| { | |
| "best_metric": 0.9526658654212952, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.031007751937984496, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00062015503875969, | |
| "grad_norm": 14.920880317687988, | |
| "learning_rate": 0.0001, | |
| "loss": 7.1109, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00062015503875969, | |
| "eval_loss": 6.155733585357666, | |
| "eval_runtime": 49.6251, | |
| "eval_samples_per_second": 13.683, | |
| "eval_steps_per_second": 6.851, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00124031007751938, | |
| "grad_norm": 12.616119384765625, | |
| "learning_rate": 0.0002, | |
| "loss": 5.6612, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0018604651162790699, | |
| "grad_norm": 15.625079154968262, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 6.7293, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00248062015503876, | |
| "grad_norm": 13.348905563354492, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 4.7204, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0031007751937984496, | |
| "grad_norm": 9.438117980957031, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 3.0829, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0037209302325581397, | |
| "grad_norm": 17.93440055847168, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 3.057, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004341085271317829, | |
| "grad_norm": 11.800411224365234, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 1.9626, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00496124031007752, | |
| "grad_norm": 11.008665084838867, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 1.8794, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005581395348837209, | |
| "grad_norm": 15.072994232177734, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 1.6519, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006201550387596899, | |
| "grad_norm": 10.600494384765625, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 1.0895, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006821705426356589, | |
| "grad_norm": 17.598783493041992, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 1.3181, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0074418604651162795, | |
| "grad_norm": 11.936248779296875, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 1.3033, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00806201550387597, | |
| "grad_norm": 14.608379364013672, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 1.1154, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.008682170542635658, | |
| "grad_norm": 13.892497062683105, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.1172, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.009302325581395349, | |
| "grad_norm": 12.43130874633789, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 1.4043, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00992248062015504, | |
| "grad_norm": 8.64314079284668, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 0.639, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.010542635658914728, | |
| "grad_norm": 12.006380081176758, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 1.269, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.011162790697674419, | |
| "grad_norm": 15.379800796508789, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.0862, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.011782945736434108, | |
| "grad_norm": 10.780191421508789, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 0.6742, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.012403100775193798, | |
| "grad_norm": 8.979784965515137, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 0.5997, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.013023255813953489, | |
| "grad_norm": 7.553980827331543, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 0.2945, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.013643410852713178, | |
| "grad_norm": 9.615273475646973, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 0.6348, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.014263565891472868, | |
| "grad_norm": 8.001143455505371, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 0.2675, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.014883720930232559, | |
| "grad_norm": 14.149334907531738, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 1.1478, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.015503875968992248, | |
| "grad_norm": 7.33767032623291, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 0.6085, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.015503875968992248, | |
| "eval_loss": 1.0661097764968872, | |
| "eval_runtime": 49.2266, | |
| "eval_samples_per_second": 13.793, | |
| "eval_steps_per_second": 6.907, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01612403100775194, | |
| "grad_norm": 8.87413501739502, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3182, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.01674418604651163, | |
| "grad_norm": 42.767024993896484, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 1.2834, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.017364341085271316, | |
| "grad_norm": 19.86754608154297, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 0.8135, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.017984496124031007, | |
| "grad_norm": 12.222258567810059, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 1.0754, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.018604651162790697, | |
| "grad_norm": 8.531135559082031, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 0.4594, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.019224806201550388, | |
| "grad_norm": 9.130881309509277, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 0.4618, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.01984496124031008, | |
| "grad_norm": 12.017380714416504, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 1.0726, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.020465116279069766, | |
| "grad_norm": 8.987724304199219, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 0.4383, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.021085271317829456, | |
| "grad_norm": 14.123013496398926, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.7477, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.021705426356589147, | |
| "grad_norm": 7.6661529541015625, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 0.2971, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.022325581395348838, | |
| "grad_norm": 12.411150932312012, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 0.4651, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.022945736434108528, | |
| "grad_norm": 5.422929763793945, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 0.3783, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.023565891472868215, | |
| "grad_norm": 2.851478338241577, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.0853, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.024186046511627906, | |
| "grad_norm": 7.006505966186523, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 0.7307, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.024806201550387597, | |
| "grad_norm": 13.194289207458496, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 0.3757, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.025426356589147287, | |
| "grad_norm": 11.843560218811035, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 0.2397, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.026046511627906978, | |
| "grad_norm": 11.480189323425293, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 0.6359, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.02666666666666667, | |
| "grad_norm": 8.796479225158691, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 0.9612, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.027286821705426356, | |
| "grad_norm": 15.973198890686035, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 1.157, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.027906976744186046, | |
| "grad_norm": 13.505546569824219, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 2.8184, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.028527131782945737, | |
| "grad_norm": 14.637463569641113, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 1.9088, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.029147286821705427, | |
| "grad_norm": 21.357471466064453, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 2.7652, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.029767441860465118, | |
| "grad_norm": 18.96230125427246, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 3.2635, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.030387596899224805, | |
| "grad_norm": 15.090560913085938, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 3.2206, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.031007751937984496, | |
| "grad_norm": 21.638938903808594, | |
| "learning_rate": 0.0, | |
| "loss": 3.67, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.031007751937984496, | |
| "eval_loss": 0.9526658654212952, | |
| "eval_runtime": 49.2321, | |
| "eval_samples_per_second": 13.792, | |
| "eval_steps_per_second": 6.906, | |
| "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": 3604771504128000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |