| { | |
| "best_metric": 0.8276850886339938, | |
| "best_model_checkpoint": "./runs/checkpoint-29920", | |
| "epoch": 2.0, | |
| "global_step": 29920, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.218154152691866e-05, | |
| "loss": 0.2013, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.2078899619883618e-05, | |
| "loss": 0.1722, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.1976257712848578e-05, | |
| "loss": 0.1653, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.1873615805813536e-05, | |
| "loss": 0.1488, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.1770973898778496e-05, | |
| "loss": 0.136, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.1668331991743454e-05, | |
| "loss": 0.1522, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.1565690084708414e-05, | |
| "loss": 0.1457, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.1463048177673372e-05, | |
| "loss": 0.1337, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.1360406270638331e-05, | |
| "loss": 0.1346, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.1257764363603291e-05, | |
| "loss": 0.1354, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.115512245656825e-05, | |
| "loss": 0.1442, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.1052480549533209e-05, | |
| "loss": 0.126, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.0949838642498167e-05, | |
| "loss": 0.1274, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.0847196735463127e-05, | |
| "loss": 0.1225, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.0744554828428085e-05, | |
| "loss": 0.1301, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1.0641912921393045e-05, | |
| "loss": 0.1357, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 1.0539271014358003e-05, | |
| "loss": 0.1272, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1.0436629107322963e-05, | |
| "loss": 0.1353, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.0333987200287922e-05, | |
| "loss": 0.1361, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.023134529325288e-05, | |
| "loss": 0.1303, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.012870338621784e-05, | |
| "loss": 0.1294, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.00260614791828e-05, | |
| "loss": 0.1131, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 9.923419572147758e-06, | |
| "loss": 0.1072, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 9.820777665112718e-06, | |
| "loss": 0.1222, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 9.718135758077678e-06, | |
| "loss": 0.1221, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 9.615493851042636e-06, | |
| "loss": 0.1196, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 9.512851944007596e-06, | |
| "loss": 0.1191, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 9.410210036972554e-06, | |
| "loss": 0.1185, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 9.307568129937513e-06, | |
| "loss": 0.1265, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9647807886095305, | |
| "eval_f1": 0.8202175303902751, | |
| "eval_loss": 0.13746094703674316, | |
| "eval_precision": 0.8026546456298522, | |
| "eval_recall": 0.8385661957090529, | |
| "eval_runtime": 509.4329, | |
| "eval_samples_per_second": 78.309, | |
| "step": 14960 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9.204926222902473e-06, | |
| "loss": 0.1162, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 9.102284315867431e-06, | |
| "loss": 0.0916, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 8.999642408832391e-06, | |
| "loss": 0.0878, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 8.897000501797349e-06, | |
| "loss": 0.0929, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 8.794358594762309e-06, | |
| "loss": 0.1018, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 8.691716687727267e-06, | |
| "loss": 0.098, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 8.589074780692227e-06, | |
| "loss": 0.0895, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 8.486432873657185e-06, | |
| "loss": 0.0824, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 8.383790966622145e-06, | |
| "loss": 0.0758, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 8.281149059587103e-06, | |
| "loss": 0.088, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 8.178507152552062e-06, | |
| "loss": 0.0975, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 8.075865245517022e-06, | |
| "loss": 0.0917, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 7.97322333848198e-06, | |
| "loss": 0.0952, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 7.87058143144694e-06, | |
| "loss": 0.0963, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 7.767939524411898e-06, | |
| "loss": 0.092, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 7.665297617376858e-06, | |
| "loss": 0.1029, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 7.562655710341816e-06, | |
| "loss": 0.0938, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 7.460013803306776e-06, | |
| "loss": 0.0995, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 7.357371896271735e-06, | |
| "loss": 0.0875, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 7.254729989236694e-06, | |
| "loss": 0.1, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 7.152088082201653e-06, | |
| "loss": 0.0841, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 7.049446175166612e-06, | |
| "loss": 0.09, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 6.946804268131571e-06, | |
| "loss": 0.0797, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 6.84416236109653e-06, | |
| "loss": 0.0888, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 6.74152045406149e-06, | |
| "loss": 0.0804, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 6.638878547026448e-06, | |
| "loss": 0.0989, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 6.536236639991408e-06, | |
| "loss": 0.0879, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 6.433594732956366e-06, | |
| "loss": 0.0955, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 6.330952825921326e-06, | |
| "loss": 0.0928, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 6.228310918886284e-06, | |
| "loss": 0.0852, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9668613541222771, | |
| "eval_f1": 0.8276850886339938, | |
| "eval_loss": 0.13479416072368622, | |
| "eval_precision": 0.8246753246753247, | |
| "eval_recall": 0.8307169021454736, | |
| "eval_runtime": 509.3337, | |
| "eval_samples_per_second": 78.324, | |
| "step": 29920 | |
| } | |
| ], | |
| "max_steps": 59840, | |
| "num_train_epochs": 4, | |
| "total_flos": 7.964185065787392e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |