| { | |
| "best_metric": 4.964861869812012, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.1224552273075157, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002449104546150314, | |
| "grad_norm": 7.140452861785889, | |
| "learning_rate": 5e-05, | |
| "loss": 10.4955, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002449104546150314, | |
| "eval_loss": 10.970553398132324, | |
| "eval_runtime": 2.9369, | |
| "eval_samples_per_second": 936.705, | |
| "eval_steps_per_second": 117.131, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004898209092300628, | |
| "grad_norm": 6.755414009094238, | |
| "learning_rate": 0.0001, | |
| "loss": 10.6407, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007347313638450942, | |
| "grad_norm": 5.720281600952148, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 9.9123, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009796418184601256, | |
| "grad_norm": 5.765336990356445, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 10.0863, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.012245522730751569, | |
| "grad_norm": 5.464238166809082, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 9.7016, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.014694627276901883, | |
| "grad_norm": 5.588547706604004, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 9.7105, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.017143731823052198, | |
| "grad_norm": 5.05673360824585, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 8.9953, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01959283636920251, | |
| "grad_norm": 5.43572473526001, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 9.1532, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.022041940915352824, | |
| "grad_norm": 5.630946636199951, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 8.9852, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.024491045461503137, | |
| "grad_norm": 5.682133197784424, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 8.9945, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02694015000765345, | |
| "grad_norm": 6.015380859375, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 9.1429, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.029389254553803767, | |
| "grad_norm": 6.519438743591309, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 9.1931, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.031838359099954076, | |
| "grad_norm": 6.041949272155762, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 8.4799, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.034287463646104396, | |
| "grad_norm": 5.421126365661621, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 7.4808, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03673656819225471, | |
| "grad_norm": 5.560758590698242, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 7.4902, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03918567273840502, | |
| "grad_norm": 5.815922260284424, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 7.4089, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.041634777284555335, | |
| "grad_norm": 5.995591163635254, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 7.2682, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04408388183070565, | |
| "grad_norm": 6.248690605163574, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 7.2071, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04653298637685596, | |
| "grad_norm": 6.144330024719238, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 6.785, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.048982090923006275, | |
| "grad_norm": 6.652873516082764, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 6.6433, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05143119546915659, | |
| "grad_norm": 6.940776824951172, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 6.4511, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0538803000153069, | |
| "grad_norm": 7.697096824645996, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 6.6621, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05632940456145722, | |
| "grad_norm": 8.201127052307129, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 6.4107, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.058778509107607534, | |
| "grad_norm": 8.622825622558594, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 6.2436, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06122761365375785, | |
| "grad_norm": 10.258541107177734, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 6.5619, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06122761365375785, | |
| "eval_loss": 5.9959306716918945, | |
| "eval_runtime": 2.9203, | |
| "eval_samples_per_second": 942.031, | |
| "eval_steps_per_second": 117.797, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06367671819990815, | |
| "grad_norm": 7.211130142211914, | |
| "learning_rate": 5e-05, | |
| "loss": 5.6802, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.06612582274605847, | |
| "grad_norm": 7.553848743438721, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 5.5996, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06857492729220879, | |
| "grad_norm": 7.340853691101074, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 5.5839, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0710240318383591, | |
| "grad_norm": 8.36943244934082, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 5.3825, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.07347313638450942, | |
| "grad_norm": 7.856369495391846, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 5.4483, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07592224093065973, | |
| "grad_norm": 8.200360298156738, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 5.32, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.07837134547681004, | |
| "grad_norm": 7.550553798675537, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 5.2876, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08082045002296036, | |
| "grad_norm": 8.68742561340332, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 5.1647, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08326955456911067, | |
| "grad_norm": 7.59812068939209, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 5.2607, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.08571865911526098, | |
| "grad_norm": 6.922670364379883, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 5.166, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0881677636614113, | |
| "grad_norm": 6.234425067901611, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 5.1715, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09061686820756161, | |
| "grad_norm": 7.038822650909424, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 5.2705, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.09306597275371192, | |
| "grad_norm": 7.074505805969238, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 5.3434, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.09551507729986224, | |
| "grad_norm": 8.038344383239746, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 5.0634, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.09796418184601255, | |
| "grad_norm": 7.753593444824219, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 4.8933, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10041328639216286, | |
| "grad_norm": 7.461465358734131, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 4.8374, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.10286239093831318, | |
| "grad_norm": 6.135587215423584, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 4.8073, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.10531149548446349, | |
| "grad_norm": 6.440159797668457, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 5.0602, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1077606000306138, | |
| "grad_norm": 6.288998603820801, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 4.7457, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.11020970457676411, | |
| "grad_norm": 6.0663957595825195, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 4.9725, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11265880912291444, | |
| "grad_norm": 5.9057817459106445, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 4.7998, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.11510791366906475, | |
| "grad_norm": 5.905740261077881, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 4.836, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.11755701821521507, | |
| "grad_norm": 6.103787899017334, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 5.1476, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.12000612276136538, | |
| "grad_norm": 6.240080833435059, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 4.9798, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.1224552273075157, | |
| "grad_norm": 7.454318046569824, | |
| "learning_rate": 0.0, | |
| "loss": 5.0739, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1224552273075157, | |
| "eval_loss": 4.964861869812012, | |
| "eval_runtime": 2.9286, | |
| "eval_samples_per_second": 939.347, | |
| "eval_steps_per_second": 117.461, | |
| "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": 3506283793612800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |