| { | |
| "best_metric": 0.24603328108787537, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.01704012950498424, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00034080259009968474, | |
| "grad_norm": 9.989192008972168, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6867, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00034080259009968474, | |
| "eval_loss": 1.7972990274429321, | |
| "eval_runtime": 43.1122, | |
| "eval_samples_per_second": 114.631, | |
| "eval_steps_per_second": 14.335, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006816051801993695, | |
| "grad_norm": 16.630624771118164, | |
| "learning_rate": 4e-05, | |
| "loss": 0.808, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0010224077702990543, | |
| "grad_norm": 13.712169647216797, | |
| "learning_rate": 6e-05, | |
| "loss": 0.6378, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001363210360398739, | |
| "grad_norm": 11.038908958435059, | |
| "learning_rate": 8e-05, | |
| "loss": 0.3884, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0017040129504984239, | |
| "grad_norm": 3.3606460094451904, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1786, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0020448155405981086, | |
| "grad_norm": 2.56026291847229, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.1869, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0023856181306977932, | |
| "grad_norm": 1.7779616117477417, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 0.1185, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002726420720797478, | |
| "grad_norm": 1.8680403232574463, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.1476, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0030672233108971626, | |
| "grad_norm": 1.670699954032898, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.1708, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0034080259009968477, | |
| "grad_norm": 1.7200086116790771, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.1603, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0037488284910965324, | |
| "grad_norm": 1.5464619398117065, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.142, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.004089631081196217, | |
| "grad_norm": 1.7468676567077637, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.1477, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004430433671295902, | |
| "grad_norm": 1.719665765762329, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 0.166, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0047712362613955865, | |
| "grad_norm": 2.118823528289795, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.1893, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.005112038851495271, | |
| "grad_norm": 2.8782100677490234, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.1739, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005452841441594956, | |
| "grad_norm": 1.666822075843811, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 0.1541, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0057936440316946405, | |
| "grad_norm": 1.7106536626815796, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 0.17, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.006134446621794325, | |
| "grad_norm": 4.83658504486084, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 0.2174, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.006475249211894011, | |
| "grad_norm": 1.4987841844558716, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 0.1582, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0068160518019936955, | |
| "grad_norm": 1.535029411315918, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.2168, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00715685439209338, | |
| "grad_norm": 1.4463130235671997, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 0.1679, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.007497656982193065, | |
| "grad_norm": 1.6651973724365234, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 0.2147, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.007838459572292749, | |
| "grad_norm": 1.7184096574783325, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.2209, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.008179262162392434, | |
| "grad_norm": 1.4899485111236572, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 0.1612, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00852006475249212, | |
| "grad_norm": 1.4448050260543823, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.1788, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00852006475249212, | |
| "eval_loss": 0.25700467824935913, | |
| "eval_runtime": 43.0715, | |
| "eval_samples_per_second": 114.74, | |
| "eval_steps_per_second": 14.348, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.008860867342591804, | |
| "grad_norm": 1.4867175817489624, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 0.2165, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.00920166993269149, | |
| "grad_norm": 1.8742293119430542, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 0.2375, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.009542472522791173, | |
| "grad_norm": 1.8608784675598145, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 0.2181, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.009883275112890859, | |
| "grad_norm": 1.6123907566070557, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 0.22, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.010224077702990542, | |
| "grad_norm": 2.038633108139038, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.2058, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.010564880293090228, | |
| "grad_norm": 1.965456485748291, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 0.2149, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.010905682883189912, | |
| "grad_norm": 1.9101155996322632, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.2067, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.011246485473289597, | |
| "grad_norm": 2.366758108139038, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 0.277, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.011587288063389281, | |
| "grad_norm": 2.540001153945923, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 0.3023, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.011928090653488967, | |
| "grad_norm": 1.989625334739685, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.2354, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01226889324358865, | |
| "grad_norm": 2.133960008621216, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 0.2815, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.012609695833688336, | |
| "grad_norm": 2.339320421218872, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 0.3322, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.012950498423788022, | |
| "grad_norm": 3.1012182235717773, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 0.394, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.013291301013887705, | |
| "grad_norm": 2.467550754547119, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 0.3025, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.013632103603987391, | |
| "grad_norm": 2.47534441947937, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 0.3145, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.013972906194087075, | |
| "grad_norm": 3.20918345451355, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.3623, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.01431370878418676, | |
| "grad_norm": 2.7930960655212402, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 0.3627, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.014654511374286444, | |
| "grad_norm": 3.190483570098877, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 0.3991, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.01499531396438613, | |
| "grad_norm": 3.2513771057128906, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 0.4175, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.015336116554485813, | |
| "grad_norm": 3.442272186279297, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.4102, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.015676919144585497, | |
| "grad_norm": 3.618436574935913, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 0.4876, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.016017721734685183, | |
| "grad_norm": 3.7486698627471924, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 0.4574, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.01635852432478487, | |
| "grad_norm": 3.1714091300964355, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 0.4395, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.016699326914884554, | |
| "grad_norm": 4.866738796234131, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 0.6403, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.01704012950498424, | |
| "grad_norm": 4.497549533843994, | |
| "learning_rate": 0.0, | |
| "loss": 0.6302, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01704012950498424, | |
| "eval_loss": 0.24603328108787537, | |
| "eval_runtime": 43.0787, | |
| "eval_samples_per_second": 114.72, | |
| "eval_steps_per_second": 14.346, | |
| "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": 1932120607948800.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |