| { | |
| "best_metric": 0.6183362007141113, | |
| "best_model_checkpoint": "governancev1/checkpoint-310", | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 310, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04838709677419355, | |
| "grad_norm": 3.0842931270599365, | |
| "learning_rate": 9.67741935483871e-07, | |
| "loss": 1.765, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0967741935483871, | |
| "grad_norm": 3.169724702835083, | |
| "learning_rate": 1.935483870967742e-06, | |
| "loss": 1.805, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.14516129032258066, | |
| "grad_norm": 3.4454946517944336, | |
| "learning_rate": 2.903225806451613e-06, | |
| "loss": 1.805, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1935483870967742, | |
| "grad_norm": 2.817859649658203, | |
| "learning_rate": 3.870967741935484e-06, | |
| "loss": 1.8016, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.24193548387096775, | |
| "grad_norm": 4.190126419067383, | |
| "learning_rate": 4.838709677419355e-06, | |
| "loss": 1.7943, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2903225806451613, | |
| "grad_norm": 3.602416515350342, | |
| "learning_rate": 5.806451612903226e-06, | |
| "loss": 1.784, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3387096774193548, | |
| "grad_norm": 3.737297773361206, | |
| "learning_rate": 6.774193548387097e-06, | |
| "loss": 1.7862, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3870967741935484, | |
| "grad_norm": 3.9539337158203125, | |
| "learning_rate": 7.741935483870968e-06, | |
| "loss": 1.8032, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.43548387096774194, | |
| "grad_norm": 3.630708932876587, | |
| "learning_rate": 8.70967741935484e-06, | |
| "loss": 1.7825, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.4838709677419355, | |
| "grad_norm": 2.1453819274902344, | |
| "learning_rate": 9.67741935483871e-06, | |
| "loss": 1.8035, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.532258064516129, | |
| "grad_norm": 3.154428243637085, | |
| "learning_rate": 9.928315412186382e-06, | |
| "loss": 1.778, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5806451612903226, | |
| "grad_norm": 2.720580816268921, | |
| "learning_rate": 9.820788530465952e-06, | |
| "loss": 1.7578, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.6290322580645161, | |
| "grad_norm": 2.502385139465332, | |
| "learning_rate": 9.71326164874552e-06, | |
| "loss": 1.7854, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6774193548387096, | |
| "grad_norm": 4.814332485198975, | |
| "learning_rate": 9.60573476702509e-06, | |
| "loss": 1.7794, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.7258064516129032, | |
| "grad_norm": 4.313498497009277, | |
| "learning_rate": 9.49820788530466e-06, | |
| "loss": 1.7557, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7741935483870968, | |
| "grad_norm": 5.430189609527588, | |
| "learning_rate": 9.39068100358423e-06, | |
| "loss": 1.778, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.8225806451612904, | |
| "grad_norm": 3.3871169090270996, | |
| "learning_rate": 9.2831541218638e-06, | |
| "loss": 1.7578, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.8709677419354839, | |
| "grad_norm": 3.650548219680786, | |
| "learning_rate": 9.17562724014337e-06, | |
| "loss": 1.7563, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.9193548387096774, | |
| "grad_norm": 2.9331789016723633, | |
| "learning_rate": 9.068100358422939e-06, | |
| "loss": 1.7639, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.967741935483871, | |
| "grad_norm": 4.592463970184326, | |
| "learning_rate": 8.96057347670251e-06, | |
| "loss": 1.7155, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5853658536585366, | |
| "eval_f1_macro": 0.5538981611199739, | |
| "eval_f1_micro": 0.5853658536585366, | |
| "eval_f1_weighted": 0.5579311937490847, | |
| "eval_loss": 1.721036434173584, | |
| "eval_precision_macro": 0.6902878530637443, | |
| "eval_precision_micro": 0.5853658536585366, | |
| "eval_precision_weighted": 0.6892010083860678, | |
| "eval_recall_macro": 0.5789682539682539, | |
| "eval_recall_micro": 0.5853658536585366, | |
| "eval_recall_weighted": 0.5853658536585366, | |
| "eval_runtime": 0.706, | |
| "eval_samples_per_second": 174.221, | |
| "eval_steps_per_second": 11.331, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.0161290322580645, | |
| "grad_norm": 3.955127477645874, | |
| "learning_rate": 8.888888888888888e-06, | |
| "loss": 1.7336, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 1.064516129032258, | |
| "grad_norm": 3.8463294506073, | |
| "learning_rate": 8.78136200716846e-06, | |
| "loss": 1.7033, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.1129032258064515, | |
| "grad_norm": 5.382518768310547, | |
| "learning_rate": 8.67383512544803e-06, | |
| "loss": 1.7024, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 1.1612903225806452, | |
| "grad_norm": 5.656961441040039, | |
| "learning_rate": 8.5663082437276e-06, | |
| "loss": 1.6256, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.2096774193548387, | |
| "grad_norm": 4.990180492401123, | |
| "learning_rate": 8.45878136200717e-06, | |
| "loss": 1.6167, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.2580645161290323, | |
| "grad_norm": 6.717923164367676, | |
| "learning_rate": 8.35125448028674e-06, | |
| "loss": 1.6665, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.3064516129032258, | |
| "grad_norm": 6.241459846496582, | |
| "learning_rate": 8.24372759856631e-06, | |
| "loss": 1.5133, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.3548387096774195, | |
| "grad_norm": 7.923880100250244, | |
| "learning_rate": 8.136200716845879e-06, | |
| "loss": 1.4838, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.403225806451613, | |
| "grad_norm": 6.954166889190674, | |
| "learning_rate": 8.028673835125449e-06, | |
| "loss": 1.5632, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.4516129032258065, | |
| "grad_norm": 8.967968940734863, | |
| "learning_rate": 7.921146953405019e-06, | |
| "loss": 1.5475, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 7.038327693939209, | |
| "learning_rate": 7.813620071684589e-06, | |
| "loss": 1.3987, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.5483870967741935, | |
| "grad_norm": 5.91029167175293, | |
| "learning_rate": 7.706093189964159e-06, | |
| "loss": 1.4075, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.596774193548387, | |
| "grad_norm": 5.255452632904053, | |
| "learning_rate": 7.5985663082437275e-06, | |
| "loss": 1.4156, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.6451612903225805, | |
| "grad_norm": 6.4161858558654785, | |
| "learning_rate": 7.491039426523297e-06, | |
| "loss": 1.4282, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.6935483870967742, | |
| "grad_norm": 6.7246270179748535, | |
| "learning_rate": 7.383512544802868e-06, | |
| "loss": 1.3218, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.7419354838709677, | |
| "grad_norm": 7.8033671379089355, | |
| "learning_rate": 7.275985663082438e-06, | |
| "loss": 1.3164, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.7903225806451613, | |
| "grad_norm": 7.699241638183594, | |
| "learning_rate": 7.168458781362008e-06, | |
| "loss": 1.2532, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 1.838709677419355, | |
| "grad_norm": 6.70715856552124, | |
| "learning_rate": 7.060931899641578e-06, | |
| "loss": 1.2094, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.8870967741935485, | |
| "grad_norm": 6.230452060699463, | |
| "learning_rate": 6.9534050179211476e-06, | |
| "loss": 1.3213, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.935483870967742, | |
| "grad_norm": 5.785920143127441, | |
| "learning_rate": 6.8458781362007174e-06, | |
| "loss": 1.2513, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.9838709677419355, | |
| "grad_norm": 4.86808967590332, | |
| "learning_rate": 6.738351254480287e-06, | |
| "loss": 1.1626, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7154471544715447, | |
| "eval_f1_macro": 0.6924669353531142, | |
| "eval_f1_micro": 0.7154471544715447, | |
| "eval_f1_weighted": 0.6954298446465806, | |
| "eval_loss": 1.1070369482040405, | |
| "eval_precision_macro": 0.7450460829493087, | |
| "eval_precision_micro": 0.7154471544715447, | |
| "eval_precision_weighted": 0.7457963358435428, | |
| "eval_recall_macro": 0.7115079365079365, | |
| "eval_recall_micro": 0.7154471544715447, | |
| "eval_recall_weighted": 0.7154471544715447, | |
| "eval_runtime": 0.72, | |
| "eval_samples_per_second": 170.83, | |
| "eval_steps_per_second": 11.111, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 2.032258064516129, | |
| "grad_norm": 4.532644748687744, | |
| "learning_rate": 6.630824372759857e-06, | |
| "loss": 0.9685, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 2.0806451612903225, | |
| "grad_norm": 5.968006134033203, | |
| "learning_rate": 6.523297491039428e-06, | |
| "loss": 1.2298, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 2.129032258064516, | |
| "grad_norm": 5.891108989715576, | |
| "learning_rate": 6.415770609318996e-06, | |
| "loss": 1.1047, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 2.1774193548387095, | |
| "grad_norm": 5.493295192718506, | |
| "learning_rate": 6.308243727598567e-06, | |
| "loss": 1.0527, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 2.225806451612903, | |
| "grad_norm": 5.447644233703613, | |
| "learning_rate": 6.200716845878137e-06, | |
| "loss": 0.8857, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 2.274193548387097, | |
| "grad_norm": 5.241428852081299, | |
| "learning_rate": 6.0931899641577065e-06, | |
| "loss": 0.9137, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 2.3225806451612905, | |
| "grad_norm": 7.360194683074951, | |
| "learning_rate": 5.985663082437276e-06, | |
| "loss": 1.1215, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 2.370967741935484, | |
| "grad_norm": 8.852798461914062, | |
| "learning_rate": 5.878136200716846e-06, | |
| "loss": 1.0209, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 2.4193548387096775, | |
| "grad_norm": 8.410216331481934, | |
| "learning_rate": 5.770609318996416e-06, | |
| "loss": 1.0577, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.467741935483871, | |
| "grad_norm": 8.898208618164062, | |
| "learning_rate": 5.663082437275986e-06, | |
| "loss": 0.9082, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 2.5161290322580645, | |
| "grad_norm": 6.314516067504883, | |
| "learning_rate": 5.555555555555557e-06, | |
| "loss": 0.79, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 2.564516129032258, | |
| "grad_norm": 7.746774673461914, | |
| "learning_rate": 5.4480286738351265e-06, | |
| "loss": 1.0791, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 2.6129032258064515, | |
| "grad_norm": 5.784223556518555, | |
| "learning_rate": 5.340501792114696e-06, | |
| "loss": 0.8398, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 2.661290322580645, | |
| "grad_norm": 6.672528266906738, | |
| "learning_rate": 5.232974910394266e-06, | |
| "loss": 0.8742, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 2.709677419354839, | |
| "grad_norm": 6.1544647216796875, | |
| "learning_rate": 5.125448028673835e-06, | |
| "loss": 0.9219, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 2.758064516129032, | |
| "grad_norm": 6.208500862121582, | |
| "learning_rate": 5.017921146953405e-06, | |
| "loss": 0.8854, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 2.806451612903226, | |
| "grad_norm": 7.67927885055542, | |
| "learning_rate": 4.910394265232976e-06, | |
| "loss": 0.7603, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 2.8548387096774195, | |
| "grad_norm": 9.24992561340332, | |
| "learning_rate": 4.802867383512545e-06, | |
| "loss": 0.819, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 2.903225806451613, | |
| "grad_norm": 7.481741428375244, | |
| "learning_rate": 4.695340501792115e-06, | |
| "loss": 0.8486, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.9516129032258065, | |
| "grad_norm": 8.279362678527832, | |
| "learning_rate": 4.587813620071685e-06, | |
| "loss": 0.7911, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 6.6752448081970215, | |
| "learning_rate": 4.480286738351255e-06, | |
| "loss": 0.5699, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7804878048780488, | |
| "eval_f1_macro": 0.7723212747631352, | |
| "eval_f1_micro": 0.7804878048780488, | |
| "eval_f1_weighted": 0.7737375265225521, | |
| "eval_loss": 0.7607462406158447, | |
| "eval_precision_macro": 0.7946850438417155, | |
| "eval_precision_micro": 0.7804878048780488, | |
| "eval_precision_weighted": 0.7944935514504388, | |
| "eval_recall_macro": 0.7777777777777777, | |
| "eval_recall_micro": 0.7804878048780488, | |
| "eval_recall_weighted": 0.7804878048780488, | |
| "eval_runtime": 0.7085, | |
| "eval_samples_per_second": 173.617, | |
| "eval_steps_per_second": 11.292, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 3.0483870967741935, | |
| "grad_norm": 6.760964393615723, | |
| "learning_rate": 4.372759856630825e-06, | |
| "loss": 0.727, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 3.096774193548387, | |
| "grad_norm": 5.095468044281006, | |
| "learning_rate": 4.265232974910394e-06, | |
| "loss": 0.6731, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 3.1451612903225805, | |
| "grad_norm": 9.518759727478027, | |
| "learning_rate": 4.157706093189964e-06, | |
| "loss": 0.8496, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 3.193548387096774, | |
| "grad_norm": 6.321383953094482, | |
| "learning_rate": 4.050179211469534e-06, | |
| "loss": 0.7368, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 3.241935483870968, | |
| "grad_norm": 5.962444305419922, | |
| "learning_rate": 3.942652329749105e-06, | |
| "loss": 0.6389, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 3.2903225806451615, | |
| "grad_norm": 6.869384765625, | |
| "learning_rate": 3.8351254480286745e-06, | |
| "loss": 0.6852, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 3.338709677419355, | |
| "grad_norm": 7.892813205718994, | |
| "learning_rate": 3.7275985663082444e-06, | |
| "loss": 0.7319, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 3.3870967741935485, | |
| "grad_norm": 9.712183952331543, | |
| "learning_rate": 3.620071684587814e-06, | |
| "loss": 0.7502, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.435483870967742, | |
| "grad_norm": 5.5098795890808105, | |
| "learning_rate": 3.5125448028673837e-06, | |
| "loss": 0.4983, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 3.4838709677419355, | |
| "grad_norm": 6.6952619552612305, | |
| "learning_rate": 3.4050179211469536e-06, | |
| "loss": 0.6215, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 3.532258064516129, | |
| "grad_norm": 8.5636625289917, | |
| "learning_rate": 3.2974910394265234e-06, | |
| "loss": 0.7535, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 3.5806451612903225, | |
| "grad_norm": 6.691638946533203, | |
| "learning_rate": 3.1899641577060937e-06, | |
| "loss": 0.8351, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 3.629032258064516, | |
| "grad_norm": 7.349640369415283, | |
| "learning_rate": 3.0824372759856636e-06, | |
| "loss": 0.6259, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 3.6774193548387095, | |
| "grad_norm": 6.965548515319824, | |
| "learning_rate": 2.974910394265233e-06, | |
| "loss": 0.7365, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 3.725806451612903, | |
| "grad_norm": 5.973796844482422, | |
| "learning_rate": 2.867383512544803e-06, | |
| "loss": 0.669, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 3.774193548387097, | |
| "grad_norm": 6.919253826141357, | |
| "learning_rate": 2.7598566308243727e-06, | |
| "loss": 0.6993, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 3.8225806451612905, | |
| "grad_norm": 6.3397908210754395, | |
| "learning_rate": 2.652329749103943e-06, | |
| "loss": 0.7181, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 3.870967741935484, | |
| "grad_norm": 5.785044193267822, | |
| "learning_rate": 2.544802867383513e-06, | |
| "loss": 0.4398, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.9193548387096775, | |
| "grad_norm": 5.988158226013184, | |
| "learning_rate": 2.4372759856630828e-06, | |
| "loss": 0.6283, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 3.967741935483871, | |
| "grad_norm": 5.8424973487854, | |
| "learning_rate": 2.3297491039426526e-06, | |
| "loss": 0.579, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8130081300813008, | |
| "eval_f1_macro": 0.808283912469959, | |
| "eval_f1_micro": 0.8130081300813008, | |
| "eval_f1_weighted": 0.8093660017426324, | |
| "eval_loss": 0.6489768624305725, | |
| "eval_precision_macro": 0.8281224884633707, | |
| "eval_precision_micro": 0.8130081300813008, | |
| "eval_precision_weighted": 0.8282651571090791, | |
| "eval_recall_macro": 0.8111111111111112, | |
| "eval_recall_micro": 0.8130081300813008, | |
| "eval_recall_weighted": 0.8130081300813008, | |
| "eval_runtime": 0.7293, | |
| "eval_samples_per_second": 168.664, | |
| "eval_steps_per_second": 10.97, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 4.016129032258065, | |
| "grad_norm": 6.205898761749268, | |
| "learning_rate": 2.222222222222222e-06, | |
| "loss": 0.6333, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 4.064516129032258, | |
| "grad_norm": 10.515931129455566, | |
| "learning_rate": 2.1146953405017924e-06, | |
| "loss": 0.8123, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 4.112903225806452, | |
| "grad_norm": 8.230704307556152, | |
| "learning_rate": 2.0071684587813622e-06, | |
| "loss": 0.4461, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 4.161290322580645, | |
| "grad_norm": 5.984982490539551, | |
| "learning_rate": 1.8996415770609319e-06, | |
| "loss": 0.6573, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 4.209677419354839, | |
| "grad_norm": 9.903221130371094, | |
| "learning_rate": 1.792114695340502e-06, | |
| "loss": 0.7067, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 4.258064516129032, | |
| "grad_norm": 5.222007751464844, | |
| "learning_rate": 1.6845878136200718e-06, | |
| "loss": 0.4508, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 4.306451612903226, | |
| "grad_norm": 6.386465072631836, | |
| "learning_rate": 1.5770609318996417e-06, | |
| "loss": 0.566, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 4.354838709677419, | |
| "grad_norm": 9.981949806213379, | |
| "learning_rate": 1.4695340501792116e-06, | |
| "loss": 0.6265, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 4.403225806451613, | |
| "grad_norm": 5.25981330871582, | |
| "learning_rate": 1.3620071684587816e-06, | |
| "loss": 0.4726, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 4.451612903225806, | |
| "grad_norm": 6.81918478012085, | |
| "learning_rate": 1.2544802867383513e-06, | |
| "loss": 0.5897, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "grad_norm": 4.158679008483887, | |
| "learning_rate": 1.1469534050179212e-06, | |
| "loss": 0.4612, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 4.548387096774194, | |
| "grad_norm": 5.195897579193115, | |
| "learning_rate": 1.039426523297491e-06, | |
| "loss": 0.6686, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 4.596774193548387, | |
| "grad_norm": 4.113834857940674, | |
| "learning_rate": 9.318996415770611e-07, | |
| "loss": 0.4569, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 4.645161290322581, | |
| "grad_norm": 6.790894031524658, | |
| "learning_rate": 8.243727598566309e-07, | |
| "loss": 0.6289, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 4.693548387096774, | |
| "grad_norm": 5.653354644775391, | |
| "learning_rate": 7.168458781362007e-07, | |
| "loss": 0.4998, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 4.741935483870968, | |
| "grad_norm": 14.646848678588867, | |
| "learning_rate": 6.093189964157707e-07, | |
| "loss": 0.6761, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 4.790322580645161, | |
| "grad_norm": 5.255918025970459, | |
| "learning_rate": 5.017921146953406e-07, | |
| "loss": 0.5684, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 4.838709677419355, | |
| "grad_norm": 5.386866569519043, | |
| "learning_rate": 3.942652329749104e-07, | |
| "loss": 0.4544, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.887096774193548, | |
| "grad_norm": 8.672043800354004, | |
| "learning_rate": 2.867383512544803e-07, | |
| "loss": 0.6241, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 4.935483870967742, | |
| "grad_norm": 7.205950736999512, | |
| "learning_rate": 1.7921146953405018e-07, | |
| "loss": 0.5675, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 4.983870967741936, | |
| "grad_norm": 12.01904582977295, | |
| "learning_rate": 7.168458781362007e-08, | |
| "loss": 0.5988, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8211382113821138, | |
| "eval_f1_macro": 0.8169326711187176, | |
| "eval_f1_micro": 0.8211382113821138, | |
| "eval_f1_weighted": 0.8178385589956776, | |
| "eval_loss": 0.6183362007141113, | |
| "eval_precision_macro": 0.8425385791952508, | |
| "eval_precision_micro": 0.8211382113821138, | |
| "eval_precision_weighted": 0.8430523097652948, | |
| "eval_recall_macro": 0.8198412698412699, | |
| "eval_recall_micro": 0.8211382113821138, | |
| "eval_recall_weighted": 0.8211382113821138, | |
| "eval_runtime": 0.723, | |
| "eval_samples_per_second": 170.115, | |
| "eval_steps_per_second": 11.064, | |
| "step": 310 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 310, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 323905893672960.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |