_per_second": 2.553, | |
| "step": 64332 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "learning_rate": 3.89974991663888e-05, | |
| "loss": 1.4954, | |
| "step": 66119 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.6909720283624589, | |
| "eval_loss": 1.4366341829299927, | |
| "eval_runtime": 1.6092, | |
| "eval_samples_per_second": 297.654, | |
| "eval_steps_per_second": 2.486, | |
| "step": 66119 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "learning_rate": 3.869989996665556e-05, | |
| "loss": 1.4925, | |
| "step": 67906 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.6896388757610297, | |
| "eval_loss": 1.4488193988800049, | |
| "eval_runtime": 1.6299, | |
| "eval_samples_per_second": 293.876, | |
| "eval_steps_per_second": 2.454, | |
| "step": 67906 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "learning_rate": 3.840196732244081e-05, | |
| "loss": 1.4889, | |
| "step": 69693 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.6906871760575155, | |
| "eval_loss": 1.4335614442825317, | |
| "eval_runtime": 1.5829, | |
| "eval_samples_per_second": 302.612, | |
| "eval_steps_per_second": 2.527, | |
| "step": 69693 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 3.810403467822608e-05, | |
| "loss": 1.4866, | |
| "step": 71480 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.6944786305661221, | |
| "eval_loss": 1.4226477146148682, | |
| "eval_runtime": 1.5748, | |
| "eval_samples_per_second": 304.158, | |
| "eval_steps_per_second": 2.54, | |
| "step": 71480 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "learning_rate": 3.7806268756252086e-05, | |
| "loss": 1.4838, | |
| "step": 73267 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.6950605409075478, | |
| "eval_loss": 1.4210412502288818, | |
| "eval_runtime": 1.6183, | |
| "eval_samples_per_second": 295.996, | |
| "eval_steps_per_second": 2.472, | |
| "step": 73267 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "learning_rate": 3.7508502834278095e-05, | |
| "loss": 1.4821, | |
| "step": 75054 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.6944428883535937, | |
| "eval_loss": 1.4080859422683716, | |
| "eval_runtime": 1.7239, | |
| "eval_samples_per_second": 277.863, | |
| "eval_steps_per_second": 2.32, | |
| "step": 75054 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "learning_rate": 3.72107369123041e-05, | |
| "loss": 1.4792, | |
| "step": 76841 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.6895113064278363, | |
| "eval_loss": 1.4496194124221802, | |
| "eval_runtime": 1.6266, | |
| "eval_samples_per_second": 294.479, | |
| "eval_steps_per_second": 2.459, | |
| "step": 76841 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "learning_rate": 3.691297099033011e-05, | |
| "loss": 1.4778, | |
| "step": 78628 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.6925052337752966, | |
| "eval_loss": 1.4263415336608887, | |
| "eval_runtime": 1.5801, | |
| "eval_samples_per_second": 303.146, | |
| "eval_steps_per_second": 2.531, | |
| "step": 78628 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "learning_rate": 3.6615038346115374e-05, | |
| "loss": 1.4754, | |
| "step": 80415 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.6981779024625238, | |
| "eval_loss": 1.3994964361190796, | |
| "eval_runtime": 1.5981, | |
| "eval_samples_per_second": 299.73, | |
| "eval_steps_per_second": 2.503, | |
| "step": 80415 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "learning_rate": 3.631727242414138e-05, | |
| "loss": 1.4736, | |
| "step": 82202 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.6992426773582804, | |
| "eval_loss": 1.3957608938217163, | |
| "eval_runtime": 1.5875, | |
| "eval_samples_per_second": 301.728, | |
| "eval_steps_per_second": 2.52, | |
| "step": 82202 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "learning_rate": 3.6019506502167385e-05, | |
| "loss": 1.4702, | |
| "step": 83989 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.6988620438365379, | |
| "eval_loss": 1.4073089361190796, | |
| "eval_runtime": 1.5808, | |
| "eval_samples_per_second": 303.008, | |
| "eval_steps_per_second": 2.53, | |
| "step": 83989 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "learning_rate": 3.572157385795265e-05, | |
| "loss": 1.4683, | |
| "step": 85776 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.6995880128675434, | |
| "eval_loss": 1.3917019367218018, | |
| "eval_runtime": 1.5795, | |
| "eval_samples_per_second": 303.265, | |
| "eval_steps_per_second": 2.532, | |
| "step": 85776 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "learning_rate": 3.5423974658219404e-05, | |
| "loss": 1.4663, | |
| "step": 87563 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.6956227054504377, | |
| "eval_loss": 1.4108972549438477, | |
| "eval_runtime": 1.5763, | |
| "eval_samples_per_second": 303.882, | |
| "eval_steps_per_second": 2.538, | |
| "step": 87563 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 3.512604201400467e-05, | |
| "loss": 1.4648, | |
| "step": 89350 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.6990693739424704, | |
| "eval_loss": 1.4003111124038696, | |
| "eval_runtime": 1.5784, | |
| "eval_samples_per_second": 303.472, | |
| "eval_steps_per_second": 2.534, | |
| "step": 89350 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "learning_rate": 3.482810936978993e-05, | |
| "loss": 1.4619, | |
| "step": 91137 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.7039692846253741, | |
| "eval_loss": 1.3846591711044312, | |
| "eval_runtime": 1.5968, | |
| "eval_samples_per_second": 299.97, | |
| "eval_steps_per_second": 2.505, | |
| "step": 91137 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "learning_rate": 3.453034344781594e-05, | |
| "loss": 1.4599, | |
| "step": 92924 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.6936358731150427, | |
| "eval_loss": 1.432299256324768, | |
| "eval_runtime": 1.5811, | |
| "eval_samples_per_second": 302.963, | |
| "eval_steps_per_second": 2.53, | |
| "step": 92924 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "learning_rate": 3.423257752584195e-05, | |
| "loss": 1.4596, | |
| "step": 94711 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.6986458829796182, | |
| "eval_loss": 1.3935346603393555, | |
| "eval_runtime": 1.6107, | |
| "eval_samples_per_second": 297.395, | |
| "eval_steps_per_second": 2.483, | |
| "step": 94711 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "learning_rate": 3.393481160386796e-05, | |
| "loss": 1.4567, | |
| "step": 96498 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.6973647322680123, | |
| "eval_loss": 1.4121975898742676, | |
| "eval_runtime": 1.5718, | |
| "eval_samples_per_second": 304.748, | |
| "eval_steps_per_second": 2.545, | |
| "step": 96498 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "learning_rate": 3.363704568189397e-05, | |
| "loss": 1.455, | |
| "step": 98285 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.697701760770372, | |
| "eval_loss": 1.3974732160568237, | |
| "eval_runtime": 1.5964, | |
| "eval_samples_per_second": 300.059, | |
| "eval_steps_per_second": 2.506, | |
| "step": 98285 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "learning_rate": 3.333927975991997e-05, | |
| "loss": 1.4533, | |
| "step": 100072 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.7003512716032037, | |
| "eval_loss": 1.3907233476638794, | |
| "eval_runtime": 1.5952, | |
| "eval_samples_per_second": 300.282, | |
| "eval_steps_per_second": 2.508, | |
| "step": 100072 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "learning_rate": 3.3041680560186735e-05, | |
| "loss": 1.4513, | |
| "step": 101859 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.6997069085833915, | |
| "eval_loss": 1.3957313299179077, | |
| "eval_runtime": 1.5802, | |
| "eval_samples_per_second": 303.121, | |
| "eval_steps_per_second": 2.531, | |
| "step": 101859 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "learning_rate": 3.274374791597199e-05, | |
| "loss": 1.45, | |
| "step": 103646 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.7000896509217236, | |
| "eval_loss": 1.390682578086853, | |
| "eval_runtime": 1.6316, | |
| "eval_samples_per_second": 293.58, | |
| "eval_steps_per_second": 2.452, | |
| "step": 103646 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "learning_rate": 3.2445815271757255e-05, | |
| "loss": 1.4466, | |
| "step": 105433 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.698792492819097, | |
| "eval_loss": 1.4062516689300537, | |
| "eval_runtime": 1.5938, | |
| "eval_samples_per_second": 300.532, | |
| "eval_steps_per_second": 2.51, | |
| "step": 105433 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "learning_rate": 3.214821607202401e-05, | |
| "loss": 1.4455, | |
| "step": 107220 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.7036078889537957, | |
| "eval_loss": 1.3599776029586792, | |
| "eval_runtime": 1.5863, | |
| "eval_samples_per_second": 301.968, | |
| "eval_steps_per_second": 2.522, | |
| "step": 107220 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "learning_rate": 3.1850283427809266e-05, | |
| "loss": 1.4439, | |
| "step": 109007 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_accuracy": 0.7015180371947121, | |
| "eval_loss": 1.3940563201904297, | |
| "eval_runtime": 1.5866, | |
| "eval_samples_per_second": 301.902, | |
| "eval_steps_per_second": 2.521, | |
| "step": 109007 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "learning_rate": 3.155235078359453e-05, | |
| "loss": 1.4432, | |
| "step": 110794 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.7016475844736108, | |
| "eval_loss": 1.3854174613952637, | |
| "eval_runtime": 1.5895, | |
| "eval_samples_per_second": 301.358, | |
| "eval_steps_per_second": 2.517, | |
| "step": 110794 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "learning_rate": 3.125458486162054e-05, | |
| "loss": 1.4404, | |
| "step": 112581 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_accuracy": 0.6972722913316973, | |
| "eval_loss": 1.4080028533935547, | |
| "eval_runtime": 1.588, | |
| "eval_samples_per_second": 301.645, | |
| "eval_steps_per_second": 2.519, | |
| "step": 112581 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "learning_rate": 3.09566522174058e-05, | |
| "loss": 1.4397, | |
| "step": 114368 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.7010520409594614, | |
| "eval_loss": 1.3923581838607788, | |
| "eval_runtime": 1.6035, | |
| "eval_samples_per_second": 298.723, | |
| "eval_steps_per_second": 2.495, | |
| "step": 114368 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "learning_rate": 3.0659053017672554e-05, | |
| "loss": 1.4366, | |
| "step": 116155 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_accuracy": 0.7049133849337983, | |
| "eval_loss": 1.3872087001800537, | |
| "eval_runtime": 1.5917, | |
| "eval_samples_per_second": 300.927, | |
| "eval_steps_per_second": 2.513, | |
| "step": 116155 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "learning_rate": 3.0361287095698566e-05, | |
| "loss": 1.4358, | |
| "step": 117942 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.7010343677010343, | |
| "eval_loss": 1.3924205303192139, | |
| "eval_runtime": 1.5814, | |
| "eval_samples_per_second": 302.891, | |
| "eval_steps_per_second": 2.529, | |
| "step": 117942 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "learning_rate": 3.0063354451483826e-05, | |
| "loss": 1.4339, | |
| "step": 119729 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_accuracy": 0.6988593369019926, | |
| "eval_loss": 1.3895306587219238, | |
| "eval_runtime": 1.7118, | |
| "eval_samples_per_second": 279.814, | |
| "eval_steps_per_second": 2.337, | |
| "step": 119729 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "learning_rate": 2.9765588529509835e-05, | |
| "loss": 1.4329, | |
| "step": 121516 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.7001914091088217, | |
| "eval_loss": 1.4007033109664917, | |
| "eval_runtime": 1.5846, | |
| "eval_samples_per_second": 302.287, | |
| "eval_steps_per_second": 2.524, | |
| "step": 121516 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "learning_rate": 2.9467822607535845e-05, | |
| "loss": 1.4319, | |
| "step": 123303 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_accuracy": 0.7047012042076765, | |
| "eval_loss": 1.3672277927398682, | |
| "eval_runtime": 1.6189, | |
| "eval_samples_per_second": 295.88, | |
| "eval_steps_per_second": 2.471, | |
| "step": 123303 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "learning_rate": 2.9169889963321108e-05, | |
| "loss": 1.4287, | |
| "step": 125090 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.7020639054580078, | |
| "eval_loss": 1.3891570568084717, | |
| "eval_runtime": 1.6012, | |
| "eval_samples_per_second": 299.158, | |
| "eval_steps_per_second": 2.498, | |
| "step": 125090 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "learning_rate": 2.8872290763587863e-05, | |
| "loss": 1.4284, | |
| "step": 126877 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_accuracy": 0.7016447644932612, | |
| "eval_loss": 1.367444396018982, | |
| "eval_runtime": 1.5982, | |
| "eval_samples_per_second": 299.72, | |
| "eval_steps_per_second": 2.503, | |
| "step": 126877 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "learning_rate": 2.8574358119373123e-05, | |
| "loss": 1.4265, | |
| "step": 128664 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.6961661071458798, | |
| "eval_loss": 1.3982675075531006, | |
| "eval_runtime": 1.5745, | |
| "eval_samples_per_second": 304.228, | |
| "eval_steps_per_second": 2.541, | |
| "step": 128664 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "learning_rate": 2.8276592197399132e-05, | |
| "loss": 1.4254, | |
| "step": 130451 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_accuracy": 0.700606782352274, | |
| "eval_loss": 1.3664897680282593, | |
| "eval_runtime": 1.5897, | |
| "eval_samples_per_second": 301.308, | |
| "eval_steps_per_second": 2.516, | |
| "step": 130451 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "learning_rate": 2.797882627542514e-05, | |
| "loss": 1.4231, | |
| "step": 132238 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_accuracy": 0.7003467887363019, | |
| "eval_loss": 1.3851745128631592, | |
| "eval_runtime": 1.602, | |
| "eval_samples_per_second": 299.009, | |
| "eval_steps_per_second": 2.497, | |
| "step": 132238 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "learning_rate": 2.76808936312104e-05, | |
| "loss": 1.4228, | |
| "step": 134025 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_accuracy": 0.6945481910920341, | |
| "eval_loss": 1.4327718019485474, | |
| "eval_runtime": 1.6912, | |
| "eval_samples_per_second": 283.237, | |
| "eval_steps_per_second": 2.365, | |
| "step": 134025 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "learning_rate": 2.738312770923641e-05, | |
| "loss": 1.4217, | |
| "step": 135812 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_accuracy": 0.7030551729953062, | |
| "eval_loss": 1.3831229209899902, | |
| "eval_runtime": 1.5761, | |
| "eval_samples_per_second": 303.914, | |
| "eval_steps_per_second": 2.538, | |
| "step": 135812 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "learning_rate": 2.708536178726242e-05, | |
| "loss": 1.4198, | |
| "step": 137599 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_accuracy": 0.7017066534751423, | |
| "eval_loss": 1.3897149562835693, | |
| "eval_runtime": 1.5767, | |
| "eval_samples_per_second": 303.804, | |
| "eval_steps_per_second": 2.537, | |
| "step": 137599 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "learning_rate": 2.6787429143047683e-05, | |
| "loss": 1.4183, | |
| "step": 139386 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_accuracy": 0.7027269918836184, | |
| "eval_loss": 1.3789587020874023, | |
| "eval_runtime": 1.5653, | |
| "eval_samples_per_second": 306.009, | |
| "eval_steps_per_second": 2.555, | |
| "step": 139386 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "learning_rate": 2.6489496498832943e-05, | |
| "loss": 1.417, | |
| "step": 141173 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_accuracy": 0.7063395950094348, | |
| "eval_loss": 1.3697491884231567, | |
| "eval_runtime": 1.5854, | |
| "eval_samples_per_second": 302.136, | |
| "eval_steps_per_second": 2.523, | |
| "step": 141173 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "learning_rate": 2.6191730576858952e-05, | |
| "loss": 1.4179, | |
| "step": 142960 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_accuracy": 0.700801300011207, | |
| "eval_loss": 1.3804936408996582, | |
| "eval_runtime": 1.5689, | |
| "eval_samples_per_second": 305.304, | |
| "eval_steps_per_second": 2.55, | |
| "step": 142960 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "learning_rate": 2.589396465488496e-05, | |
| "loss": 1.414, | |
| "step": 144747 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_accuracy": 0.7050930684024209, | |
| "eval_loss": 1.3579356670379639, | |
| "eval_runtime": 1.5646, | |
| "eval_samples_per_second": 306.14, | |
| "eval_steps_per_second": 2.556, | |
| "step": 144747 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "learning_rate": 2.559619873291097e-05, | |
| "loss": 1.4132, | |
| "step": 146534 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_accuracy": 0.7054125504382913, | |
| "eval_loss": 1.3726812601089478, | |
| "eval_runtime": 1.5755, | |
| "eval_samples_per_second": 304.04, | |
| "eval_steps_per_second": 2.539, | |
| "step": 146534 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "learning_rate": 2.5298599533177726e-05, | |
| "loss": 1.4112, | |
| "step": 148321 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_accuracy": 0.7013713965855024, | |
| "eval_loss": 1.3762907981872559, | |
| "eval_runtime": 1.5766, | |
| "eval_samples_per_second": 303.809, | |
| "eval_steps_per_second": 2.537, | |
| "step": 148321 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "learning_rate": 2.5000666888962985e-05, | |
| "loss": 1.412, | |
| "step": 150108 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_accuracy": 0.7051213694401571, | |
| "eval_loss": 1.3806371688842773, | |
| "eval_runtime": 1.5857, | |
| "eval_samples_per_second": 302.069, | |
| "eval_steps_per_second": 2.523, | |
| "step": 150108 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "learning_rate": 2.4702734244748252e-05, | |
| "loss": 1.4103, | |
| "step": 151895 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_accuracy": 0.7021642142599828, | |
| "eval_loss": 1.3889108896255493, | |
| "eval_runtime": 1.5884, | |
| "eval_samples_per_second": 301.569, | |
| "eval_steps_per_second": 2.518, | |
| "step": 151895 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "learning_rate": 2.4405135045015007e-05, | |
| "loss": 1.4082, | |
| "step": 153682 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_accuracy": 0.6992571829011913, | |
| "eval_loss": 1.3886325359344482, | |
| "eval_runtime": 1.5712, | |
| "eval_samples_per_second": 304.856, | |
| "eval_steps_per_second": 2.546, | |
| "step": 153682 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "learning_rate": 2.4107369123041016e-05, | |
| "loss": 1.4068, | |
| "step": 155469 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_accuracy": 0.7025410225589132, | |
| "eval_loss": 1.3720707893371582, | |
| "eval_runtime": 1.5911, | |
| "eval_samples_per_second": 301.051, | |
| "eval_steps_per_second": 2.514, | |
| "step": 155469 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "learning_rate": 2.3809436478826276e-05, | |
| "loss": 1.4068, | |
| "step": 157256 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_accuracy": 0.7049852548799326, | |
| "eval_loss": 1.3589400053024292, | |
| "eval_runtime": 1.5763, | |
| "eval_samples_per_second": 303.874, | |
| "eval_steps_per_second": 2.538, | |
| "step": 157256 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "learning_rate": 2.351150383461154e-05, | |
| "loss": 1.4043, | |
| "step": 159043 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_accuracy": 0.7043347949159128, | |
| "eval_loss": 1.359857439994812, | |
| "eval_runtime": 1.5796, | |
| "eval_samples_per_second": 303.245, | |
| "eval_steps_per_second": 2.532, | |
| "step": 159043 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "learning_rate": 2.321373791263755e-05, | |
| "loss": 1.4042, | |
| "step": 160830 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_accuracy": 0.7055383080164098, | |
| "eval_loss": 1.3674854040145874, | |
| "eval_runtime": 1.7188, | |
| "eval_samples_per_second": 278.687, | |
| "eval_steps_per_second": 2.327, | |
| "step": 160830 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "learning_rate": 2.2915971990663558e-05, | |
| "loss": 1.4033, | |
| "step": 162617 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_accuracy": 0.7031184095829935, | |
| "eval_loss": 1.3719748258590698, | |
| "eval_runtime": 1.5775, | |
| "eval_samples_per_second": 303.654, | |
| "eval_steps_per_second": 2.536, | |
| "step": 162617 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "learning_rate": 2.2618206068689564e-05, | |
| "loss": 1.402, | |
| "step": 164404 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_accuracy": 0.7067319874989442, | |
| "eval_loss": 1.3505655527114868, | |
| "eval_runtime": 1.5905, | |
| "eval_samples_per_second": 301.16, | |
| "eval_steps_per_second": 2.515, | |
| "step": 164404 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "learning_rate": 2.2320273424474827e-05, | |
| "loss": 1.4004, | |
| "step": 166191 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_accuracy": 0.701749972045175, | |
| "eval_loss": 1.3833116292953491, | |
| "eval_runtime": 1.5756, | |
| "eval_samples_per_second": 304.01, | |
| "eval_steps_per_second": 2.539, | |
| "step": 166191 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "learning_rate": 2.2022340780260087e-05, | |
| "loss": 1.4001, | |
| "step": 167978 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_accuracy": 0.7020838620534078, | |
| "eval_loss": 1.3734411001205444, | |
| "eval_runtime": 1.5691, | |
| "eval_samples_per_second": 305.274, | |
| "eval_steps_per_second": 2.549, | |
| "step": 167978 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "learning_rate": 2.1724574858286096e-05, | |
| "loss": 1.398, | |
| "step": 169765 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_accuracy": 0.7036638236377547, | |
| "eval_loss": 1.3791979551315308, | |
| "eval_runtime": 1.5625, | |
| "eval_samples_per_second": 306.555, | |
| "eval_steps_per_second": 2.56, | |
| "step": 169765 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "learning_rate": 2.1426975658552855e-05, | |
| "loss": 1.3983, | |
| "step": 171552 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_accuracy": 0.7049873914261698, | |
| "eval_loss": 1.3675692081451416, | |
| "eval_runtime": 1.5747, | |
| "eval_samples_per_second": 304.183, | |
| "eval_steps_per_second": 2.54, | |
| "step": 171552 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "learning_rate": 2.112904301433811e-05, | |
| "loss": 1.3966, | |
| "step": 173339 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_accuracy": 0.7027283114566787, | |
| "eval_loss": 1.3888317346572876, | |
| "eval_runtime": 1.5809, | |
| "eval_samples_per_second": 302.986, | |
| "eval_steps_per_second": 2.53, | |
| "step": 173339 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "learning_rate": 2.0831110370123374e-05, | |
| "loss": 1.3953, | |
| "step": 175126 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_accuracy": 0.7004118244386777, | |
| "eval_loss": 1.3927955627441406, | |
| "eval_runtime": 1.5702, | |
| "eval_samples_per_second": 305.058, | |
| "eval_steps_per_second": 2.547, | |
| "step": 175126 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "learning_rate": 2.0533344448149383e-05, | |
| "loss": 1.3934, | |
| "step": 176913 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_accuracy": 0.7010918253079508, | |
| "eval_loss": 1.382420301437378, | |
| "eval_runtime": 1.5875, | |
| "eval_samples_per_second": 301.726, | |
| "eval_steps_per_second": 2.52, | |
| "step": 176913 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "learning_rate": 2.0235578526175393e-05, | |
| "loss": 1.3928, | |
| "step": 178700 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_accuracy": 0.703971419076105, | |
| "eval_loss": 1.382891297340393, | |
| "eval_runtime": 1.5699, | |
| "eval_samples_per_second": 305.124, | |
| "eval_steps_per_second": 2.548, | |
| "step": 178700 | |
| }, | |
| { | |
| "epoch": 101.0, | |
| "learning_rate": 1.99378126042014e-05, | |
| "loss": 1.3919, | |
| "step": 180487 | |
| }, | |
| { | |
| "epoch": 101.0, | |
| "eval_accuracy": 0.7045689534721252, | |
| "eval_loss": 1.3534067869186401, | |
| "eval_runtime": 1.5763, | |
| "eval_samples_per_second": 303.883, | |
| "eval_steps_per_second": 2.538, | |
| "step": 180487 | |
| }, | |
| { | |
| "epoch": 102.0, | |
| "learning_rate": 1.9640213404468157e-05, | |
| "loss": 1.3902, | |
| "step": 182274 | |
| }, | |
| { | |
| "epoch": 102.0, | |
| "eval_accuracy": 0.7048191080299756, | |
| "eval_loss": 1.3559306859970093, | |
| "eval_runtime": 1.7782, | |
| "eval_samples_per_second": 269.367, | |
| "eval_steps_per_second": 2.249, | |
| "step": 182274 | |
| }, | |
| { | |
| "epoch": 103.0, | |
| "learning_rate": 1.934228076025342e-05, | |
| "loss": 1.3896, | |
| "step": 184061 | |
| }, | |
| { | |
| "epoch": 103.0, | |
| "eval_accuracy": 0.7044582060694371, | |
| "eval_loss": 1.3681745529174805, | |
| "eval_runtime": 1.5953, | |
| "eval_samples_per_second": 300.253, | |
| "eval_steps_per_second": 2.507, | |
| "step": 184061 | |
| }, | |
| { | |
| "epoch": 104.0, | |
| "learning_rate": 1.904451483827943e-05, | |
| "loss": 1.3895, | |
| "step": 185848 | |
| }, | |
| { | |
| "epoch": 104.0, | |
| "eval_accuracy": 0.7053175360772643, | |
| "eval_loss": 1.3642874956130981, | |
| "eval_runtime": 1.584, | |
| "eval_samples_per_second": 302.391, | |
| "eval_steps_per_second": 2.525, | |
| "step": 185848 | |
| }, | |
| { | |
| "epoch": 105.0, | |
| "learning_rate": 1.874658219406469e-05, | |
| "loss": 1.3884, | |
| "step": 187635 | |
| }, | |
| { | |
| "epoch": 105.0, | |
| "eval_accuracy": 0.7018311771061307, | |
| "eval_loss": 1.3854254484176636, | |
| "eval_runtime": 1.7105, | |
| "eval_samples_per_second": 280.037, | |
| "eval_steps_per_second": 2.339, | |
| "step": 187635 | |
| }, | |
| { | |
| "epoch": 106.0, | |
| "learning_rate": 1.8448816272090695e-05, | |
| "loss": 1.3878, | |
| "step": 189422 | |
| }, | |
| { | |
| "epoch": 106.0, | |
| "eval_accuracy": 0.7038266741699494, | |
| "eval_loss": 1.370182752609253, | |
| "eval_runtime": 1.5712, | |
| "eval_samples_per_second": 304.857, | |
| "eval_steps_per_second": 2.546, | |
| "step": 189422 | |
| }, | |
| { | |
| "epoch": 107.0, | |
| "learning_rate": 1.8151050350116704e-05, | |
| "loss": 1.3865, | |
| "step": 191209 | |
| }, | |
| { | |
| "epoch": 107.0, | |
| "eval_accuracy": 0.7055550824604729, | |
| "eval_loss": 1.3529911041259766, | |
| "eval_runtime": 1.587, | |
| "eval_samples_per_second": 301.822, | |
| "eval_steps_per_second": 2.52, | |
| "step": 191209 | |
| }, | |
| { | |
| "epoch": 108.0, | |
| "learning_rate": 1.7853284428142717e-05, | |
| "loss": 1.3842, | |
| "step": 192996 | |
| }, | |
| { | |
| "epoch": 108.0, | |
| "eval_accuracy": 0.7007661234155175, | |
| "eval_loss": 1.3804410696029663, | |
| "eval_runtime": 1.5953, | |
| "eval_samples_per_second": 300.25, | |
| "eval_steps_per_second": 2.507, | |
| "step": 192996 | |
| }, | |
| { | |
| "epoch": 109.0, | |
| "learning_rate": 1.7555351783927977e-05, | |
| "loss": 1.3836, | |
| "step": 194783 | |
| }, | |
| { | |
| "epoch": 109.0, | |
| "eval_accuracy": 0.7072856221792392, | |
| "eval_loss": 1.3507838249206543, | |
| "eval_runtime": 1.5928, | |
| "eval_samples_per_second": 300.728, | |
| "eval_steps_per_second": 2.511, | |
| "step": 194783 | |
| }, | |
| { | |
| "epoch": 110.0, | |
| "learning_rate": 1.7257585861953983e-05, | |
| "loss": 1.3831, | |
| "step": 196570 | |
| }, | |
| { | |
| "epoch": 110.0, | |
| "eval_accuracy": 0.7002392681210415, | |
| "eval_loss": 1.3821208477020264, | |
| "eval_runtime": 1.5673, | |
| "eval_samples_per_second": 305.62, | |
| "eval_steps_per_second": 2.552, | |
| "step": 196570 | |
| }, | |
| { | |
| "epoch": 111.0, | |
| "learning_rate": 1.6959819939979992e-05, | |
| "loss": 1.3828, | |
| "step": 198357 | |
| }, | |
| { | |
| "epoch": 111.0, | |
| "eval_accuracy": 0.7063221331514015, | |
| "eval_loss": 1.355231523513794, | |
| "eval_runtime": 1.5725, | |
| "eval_samples_per_second": 304.605, | |
| "eval_steps_per_second": 2.544, | |
| "step": 198357 | |
| }, | |
| { | |
| "epoch": 112.0, | |
| "learning_rate": 1.6662054018006005e-05, | |
| "loss": 1.382, | |
| "step": 200144 | |
| }, | |
| { | |
| "epoch": 112.0, | |
| "eval_accuracy": 0.7089512489136833, | |
| "eval_loss": 1.3567301034927368, | |
| "eval_runtime": 1.5868, | |
| "eval_samples_per_second": 301.856, | |
| "eval_steps_per_second": 2.521, | |
| "step": 200144 | |
| }, | |
| { | |
| "epoch": 113.0, | |
| "learning_rate": 1.6364288096032014e-05, | |
| "loss": 1.3806, | |
| "step": 201931 | |
| }, | |
| { | |
| "epoch": 113.0, | |
| "eval_accuracy": 0.7021602747892242, | |
| "eval_loss": 1.3915045261383057, | |
| "eval_runtime": 1.5651, | |
| "eval_samples_per_second": 306.042, | |
| "eval_steps_per_second": 2.556, | |
| "step": 201931 | |
| }, | |
| { | |
| "epoch": 114.0, | |
| "learning_rate": 1.6066355451817274e-05, | |
| "loss": 1.3802, | |
| "step": 203718 | |
| }, | |
| { | |
| "epoch": 114.0, | |
| "eval_accuracy": 0.7098393008175923, | |
| "eval_loss": 1.366058588027954, | |
| "eval_runtime": 1.5787, | |
| "eval_samples_per_second": 303.406, | |
| "eval_steps_per_second": 2.534, | |
| "step": 203718 | |
| }, | |
| { | |
| "epoch": 115.0, | |
| "learning_rate": 1.576858952984328e-05, | |
| "loss": 1.3789, | |
| "step": 205505 | |
| }, | |
| { | |
| "epoch": 115.0, | |
| "eval_accuracy": 0.7071270105379922, | |
| "eval_loss": 1.358585000038147, | |
| "eval_runtime": 1.5848, | |
| "eval_samples_per_second": 302.249, | |
| "eval_steps_per_second": 2.524, | |
| "step": 205505 | |
| }, | |
| { | |
| "epoch": 116.0, | |
| "learning_rate": 1.5470656885628543e-05, | |
| "loss": 1.3789, | |
| "step": 207292 | |
| }, | |
| { | |
| "epoch": 116.0, | |
| "eval_accuracy": 0.7049299719887955, | |
| "eval_loss": 1.3643481731414795, | |
| "eval_runtime": 1.5702, | |
| "eval_samples_per_second": 305.048, | |
| "eval_steps_per_second": 2.547, | |
| "step": 207292 | |
| }, | |
| { | |
| "epoch": 117.0, | |
| "learning_rate": 1.5172724241413804e-05, | |
| "loss": 1.3782, | |
| "step": 209079 | |
| }, | |
| { | |
| "epoch": 117.0, | |
| "eval_accuracy": 0.7037224045555275, | |
| "eval_loss": 1.3715710639953613, | |
| "eval_runtime": 1.5697, | |
| "eval_samples_per_second": 305.149, | |
| "eval_steps_per_second": 2.548, | |
| "step": 209079 | |
| }, | |
| { | |
| "epoch": 118.0, | |
| "learning_rate": 1.4874958319439813e-05, | |
| "loss": 1.3763, | |
| "step": 210866 | |
| }, | |
| { | |
| "epoch": 118.0, | |
| "eval_accuracy": 0.70765141977899, | |
| "eval_loss": 1.3476457595825195, | |
| "eval_runtime": 1.5964, | |
| "eval_samples_per_second": 300.046, | |
| "eval_steps_per_second": 2.506, | |
| "step": 210866 | |
| }, | |
| { | |
| "epoch": 119.0, | |
| "learning_rate": 1.4577192397465823e-05, | |
| "loss": 1.3762, | |
| "step": 212653 | |
| }, | |
| { | |
| "epoch": 119.0, | |
| "eval_accuracy": 0.7066520959426138, | |
| "eval_loss": 1.3518937826156616, | |
| "eval_runtime": 1.6463, | |
| "eval_samples_per_second": 290.954, | |
| "eval_steps_per_second": 2.43, | |
| "step": 212653 | |
| }, | |
| { | |
| "epoch": 120.0, | |
| "learning_rate": 1.427942647549183e-05, | |
| "loss": 1.3741, | |
| "step": 214440 | |
| }, | |
| { | |
| "epoch": 120.0, | |
| "eval_accuracy": 0.7027226737907122, | |
| "eval_loss": 1.3735955953598022, | |
| "eval_runtime": 1.5849, | |
| "eval_samples_per_second": 302.235, | |
| "eval_steps_per_second": 2.524, | |
| "step": 214440 | |
| }, | |
| { | |
| "epoch": 121.0, | |
| "learning_rate": 1.398166055351784e-05, | |
| "loss": 1.3741, | |
| "step": 216227 | |
| }, | |
| { | |
| "epoch": 121.0, | |
| "eval_accuracy": 0.7072822864813468, | |
| "eval_loss": 1.339490532875061, | |
| "eval_runtime": 1.5667, | |
| "eval_samples_per_second": 305.741, | |
| "eval_steps_per_second": 2.553, | |
| "step": 216227 | |
| }, | |
| { | |
| "epoch": 122.0, | |
| "learning_rate": 1.3684061353784596e-05, | |
| "loss": 1.3732, | |
| "step": 218014 | |
| }, | |
| { | |
| "epoch": 122.0, | |
| "eval_accuracy": 0.7020326111235202, | |
| "eval_loss": 1.3724454641342163, | |
| "eval_runtime": 1.7004, | |
| "eval_samples_per_second": 281.702, | |
| "eval_steps_per_second": 2.352, | |
| "step": 218014 | |
| }, | |
| { | |
| "epoch": 123.0, | |
| "learning_rate": 1.3386128709569856e-05, | |
| "loss": 1.3724, | |
| "step": 219801 | |
| }, | |
| { | |
| "epoch": 123.0, | |
| "eval_accuracy": 0.7025496548809691, | |
| "eval_loss": 1.37235689163208, | |
| "eval_runtime": 1.5713, | |
| "eval_samples_per_second": 304.85, | |
| "eval_steps_per_second": 2.546, | |
| "step": 219801 | |
| }, | |
| { | |
| "epoch": 124.0, | |
| "learning_rate": 1.3088362787595865e-05, | |
| "loss": 1.3715, | |
| "step": 221588 | |
| }, | |
| { | |
| "epoch": 124.0, | |
| "eval_accuracy": 0.7083146445391343, | |
| "eval_loss": 1.3571741580963135, | |
| "eval_runtime": 1.5874, | |
| "eval_samples_per_second": 301.751, | |
| "eval_steps_per_second": 2.52, | |
| "step": 221588 | |
| }, | |
| { | |
| "epoch": 125.0, | |
| "learning_rate": 1.2790430143381127e-05, | |
| "loss": 1.3713, | |
| "step": 223375 | |
| }, | |
| { | |
| "epoch": 125.0, | |
| "eval_accuracy": 0.7100663560638147, | |
| "eval_loss": 1.3430290222167969, | |
| "eval_runtime": 1.5682, | |
| "eval_samples_per_second": 305.439, | |
| "eval_steps_per_second": 2.551, | |
| "step": 223375 | |
| }, | |
| { | |
| "epoch": 126.0, | |
| "learning_rate": 1.2492497499166388e-05, | |
| "loss": 1.369, | |
| "step": 225162 | |
| }, | |
| { | |
| "epoch": 126.0, | |
| "eval_accuracy": 0.7103282312449283, | |
| "eval_loss": 1.3457125425338745, | |
| "eval_runtime": 1.7081, | |
| "eval_samples_per_second": 280.423, | |
| "eval_steps_per_second": 2.342, | |
| "step": 225162 | |
| }, | |
| { | |
| "epoch": 127.0, | |
| "learning_rate": 1.2194731577192398e-05, | |
| "loss": 1.3687, | |
| "step": 226949 | |
| }, | |
| { | |
| "epoch": 127.0, | |
| "eval_accuracy": 0.7112089514568553, | |
| "eval_loss": 1.3456733226776123, | |
| "eval_runtime": 1.5857, | |
| "eval_samples_per_second": 302.075, | |
| "eval_steps_per_second": 2.523, | |
| "step": 226949 | |
| }, | |
| { | |
| "epoch": 128.0, | |
| "learning_rate": 1.1896965655218407e-05, | |
| "loss": 1.3698, | |
| "step": 228736 | |
| }, | |
| { | |
| "epoch": 128.0, | |
| "eval_accuracy": 0.7024267451069125, | |
| "eval_loss": 1.3649426698684692, | |
| "eval_runtime": 1.5737, | |
| "eval_samples_per_second": 304.386, | |
| "eval_steps_per_second": 2.542, | |
| "step": 228736 | |
| }, | |
| { | |
| "epoch": 129.0, | |
| "learning_rate": 1.1599199733244414e-05, | |
| "loss": 1.3683, | |
| "step": 230523 | |
| }, | |
| { | |
| "epoch": 129.0, | |
| "eval_accuracy": 0.7105218474077428, | |
| "eval_loss": 1.3422349691390991, | |
| "eval_runtime": 1.5749, | |
| "eval_samples_per_second": 304.149, | |
| "eval_steps_per_second": 2.54, | |
| "step": 230523 | |
| }, | |
| { | |
| "epoch": 130.0, | |
| "learning_rate": 1.1301433811270425e-05, | |
| "loss": 1.3668, | |
| "step": 232310 | |
| }, | |
| { | |
| "epoch": 130.0, | |
| "eval_accuracy": 0.7058147358977235, | |
| "eval_loss": 1.3530675172805786, | |
| "eval_runtime": 1.5757, | |
| "eval_samples_per_second": 303.997, | |
| "eval_steps_per_second": 2.539, | |
| "step": 232310 | |
| }, | |
| { | |
| "epoch": 131.0, | |
| "learning_rate": 1.1003667889296433e-05, | |
| "loss": 1.3675, | |
| "step": 234097 | |
| }, | |
| { | |
| "epoch": 131.0, | |
| "eval_accuracy": 0.7058542882801976, | |
| "eval_loss": 1.3607447147369385, | |
| "eval_runtime": 1.5807, | |
| "eval_samples_per_second": 303.038, | |
| "eval_steps_per_second": 2.531, | |
| "step": 234097 | |
| }, | |
| { | |
| "epoch": 132.0, | |
| "learning_rate": 1.0705901967322442e-05, | |
| "loss": 1.3661, | |
| "step": 235884 | |
| }, | |
| { | |
| "epoch": 132.0, | |
| "eval_accuracy": 0.7062627163521837, | |
| "eval_loss": 1.3552587032318115, | |
| "eval_runtime": 1.5753, | |
| "eval_samples_per_second": 304.064, | |
| "eval_steps_per_second": 2.539, | |
| "step": 235884 | |
| }, | |
| { | |
| "epoch": 133.0, | |
| "learning_rate": 1.040813604534845e-05, | |
| "loss": 1.3642, | |
| "step": 237671 | |
| }, | |
| { | |
| "epoch": 133.0, | |
| "eval_accuracy": 0.7053641566603075, | |
| "eval_loss": 1.3540754318237305, | |
| "eval_runtime": 1.5925, | |
| "eval_samples_per_second": 300.778, | |
| "eval_steps_per_second": 2.512, | |
| "step": 237671 | |
| }, | |
| { | |
| "epoch": 134.0, | |
| "learning_rate": 1.0110203401133713e-05, | |
| "loss": 1.364, | |
| "step": 239458 | |
| }, | |
| { | |
| "epoch": 134.0, | |
| "eval_accuracy": 0.7079530276046304, | |
| "eval_loss": 1.3564157485961914, | |
| "eval_runtime": 1.7195, | |
| "eval_samples_per_second": 278.562, | |
| "eval_steps_per_second": 2.326, | |
| "step": 239458 | |
| }, | |
| { | |
| "epoch": 135.0, | |
| "learning_rate": 9.81243747915972e-06, | |
| "loss": 1.3635, | |
| "step": 241245 | |
| }, | |
| { | |
| "epoch": 135.0, | |
| "eval_accuracy": 0.7055403556771546, | |
| "eval_loss": 1.3633564710617065, | |
| "eval_runtime": 1.5788, | |
| "eval_samples_per_second": 303.389, | |
| "eval_steps_per_second": 2.534, | |
| "step": 241245 | |
| }, | |
| { | |
| "epoch": 136.0, | |
| "learning_rate": 9.51467155718573e-06, | |
| "loss": 1.3621, | |
| "step": 243032 | |
| }, | |
| { | |
| "epoch": 136.0, | |
| "eval_accuracy": 0.7042685476900772, | |
| "eval_loss": 1.3689273595809937, | |
| "eval_runtime": 1.5862, | |
| "eval_samples_per_second": 301.987, | |
| "eval_steps_per_second": 2.522, | |
| "step": 243032 | |
| }, | |
| { | |
| "epoch": 137.0, | |
| "learning_rate": 9.217072357452485e-06, | |
| "loss": 1.3623, | |
| "step": 244819 | |
| }, | |
| { | |
| "epoch": 137.0, | |
| "eval_accuracy": 0.7086510057673372, | |
| "eval_loss": 1.3668452501296997, | |
| "eval_runtime": 1.7126, | |
| "eval_samples_per_second": 279.697, | |
| "eval_steps_per_second": 2.336, | |
| "step": 244819 | |
| }, | |
| { | |
| "epoch": 138.0, | |
| "learning_rate": 8.919139713237746e-06, | |
| "loss": 1.3614, | |
| "step": 246606 | |
| }, | |
| { | |
| "epoch": 138.0, | |
| "eval_accuracy": 0.7061014196511074, | |
| "eval_loss": 1.3534598350524902, | |
| "eval_runtime": 1.5838, | |
| "eval_samples_per_second": 302.445, | |
| "eval_steps_per_second": 2.526, | |
| "step": 246606 | |
| }, | |
| { | |
| "epoch": 139.0, | |
| "learning_rate": 8.621373791263756e-06, | |
| "loss": 1.3614, | |
| "step": 248393 | |
| }, | |
| { | |
| "epoch": 139.0, | |
| "eval_accuracy": 0.7085629563319998, | |
| "eval_loss": 1.358819603919983, | |
| "eval_runtime": 1.606, | |
| "eval_samples_per_second": 298.26, | |
| "eval_steps_per_second": 2.491, | |
| "step": 248393 | |
| }, | |
| { | |
| "epoch": 140.0, | |
| "learning_rate": 8.323607869289763e-06, | |
| "loss": 1.3588, | |
| "step": 250180 | |
| }, | |
| { | |
| "epoch": 140.0, | |
| "eval_accuracy": 0.7090991475744103, | |
| "eval_loss": 1.3471907377243042, | |
| "eval_runtime": 1.5823, | |
| "eval_samples_per_second": 302.722, | |
| "eval_steps_per_second": 2.528, | |
| "step": 250180 | |
| }, | |
| { | |
| "epoch": 141.0, | |
| "learning_rate": 8.025841947315772e-06, | |
| "loss": 1.3598, | |
| "step": 251967 | |
| }, | |
| { | |
| "epoch": 141.0, | |
| "eval_accuracy": 0.7084796225037217, | |
| "eval_loss": 1.3424988985061646, | |
| "eval_runtime": 1.5825, | |
| "eval_samples_per_second": 302.692, | |
| "eval_steps_per_second": 2.528, | |
| "step": 251967 | |
| }, | |
| { | |
| "epoch": 142.0, | |
| "learning_rate": 7.728076025341782e-06, | |
| "loss": 1.3601, | |
| "step": 253754 | |
| }, | |
| { | |
| "epoch": 142.0, | |
| "eval_accuracy": 0.7098971286457155, | |
| "eval_loss": 1.3533294200897217, | |
| "eval_runtime": 1.7592, | |
| "eval_samples_per_second": 272.276, | |
| "eval_steps_per_second": 2.274, | |
| "step": 253754 | |
| }, | |
| { | |
| "epoch": 143.0, | |
| "learning_rate": 7.430143381127043e-06, | |
| "loss": 1.3585, | |
| "step": 255541 | |
| }, | |
| { | |
| "epoch": 143.0, | |
| "eval_accuracy": 0.711209661674058, | |
| "eval_loss": 1.329834222793579, | |
| "eval_runtime": 1.5914, | |
| "eval_samples_per_second": 300.99, | |
| "eval_steps_per_second": 2.513, | |
| "step": 255541 | |
| }, | |
| { | |
| "epoch": 144.0, | |
| "learning_rate": 7.132377459153051e-06, | |
| "loss": 1.3586, | |
| "step": 257328 | |
| }, | |
| { | |
| "epoch": 144.0, | |
| "eval_accuracy": 0.703638680447402, | |
| "eval_loss": 1.3582900762557983, | |
| "eval_runtime": 1.5993, | |
| "eval_samples_per_second": 299.511, | |
| "eval_steps_per_second": 2.501, | |
| "step": 257328 | |
| }, | |
| { | |
| "epoch": 145.0, | |
| "learning_rate": 6.83461153717906e-06, | |
| "loss": 1.3583, | |
| "step": 259115 | |
| }, | |
| { | |
| "epoch": 145.0, | |
| "eval_accuracy": 0.7081236721458124, | |
| "eval_loss": 1.3454816341400146, | |
| "eval_runtime": 1.6765, | |
| "eval_samples_per_second": 285.71, | |
| "eval_steps_per_second": 2.386, | |
| "step": 259115 | |
| }, | |
| { | |
| "epoch": 146.0, | |
| "learning_rate": 6.536845615205069e-06, | |
| "loss": 1.3567, | |
| "step": 260902 | |
| }, | |
| { | |
| "epoch": 146.0, | |
| "eval_accuracy": 0.7044657007018338, | |
| "eval_loss": 1.367392659187317, | |
| "eval_runtime": 1.5885, | |
| "eval_samples_per_second": 301.545, | |
| "eval_steps_per_second": 2.518, | |
| "step": 260902 | |
| }, | |
| { | |
| "epoch": 147.0, | |
| "learning_rate": 6.239079693231077e-06, | |
| "loss": 1.3561, | |
| "step": 262689 | |
| }, | |
| { | |
| "epoch": 147.0, | |
| "eval_accuracy": 0.7055519671993036, | |
| "eval_loss": 1.370457649230957, | |
| "eval_runtime": 1.577, | |
| "eval_samples_per_second": 303.746, | |
| "eval_steps_per_second": 2.537, | |
| "step": 262689 | |
| }, | |
| { | |
| "epoch": 148.0, | |
| "learning_rate": 5.941147049016339e-06, | |
| "loss": 1.3552, | |
| "step": 264476 | |
| }, | |
| { | |
| "epoch": 148.0, | |
| "eval_accuracy": 0.7079978529253892, | |
| "eval_loss": 1.3506109714508057, | |
| "eval_runtime": 1.5817, | |
| "eval_samples_per_second": 302.839, | |
| "eval_steps_per_second": 2.529, | |
| "step": 264476 | |
| }, | |
| { | |
| "epoch": 149.0, | |
| "learning_rate": 5.6432144048016e-06, | |
| "loss": 1.3547, | |
| "step": 266263 | |
| }, | |
| { | |
| "epoch": 149.0, | |
| "eval_accuracy": 0.7119885902849632, | |
| "eval_loss": 1.3456552028656006, | |
| "eval_runtime": 1.7734, | |
| "eval_samples_per_second": 270.099, | |
| "eval_steps_per_second": 2.256, | |
| "step": 266263 | |
| }, | |
| { | |
| "epoch": 150.0, | |
| "learning_rate": 5.34544848282761e-06, | |
| "loss": 1.3538, | |
| "step": 268050 | |
| }, | |
| { | |
| "epoch": 150.0, | |
| "eval_accuracy": 0.7099597756501048, | |
| "eval_loss": 1.3244553804397583, | |
| "eval_runtime": 1.5873, | |
| "eval_samples_per_second": 301.767, | |
| "eval_steps_per_second": 2.52, | |
| "step": 268050 | |
| }, | |
| { | |
| "epoch": 151.0, | |
| "learning_rate": 5.047682560853618e-06, | |
| "loss": 1.3543, | |
| "step": 269837 | |
| }, | |
| { | |
| "epoch": 151.0, | |
| "eval_accuracy": 0.7109617665330096, | |
| "eval_loss": 1.3277746438980103, | |
| "eval_runtime": 1.5987, | |
| "eval_samples_per_second": 299.621, | |
| "eval_steps_per_second": 2.502, | |
| "step": 269837 | |
| }, | |
| { | |
| "epoch": 152.0, | |
| "learning_rate": 4.749916638879627e-06, | |
| "loss": 1.3549, | |
| "step": 271624 | |
| }, | |
| { | |
| "epoch": 152.0, | |
| "eval_accuracy": 0.7103175715446927, | |
| "eval_loss": 1.334486961364746, | |
| "eval_runtime": 1.6577, | |
| "eval_samples_per_second": 288.956, | |
| "eval_steps_per_second": 2.413, | |
| "step": 271624 | |
| }, | |
| { | |
| "epoch": 153.0, | |
| "learning_rate": 4.452150716905636e-06, | |
| "loss": 1.3528, | |
| "step": 273411 | |
| }, | |
| { | |
| "epoch": 153.0, | |
| "eval_accuracy": 0.7089188813134827, | |
| "eval_loss": 1.3335890769958496, | |
| "eval_runtime": 1.5839, | |
| "eval_samples_per_second": 302.417, | |
| "eval_steps_per_second": 2.525, | |
| "step": 273411 | |
| }, | |
| { | |
| "epoch": 154.0, | |
| "learning_rate": 4.154551517172391e-06, | |
| "loss": 1.3528, | |
| "step": 275198 | |
| }, | |
| { | |
| "epoch": 154.0, | |
| "eval_accuracy": 0.7074926352064921, | |
| "eval_loss": 1.3620299100875854, | |
| "eval_runtime": 1.6136, | |
| "eval_samples_per_second": 296.847, | |
| "eval_steps_per_second": 2.479, | |
| "step": 275198 | |
| }, | |
| { | |
| "epoch": 155.0, | |
| "learning_rate": 3.856618872957652e-06, | |
| "loss": 1.3531, | |
| "step": 276985 | |
| }, | |
| { | |
| "epoch": 155.0, | |
| "eval_accuracy": 0.7119889627210272, | |
| "eval_loss": 1.3383039236068726, | |
| "eval_runtime": 1.6118, | |
| "eval_samples_per_second": 297.175, | |
| "eval_steps_per_second": 2.482, | |
| "step": 276985 | |
| }, | |
| { | |
| "epoch": 156.0, | |
| "learning_rate": 3.558852950983661e-06, | |
| "loss": 1.3525, | |
| "step": 278772 | |
| }, | |
| { | |
| "epoch": 156.0, | |
| "eval_accuracy": 0.709147771696638, | |
| "eval_loss": 1.3376810550689697, | |
| "eval_runtime": 1.6014, | |
| "eval_samples_per_second": 299.106, | |
| "eval_steps_per_second": 2.498, | |
| "step": 278772 | |
| }, | |
| { | |
| "epoch": 157.0, | |
| "learning_rate": 3.2609203067689235e-06, | |
| "loss": 1.3509, | |
| "step": 280559 | |
| }, | |
| { | |
| "epoch": 157.0, | |
| "eval_accuracy": 0.7054241768129798, | |
| "eval_loss": 1.363862156867981, | |
| "eval_runtime": 1.5926, | |
| "eval_samples_per_second": 300.762, | |
| "eval_steps_per_second": 2.512, | |
| "step": 280559 | |
| }, | |
| { | |
| "epoch": 158.0, | |
| "learning_rate": 2.962987662554185e-06, | |
| "loss": 1.3502, | |
| "step": 282346 | |
| }, | |
| { | |
| "epoch": 158.0, | |
| "eval_accuracy": 0.7090706112196483, | |
| "eval_loss": 1.345644235610962, | |
| "eval_runtime": 1.7541, | |
| "eval_samples_per_second": 273.075, | |
| "eval_steps_per_second": 2.28, | |
| "step": 282346 | |
| }, | |
| { | |
| "epoch": 159.0, | |
| "learning_rate": 2.6653884628209403e-06, | |
| "loss": 1.351, | |
| "step": 284133 | |
| }, | |
| { | |
| "epoch": 159.0, | |
| "eval_accuracy": 0.7110125231650475, | |
| "eval_loss": 1.3358895778656006, | |
| "eval_runtime": 1.7083, | |
| "eval_samples_per_second": 280.394, | |
| "eval_steps_per_second": 2.341, | |
| "step": 284133 | |
| }, | |
| { | |
| "epoch": 160.0, | |
| "learning_rate": 2.3674558186062022e-06, | |
| "loss": 1.3493, | |
| "step": 285920 | |
| }, | |
| { | |
| "epoch": 160.0, | |
| "eval_accuracy": 0.7128785320274682, | |
| "eval_loss": 1.3361459970474243, | |
| "eval_runtime": 1.5991, | |
| "eval_samples_per_second": 299.536, | |
| "eval_steps_per_second": 2.501, | |
| "step": 285920 | |
| }, | |
| { | |
| "epoch": 161.0, | |
| "learning_rate": 2.069523174391464e-06, | |
| "loss": 1.3497, | |
| "step": 287707 | |
| }, | |
| { | |
| "epoch": 161.0, | |
| "eval_accuracy": 0.7090949997187693, | |
| "eval_loss": 1.3350205421447754, | |
| "eval_runtime": 1.5987, | |
| "eval_samples_per_second": 299.61, | |
| "eval_steps_per_second": 2.502, | |
| "step": 287707 | |
| }, | |
| { | |
| "epoch": 162.0, | |
| "learning_rate": 1.7717572524174725e-06, | |
| "loss": 1.3484, | |
| "step": 289494 | |
| }, | |
| { | |
| "epoch": 162.0, | |
| "eval_accuracy": 0.7074801387490209, | |
| "eval_loss": 1.3582346439361572, | |
| "eval_runtime": 1.5871, | |
| "eval_samples_per_second": 301.812, | |
| "eval_steps_per_second": 2.52, | |
| "step": 289494 | |
| }, | |
| { | |
| "epoch": 163.0, | |
| "learning_rate": 1.4739913304434811e-06, | |
| "loss": 1.35, | |
| "step": 291281 | |
| }, | |
| { | |
| "epoch": 163.0, | |
| "eval_accuracy": 0.7099812203940914, | |
| "eval_loss": 1.3440545797348022, | |
| "eval_runtime": 1.5859, | |
| "eval_samples_per_second": 302.036, | |
| "eval_steps_per_second": 2.522, | |
| "step": 291281 | |
| }, | |
| { | |
| "epoch": 164.0, | |
| "learning_rate": 1.17622540846949e-06, | |
| "loss": 1.3485, | |
| "step": 293068 | |
| }, | |
| { | |
| "epoch": 164.0, | |
| "eval_accuracy": 0.709328337341312, | |
| "eval_loss": 1.322691559791565, | |
| "eval_runtime": 1.6662, | |
| "eval_samples_per_second": 287.479, | |
| "eval_steps_per_second": 2.401, | |
| "step": 293068 | |
| }, | |
| { | |
| "epoch": 165.0, | |
| "learning_rate": 8.784594864954986e-07, | |
| "loss": 1.3485, | |
| "step": 294855 | |
| }, | |
| { | |
| "epoch": 165.0, | |
| "eval_accuracy": 0.711818259167872, | |
| "eval_loss": 1.3385770320892334, | |
| "eval_runtime": 1.6184, | |
| "eval_samples_per_second": 295.967, | |
| "eval_steps_per_second": 2.472, | |
| "step": 294855 | |
| }, | |
| { | |
| "epoch": 166.0, | |
| "learning_rate": 5.806935645215072e-07, | |
| "loss": 1.3483, | |
| "step": 296642 | |
| }, | |
| { | |
| "epoch": 166.0, | |
| "eval_accuracy": 0.7086703561799347, | |
| "eval_loss": 1.347002625465393, | |
| "eval_runtime": 1.5811, | |
| "eval_samples_per_second": 302.945, | |
| "eval_steps_per_second": 2.53, | |
| "step": 296642 | |
| }, | |
| { | |
| "epoch": 167.0, | |
| "learning_rate": 2.829276425475159e-07, | |
| "loss": 1.3481, | |
| "step": 298429 | |
| }, | |
| { | |
| "epoch": 167.0, | |
| "eval_accuracy": 0.7087042253521126, | |
| "eval_loss": 1.3404722213745117, | |
| "eval_runtime": 1.6093, | |
| "eval_samples_per_second": 297.645, | |
| "eval_steps_per_second": 2.486, | |
| "step": 298429 | |
| }, | |
| { | |
| "epoch": 167.88, | |
| "learning_rate": 2.1007002334111373e-08, | |
| "loss": 1.3465, | |
| "step": 300000 | |
| }, | |
| { | |
| "epoch": 167.88, | |
| "eval_accuracy": 0.7062244840892568, | |
| "eval_loss": 1.3382107019424438, | |
| "eval_runtime": 1.6088, | |
| "eval_samples_per_second": 297.737, | |
| "eval_steps_per_second": 2.486, | |
| "step": 300000 | |
| }, | |
| { | |
| "epoch": 167.88, | |
| "step": 300000, | |
| "total_flos": 5.088223250635293e+18, | |
| "train_loss": 1.4402713134765626, | |
| "train_runtime": 110171.7858, | |
| "train_samples_per_second": 348.547, | |
| "train_steps_per_second": 2.723 | |
| } | |
| ], | |
| "max_steps": 300000, | |
| "num_train_epochs": 168, | |
| "total_flos": 5.088223250635293e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |