| { | |
| "best_metric": 0.8296974301338196, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.7241379310344827, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.034482758620689655, | |
| "grad_norm": 1.2411022186279297, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3204, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.034482758620689655, | |
| "eval_loss": 1.5744717121124268, | |
| "eval_runtime": 4.1334, | |
| "eval_samples_per_second": 47.177, | |
| "eval_steps_per_second": 6.048, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06896551724137931, | |
| "grad_norm": 1.5661057233810425, | |
| "learning_rate": 0.0001, | |
| "loss": 1.4652, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.10344827586206896, | |
| "grad_norm": 1.5970726013183594, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.5257, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.13793103448275862, | |
| "grad_norm": 1.3731942176818848, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.4154, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.1724137931034483, | |
| "grad_norm": 1.348717212677002, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.33, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.20689655172413793, | |
| "grad_norm": 1.1201543807983398, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.2998, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2413793103448276, | |
| "grad_norm": 1.5150401592254639, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.2943, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.27586206896551724, | |
| "grad_norm": 0.8315752148628235, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.0113, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3103448275862069, | |
| "grad_norm": 0.7831391096115112, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.0314, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3448275862068966, | |
| "grad_norm": 0.9782406687736511, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.0441, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3793103448275862, | |
| "grad_norm": 0.8368247747421265, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.0003, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.41379310344827586, | |
| "grad_norm": 0.633226752281189, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.9841, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.4482758620689655, | |
| "grad_norm": 0.668292760848999, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.0319, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.4827586206896552, | |
| "grad_norm": 0.8432500958442688, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.0935, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5172413793103449, | |
| "grad_norm": 0.6698826551437378, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.8511, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5517241379310345, | |
| "grad_norm": 0.59513258934021, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.8514, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5862068965517241, | |
| "grad_norm": 0.608653724193573, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.9371, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6206896551724138, | |
| "grad_norm": 0.5555115342140198, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.9159, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6551724137931034, | |
| "grad_norm": 0.573492169380188, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.8599, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.6896551724137931, | |
| "grad_norm": 0.5985779762268066, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.9408, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7241379310344828, | |
| "grad_norm": 0.8476566076278687, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.0202, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.7586206896551724, | |
| "grad_norm": 0.4384811520576477, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.7485, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.7931034482758621, | |
| "grad_norm": 0.49077481031417847, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.9319, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.8275862068965517, | |
| "grad_norm": 0.5539901256561279, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.9821, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.8620689655172413, | |
| "grad_norm": 0.5785988569259644, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.9932, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8620689655172413, | |
| "eval_loss": 0.8770236968994141, | |
| "eval_runtime": 4.1033, | |
| "eval_samples_per_second": 47.523, | |
| "eval_steps_per_second": 6.093, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.896551724137931, | |
| "grad_norm": 0.5288706421852112, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8239, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.9310344827586207, | |
| "grad_norm": 0.5527832508087158, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.8806, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.9655172413793104, | |
| "grad_norm": 0.7218241095542908, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.9175, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.44543588161468506, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.736, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.0344827586206897, | |
| "grad_norm": 0.40811803936958313, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.8053, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0689655172413792, | |
| "grad_norm": 0.4515950381755829, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.8298, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.103448275862069, | |
| "grad_norm": 0.5151574015617371, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.924, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.1379310344827587, | |
| "grad_norm": 0.4836006462574005, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.7411, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.1724137931034484, | |
| "grad_norm": 0.5116979479789734, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.8224, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.206896551724138, | |
| "grad_norm": 0.543500542640686, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.824, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.2413793103448276, | |
| "grad_norm": 0.6314417719841003, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.8329, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.2758620689655173, | |
| "grad_norm": 0.3729710280895233, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.7086, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.3103448275862069, | |
| "grad_norm": 0.4598703980445862, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.7906, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.3448275862068966, | |
| "grad_norm": 0.5059497356414795, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.7268, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.3793103448275863, | |
| "grad_norm": 0.48165661096572876, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.8421, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.4137931034482758, | |
| "grad_norm": 0.5090142488479614, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.7836, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.4482758620689655, | |
| "grad_norm": 0.5581346750259399, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.7805, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.4827586206896552, | |
| "grad_norm": 0.6325652599334717, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.8853, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.5172413793103448, | |
| "grad_norm": 0.3990720212459564, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.7517, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.5517241379310345, | |
| "grad_norm": 0.45109397172927856, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.7909, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.5862068965517242, | |
| "grad_norm": 0.512504518032074, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.8714, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.6206896551724137, | |
| "grad_norm": 0.4838815927505493, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.8317, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.6551724137931034, | |
| "grad_norm": 0.526544451713562, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.7849, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.6896551724137931, | |
| "grad_norm": 0.6029788255691528, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.901, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.7241379310344827, | |
| "grad_norm": 0.6109845042228699, | |
| "learning_rate": 0.0, | |
| "loss": 0.8062, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.7241379310344827, | |
| "eval_loss": 0.8296974301338196, | |
| "eval_runtime": 4.1199, | |
| "eval_samples_per_second": 47.331, | |
| "eval_steps_per_second": 6.068, | |
| "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": 8.33416392081408e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |