| { | |
| "best_metric": 0.6597008109092712, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.019807863721897592, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00039615727443795186, | |
| "grad_norm": 15.38939380645752, | |
| "learning_rate": 2e-05, | |
| "loss": 2.6599, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00039615727443795186, | |
| "eval_loss": 1.200274109840393, | |
| "eval_runtime": 154.9972, | |
| "eval_samples_per_second": 27.433, | |
| "eval_steps_per_second": 3.432, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007923145488759037, | |
| "grad_norm": 16.734960556030273, | |
| "learning_rate": 4e-05, | |
| "loss": 3.396, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0011884718233138556, | |
| "grad_norm": 15.702166557312012, | |
| "learning_rate": 6e-05, | |
| "loss": 2.8498, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0015846290977518075, | |
| "grad_norm": 13.420672416687012, | |
| "learning_rate": 8e-05, | |
| "loss": 2.7706, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0019807863721897595, | |
| "grad_norm": 9.73044490814209, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5057, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0023769436466277113, | |
| "grad_norm": 11.664520263671875, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 2.7975, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002773100921065663, | |
| "grad_norm": 8.877344131469727, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 2.5462, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003169258195503615, | |
| "grad_norm": 9.045130729675293, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 2.6158, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0035654154699415667, | |
| "grad_norm": 9.858509063720703, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 2.8669, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003961572744379519, | |
| "grad_norm": 8.872286796569824, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 2.516, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004357730018817471, | |
| "grad_norm": 9.686171531677246, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 2.5248, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.004753887293255423, | |
| "grad_norm": 10.663348197937012, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 3.0213, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.005150044567693374, | |
| "grad_norm": 9.221182823181152, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 2.4556, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005546201842131326, | |
| "grad_norm": 9.011594772338867, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 2.2169, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.005942359116569278, | |
| "grad_norm": 9.134177207946777, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 2.6884, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00633851639100723, | |
| "grad_norm": 8.743730545043945, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 2.4097, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.006734673665445182, | |
| "grad_norm": 9.52989673614502, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 2.7904, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0071308309398831335, | |
| "grad_norm": 9.70661735534668, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 2.4424, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.007526988214321085, | |
| "grad_norm": 10.09250259399414, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 2.436, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.007923145488759038, | |
| "grad_norm": 8.261049270629883, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.318, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008319302763196989, | |
| "grad_norm": 9.031270027160645, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 2.4178, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.008715460037634942, | |
| "grad_norm": 12.21824836730957, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 2.7133, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.009111617312072893, | |
| "grad_norm": 10.730268478393555, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 2.6344, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.009507774586510845, | |
| "grad_norm": 9.152085304260254, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 2.3463, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.009903931860948796, | |
| "grad_norm": 9.404061317443848, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 2.3261, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.009903931860948796, | |
| "eval_loss": 0.6671332120895386, | |
| "eval_runtime": 156.6633, | |
| "eval_samples_per_second": 27.141, | |
| "eval_steps_per_second": 3.396, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.010300089135386749, | |
| "grad_norm": 12.529690742492676, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 2.8625, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0106962464098247, | |
| "grad_norm": 10.027824401855469, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 2.5588, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.011092403684262652, | |
| "grad_norm": 10.082047462463379, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 2.4771, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.011488560958700603, | |
| "grad_norm": 11.15814208984375, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 2.4113, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.011884718233138556, | |
| "grad_norm": 10.759804725646973, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 2.8421, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.012280875507576509, | |
| "grad_norm": 10.599135398864746, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 2.6885, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.01267703278201446, | |
| "grad_norm": 11.816875457763672, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 3.0024, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.013073190056452412, | |
| "grad_norm": 10.234508514404297, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 2.0345, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.013469347330890363, | |
| "grad_norm": 12.437875747680664, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 2.7898, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.013865504605328316, | |
| "grad_norm": 10.455293655395508, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.2859, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.014261661879766267, | |
| "grad_norm": 10.511425971984863, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 2.2994, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.01465781915420422, | |
| "grad_norm": 11.496809959411621, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 2.7418, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.01505397642864217, | |
| "grad_norm": 13.628725051879883, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 3.0457, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.015450133703080123, | |
| "grad_norm": 13.12936782836914, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 2.5216, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.015846290977518076, | |
| "grad_norm": 10.766741752624512, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 2.3881, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.016242448251956025, | |
| "grad_norm": 15.045173645019531, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 3.1368, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.016638605526393978, | |
| "grad_norm": 10.670278549194336, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 2.4484, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.01703476280083193, | |
| "grad_norm": 14.797165870666504, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 3.4172, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.017430920075269883, | |
| "grad_norm": 12.900824546813965, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 2.7403, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.017827077349707832, | |
| "grad_norm": 12.451089859008789, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 3.1842, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.018223234624145785, | |
| "grad_norm": 14.523232460021973, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 3.4595, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.018619391898583738, | |
| "grad_norm": 12.919535636901855, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 3.0023, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.01901554917302169, | |
| "grad_norm": 13.515146255493164, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 2.8616, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.019411706447459643, | |
| "grad_norm": 13.035895347595215, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 2.3172, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.019807863721897592, | |
| "grad_norm": 19.37661361694336, | |
| "learning_rate": 0.0, | |
| "loss": 3.5126, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.019807863721897592, | |
| "eval_loss": 0.6597008109092712, | |
| "eval_runtime": 156.6523, | |
| "eval_samples_per_second": 27.143, | |
| "eval_steps_per_second": 3.396, | |
| "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": 3.5953824975814656e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |