| { | |
| "best_metric": 11.886842727661133, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.2740157480314962, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.025196850393700787, | |
| "grad_norm": 0.16284212470054626, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9314, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.025196850393700787, | |
| "eval_loss": 11.933157920837402, | |
| "eval_runtime": 3.9016, | |
| "eval_samples_per_second": 68.69, | |
| "eval_steps_per_second": 8.714, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.050393700787401574, | |
| "grad_norm": 0.20092415809631348, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9326, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.07559055118110236, | |
| "grad_norm": 0.2008458524942398, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 11.9314, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.10078740157480315, | |
| "grad_norm": 0.2192167490720749, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 11.9327, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.12598425196850394, | |
| "grad_norm": 0.25790461897850037, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 11.9308, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.15118110236220472, | |
| "grad_norm": 0.24272070825099945, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 11.9274, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1763779527559055, | |
| "grad_norm": 0.2548143267631531, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 11.9274, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2015748031496063, | |
| "grad_norm": 0.3137708306312561, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.9233, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.22677165354330708, | |
| "grad_norm": 0.39684319496154785, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 11.9195, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.25196850393700787, | |
| "grad_norm": 0.23756013810634613, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 11.922, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.27716535433070866, | |
| "grad_norm": 0.2792322039604187, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 11.9233, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.30236220472440944, | |
| "grad_norm": 0.3265670835971832, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 11.9192, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.32755905511811023, | |
| "grad_norm": 0.33717963099479675, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 11.9196, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.352755905511811, | |
| "grad_norm": 0.37349534034729004, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.9146, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3779527559055118, | |
| "grad_norm": 0.3645245432853699, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 11.915, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.4031496062992126, | |
| "grad_norm": 0.3812781274318695, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 11.9093, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.4283464566929134, | |
| "grad_norm": 0.40365922451019287, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 11.9071, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.45354330708661417, | |
| "grad_norm": 0.37025293707847595, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 11.9095, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.47874015748031495, | |
| "grad_norm": 0.4620673954486847, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 11.9, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.5039370078740157, | |
| "grad_norm": 0.3636421859264374, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 11.9112, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5291338582677165, | |
| "grad_norm": 0.3550845980644226, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 11.9063, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.5543307086614173, | |
| "grad_norm": 0.38180872797966003, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 11.9031, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5795275590551181, | |
| "grad_norm": 0.3487289845943451, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 11.9015, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.6047244094488189, | |
| "grad_norm": 0.34168243408203125, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 11.9002, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.6299212598425197, | |
| "grad_norm": 0.3240868151187897, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 11.9019, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6299212598425197, | |
| "eval_loss": 11.895190238952637, | |
| "eval_runtime": 3.8826, | |
| "eval_samples_per_second": 69.026, | |
| "eval_steps_per_second": 8.757, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6551181102362205, | |
| "grad_norm": 0.331646203994751, | |
| "learning_rate": 5e-05, | |
| "loss": 11.8964, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.6803149606299213, | |
| "grad_norm": 0.3141518533229828, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 11.8942, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.705511811023622, | |
| "grad_norm": 0.3754909038543701, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 11.8913, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.7307086614173228, | |
| "grad_norm": 0.4402559995651245, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 11.8858, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.7559055118110236, | |
| "grad_norm": 0.3316049575805664, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 11.9006, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7811023622047244, | |
| "grad_norm": 0.3181600868701935, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 11.8977, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.8062992125984252, | |
| "grad_norm": 0.30616819858551025, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 11.8965, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.831496062992126, | |
| "grad_norm": 0.3036477267742157, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 11.895, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.8566929133858268, | |
| "grad_norm": 0.2968073785305023, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 11.8921, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.8818897637795275, | |
| "grad_norm": 0.2789314389228821, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 11.8925, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.9070866141732283, | |
| "grad_norm": 0.28592121601104736, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 11.8882, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.9322834645669291, | |
| "grad_norm": 0.3040885925292969, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 11.8865, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.9574803149606299, | |
| "grad_norm": 0.303553968667984, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 11.8896, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.9826771653543307, | |
| "grad_norm": 0.44159021973609924, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 11.8882, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.022047244094488, | |
| "grad_norm": 0.6005897521972656, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 22.7735, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.047244094488189, | |
| "grad_norm": 0.2941368520259857, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 11.6916, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.0724409448818897, | |
| "grad_norm": 0.2826595604419708, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 11.8378, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.0976377952755905, | |
| "grad_norm": 0.28620612621307373, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 11.8422, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.1228346456692913, | |
| "grad_norm": 0.27169060707092285, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 11.8735, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.148031496062992, | |
| "grad_norm": 0.260793536901474, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 11.8909, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.1732283464566928, | |
| "grad_norm": 0.2629808187484741, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 11.912, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.1984251968503936, | |
| "grad_norm": 0.2864266633987427, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 11.8981, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.2236220472440944, | |
| "grad_norm": 0.30693575739860535, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 11.9876, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.2488188976377952, | |
| "grad_norm": 0.26912087202072144, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 9.5, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.2740157480314962, | |
| "grad_norm": 0.3693660795688629, | |
| "learning_rate": 0.0, | |
| "loss": 14.3454, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.2740157480314962, | |
| "eval_loss": 11.886842727661133, | |
| "eval_runtime": 3.8979, | |
| "eval_samples_per_second": 68.754, | |
| "eval_steps_per_second": 8.723, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 417996147261440.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |