| { | |
| "best_metric": 0.4442506432533264, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.0034616449736914984, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.923289947382996e-05, | |
| "grad_norm": 25.03363609313965, | |
| "learning_rate": 0.0001, | |
| "loss": 25.4085, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.923289947382996e-05, | |
| "eval_loss": 6.303963661193848, | |
| "eval_runtime": 1556.9289, | |
| "eval_samples_per_second": 3.906, | |
| "eval_steps_per_second": 1.953, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00013846579894765993, | |
| "grad_norm": 18.28585433959961, | |
| "learning_rate": 0.0002, | |
| "loss": 26.7283, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0002076986984214899, | |
| "grad_norm": 16.703285217285156, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 25.6386, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00027693159789531985, | |
| "grad_norm": 19.086830139160156, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 24.214, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0003461644973691498, | |
| "grad_norm": 18.092313766479492, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 20.912, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0004153973968429798, | |
| "grad_norm": 18.3270263671875, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 16.8218, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00048463029631680974, | |
| "grad_norm": 22.461029052734375, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 12.7794, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0005538631957906397, | |
| "grad_norm": 21.475221633911133, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 15.4015, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006230960952644697, | |
| "grad_norm": 31.454824447631836, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 9.4117, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0006923289947382996, | |
| "grad_norm": 30.230730056762695, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 12.9475, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007615618942121296, | |
| "grad_norm": 20.24393081665039, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 9.7422, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0008307947936859596, | |
| "grad_norm": 23.50675392150879, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 7.8627, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0009000276931597895, | |
| "grad_norm": 13.773619651794434, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 7.036, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0009692605926336195, | |
| "grad_norm": 12.892599105834961, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 5.7729, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0010384934921074495, | |
| "grad_norm": 16.389083862304688, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 5.1589, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0011077263915812794, | |
| "grad_norm": 20.99011993408203, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 7.2829, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0011769592910551095, | |
| "grad_norm": 14.472877502441406, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 3.5348, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0012461921905289393, | |
| "grad_norm": 13.577648162841797, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 2.7133, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0013154250900027694, | |
| "grad_norm": 14.178506851196289, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 4.3797, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0013846579894765993, | |
| "grad_norm": 13.145532608032227, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 3.0471, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0014538908889504293, | |
| "grad_norm": 19.747013092041016, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 3.4614, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0015231237884242592, | |
| "grad_norm": 18.29702377319336, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 3.4528, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0015923566878980893, | |
| "grad_norm": 30.16427230834961, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 2.1102, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.001661589587371919, | |
| "grad_norm": 10.87189769744873, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 2.1856, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0017308224868457492, | |
| "grad_norm": 12.407576560974121, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 2.0214, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0017308224868457492, | |
| "eval_loss": 0.5757687091827393, | |
| "eval_runtime": 1566.7781, | |
| "eval_samples_per_second": 3.882, | |
| "eval_steps_per_second": 1.941, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.001800055386319579, | |
| "grad_norm": 9.80317211151123, | |
| "learning_rate": 0.0001, | |
| "loss": 1.7549, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.001869288285793409, | |
| "grad_norm": 15.72749137878418, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 2.2773, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.001938521185267239, | |
| "grad_norm": 15.096418380737305, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 1.8499, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.002007754084741069, | |
| "grad_norm": 24.820247650146484, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 2.855, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.002076986984214899, | |
| "grad_norm": 14.719782829284668, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 2.5231, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002146219883688729, | |
| "grad_norm": 9.150571823120117, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 1.8756, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.002215452783162559, | |
| "grad_norm": 14.688347816467285, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 1.7645, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0022846856826363887, | |
| "grad_norm": 18.42392349243164, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 2.1888, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.002353918582110219, | |
| "grad_norm": 12.466184616088867, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 2.137, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.002423151481584049, | |
| "grad_norm": 11.869159698486328, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 1.9136, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0024923843810578787, | |
| "grad_norm": 10.24367618560791, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 1.6125, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0025616172805317085, | |
| "grad_norm": 10.600191116333008, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 2.1622, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.002630850180005539, | |
| "grad_norm": 9.307639122009277, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 1.8964, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0027000830794793687, | |
| "grad_norm": 7.141270637512207, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 1.8054, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0027693159789531985, | |
| "grad_norm": 12.76805305480957, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 1.6684, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0028385488784270284, | |
| "grad_norm": 20.816078186035156, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 2.1496, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0029077817779008587, | |
| "grad_norm": 6.196358680725098, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 1.3874, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0029770146773746885, | |
| "grad_norm": 10.963146209716797, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 1.638, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0030462475768485184, | |
| "grad_norm": 9.570157051086426, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 1.4989, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.003115480476322348, | |
| "grad_norm": 12.58957290649414, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 2.2585, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0031847133757961785, | |
| "grad_norm": 7.2112932205200195, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 1.3987, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0032539462752700084, | |
| "grad_norm": 14.840339660644531, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 1.99, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.003323179174743838, | |
| "grad_norm": 10.862496376037598, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 1.4887, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.003392412074217668, | |
| "grad_norm": 20.067378997802734, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 2.5822, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0034616449736914984, | |
| "grad_norm": 15.832198143005371, | |
| "learning_rate": 0.0, | |
| "loss": 2.7017, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0034616449736914984, | |
| "eval_loss": 0.4442506432533264, | |
| "eval_runtime": 1568.662, | |
| "eval_samples_per_second": 3.877, | |
| "eval_steps_per_second": 1.939, | |
| "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": 1, | |
| "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": 6.53458201903104e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |