| { | |
| "best_metric": 0.0006301512476056814, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.06756756756756757, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013513513513513514, | |
| "grad_norm": 0.44484832882881165, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2322, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013513513513513514, | |
| "eval_loss": 0.5629749894142151, | |
| "eval_runtime": 150.2208, | |
| "eval_samples_per_second": 33.184, | |
| "eval_steps_per_second": 4.154, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002702702702702703, | |
| "grad_norm": 0.5713135004043579, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2991, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004054054054054054, | |
| "grad_norm": 0.6531310081481934, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.2861, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005405405405405406, | |
| "grad_norm": 0.5933589935302734, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.19, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006756756756756757, | |
| "grad_norm": 0.6841403841972351, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.0957, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008108108108108109, | |
| "grad_norm": 0.38407307863235474, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.0356, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00945945945945946, | |
| "grad_norm": 0.11326621472835541, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.013, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010810810810810811, | |
| "grad_norm": 0.1718500405550003, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0093, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.012162162162162163, | |
| "grad_norm": 0.16105777025222778, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.0054, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013513513513513514, | |
| "grad_norm": 0.13872313499450684, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.0029, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014864864864864866, | |
| "grad_norm": 0.38686418533325195, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.0082, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.016216216216216217, | |
| "grad_norm": 0.15410937368869781, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.0043, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01756756756756757, | |
| "grad_norm": 0.244472935795784, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.0124, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01891891891891892, | |
| "grad_norm": 0.09916836023330688, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0034, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.02027027027027027, | |
| "grad_norm": 0.03881961852312088, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.0027, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.021621621621621623, | |
| "grad_norm": 0.02336873672902584, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.0009, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.022972972972972974, | |
| "grad_norm": 0.07001945376396179, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.0012, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.024324324324324326, | |
| "grad_norm": 0.029095953330397606, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0011, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.025675675675675677, | |
| "grad_norm": 0.023340551182627678, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.0005, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02702702702702703, | |
| "grad_norm": 0.03951576352119446, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.002, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02837837837837838, | |
| "grad_norm": 0.04075232520699501, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.0007, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02972972972972973, | |
| "grad_norm": 0.019823746755719185, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.0006, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.031081081081081083, | |
| "grad_norm": 0.03433848172426224, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0003, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.032432432432432434, | |
| "grad_norm": 0.052711162716150284, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.001, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.033783783783783786, | |
| "grad_norm": 0.07798641920089722, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.0026, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.033783783783783786, | |
| "eval_loss": 0.0010330178774893284, | |
| "eval_runtime": 150.9966, | |
| "eval_samples_per_second": 33.014, | |
| "eval_steps_per_second": 4.133, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03513513513513514, | |
| "grad_norm": 0.059504590928554535, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0017, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03648648648648649, | |
| "grad_norm": 0.051970165222883224, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.0005, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03783783783783784, | |
| "grad_norm": 0.041706208139657974, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.0006, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03918918918918919, | |
| "grad_norm": 0.025141162797808647, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.0005, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.04054054054054054, | |
| "grad_norm": 0.024181494489312172, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0004, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.041891891891891894, | |
| "grad_norm": 0.0042442684061825275, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.0002, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.043243243243243246, | |
| "grad_norm": 0.07526511698961258, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0009, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0445945945945946, | |
| "grad_norm": 0.007108128629624844, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.0002, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.04594594594594595, | |
| "grad_norm": 0.06577383726835251, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0006, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0472972972972973, | |
| "grad_norm": 0.006310014054179192, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0002, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04864864864864865, | |
| "grad_norm": 0.019449524581432343, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.0004, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.01652936451137066, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.0005, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.051351351351351354, | |
| "grad_norm": 0.0990108922123909, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0044, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.052702702702702706, | |
| "grad_norm": 0.06821031123399734, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.0011, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.05405405405405406, | |
| "grad_norm": 0.01180900540202856, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0004, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05540540540540541, | |
| "grad_norm": 0.03767711669206619, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0008, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.05675675675675676, | |
| "grad_norm": 0.015823999419808388, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0001, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.05810810810810811, | |
| "grad_norm": 0.13913719356060028, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.0006, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.05945945945945946, | |
| "grad_norm": 0.021133115515112877, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0003, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.060810810810810814, | |
| "grad_norm": 0.03227214142680168, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.0012, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.062162162162162166, | |
| "grad_norm": 0.00861811637878418, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0002, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.06351351351351352, | |
| "grad_norm": 0.00826831255108118, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0002, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.06486486486486487, | |
| "grad_norm": 0.03811093792319298, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0004, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06621621621621622, | |
| "grad_norm": 0.018121542409062386, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.0003, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06756756756756757, | |
| "grad_norm": 0.3153094947338104, | |
| "learning_rate": 0.0, | |
| "loss": 0.004, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06756756756756757, | |
| "eval_loss": 0.0006301512476056814, | |
| "eval_runtime": 150.859, | |
| "eval_samples_per_second": 33.044, | |
| "eval_steps_per_second": 4.136, | |
| "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": 5.969948642440643e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |