| { | |
| "best_metric": 0.09587574750185013, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.7162041181736795, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01432408236347359, | |
| "grad_norm": 63.055362701416016, | |
| "learning_rate": 5e-05, | |
| "loss": 1.103, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01432408236347359, | |
| "eval_loss": 1.0215070247650146, | |
| "eval_runtime": 14.3994, | |
| "eval_samples_per_second": 32.64, | |
| "eval_steps_per_second": 4.097, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02864816472694718, | |
| "grad_norm": 74.32926177978516, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9493, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04297224709042077, | |
| "grad_norm": 72.27410888671875, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.5497, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05729632945389436, | |
| "grad_norm": 46.700836181640625, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.1979, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07162041181736795, | |
| "grad_norm": 19.62844467163086, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.1001, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08594449418084155, | |
| "grad_norm": 19.621530532836914, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.0659, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.10026857654431513, | |
| "grad_norm": 16.500459671020508, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.1086, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.11459265890778872, | |
| "grad_norm": 16.219865798950195, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0392, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.12891674127126232, | |
| "grad_norm": 27.937068939208984, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.0779, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1432408236347359, | |
| "grad_norm": 12.639532089233398, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.1651, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1575649059982095, | |
| "grad_norm": 45.64315414428711, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.7781, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1718889883616831, | |
| "grad_norm": 51.64421463012695, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.3408, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.18621307072515667, | |
| "grad_norm": 55.34473419189453, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.0015, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.20053715308863027, | |
| "grad_norm": 66.8047103881836, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.3822, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.21486123545210384, | |
| "grad_norm": 57.349098205566406, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.1784, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.22918531781557744, | |
| "grad_norm": 23.43671226501465, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.089, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.24350940017905104, | |
| "grad_norm": 6.633354187011719, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.029, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.25783348254252464, | |
| "grad_norm": 6.5723557472229, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0422, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2721575649059982, | |
| "grad_norm": 4.889287948608398, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.0295, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2864816472694718, | |
| "grad_norm": 8.272890090942383, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0129, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3008057296329454, | |
| "grad_norm": 3.8905489444732666, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.0569, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.315129811996419, | |
| "grad_norm": 4.120612621307373, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.0305, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3294538943598926, | |
| "grad_norm": 22.227991104125977, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.1857, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3437779767233662, | |
| "grad_norm": 56.35881423950195, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.3667, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.35810205908683973, | |
| "grad_norm": 46.99864196777344, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.1759, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.35810205908683973, | |
| "eval_loss": 0.12282446771860123, | |
| "eval_runtime": 14.6624, | |
| "eval_samples_per_second": 32.055, | |
| "eval_steps_per_second": 4.024, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.37242614145031333, | |
| "grad_norm": 33.184486389160156, | |
| "learning_rate": 5e-05, | |
| "loss": 0.601, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.38675022381378693, | |
| "grad_norm": 15.069119453430176, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.0596, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.40107430617726053, | |
| "grad_norm": 4.007075786590576, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.0156, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.41539838854073413, | |
| "grad_norm": 4.233516216278076, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.021, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.4297224709042077, | |
| "grad_norm": 1.1447811126708984, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0023, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4440465532676813, | |
| "grad_norm": 1.9399925470352173, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.0104, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.4583706356311549, | |
| "grad_norm": 0.5079887509346008, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.001, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4726947179946285, | |
| "grad_norm": 0.320555180311203, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.0006, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.4870188003581021, | |
| "grad_norm": 3.9572017192840576, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0168, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5013428827215757, | |
| "grad_norm": 10.02822494506836, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0444, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5156669650850493, | |
| "grad_norm": 57.605918884277344, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.2545, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5299910474485229, | |
| "grad_norm": 35.58195114135742, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.1567, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5443151298119964, | |
| "grad_norm": 21.149555206298828, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.6636, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.55863921217547, | |
| "grad_norm": 29.886781692504883, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.1354, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5729632945389436, | |
| "grad_norm": 3.169788360595703, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0168, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5872873769024172, | |
| "grad_norm": 2.152250289916992, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0159, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.6016114592658908, | |
| "grad_norm": 1.8241573572158813, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0029, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6159355416293644, | |
| "grad_norm": 1.5569576025009155, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.014, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.630259623992838, | |
| "grad_norm": 0.5868328213691711, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0017, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6445837063563116, | |
| "grad_norm": 1.1041371822357178, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.0115, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6589077887197852, | |
| "grad_norm": 2.012267827987671, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0204, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6732318710832588, | |
| "grad_norm": 1.2815735340118408, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0067, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6875559534467324, | |
| "grad_norm": 13.361666679382324, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0906, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.7018800358102059, | |
| "grad_norm": 19.576683044433594, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.1782, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.7162041181736795, | |
| "grad_norm": 17.42030906677246, | |
| "learning_rate": 0.0, | |
| "loss": 0.1183, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7162041181736795, | |
| "eval_loss": 0.09587574750185013, | |
| "eval_runtime": 14.6657, | |
| "eval_samples_per_second": 32.048, | |
| "eval_steps_per_second": 4.023, | |
| "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": 5.688797699537633e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |