| { | |
| "best_metric": 0.6681258082389832, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.10303967027305512, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0020607934054611026, | |
| "grad_norm": 29.148273468017578, | |
| "learning_rate": 0.0001, | |
| "loss": 6.3214, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0020607934054611026, | |
| "eval_loss": 9.2053804397583, | |
| "eval_runtime": 15.2432, | |
| "eval_samples_per_second": 13.449, | |
| "eval_steps_per_second": 6.757, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004121586810922205, | |
| "grad_norm": 36.22698974609375, | |
| "learning_rate": 0.0002, | |
| "loss": 6.6115, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0061823802163833074, | |
| "grad_norm": 23.70931625366211, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 5.1783, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00824317362184441, | |
| "grad_norm": 20.946331024169922, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 3.7375, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.010303967027305513, | |
| "grad_norm": 12.989495277404785, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 2.4732, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.012364760432766615, | |
| "grad_norm": 16.429964065551758, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 2.2351, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.014425553838227717, | |
| "grad_norm": 13.84890079498291, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 0.9687, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01648634724368882, | |
| "grad_norm": 34.05931091308594, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 0.6392, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01854714064914992, | |
| "grad_norm": 29.02243995666504, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 1.246, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.020607934054611025, | |
| "grad_norm": 15.838531494140625, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 0.8761, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02266872746007213, | |
| "grad_norm": 14.478208541870117, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 1.159, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02472952086553323, | |
| "grad_norm": 10.877490997314453, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 0.6689, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.026790314270994334, | |
| "grad_norm": 10.949230194091797, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 0.3131, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.028851107676455434, | |
| "grad_norm": 7.338247776031494, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.3484, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.030911901081916538, | |
| "grad_norm": 11.679816246032715, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 0.4747, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03297269448737764, | |
| "grad_norm": 7.882423400878906, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 0.3737, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03503348789283874, | |
| "grad_norm": 13.34092903137207, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 0.4526, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03709428129829984, | |
| "grad_norm": 9.12542724609375, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.4328, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03915507470376095, | |
| "grad_norm": 9.532864570617676, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 0.4319, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04121586810922205, | |
| "grad_norm": 4.404548645019531, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 0.2462, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04327666151468315, | |
| "grad_norm": 3.681804895401001, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 0.2135, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04533745492014426, | |
| "grad_norm": 4.448928356170654, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 0.2531, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.04739824832560536, | |
| "grad_norm": 13.782437324523926, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 0.4945, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.04945904173106646, | |
| "grad_norm": 35.12315368652344, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 0.9411, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05151983513652756, | |
| "grad_norm": 62.50826644897461, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 0.823, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05151983513652756, | |
| "eval_loss": 0.6681258082389832, | |
| "eval_runtime": 14.8471, | |
| "eval_samples_per_second": 13.807, | |
| "eval_steps_per_second": 6.937, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05358062854198867, | |
| "grad_norm": 15.42173957824707, | |
| "learning_rate": 0.0001, | |
| "loss": 0.4441, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.05564142194744977, | |
| "grad_norm": 1.8112399578094482, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 0.0552, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.05770221535291087, | |
| "grad_norm": 0.7334427833557129, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 0.0083, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.059763008758371976, | |
| "grad_norm": 9.213266372680664, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 0.2998, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.061823802163833076, | |
| "grad_norm": 3.4060914516448975, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 0.0579, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06388459556929418, | |
| "grad_norm": 0.07256096601486206, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 0.001, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.06594538897475528, | |
| "grad_norm": 0.05080750212073326, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 0.0008, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.06800618238021638, | |
| "grad_norm": 4.680781841278076, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 0.0752, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.07006697578567748, | |
| "grad_norm": 1.9387208223342896, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.0059, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.07212776919113859, | |
| "grad_norm": 0.2535548806190491, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 0.002, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.07418856259659969, | |
| "grad_norm": 0.1797764152288437, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 0.0015, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0762493560020608, | |
| "grad_norm": 0.1363029181957245, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 0.0014, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0783101494075219, | |
| "grad_norm": 0.08102747797966003, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.0009, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.080370942812983, | |
| "grad_norm": 0.08120626956224442, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 0.0009, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0824317362184441, | |
| "grad_norm": 0.06320202350616455, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 0.0007, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0844925296239052, | |
| "grad_norm": 0.06635958701372147, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 0.0007, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0865533230293663, | |
| "grad_norm": 0.04807131737470627, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 0.0006, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0886141164348274, | |
| "grad_norm": 0.06771901249885559, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 0.0007, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.09067490984028852, | |
| "grad_norm": 0.046476930379867554, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 0.0005, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.09273570324574962, | |
| "grad_norm": 13.438279151916504, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 0.0353, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.09479649665121072, | |
| "grad_norm": 20.22861099243164, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 0.05, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.09685729005667182, | |
| "grad_norm": 26.98645782470703, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 0.0715, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.09891808346213292, | |
| "grad_norm": 26.829103469848633, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 0.0614, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.10097887686759402, | |
| "grad_norm": 35.39474868774414, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 0.0936, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.10303967027305512, | |
| "grad_norm": 19.681806564331055, | |
| "learning_rate": 0.0, | |
| "loss": 0.041, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.10303967027305512, | |
| "eval_loss": 1.1938879489898682, | |
| "eval_runtime": 14.8623, | |
| "eval_samples_per_second": 13.793, | |
| "eval_steps_per_second": 6.93, | |
| "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": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3604771504128000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |