| { |
| "best_global_step": 363, |
| "best_metric": 0.6060348153114319, |
| "best_model_checkpoint": "/home/plucky/ml-workspace/models/gemma4-26b-securecode/checkpoint-363", |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 363, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 1.1113492242991925, |
| "epoch": 0.0827300930713547, |
| "grad_norm": 10.3125, |
| "learning_rate": 1.8e-05, |
| "loss": 93.48836059570313, |
| "mean_token_accuracy": 0.4107020549476147, |
| "num_tokens": 81920.0, |
| "step": 10 |
| }, |
| { |
| "entropy": 0.8875315530225635, |
| "epoch": 0.1654601861427094, |
| "grad_norm": 6.15625, |
| "learning_rate": 3.8e-05, |
| "loss": 67.76697998046875, |
| "mean_token_accuracy": 0.5182974558323622, |
| "num_tokens": 163840.0, |
| "step": 20 |
| }, |
| { |
| "entropy": 0.673606987670064, |
| "epoch": 0.2481902792140641, |
| "grad_norm": 2.421875, |
| "learning_rate": 5.8e-05, |
| "loss": 37.221334838867186, |
| "mean_token_accuracy": 0.6476027386263012, |
| "num_tokens": 245760.0, |
| "step": 30 |
| }, |
| { |
| "entropy": 1.0845661748200655, |
| "epoch": 0.3309203722854188, |
| "grad_norm": 1.3671875, |
| "learning_rate": 7.800000000000001e-05, |
| "loss": 22.017848205566406, |
| "mean_token_accuracy": 0.7083170266821981, |
| "num_tokens": 327680.0, |
| "step": 40 |
| }, |
| { |
| "entropy": 1.1636322166770696, |
| "epoch": 0.4136504653567735, |
| "grad_norm": 0.703125, |
| "learning_rate": 9.8e-05, |
| "loss": 17.47879638671875, |
| "mean_token_accuracy": 0.7332558700814843, |
| "num_tokens": 409600.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 0.9551631901413202, |
| "epoch": 0.4963805584281282, |
| "grad_norm": 0.40625, |
| "learning_rate": 0.000118, |
| "loss": 15.09481201171875, |
| "mean_token_accuracy": 0.7555772982537746, |
| "num_tokens": 491520.0, |
| "step": 60 |
| }, |
| { |
| "entropy": 0.8048430571332574, |
| "epoch": 0.5791106514994829, |
| "grad_norm": 0.375, |
| "learning_rate": 0.000138, |
| "loss": 13.297686767578124, |
| "mean_token_accuracy": 0.7774828754365444, |
| "num_tokens": 573440.0, |
| "step": 70 |
| }, |
| { |
| "entropy": 0.8100443260744215, |
| "epoch": 0.6618407445708376, |
| "grad_norm": 0.4609375, |
| "learning_rate": 0.00015800000000000002, |
| "loss": 12.752572631835937, |
| "mean_token_accuracy": 0.7837084107100963, |
| "num_tokens": 655360.0, |
| "step": 80 |
| }, |
| { |
| "entropy": 0.7172152267768979, |
| "epoch": 0.7445708376421923, |
| "grad_norm": 2.1875, |
| "learning_rate": 0.00017800000000000002, |
| "loss": 11.629959106445312, |
| "mean_token_accuracy": 0.799449609220028, |
| "num_tokens": 737280.0, |
| "step": 90 |
| }, |
| { |
| "entropy": 0.7284062243998051, |
| "epoch": 0.827300930713547, |
| "grad_norm": 0.40625, |
| "learning_rate": 0.00019800000000000002, |
| "loss": 11.506278991699219, |
| "mean_token_accuracy": 0.8022871781140566, |
| "num_tokens": 819200.0, |
| "step": 100 |
| }, |
| { |
| "entropy": 0.6922262106090784, |
| "epoch": 0.9100310237849017, |
| "grad_norm": 0.341796875, |
| "learning_rate": 0.00019942266891397815, |
| "loss": 11.149666595458985, |
| "mean_token_accuracy": 0.8068982377648354, |
| "num_tokens": 901120.0, |
| "step": 110 |
| }, |
| { |
| "entropy": 0.6608987387269736, |
| "epoch": 0.9927611168562565, |
| "grad_norm": 0.373046875, |
| "learning_rate": 0.00019743551343638324, |
| "loss": 10.666960906982421, |
| "mean_token_accuracy": 0.8124388422816992, |
| "num_tokens": 983040.0, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_entropy": 0.6862195637336997, |
| "eval_loss": 0.6695265769958496, |
| "eval_mean_token_accuracy": 0.8135074851124786, |
| "eval_num_tokens": 990208.0, |
| "eval_runtime": 255.0413, |
| "eval_samples_per_second": 0.843, |
| "eval_steps_per_second": 0.843, |
| "step": 121 |
| }, |
| { |
| "entropy": 0.6788679953617386, |
| "epoch": 1.0744570837642193, |
| "grad_norm": 0.3984375, |
| "learning_rate": 0.00019405971991583108, |
| "loss": 10.533837127685548, |
| "mean_token_accuracy": 0.8129133717923225, |
| "num_tokens": 1063936.0, |
| "step": 130 |
| }, |
| { |
| "entropy": 0.5800832805223763, |
| "epoch": 1.157187176835574, |
| "grad_norm": 0.333984375, |
| "learning_rate": 0.00018934339971482674, |
| "loss": 9.498150634765626, |
| "mean_token_accuracy": 0.8281555753201246, |
| "num_tokens": 1145856.0, |
| "step": 140 |
| }, |
| { |
| "entropy": 0.6344770405441522, |
| "epoch": 1.2399172699069285, |
| "grad_norm": 0.388671875, |
| "learning_rate": 0.00018335376920472097, |
| "loss": 10.217367553710938, |
| "mean_token_accuracy": 0.8195327781140804, |
| "num_tokens": 1227776.0, |
| "step": 150 |
| }, |
| { |
| "entropy": 0.6310219537466765, |
| "epoch": 1.3226473629782833, |
| "grad_norm": 0.380859375, |
| "learning_rate": 0.00017617619180688085, |
| "loss": 10.081737518310547, |
| "mean_token_accuracy": 0.8219178050756455, |
| "num_tokens": 1309696.0, |
| "step": 160 |
| }, |
| { |
| "entropy": 0.5863334746100008, |
| "epoch": 1.4053774560496382, |
| "grad_norm": 0.341796875, |
| "learning_rate": 0.00016791296140450545, |
| "loss": 9.392319488525391, |
| "mean_token_accuracy": 0.8319227002561093, |
| "num_tokens": 1391616.0, |
| "step": 170 |
| }, |
| { |
| "entropy": 0.6232900662347675, |
| "epoch": 1.4881075491209927, |
| "grad_norm": 0.44921875, |
| "learning_rate": 0.0001586818444637402, |
| "loss": 10.051438140869141, |
| "mean_token_accuracy": 0.8215264175087214, |
| "num_tokens": 1473536.0, |
| "step": 180 |
| }, |
| { |
| "entropy": 0.6163463215343654, |
| "epoch": 1.5708376421923473, |
| "grad_norm": 0.384765625, |
| "learning_rate": 0.0001486144016415862, |
| "loss": 9.878226470947265, |
| "mean_token_accuracy": 0.8220768082886935, |
| "num_tokens": 1555456.0, |
| "step": 190 |
| }, |
| { |
| "entropy": 0.588023800123483, |
| "epoch": 1.6535677352637022, |
| "grad_norm": 0.3515625, |
| "learning_rate": 0.00013785411280082746, |
| "loss": 9.45407943725586, |
| "mean_token_accuracy": 0.8305283710360527, |
| "num_tokens": 1637376.0, |
| "step": 200 |
| }, |
| { |
| "entropy": 0.599842881783843, |
| "epoch": 1.736297828335057, |
| "grad_norm": 0.37890625, |
| "learning_rate": 0.00012655433215401438, |
| "loss": 9.548422241210938, |
| "mean_token_accuracy": 0.8284735765308142, |
| "num_tokens": 1719296.0, |
| "step": 210 |
| }, |
| { |
| "entropy": 0.6552030782215297, |
| "epoch": 1.8190279214064116, |
| "grad_norm": 0.361328125, |
| "learning_rate": 0.00011487610267952142, |
| "loss": 10.46890640258789, |
| "mean_token_accuracy": 0.8134295467287302, |
| "num_tokens": 1801216.0, |
| "step": 220 |
| }, |
| { |
| "entropy": 0.5984975789207965, |
| "epoch": 1.9017580144777662, |
| "grad_norm": 0.353515625, |
| "learning_rate": 0.00010298586095833151, |
| "loss": 9.603475952148438, |
| "mean_token_accuracy": 0.827079250663519, |
| "num_tokens": 1883136.0, |
| "step": 230 |
| }, |
| { |
| "entropy": 0.5947112645488233, |
| "epoch": 1.984488107549121, |
| "grad_norm": 0.64453125, |
| "learning_rate": 9.10530651419099e-05, |
| "loss": 9.561953735351562, |
| "mean_token_accuracy": 0.8265655554831028, |
| "num_tokens": 1965056.0, |
| "step": 240 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_entropy": 0.6100467269503793, |
| "eval_loss": 0.6102388501167297, |
| "eval_mean_token_accuracy": 0.8254676164582718, |
| "eval_num_tokens": 1980416.0, |
| "eval_runtime": 254.828, |
| "eval_samples_per_second": 0.844, |
| "eval_steps_per_second": 0.844, |
| "step": 242 |
| }, |
| { |
| "entropy": 0.5080371947511088, |
| "epoch": 2.066184074457084, |
| "grad_norm": 0.453125, |
| "learning_rate": 7.924777985705556e-05, |
| "loss": 8.056553649902344, |
| "mean_token_accuracy": 0.8497857213774814, |
| "num_tokens": 2045952.0, |
| "step": 250 |
| }, |
| { |
| "entropy": 0.5341692148707807, |
| "epoch": 2.1489141675284387, |
| "grad_norm": 0.384765625, |
| "learning_rate": 6.773825246734622e-05, |
| "loss": 8.356841278076171, |
| "mean_token_accuracy": 0.8431262206286192, |
| "num_tokens": 2127872.0, |
| "step": 260 |
| }, |
| { |
| "entropy": 0.5629857819527387, |
| "epoch": 2.231644260599793, |
| "grad_norm": 0.328125, |
| "learning_rate": 5.668851523397829e-05, |
| "loss": 9.067486572265626, |
| "mean_token_accuracy": 0.8315435405820608, |
| "num_tokens": 2209792.0, |
| "step": 270 |
| }, |
| { |
| "entropy": 0.5280973493587225, |
| "epoch": 2.314374353671148, |
| "grad_norm": 0.361328125, |
| "learning_rate": 4.625604754968839e-05, |
| "loss": 8.390058135986328, |
| "mean_token_accuracy": 0.8423923663794994, |
| "num_tokens": 2291712.0, |
| "step": 280 |
| }, |
| { |
| "entropy": 0.5421305931173265, |
| "epoch": 2.3971044467425027, |
| "grad_norm": 0.353515625, |
| "learning_rate": 3.658953156328857e-05, |
| "loss": 8.713886260986328, |
| "mean_token_accuracy": 0.8375489212572574, |
| "num_tokens": 2373632.0, |
| "step": 290 |
| }, |
| { |
| "entropy": 0.5257686520460993, |
| "epoch": 2.479834539813857, |
| "grad_norm": 0.373046875, |
| "learning_rate": 2.7826733181357932e-05, |
| "loss": 8.388682556152343, |
| "mean_token_accuracy": 0.8447284691035748, |
| "num_tokens": 2455552.0, |
| "step": 300 |
| }, |
| { |
| "entropy": 0.5735760541632772, |
| "epoch": 2.562564632885212, |
| "grad_norm": 0.421875, |
| "learning_rate": 2.0092538646774072e-05, |
| "loss": 9.259294891357422, |
| "mean_token_accuracy": 0.8287671197205781, |
| "num_tokens": 2537472.0, |
| "step": 310 |
| }, |
| { |
| "entropy": 0.5352369678206742, |
| "epoch": 2.6452947259565667, |
| "grad_norm": 0.369140625, |
| "learning_rate": 1.3497174676506674e-05, |
| "loss": 8.547685241699218, |
| "mean_token_accuracy": 0.8413160435855389, |
| "num_tokens": 2619392.0, |
| "step": 320 |
| }, |
| { |
| "entropy": 0.540962244477123, |
| "epoch": 2.7280248190279215, |
| "grad_norm": 0.365234375, |
| "learning_rate": 8.134637525034839e-06, |
| "loss": 8.591437530517577, |
| "mean_token_accuracy": 0.838882090896368, |
| "num_tokens": 2701312.0, |
| "step": 330 |
| }, |
| { |
| "entropy": 0.5567054254934192, |
| "epoch": 2.8107549120992763, |
| "grad_norm": 0.353515625, |
| "learning_rate": 4.081353362167406e-06, |
| "loss": 8.788534545898438, |
| "mean_token_accuracy": 0.8374510746449232, |
| "num_tokens": 2783232.0, |
| "step": 340 |
| }, |
| { |
| "entropy": 0.5575114467181266, |
| "epoch": 2.8934850051706307, |
| "grad_norm": 0.35546875, |
| "learning_rate": 1.3950890573852126e-06, |
| "loss": 8.935771179199218, |
| "mean_token_accuracy": 0.8345768079161644, |
| "num_tokens": 2865152.0, |
| "step": 350 |
| }, |
| { |
| "entropy": 0.5235911178402602, |
| "epoch": 2.9762150982419855, |
| "grad_norm": 0.36328125, |
| "learning_rate": 1.1412889406192673e-07, |
| "loss": 8.273484039306641, |
| "mean_token_accuracy": 0.8450831711292267, |
| "num_tokens": 2947072.0, |
| "step": 360 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_entropy": 0.5448623623265777, |
| "eval_loss": 0.6060348153114319, |
| "eval_mean_token_accuracy": 0.8278159535208414, |
| "eval_num_tokens": 2970624.0, |
| "eval_runtime": 254.9017, |
| "eval_samples_per_second": 0.843, |
| "eval_steps_per_second": 0.843, |
| "step": 363 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 363, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4.471321806592082e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
