| { | |
| "best_metric": 6.652959823608398, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.17467248908296942, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0034934497816593887, | |
| "grad_norm": 1.2674891948699951, | |
| "learning_rate": 0.0001, | |
| "loss": 6.9803, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0034934497816593887, | |
| "eval_loss": 6.96870231628418, | |
| "eval_runtime": 0.5598, | |
| "eval_samples_per_second": 861.026, | |
| "eval_steps_per_second": 108.968, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0069868995633187774, | |
| "grad_norm": 1.167529821395874, | |
| "learning_rate": 0.0002, | |
| "loss": 6.9644, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.010480349344978166, | |
| "grad_norm": 1.328774094581604, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 6.9648, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013973799126637555, | |
| "grad_norm": 1.290858507156372, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 6.9454, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.017467248908296942, | |
| "grad_norm": 1.2717573642730713, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 6.9509, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02096069868995633, | |
| "grad_norm": 1.3567962646484375, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 6.9508, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02445414847161572, | |
| "grad_norm": 1.3295303583145142, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 6.9348, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02794759825327511, | |
| "grad_norm": 1.3175486326217651, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 6.9143, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0314410480349345, | |
| "grad_norm": 1.343460202217102, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 6.8924, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.034934497816593885, | |
| "grad_norm": 1.3586691617965698, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 6.9019, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03842794759825328, | |
| "grad_norm": 1.3719342947006226, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 6.8752, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04192139737991266, | |
| "grad_norm": 1.3882746696472168, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 6.8832, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.045414847161572056, | |
| "grad_norm": 1.5403207540512085, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 6.8564, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04890829694323144, | |
| "grad_norm": 1.565467357635498, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 6.8457, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.05240174672489083, | |
| "grad_norm": 1.5675280094146729, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 6.8248, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05589519650655022, | |
| "grad_norm": 1.7489842176437378, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 6.8316, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.059388646288209605, | |
| "grad_norm": 1.6354056596755981, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 6.8119, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.062882096069869, | |
| "grad_norm": 1.781294345855713, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 6.8308, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06637554585152838, | |
| "grad_norm": 1.7501847743988037, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 6.8053, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06986899563318777, | |
| "grad_norm": 1.4909464120864868, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 6.7851, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07336244541484715, | |
| "grad_norm": 1.9255237579345703, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 6.7947, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.07685589519650655, | |
| "grad_norm": 1.619134783744812, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 6.7653, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.08034934497816594, | |
| "grad_norm": 1.5726633071899414, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 6.7588, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.08384279475982533, | |
| "grad_norm": 1.5614157915115356, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 6.7465, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.08733624454148471, | |
| "grad_norm": 1.582399606704712, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 6.7322, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08733624454148471, | |
| "eval_loss": 6.726648807525635, | |
| "eval_runtime": 0.5422, | |
| "eval_samples_per_second": 888.912, | |
| "eval_steps_per_second": 112.497, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09082969432314411, | |
| "grad_norm": 1.812982201576233, | |
| "learning_rate": 0.0001, | |
| "loss": 6.7298, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0943231441048035, | |
| "grad_norm": 1.5379116535186768, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 6.7249, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.09781659388646288, | |
| "grad_norm": 1.741886019706726, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 6.7238, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.10131004366812227, | |
| "grad_norm": 1.7986143827438354, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 6.7093, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.10480349344978165, | |
| "grad_norm": 1.425921082496643, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 6.7057, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10829694323144105, | |
| "grad_norm": 1.772549033164978, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 6.6974, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.11179039301310044, | |
| "grad_norm": 1.5202797651290894, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 6.6887, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.11528384279475982, | |
| "grad_norm": 1.4495679140090942, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 6.7014, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.11877729257641921, | |
| "grad_norm": 1.540390968322754, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 6.6742, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.1222707423580786, | |
| "grad_norm": 1.3800748586654663, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 6.6797, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.125764192139738, | |
| "grad_norm": 1.4461179971694946, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 6.6783, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.12925764192139738, | |
| "grad_norm": 1.652401089668274, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 6.6752, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.13275109170305677, | |
| "grad_norm": 1.2902202606201172, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 6.6734, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.13624454148471615, | |
| "grad_norm": 1.6424710750579834, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 6.652, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.13973799126637554, | |
| "grad_norm": 1.5350518226623535, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 6.6633, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.14323144104803492, | |
| "grad_norm": 1.5188205242156982, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 6.6782, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.1467248908296943, | |
| "grad_norm": 1.3603993654251099, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 6.658, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.15021834061135372, | |
| "grad_norm": 1.5245517492294312, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 6.6588, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1537117903930131, | |
| "grad_norm": 1.564213514328003, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 6.6585, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1572052401746725, | |
| "grad_norm": 1.2466707229614258, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 6.6749, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.16069868995633188, | |
| "grad_norm": 1.3464109897613525, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 6.6599, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.16419213973799127, | |
| "grad_norm": 1.6725873947143555, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 6.647, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.16768558951965065, | |
| "grad_norm": 1.3510116338729858, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 6.6581, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.17117903930131004, | |
| "grad_norm": 1.3306465148925781, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 6.6537, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.17467248908296942, | |
| "grad_norm": 1.4314719438552856, | |
| "learning_rate": 0.0, | |
| "loss": 6.6494, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.17467248908296942, | |
| "eval_loss": 6.652959823608398, | |
| "eval_runtime": 0.5563, | |
| "eval_samples_per_second": 866.488, | |
| "eval_steps_per_second": 109.659, | |
| "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": 2357211955200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |