| { | |
| "best_metric": 0.7660866975784302, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.4652014652014653, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.029304029304029304, | |
| "grad_norm": 42.79911804199219, | |
| "learning_rate": 5e-05, | |
| "loss": 10.8108, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.029304029304029304, | |
| "eval_loss": 11.66943359375, | |
| "eval_runtime": 11.9937, | |
| "eval_samples_per_second": 19.177, | |
| "eval_steps_per_second": 2.418, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05860805860805861, | |
| "grad_norm": 44.03789520263672, | |
| "learning_rate": 0.0001, | |
| "loss": 11.4368, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.08791208791208792, | |
| "grad_norm": 31.440637588500977, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 8.0577, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.11721611721611722, | |
| "grad_norm": 18.14752769470215, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.819, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.14652014652014653, | |
| "grad_norm": 10.853924751281738, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.1941, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.17582417582417584, | |
| "grad_norm": 4.0812764167785645, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.167, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.20512820512820512, | |
| "grad_norm": 4.215566158294678, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.23443223443223443, | |
| "grad_norm": 2.415107011795044, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.9698, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.26373626373626374, | |
| "grad_norm": 1.5998706817626953, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.8685, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.29304029304029305, | |
| "grad_norm": 1.1185362339019775, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.7608, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.32234432234432236, | |
| "grad_norm": 0.751507043838501, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.7363, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3516483516483517, | |
| "grad_norm": 1.6269491910934448, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.809, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "grad_norm": 1.7686549425125122, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.7639, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.41025641025641024, | |
| "grad_norm": 0.911514401435852, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.8109, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.43956043956043955, | |
| "grad_norm": 0.8268836736679077, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.8095, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.46886446886446886, | |
| "grad_norm": 0.526158332824707, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.8206, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.4981684981684982, | |
| "grad_norm": 0.6835467219352722, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.808, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.5274725274725275, | |
| "grad_norm": 0.6901230812072754, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.7211, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.5567765567765568, | |
| "grad_norm": 0.24927528202533722, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.7401, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.5860805860805861, | |
| "grad_norm": 0.3317570984363556, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.7348, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 0.692633867263794, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.7883, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.6446886446886447, | |
| "grad_norm": 1.3346521854400635, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.8881, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.673992673992674, | |
| "grad_norm": 0.8085936307907104, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.827, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.7032967032967034, | |
| "grad_norm": 0.3096141517162323, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.8136, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.7326007326007326, | |
| "grad_norm": 0.35282421112060547, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.8125, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7326007326007326, | |
| "eval_loss": 0.7876332402229309, | |
| "eval_runtime": 11.9922, | |
| "eval_samples_per_second": 19.179, | |
| "eval_steps_per_second": 2.418, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7619047619047619, | |
| "grad_norm": 0.5740500092506409, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7998, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.7912087912087912, | |
| "grad_norm": 1.062048316001892, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.7508, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.8205128205128205, | |
| "grad_norm": 0.8686541318893433, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.7552, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.8498168498168498, | |
| "grad_norm": 0.5461609363555908, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.7701, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.8791208791208791, | |
| "grad_norm": 0.20379406213760376, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.7829, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.9084249084249084, | |
| "grad_norm": 0.48669975996017456, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.8228, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.9377289377289377, | |
| "grad_norm": 0.4675156772136688, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.807, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.967032967032967, | |
| "grad_norm": 1.1531270742416382, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.885, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.9963369963369964, | |
| "grad_norm": 0.7078146934509277, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.8386, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.0256410256410255, | |
| "grad_norm": 1.082878828048706, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.441, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.054945054945055, | |
| "grad_norm": 0.5584947466850281, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.7131, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.0842490842490842, | |
| "grad_norm": 0.623293399810791, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.7405, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.1135531135531136, | |
| "grad_norm": 0.5018717646598816, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.7195, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 0.893699586391449, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.8149, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.1721611721611722, | |
| "grad_norm": 0.6624011397361755, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.81, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.2014652014652014, | |
| "grad_norm": 0.39665865898132324, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.7523, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.2307692307692308, | |
| "grad_norm": 0.5487731695175171, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.8137, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.26007326007326, | |
| "grad_norm": 0.5722079873085022, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.7874, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.2893772893772895, | |
| "grad_norm": 0.6342135071754456, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.7224, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.3186813186813187, | |
| "grad_norm": 0.5970407128334045, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.7422, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.347985347985348, | |
| "grad_norm": 0.600911557674408, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.7389, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.3772893772893773, | |
| "grad_norm": 0.5775716304779053, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.7585, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.4065934065934065, | |
| "grad_norm": 0.5375389456748962, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.7847, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.435897435897436, | |
| "grad_norm": 0.4871210753917694, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.798, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.4652014652014653, | |
| "grad_norm": 0.7523501515388489, | |
| "learning_rate": 0.0, | |
| "loss": 0.7955, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.4652014652014653, | |
| "eval_loss": 0.7660866975784302, | |
| "eval_runtime": 11.9906, | |
| "eval_samples_per_second": 19.182, | |
| "eval_steps_per_second": 2.419, | |
| "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": 6.631381723512832e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |