| { | |
| "best_metric": 0.6011509895324707, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.008699812954021488, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00017399625908042976, | |
| "grad_norm": 0.3976498544216156, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5969, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00017399625908042976, | |
| "eval_loss": 0.8338358402252197, | |
| "eval_runtime": 189.313, | |
| "eval_samples_per_second": 51.132, | |
| "eval_steps_per_second": 6.392, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00034799251816085953, | |
| "grad_norm": 0.48601222038269043, | |
| "learning_rate": 4e-05, | |
| "loss": 0.6603, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005219887772412893, | |
| "grad_norm": 0.5396395325660706, | |
| "learning_rate": 6e-05, | |
| "loss": 0.7033, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006959850363217191, | |
| "grad_norm": 0.3960111737251282, | |
| "learning_rate": 8e-05, | |
| "loss": 0.7342, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008699812954021488, | |
| "grad_norm": 0.31853243708610535, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6619, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0010439775544825785, | |
| "grad_norm": 0.3379541337490082, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.7001, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0012179738135630084, | |
| "grad_norm": 0.3909156024456024, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 0.6644, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0013919700726434381, | |
| "grad_norm": 0.38534092903137207, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.6815, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.001565966331723868, | |
| "grad_norm": 0.375773161649704, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.6851, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0017399625908042977, | |
| "grad_norm": 0.29953908920288086, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.597, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0019139588498847274, | |
| "grad_norm": 0.29431456327438354, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.617, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.002087955108965157, | |
| "grad_norm": 0.2907293438911438, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.6329, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002261951368045587, | |
| "grad_norm": 0.2917402982711792, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 0.628, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.002435947627126017, | |
| "grad_norm": 0.27866703271865845, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.6297, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0026099438862064468, | |
| "grad_norm": 0.2853500545024872, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.6677, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0027839401452868762, | |
| "grad_norm": 0.28103628754615784, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 0.6232, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.002957936404367306, | |
| "grad_norm": 0.2904147803783417, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 0.6318, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.003131932663447736, | |
| "grad_norm": 0.3015044629573822, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 0.6611, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0033059289225281655, | |
| "grad_norm": 0.2805950939655304, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 0.5837, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0034799251816085954, | |
| "grad_norm": 0.2991722822189331, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.6502, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0036539214406890253, | |
| "grad_norm": 0.29726454615592957, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 0.6497, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0038279176997694547, | |
| "grad_norm": 0.29053497314453125, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 0.5781, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.004001913958849885, | |
| "grad_norm": 0.32980453968048096, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.6125, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.004175910217930314, | |
| "grad_norm": 0.2995961606502533, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 0.6327, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004349906477010744, | |
| "grad_norm": 0.30183839797973633, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.6477, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004349906477010744, | |
| "eval_loss": 0.6230759024620056, | |
| "eval_runtime": 190.2274, | |
| "eval_samples_per_second": 50.886, | |
| "eval_steps_per_second": 6.361, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004523902736091174, | |
| "grad_norm": 0.31274470686912537, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 0.6096, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.004697898995171604, | |
| "grad_norm": 0.32117345929145813, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 0.6286, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.004871895254252034, | |
| "grad_norm": 0.32933807373046875, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 0.5944, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.005045891513332464, | |
| "grad_norm": 0.351071298122406, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 0.5933, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0052198877724128935, | |
| "grad_norm": 0.31884631514549255, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.6248, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0053938840314933225, | |
| "grad_norm": 0.34024742245674133, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 0.6292, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0055678802905737524, | |
| "grad_norm": 0.3358078896999359, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.6344, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.005741876549654182, | |
| "grad_norm": 0.31253138184547424, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 0.5386, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.005915872808734612, | |
| "grad_norm": 0.3540220856666565, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 0.6591, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.006089869067815042, | |
| "grad_norm": 0.3631910979747772, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.6059, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.006263865326895472, | |
| "grad_norm": 0.355940580368042, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 0.6156, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.006437861585975902, | |
| "grad_norm": 0.427781879901886, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 0.7358, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.006611857845056331, | |
| "grad_norm": 0.3944018483161926, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 0.6576, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.006785854104136761, | |
| "grad_norm": 0.38060876727104187, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 0.5713, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.006959850363217191, | |
| "grad_norm": 0.427198201417923, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 0.6833, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.007133846622297621, | |
| "grad_norm": 0.4212252199649811, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.6029, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0073078428813780506, | |
| "grad_norm": 0.45848748087882996, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 0.6784, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0074818391404584805, | |
| "grad_norm": 0.4559570848941803, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 0.6133, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0076558353995389095, | |
| "grad_norm": 0.4943748712539673, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 0.5837, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.00782983165861934, | |
| "grad_norm": 0.5308108925819397, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.6114, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.00800382791769977, | |
| "grad_norm": 0.5437849760055542, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 0.5849, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0081778241767802, | |
| "grad_norm": 0.5877715349197388, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 0.6909, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.008351820435860628, | |
| "grad_norm": 0.5954829454421997, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 0.634, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.008525816694941058, | |
| "grad_norm": 0.6944670081138611, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 0.6864, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.008699812954021488, | |
| "grad_norm": 1.0665466785430908, | |
| "learning_rate": 0.0, | |
| "loss": 0.7594, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008699812954021488, | |
| "eval_loss": 0.6011509895324707, | |
| "eval_runtime": 190.2616, | |
| "eval_samples_per_second": 50.877, | |
| "eval_steps_per_second": 6.36, | |
| "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": 9218902751969280.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |