| { | |
| "best_metric": 10.374860763549805, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.06015037593984962, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012030075187969924, | |
| "grad_norm": 0.15661068260669708, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3774, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012030075187969924, | |
| "eval_loss": 10.382529258728027, | |
| "eval_runtime": 4.8107, | |
| "eval_samples_per_second": 1164.064, | |
| "eval_steps_per_second": 145.508, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002406015037593985, | |
| "grad_norm": 0.10033681988716125, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3795, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0036090225563909775, | |
| "grad_norm": 0.06864454597234726, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 10.3788, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00481203007518797, | |
| "grad_norm": 0.05666627362370491, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 10.3832, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006015037593984963, | |
| "grad_norm": 0.05942448228597641, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 10.382, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007218045112781955, | |
| "grad_norm": 0.057637158781290054, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 10.3819, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008421052631578947, | |
| "grad_norm": 0.0579264871776104, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 10.3811, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00962406015037594, | |
| "grad_norm": 0.058728329837322235, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.3836, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.010827067669172932, | |
| "grad_norm": 0.05199946090579033, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 10.3825, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012030075187969926, | |
| "grad_norm": 0.06942569464445114, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.3808, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013233082706766918, | |
| "grad_norm": 0.08756458759307861, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 10.3776, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01443609022556391, | |
| "grad_norm": 0.09705308079719543, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 10.3796, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.015639097744360904, | |
| "grad_norm": 0.16064858436584473, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 10.3754, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.016842105263157894, | |
| "grad_norm": 0.1374071091413498, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.3755, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01804511278195489, | |
| "grad_norm": 0.08335836231708527, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 10.3766, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01924812030075188, | |
| "grad_norm": 0.06066974624991417, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 10.3771, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.020451127819548873, | |
| "grad_norm": 0.05714043602347374, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 10.3779, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.021654135338345863, | |
| "grad_norm": 0.05652148276567459, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 10.3787, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.022857142857142857, | |
| "grad_norm": 0.05669313669204712, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 10.3785, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02406015037593985, | |
| "grad_norm": 0.054148104041814804, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.383, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02526315789473684, | |
| "grad_norm": 0.05806390196084976, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 10.3796, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.026466165413533835, | |
| "grad_norm": 0.06721248477697372, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 10.3811, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.027669172932330826, | |
| "grad_norm": 0.07443418353796005, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 10.3771, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.02887218045112782, | |
| "grad_norm": 0.08482617884874344, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 10.3792, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03007518796992481, | |
| "grad_norm": 0.12289085984230042, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 10.3856, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03007518796992481, | |
| "eval_loss": 10.376715660095215, | |
| "eval_runtime": 4.8177, | |
| "eval_samples_per_second": 1162.389, | |
| "eval_steps_per_second": 145.299, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03127819548872181, | |
| "grad_norm": 0.188450425863266, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3677, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0324812030075188, | |
| "grad_norm": 0.1014418974518776, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 10.3741, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03368421052631579, | |
| "grad_norm": 0.06390609592199326, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 10.3749, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03488721804511278, | |
| "grad_norm": 0.06750831753015518, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 10.3781, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.03609022556390978, | |
| "grad_norm": 0.052159812301397324, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 10.3768, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03729323308270677, | |
| "grad_norm": 0.07348703593015671, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 10.3756, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03849624060150376, | |
| "grad_norm": 0.06757855415344238, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 10.3782, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.039699248120300755, | |
| "grad_norm": 0.06782123446464539, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 10.378, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.040902255639097745, | |
| "grad_norm": 0.06930963695049286, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 10.3763, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.042105263157894736, | |
| "grad_norm": 0.08735895156860352, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 10.3796, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.043308270676691726, | |
| "grad_norm": 0.08168835937976837, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 10.379, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.044511278195488724, | |
| "grad_norm": 0.10469164699316025, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 10.3799, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.045714285714285714, | |
| "grad_norm": 0.18160542845726013, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 10.3644, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.046917293233082705, | |
| "grad_norm": 0.13455776870250702, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 10.3691, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0481203007518797, | |
| "grad_norm": 0.08988126367330551, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 10.3727, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04932330827067669, | |
| "grad_norm": 0.07319313287734985, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 10.3758, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.05052631578947368, | |
| "grad_norm": 0.06437268853187561, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 10.3747, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.051729323308270674, | |
| "grad_norm": 0.058004025369882584, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 10.3783, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.05293233082706767, | |
| "grad_norm": 0.06401561945676804, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 10.3742, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.05413533834586466, | |
| "grad_norm": 0.0757477805018425, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 10.3734, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05533834586466165, | |
| "grad_norm": 0.07375133037567139, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 10.3783, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.05654135338345865, | |
| "grad_norm": 0.08306660503149033, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 10.3792, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.05774436090225564, | |
| "grad_norm": 0.08625657111406326, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 10.3759, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.05894736842105263, | |
| "grad_norm": 0.09709803760051727, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 10.3772, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06015037593984962, | |
| "grad_norm": 0.1422736793756485, | |
| "learning_rate": 0.0, | |
| "loss": 10.3807, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06015037593984962, | |
| "eval_loss": 10.374860763549805, | |
| "eval_runtime": 4.8174, | |
| "eval_samples_per_second": 1162.461, | |
| "eval_steps_per_second": 145.308, | |
| "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": 84622607646720.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |