| { | |
| "best_metric": 0.3493710160255432, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.5586592178770949, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0111731843575419, | |
| "grad_norm": 1.9335039854049683, | |
| "learning_rate": 5e-05, | |
| "loss": 2.7995, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0111731843575419, | |
| "eval_loss": 3.844452142715454, | |
| "eval_runtime": 37.0183, | |
| "eval_samples_per_second": 16.289, | |
| "eval_steps_per_second": 2.053, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0223463687150838, | |
| "grad_norm": 2.5465948581695557, | |
| "learning_rate": 0.0001, | |
| "loss": 3.3779, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0335195530726257, | |
| "grad_norm": 2.5162341594696045, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 3.1282, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0446927374301676, | |
| "grad_norm": 2.615168571472168, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.9419, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.055865921787709494, | |
| "grad_norm": 2.81192684173584, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.4591, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0670391061452514, | |
| "grad_norm": 2.6667568683624268, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.9899, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0782122905027933, | |
| "grad_norm": 3.4611449241638184, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.0036, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0893854748603352, | |
| "grad_norm": 4.952938079833984, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.9836, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1005586592178771, | |
| "grad_norm": 4.240049839019775, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.997, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.11173184357541899, | |
| "grad_norm": 2.3263561725616455, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.9983, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12290502793296089, | |
| "grad_norm": 3.221536874771118, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.1286, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1340782122905028, | |
| "grad_norm": 4.037166595458984, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.1058, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1452513966480447, | |
| "grad_norm": 2.671057939529419, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.8863, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1564245810055866, | |
| "grad_norm": 3.492326259613037, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.3156, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.16759776536312848, | |
| "grad_norm": 2.323608875274658, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.9216, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1787709497206704, | |
| "grad_norm": 2.286482334136963, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.7754, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.18994413407821228, | |
| "grad_norm": 1.7907555103302002, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.7062, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.2011173184357542, | |
| "grad_norm": 2.0981123447418213, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.6787, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2122905027932961, | |
| "grad_norm": 1.53839910030365, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.6849, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.22346368715083798, | |
| "grad_norm": 1.8976991176605225, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.7777, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2346368715083799, | |
| "grad_norm": 1.8834900856018066, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.7695, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.24581005586592178, | |
| "grad_norm": 1.6889883279800415, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.8955, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2569832402234637, | |
| "grad_norm": 2.1583051681518555, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.9089, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2681564245810056, | |
| "grad_norm": 2.697247266769409, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.8759, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.27932960893854747, | |
| "grad_norm": 3.21006441116333, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.0099, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.27932960893854747, | |
| "eval_loss": 0.6153441071510315, | |
| "eval_runtime": 36.9188, | |
| "eval_samples_per_second": 16.333, | |
| "eval_steps_per_second": 2.059, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2905027932960894, | |
| "grad_norm": 3.640821933746338, | |
| "learning_rate": 5e-05, | |
| "loss": 0.773, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3016759776536313, | |
| "grad_norm": 2.355128526687622, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.5255, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3128491620111732, | |
| "grad_norm": 2.0450501441955566, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.4143, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3240223463687151, | |
| "grad_norm": 1.4887375831604004, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.3391, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.33519553072625696, | |
| "grad_norm": 1.2593166828155518, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.3544, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3463687150837989, | |
| "grad_norm": 1.853230595588684, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.3347, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.3575418994413408, | |
| "grad_norm": 1.62923264503479, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.3906, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.3687150837988827, | |
| "grad_norm": 1.8756768703460693, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.3795, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.37988826815642457, | |
| "grad_norm": 1.8412232398986816, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.3968, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.39106145251396646, | |
| "grad_norm": 2.1290626525878906, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.458, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4022346368715084, | |
| "grad_norm": 2.3173768520355225, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.5238, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.4134078212290503, | |
| "grad_norm": 4.143202304840088, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.6603, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.4245810055865922, | |
| "grad_norm": 2.3867380619049072, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.5852, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.43575418994413406, | |
| "grad_norm": 2.476198434829712, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.3394, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.44692737430167595, | |
| "grad_norm": 2.8215203285217285, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.3283, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4581005586592179, | |
| "grad_norm": 2.8288891315460205, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.2943, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.4692737430167598, | |
| "grad_norm": 2.5968244075775146, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.2975, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.48044692737430167, | |
| "grad_norm": 1.5942438840866089, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.264, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.49162011173184356, | |
| "grad_norm": 1.9241458177566528, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.3016, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5027932960893855, | |
| "grad_norm": 2.264237403869629, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.3179, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5139664804469274, | |
| "grad_norm": 2.3775475025177, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.3435, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5251396648044693, | |
| "grad_norm": 2.234323263168335, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.3742, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5363128491620112, | |
| "grad_norm": 1.941105842590332, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.4158, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.547486033519553, | |
| "grad_norm": 2.362673759460449, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.4802, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.5586592178770949, | |
| "grad_norm": 2.9098291397094727, | |
| "learning_rate": 0.0, | |
| "loss": 0.6609, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5586592178770949, | |
| "eval_loss": 0.3493710160255432, | |
| "eval_runtime": 16.8321, | |
| "eval_samples_per_second": 35.824, | |
| "eval_steps_per_second": 4.515, | |
| "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": 5.624057810649088e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |