| { | |
| "best_metric": 0.7137496471405029, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.024351637647631805, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00048703275295263604, | |
| "grad_norm": 0.9668720960617065, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7861, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00048703275295263604, | |
| "eval_loss": 0.8942872285842896, | |
| "eval_runtime": 52.1362, | |
| "eval_samples_per_second": 66.345, | |
| "eval_steps_per_second": 8.305, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009740655059052721, | |
| "grad_norm": 1.109323501586914, | |
| "learning_rate": 4e-05, | |
| "loss": 0.7208, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0014610982588579083, | |
| "grad_norm": 0.8979827165603638, | |
| "learning_rate": 6e-05, | |
| "loss": 0.7672, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0019481310118105442, | |
| "grad_norm": 0.7457740306854248, | |
| "learning_rate": 8e-05, | |
| "loss": 0.7396, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0024351637647631805, | |
| "grad_norm": 0.9767470955848694, | |
| "learning_rate": 0.0001, | |
| "loss": 0.788, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0029221965177158166, | |
| "grad_norm": 0.928979754447937, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.7996, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0034092292706684527, | |
| "grad_norm": 0.7546679377555847, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 0.7589, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0038962620236210883, | |
| "grad_norm": 0.757028341293335, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.9003, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004383294776573725, | |
| "grad_norm": 0.7388772964477539, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.7762, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004870327529526361, | |
| "grad_norm": 0.713144063949585, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.745, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005357360282478997, | |
| "grad_norm": 0.6719604134559631, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.7749, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005844393035431633, | |
| "grad_norm": 0.6307094693183899, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.6938, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006331425788384269, | |
| "grad_norm": 0.6746920943260193, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 0.8753, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.006818458541336905, | |
| "grad_norm": 0.6357215642929077, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.7801, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0073054912942895405, | |
| "grad_norm": 0.7156640291213989, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.7304, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007792524047242177, | |
| "grad_norm": 0.7125033140182495, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 0.7382, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.008279556800194814, | |
| "grad_norm": 0.7216728925704956, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 0.7764, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.00876658955314745, | |
| "grad_norm": 0.6608908176422119, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 0.7247, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.009253622306100086, | |
| "grad_norm": 0.7499627470970154, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 0.796, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.009740655059052722, | |
| "grad_norm": 0.6988794803619385, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.7523, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010227687812005358, | |
| "grad_norm": 0.7267606854438782, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 0.7685, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.010714720564957994, | |
| "grad_norm": 0.6517067551612854, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 0.7143, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01120175331791063, | |
| "grad_norm": 0.6588945984840393, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.7267, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.011688786070863266, | |
| "grad_norm": 0.6455866694450378, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 0.771, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.012175818823815902, | |
| "grad_norm": 0.6290040016174316, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.7143, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012175818823815902, | |
| "eval_loss": 0.7276486754417419, | |
| "eval_runtime": 52.1205, | |
| "eval_samples_per_second": 66.365, | |
| "eval_steps_per_second": 8.308, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012662851576768538, | |
| "grad_norm": 0.6263149976730347, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 0.8059, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.013149884329721175, | |
| "grad_norm": 0.649336576461792, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 0.714, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.01363691708267381, | |
| "grad_norm": 0.6983732581138611, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 0.7714, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.014123949835626447, | |
| "grad_norm": 0.6310800909996033, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 0.7492, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.014610982588579081, | |
| "grad_norm": 0.6215700507164001, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.6541, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.015098015341531717, | |
| "grad_norm": 0.7055749893188477, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 0.6742, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.015585048094484353, | |
| "grad_norm": 0.634620189666748, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.6968, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.01607208084743699, | |
| "grad_norm": 0.6823827028274536, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 0.7632, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.016559113600389627, | |
| "grad_norm": 0.6950632929801941, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 0.7368, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.017046146353342263, | |
| "grad_norm": 0.7879264950752258, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.8233, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0175331791062949, | |
| "grad_norm": 0.6341107487678528, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 0.6603, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.018020211859247535, | |
| "grad_norm": 0.6985974311828613, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 0.6774, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.01850724461220017, | |
| "grad_norm": 0.7165974378585815, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 0.7472, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.018994277365152808, | |
| "grad_norm": 0.7006275057792664, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 0.6472, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.019481310118105444, | |
| "grad_norm": 0.6504078507423401, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 0.7263, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01996834287105808, | |
| "grad_norm": 0.6661069989204407, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.6685, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.020455375624010716, | |
| "grad_norm": 0.7080692648887634, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 0.6859, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.020942408376963352, | |
| "grad_norm": 0.7681254744529724, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 0.6853, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.021429441129915988, | |
| "grad_norm": 0.7165603637695312, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 0.6546, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.021916473882868624, | |
| "grad_norm": 0.7238483428955078, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.7094, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02240350663582126, | |
| "grad_norm": 0.7569670677185059, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 0.669, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.022890539388773896, | |
| "grad_norm": 0.7207056879997253, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 0.6464, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.023377572141726533, | |
| "grad_norm": 0.7816201448440552, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 0.6456, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.02386460489467917, | |
| "grad_norm": 0.8748300671577454, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 0.7031, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.024351637647631805, | |
| "grad_norm": 0.933390200138092, | |
| "learning_rate": 0.0, | |
| "loss": 0.5756, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.024351637647631805, | |
| "eval_loss": 0.7137496471405029, | |
| "eval_runtime": 52.1712, | |
| "eval_samples_per_second": 66.301, | |
| "eval_steps_per_second": 8.3, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3603404933824512.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |