| { | |
| "best_metric": 1.1852225065231323, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.02226737551145378, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00044534751022907564, | |
| "grad_norm": 47.820091247558594, | |
| "learning_rate": 5e-05, | |
| "loss": 5.2543, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00044534751022907564, | |
| "eval_loss": 6.243781089782715, | |
| "eval_runtime": 744.0971, | |
| "eval_samples_per_second": 20.331, | |
| "eval_steps_per_second": 2.541, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008906950204581513, | |
| "grad_norm": 46.48420333862305, | |
| "learning_rate": 0.0001, | |
| "loss": 5.2971, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001336042530687227, | |
| "grad_norm": 48.014095306396484, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 5.457, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0017813900409163026, | |
| "grad_norm": 70.3463134765625, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 5.7215, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002226737551145378, | |
| "grad_norm": 76.0959243774414, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 4.7351, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002672085061374454, | |
| "grad_norm": 83.88655853271484, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 4.3951, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0031174325716035295, | |
| "grad_norm": 77.48736572265625, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 3.9592, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003562780081832605, | |
| "grad_norm": 70.22590637207031, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.5774, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00400812759206168, | |
| "grad_norm": 46.89838409423828, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 3.2751, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004453475102290756, | |
| "grad_norm": 49.71886444091797, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.7456, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0048988226125198315, | |
| "grad_norm": 48.742008209228516, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.5329, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005344170122748908, | |
| "grad_norm": 46.254913330078125, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.6578, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0057895176329779835, | |
| "grad_norm": 44.46732711791992, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.4587, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.006234865143207059, | |
| "grad_norm": 36.25248336791992, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.1404, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.006680212653436135, | |
| "grad_norm": 40.008113861083984, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.8034, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00712556016366521, | |
| "grad_norm": 43.887779235839844, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.7803, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.007570907673894286, | |
| "grad_norm": 41.66914367675781, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.8475, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.00801625518412336, | |
| "grad_norm": 43.23410415649414, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.6487, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.008461602694352437, | |
| "grad_norm": 44.319541931152344, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.5857, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.008906950204581512, | |
| "grad_norm": 29.81724739074707, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.2978, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009352297714810588, | |
| "grad_norm": 36.0647087097168, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.336, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.009797645225039663, | |
| "grad_norm": 38.552913665771484, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.5046, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01024299273526874, | |
| "grad_norm": 36.910823822021484, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.48, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.010688340245497816, | |
| "grad_norm": 35.79655075073242, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.2946, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01113368775572689, | |
| "grad_norm": 34.37594985961914, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.4518, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01113368775572689, | |
| "eval_loss": 1.3517735004425049, | |
| "eval_runtime": 738.598, | |
| "eval_samples_per_second": 20.482, | |
| "eval_steps_per_second": 2.56, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.011579035265955967, | |
| "grad_norm": 31.578306198120117, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5302, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.012024382776185042, | |
| "grad_norm": 32.41142654418945, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.4894, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.012469730286414118, | |
| "grad_norm": 29.10211181640625, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.1829, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.012915077796643193, | |
| "grad_norm": 29.35639190673828, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.2621, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.01336042530687227, | |
| "grad_norm": 27.41828727722168, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.1494, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.013805772817101344, | |
| "grad_norm": 30.824016571044922, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.1637, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.01425112032733042, | |
| "grad_norm": 29.908170700073242, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.0638, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.014696467837559495, | |
| "grad_norm": 28.103967666625977, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.3472, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.015141815347788572, | |
| "grad_norm": 28.541160583496094, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.0059, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.015587162858017646, | |
| "grad_norm": 35.961116790771484, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.0923, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01603251036824672, | |
| "grad_norm": 31.927988052368164, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.1726, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.016477857878475798, | |
| "grad_norm": 29.283533096313477, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.0773, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.016923205388704874, | |
| "grad_norm": 35.0276985168457, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.2266, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.01736855289893395, | |
| "grad_norm": 31.353435516357422, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.3432, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.017813900409163023, | |
| "grad_norm": 25.898488998413086, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.1339, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0182592479193921, | |
| "grad_norm": 27.802701950073242, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.1603, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.018704595429621176, | |
| "grad_norm": 29.901636123657227, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.0778, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.019149942939850253, | |
| "grad_norm": 31.745235443115234, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.2362, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.019595290450079326, | |
| "grad_norm": 38.1978759765625, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.9836, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.020040637960308402, | |
| "grad_norm": 34.44917678833008, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.052, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02048598547053748, | |
| "grad_norm": 32.72460174560547, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.3235, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.020931332980766555, | |
| "grad_norm": 27.416658401489258, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.0552, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.02137668049099563, | |
| "grad_norm": 33.398563385009766, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.1847, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.021822028001224705, | |
| "grad_norm": 31.242271423339844, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.1074, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.02226737551145378, | |
| "grad_norm": 35.66719436645508, | |
| "learning_rate": 0.0, | |
| "loss": 1.2356, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02226737551145378, | |
| "eval_loss": 1.1852225065231323, | |
| "eval_runtime": 739.9181, | |
| "eval_samples_per_second": 20.446, | |
| "eval_steps_per_second": 2.556, | |
| "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": 1.0952750720352256e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |