| { |
| "best_metric": 6.676162593066692e-05, |
| "best_model_checkpoint": "autotrain-7odil-vp48l/checkpoint-3000", |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 3000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.025, |
| "grad_norm": 1.9831761121749878, |
| "learning_rate": 4.166666666666667e-06, |
| "loss": 1.9634, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.05, |
| "grad_norm": 3.9359655380249023, |
| "learning_rate": 8.333333333333334e-06, |
| "loss": 1.8703, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.075, |
| "grad_norm": 5.147686004638672, |
| "learning_rate": 1.25e-05, |
| "loss": 1.5786, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 4.199033260345459, |
| "learning_rate": 1.6666666666666667e-05, |
| "loss": 1.0025, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.125, |
| "grad_norm": 2.716735601425171, |
| "learning_rate": 2.0833333333333336e-05, |
| "loss": 0.4952, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.15, |
| "grad_norm": 1.7983918190002441, |
| "learning_rate": 2.5e-05, |
| "loss": 0.2272, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.175, |
| "grad_norm": 0.49452969431877136, |
| "learning_rate": 2.916666666666667e-05, |
| "loss": 0.078, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 0.23962058126926422, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 0.0345, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.225, |
| "grad_norm": 0.1509809046983719, |
| "learning_rate": 3.7500000000000003e-05, |
| "loss": 0.0195, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 0.13671720027923584, |
| "learning_rate": 4.166666666666667e-05, |
| "loss": 0.0132, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.275, |
| "grad_norm": 0.07179934531450272, |
| "learning_rate": 4.5833333333333334e-05, |
| "loss": 0.0094, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 0.06333258748054504, |
| "learning_rate": 5e-05, |
| "loss": 0.0074, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.325, |
| "grad_norm": 0.07822247594594955, |
| "learning_rate": 4.9537037037037035e-05, |
| "loss": 0.0056, |
| "step": 325 |
| }, |
| { |
| "epoch": 0.35, |
| "grad_norm": 0.05372656136751175, |
| "learning_rate": 4.9074074074074075e-05, |
| "loss": 0.0046, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.375, |
| "grad_norm": 0.035013675689697266, |
| "learning_rate": 4.8611111111111115e-05, |
| "loss": 0.004, |
| "step": 375 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 0.041423212736845016, |
| "learning_rate": 4.814814814814815e-05, |
| "loss": 0.0035, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.425, |
| "grad_norm": 0.041730575263500214, |
| "learning_rate": 4.768518518518519e-05, |
| "loss": 0.0028, |
| "step": 425 |
| }, |
| { |
| "epoch": 0.45, |
| "grad_norm": 0.029097281396389008, |
| "learning_rate": 4.722222222222222e-05, |
| "loss": 0.0024, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.475, |
| "grad_norm": 0.018743053078651428, |
| "learning_rate": 4.675925925925926e-05, |
| "loss": 0.0022, |
| "step": 475 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 0.024263164028525352, |
| "learning_rate": 4.62962962962963e-05, |
| "loss": 0.0019, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.525, |
| "grad_norm": 0.026380807161331177, |
| "learning_rate": 4.5833333333333334e-05, |
| "loss": 0.0018, |
| "step": 525 |
| }, |
| { |
| "epoch": 0.55, |
| "grad_norm": 0.011210402473807335, |
| "learning_rate": 4.5370370370370374e-05, |
| "loss": 0.0016, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.575, |
| "grad_norm": 0.018315857276320457, |
| "learning_rate": 4.490740740740741e-05, |
| "loss": 0.0014, |
| "step": 575 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 0.01992151141166687, |
| "learning_rate": 4.4444444444444447e-05, |
| "loss": 0.0014, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.625, |
| "grad_norm": 0.013192097656428814, |
| "learning_rate": 4.3981481481481486e-05, |
| "loss": 0.0012, |
| "step": 625 |
| }, |
| { |
| "epoch": 0.65, |
| "grad_norm": 0.012587452307343483, |
| "learning_rate": 4.351851851851852e-05, |
| "loss": 0.0011, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.675, |
| "grad_norm": 0.01079911831766367, |
| "learning_rate": 4.305555555555556e-05, |
| "loss": 0.001, |
| "step": 675 |
| }, |
| { |
| "epoch": 0.7, |
| "grad_norm": 0.012937197461724281, |
| "learning_rate": 4.259259259259259e-05, |
| "loss": 0.001, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.725, |
| "grad_norm": 0.010724306106567383, |
| "learning_rate": 4.212962962962963e-05, |
| "loss": 0.0009, |
| "step": 725 |
| }, |
| { |
| "epoch": 0.75, |
| "grad_norm": 0.01117613259702921, |
| "learning_rate": 4.166666666666667e-05, |
| "loss": 0.0009, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.775, |
| "grad_norm": 0.009770487435162067, |
| "learning_rate": 4.1203703703703705e-05, |
| "loss": 0.0008, |
| "step": 775 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.009905874729156494, |
| "learning_rate": 4.074074074074074e-05, |
| "loss": 0.0008, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.825, |
| "grad_norm": 0.007548601366579533, |
| "learning_rate": 4.027777777777778e-05, |
| "loss": 0.0007, |
| "step": 825 |
| }, |
| { |
| "epoch": 0.85, |
| "grad_norm": 0.006770648993551731, |
| "learning_rate": 3.981481481481482e-05, |
| "loss": 0.0007, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.875, |
| "grad_norm": 0.010729338973760605, |
| "learning_rate": 3.935185185185186e-05, |
| "loss": 0.0007, |
| "step": 875 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 0.009794618003070354, |
| "learning_rate": 3.888888888888889e-05, |
| "loss": 0.0006, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.925, |
| "grad_norm": 0.007390674669295549, |
| "learning_rate": 3.8425925925925924e-05, |
| "loss": 0.0006, |
| "step": 925 |
| }, |
| { |
| "epoch": 0.95, |
| "grad_norm": 0.006331269163638353, |
| "learning_rate": 3.7962962962962964e-05, |
| "loss": 0.0005, |
| "step": 950 |
| }, |
| { |
| "epoch": 0.975, |
| "grad_norm": 0.009682104922831059, |
| "learning_rate": 3.7500000000000003e-05, |
| "loss": 0.0005, |
| "step": 975 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.008350877091288567, |
| "learning_rate": 3.7037037037037037e-05, |
| "loss": 0.0005, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 1.0, |
| "eval_f1_macro": 1.0, |
| "eval_f1_micro": 1.0, |
| "eval_f1_weighted": 1.0, |
| "eval_loss": 0.0003003589517902583, |
| "eval_precision_macro": 1.0, |
| "eval_precision_micro": 1.0, |
| "eval_precision_weighted": 1.0, |
| "eval_recall_macro": 1.0, |
| "eval_recall_micro": 1.0, |
| "eval_recall_weighted": 1.0, |
| "eval_runtime": 252.8474, |
| "eval_samples_per_second": 7.91, |
| "eval_steps_per_second": 0.494, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.025, |
| "grad_norm": 0.0058663454838097095, |
| "learning_rate": 3.6574074074074076e-05, |
| "loss": 0.0005, |
| "step": 1025 |
| }, |
| { |
| "epoch": 1.05, |
| "grad_norm": 0.005394589621573687, |
| "learning_rate": 3.611111111111111e-05, |
| "loss": 0.0005, |
| "step": 1050 |
| }, |
| { |
| "epoch": 1.075, |
| "grad_norm": 0.006175881251692772, |
| "learning_rate": 3.564814814814815e-05, |
| "loss": 0.0005, |
| "step": 1075 |
| }, |
| { |
| "epoch": 1.1, |
| "grad_norm": 0.003940545488148928, |
| "learning_rate": 3.518518518518519e-05, |
| "loss": 0.0004, |
| "step": 1100 |
| }, |
| { |
| "epoch": 1.125, |
| "grad_norm": 0.004921493120491505, |
| "learning_rate": 3.472222222222222e-05, |
| "loss": 0.0004, |
| "step": 1125 |
| }, |
| { |
| "epoch": 1.15, |
| "grad_norm": 0.004267093725502491, |
| "learning_rate": 3.425925925925926e-05, |
| "loss": 0.0004, |
| "step": 1150 |
| }, |
| { |
| "epoch": 1.175, |
| "grad_norm": 0.004450589884072542, |
| "learning_rate": 3.3796296296296295e-05, |
| "loss": 0.0004, |
| "step": 1175 |
| }, |
| { |
| "epoch": 1.2, |
| "grad_norm": 0.004894304554909468, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 0.0004, |
| "step": 1200 |
| }, |
| { |
| "epoch": 1.225, |
| "grad_norm": 0.005115053616464138, |
| "learning_rate": 3.2870370370370375e-05, |
| "loss": 0.0004, |
| "step": 1225 |
| }, |
| { |
| "epoch": 1.25, |
| "grad_norm": 0.00417192792519927, |
| "learning_rate": 3.240740740740741e-05, |
| "loss": 0.0003, |
| "step": 1250 |
| }, |
| { |
| "epoch": 1.275, |
| "grad_norm": 0.003110726596787572, |
| "learning_rate": 3.194444444444444e-05, |
| "loss": 0.0003, |
| "step": 1275 |
| }, |
| { |
| "epoch": 1.3, |
| "grad_norm": 0.004500871989876032, |
| "learning_rate": 3.148148148148148e-05, |
| "loss": 0.0003, |
| "step": 1300 |
| }, |
| { |
| "epoch": 1.325, |
| "grad_norm": 0.007220442872494459, |
| "learning_rate": 3.101851851851852e-05, |
| "loss": 0.0003, |
| "step": 1325 |
| }, |
| { |
| "epoch": 1.35, |
| "grad_norm": 0.004517797380685806, |
| "learning_rate": 3.055555555555556e-05, |
| "loss": 0.0003, |
| "step": 1350 |
| }, |
| { |
| "epoch": 1.375, |
| "grad_norm": 0.004377953242510557, |
| "learning_rate": 3.0092592592592593e-05, |
| "loss": 0.0003, |
| "step": 1375 |
| }, |
| { |
| "epoch": 1.4, |
| "grad_norm": 0.003857560455799103, |
| "learning_rate": 2.962962962962963e-05, |
| "loss": 0.0003, |
| "step": 1400 |
| }, |
| { |
| "epoch": 1.425, |
| "grad_norm": 0.0031161897350102663, |
| "learning_rate": 2.916666666666667e-05, |
| "loss": 0.0003, |
| "step": 1425 |
| }, |
| { |
| "epoch": 1.45, |
| "grad_norm": 0.00418724725022912, |
| "learning_rate": 2.8703703703703706e-05, |
| "loss": 0.0003, |
| "step": 1450 |
| }, |
| { |
| "epoch": 1.475, |
| "grad_norm": 0.0038644387386739254, |
| "learning_rate": 2.824074074074074e-05, |
| "loss": 0.0003, |
| "step": 1475 |
| }, |
| { |
| "epoch": 1.5, |
| "grad_norm": 0.0028685845900326967, |
| "learning_rate": 2.777777777777778e-05, |
| "loss": 0.0003, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.525, |
| "grad_norm": 0.0030455435626208782, |
| "learning_rate": 2.7314814814814816e-05, |
| "loss": 0.0003, |
| "step": 1525 |
| }, |
| { |
| "epoch": 1.55, |
| "grad_norm": 0.004415576346218586, |
| "learning_rate": 2.6851851851851855e-05, |
| "loss": 0.0002, |
| "step": 1550 |
| }, |
| { |
| "epoch": 1.575, |
| "grad_norm": 0.0032394465524703264, |
| "learning_rate": 2.6388888888888892e-05, |
| "loss": 0.0002, |
| "step": 1575 |
| }, |
| { |
| "epoch": 1.6, |
| "grad_norm": 0.0036883000284433365, |
| "learning_rate": 2.5925925925925925e-05, |
| "loss": 0.0002, |
| "step": 1600 |
| }, |
| { |
| "epoch": 1.625, |
| "grad_norm": 0.002775784581899643, |
| "learning_rate": 2.5462962962962965e-05, |
| "loss": 0.0002, |
| "step": 1625 |
| }, |
| { |
| "epoch": 1.65, |
| "grad_norm": 0.00252612610347569, |
| "learning_rate": 2.5e-05, |
| "loss": 0.0002, |
| "step": 1650 |
| }, |
| { |
| "epoch": 1.675, |
| "grad_norm": 0.003114240476861596, |
| "learning_rate": 2.4537037037037038e-05, |
| "loss": 0.0002, |
| "step": 1675 |
| }, |
| { |
| "epoch": 1.7, |
| "grad_norm": 0.0045029474422335625, |
| "learning_rate": 2.4074074074074074e-05, |
| "loss": 0.0002, |
| "step": 1700 |
| }, |
| { |
| "epoch": 1.725, |
| "grad_norm": 0.0029288099613040686, |
| "learning_rate": 2.361111111111111e-05, |
| "loss": 0.0002, |
| "step": 1725 |
| }, |
| { |
| "epoch": 1.75, |
| "grad_norm": 0.0029125239234417677, |
| "learning_rate": 2.314814814814815e-05, |
| "loss": 0.0002, |
| "step": 1750 |
| }, |
| { |
| "epoch": 1.775, |
| "grad_norm": 0.0026727975346148014, |
| "learning_rate": 2.2685185185185187e-05, |
| "loss": 0.0002, |
| "step": 1775 |
| }, |
| { |
| "epoch": 1.8, |
| "grad_norm": 0.0019383927574381232, |
| "learning_rate": 2.2222222222222223e-05, |
| "loss": 0.0002, |
| "step": 1800 |
| }, |
| { |
| "epoch": 1.825, |
| "grad_norm": 0.0030314610339701176, |
| "learning_rate": 2.175925925925926e-05, |
| "loss": 0.0002, |
| "step": 1825 |
| }, |
| { |
| "epoch": 1.85, |
| "grad_norm": 0.0029118990059942007, |
| "learning_rate": 2.1296296296296296e-05, |
| "loss": 0.0002, |
| "step": 1850 |
| }, |
| { |
| "epoch": 1.875, |
| "grad_norm": 0.002271339064463973, |
| "learning_rate": 2.0833333333333336e-05, |
| "loss": 0.0002, |
| "step": 1875 |
| }, |
| { |
| "epoch": 1.9, |
| "grad_norm": 0.0020249192602932453, |
| "learning_rate": 2.037037037037037e-05, |
| "loss": 0.0002, |
| "step": 1900 |
| }, |
| { |
| "epoch": 1.925, |
| "grad_norm": 0.002170481951907277, |
| "learning_rate": 1.990740740740741e-05, |
| "loss": 0.0002, |
| "step": 1925 |
| }, |
| { |
| "epoch": 1.95, |
| "grad_norm": 0.0021853959187865257, |
| "learning_rate": 1.9444444444444445e-05, |
| "loss": 0.0002, |
| "step": 1950 |
| }, |
| { |
| "epoch": 1.975, |
| "grad_norm": 0.0024531374219805002, |
| "learning_rate": 1.8981481481481482e-05, |
| "loss": 0.0002, |
| "step": 1975 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.0020948376040905714, |
| "learning_rate": 1.8518518518518518e-05, |
| "loss": 0.0002, |
| "step": 2000 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 1.0, |
| "eval_f1_macro": 1.0, |
| "eval_f1_micro": 1.0, |
| "eval_f1_weighted": 1.0, |
| "eval_loss": 9.583658538758755e-05, |
| "eval_precision_macro": 1.0, |
| "eval_precision_micro": 1.0, |
| "eval_precision_weighted": 1.0, |
| "eval_recall_macro": 1.0, |
| "eval_recall_micro": 1.0, |
| "eval_recall_weighted": 1.0, |
| "eval_runtime": 274.5731, |
| "eval_samples_per_second": 7.284, |
| "eval_steps_per_second": 0.455, |
| "step": 2000 |
| }, |
| { |
| "epoch": 2.025, |
| "grad_norm": 0.0017642254242673516, |
| "learning_rate": 1.8055555555555555e-05, |
| "loss": 0.0002, |
| "step": 2025 |
| }, |
| { |
| "epoch": 2.05, |
| "grad_norm": 0.002351736184209585, |
| "learning_rate": 1.7592592592592595e-05, |
| "loss": 0.0002, |
| "step": 2050 |
| }, |
| { |
| "epoch": 2.075, |
| "grad_norm": 0.001802345854230225, |
| "learning_rate": 1.712962962962963e-05, |
| "loss": 0.0002, |
| "step": 2075 |
| }, |
| { |
| "epoch": 2.1, |
| "grad_norm": 0.004205259494483471, |
| "learning_rate": 1.6666666666666667e-05, |
| "loss": 0.0002, |
| "step": 2100 |
| }, |
| { |
| "epoch": 2.125, |
| "grad_norm": 0.0024293495807796717, |
| "learning_rate": 1.6203703703703704e-05, |
| "loss": 0.0001, |
| "step": 2125 |
| }, |
| { |
| "epoch": 2.15, |
| "grad_norm": 0.002529233694076538, |
| "learning_rate": 1.574074074074074e-05, |
| "loss": 0.0002, |
| "step": 2150 |
| }, |
| { |
| "epoch": 2.175, |
| "grad_norm": 0.00464004697278142, |
| "learning_rate": 1.527777777777778e-05, |
| "loss": 0.0002, |
| "step": 2175 |
| }, |
| { |
| "epoch": 2.2, |
| "grad_norm": 0.0022527112159878016, |
| "learning_rate": 1.4814814814814815e-05, |
| "loss": 0.0002, |
| "step": 2200 |
| }, |
| { |
| "epoch": 2.225, |
| "grad_norm": 0.0029627634212374687, |
| "learning_rate": 1.4351851851851853e-05, |
| "loss": 0.0001, |
| "step": 2225 |
| }, |
| { |
| "epoch": 2.25, |
| "grad_norm": 0.003177474718540907, |
| "learning_rate": 1.388888888888889e-05, |
| "loss": 0.0002, |
| "step": 2250 |
| }, |
| { |
| "epoch": 2.275, |
| "grad_norm": 0.0013587498106062412, |
| "learning_rate": 1.3425925925925928e-05, |
| "loss": 0.0001, |
| "step": 2275 |
| }, |
| { |
| "epoch": 2.3, |
| "grad_norm": 0.002243857365101576, |
| "learning_rate": 1.2962962962962962e-05, |
| "loss": 0.0001, |
| "step": 2300 |
| }, |
| { |
| "epoch": 2.325, |
| "grad_norm": 0.001520108082331717, |
| "learning_rate": 1.25e-05, |
| "loss": 0.0001, |
| "step": 2325 |
| }, |
| { |
| "epoch": 2.35, |
| "grad_norm": 0.001689109718427062, |
| "learning_rate": 1.2037037037037037e-05, |
| "loss": 0.0001, |
| "step": 2350 |
| }, |
| { |
| "epoch": 2.375, |
| "grad_norm": 0.0024859753903001547, |
| "learning_rate": 1.1574074074074075e-05, |
| "loss": 0.0001, |
| "step": 2375 |
| }, |
| { |
| "epoch": 2.4, |
| "grad_norm": 0.0026000950019806623, |
| "learning_rate": 1.1111111111111112e-05, |
| "loss": 0.0001, |
| "step": 2400 |
| }, |
| { |
| "epoch": 2.425, |
| "grad_norm": 0.002047985326498747, |
| "learning_rate": 1.0648148148148148e-05, |
| "loss": 0.0001, |
| "step": 2425 |
| }, |
| { |
| "epoch": 2.45, |
| "grad_norm": 0.0015425788005813956, |
| "learning_rate": 1.0185185185185185e-05, |
| "loss": 0.0001, |
| "step": 2450 |
| }, |
| { |
| "epoch": 2.475, |
| "grad_norm": 0.0018854117952287197, |
| "learning_rate": 9.722222222222223e-06, |
| "loss": 0.0001, |
| "step": 2475 |
| }, |
| { |
| "epoch": 2.5, |
| "grad_norm": 0.0014580640709027648, |
| "learning_rate": 9.259259259259259e-06, |
| "loss": 0.0001, |
| "step": 2500 |
| }, |
| { |
| "epoch": 2.525, |
| "grad_norm": 0.0019544586539268494, |
| "learning_rate": 8.796296296296297e-06, |
| "loss": 0.0001, |
| "step": 2525 |
| }, |
| { |
| "epoch": 2.55, |
| "grad_norm": 0.0023410411085933447, |
| "learning_rate": 8.333333333333334e-06, |
| "loss": 0.0001, |
| "step": 2550 |
| }, |
| { |
| "epoch": 2.575, |
| "grad_norm": 0.0013650900218635798, |
| "learning_rate": 7.87037037037037e-06, |
| "loss": 0.0001, |
| "step": 2575 |
| }, |
| { |
| "epoch": 2.6, |
| "grad_norm": 0.008295529522001743, |
| "learning_rate": 7.4074074074074075e-06, |
| "loss": 0.0001, |
| "step": 2600 |
| }, |
| { |
| "epoch": 2.625, |
| "grad_norm": 0.0017800548812374473, |
| "learning_rate": 6.944444444444445e-06, |
| "loss": 0.0001, |
| "step": 2625 |
| }, |
| { |
| "epoch": 2.65, |
| "grad_norm": 0.0020650553051382303, |
| "learning_rate": 6.481481481481481e-06, |
| "loss": 0.0001, |
| "step": 2650 |
| }, |
| { |
| "epoch": 2.675, |
| "grad_norm": 0.002936688484624028, |
| "learning_rate": 6.0185185185185185e-06, |
| "loss": 0.0001, |
| "step": 2675 |
| }, |
| { |
| "epoch": 2.7, |
| "grad_norm": 0.0020264526829123497, |
| "learning_rate": 5.555555555555556e-06, |
| "loss": 0.0001, |
| "step": 2700 |
| }, |
| { |
| "epoch": 2.725, |
| "grad_norm": 0.001260068267583847, |
| "learning_rate": 5.092592592592592e-06, |
| "loss": 0.0001, |
| "step": 2725 |
| }, |
| { |
| "epoch": 2.75, |
| "grad_norm": 0.0013758167624473572, |
| "learning_rate": 4.6296296296296296e-06, |
| "loss": 0.0001, |
| "step": 2750 |
| }, |
| { |
| "epoch": 2.775, |
| "grad_norm": 0.0018719694344326854, |
| "learning_rate": 4.166666666666667e-06, |
| "loss": 0.0001, |
| "step": 2775 |
| }, |
| { |
| "epoch": 2.8, |
| "grad_norm": 0.0019297786056995392, |
| "learning_rate": 3.7037037037037037e-06, |
| "loss": 0.0001, |
| "step": 2800 |
| }, |
| { |
| "epoch": 2.825, |
| "grad_norm": 0.0015490080695599318, |
| "learning_rate": 3.2407407407407406e-06, |
| "loss": 0.0001, |
| "step": 2825 |
| }, |
| { |
| "epoch": 2.85, |
| "grad_norm": 0.0017714012647047639, |
| "learning_rate": 2.777777777777778e-06, |
| "loss": 0.0001, |
| "step": 2850 |
| }, |
| { |
| "epoch": 2.875, |
| "grad_norm": 0.001514387782663107, |
| "learning_rate": 2.3148148148148148e-06, |
| "loss": 0.0001, |
| "step": 2875 |
| }, |
| { |
| "epoch": 2.9, |
| "grad_norm": 0.0017558818217366934, |
| "learning_rate": 1.8518518518518519e-06, |
| "loss": 0.0001, |
| "step": 2900 |
| }, |
| { |
| "epoch": 2.925, |
| "grad_norm": 0.0014736577868461609, |
| "learning_rate": 1.388888888888889e-06, |
| "loss": 0.0001, |
| "step": 2925 |
| }, |
| { |
| "epoch": 2.95, |
| "grad_norm": 0.0018687807023525238, |
| "learning_rate": 9.259259259259259e-07, |
| "loss": 0.0001, |
| "step": 2950 |
| }, |
| { |
| "epoch": 2.975, |
| "grad_norm": 0.0012901716399937868, |
| "learning_rate": 4.6296296296296297e-07, |
| "loss": 0.0001, |
| "step": 2975 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.001818928518332541, |
| "learning_rate": 0.0, |
| "loss": 0.0001, |
| "step": 3000 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 1.0, |
| "eval_f1_macro": 1.0, |
| "eval_f1_micro": 1.0, |
| "eval_f1_weighted": 1.0, |
| "eval_loss": 6.676162593066692e-05, |
| "eval_precision_macro": 1.0, |
| "eval_precision_micro": 1.0, |
| "eval_precision_weighted": 1.0, |
| "eval_recall_macro": 1.0, |
| "eval_recall_micro": 1.0, |
| "eval_recall_weighted": 1.0, |
| "eval_runtime": 241.5667, |
| "eval_samples_per_second": 8.279, |
| "eval_steps_per_second": 0.517, |
| "step": 3000 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 3000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 5, |
| "early_stopping_threshold": 0.01 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 2 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 794875262976000.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
