| { | |
| "best_metric": 0.13600419461727142, | |
| "best_model_checkpoint": "ghgmetricsv1/checkpoint-205", | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 205, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04878048780487805, | |
| "grad_norm": 2.9317479133605957, | |
| "learning_rate": 9.523809523809525e-07, | |
| "loss": 1.3932, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0975609756097561, | |
| "grad_norm": 3.9777166843414307, | |
| "learning_rate": 1.904761904761905e-06, | |
| "loss": 1.3836, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.14634146341463414, | |
| "grad_norm": 1.704893946647644, | |
| "learning_rate": 2.8571428571428573e-06, | |
| "loss": 1.3873, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1951219512195122, | |
| "grad_norm": 6.335275650024414, | |
| "learning_rate": 3.80952380952381e-06, | |
| "loss": 1.3632, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.24390243902439024, | |
| "grad_norm": 4.805781841278076, | |
| "learning_rate": 4.761904761904762e-06, | |
| "loss": 1.3751, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2926829268292683, | |
| "grad_norm": 3.296025037765503, | |
| "learning_rate": 5.7142857142857145e-06, | |
| "loss": 1.3728, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.34146341463414637, | |
| "grad_norm": 5.443967819213867, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 1.3971, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3902439024390244, | |
| "grad_norm": 2.8683745861053467, | |
| "learning_rate": 7.61904761904762e-06, | |
| "loss": 1.3835, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.43902439024390244, | |
| "grad_norm": 3.625200033187866, | |
| "learning_rate": 8.571428571428571e-06, | |
| "loss": 1.3608, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.4878048780487805, | |
| "grad_norm": 3.082287549972534, | |
| "learning_rate": 9.523809523809525e-06, | |
| "loss": 1.3707, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5365853658536586, | |
| "grad_norm": 3.2846016883850098, | |
| "learning_rate": 9.945652173913044e-06, | |
| "loss": 1.3676, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5853658536585366, | |
| "grad_norm": 2.4396913051605225, | |
| "learning_rate": 9.836956521739131e-06, | |
| "loss": 1.3729, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.6341463414634146, | |
| "grad_norm": 3.262892246246338, | |
| "learning_rate": 9.728260869565218e-06, | |
| "loss": 1.3281, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.6829268292682927, | |
| "grad_norm": 3.9962172508239746, | |
| "learning_rate": 9.619565217391305e-06, | |
| "loss": 1.3489, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.7317073170731707, | |
| "grad_norm": 3.4944751262664795, | |
| "learning_rate": 9.510869565217392e-06, | |
| "loss": 1.3397, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7804878048780488, | |
| "grad_norm": 3.8272864818573, | |
| "learning_rate": 9.402173913043479e-06, | |
| "loss": 1.3642, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.8292682926829268, | |
| "grad_norm": 3.0262584686279297, | |
| "learning_rate": 9.293478260869566e-06, | |
| "loss": 1.2988, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.8780487804878049, | |
| "grad_norm": 3.4564623832702637, | |
| "learning_rate": 9.184782608695653e-06, | |
| "loss": 1.3577, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.926829268292683, | |
| "grad_norm": 3.0925350189208984, | |
| "learning_rate": 9.07608695652174e-06, | |
| "loss": 1.3337, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.975609756097561, | |
| "grad_norm": 5.996058940887451, | |
| "learning_rate": 8.967391304347827e-06, | |
| "loss": 1.2585, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6951219512195121, | |
| "eval_f1_macro": 0.6114890400604687, | |
| "eval_f1_micro": 0.6951219512195121, | |
| "eval_f1_weighted": 0.60425308334716, | |
| "eval_loss": 1.2632431983947754, | |
| "eval_precision_macro": 0.5512016718913271, | |
| "eval_precision_micro": 0.6951219512195121, | |
| "eval_precision_weighted": 0.5440400642250938, | |
| "eval_recall_macro": 0.7023809523809523, | |
| "eval_recall_micro": 0.6951219512195121, | |
| "eval_recall_weighted": 0.6951219512195121, | |
| "eval_runtime": 0.4935, | |
| "eval_samples_per_second": 166.174, | |
| "eval_steps_per_second": 12.159, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.024390243902439, | |
| "grad_norm": 3.56406307220459, | |
| "learning_rate": 8.858695652173914e-06, | |
| "loss": 1.2581, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.0731707317073171, | |
| "grad_norm": 4.123223781585693, | |
| "learning_rate": 8.750000000000001e-06, | |
| "loss": 1.2903, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.1219512195121952, | |
| "grad_norm": 5.944389343261719, | |
| "learning_rate": 8.641304347826088e-06, | |
| "loss": 1.2028, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.170731707317073, | |
| "grad_norm": 6.736316680908203, | |
| "learning_rate": 8.532608695652175e-06, | |
| "loss": 1.1808, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.2195121951219512, | |
| "grad_norm": 5.414186000823975, | |
| "learning_rate": 8.423913043478262e-06, | |
| "loss": 1.2169, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.2682926829268293, | |
| "grad_norm": 4.436485767364502, | |
| "learning_rate": 8.315217391304349e-06, | |
| "loss": 1.0759, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.3170731707317074, | |
| "grad_norm": 5.241353511810303, | |
| "learning_rate": 8.206521739130436e-06, | |
| "loss": 0.969, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.3658536585365852, | |
| "grad_norm": 5.724743843078613, | |
| "learning_rate": 8.097826086956523e-06, | |
| "loss": 1.0252, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.4146341463414633, | |
| "grad_norm": 7.156280517578125, | |
| "learning_rate": 7.98913043478261e-06, | |
| "loss": 0.9933, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 1.4634146341463414, | |
| "grad_norm": 5.4803032875061035, | |
| "learning_rate": 7.880434782608695e-06, | |
| "loss": 1.0366, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.5121951219512195, | |
| "grad_norm": 6.876482009887695, | |
| "learning_rate": 7.771739130434784e-06, | |
| "loss": 0.9037, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.5609756097560976, | |
| "grad_norm": 6.233717918395996, | |
| "learning_rate": 7.66304347826087e-06, | |
| "loss": 0.9415, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.6097560975609757, | |
| "grad_norm": 4.58766508102417, | |
| "learning_rate": 7.5543478260869576e-06, | |
| "loss": 0.8246, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.6585365853658538, | |
| "grad_norm": 3.917952537536621, | |
| "learning_rate": 7.445652173913044e-06, | |
| "loss": 0.7553, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.7073170731707317, | |
| "grad_norm": 6.8940110206604, | |
| "learning_rate": 7.3369565217391315e-06, | |
| "loss": 0.8116, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.7560975609756098, | |
| "grad_norm": 5.17503023147583, | |
| "learning_rate": 7.228260869565218e-06, | |
| "loss": 0.7152, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.8048780487804879, | |
| "grad_norm": 4.659473419189453, | |
| "learning_rate": 7.119565217391305e-06, | |
| "loss": 0.6917, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.8536585365853657, | |
| "grad_norm": 4.061087608337402, | |
| "learning_rate": 7.0108695652173915e-06, | |
| "loss": 0.6462, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.9024390243902438, | |
| "grad_norm": 4.6313042640686035, | |
| "learning_rate": 6.9021739130434785e-06, | |
| "loss": 0.542, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.951219512195122, | |
| "grad_norm": 4.6593337059021, | |
| "learning_rate": 6.793478260869566e-06, | |
| "loss": 0.4713, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 6.978389739990234, | |
| "learning_rate": 6.6847826086956524e-06, | |
| "loss": 0.5677, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9512195121951219, | |
| "eval_f1_macro": 0.950956937799043, | |
| "eval_f1_micro": 0.9512195121951219, | |
| "eval_f1_weighted": 0.9508694130003501, | |
| "eval_loss": 0.47162312269210815, | |
| "eval_precision_macro": 0.9583333333333334, | |
| "eval_precision_micro": 0.9512195121951219, | |
| "eval_precision_weighted": 0.9593495934959351, | |
| "eval_recall_macro": 0.9523809523809523, | |
| "eval_recall_micro": 0.9512195121951219, | |
| "eval_recall_weighted": 0.9512195121951219, | |
| "eval_runtime": 0.4717, | |
| "eval_samples_per_second": 173.839, | |
| "eval_steps_per_second": 12.72, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 2.048780487804878, | |
| "grad_norm": 7.042616844177246, | |
| "learning_rate": 6.57608695652174e-06, | |
| "loss": 0.616, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 2.097560975609756, | |
| "grad_norm": 3.9137861728668213, | |
| "learning_rate": 6.467391304347826e-06, | |
| "loss": 0.4503, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 2.1463414634146343, | |
| "grad_norm": 4.030788898468018, | |
| "learning_rate": 6.358695652173914e-06, | |
| "loss": 0.4646, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 2.1951219512195124, | |
| "grad_norm": 3.972332000732422, | |
| "learning_rate": 6.25e-06, | |
| "loss": 0.3834, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.2439024390243905, | |
| "grad_norm": 4.146308422088623, | |
| "learning_rate": 6.141304347826087e-06, | |
| "loss": 0.4568, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 2.292682926829268, | |
| "grad_norm": 5.081860542297363, | |
| "learning_rate": 6.032608695652174e-06, | |
| "loss": 0.3908, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 2.341463414634146, | |
| "grad_norm": 4.0336737632751465, | |
| "learning_rate": 5.923913043478261e-06, | |
| "loss": 0.3683, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 2.3902439024390243, | |
| "grad_norm": 4.34877347946167, | |
| "learning_rate": 5.815217391304349e-06, | |
| "loss": 0.3549, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 2.4390243902439024, | |
| "grad_norm": 4.02614688873291, | |
| "learning_rate": 5.706521739130435e-06, | |
| "loss": 0.2872, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.4878048780487805, | |
| "grad_norm": 3.376811981201172, | |
| "learning_rate": 5.597826086956523e-06, | |
| "loss": 0.2727, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 2.5365853658536586, | |
| "grad_norm": 3.333051919937134, | |
| "learning_rate": 5.489130434782609e-06, | |
| "loss": 0.4225, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 2.5853658536585367, | |
| "grad_norm": 5.0091233253479, | |
| "learning_rate": 5.380434782608695e-06, | |
| "loss": 0.3101, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 2.6341463414634148, | |
| "grad_norm": 2.833436965942383, | |
| "learning_rate": 5.271739130434783e-06, | |
| "loss": 0.2518, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 2.682926829268293, | |
| "grad_norm": 5.041337966918945, | |
| "learning_rate": 5.16304347826087e-06, | |
| "loss": 0.2779, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.7317073170731705, | |
| "grad_norm": 2.2699122428894043, | |
| "learning_rate": 5.054347826086957e-06, | |
| "loss": 0.2463, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 2.7804878048780486, | |
| "grad_norm": 4.098880290985107, | |
| "learning_rate": 4.945652173913044e-06, | |
| "loss": 0.2166, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 2.8292682926829267, | |
| "grad_norm": 2.4703168869018555, | |
| "learning_rate": 4.836956521739131e-06, | |
| "loss": 0.208, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 2.8780487804878048, | |
| "grad_norm": 1.5095465183258057, | |
| "learning_rate": 4.728260869565218e-06, | |
| "loss": 0.162, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 2.926829268292683, | |
| "grad_norm": 2.051690101623535, | |
| "learning_rate": 4.619565217391305e-06, | |
| "loss": 0.1421, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.975609756097561, | |
| "grad_norm": 3.00022292137146, | |
| "learning_rate": 4.510869565217392e-06, | |
| "loss": 0.1608, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9512195121951219, | |
| "eval_f1_macro": 0.950956937799043, | |
| "eval_f1_micro": 0.9512195121951219, | |
| "eval_f1_weighted": 0.9508694130003501, | |
| "eval_loss": 0.168848916888237, | |
| "eval_precision_macro": 0.9583333333333334, | |
| "eval_precision_micro": 0.9512195121951219, | |
| "eval_precision_weighted": 0.9593495934959351, | |
| "eval_recall_macro": 0.9523809523809523, | |
| "eval_recall_micro": 0.9512195121951219, | |
| "eval_recall_weighted": 0.9512195121951219, | |
| "eval_runtime": 0.4909, | |
| "eval_samples_per_second": 167.047, | |
| "eval_steps_per_second": 12.223, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 3.024390243902439, | |
| "grad_norm": 3.7563741207122803, | |
| "learning_rate": 4.402173913043479e-06, | |
| "loss": 0.1614, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 3.073170731707317, | |
| "grad_norm": 2.9541540145874023, | |
| "learning_rate": 4.293478260869566e-06, | |
| "loss": 0.1264, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 3.1219512195121952, | |
| "grad_norm": 6.017066955566406, | |
| "learning_rate": 4.184782608695653e-06, | |
| "loss": 0.222, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 3.1707317073170733, | |
| "grad_norm": 1.9936599731445312, | |
| "learning_rate": 4.07608695652174e-06, | |
| "loss": 0.1367, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 3.2195121951219514, | |
| "grad_norm": 1.2631906270980835, | |
| "learning_rate": 3.967391304347827e-06, | |
| "loss": 0.1826, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 3.2682926829268295, | |
| "grad_norm": 1.4446691274642944, | |
| "learning_rate": 3.8586956521739136e-06, | |
| "loss": 0.1043, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 3.317073170731707, | |
| "grad_norm": 2.9397401809692383, | |
| "learning_rate": 3.7500000000000005e-06, | |
| "loss": 0.115, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 3.3658536585365852, | |
| "grad_norm": 4.312378883361816, | |
| "learning_rate": 3.6413043478260875e-06, | |
| "loss": 0.2012, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 3.4146341463414633, | |
| "grad_norm": 3.6363883018493652, | |
| "learning_rate": 3.5326086956521745e-06, | |
| "loss": 0.1988, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 3.4634146341463414, | |
| "grad_norm": 0.9747779369354248, | |
| "learning_rate": 3.4239130434782614e-06, | |
| "loss": 0.1, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 3.5121951219512195, | |
| "grad_norm": 1.1869757175445557, | |
| "learning_rate": 3.315217391304348e-06, | |
| "loss": 0.0899, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 3.5609756097560976, | |
| "grad_norm": 4.576517581939697, | |
| "learning_rate": 3.206521739130435e-06, | |
| "loss": 0.1466, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 3.6097560975609757, | |
| "grad_norm": 0.8520755171775818, | |
| "learning_rate": 3.097826086956522e-06, | |
| "loss": 0.0733, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 3.658536585365854, | |
| "grad_norm": 0.8718931078910828, | |
| "learning_rate": 2.989130434782609e-06, | |
| "loss": 0.0739, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 3.7073170731707314, | |
| "grad_norm": 5.841705322265625, | |
| "learning_rate": 2.880434782608696e-06, | |
| "loss": 0.1244, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 3.7560975609756095, | |
| "grad_norm": 1.4700547456741333, | |
| "learning_rate": 2.771739130434783e-06, | |
| "loss": 0.0914, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 3.8048780487804876, | |
| "grad_norm": 1.7812182903289795, | |
| "learning_rate": 2.6630434782608698e-06, | |
| "loss": 0.3075, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 3.8536585365853657, | |
| "grad_norm": 1.647403597831726, | |
| "learning_rate": 2.554347826086957e-06, | |
| "loss": 0.0708, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 3.902439024390244, | |
| "grad_norm": 5.995601177215576, | |
| "learning_rate": 2.4456521739130437e-06, | |
| "loss": 0.2148, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 3.951219512195122, | |
| "grad_norm": 0.676275372505188, | |
| "learning_rate": 2.3369565217391307e-06, | |
| "loss": 0.0611, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 1.365096092224121, | |
| "learning_rate": 2.2282608695652176e-06, | |
| "loss": 0.0752, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9512195121951219, | |
| "eval_f1_macro": 0.950956937799043, | |
| "eval_f1_micro": 0.9512195121951219, | |
| "eval_f1_weighted": 0.9508694130003501, | |
| "eval_loss": 0.1366794854402542, | |
| "eval_precision_macro": 0.9583333333333334, | |
| "eval_precision_micro": 0.9512195121951219, | |
| "eval_precision_weighted": 0.9593495934959351, | |
| "eval_recall_macro": 0.9523809523809523, | |
| "eval_recall_micro": 0.9512195121951219, | |
| "eval_recall_weighted": 0.9512195121951219, | |
| "eval_runtime": 0.4791, | |
| "eval_samples_per_second": 171.169, | |
| "eval_steps_per_second": 12.525, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 4.048780487804878, | |
| "grad_norm": 0.8058091402053833, | |
| "learning_rate": 2.1195652173913046e-06, | |
| "loss": 0.0717, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 4.097560975609756, | |
| "grad_norm": 1.4378560781478882, | |
| "learning_rate": 2.0108695652173916e-06, | |
| "loss": 0.1008, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 4.146341463414634, | |
| "grad_norm": 4.043826103210449, | |
| "learning_rate": 1.9021739130434785e-06, | |
| "loss": 0.1217, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 4.195121951219512, | |
| "grad_norm": 0.8742417097091675, | |
| "learning_rate": 1.7934782608695653e-06, | |
| "loss": 0.1098, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 4.2439024390243905, | |
| "grad_norm": 2.178234577178955, | |
| "learning_rate": 1.6847826086956522e-06, | |
| "loss": 0.1247, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 4.2926829268292686, | |
| "grad_norm": 0.7950467467308044, | |
| "learning_rate": 1.5760869565217394e-06, | |
| "loss": 0.0651, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 4.341463414634147, | |
| "grad_norm": 0.954619824886322, | |
| "learning_rate": 1.4673913043478264e-06, | |
| "loss": 0.0552, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 4.390243902439025, | |
| "grad_norm": 6.469586372375488, | |
| "learning_rate": 1.3586956521739131e-06, | |
| "loss": 0.2431, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 4.439024390243903, | |
| "grad_norm": 0.6579374074935913, | |
| "learning_rate": 1.25e-06, | |
| "loss": 0.0656, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 4.487804878048781, | |
| "grad_norm": 4.1302361488342285, | |
| "learning_rate": 1.141304347826087e-06, | |
| "loss": 0.1081, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 4.536585365853659, | |
| "grad_norm": 1.015049934387207, | |
| "learning_rate": 1.032608695652174e-06, | |
| "loss": 0.1111, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 4.585365853658536, | |
| "grad_norm": 0.679076611995697, | |
| "learning_rate": 9.239130434782609e-07, | |
| "loss": 0.0595, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 4.634146341463414, | |
| "grad_norm": 1.741278052330017, | |
| "learning_rate": 8.152173913043479e-07, | |
| "loss": 0.1325, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 4.682926829268292, | |
| "grad_norm": 5.028622150421143, | |
| "learning_rate": 7.065217391304348e-07, | |
| "loss": 0.173, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 4.7317073170731705, | |
| "grad_norm": 0.735034704208374, | |
| "learning_rate": 5.978260869565218e-07, | |
| "loss": 0.0457, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 4.780487804878049, | |
| "grad_norm": 7.007546424865723, | |
| "learning_rate": 4.891304347826088e-07, | |
| "loss": 0.1926, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 4.829268292682927, | |
| "grad_norm": 0.8504419922828674, | |
| "learning_rate": 3.804347826086957e-07, | |
| "loss": 0.1623, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 4.878048780487805, | |
| "grad_norm": 1.4162288904190063, | |
| "learning_rate": 2.7173913043478264e-07, | |
| "loss": 0.0726, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 4.926829268292683, | |
| "grad_norm": 0.7092806696891785, | |
| "learning_rate": 1.6304347826086958e-07, | |
| "loss": 0.0515, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 4.975609756097561, | |
| "grad_norm": 0.7422751784324646, | |
| "learning_rate": 5.4347826086956524e-08, | |
| "loss": 0.0845, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9512195121951219, | |
| "eval_f1_macro": 0.950956937799043, | |
| "eval_f1_micro": 0.9512195121951219, | |
| "eval_f1_weighted": 0.9508694130003501, | |
| "eval_loss": 0.13600419461727142, | |
| "eval_precision_macro": 0.9583333333333334, | |
| "eval_precision_micro": 0.9512195121951219, | |
| "eval_precision_weighted": 0.9593495934959351, | |
| "eval_recall_macro": 0.9523809523809523, | |
| "eval_recall_micro": 0.9512195121951219, | |
| "eval_recall_weighted": 0.9512195121951219, | |
| "eval_runtime": 0.491, | |
| "eval_samples_per_second": 167.022, | |
| "eval_steps_per_second": 12.221, | |
| "step": 205 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 205, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 215929561128960.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |