| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 13.0, | |
| "global_step": 84409, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.9897325324708663e-05, | |
| "loss": 0.0613, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.9794650649417323e-05, | |
| "loss": 0.0384, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.9691975974125984e-05, | |
| "loss": 0.0347, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.9589301298834645e-05, | |
| "loss": 0.0304, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.9486626623543306e-05, | |
| "loss": 0.0317, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.9383951948251964e-05, | |
| "loss": 0.0293, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 1.9281277272960624e-05, | |
| "loss": 0.0264, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.9178602597669285e-05, | |
| "loss": 0.0267, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.907592792237795e-05, | |
| "loss": 0.0276, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.8973253247086607e-05, | |
| "loss": 0.0246, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1.8870578571795268e-05, | |
| "loss": 0.0247, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.876790389650393e-05, | |
| "loss": 0.0231, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9923576779814453, | |
| "eval_f1": 0.9008350730688935, | |
| "eval_loss": 0.021180663257837296, | |
| "eval_precision": 0.8908472243462303, | |
| "eval_recall": 0.9110494213324992, | |
| "eval_runtime": 51.6414, | |
| "eval_samples_per_second": 430.469, | |
| "eval_steps_per_second": 26.916, | |
| "step": 6493 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.866522922121259e-05, | |
| "loss": 0.0246, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 1.856255454592125e-05, | |
| "loss": 0.0166, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 1.845987987062991e-05, | |
| "loss": 0.0169, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 1.8357205195338572e-05, | |
| "loss": 0.0155, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 1.825453052004723e-05, | |
| "loss": 0.0157, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 1.8151855844755894e-05, | |
| "loss": 0.0165, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 1.8049181169464555e-05, | |
| "loss": 0.0165, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 1.7946506494173212e-05, | |
| "loss": 0.0157, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 1.7843831818881873e-05, | |
| "loss": 0.0161, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 1.7741157143590534e-05, | |
| "loss": 0.0166, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 1.7638482468299195e-05, | |
| "loss": 0.0163, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 1.7535807793007856e-05, | |
| "loss": 0.0147, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.7433133117716517e-05, | |
| "loss": 0.0154, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9932060344168305, | |
| "eval_f1": 0.9151427443757401, | |
| "eval_loss": 0.020859336480498314, | |
| "eval_precision": 0.881111794723318, | |
| "eval_recall": 0.9519080387863622, | |
| "eval_runtime": 51.2977, | |
| "eval_samples_per_second": 433.353, | |
| "eval_steps_per_second": 27.097, | |
| "step": 12986 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.7330458442425178e-05, | |
| "loss": 0.0167, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 1.722778376713384e-05, | |
| "loss": 0.0097, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 1.71251090918425e-05, | |
| "loss": 0.0096, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 1.702243441655116e-05, | |
| "loss": 0.0092, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 1.691975974125982e-05, | |
| "loss": 0.0106, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 1.681708506596848e-05, | |
| "loss": 0.0102, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 1.671441039067714e-05, | |
| "loss": 0.0103, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 1.66117357153858e-05, | |
| "loss": 0.0094, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 1.650906104009446e-05, | |
| "loss": 0.0103, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 1.6406386364803122e-05, | |
| "loss": 0.0096, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 1.6303711689511783e-05, | |
| "loss": 0.0103, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 1.6201037014220444e-05, | |
| "loss": 0.01, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 1.6098362338929105e-05, | |
| "loss": 0.0099, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9953580496931748, | |
| "eval_f1": 0.9364340787171451, | |
| "eval_loss": 0.017423413693904877, | |
| "eval_precision": 0.9212537358604774, | |
| "eval_recall": 0.9521230841413826, | |
| "eval_runtime": 51.2859, | |
| "eval_samples_per_second": 433.453, | |
| "eval_steps_per_second": 27.103, | |
| "step": 19479 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 1.5995687663637766e-05, | |
| "loss": 0.0097, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 1.5893012988346427e-05, | |
| "loss": 0.0067, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 1.5790338313055087e-05, | |
| "loss": 0.0072, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 1.5687663637763745e-05, | |
| "loss": 0.0065, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 1.5584988962472406e-05, | |
| "loss": 0.0063, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 1.5482314287181067e-05, | |
| "loss": 0.0082, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 1.537963961188973e-05, | |
| "loss": 0.0063, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 1.527696493659839e-05, | |
| "loss": 0.0073, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 1.517429026130705e-05, | |
| "loss": 0.0067, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 1.507161558601571e-05, | |
| "loss": 0.0066, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 1.4968940910724373e-05, | |
| "loss": 0.0073, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 1.4866266235433032e-05, | |
| "loss": 0.0063, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 1.4763591560141693e-05, | |
| "loss": 0.0066, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9954778037113075, | |
| "eval_f1": 0.9395088840087842, | |
| "eval_loss": 0.018721075728535652, | |
| "eval_precision": 0.9144290023502415, | |
| "eval_recall": 0.9660032843290585, | |
| "eval_runtime": 51.1646, | |
| "eval_samples_per_second": 434.48, | |
| "eval_steps_per_second": 27.167, | |
| "step": 25972 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 1.4660916884850354e-05, | |
| "loss": 0.007, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 1.4558242209559013e-05, | |
| "loss": 0.0045, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 1.4455567534267674e-05, | |
| "loss": 0.0055, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "learning_rate": 1.4352892858976335e-05, | |
| "loss": 0.0048, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 1.4250218183684995e-05, | |
| "loss": 0.0047, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 1.4147543508393655e-05, | |
| "loss": 0.0046, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 1.4044868833102317e-05, | |
| "loss": 0.0046, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "learning_rate": 1.3942194157810978e-05, | |
| "loss": 0.0049, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 1.3839519482519637e-05, | |
| "loss": 0.0056, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 1.3736844807228298e-05, | |
| "loss": 0.0054, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "learning_rate": 1.3634170131936959e-05, | |
| "loss": 0.0055, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "learning_rate": 1.353149545664562e-05, | |
| "loss": 0.0052, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "learning_rate": 1.3428820781354279e-05, | |
| "loss": 0.0047, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.996386037155759, | |
| "eval_f1": 0.9499301079443971, | |
| "eval_loss": 0.01743621565401554, | |
| "eval_precision": 0.9434096868733611, | |
| "eval_recall": 0.9565412887081639, | |
| "eval_runtime": 50.9241, | |
| "eval_samples_per_second": 436.532, | |
| "eval_steps_per_second": 27.296, | |
| "step": 32465 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 1.332614610606294e-05, | |
| "loss": 0.0049, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 5.08, | |
| "learning_rate": 1.3223471430771601e-05, | |
| "loss": 0.0032, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "learning_rate": 1.3120796755480263e-05, | |
| "loss": 0.0035, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 1.3018122080188923e-05, | |
| "loss": 0.0033, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 5.31, | |
| "learning_rate": 1.2915447404897584e-05, | |
| "loss": 0.0031, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 5.39, | |
| "learning_rate": 1.2812772729606244e-05, | |
| "loss": 0.0037, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 5.47, | |
| "learning_rate": 1.2710098054314904e-05, | |
| "loss": 0.0037, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 5.54, | |
| "learning_rate": 1.2607423379023564e-05, | |
| "loss": 0.0043, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 5.62, | |
| "learning_rate": 1.2504748703732225e-05, | |
| "loss": 0.0034, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "learning_rate": 1.2402074028440886e-05, | |
| "loss": 0.0036, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 5.78, | |
| "learning_rate": 1.2299399353149545e-05, | |
| "loss": 0.003, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 5.85, | |
| "learning_rate": 1.2196724677858208e-05, | |
| "loss": 0.0037, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 1.2094050002566869e-05, | |
| "loss": 0.0032, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9964631065733692, | |
| "eval_f1": 0.9498019389642716, | |
| "eval_loss": 0.020042115822434425, | |
| "eval_precision": 0.9411696961553965, | |
| "eval_recall": 0.9585939943697216, | |
| "eval_runtime": 50.9154, | |
| "eval_samples_per_second": 436.607, | |
| "eval_steps_per_second": 27.3, | |
| "step": 38958 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 1.199137532727553e-05, | |
| "loss": 0.0034, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 1.1888700651984189e-05, | |
| "loss": 0.0023, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 6.16, | |
| "learning_rate": 1.178602597669285e-05, | |
| "loss": 0.0022, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "learning_rate": 1.168335130140151e-05, | |
| "loss": 0.0026, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 6.31, | |
| "learning_rate": 1.158067662611017e-05, | |
| "loss": 0.003, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 6.39, | |
| "learning_rate": 1.147800195081883e-05, | |
| "loss": 0.0024, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "learning_rate": 1.1375327275527492e-05, | |
| "loss": 0.0026, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 6.55, | |
| "learning_rate": 1.1272652600236154e-05, | |
| "loss": 0.0029, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 6.62, | |
| "learning_rate": 1.1169977924944813e-05, | |
| "loss": 0.0028, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "learning_rate": 1.1067303249653474e-05, | |
| "loss": 0.0022, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 6.78, | |
| "learning_rate": 1.0964628574362135e-05, | |
| "loss": 0.0026, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 6.85, | |
| "learning_rate": 1.0861953899070794e-05, | |
| "loss": 0.0026, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 6.93, | |
| "learning_rate": 1.0759279223779455e-05, | |
| "loss": 0.0028, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9966623013758077, | |
| "eval_f1": 0.9540412662796937, | |
| "eval_loss": 0.02194616012275219, | |
| "eval_precision": 0.9521741670399003, | |
| "eval_recall": 0.955915702220832, | |
| "eval_runtime": 51.3344, | |
| "eval_samples_per_second": 433.043, | |
| "eval_steps_per_second": 27.077, | |
| "step": 45451 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 1.0656604548488116e-05, | |
| "loss": 0.0024, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 7.08, | |
| "learning_rate": 1.0553929873196777e-05, | |
| "loss": 0.0017, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 7.16, | |
| "learning_rate": 1.0451255197905436e-05, | |
| "loss": 0.0017, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 7.24, | |
| "learning_rate": 1.0348580522614099e-05, | |
| "loss": 0.0017, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 7.32, | |
| "learning_rate": 1.024590584732276e-05, | |
| "loss": 0.0018, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 7.39, | |
| "learning_rate": 1.014323117203142e-05, | |
| "loss": 0.0019, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 7.47, | |
| "learning_rate": 1.004055649674008e-05, | |
| "loss": 0.0019, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 7.55, | |
| "learning_rate": 9.93788182144874e-06, | |
| "loss": 0.0021, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 7.62, | |
| "learning_rate": 9.835207146157401e-06, | |
| "loss": 0.0021, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 7.7, | |
| "learning_rate": 9.732532470866062e-06, | |
| "loss": 0.0024, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 7.78, | |
| "learning_rate": 9.629857795574721e-06, | |
| "loss": 0.0024, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 7.85, | |
| "learning_rate": 9.527183120283382e-06, | |
| "loss": 0.0022, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 7.93, | |
| "learning_rate": 9.424508444992043e-06, | |
| "loss": 0.002, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9969071449871383, | |
| "eval_f1": 0.95708591545198, | |
| "eval_loss": 0.02347610704600811, | |
| "eval_precision": 0.9496353034006274, | |
| "eval_recall": 0.9646543634657492, | |
| "eval_runtime": 51.2371, | |
| "eval_samples_per_second": 433.865, | |
| "eval_steps_per_second": 27.129, | |
| "step": 51944 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 9.321833769700704e-06, | |
| "loss": 0.0014, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 8.09, | |
| "learning_rate": 9.219159094409365e-06, | |
| "loss": 0.0014, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 8.16, | |
| "learning_rate": 9.116484419118026e-06, | |
| "loss": 0.0013, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 8.24, | |
| "learning_rate": 9.013809743826687e-06, | |
| "loss": 0.0016, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "learning_rate": 8.911135068535346e-06, | |
| "loss": 0.0014, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 8.39, | |
| "learning_rate": 8.808460393244007e-06, | |
| "loss": 0.0016, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 8.47, | |
| "learning_rate": 8.705785717952668e-06, | |
| "loss": 0.0013, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 8.55, | |
| "learning_rate": 8.603111042661328e-06, | |
| "loss": 0.0013, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 8.62, | |
| "learning_rate": 8.50043636736999e-06, | |
| "loss": 0.0011, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 8.7, | |
| "learning_rate": 8.39776169207865e-06, | |
| "loss": 0.0014, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 8.78, | |
| "learning_rate": 8.29508701678731e-06, | |
| "loss": 0.0016, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "learning_rate": 8.19241234149597e-06, | |
| "loss": 0.0015, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 8.93, | |
| "learning_rate": 8.089737666204631e-06, | |
| "loss": 0.0019, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.9969735432546178, | |
| "eval_f1": 0.957957696804553, | |
| "eval_loss": 0.02377239800989628, | |
| "eval_precision": 0.9470949005521695, | |
| "eval_recall": 0.9690725680325305, | |
| "eval_runtime": 57.1242, | |
| "eval_samples_per_second": 389.152, | |
| "eval_steps_per_second": 24.333, | |
| "step": 58437 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 7.987062990913292e-06, | |
| "loss": 0.0014, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "learning_rate": 7.884388315621953e-06, | |
| "loss": 0.0014, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 9.16, | |
| "learning_rate": 7.781713640330612e-06, | |
| "loss": 0.0013, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 9.24, | |
| "learning_rate": 7.679038965039273e-06, | |
| "loss": 0.0013, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 9.32, | |
| "learning_rate": 7.576364289747934e-06, | |
| "loss": 0.0012, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 9.39, | |
| "learning_rate": 7.473689614456595e-06, | |
| "loss": 0.0011, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "learning_rate": 7.371014939165256e-06, | |
| "loss": 0.001, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 9.55, | |
| "learning_rate": 7.2683402638739165e-06, | |
| "loss": 0.0014, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 9.63, | |
| "learning_rate": 7.1656655885825765e-06, | |
| "loss": 0.0011, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 9.7, | |
| "learning_rate": 7.062990913291237e-06, | |
| "loss": 0.0014, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 9.78, | |
| "learning_rate": 6.960316237999898e-06, | |
| "loss": 0.0009, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 9.86, | |
| "learning_rate": 6.857641562708558e-06, | |
| "loss": 0.0011, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 9.93, | |
| "learning_rate": 6.754966887417219e-06, | |
| "loss": 0.0012, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9970482413055323, | |
| "eval_f1": 0.9589748568100184, | |
| "eval_loss": 0.02672559767961502, | |
| "eval_precision": 0.9524470669906282, | |
| "eval_recall": 0.9655927431967469, | |
| "eval_runtime": 50.0835, | |
| "eval_samples_per_second": 443.858, | |
| "eval_steps_per_second": 27.754, | |
| "step": 64930 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "learning_rate": 6.652292212125879e-06, | |
| "loss": 0.0014, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 10.09, | |
| "learning_rate": 6.54961753683454e-06, | |
| "loss": 0.001, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 10.16, | |
| "learning_rate": 6.446942861543201e-06, | |
| "loss": 0.0009, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 10.24, | |
| "learning_rate": 6.344268186251862e-06, | |
| "loss": 0.0007, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 10.32, | |
| "learning_rate": 6.241593510960522e-06, | |
| "loss": 0.0009, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 10.4, | |
| "learning_rate": 6.138918835669183e-06, | |
| "loss": 0.001, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 10.47, | |
| "learning_rate": 6.036244160377844e-06, | |
| "loss": 0.0011, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 10.55, | |
| "learning_rate": 5.9335694850865045e-06, | |
| "loss": 0.0011, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 10.63, | |
| "learning_rate": 5.8308948097951645e-06, | |
| "loss": 0.001, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 10.7, | |
| "learning_rate": 5.7282201345038246e-06, | |
| "loss": 0.0011, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 10.78, | |
| "learning_rate": 5.6255454592124854e-06, | |
| "loss": 0.001, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 10.86, | |
| "learning_rate": 5.522870783921146e-06, | |
| "loss": 0.0007, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 10.93, | |
| "learning_rate": 5.420196108629807e-06, | |
| "loss": 0.0012, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.9972326150661226, | |
| "eval_f1": 0.9617262499878666, | |
| "eval_loss": 0.026968594640493393, | |
| "eval_precision": 0.9550791416838574, | |
| "eval_recall": 0.9684665311229278, | |
| "eval_runtime": 49.8699, | |
| "eval_samples_per_second": 445.76, | |
| "eval_steps_per_second": 27.873, | |
| "step": 71423 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "learning_rate": 5.317521433338467e-06, | |
| "loss": 0.0008, | |
| "step": 71500 | |
| }, | |
| { | |
| "epoch": 11.09, | |
| "learning_rate": 5.214846758047128e-06, | |
| "loss": 0.0008, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 11.17, | |
| "learning_rate": 5.112172082755789e-06, | |
| "loss": 0.0008, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 11.24, | |
| "learning_rate": 5.00949740746445e-06, | |
| "loss": 0.0007, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 11.32, | |
| "learning_rate": 4.90682273217311e-06, | |
| "loss": 0.0007, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 11.4, | |
| "learning_rate": 4.804148056881771e-06, | |
| "loss": 0.0007, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 11.47, | |
| "learning_rate": 4.701473381590432e-06, | |
| "loss": 0.0009, | |
| "step": 74500 | |
| }, | |
| { | |
| "epoch": 11.55, | |
| "learning_rate": 4.598798706299092e-06, | |
| "loss": 0.0007, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 11.63, | |
| "learning_rate": 4.4961240310077525e-06, | |
| "loss": 0.0008, | |
| "step": 75500 | |
| }, | |
| { | |
| "epoch": 11.7, | |
| "learning_rate": 4.393449355716413e-06, | |
| "loss": 0.0007, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 11.78, | |
| "learning_rate": 4.2907746804250734e-06, | |
| "loss": 0.0007, | |
| "step": 76500 | |
| }, | |
| { | |
| "epoch": 11.86, | |
| "learning_rate": 4.188100005133734e-06, | |
| "loss": 0.0007, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 11.94, | |
| "learning_rate": 4.085425329842394e-06, | |
| "loss": 0.0007, | |
| "step": 77500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.9971656239569692, | |
| "eval_f1": 0.9604331205247123, | |
| "eval_loss": 0.02845791168510914, | |
| "eval_precision": 0.953384443502716, | |
| "eval_recall": 0.9675868001251173, | |
| "eval_runtime": 49.6251, | |
| "eval_samples_per_second": 447.959, | |
| "eval_steps_per_second": 28.01, | |
| "step": 77916 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "learning_rate": 3.982750654551055e-06, | |
| "loss": 0.0007, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 12.09, | |
| "learning_rate": 3.880075979259716e-06, | |
| "loss": 0.0007, | |
| "step": 78500 | |
| }, | |
| { | |
| "epoch": 12.17, | |
| "learning_rate": 3.7774013039683766e-06, | |
| "loss": 0.0008, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 12.24, | |
| "learning_rate": 3.6747266286770374e-06, | |
| "loss": 0.0008, | |
| "step": 79500 | |
| }, | |
| { | |
| "epoch": 12.32, | |
| "learning_rate": 3.572051953385698e-06, | |
| "loss": 0.0007, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 12.4, | |
| "learning_rate": 3.4693772780943583e-06, | |
| "loss": 0.0007, | |
| "step": 80500 | |
| }, | |
| { | |
| "epoch": 12.47, | |
| "learning_rate": 3.366702602803019e-06, | |
| "loss": 0.0007, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 12.55, | |
| "learning_rate": 3.2640279275116792e-06, | |
| "loss": 0.0006, | |
| "step": 81500 | |
| }, | |
| { | |
| "epoch": 12.63, | |
| "learning_rate": 3.16135325222034e-06, | |
| "loss": 0.0005, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 12.71, | |
| "learning_rate": 3.0586785769290006e-06, | |
| "loss": 0.0007, | |
| "step": 82500 | |
| }, | |
| { | |
| "epoch": 12.78, | |
| "learning_rate": 2.9560039016376615e-06, | |
| "loss": 0.0006, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 12.86, | |
| "learning_rate": 2.853329226346322e-06, | |
| "loss": 0.0006, | |
| "step": 83500 | |
| }, | |
| { | |
| "epoch": 12.94, | |
| "learning_rate": 2.7506545510549828e-06, | |
| "loss": 0.0006, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.9972806352417104, | |
| "eval_f1": 0.9628492298722122, | |
| "eval_loss": 0.02913038246333599, | |
| "eval_precision": 0.9572585164145073, | |
| "eval_recall": 0.968505630278386, | |
| "eval_runtime": 49.7978, | |
| "eval_samples_per_second": 446.405, | |
| "eval_steps_per_second": 27.913, | |
| "step": 84409 | |
| } | |
| ], | |
| "max_steps": 97395, | |
| "num_train_epochs": 15, | |
| "total_flos": 3.5286877927060275e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |