| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.25, |
| "eval_steps": 500, |
| "global_step": 100, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "Batch Mean": -3.22344970703125, |
| "accuracy": 0.5390625, |
| "epoch": 0, |
| "step": 0 |
| }, |
| { |
| "epoch": 0.0025, |
| "grad_norm": 32.78241729736328, |
| "learning_rate": 2.5000000000000004e-07, |
| "loss": 0.8624, |
| "step": 1 |
| }, |
| { |
| "Batch Mean": -3.20245361328125, |
| "accuracy": 0.5234375, |
| "epoch": 0.0025, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.005, |
| "grad_norm": 33.311607360839844, |
| "learning_rate": 5.000000000000001e-07, |
| "loss": 0.8721, |
| "step": 2 |
| }, |
| { |
| "Batch Mean": -3.2308349609375, |
| "accuracy": 0.4453125, |
| "epoch": 0.005, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.0075, |
| "grad_norm": 33.00279998779297, |
| "learning_rate": 7.5e-07, |
| "loss": 0.8678, |
| "step": 3 |
| }, |
| { |
| "Batch Mean": -3.2086181640625, |
| "accuracy": 0.46875, |
| "epoch": 0.0075, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.01, |
| "grad_norm": 33.870765686035156, |
| "learning_rate": 1.0000000000000002e-06, |
| "loss": 0.8713, |
| "step": 4 |
| }, |
| { |
| "Batch Mean": -3.101593017578125, |
| "accuracy": 0.5234375, |
| "epoch": 0.01, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.0125, |
| "grad_norm": 31.95158576965332, |
| "learning_rate": 1.25e-06, |
| "loss": 0.8448, |
| "step": 5 |
| }, |
| { |
| "Batch Mean": -2.778167724609375, |
| "accuracy": 0.4921875, |
| "epoch": 0.0125, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.015, |
| "grad_norm": 29.81480598449707, |
| "learning_rate": 1.5e-06, |
| "loss": 0.83, |
| "step": 6 |
| }, |
| { |
| "Batch Mean": -2.60491943359375, |
| "accuracy": 0.5859375, |
| "epoch": 0.015, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.0175, |
| "grad_norm": 27.83857536315918, |
| "learning_rate": 1.75e-06, |
| "loss": 0.7811, |
| "step": 7 |
| }, |
| { |
| "Batch Mean": -1.55364990234375, |
| "accuracy": 0.453125, |
| "epoch": 0.0175, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.02, |
| "grad_norm": 16.97942352294922, |
| "learning_rate": 2.0000000000000003e-06, |
| "loss": 0.7517, |
| "step": 8 |
| }, |
| { |
| "Batch Mean": -1.18939208984375, |
| "accuracy": 0.5, |
| "epoch": 0.02, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.0225, |
| "grad_norm": 14.753767967224121, |
| "learning_rate": 2.25e-06, |
| "loss": 0.7148, |
| "step": 9 |
| }, |
| { |
| "Batch Mean": 2.347869873046875, |
| "accuracy": 0.5703125, |
| "epoch": 0.0225, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.025, |
| "grad_norm": 26.016891479492188, |
| "learning_rate": 2.5e-06, |
| "loss": 0.7679, |
| "step": 10 |
| }, |
| { |
| "Batch Mean": 2.7044677734375, |
| "accuracy": 0.5078125, |
| "epoch": 0.025, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.0275, |
| "grad_norm": 28.977327346801758, |
| "learning_rate": 2.7500000000000004e-06, |
| "loss": 0.8112, |
| "step": 11 |
| }, |
| { |
| "Batch Mean": 3.05706787109375, |
| "accuracy": 0.578125, |
| "epoch": 0.0275, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.03, |
| "grad_norm": 31.655277252197266, |
| "learning_rate": 3e-06, |
| "loss": 0.8257, |
| "step": 12 |
| }, |
| { |
| "Batch Mean": 2.95458984375, |
| "accuracy": 0.625, |
| "epoch": 0.03, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.0325, |
| "grad_norm": 30.472238540649414, |
| "learning_rate": 3.2500000000000002e-06, |
| "loss": 0.8023, |
| "step": 13 |
| }, |
| { |
| "Batch Mean": 2.543212890625, |
| "accuracy": 0.6484375, |
| "epoch": 0.0325, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.035, |
| "grad_norm": 24.27365493774414, |
| "learning_rate": 3.5e-06, |
| "loss": 0.7431, |
| "step": 14 |
| }, |
| { |
| "Batch Mean": 2.131500244140625, |
| "accuracy": 0.7265625, |
| "epoch": 0.035, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.0375, |
| "grad_norm": 20.063459396362305, |
| "learning_rate": 3.7500000000000005e-06, |
| "loss": 0.6869, |
| "step": 15 |
| }, |
| { |
| "Batch Mean": 1.4629058837890625, |
| "accuracy": 0.65625, |
| "epoch": 0.0375, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.04, |
| "grad_norm": 13.922951698303223, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 0.6427, |
| "step": 16 |
| }, |
| { |
| "Batch Mean": 0.45629656314849854, |
| "accuracy": 0.6953125, |
| "epoch": 0.04, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.0425, |
| "grad_norm": 8.479089736938477, |
| "learning_rate": 4.25e-06, |
| "loss": 0.6811, |
| "step": 17 |
| }, |
| { |
| "Batch Mean": -0.6575782299041748, |
| "accuracy": 0.6875, |
| "epoch": 0.0425, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.045, |
| "grad_norm": 8.51148509979248, |
| "learning_rate": 4.5e-06, |
| "loss": 0.6173, |
| "step": 18 |
| }, |
| { |
| "Batch Mean": -1.4419012069702148, |
| "accuracy": 0.6796875, |
| "epoch": 0.045, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.0475, |
| "grad_norm": 13.423223495483398, |
| "learning_rate": 4.75e-06, |
| "loss": 0.6464, |
| "step": 19 |
| }, |
| { |
| "Batch Mean": -1.6556549072265625, |
| "accuracy": 0.7109375, |
| "epoch": 0.0475, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.05, |
| "grad_norm": 14.950621604919434, |
| "learning_rate": 5e-06, |
| "loss": 0.6417, |
| "step": 20 |
| }, |
| { |
| "Batch Mean": -1.1625317335128784, |
| "accuracy": 0.5859375, |
| "epoch": 0.05, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0525, |
| "grad_norm": 12.365989685058594, |
| "learning_rate": 4.986842105263158e-06, |
| "loss": 0.6729, |
| "step": 21 |
| }, |
| { |
| "Batch Mean": -0.22168993949890137, |
| "accuracy": 0.7265625, |
| "epoch": 0.0525, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.055, |
| "grad_norm": 7.174764633178711, |
| "learning_rate": 4.973684210526316e-06, |
| "loss": 0.5512, |
| "step": 22 |
| }, |
| { |
| "Batch Mean": 0.6636912226676941, |
| "accuracy": 0.65625, |
| "epoch": 0.055, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.0575, |
| "grad_norm": 10.331341743469238, |
| "learning_rate": 4.960526315789474e-06, |
| "loss": 0.629, |
| "step": 23 |
| }, |
| { |
| "Batch Mean": 1.0205326080322266, |
| "accuracy": 0.5859375, |
| "epoch": 0.0575, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.06, |
| "grad_norm": 11.934816360473633, |
| "learning_rate": 4.947368421052632e-06, |
| "loss": 0.6926, |
| "step": 24 |
| }, |
| { |
| "Batch Mean": 0.9423030614852905, |
| "accuracy": 0.6875, |
| "epoch": 0.06, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.0625, |
| "grad_norm": 10.728033065795898, |
| "learning_rate": 4.9342105263157895e-06, |
| "loss": 0.5973, |
| "step": 25 |
| }, |
| { |
| "Batch Mean": 0.4570488929748535, |
| "accuracy": 0.6875, |
| "epoch": 0.0625, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.065, |
| "grad_norm": 7.620607852935791, |
| "learning_rate": 4.921052631578948e-06, |
| "loss": 0.562, |
| "step": 26 |
| }, |
| { |
| "Batch Mean": -0.23614200949668884, |
| "accuracy": 0.7421875, |
| "epoch": 0.065, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.0675, |
| "grad_norm": 6.778779029846191, |
| "learning_rate": 4.907894736842106e-06, |
| "loss": 0.5411, |
| "step": 27 |
| }, |
| { |
| "Batch Mean": -0.8051831722259521, |
| "accuracy": 0.609375, |
| "epoch": 0.0675, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.07, |
| "grad_norm": 8.988683700561523, |
| "learning_rate": 4.894736842105264e-06, |
| "loss": 0.6348, |
| "step": 28 |
| }, |
| { |
| "Batch Mean": -0.7894483804702759, |
| "accuracy": 0.7265625, |
| "epoch": 0.07, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.0725, |
| "grad_norm": 8.688234329223633, |
| "learning_rate": 4.881578947368422e-06, |
| "loss": 0.5782, |
| "step": 29 |
| }, |
| { |
| "Batch Mean": -0.18249624967575073, |
| "accuracy": 0.71875, |
| "epoch": 0.0725, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.075, |
| "grad_norm": 5.793314456939697, |
| "learning_rate": 4.8684210526315795e-06, |
| "loss": 0.5502, |
| "step": 30 |
| }, |
| { |
| "Batch Mean": 0.33211851119995117, |
| "accuracy": 0.75, |
| "epoch": 0.075, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.0775, |
| "grad_norm": 6.008676528930664, |
| "learning_rate": 4.855263157894737e-06, |
| "loss": 0.5131, |
| "step": 31 |
| }, |
| { |
| "Batch Mean": 0.7284603118896484, |
| "accuracy": 0.765625, |
| "epoch": 0.0775, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 8.172709465026855, |
| "learning_rate": 4.842105263157895e-06, |
| "loss": 0.5496, |
| "step": 32 |
| }, |
| { |
| "Batch Mean": 0.7859265804290771, |
| "accuracy": 0.703125, |
| "epoch": 0.08, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.0825, |
| "grad_norm": 9.267521858215332, |
| "learning_rate": 4.828947368421053e-06, |
| "loss": 0.5903, |
| "step": 33 |
| }, |
| { |
| "Batch Mean": 0.13241028785705566, |
| "accuracy": 0.7109375, |
| "epoch": 0.0825, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.085, |
| "grad_norm": 7.105382442474365, |
| "learning_rate": 4.815789473684211e-06, |
| "loss": 0.5725, |
| "step": 34 |
| }, |
| { |
| "Batch Mean": -0.3201490640640259, |
| "accuracy": 0.7890625, |
| "epoch": 0.085, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.0875, |
| "grad_norm": 6.344538688659668, |
| "learning_rate": 4.802631578947369e-06, |
| "loss": 0.4902, |
| "step": 35 |
| }, |
| { |
| "Batch Mean": -0.7660524845123291, |
| "accuracy": 0.796875, |
| "epoch": 0.0875, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.09, |
| "grad_norm": 8.478452682495117, |
| "learning_rate": 4.789473684210527e-06, |
| "loss": 0.5135, |
| "step": 36 |
| }, |
| { |
| "Batch Mean": -0.5964984893798828, |
| "accuracy": 0.65625, |
| "epoch": 0.09, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.0925, |
| "grad_norm": 8.487342834472656, |
| "learning_rate": 4.7763157894736844e-06, |
| "loss": 0.5517, |
| "step": 37 |
| }, |
| { |
| "Batch Mean": -0.2701318860054016, |
| "accuracy": 0.75, |
| "epoch": 0.0925, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.095, |
| "grad_norm": 7.8622236251831055, |
| "learning_rate": 4.763157894736842e-06, |
| "loss": 0.5405, |
| "step": 38 |
| }, |
| { |
| "Batch Mean": 0.3329949378967285, |
| "accuracy": 0.6640625, |
| "epoch": 0.095, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.0975, |
| "grad_norm": 8.729914665222168, |
| "learning_rate": 4.75e-06, |
| "loss": 0.61, |
| "step": 39 |
| }, |
| { |
| "Batch Mean": 0.8064537048339844, |
| "accuracy": 0.765625, |
| "epoch": 0.0975, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 9.266338348388672, |
| "learning_rate": 4.736842105263158e-06, |
| "loss": 0.5148, |
| "step": 40 |
| }, |
| { |
| "Batch Mean": 0.636286735534668, |
| "accuracy": 0.78125, |
| "epoch": 0.1, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.1025, |
| "grad_norm": 7.88658332824707, |
| "learning_rate": 4.723684210526316e-06, |
| "loss": 0.504, |
| "step": 41 |
| }, |
| { |
| "Batch Mean": -0.03002452850341797, |
| "accuracy": 0.75, |
| "epoch": 0.1025, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.105, |
| "grad_norm": 6.346695899963379, |
| "learning_rate": 4.710526315789474e-06, |
| "loss": 0.5241, |
| "step": 42 |
| }, |
| { |
| "Batch Mean": -0.518393874168396, |
| "accuracy": 0.734375, |
| "epoch": 0.105, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.1075, |
| "grad_norm": 8.447480201721191, |
| "learning_rate": 4.697368421052632e-06, |
| "loss": 0.5379, |
| "step": 43 |
| }, |
| { |
| "Batch Mean": -0.4221421480178833, |
| "accuracy": 0.78125, |
| "epoch": 0.1075, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.11, |
| "grad_norm": 7.111172676086426, |
| "learning_rate": 4.68421052631579e-06, |
| "loss": 0.463, |
| "step": 44 |
| }, |
| { |
| "Batch Mean": -0.09055519104003906, |
| "accuracy": 0.7421875, |
| "epoch": 0.11, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.1125, |
| "grad_norm": 7.127180099487305, |
| "learning_rate": 4.671052631578948e-06, |
| "loss": 0.5026, |
| "step": 45 |
| }, |
| { |
| "Batch Mean": 0.23522070050239563, |
| "accuracy": 0.8046875, |
| "epoch": 0.1125, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.115, |
| "grad_norm": 7.237793922424316, |
| "learning_rate": 4.657894736842106e-06, |
| "loss": 0.4267, |
| "step": 46 |
| }, |
| { |
| "Batch Mean": 0.3779289126396179, |
| "accuracy": 0.7109375, |
| "epoch": 0.115, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.1175, |
| "grad_norm": 11.18747329711914, |
| "learning_rate": 4.6447368421052635e-06, |
| "loss": 0.5298, |
| "step": 47 |
| }, |
| { |
| "Batch Mean": 0.10932159423828125, |
| "accuracy": 0.7265625, |
| "epoch": 0.1175, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.12, |
| "grad_norm": 7.571730136871338, |
| "learning_rate": 4.631578947368421e-06, |
| "loss": 0.4557, |
| "step": 48 |
| }, |
| { |
| "Batch Mean": 0.2413313388824463, |
| "accuracy": 0.765625, |
| "epoch": 0.12, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.1225, |
| "grad_norm": 7.670024394989014, |
| "learning_rate": 4.618421052631579e-06, |
| "loss": 0.5069, |
| "step": 49 |
| }, |
| { |
| "Batch Mean": -0.15598678588867188, |
| "accuracy": 0.6953125, |
| "epoch": 0.1225, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.125, |
| "grad_norm": 10.166374206542969, |
| "learning_rate": 4.605263157894737e-06, |
| "loss": 0.5951, |
| "step": 50 |
| }, |
| { |
| "Batch Mean": -0.4917259216308594, |
| "accuracy": 0.6953125, |
| "epoch": 0.125, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.1275, |
| "grad_norm": 9.27407169342041, |
| "learning_rate": 4.592105263157895e-06, |
| "loss": 0.5234, |
| "step": 51 |
| }, |
| { |
| "Batch Mean": -0.1558108925819397, |
| "accuracy": 0.78125, |
| "epoch": 0.1275, |
| "step": 51 |
| }, |
| { |
| "epoch": 0.13, |
| "grad_norm": 6.958871364593506, |
| "learning_rate": 4.578947368421053e-06, |
| "loss": 0.4772, |
| "step": 52 |
| }, |
| { |
| "Batch Mean": 0.010368764400482178, |
| "accuracy": 0.71875, |
| "epoch": 0.13, |
| "step": 52 |
| }, |
| { |
| "epoch": 0.1325, |
| "grad_norm": 9.204265594482422, |
| "learning_rate": 4.565789473684211e-06, |
| "loss": 0.5679, |
| "step": 53 |
| }, |
| { |
| "Batch Mean": 0.1981235146522522, |
| "accuracy": 0.734375, |
| "epoch": 0.1325, |
| "step": 53 |
| }, |
| { |
| "epoch": 0.135, |
| "grad_norm": 7.802533149719238, |
| "learning_rate": 4.552631578947369e-06, |
| "loss": 0.5008, |
| "step": 54 |
| }, |
| { |
| "Batch Mean": 0.41782093048095703, |
| "accuracy": 0.7421875, |
| "epoch": 0.135, |
| "step": 54 |
| }, |
| { |
| "epoch": 0.1375, |
| "grad_norm": 7.295779228210449, |
| "learning_rate": 4.539473684210527e-06, |
| "loss": 0.5169, |
| "step": 55 |
| }, |
| { |
| "Batch Mean": 0.34867769479751587, |
| "accuracy": 0.7890625, |
| "epoch": 0.1375, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.14, |
| "grad_norm": 6.531123161315918, |
| "learning_rate": 4.526315789473685e-06, |
| "loss": 0.4554, |
| "step": 56 |
| }, |
| { |
| "Batch Mean": -0.32196617126464844, |
| "accuracy": 0.703125, |
| "epoch": 0.14, |
| "step": 56 |
| }, |
| { |
| "epoch": 0.1425, |
| "grad_norm": 8.351095199584961, |
| "learning_rate": 4.513157894736843e-06, |
| "loss": 0.5658, |
| "step": 57 |
| }, |
| { |
| "Batch Mean": -0.301898717880249, |
| "accuracy": 0.7578125, |
| "epoch": 0.1425, |
| "step": 57 |
| }, |
| { |
| "epoch": 0.145, |
| "grad_norm": 6.481894493103027, |
| "learning_rate": 4.5e-06, |
| "loss": 0.5244, |
| "step": 58 |
| }, |
| { |
| "Batch Mean": -0.5122654438018799, |
| "accuracy": 0.75, |
| "epoch": 0.145, |
| "step": 58 |
| }, |
| { |
| "epoch": 0.1475, |
| "grad_norm": 7.288686752319336, |
| "learning_rate": 4.4868421052631584e-06, |
| "loss": 0.49, |
| "step": 59 |
| }, |
| { |
| "Batch Mean": -0.15232443809509277, |
| "accuracy": 0.7109375, |
| "epoch": 0.1475, |
| "step": 59 |
| }, |
| { |
| "epoch": 0.15, |
| "grad_norm": 6.799753665924072, |
| "learning_rate": 4.473684210526316e-06, |
| "loss": 0.5079, |
| "step": 60 |
| }, |
| { |
| "Batch Mean": 0.15944302082061768, |
| "accuracy": 0.8046875, |
| "epoch": 0.15, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.1525, |
| "grad_norm": 6.836521625518799, |
| "learning_rate": 4.460526315789474e-06, |
| "loss": 0.4475, |
| "step": 61 |
| }, |
| { |
| "Batch Mean": 0.6559411287307739, |
| "accuracy": 0.7734375, |
| "epoch": 0.1525, |
| "step": 61 |
| }, |
| { |
| "epoch": 0.155, |
| "grad_norm": 9.224549293518066, |
| "learning_rate": 4.447368421052632e-06, |
| "loss": 0.4865, |
| "step": 62 |
| }, |
| { |
| "Batch Mean": 0.4529900550842285, |
| "accuracy": 0.6953125, |
| "epoch": 0.155, |
| "step": 62 |
| }, |
| { |
| "epoch": 0.1575, |
| "grad_norm": 8.381292343139648, |
| "learning_rate": 4.43421052631579e-06, |
| "loss": 0.4857, |
| "step": 63 |
| }, |
| { |
| "Batch Mean": -0.047610118985176086, |
| "accuracy": 0.7109375, |
| "epoch": 0.1575, |
| "step": 63 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 8.044920921325684, |
| "learning_rate": 4.4210526315789476e-06, |
| "loss": 0.5013, |
| "step": 64 |
| }, |
| { |
| "Batch Mean": -0.3421214818954468, |
| "accuracy": 0.7734375, |
| "epoch": 0.16, |
| "step": 64 |
| }, |
| { |
| "epoch": 0.1625, |
| "grad_norm": 7.571659088134766, |
| "learning_rate": 4.407894736842105e-06, |
| "loss": 0.4956, |
| "step": 65 |
| }, |
| { |
| "Batch Mean": -0.0925983190536499, |
| "accuracy": 0.703125, |
| "epoch": 0.1625, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.165, |
| "grad_norm": 9.129205703735352, |
| "learning_rate": 4.394736842105263e-06, |
| "loss": 0.5488, |
| "step": 66 |
| }, |
| { |
| "Batch Mean": -0.12005829811096191, |
| "accuracy": 0.78125, |
| "epoch": 0.165, |
| "step": 66 |
| }, |
| { |
| "epoch": 0.1675, |
| "grad_norm": 8.270757675170898, |
| "learning_rate": 4.381578947368421e-06, |
| "loss": 0.4158, |
| "step": 67 |
| }, |
| { |
| "Batch Mean": 0.4386889934539795, |
| "accuracy": 0.7421875, |
| "epoch": 0.1675, |
| "step": 67 |
| }, |
| { |
| "epoch": 0.17, |
| "grad_norm": 11.129798889160156, |
| "learning_rate": 4.368421052631579e-06, |
| "loss": 0.4829, |
| "step": 68 |
| }, |
| { |
| "Batch Mean": -0.12494802474975586, |
| "accuracy": 0.71875, |
| "epoch": 0.17, |
| "step": 68 |
| }, |
| { |
| "epoch": 0.1725, |
| "grad_norm": 10.14079761505127, |
| "learning_rate": 4.3552631578947375e-06, |
| "loss": 0.4988, |
| "step": 69 |
| }, |
| { |
| "Batch Mean": -0.322005033493042, |
| "accuracy": 0.7421875, |
| "epoch": 0.1725, |
| "step": 69 |
| }, |
| { |
| "epoch": 0.175, |
| "grad_norm": 8.12278938293457, |
| "learning_rate": 4.342105263157895e-06, |
| "loss": 0.5207, |
| "step": 70 |
| }, |
| { |
| "Batch Mean": -0.3203928768634796, |
| "accuracy": 0.7265625, |
| "epoch": 0.175, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.1775, |
| "grad_norm": 8.622071266174316, |
| "learning_rate": 4.328947368421053e-06, |
| "loss": 0.508, |
| "step": 71 |
| }, |
| { |
| "Batch Mean": -0.11252805590629578, |
| "accuracy": 0.7578125, |
| "epoch": 0.1775, |
| "step": 71 |
| }, |
| { |
| "epoch": 0.18, |
| "grad_norm": 7.229330062866211, |
| "learning_rate": 4.315789473684211e-06, |
| "loss": 0.443, |
| "step": 72 |
| }, |
| { |
| "Batch Mean": 0.08833515644073486, |
| "accuracy": 0.828125, |
| "epoch": 0.18, |
| "step": 72 |
| }, |
| { |
| "epoch": 0.1825, |
| "grad_norm": 5.973883152008057, |
| "learning_rate": 4.302631578947369e-06, |
| "loss": 0.3979, |
| "step": 73 |
| }, |
| { |
| "Batch Mean": 0.46913909912109375, |
| "accuracy": 0.7265625, |
| "epoch": 0.1825, |
| "step": 73 |
| }, |
| { |
| "epoch": 0.185, |
| "grad_norm": 7.876657485961914, |
| "learning_rate": 4.289473684210527e-06, |
| "loss": 0.4785, |
| "step": 74 |
| }, |
| { |
| "Batch Mean": 0.18231534957885742, |
| "accuracy": 0.8125, |
| "epoch": 0.185, |
| "step": 74 |
| }, |
| { |
| "epoch": 0.1875, |
| "grad_norm": 6.78118371963501, |
| "learning_rate": 4.276315789473684e-06, |
| "loss": 0.4094, |
| "step": 75 |
| }, |
| { |
| "Batch Mean": 0.42796552181243896, |
| "accuracy": 0.8125, |
| "epoch": 0.1875, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.19, |
| "grad_norm": 7.038549423217773, |
| "learning_rate": 4.2631578947368425e-06, |
| "loss": 0.4018, |
| "step": 76 |
| }, |
| { |
| "Batch Mean": -0.197587251663208, |
| "accuracy": 0.7734375, |
| "epoch": 0.19, |
| "step": 76 |
| }, |
| { |
| "epoch": 0.1925, |
| "grad_norm": 7.44735050201416, |
| "learning_rate": 4.25e-06, |
| "loss": 0.4534, |
| "step": 77 |
| }, |
| { |
| "Batch Mean": -0.12531863152980804, |
| "accuracy": 0.7890625, |
| "epoch": 0.1925, |
| "step": 77 |
| }, |
| { |
| "epoch": 0.195, |
| "grad_norm": 7.824428081512451, |
| "learning_rate": 4.236842105263158e-06, |
| "loss": 0.4709, |
| "step": 78 |
| }, |
| { |
| "Batch Mean": -0.003929615020751953, |
| "accuracy": 0.7109375, |
| "epoch": 0.195, |
| "step": 78 |
| }, |
| { |
| "epoch": 0.1975, |
| "grad_norm": 8.514533996582031, |
| "learning_rate": 4.223684210526316e-06, |
| "loss": 0.5496, |
| "step": 79 |
| }, |
| { |
| "Batch Mean": 0.02380847930908203, |
| "accuracy": 0.7578125, |
| "epoch": 0.1975, |
| "step": 79 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 10.371747970581055, |
| "learning_rate": 4.210526315789474e-06, |
| "loss": 0.5056, |
| "step": 80 |
| }, |
| { |
| "Batch Mean": -0.47749924659729004, |
| "accuracy": 0.796875, |
| "epoch": 0.2, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.2025, |
| "grad_norm": 9.618741989135742, |
| "learning_rate": 4.197368421052632e-06, |
| "loss": 0.5261, |
| "step": 81 |
| }, |
| { |
| "Batch Mean": -0.46868181228637695, |
| "accuracy": 0.703125, |
| "epoch": 0.2025, |
| "step": 81 |
| }, |
| { |
| "epoch": 0.205, |
| "grad_norm": 9.87120246887207, |
| "learning_rate": 4.18421052631579e-06, |
| "loss": 0.5131, |
| "step": 82 |
| }, |
| { |
| "Batch Mean": 0.32471323013305664, |
| "accuracy": 0.8203125, |
| "epoch": 0.205, |
| "step": 82 |
| }, |
| { |
| "epoch": 0.2075, |
| "grad_norm": 7.470169544219971, |
| "learning_rate": 4.171052631578948e-06, |
| "loss": 0.3878, |
| "step": 83 |
| }, |
| { |
| "Batch Mean": 0.13215994834899902, |
| "accuracy": 0.7890625, |
| "epoch": 0.2075, |
| "step": 83 |
| }, |
| { |
| "epoch": 0.21, |
| "grad_norm": 8.594000816345215, |
| "learning_rate": 4.157894736842106e-06, |
| "loss": 0.5226, |
| "step": 84 |
| }, |
| { |
| "Batch Mean": -0.15986275672912598, |
| "accuracy": 0.734375, |
| "epoch": 0.21, |
| "step": 84 |
| }, |
| { |
| "epoch": 0.2125, |
| "grad_norm": 8.745137214660645, |
| "learning_rate": 4.144736842105263e-06, |
| "loss": 0.5466, |
| "step": 85 |
| }, |
| { |
| "Batch Mean": -0.6324893832206726, |
| "accuracy": 0.7734375, |
| "epoch": 0.2125, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.215, |
| "grad_norm": 9.078672409057617, |
| "learning_rate": 4.1315789473684216e-06, |
| "loss": 0.55, |
| "step": 86 |
| }, |
| { |
| "Batch Mean": 0.31803226470947266, |
| "accuracy": 0.71875, |
| "epoch": 0.215, |
| "step": 86 |
| }, |
| { |
| "epoch": 0.2175, |
| "grad_norm": 6.7177581787109375, |
| "learning_rate": 4.118421052631579e-06, |
| "loss": 0.5148, |
| "step": 87 |
| }, |
| { |
| "Batch Mean": 0.16668707132339478, |
| "accuracy": 0.7578125, |
| "epoch": 0.2175, |
| "step": 87 |
| }, |
| { |
| "epoch": 0.22, |
| "grad_norm": 6.152680397033691, |
| "learning_rate": 4.105263157894737e-06, |
| "loss": 0.5204, |
| "step": 88 |
| }, |
| { |
| "Batch Mean": -0.18514534831047058, |
| "accuracy": 0.7578125, |
| "epoch": 0.22, |
| "step": 88 |
| }, |
| { |
| "epoch": 0.2225, |
| "grad_norm": 5.66470193862915, |
| "learning_rate": 4.092105263157895e-06, |
| "loss": 0.4949, |
| "step": 89 |
| }, |
| { |
| "Batch Mean": 0.049420952796936035, |
| "accuracy": 0.7265625, |
| "epoch": 0.2225, |
| "step": 89 |
| }, |
| { |
| "epoch": 0.225, |
| "grad_norm": 5.757960796356201, |
| "learning_rate": 4.078947368421053e-06, |
| "loss": 0.4673, |
| "step": 90 |
| }, |
| { |
| "Batch Mean": 0.05896341800689697, |
| "accuracy": 0.7578125, |
| "epoch": 0.225, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.2275, |
| "grad_norm": 5.6377739906311035, |
| "learning_rate": 4.065789473684211e-06, |
| "loss": 0.5187, |
| "step": 91 |
| }, |
| { |
| "Batch Mean": 0.11456716060638428, |
| "accuracy": 0.75, |
| "epoch": 0.2275, |
| "step": 91 |
| }, |
| { |
| "epoch": 0.23, |
| "grad_norm": 5.526971817016602, |
| "learning_rate": 4.052631578947368e-06, |
| "loss": 0.4885, |
| "step": 92 |
| }, |
| { |
| "Batch Mean": 0.30746984481811523, |
| "accuracy": 0.796875, |
| "epoch": 0.23, |
| "step": 92 |
| }, |
| { |
| "epoch": 0.2325, |
| "grad_norm": 6.554511070251465, |
| "learning_rate": 4.0394736842105265e-06, |
| "loss": 0.4602, |
| "step": 93 |
| }, |
| { |
| "Batch Mean": -0.19295340776443481, |
| "accuracy": 0.7734375, |
| "epoch": 0.2325, |
| "step": 93 |
| }, |
| { |
| "epoch": 0.235, |
| "grad_norm": 6.230556488037109, |
| "learning_rate": 4.026315789473684e-06, |
| "loss": 0.484, |
| "step": 94 |
| }, |
| { |
| "Batch Mean": -0.1081857681274414, |
| "accuracy": 0.8125, |
| "epoch": 0.235, |
| "step": 94 |
| }, |
| { |
| "epoch": 0.2375, |
| "grad_norm": 5.673005104064941, |
| "learning_rate": 4.013157894736842e-06, |
| "loss": 0.46, |
| "step": 95 |
| }, |
| { |
| "Batch Mean": -0.01769113540649414, |
| "accuracy": 0.7109375, |
| "epoch": 0.2375, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 6.975053787231445, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 0.5193, |
| "step": 96 |
| }, |
| { |
| "Batch Mean": 0.018754109740257263, |
| "accuracy": 0.796875, |
| "epoch": 0.24, |
| "step": 96 |
| }, |
| { |
| "epoch": 0.2425, |
| "grad_norm": 7.40658712387085, |
| "learning_rate": 3.986842105263158e-06, |
| "loss": 0.4594, |
| "step": 97 |
| }, |
| { |
| "Batch Mean": 0.1552438735961914, |
| "accuracy": 0.78125, |
| "epoch": 0.2425, |
| "step": 97 |
| }, |
| { |
| "epoch": 0.245, |
| "grad_norm": 8.391383171081543, |
| "learning_rate": 3.9736842105263165e-06, |
| "loss": 0.4326, |
| "step": 98 |
| }, |
| { |
| "Batch Mean": 0.16905894875526428, |
| "accuracy": 0.8515625, |
| "epoch": 0.245, |
| "step": 98 |
| }, |
| { |
| "epoch": 0.2475, |
| "grad_norm": 7.3470611572265625, |
| "learning_rate": 3.960526315789474e-06, |
| "loss": 0.3526, |
| "step": 99 |
| }, |
| { |
| "Batch Mean": 0.19422674179077148, |
| "accuracy": 0.828125, |
| "epoch": 0.2475, |
| "step": 99 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 10.861686706542969, |
| "learning_rate": 3.947368421052632e-06, |
| "loss": 0.4482, |
| "step": 100 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 400, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 100, |
| "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": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
