| { | |
| "best_metric": 0.6960844397544861, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.15618898867629832, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0031237797735259665, | |
| "grad_norm": 123.4577407836914, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3888, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0031237797735259665, | |
| "eval_loss": 4.010549068450928, | |
| "eval_runtime": 62.3565, | |
| "eval_samples_per_second": 34.591, | |
| "eval_steps_per_second": 4.33, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006247559547051933, | |
| "grad_norm": 195.81715393066406, | |
| "learning_rate": 0.0001, | |
| "loss": 1.9557, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.009371339320577899, | |
| "grad_norm": 181.35487365722656, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.732, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.012495119094103866, | |
| "grad_norm": 148.23948669433594, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.1532, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.015618898867629832, | |
| "grad_norm": 95.68206787109375, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.5112, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.018742678641155797, | |
| "grad_norm": 68.1971206665039, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.3027, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.021866458414681766, | |
| "grad_norm": 88.98738098144531, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.1517, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.024990238188207732, | |
| "grad_norm": 62.99566650390625, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.2107, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.028114017961733698, | |
| "grad_norm": 49.76944351196289, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.0489, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.031237797735259663, | |
| "grad_norm": 39.21405029296875, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.9703, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03436157750878563, | |
| "grad_norm": 34.17335891723633, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.0728, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.037485357282311595, | |
| "grad_norm": 36.63615417480469, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.0314, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04060913705583756, | |
| "grad_norm": 36.554229736328125, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.8873, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04373291682936353, | |
| "grad_norm": 26.738367080688477, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.6655, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0468566966028895, | |
| "grad_norm": 24.847402572631836, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.6342, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.049980476376415464, | |
| "grad_norm": 26.894756317138672, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.6856, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05310425614994143, | |
| "grad_norm": 26.362733840942383, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.7546, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.056228035923467395, | |
| "grad_norm": 34.913875579833984, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.8084, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05935181569699336, | |
| "grad_norm": 30.74034881591797, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.8098, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06247559547051933, | |
| "grad_norm": 36.61556625366211, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.7698, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0655993752440453, | |
| "grad_norm": 29.092626571655273, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.7357, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06872315501757126, | |
| "grad_norm": 36.90818405151367, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.8158, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07184693479109723, | |
| "grad_norm": 32.904396057128906, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.7916, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07497071456462319, | |
| "grad_norm": 33.92314529418945, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.8483, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.07809449433814916, | |
| "grad_norm": 31.703176498413086, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.7899, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07809449433814916, | |
| "eval_loss": 0.7294516563415527, | |
| "eval_runtime": 62.4375, | |
| "eval_samples_per_second": 34.547, | |
| "eval_steps_per_second": 4.324, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08121827411167512, | |
| "grad_norm": 20.791725158691406, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6133, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0843420538852011, | |
| "grad_norm": 25.42897605895996, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.6555, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.08746583365872707, | |
| "grad_norm": 24.95623779296875, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.7177, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.09058961343225302, | |
| "grad_norm": 25.04736328125, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.6268, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.093713393205779, | |
| "grad_norm": 25.7648983001709, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.6801, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09683717297930496, | |
| "grad_norm": 21.772857666015625, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.6209, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.09996095275283093, | |
| "grad_norm": 23.983652114868164, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.6367, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.10308473252635689, | |
| "grad_norm": 25.340946197509766, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.6879, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.10620851229988286, | |
| "grad_norm": 27.262245178222656, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.82, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.10933229207340882, | |
| "grad_norm": 29.177738189697266, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.7947, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.11245607184693479, | |
| "grad_norm": 29.051311492919922, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.7873, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.11557985162046076, | |
| "grad_norm": 31.636856079101562, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.809, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.11870363139398672, | |
| "grad_norm": 23.124906539916992, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.6913, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.1218274111675127, | |
| "grad_norm": 15.812859535217285, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.4575, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.12495119094103865, | |
| "grad_norm": 19.333393096923828, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.5977, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1280749707145646, | |
| "grad_norm": 20.976985931396484, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.6742, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.1311987504880906, | |
| "grad_norm": 23.88761329650879, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.654, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.13432253026161656, | |
| "grad_norm": 26.551042556762695, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.6539, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.13744631003514252, | |
| "grad_norm": 25.536396026611328, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.7266, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1405700898086685, | |
| "grad_norm": 27.101118087768555, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.7213, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.14369386958219446, | |
| "grad_norm": 23.394760131835938, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.6518, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.14681764935572042, | |
| "grad_norm": 27.829160690307617, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.7054, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.14994142912924638, | |
| "grad_norm": 26.184154510498047, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.6976, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.15306520890277237, | |
| "grad_norm": 28.922327041625977, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.7447, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.15618898867629832, | |
| "grad_norm": 30.464828491210938, | |
| "learning_rate": 0.0, | |
| "loss": 0.8527, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.15618898867629832, | |
| "eval_loss": 0.6960844397544861, | |
| "eval_runtime": 62.4671, | |
| "eval_samples_per_second": 34.53, | |
| "eval_steps_per_second": 4.322, | |
| "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": 5.658021338284032e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |