{ "best_metric": 0.6621928215026855, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.03842459173871278, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0007684918347742555, "grad_norm": 1.1188583374023438, "learning_rate": 0.0001, "loss": 1.0891, "step": 1 }, { "epoch": 0.0007684918347742555, "eval_loss": 3.402336597442627, "eval_runtime": 191.6418, "eval_samples_per_second": 2.86, "eval_steps_per_second": 1.43, "step": 1 }, { "epoch": 0.001536983669548511, "grad_norm": 1.6677217483520508, "learning_rate": 0.0002, "loss": 1.4543, "step": 2 }, { "epoch": 0.0023054755043227667, "grad_norm": 1.7429873943328857, "learning_rate": 0.00019978589232386035, "loss": 1.5349, "step": 3 }, { "epoch": 0.003073967339097022, "grad_norm": 1.5597237348556519, "learning_rate": 0.00019914448613738106, "loss": 1.2103, "step": 4 }, { "epoch": 0.0038424591738712775, "grad_norm": 2.7055306434631348, "learning_rate": 0.00019807852804032305, "loss": 1.072, "step": 5 }, { "epoch": 0.004610951008645533, "grad_norm": 2.731037139892578, "learning_rate": 0.00019659258262890683, "loss": 1.0839, "step": 6 }, { "epoch": 0.005379442843419789, "grad_norm": 1.686295986175537, "learning_rate": 0.0001946930129495106, "loss": 0.8141, "step": 7 }, { "epoch": 0.006147934678194044, "grad_norm": 1.4061486721038818, "learning_rate": 0.0001923879532511287, "loss": 0.6588, "step": 8 }, { "epoch": 0.0069164265129683, "grad_norm": 1.53168523311615, "learning_rate": 0.00018968727415326884, "loss": 0.73, "step": 9 }, { "epoch": 0.007684918347742555, "grad_norm": 1.0826469659805298, "learning_rate": 0.00018660254037844388, "loss": 0.5536, "step": 10 }, { "epoch": 0.00845341018251681, "grad_norm": 1.28086256980896, "learning_rate": 0.00018314696123025454, "loss": 0.5734, "step": 11 }, { "epoch": 0.009221902017291067, "grad_norm": 1.5090341567993164, "learning_rate": 0.00017933533402912354, "loss": 0.4795, "step": 12 }, { "epoch": 0.009990393852065321, "grad_norm": 1.4438533782958984, "learning_rate": 0.00017518398074789775, "loss": 0.5919, "step": 13 }, { "epoch": 0.010758885686839578, "grad_norm": 1.4994761943817139, "learning_rate": 0.00017071067811865476, "loss": 0.4987, "step": 14 }, { "epoch": 0.011527377521613832, "grad_norm": 1.3660697937011719, "learning_rate": 0.00016593458151000688, "loss": 0.6833, "step": 15 }, { "epoch": 0.012295869356388088, "grad_norm": 1.2865175008773804, "learning_rate": 0.00016087614290087208, "loss": 0.6312, "step": 16 }, { "epoch": 0.013064361191162345, "grad_norm": 1.6526931524276733, "learning_rate": 0.00015555702330196023, "loss": 0.5865, "step": 17 }, { "epoch": 0.0138328530259366, "grad_norm": 1.6482139825820923, "learning_rate": 0.00015000000000000001, "loss": 0.6131, "step": 18 }, { "epoch": 0.014601344860710855, "grad_norm": 1.7616355419158936, "learning_rate": 0.00014422886902190014, "loss": 0.6195, "step": 19 }, { "epoch": 0.01536983669548511, "grad_norm": 1.3635176420211792, "learning_rate": 0.000138268343236509, "loss": 0.5372, "step": 20 }, { "epoch": 0.016138328530259365, "grad_norm": 1.7781474590301514, "learning_rate": 0.00013214394653031616, "loss": 0.8488, "step": 21 }, { "epoch": 0.01690682036503362, "grad_norm": 1.7835301160812378, "learning_rate": 0.00012588190451025207, "loss": 0.6644, "step": 22 }, { "epoch": 0.017675312199807877, "grad_norm": 1.841204047203064, "learning_rate": 0.00011950903220161285, "loss": 0.6199, "step": 23 }, { "epoch": 0.018443804034582133, "grad_norm": 2.19480562210083, "learning_rate": 0.00011305261922200519, "loss": 0.8213, "step": 24 }, { "epoch": 0.01921229586935639, "grad_norm": 3.188343048095703, "learning_rate": 0.00010654031292301432, "loss": 0.5297, "step": 25 }, { "epoch": 0.01921229586935639, "eval_loss": 0.6813758015632629, "eval_runtime": 193.0897, "eval_samples_per_second": 2.838, "eval_steps_per_second": 1.419, "step": 25 }, { "epoch": 0.019980787704130643, "grad_norm": 2.3865928649902344, "learning_rate": 0.0001, "loss": 0.5742, "step": 26 }, { "epoch": 0.0207492795389049, "grad_norm": 2.167008399963379, "learning_rate": 9.345968707698569e-05, "loss": 0.7711, "step": 27 }, { "epoch": 0.021517771373679155, "grad_norm": 2.8643157482147217, "learning_rate": 8.694738077799488e-05, "loss": 0.7881, "step": 28 }, { "epoch": 0.02228626320845341, "grad_norm": 2.675781011581421, "learning_rate": 8.049096779838719e-05, "loss": 0.8584, "step": 29 }, { "epoch": 0.023054755043227664, "grad_norm": 5.553785800933838, "learning_rate": 7.411809548974792e-05, "loss": 0.7431, "step": 30 }, { "epoch": 0.02382324687800192, "grad_norm": 2.85943341255188, "learning_rate": 6.785605346968386e-05, "loss": 0.8504, "step": 31 }, { "epoch": 0.024591738712776177, "grad_norm": 2.1145620346069336, "learning_rate": 6.173165676349103e-05, "loss": 0.4937, "step": 32 }, { "epoch": 0.025360230547550433, "grad_norm": 2.0370304584503174, "learning_rate": 5.577113097809989e-05, "loss": 0.8028, "step": 33 }, { "epoch": 0.02612872238232469, "grad_norm": 2.053551197052002, "learning_rate": 5.000000000000002e-05, "loss": 0.7418, "step": 34 }, { "epoch": 0.026897214217098942, "grad_norm": 1.7939903736114502, "learning_rate": 4.444297669803981e-05, "loss": 0.5822, "step": 35 }, { "epoch": 0.0276657060518732, "grad_norm": 2.718136787414551, "learning_rate": 3.9123857099127936e-05, "loss": 0.8955, "step": 36 }, { "epoch": 0.028434197886647455, "grad_norm": 2.0340025424957275, "learning_rate": 3.406541848999312e-05, "loss": 0.49, "step": 37 }, { "epoch": 0.02920268972142171, "grad_norm": 2.521495819091797, "learning_rate": 2.9289321881345254e-05, "loss": 0.7506, "step": 38 }, { "epoch": 0.029971181556195964, "grad_norm": 1.7781364917755127, "learning_rate": 2.4816019252102273e-05, "loss": 0.5979, "step": 39 }, { "epoch": 0.03073967339097022, "grad_norm": 2.1692018508911133, "learning_rate": 2.0664665970876496e-05, "loss": 0.654, "step": 40 }, { "epoch": 0.031508165225744476, "grad_norm": 3.2491769790649414, "learning_rate": 1.6853038769745467e-05, "loss": 0.8937, "step": 41 }, { "epoch": 0.03227665706051873, "grad_norm": 2.3188233375549316, "learning_rate": 1.339745962155613e-05, "loss": 0.7068, "step": 42 }, { "epoch": 0.03304514889529299, "grad_norm": 3.3548412322998047, "learning_rate": 1.0312725846731175e-05, "loss": 0.9072, "step": 43 }, { "epoch": 0.03381364073006724, "grad_norm": 3.1296138763427734, "learning_rate": 7.612046748871327e-06, "loss": 0.9079, "step": 44 }, { "epoch": 0.0345821325648415, "grad_norm": 2.4776840209960938, "learning_rate": 5.306987050489442e-06, "loss": 0.5561, "step": 45 }, { "epoch": 0.035350624399615754, "grad_norm": 3.5687758922576904, "learning_rate": 3.40741737109318e-06, "loss": 0.7228, "step": 46 }, { "epoch": 0.03611911623439001, "grad_norm": 5.37619686126709, "learning_rate": 1.921471959676957e-06, "loss": 0.8427, "step": 47 }, { "epoch": 0.03688760806916427, "grad_norm": 5.639602184295654, "learning_rate": 8.555138626189618e-07, "loss": 1.1088, "step": 48 }, { "epoch": 0.03765609990393852, "grad_norm": 3.618199110031128, "learning_rate": 2.141076761396521e-07, "loss": 0.8533, "step": 49 }, { "epoch": 0.03842459173871278, "grad_norm": 5.885342597961426, "learning_rate": 0.0, "loss": 0.5561, "step": 50 }, { "epoch": 0.03842459173871278, "eval_loss": 0.6621928215026855, "eval_runtime": 193.1089, "eval_samples_per_second": 2.838, "eval_steps_per_second": 1.419, "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": 7.41887283560448e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }