| { | |
| "best_metric": 0.7463985085487366, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.03422899195618689, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006845798391237378, | |
| "grad_norm": 0.25282052159309387, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5592, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006845798391237378, | |
| "eval_loss": 0.9501175284385681, | |
| "eval_runtime": 173.9775, | |
| "eval_samples_per_second": 3.535, | |
| "eval_steps_per_second": 1.77, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013691596782474755, | |
| "grad_norm": 0.5238334536552429, | |
| "learning_rate": 0.0002, | |
| "loss": 0.663, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0020537395173712133, | |
| "grad_norm": 0.5488997101783752, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 0.583, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002738319356494951, | |
| "grad_norm": 0.38578325510025024, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 0.6462, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003422899195618689, | |
| "grad_norm": 0.5969985723495483, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 0.737, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004107479034742427, | |
| "grad_norm": 0.677198588848114, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 0.721, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004792058873866164, | |
| "grad_norm": 0.43101000785827637, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 0.8587, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005476638712989902, | |
| "grad_norm": 0.43668434023857117, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 0.6926, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00616121855211364, | |
| "grad_norm": 0.4872725307941437, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 0.6979, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006845798391237378, | |
| "grad_norm": 0.45551222562789917, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 0.5902, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0075303782303611155, | |
| "grad_norm": 0.5328372716903687, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 0.8881, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.008214958069484853, | |
| "grad_norm": 0.4792215824127197, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 0.7159, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.008899537908608592, | |
| "grad_norm": 0.5611771941184998, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 0.7192, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.009584117747732329, | |
| "grad_norm": 0.6743291020393372, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.7356, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.010268697586856067, | |
| "grad_norm": 0.6450310945510864, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 0.6947, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010953277425979804, | |
| "grad_norm": 0.6415031552314758, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 0.6267, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.011637857265103543, | |
| "grad_norm": 0.6395275592803955, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 0.7378, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01232243710422728, | |
| "grad_norm": 0.6193127632141113, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.7111, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.013007016943351019, | |
| "grad_norm": 0.6310256123542786, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 0.7352, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.013691596782474755, | |
| "grad_norm": 0.7274715304374695, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 0.7348, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.014376176621598494, | |
| "grad_norm": 0.6225596070289612, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 0.8002, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.015060756460722231, | |
| "grad_norm": 0.6990033388137817, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 0.7106, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01574533629984597, | |
| "grad_norm": 0.7687625288963318, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 0.7688, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.016429916138969707, | |
| "grad_norm": 0.8566373586654663, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 0.9884, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.017114495978093443, | |
| "grad_norm": 0.707819402217865, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 0.6778, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.017114495978093443, | |
| "eval_loss": 0.757265567779541, | |
| "eval_runtime": 175.3735, | |
| "eval_samples_per_second": 3.507, | |
| "eval_steps_per_second": 1.756, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.017799075817217184, | |
| "grad_norm": 0.7362199425697327, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7578, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.01848365565634092, | |
| "grad_norm": 0.7891442179679871, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 0.8214, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.019168235495464658, | |
| "grad_norm": 0.7279160022735596, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 0.6954, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.019852815334588398, | |
| "grad_norm": 0.7480013966560364, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 0.7565, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.020537395173712135, | |
| "grad_norm": 0.6995139122009277, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 0.7785, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.021221975012835872, | |
| "grad_norm": 0.7900039553642273, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 0.856, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.02190655485195961, | |
| "grad_norm": 0.775541365146637, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 0.8656, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.02259113469108335, | |
| "grad_norm": 0.7846947312355042, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 0.7725, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.023275714530207086, | |
| "grad_norm": 0.7840977311134338, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.6967, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.023960294369330823, | |
| "grad_norm": 0.7890691757202148, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 0.799, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.02464487420845456, | |
| "grad_norm": 0.9354871511459351, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 0.7397, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0253294540475783, | |
| "grad_norm": 0.8776700496673584, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 0.7285, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.026014033886702037, | |
| "grad_norm": 0.8412185311317444, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.6084, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.026698613725825774, | |
| "grad_norm": 0.9186910390853882, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 0.9773, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.02738319356494951, | |
| "grad_norm": 0.8276947736740112, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 0.8109, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02806777340407325, | |
| "grad_norm": 0.8860321044921875, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 0.7461, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.028752353243196988, | |
| "grad_norm": 0.9271875619888306, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 0.8198, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.029436933082320725, | |
| "grad_norm": 0.9980719089508057, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 0.715, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.030121512921444462, | |
| "grad_norm": 0.8296429514884949, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 0.7061, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.030806092760568202, | |
| "grad_norm": 0.9510181546211243, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 0.7851, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03149067259969194, | |
| "grad_norm": 1.0919767618179321, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 0.9219, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.03217525243881568, | |
| "grad_norm": 1.0661510229110718, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 0.6854, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.03285983227793941, | |
| "grad_norm": 1.2622677087783813, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 0.9412, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.03354441211706315, | |
| "grad_norm": 1.1761354207992554, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 0.616, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.03422899195618689, | |
| "grad_norm": 1.9178863763809204, | |
| "learning_rate": 0.0, | |
| "loss": 0.7909, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03422899195618689, | |
| "eval_loss": 0.7463985085487366, | |
| "eval_runtime": 175.2305, | |
| "eval_samples_per_second": 3.51, | |
| "eval_steps_per_second": 1.758, | |
| "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 | |
| } | |