| { | |
| "best_metric": 1.4880585670471191, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.020766275568476794, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004153255113695359, | |
| "grad_norm": 3.7503223419189453, | |
| "learning_rate": 0.0001, | |
| "loss": 4.3267, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004153255113695359, | |
| "eval_loss": 3.2507529258728027, | |
| "eval_runtime": 315.7811, | |
| "eval_samples_per_second": 3.211, | |
| "eval_steps_per_second": 1.606, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008306510227390718, | |
| "grad_norm": 4.684205532073975, | |
| "learning_rate": 0.0002, | |
| "loss": 3.5536, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0012459765341086076, | |
| "grad_norm": 4.447961330413818, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 3.4523, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0016613020454781435, | |
| "grad_norm": 3.805811643600464, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 1.9321, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0020766275568476792, | |
| "grad_norm": 1.8339935541152954, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 1.0197, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002491953068217215, | |
| "grad_norm": 0.6933320760726929, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 0.7521, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002907278579586751, | |
| "grad_norm": 0.6948239207267761, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 0.6892, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003322604090956287, | |
| "grad_norm": 0.6498672366142273, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 0.6822, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003737929602325823, | |
| "grad_norm": 0.6903563737869263, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 0.6204, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0041532551136953585, | |
| "grad_norm": 0.7025269865989685, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 0.6187, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004568580625064895, | |
| "grad_norm": 0.6186163425445557, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 0.557, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00498390613643443, | |
| "grad_norm": 0.5350794792175293, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 0.5196, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.005399231647803967, | |
| "grad_norm": 0.4320513904094696, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 0.5012, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005814557159173502, | |
| "grad_norm": 0.4194105863571167, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.5322, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.006229882670543038, | |
| "grad_norm": 0.3983699679374695, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 0.5075, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006645208181912574, | |
| "grad_norm": 0.32669129967689514, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 0.446, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00706053369328211, | |
| "grad_norm": 0.2875390648841858, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 0.4035, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.007475859204651646, | |
| "grad_norm": 0.28854599595069885, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.4666, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.007891184716021182, | |
| "grad_norm": 0.26025399565696716, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 0.3959, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.008306510227390717, | |
| "grad_norm": 0.23188425600528717, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 0.4652, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008721835738760253, | |
| "grad_norm": 0.24908408522605896, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 0.4689, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00913716125012979, | |
| "grad_norm": 0.2741258144378662, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 0.4658, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.009552486761499324, | |
| "grad_norm": 0.25350722670555115, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 0.3976, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.00996781227286886, | |
| "grad_norm": 0.28189408779144287, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 0.5051, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.010383137784238397, | |
| "grad_norm": 0.22139275074005127, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 0.3642, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.010383137784238397, | |
| "eval_loss": 1.629266619682312, | |
| "eval_runtime": 316.8732, | |
| "eval_samples_per_second": 3.2, | |
| "eval_steps_per_second": 1.6, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.010798463295607933, | |
| "grad_norm": 0.24868632853031158, | |
| "learning_rate": 0.0001, | |
| "loss": 0.4748, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.011213788806977468, | |
| "grad_norm": 0.5774146914482117, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 1.7875, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.011629114318347004, | |
| "grad_norm": 0.7732341885566711, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 2.6975, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.01204443982971654, | |
| "grad_norm": 0.7076338529586792, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 2.7049, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.012459765341086075, | |
| "grad_norm": 0.7225150465965271, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 2.9696, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.012875090852455612, | |
| "grad_norm": 0.6315404772758484, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 2.7684, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.013290416363825148, | |
| "grad_norm": 0.6427789926528931, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 2.7576, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.013705741875194685, | |
| "grad_norm": 0.6234633922576904, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 2.7386, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.01412106738656422, | |
| "grad_norm": 0.6091985702514648, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 2.8351, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.014536392897933756, | |
| "grad_norm": 0.5979273915290833, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 2.7006, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.014951718409303292, | |
| "grad_norm": 0.5986985564231873, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 2.8208, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.015367043920672827, | |
| "grad_norm": 0.6158512234687805, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 2.4706, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.015782369432042365, | |
| "grad_norm": 0.6060137152671814, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 2.5508, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0161976949434119, | |
| "grad_norm": 0.6137194633483887, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 2.5507, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.016613020454781434, | |
| "grad_norm": 0.6484068632125854, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 2.5866, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.017028345966150972, | |
| "grad_norm": 0.6532328128814697, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 2.9501, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.017443671477520507, | |
| "grad_norm": 0.6872005462646484, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 2.8211, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.01785899698889004, | |
| "grad_norm": 0.7130753993988037, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 2.7857, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.01827432250025958, | |
| "grad_norm": 0.6461330652236938, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 2.6955, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.018689648011629114, | |
| "grad_norm": 0.6232130527496338, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 2.5653, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01910497352299865, | |
| "grad_norm": 0.7634522318840027, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 2.9665, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.019520299034368187, | |
| "grad_norm": 0.6845643520355225, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 3.0372, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.01993562454573772, | |
| "grad_norm": 0.633053183555603, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 2.7007, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.02035095005710726, | |
| "grad_norm": 0.7356605529785156, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 3.2683, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.020766275568476794, | |
| "grad_norm": 0.7480798363685608, | |
| "learning_rate": 0.0, | |
| "loss": 3.1527, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.020766275568476794, | |
| "eval_loss": 1.4880585670471191, | |
| "eval_runtime": 316.8721, | |
| "eval_samples_per_second": 3.2, | |
| "eval_steps_per_second": 1.6, | |
| "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": 6.99038693326848e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |