| { | |
| "best_metric": 1.574446678161621, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.013854013334487835, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002770802666897567, | |
| "grad_norm": 1.0172698497772217, | |
| "learning_rate": 5e-05, | |
| "loss": 2.0435, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002770802666897567, | |
| "eval_loss": 2.6185038089752197, | |
| "eval_runtime": 440.8372, | |
| "eval_samples_per_second": 55.154, | |
| "eval_steps_per_second": 6.896, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005541605333795133, | |
| "grad_norm": 1.3333725929260254, | |
| "learning_rate": 0.0001, | |
| "loss": 2.1851, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008312408000692701, | |
| "grad_norm": 1.4274028539657593, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.2284, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011083210667590267, | |
| "grad_norm": 1.268067479133606, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.1165, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0013854013334487834, | |
| "grad_norm": 1.0901422500610352, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.056, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0016624816001385402, | |
| "grad_norm": 1.1695683002471924, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.9676, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0019395618668282969, | |
| "grad_norm": 1.228065848350525, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.0373, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0022166421335180534, | |
| "grad_norm": 1.2500860691070557, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.0231, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0024937224002078103, | |
| "grad_norm": 1.4088391065597534, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.9904, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002770802666897567, | |
| "grad_norm": 1.321844220161438, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.7991, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003047882933587324, | |
| "grad_norm": 1.5810325145721436, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.8138, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0033249632002770803, | |
| "grad_norm": 1.3065353631973267, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.858, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.003602043466966837, | |
| "grad_norm": 1.1042661666870117, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.921, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0038791237336565938, | |
| "grad_norm": 1.3776724338531494, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.7046, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.004156204000346351, | |
| "grad_norm": 1.3263698816299438, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.756, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004433284267036107, | |
| "grad_norm": 1.1119990348815918, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.7557, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004710364533725864, | |
| "grad_norm": 0.7953896522521973, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.6287, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.004987444800415621, | |
| "grad_norm": 0.8209851384162903, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.691, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.005264525067105377, | |
| "grad_norm": 1.1580805778503418, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.6265, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.005541605333795134, | |
| "grad_norm": 1.1431478261947632, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.7062, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005818685600484891, | |
| "grad_norm": 0.8607553243637085, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.6295, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.006095765867174648, | |
| "grad_norm": 0.7982295155525208, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.5984, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.006372846133864404, | |
| "grad_norm": 0.8336132168769836, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.6866, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.006649926400554161, | |
| "grad_norm": 0.9011556506156921, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.6677, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0069270066672439175, | |
| "grad_norm": 1.1473370790481567, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.8729, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0069270066672439175, | |
| "eval_loss": 1.6248844861984253, | |
| "eval_runtime": 441.174, | |
| "eval_samples_per_second": 55.112, | |
| "eval_steps_per_second": 6.891, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007204086933933674, | |
| "grad_norm": 0.569159209728241, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6105, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.007481167200623431, | |
| "grad_norm": 0.6634584069252014, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.5842, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0077582474673131875, | |
| "grad_norm": 0.6659657955169678, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.614, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.008035327734002944, | |
| "grad_norm": 0.7010889053344727, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.6537, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.008312408000692701, | |
| "grad_norm": 0.6605480313301086, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.6621, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008589488267382457, | |
| "grad_norm": 0.698592483997345, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.7071, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.008866568534072214, | |
| "grad_norm": 0.7084943056106567, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.5723, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.009143648800761971, | |
| "grad_norm": 0.6080454587936401, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.5525, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.009420729067451727, | |
| "grad_norm": 0.7002612352371216, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.6181, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.009697809334141484, | |
| "grad_norm": 0.6785765886306763, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.5518, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.009974889600831241, | |
| "grad_norm": 0.7487239241600037, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.5369, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.010251969867520997, | |
| "grad_norm": 0.8074867129325867, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.6678, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.010529050134210753, | |
| "grad_norm": 0.6005417704582214, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.6568, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.010806130400900511, | |
| "grad_norm": 0.596122145652771, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.5572, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.011083210667590267, | |
| "grad_norm": 0.5598776936531067, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.5768, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.011360290934280023, | |
| "grad_norm": 0.56935054063797, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.4968, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.011637371200969781, | |
| "grad_norm": 0.5927587151527405, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.5508, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.011914451467659537, | |
| "grad_norm": 0.8119907975196838, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.663, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.012191531734349295, | |
| "grad_norm": 0.6603608727455139, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.5939, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.012468612001039051, | |
| "grad_norm": 0.6734949350357056, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.6528, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.012745692267728807, | |
| "grad_norm": 0.6059690117835999, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.5085, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.013022772534418565, | |
| "grad_norm": 0.6954624056816101, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.501, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.013299852801108321, | |
| "grad_norm": 0.7555593252182007, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.5964, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.013576933067798077, | |
| "grad_norm": 0.7384346723556519, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.5567, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.013854013334487835, | |
| "grad_norm": 1.1048245429992676, | |
| "learning_rate": 0.0, | |
| "loss": 1.7697, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.013854013334487835, | |
| "eval_loss": 1.574446678161621, | |
| "eval_runtime": 440.9601, | |
| "eval_samples_per_second": 55.139, | |
| "eval_steps_per_second": 6.894, | |
| "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": 2.229252309123072e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |