| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.4, | |
| "eval_steps": 500, | |
| "global_step": 160, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "Batch Mean": 2.64666748046875, | |
| "accuracy": 0.484375, | |
| "epoch": 0, | |
| "step": 0 | |
| }, | |
| { | |
| "epoch": 0.0025, | |
| "grad_norm": 9.6364107131958, | |
| "learning_rate": 2.5000000000000004e-07, | |
| "loss": 0.723, | |
| "step": 1 | |
| }, | |
| { | |
| "Batch Mean": 2.6478805541992188, | |
| "accuracy": 0.46875, | |
| "epoch": 0.0025, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005, | |
| "grad_norm": 7.393254280090332, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 0.7006, | |
| "step": 2 | |
| }, | |
| { | |
| "Batch Mean": 2.62982177734375, | |
| "accuracy": 0.4453125, | |
| "epoch": 0.005, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0075, | |
| "grad_norm": 8.464498519897461, | |
| "learning_rate": 7.5e-07, | |
| "loss": 0.7093, | |
| "step": 3 | |
| }, | |
| { | |
| "Batch Mean": 2.6655197143554688, | |
| "accuracy": 0.5, | |
| "epoch": 0.0075, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 7.2742462158203125, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.7101, | |
| "step": 4 | |
| }, | |
| { | |
| "Batch Mean": 2.616424560546875, | |
| "accuracy": 0.4296875, | |
| "epoch": 0.01, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0125, | |
| "grad_norm": 8.216493606567383, | |
| "learning_rate": 1.25e-06, | |
| "loss": 0.7145, | |
| "step": 5 | |
| }, | |
| { | |
| "Batch Mean": 2.6591033935546875, | |
| "accuracy": 0.546875, | |
| "epoch": 0.0125, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015, | |
| "grad_norm": 8.033185958862305, | |
| "learning_rate": 1.5e-06, | |
| "loss": 0.6821, | |
| "step": 6 | |
| }, | |
| { | |
| "Batch Mean": 2.6329345703125, | |
| "accuracy": 0.640625, | |
| "epoch": 0.015, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0175, | |
| "grad_norm": 10.476421356201172, | |
| "learning_rate": 1.75e-06, | |
| "loss": 0.6911, | |
| "step": 7 | |
| }, | |
| { | |
| "Batch Mean": 2.680908203125, | |
| "accuracy": 0.5859375, | |
| "epoch": 0.0175, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 9.513436317443848, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.6859, | |
| "step": 8 | |
| }, | |
| { | |
| "Batch Mean": 2.658843994140625, | |
| "accuracy": 0.53125, | |
| "epoch": 0.02, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0225, | |
| "grad_norm": 7.415161609649658, | |
| "learning_rate": 2.25e-06, | |
| "loss": 0.6839, | |
| "step": 9 | |
| }, | |
| { | |
| "Batch Mean": 2.74237060546875, | |
| "accuracy": 0.6328125, | |
| "epoch": 0.0225, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.025, | |
| "grad_norm": 6.572882175445557, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.6557, | |
| "step": 10 | |
| }, | |
| { | |
| "Batch Mean": 2.9183349609375, | |
| "accuracy": 0.65625, | |
| "epoch": 0.025, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0275, | |
| "grad_norm": 6.594631671905518, | |
| "learning_rate": 2.7500000000000004e-06, | |
| "loss": 0.6336, | |
| "step": 11 | |
| }, | |
| { | |
| "Batch Mean": 2.929656982421875, | |
| "accuracy": 0.546875, | |
| "epoch": 0.0275, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 6.199557304382324, | |
| "learning_rate": 3e-06, | |
| "loss": 0.6784, | |
| "step": 12 | |
| }, | |
| { | |
| "Batch Mean": 2.938323974609375, | |
| "accuracy": 0.59375, | |
| "epoch": 0.03, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0325, | |
| "grad_norm": 8.091628074645996, | |
| "learning_rate": 3.2500000000000002e-06, | |
| "loss": 0.6887, | |
| "step": 13 | |
| }, | |
| { | |
| "Batch Mean": 3.0481414794921875, | |
| "accuracy": 0.6171875, | |
| "epoch": 0.0325, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.035, | |
| "grad_norm": 8.876925468444824, | |
| "learning_rate": 3.5e-06, | |
| "loss": 0.6421, | |
| "step": 14 | |
| }, | |
| { | |
| "Batch Mean": 3.2818450927734375, | |
| "accuracy": 0.703125, | |
| "epoch": 0.035, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0375, | |
| "grad_norm": 10.33357048034668, | |
| "learning_rate": 3.7500000000000005e-06, | |
| "loss": 0.5853, | |
| "step": 15 | |
| }, | |
| { | |
| "Batch Mean": 3.2837677001953125, | |
| "accuracy": 0.625, | |
| "epoch": 0.0375, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 11.141650199890137, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.6495, | |
| "step": 16 | |
| }, | |
| { | |
| "Batch Mean": 3.2836532592773438, | |
| "accuracy": 0.6015625, | |
| "epoch": 0.04, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0425, | |
| "grad_norm": 8.093420028686523, | |
| "learning_rate": 4.25e-06, | |
| "loss": 0.6607, | |
| "step": 17 | |
| }, | |
| { | |
| "Batch Mean": 3.3738174438476562, | |
| "accuracy": 0.65625, | |
| "epoch": 0.0425, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.045, | |
| "grad_norm": 8.171963691711426, | |
| "learning_rate": 4.5e-06, | |
| "loss": 0.5946, | |
| "step": 18 | |
| }, | |
| { | |
| "Batch Mean": 3.8035507202148438, | |
| "accuracy": 0.6015625, | |
| "epoch": 0.045, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0475, | |
| "grad_norm": 10.379010200500488, | |
| "learning_rate": 4.75e-06, | |
| "loss": 0.62, | |
| "step": 19 | |
| }, | |
| { | |
| "Batch Mean": 4.241037845611572, | |
| "accuracy": 0.7421875, | |
| "epoch": 0.0475, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 8.072366714477539, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6094, | |
| "step": 20 | |
| }, | |
| { | |
| "Batch Mean": 4.397010803222656, | |
| "accuracy": 0.65625, | |
| "epoch": 0.05, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0525, | |
| "grad_norm": 7.2537384033203125, | |
| "learning_rate": 4.986842105263158e-06, | |
| "loss": 0.5916, | |
| "step": 21 | |
| }, | |
| { | |
| "Batch Mean": 4.36688232421875, | |
| "accuracy": 0.671875, | |
| "epoch": 0.0525, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.055, | |
| "grad_norm": 8.559549331665039, | |
| "learning_rate": 4.973684210526316e-06, | |
| "loss": 0.5884, | |
| "step": 22 | |
| }, | |
| { | |
| "Batch Mean": 4.482940673828125, | |
| "accuracy": 0.6640625, | |
| "epoch": 0.055, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0575, | |
| "grad_norm": 8.731099128723145, | |
| "learning_rate": 4.960526315789474e-06, | |
| "loss": 0.6106, | |
| "step": 23 | |
| }, | |
| { | |
| "Batch Mean": 4.41278076171875, | |
| "accuracy": 0.7109375, | |
| "epoch": 0.0575, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 6.149895191192627, | |
| "learning_rate": 4.947368421052632e-06, | |
| "loss": 0.5569, | |
| "step": 24 | |
| }, | |
| { | |
| "Batch Mean": 4.1328277587890625, | |
| "accuracy": 0.6484375, | |
| "epoch": 0.06, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0625, | |
| "grad_norm": 6.8678879737854, | |
| "learning_rate": 4.9342105263157895e-06, | |
| "loss": 0.5729, | |
| "step": 25 | |
| }, | |
| { | |
| "Batch Mean": 3.8360061645507812, | |
| "accuracy": 0.6484375, | |
| "epoch": 0.0625, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.065, | |
| "grad_norm": 6.591639041900635, | |
| "learning_rate": 4.921052631578948e-06, | |
| "loss": 0.5902, | |
| "step": 26 | |
| }, | |
| { | |
| "Batch Mean": 3.9048538208007812, | |
| "accuracy": 0.6953125, | |
| "epoch": 0.065, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0675, | |
| "grad_norm": 5.855933666229248, | |
| "learning_rate": 4.907894736842106e-06, | |
| "loss": 0.5666, | |
| "step": 27 | |
| }, | |
| { | |
| "Batch Mean": 3.7672348022460938, | |
| "accuracy": 0.6953125, | |
| "epoch": 0.0675, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 5.393594264984131, | |
| "learning_rate": 4.894736842105264e-06, | |
| "loss": 0.5508, | |
| "step": 28 | |
| }, | |
| { | |
| "Batch Mean": 3.723773956298828, | |
| "accuracy": 0.65625, | |
| "epoch": 0.07, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0725, | |
| "grad_norm": 5.428353786468506, | |
| "learning_rate": 4.881578947368422e-06, | |
| "loss": 0.5694, | |
| "step": 29 | |
| }, | |
| { | |
| "Batch Mean": 3.7498779296875, | |
| "accuracy": 0.6953125, | |
| "epoch": 0.0725, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.075, | |
| "grad_norm": 5.005551338195801, | |
| "learning_rate": 4.8684210526315795e-06, | |
| "loss": 0.5905, | |
| "step": 30 | |
| }, | |
| { | |
| "Batch Mean": 3.564330577850342, | |
| "accuracy": 0.671875, | |
| "epoch": 0.075, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0775, | |
| "grad_norm": 6.4090681076049805, | |
| "learning_rate": 4.855263157894737e-06, | |
| "loss": 0.5901, | |
| "step": 31 | |
| }, | |
| { | |
| "Batch Mean": 3.5886306762695312, | |
| "accuracy": 0.7421875, | |
| "epoch": 0.0775, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 6.025192737579346, | |
| "learning_rate": 4.842105263157895e-06, | |
| "loss": 0.5265, | |
| "step": 32 | |
| }, | |
| { | |
| "Batch Mean": 3.64593505859375, | |
| "accuracy": 0.6953125, | |
| "epoch": 0.08, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0825, | |
| "grad_norm": 6.129398345947266, | |
| "learning_rate": 4.828947368421053e-06, | |
| "loss": 0.5083, | |
| "step": 33 | |
| }, | |
| { | |
| "Batch Mean": 3.5973358154296875, | |
| "accuracy": 0.6875, | |
| "epoch": 0.0825, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.085, | |
| "grad_norm": 6.91660737991333, | |
| "learning_rate": 4.815789473684211e-06, | |
| "loss": 0.5365, | |
| "step": 34 | |
| }, | |
| { | |
| "Batch Mean": 3.6286163330078125, | |
| "accuracy": 0.7109375, | |
| "epoch": 0.085, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0875, | |
| "grad_norm": 7.553361892700195, | |
| "learning_rate": 4.802631578947369e-06, | |
| "loss": 0.5196, | |
| "step": 35 | |
| }, | |
| { | |
| "Batch Mean": 3.5937328338623047, | |
| "accuracy": 0.7109375, | |
| "epoch": 0.0875, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 7.884591579437256, | |
| "learning_rate": 4.789473684210527e-06, | |
| "loss": 0.5533, | |
| "step": 36 | |
| }, | |
| { | |
| "Batch Mean": 3.28558349609375, | |
| "accuracy": 0.6796875, | |
| "epoch": 0.09, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0925, | |
| "grad_norm": 8.118135452270508, | |
| "learning_rate": 4.7763157894736844e-06, | |
| "loss": 0.5145, | |
| "step": 37 | |
| }, | |
| { | |
| "Batch Mean": 3.079477310180664, | |
| "accuracy": 0.7421875, | |
| "epoch": 0.0925, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.095, | |
| "grad_norm": 10.431463241577148, | |
| "learning_rate": 4.763157894736842e-06, | |
| "loss": 0.6, | |
| "step": 38 | |
| }, | |
| { | |
| "Batch Mean": 2.9296703338623047, | |
| "accuracy": 0.7578125, | |
| "epoch": 0.095, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0975, | |
| "grad_norm": 8.055816650390625, | |
| "learning_rate": 4.75e-06, | |
| "loss": 0.445, | |
| "step": 39 | |
| }, | |
| { | |
| "Batch Mean": 2.9282093048095703, | |
| "accuracy": 0.7109375, | |
| "epoch": 0.0975, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 9.155073165893555, | |
| "learning_rate": 4.736842105263158e-06, | |
| "loss": 0.5568, | |
| "step": 40 | |
| }, | |
| { | |
| "Batch Mean": 2.4473862648010254, | |
| "accuracy": 0.6171875, | |
| "epoch": 0.1, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1025, | |
| "grad_norm": 8.89163589477539, | |
| "learning_rate": 4.723684210526316e-06, | |
| "loss": 0.5934, | |
| "step": 41 | |
| }, | |
| { | |
| "Batch Mean": 2.4439845085144043, | |
| "accuracy": 0.6953125, | |
| "epoch": 0.1025, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.105, | |
| "grad_norm": 7.411705017089844, | |
| "learning_rate": 4.710526315789474e-06, | |
| "loss": 0.5522, | |
| "step": 42 | |
| }, | |
| { | |
| "Batch Mean": 1.7335999011993408, | |
| "accuracy": 0.734375, | |
| "epoch": 0.105, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1075, | |
| "grad_norm": 7.0730109214782715, | |
| "learning_rate": 4.697368421052632e-06, | |
| "loss": 0.5157, | |
| "step": 43 | |
| }, | |
| { | |
| "Batch Mean": 1.7379779815673828, | |
| "accuracy": 0.71875, | |
| "epoch": 0.1075, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 7.879677772521973, | |
| "learning_rate": 4.68421052631579e-06, | |
| "loss": 0.5405, | |
| "step": 44 | |
| }, | |
| { | |
| "Batch Mean": 1.7085151672363281, | |
| "accuracy": 0.6796875, | |
| "epoch": 0.11, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1125, | |
| "grad_norm": 6.630401611328125, | |
| "learning_rate": 4.671052631578948e-06, | |
| "loss": 0.564, | |
| "step": 45 | |
| }, | |
| { | |
| "Batch Mean": 1.7431907653808594, | |
| "accuracy": 0.734375, | |
| "epoch": 0.1125, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.115, | |
| "grad_norm": 6.569342136383057, | |
| "learning_rate": 4.657894736842106e-06, | |
| "loss": 0.4969, | |
| "step": 46 | |
| }, | |
| { | |
| "Batch Mean": 2.4792041778564453, | |
| "accuracy": 0.6953125, | |
| "epoch": 0.115, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.1175, | |
| "grad_norm": 6.198298931121826, | |
| "learning_rate": 4.6447368421052635e-06, | |
| "loss": 0.5501, | |
| "step": 47 | |
| }, | |
| { | |
| "Batch Mean": 2.4960689544677734, | |
| "accuracy": 0.7578125, | |
| "epoch": 0.1175, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 5.984739780426025, | |
| "learning_rate": 4.631578947368421e-06, | |
| "loss": 0.4513, | |
| "step": 48 | |
| }, | |
| { | |
| "Batch Mean": 2.7437705993652344, | |
| "accuracy": 0.71875, | |
| "epoch": 0.12, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1225, | |
| "grad_norm": 6.669623374938965, | |
| "learning_rate": 4.618421052631579e-06, | |
| "loss": 0.5404, | |
| "step": 49 | |
| }, | |
| { | |
| "Batch Mean": 2.672210693359375, | |
| "accuracy": 0.75, | |
| "epoch": 0.1225, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.125, | |
| "grad_norm": 6.217676639556885, | |
| "learning_rate": 4.605263157894737e-06, | |
| "loss": 0.4668, | |
| "step": 50 | |
| }, | |
| { | |
| "Batch Mean": 2.7935009002685547, | |
| "accuracy": 0.75, | |
| "epoch": 0.125, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1275, | |
| "grad_norm": 7.666802883148193, | |
| "learning_rate": 4.592105263157895e-06, | |
| "loss": 0.5491, | |
| "step": 51 | |
| }, | |
| { | |
| "Batch Mean": 2.651923179626465, | |
| "accuracy": 0.734375, | |
| "epoch": 0.1275, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 9.799866676330566, | |
| "learning_rate": 4.578947368421053e-06, | |
| "loss": 0.5173, | |
| "step": 52 | |
| }, | |
| { | |
| "Batch Mean": 2.9287376403808594, | |
| "accuracy": 0.734375, | |
| "epoch": 0.13, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.1325, | |
| "grad_norm": 8.577540397644043, | |
| "learning_rate": 4.565789473684211e-06, | |
| "loss": 0.5279, | |
| "step": 53 | |
| }, | |
| { | |
| "Batch Mean": 3.0377674102783203, | |
| "accuracy": 0.7265625, | |
| "epoch": 0.1325, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.135, | |
| "grad_norm": 8.099453926086426, | |
| "learning_rate": 4.552631578947369e-06, | |
| "loss": 0.5122, | |
| "step": 54 | |
| }, | |
| { | |
| "Batch Mean": 3.3550057411193848, | |
| "accuracy": 0.6953125, | |
| "epoch": 0.135, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.1375, | |
| "grad_norm": 9.597841262817383, | |
| "learning_rate": 4.539473684210527e-06, | |
| "loss": 0.5034, | |
| "step": 55 | |
| }, | |
| { | |
| "Batch Mean": 3.3833670616149902, | |
| "accuracy": 0.7578125, | |
| "epoch": 0.1375, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 9.208806037902832, | |
| "learning_rate": 4.526315789473685e-06, | |
| "loss": 0.53, | |
| "step": 56 | |
| }, | |
| { | |
| "Batch Mean": 3.255979537963867, | |
| "accuracy": 0.7890625, | |
| "epoch": 0.14, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.1425, | |
| "grad_norm": 7.923739910125732, | |
| "learning_rate": 4.513157894736843e-06, | |
| "loss": 0.4315, | |
| "step": 57 | |
| }, | |
| { | |
| "Batch Mean": 3.003221273422241, | |
| "accuracy": 0.7265625, | |
| "epoch": 0.1425, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.145, | |
| "grad_norm": 8.64991569519043, | |
| "learning_rate": 4.5e-06, | |
| "loss": 0.5038, | |
| "step": 58 | |
| }, | |
| { | |
| "Batch Mean": 3.122058868408203, | |
| "accuracy": 0.78125, | |
| "epoch": 0.145, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.1475, | |
| "grad_norm": 8.633460998535156, | |
| "learning_rate": 4.4868421052631584e-06, | |
| "loss": 0.4886, | |
| "step": 59 | |
| }, | |
| { | |
| "Batch Mean": 2.8752236366271973, | |
| "accuracy": 0.7109375, | |
| "epoch": 0.1475, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 8.399279594421387, | |
| "learning_rate": 4.473684210526316e-06, | |
| "loss": 0.5239, | |
| "step": 60 | |
| }, | |
| { | |
| "Batch Mean": 2.694100856781006, | |
| "accuracy": 0.7578125, | |
| "epoch": 0.15, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.1525, | |
| "grad_norm": 7.846778869628906, | |
| "learning_rate": 4.460526315789474e-06, | |
| "loss": 0.4538, | |
| "step": 61 | |
| }, | |
| { | |
| "Batch Mean": 2.59914493560791, | |
| "accuracy": 0.8046875, | |
| "epoch": 0.1525, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.155, | |
| "grad_norm": 7.844125270843506, | |
| "learning_rate": 4.447368421052632e-06, | |
| "loss": 0.4234, | |
| "step": 62 | |
| }, | |
| { | |
| "Batch Mean": 2.431262493133545, | |
| "accuracy": 0.75, | |
| "epoch": 0.155, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.1575, | |
| "grad_norm": 8.15548038482666, | |
| "learning_rate": 4.43421052631579e-06, | |
| "loss": 0.4695, | |
| "step": 63 | |
| }, | |
| { | |
| "Batch Mean": 2.162135124206543, | |
| "accuracy": 0.7421875, | |
| "epoch": 0.1575, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 9.166322708129883, | |
| "learning_rate": 4.4210526315789476e-06, | |
| "loss": 0.4898, | |
| "step": 64 | |
| }, | |
| { | |
| "Batch Mean": 1.8282737731933594, | |
| "accuracy": 0.75, | |
| "epoch": 0.16, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.1625, | |
| "grad_norm": 9.52655029296875, | |
| "learning_rate": 4.407894736842105e-06, | |
| "loss": 0.4651, | |
| "step": 65 | |
| }, | |
| { | |
| "Batch Mean": 1.9480819702148438, | |
| "accuracy": 0.7890625, | |
| "epoch": 0.1625, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.165, | |
| "grad_norm": 8.491720199584961, | |
| "learning_rate": 4.394736842105263e-06, | |
| "loss": 0.4578, | |
| "step": 66 | |
| }, | |
| { | |
| "Batch Mean": 1.8442394733428955, | |
| "accuracy": 0.7734375, | |
| "epoch": 0.165, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.1675, | |
| "grad_norm": 9.01707649230957, | |
| "learning_rate": 4.381578947368421e-06, | |
| "loss": 0.4858, | |
| "step": 67 | |
| }, | |
| { | |
| "Batch Mean": 1.2759554386138916, | |
| "accuracy": 0.6953125, | |
| "epoch": 0.1675, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 10.790990829467773, | |
| "learning_rate": 4.368421052631579e-06, | |
| "loss": 0.5368, | |
| "step": 68 | |
| }, | |
| { | |
| "Batch Mean": 0.916658878326416, | |
| "accuracy": 0.7109375, | |
| "epoch": 0.17, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.1725, | |
| "grad_norm": 10.27574634552002, | |
| "learning_rate": 4.3552631578947375e-06, | |
| "loss": 0.5475, | |
| "step": 69 | |
| }, | |
| { | |
| "Batch Mean": 0.9389474391937256, | |
| "accuracy": 0.6875, | |
| "epoch": 0.1725, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.175, | |
| "grad_norm": 9.463624954223633, | |
| "learning_rate": 4.342105263157895e-06, | |
| "loss": 0.5295, | |
| "step": 70 | |
| }, | |
| { | |
| "Batch Mean": 0.6801865100860596, | |
| "accuracy": 0.78125, | |
| "epoch": 0.175, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1775, | |
| "grad_norm": 7.813968658447266, | |
| "learning_rate": 4.328947368421053e-06, | |
| "loss": 0.4602, | |
| "step": 71 | |
| }, | |
| { | |
| "Batch Mean": 0.6634016036987305, | |
| "accuracy": 0.78125, | |
| "epoch": 0.1775, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 7.322629928588867, | |
| "learning_rate": 4.315789473684211e-06, | |
| "loss": 0.4328, | |
| "step": 72 | |
| }, | |
| { | |
| "Batch Mean": 0.518225908279419, | |
| "accuracy": 0.8359375, | |
| "epoch": 0.18, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.1825, | |
| "grad_norm": 7.121971130371094, | |
| "learning_rate": 4.302631578947369e-06, | |
| "loss": 0.3997, | |
| "step": 73 | |
| }, | |
| { | |
| "Batch Mean": 0.6286078691482544, | |
| "accuracy": 0.75, | |
| "epoch": 0.1825, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.185, | |
| "grad_norm": 8.812067031860352, | |
| "learning_rate": 4.289473684210527e-06, | |
| "loss": 0.5345, | |
| "step": 74 | |
| }, | |
| { | |
| "Batch Mean": 0.4055500030517578, | |
| "accuracy": 0.78125, | |
| "epoch": 0.185, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.1875, | |
| "grad_norm": 8.031818389892578, | |
| "learning_rate": 4.276315789473684e-06, | |
| "loss": 0.4436, | |
| "step": 75 | |
| }, | |
| { | |
| "Batch Mean": 0.6844688057899475, | |
| "accuracy": 0.6640625, | |
| "epoch": 0.1875, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 9.14492130279541, | |
| "learning_rate": 4.2631578947368425e-06, | |
| "loss": 0.5727, | |
| "step": 76 | |
| }, | |
| { | |
| "Batch Mean": 0.549891471862793, | |
| "accuracy": 0.7578125, | |
| "epoch": 0.19, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.1925, | |
| "grad_norm": 8.721407890319824, | |
| "learning_rate": 4.25e-06, | |
| "loss": 0.4997, | |
| "step": 77 | |
| }, | |
| { | |
| "Batch Mean": 0.3632768988609314, | |
| "accuracy": 0.703125, | |
| "epoch": 0.1925, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.195, | |
| "grad_norm": 8.776328086853027, | |
| "learning_rate": 4.236842105263158e-06, | |
| "loss": 0.5442, | |
| "step": 78 | |
| }, | |
| { | |
| "Batch Mean": 0.4604153633117676, | |
| "accuracy": 0.7421875, | |
| "epoch": 0.195, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.1975, | |
| "grad_norm": 7.281062126159668, | |
| "learning_rate": 4.223684210526316e-06, | |
| "loss": 0.4793, | |
| "step": 79 | |
| }, | |
| { | |
| "Batch Mean": 0.605268120765686, | |
| "accuracy": 0.765625, | |
| "epoch": 0.1975, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 7.533178329467773, | |
| "learning_rate": 4.210526315789474e-06, | |
| "loss": 0.4338, | |
| "step": 80 | |
| }, | |
| { | |
| "Batch Mean": 0.9789919257164001, | |
| "accuracy": 0.75, | |
| "epoch": 0.2, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2025, | |
| "grad_norm": 7.2433671951293945, | |
| "learning_rate": 4.197368421052632e-06, | |
| "loss": 0.4785, | |
| "step": 81 | |
| }, | |
| { | |
| "Batch Mean": 1.114579200744629, | |
| "accuracy": 0.71875, | |
| "epoch": 0.2025, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.205, | |
| "grad_norm": 7.2934064865112305, | |
| "learning_rate": 4.18421052631579e-06, | |
| "loss": 0.4836, | |
| "step": 82 | |
| }, | |
| { | |
| "Batch Mean": 1.0528812408447266, | |
| "accuracy": 0.7578125, | |
| "epoch": 0.205, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.2075, | |
| "grad_norm": 7.544822692871094, | |
| "learning_rate": 4.171052631578948e-06, | |
| "loss": 0.5077, | |
| "step": 83 | |
| }, | |
| { | |
| "Batch Mean": 1.1365894079208374, | |
| "accuracy": 0.671875, | |
| "epoch": 0.2075, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 8.340349197387695, | |
| "learning_rate": 4.157894736842106e-06, | |
| "loss": 0.579, | |
| "step": 84 | |
| }, | |
| { | |
| "Batch Mean": 1.7320103645324707, | |
| "accuracy": 0.8125, | |
| "epoch": 0.21, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.2125, | |
| "grad_norm": 6.645724296569824, | |
| "learning_rate": 4.144736842105263e-06, | |
| "loss": 0.4114, | |
| "step": 85 | |
| }, | |
| { | |
| "Batch Mean": 1.443530559539795, | |
| "accuracy": 0.7578125, | |
| "epoch": 0.2125, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.215, | |
| "grad_norm": 6.647582530975342, | |
| "learning_rate": 4.1315789473684216e-06, | |
| "loss": 0.4369, | |
| "step": 86 | |
| }, | |
| { | |
| "Batch Mean": 1.5358202457427979, | |
| "accuracy": 0.7578125, | |
| "epoch": 0.215, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.2175, | |
| "grad_norm": 7.315903186798096, | |
| "learning_rate": 4.118421052631579e-06, | |
| "loss": 0.4895, | |
| "step": 87 | |
| }, | |
| { | |
| "Batch Mean": 1.7256877422332764, | |
| "accuracy": 0.7734375, | |
| "epoch": 0.2175, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 8.285420417785645, | |
| "learning_rate": 4.105263157894737e-06, | |
| "loss": 0.5035, | |
| "step": 88 | |
| }, | |
| { | |
| "Batch Mean": 1.5997413396835327, | |
| "accuracy": 0.75, | |
| "epoch": 0.22, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.2225, | |
| "grad_norm": 7.990715026855469, | |
| "learning_rate": 4.092105263157895e-06, | |
| "loss": 0.51, | |
| "step": 89 | |
| }, | |
| { | |
| "Batch Mean": 1.6425485610961914, | |
| "accuracy": 0.734375, | |
| "epoch": 0.2225, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.225, | |
| "grad_norm": 8.72641658782959, | |
| "learning_rate": 4.078947368421053e-06, | |
| "loss": 0.4908, | |
| "step": 90 | |
| }, | |
| { | |
| "Batch Mean": 1.9212679862976074, | |
| "accuracy": 0.84375, | |
| "epoch": 0.225, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.2275, | |
| "grad_norm": 7.567220211029053, | |
| "learning_rate": 4.065789473684211e-06, | |
| "loss": 0.4152, | |
| "step": 91 | |
| }, | |
| { | |
| "Batch Mean": 1.6822540760040283, | |
| "accuracy": 0.8046875, | |
| "epoch": 0.2275, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 7.402642726898193, | |
| "learning_rate": 4.052631578947368e-06, | |
| "loss": 0.4054, | |
| "step": 92 | |
| }, | |
| { | |
| "Batch Mean": 1.5377750396728516, | |
| "accuracy": 0.75, | |
| "epoch": 0.23, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.2325, | |
| "grad_norm": 8.574016571044922, | |
| "learning_rate": 4.0394736842105265e-06, | |
| "loss": 0.4739, | |
| "step": 93 | |
| }, | |
| { | |
| "Batch Mean": 1.332385540008545, | |
| "accuracy": 0.734375, | |
| "epoch": 0.2325, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.235, | |
| "grad_norm": 8.827500343322754, | |
| "learning_rate": 4.026315789473684e-06, | |
| "loss": 0.4983, | |
| "step": 94 | |
| }, | |
| { | |
| "Batch Mean": 1.0707147121429443, | |
| "accuracy": 0.8046875, | |
| "epoch": 0.235, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.2375, | |
| "grad_norm": 7.975078105926514, | |
| "learning_rate": 4.013157894736842e-06, | |
| "loss": 0.4709, | |
| "step": 95 | |
| }, | |
| { | |
| "Batch Mean": 1.1354491710662842, | |
| "accuracy": 0.75, | |
| "epoch": 0.2375, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 7.764720916748047, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.4697, | |
| "step": 96 | |
| }, | |
| { | |
| "Batch Mean": 0.7834959030151367, | |
| "accuracy": 0.765625, | |
| "epoch": 0.24, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.2425, | |
| "grad_norm": 8.38682746887207, | |
| "learning_rate": 3.986842105263158e-06, | |
| "loss": 0.46, | |
| "step": 97 | |
| }, | |
| { | |
| "Batch Mean": 0.9441508650779724, | |
| "accuracy": 0.8359375, | |
| "epoch": 0.2425, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.245, | |
| "grad_norm": 8.565149307250977, | |
| "learning_rate": 3.9736842105263165e-06, | |
| "loss": 0.4071, | |
| "step": 98 | |
| }, | |
| { | |
| "Batch Mean": 0.8886473178863525, | |
| "accuracy": 0.8203125, | |
| "epoch": 0.245, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.2475, | |
| "grad_norm": 7.316027641296387, | |
| "learning_rate": 3.960526315789474e-06, | |
| "loss": 0.413, | |
| "step": 99 | |
| }, | |
| { | |
| "Batch Mean": 1.3381073474884033, | |
| "accuracy": 0.765625, | |
| "epoch": 0.2475, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 7.380762577056885, | |
| "learning_rate": 3.947368421052632e-06, | |
| "loss": 0.4639, | |
| "step": 100 | |
| }, | |
| { | |
| "Batch Mean": 1.8181347846984863, | |
| "accuracy": 0.78125, | |
| "epoch": 0.25, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2525, | |
| "grad_norm": 8.348108291625977, | |
| "learning_rate": 3.93421052631579e-06, | |
| "loss": 0.4568, | |
| "step": 101 | |
| }, | |
| { | |
| "Batch Mean": 1.850348711013794, | |
| "accuracy": 0.828125, | |
| "epoch": 0.2525, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.255, | |
| "grad_norm": 7.533435821533203, | |
| "learning_rate": 3.921052631578947e-06, | |
| "loss": 0.4471, | |
| "step": 102 | |
| }, | |
| { | |
| "Batch Mean": 1.8302688598632812, | |
| "accuracy": 0.7265625, | |
| "epoch": 0.255, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.2575, | |
| "grad_norm": 7.560754776000977, | |
| "learning_rate": 3.907894736842106e-06, | |
| "loss": 0.4922, | |
| "step": 103 | |
| }, | |
| { | |
| "Batch Mean": 1.832013487815857, | |
| "accuracy": 0.7734375, | |
| "epoch": 0.2575, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 8.4998197555542, | |
| "learning_rate": 3.894736842105263e-06, | |
| "loss": 0.4636, | |
| "step": 104 | |
| }, | |
| { | |
| "Batch Mean": 1.9380416870117188, | |
| "accuracy": 0.7421875, | |
| "epoch": 0.26, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.2625, | |
| "grad_norm": 8.759364128112793, | |
| "learning_rate": 3.8815789473684214e-06, | |
| "loss": 0.5117, | |
| "step": 105 | |
| }, | |
| { | |
| "Batch Mean": 2.0537302494049072, | |
| "accuracy": 0.78125, | |
| "epoch": 0.2625, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.265, | |
| "grad_norm": 7.300965785980225, | |
| "learning_rate": 3.868421052631579e-06, | |
| "loss": 0.3956, | |
| "step": 106 | |
| }, | |
| { | |
| "Batch Mean": 2.236231803894043, | |
| "accuracy": 0.7890625, | |
| "epoch": 0.265, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.2675, | |
| "grad_norm": 7.826519012451172, | |
| "learning_rate": 3.855263157894737e-06, | |
| "loss": 0.462, | |
| "step": 107 | |
| }, | |
| { | |
| "Batch Mean": 2.2571160793304443, | |
| "accuracy": 0.78125, | |
| "epoch": 0.2675, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 7.177440643310547, | |
| "learning_rate": 3.842105263157895e-06, | |
| "loss": 0.4264, | |
| "step": 108 | |
| }, | |
| { | |
| "Batch Mean": 2.3395166397094727, | |
| "accuracy": 0.8359375, | |
| "epoch": 0.27, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.2725, | |
| "grad_norm": 7.556861877441406, | |
| "learning_rate": 3.828947368421053e-06, | |
| "loss": 0.3825, | |
| "step": 109 | |
| }, | |
| { | |
| "Batch Mean": 2.5364012718200684, | |
| "accuracy": 0.7890625, | |
| "epoch": 0.2725, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.275, | |
| "grad_norm": 8.785236358642578, | |
| "learning_rate": 3.815789473684211e-06, | |
| "loss": 0.4915, | |
| "step": 110 | |
| }, | |
| { | |
| "Batch Mean": 2.545170783996582, | |
| "accuracy": 0.71875, | |
| "epoch": 0.275, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2775, | |
| "grad_norm": 8.062837600708008, | |
| "learning_rate": 3.802631578947369e-06, | |
| "loss": 0.5025, | |
| "step": 111 | |
| }, | |
| { | |
| "Batch Mean": 2.6232008934020996, | |
| "accuracy": 0.7734375, | |
| "epoch": 0.2775, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 7.3966498374938965, | |
| "learning_rate": 3.789473684210527e-06, | |
| "loss": 0.4145, | |
| "step": 112 | |
| }, | |
| { | |
| "Batch Mean": 2.351048469543457, | |
| "accuracy": 0.6953125, | |
| "epoch": 0.28, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.2825, | |
| "grad_norm": 7.810081958770752, | |
| "learning_rate": 3.7763157894736847e-06, | |
| "loss": 0.5147, | |
| "step": 113 | |
| }, | |
| { | |
| "Batch Mean": 1.6083295345306396, | |
| "accuracy": 0.796875, | |
| "epoch": 0.2825, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.285, | |
| "grad_norm": 6.8766703605651855, | |
| "learning_rate": 3.7631578947368426e-06, | |
| "loss": 0.4275, | |
| "step": 114 | |
| }, | |
| { | |
| "Batch Mean": 1.594513177871704, | |
| "accuracy": 0.8046875, | |
| "epoch": 0.285, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.2875, | |
| "grad_norm": 7.07267427444458, | |
| "learning_rate": 3.7500000000000005e-06, | |
| "loss": 0.4197, | |
| "step": 115 | |
| }, | |
| { | |
| "Batch Mean": 1.6583623886108398, | |
| "accuracy": 0.7421875, | |
| "epoch": 0.2875, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 8.415107727050781, | |
| "learning_rate": 3.736842105263158e-06, | |
| "loss": 0.4723, | |
| "step": 116 | |
| }, | |
| { | |
| "Batch Mean": 1.6947704553604126, | |
| "accuracy": 0.8203125, | |
| "epoch": 0.29, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.2925, | |
| "grad_norm": 7.132028102874756, | |
| "learning_rate": 3.723684210526316e-06, | |
| "loss": 0.4039, | |
| "step": 117 | |
| }, | |
| { | |
| "Batch Mean": 1.7144229412078857, | |
| "accuracy": 0.8046875, | |
| "epoch": 0.2925, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.295, | |
| "grad_norm": 6.850518703460693, | |
| "learning_rate": 3.710526315789474e-06, | |
| "loss": 0.4148, | |
| "step": 118 | |
| }, | |
| { | |
| "Batch Mean": 1.4002912044525146, | |
| "accuracy": 0.828125, | |
| "epoch": 0.295, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.2975, | |
| "grad_norm": 7.008551120758057, | |
| "learning_rate": 3.6973684210526317e-06, | |
| "loss": 0.3972, | |
| "step": 119 | |
| }, | |
| { | |
| "Batch Mean": 1.1955918073654175, | |
| "accuracy": 0.7890625, | |
| "epoch": 0.2975, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 8.176568984985352, | |
| "learning_rate": 3.6842105263157896e-06, | |
| "loss": 0.4894, | |
| "step": 120 | |
| }, | |
| { | |
| "Batch Mean": 1.4260971546173096, | |
| "accuracy": 0.765625, | |
| "epoch": 0.3, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3025, | |
| "grad_norm": 7.905389308929443, | |
| "learning_rate": 3.6710526315789476e-06, | |
| "loss": 0.4796, | |
| "step": 121 | |
| }, | |
| { | |
| "Batch Mean": 1.1381725072860718, | |
| "accuracy": 0.84375, | |
| "epoch": 0.3025, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.305, | |
| "grad_norm": 7.464083194732666, | |
| "learning_rate": 3.657894736842106e-06, | |
| "loss": 0.387, | |
| "step": 122 | |
| }, | |
| { | |
| "Batch Mean": 1.064018726348877, | |
| "accuracy": 0.8125, | |
| "epoch": 0.305, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.3075, | |
| "grad_norm": 8.280699729919434, | |
| "learning_rate": 3.644736842105264e-06, | |
| "loss": 0.4154, | |
| "step": 123 | |
| }, | |
| { | |
| "Batch Mean": 1.3708758354187012, | |
| "accuracy": 0.765625, | |
| "epoch": 0.3075, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 9.830754280090332, | |
| "learning_rate": 3.6315789473684217e-06, | |
| "loss": 0.5003, | |
| "step": 124 | |
| }, | |
| { | |
| "Batch Mean": 1.162580132484436, | |
| "accuracy": 0.828125, | |
| "epoch": 0.31, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.3125, | |
| "grad_norm": 8.671696662902832, | |
| "learning_rate": 3.618421052631579e-06, | |
| "loss": 0.4389, | |
| "step": 125 | |
| }, | |
| { | |
| "Batch Mean": 0.671147346496582, | |
| "accuracy": 0.8125, | |
| "epoch": 0.3125, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.315, | |
| "grad_norm": 8.493339538574219, | |
| "learning_rate": 3.605263157894737e-06, | |
| "loss": 0.4434, | |
| "step": 126 | |
| }, | |
| { | |
| "Batch Mean": 0.8207384347915649, | |
| "accuracy": 0.8203125, | |
| "epoch": 0.315, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.3175, | |
| "grad_norm": 8.274676322937012, | |
| "learning_rate": 3.592105263157895e-06, | |
| "loss": 0.4057, | |
| "step": 127 | |
| }, | |
| { | |
| "Batch Mean": 0.5156043767929077, | |
| "accuracy": 0.75, | |
| "epoch": 0.3175, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 9.094855308532715, | |
| "learning_rate": 3.578947368421053e-06, | |
| "loss": 0.4661, | |
| "step": 128 | |
| }, | |
| { | |
| "Batch Mean": 0.43193674087524414, | |
| "accuracy": 0.8203125, | |
| "epoch": 0.32, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.3225, | |
| "grad_norm": 8.729266166687012, | |
| "learning_rate": 3.565789473684211e-06, | |
| "loss": 0.4586, | |
| "step": 129 | |
| }, | |
| { | |
| "Batch Mean": 0.30504658818244934, | |
| "accuracy": 0.7421875, | |
| "epoch": 0.3225, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.325, | |
| "grad_norm": 11.113021850585938, | |
| "learning_rate": 3.5526315789473687e-06, | |
| "loss": 0.4894, | |
| "step": 130 | |
| }, | |
| { | |
| "Batch Mean": 0.3271394371986389, | |
| "accuracy": 0.7734375, | |
| "epoch": 0.325, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3275, | |
| "grad_norm": 8.692556381225586, | |
| "learning_rate": 3.5394736842105266e-06, | |
| "loss": 0.4227, | |
| "step": 131 | |
| }, | |
| { | |
| "Batch Mean": 0.6269352436065674, | |
| "accuracy": 0.7734375, | |
| "epoch": 0.3275, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 8.046867370605469, | |
| "learning_rate": 3.5263157894736846e-06, | |
| "loss": 0.496, | |
| "step": 132 | |
| }, | |
| { | |
| "Batch Mean": 0.6559182405471802, | |
| "accuracy": 0.765625, | |
| "epoch": 0.33, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.3325, | |
| "grad_norm": 7.385076999664307, | |
| "learning_rate": 3.513157894736842e-06, | |
| "loss": 0.4459, | |
| "step": 133 | |
| }, | |
| { | |
| "Batch Mean": 0.5328922271728516, | |
| "accuracy": 0.7578125, | |
| "epoch": 0.3325, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.335, | |
| "grad_norm": 7.108922481536865, | |
| "learning_rate": 3.5e-06, | |
| "loss": 0.428, | |
| "step": 134 | |
| }, | |
| { | |
| "Batch Mean": 1.1600193977355957, | |
| "accuracy": 0.828125, | |
| "epoch": 0.335, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.3375, | |
| "grad_norm": 6.962152004241943, | |
| "learning_rate": 3.486842105263158e-06, | |
| "loss": 0.4237, | |
| "step": 135 | |
| }, | |
| { | |
| "Batch Mean": 1.1642009019851685, | |
| "accuracy": 0.6953125, | |
| "epoch": 0.3375, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 7.879281520843506, | |
| "learning_rate": 3.473684210526316e-06, | |
| "loss": 0.528, | |
| "step": 136 | |
| }, | |
| { | |
| "Batch Mean": 1.0588830709457397, | |
| "accuracy": 0.6953125, | |
| "epoch": 0.34, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.3425, | |
| "grad_norm": 9.492472648620605, | |
| "learning_rate": 3.460526315789474e-06, | |
| "loss": 0.5365, | |
| "step": 137 | |
| }, | |
| { | |
| "Batch Mean": 1.3413481712341309, | |
| "accuracy": 0.8046875, | |
| "epoch": 0.3425, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.345, | |
| "grad_norm": 6.448349952697754, | |
| "learning_rate": 3.447368421052632e-06, | |
| "loss": 0.4449, | |
| "step": 138 | |
| }, | |
| { | |
| "Batch Mean": 1.3028790950775146, | |
| "accuracy": 0.7578125, | |
| "epoch": 0.345, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.3475, | |
| "grad_norm": 6.54162073135376, | |
| "learning_rate": 3.43421052631579e-06, | |
| "loss": 0.4109, | |
| "step": 139 | |
| }, | |
| { | |
| "Batch Mean": 1.206446886062622, | |
| "accuracy": 0.7734375, | |
| "epoch": 0.3475, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 7.594364166259766, | |
| "learning_rate": 3.421052631578948e-06, | |
| "loss": 0.4771, | |
| "step": 140 | |
| }, | |
| { | |
| "Batch Mean": 1.425430417060852, | |
| "accuracy": 0.7734375, | |
| "epoch": 0.35, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3525, | |
| "grad_norm": 6.744152069091797, | |
| "learning_rate": 3.4078947368421057e-06, | |
| "loss": 0.4458, | |
| "step": 141 | |
| }, | |
| { | |
| "Batch Mean": 1.4311294555664062, | |
| "accuracy": 0.765625, | |
| "epoch": 0.3525, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.355, | |
| "grad_norm": 6.789750576019287, | |
| "learning_rate": 3.3947368421052636e-06, | |
| "loss": 0.4798, | |
| "step": 142 | |
| }, | |
| { | |
| "Batch Mean": 1.6251521110534668, | |
| "accuracy": 0.765625, | |
| "epoch": 0.355, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.3575, | |
| "grad_norm": 7.658289909362793, | |
| "learning_rate": 3.381578947368421e-06, | |
| "loss": 0.5209, | |
| "step": 143 | |
| }, | |
| { | |
| "Batch Mean": 1.5901494026184082, | |
| "accuracy": 0.7890625, | |
| "epoch": 0.3575, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 7.741049289703369, | |
| "learning_rate": 3.368421052631579e-06, | |
| "loss": 0.448, | |
| "step": 144 | |
| }, | |
| { | |
| "Batch Mean": 1.7485175132751465, | |
| "accuracy": 0.71875, | |
| "epoch": 0.36, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.3625, | |
| "grad_norm": 7.933503150939941, | |
| "learning_rate": 3.355263157894737e-06, | |
| "loss": 0.4745, | |
| "step": 145 | |
| }, | |
| { | |
| "Batch Mean": 1.8909566402435303, | |
| "accuracy": 0.796875, | |
| "epoch": 0.3625, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.365, | |
| "grad_norm": 7.310222148895264, | |
| "learning_rate": 3.342105263157895e-06, | |
| "loss": 0.4671, | |
| "step": 146 | |
| }, | |
| { | |
| "Batch Mean": 2.035611152648926, | |
| "accuracy": 0.75, | |
| "epoch": 0.365, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.3675, | |
| "grad_norm": 7.8623809814453125, | |
| "learning_rate": 3.3289473684210528e-06, | |
| "loss": 0.5079, | |
| "step": 147 | |
| }, | |
| { | |
| "Batch Mean": 2.0848422050476074, | |
| "accuracy": 0.8203125, | |
| "epoch": 0.3675, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 7.38020133972168, | |
| "learning_rate": 3.3157894736842107e-06, | |
| "loss": 0.5131, | |
| "step": 148 | |
| }, | |
| { | |
| "Batch Mean": 1.9938535690307617, | |
| "accuracy": 0.7734375, | |
| "epoch": 0.37, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.3725, | |
| "grad_norm": 7.401918411254883, | |
| "learning_rate": 3.302631578947369e-06, | |
| "loss": 0.4059, | |
| "step": 149 | |
| }, | |
| { | |
| "Batch Mean": 1.9994306564331055, | |
| "accuracy": 0.8515625, | |
| "epoch": 0.3725, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.375, | |
| "grad_norm": 7.515151500701904, | |
| "learning_rate": 3.289473684210527e-06, | |
| "loss": 0.4198, | |
| "step": 150 | |
| }, | |
| { | |
| "Batch Mean": 1.9627342224121094, | |
| "accuracy": 0.78125, | |
| "epoch": 0.375, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3775, | |
| "grad_norm": 9.086411476135254, | |
| "learning_rate": 3.276315789473685e-06, | |
| "loss": 0.407, | |
| "step": 151 | |
| }, | |
| { | |
| "Batch Mean": 2.247910499572754, | |
| "accuracy": 0.75, | |
| "epoch": 0.3775, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 8.9763765335083, | |
| "learning_rate": 3.2631578947368423e-06, | |
| "loss": 0.5274, | |
| "step": 152 | |
| }, | |
| { | |
| "Batch Mean": 2.261256694793701, | |
| "accuracy": 0.8125, | |
| "epoch": 0.38, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.3825, | |
| "grad_norm": 6.913736820220947, | |
| "learning_rate": 3.2500000000000002e-06, | |
| "loss": 0.4049, | |
| "step": 153 | |
| }, | |
| { | |
| "Batch Mean": 2.136556386947632, | |
| "accuracy": 0.78125, | |
| "epoch": 0.3825, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.385, | |
| "grad_norm": 7.755904674530029, | |
| "learning_rate": 3.236842105263158e-06, | |
| "loss": 0.449, | |
| "step": 154 | |
| }, | |
| { | |
| "Batch Mean": 2.088193416595459, | |
| "accuracy": 0.8046875, | |
| "epoch": 0.385, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.3875, | |
| "grad_norm": 7.1718316078186035, | |
| "learning_rate": 3.223684210526316e-06, | |
| "loss": 0.4129, | |
| "step": 155 | |
| }, | |
| { | |
| "Batch Mean": 2.5068817138671875, | |
| "accuracy": 0.796875, | |
| "epoch": 0.3875, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 9.461467742919922, | |
| "learning_rate": 3.210526315789474e-06, | |
| "loss": 0.4147, | |
| "step": 156 | |
| }, | |
| { | |
| "Batch Mean": 2.0449132919311523, | |
| "accuracy": 0.7578125, | |
| "epoch": 0.39, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.3925, | |
| "grad_norm": 8.785501480102539, | |
| "learning_rate": 3.197368421052632e-06, | |
| "loss": 0.478, | |
| "step": 157 | |
| }, | |
| { | |
| "Batch Mean": 2.2665648460388184, | |
| "accuracy": 0.8203125, | |
| "epoch": 0.3925, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.395, | |
| "grad_norm": 7.906212329864502, | |
| "learning_rate": 3.1842105263157898e-06, | |
| "loss": 0.4083, | |
| "step": 158 | |
| }, | |
| { | |
| "Batch Mean": 1.8799333572387695, | |
| "accuracy": 0.734375, | |
| "epoch": 0.395, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.3975, | |
| "grad_norm": 9.25344467163086, | |
| "learning_rate": 3.1710526315789477e-06, | |
| "loss": 0.5007, | |
| "step": 159 | |
| }, | |
| { | |
| "Batch Mean": 2.178339719772339, | |
| "accuracy": 0.828125, | |
| "epoch": 0.3975, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 8.476263046264648, | |
| "learning_rate": 3.157894736842105e-06, | |
| "loss": 0.4184, | |
| "step": 160 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 400, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 80, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |