| { | |
| "best_metric": 1.1276211738586426, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.5751258087706685, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.011502516175413372, | |
| "grad_norm": 54.74974060058594, | |
| "learning_rate": 5e-05, | |
| "loss": 13.6585, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011502516175413372, | |
| "eval_loss": 14.432367324829102, | |
| "eval_runtime": 30.7032, | |
| "eval_samples_per_second": 19.086, | |
| "eval_steps_per_second": 2.41, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.023005032350826744, | |
| "grad_norm": 55.013160705566406, | |
| "learning_rate": 0.0001, | |
| "loss": 13.9468, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03450754852624011, | |
| "grad_norm": 37.52449035644531, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 9.1914, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04601006470165349, | |
| "grad_norm": 33.63827133178711, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 4.6916, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05751258087706686, | |
| "grad_norm": 16.19045639038086, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.3952, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06901509705248023, | |
| "grad_norm": 17.36304473876953, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.7037, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.08051761322789361, | |
| "grad_norm": 8.165637969970703, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.4678, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.09202012940330698, | |
| "grad_norm": 3.5105607509613037, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.2518, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.10352264557872035, | |
| "grad_norm": 3.2218363285064697, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.2587, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.11502516175413371, | |
| "grad_norm": 2.5013206005096436, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.2062, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12652767792954708, | |
| "grad_norm": 1.9085819721221924, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.1854, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.13803019410496045, | |
| "grad_norm": 1.6803501844406128, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.1762, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.14953271028037382, | |
| "grad_norm": 1.2716994285583496, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.1615, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.16103522645578722, | |
| "grad_norm": 1.4381122589111328, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.1654, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.17253774263120059, | |
| "grad_norm": 1.1117327213287354, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.1519, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.18404025880661395, | |
| "grad_norm": 1.494673490524292, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.1852, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.19554277498202732, | |
| "grad_norm": 0.5122988224029541, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.1529, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.2070452911574407, | |
| "grad_norm": 0.7242271900177002, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.1698, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.21854780733285406, | |
| "grad_norm": 0.6992008090019226, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.1673, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.23005032350826743, | |
| "grad_norm": 0.4791838228702545, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.1476, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2415528396836808, | |
| "grad_norm": 0.3778429329395294, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.1497, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.25305535585909417, | |
| "grad_norm": 0.4122251272201538, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.1404, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.26455787203450754, | |
| "grad_norm": 0.6639677286148071, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.143, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2760603882099209, | |
| "grad_norm": 0.5313247442245483, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.1394, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2875629043853343, | |
| "grad_norm": 0.5560535192489624, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.1246, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2875629043853343, | |
| "eval_loss": 1.1616710424423218, | |
| "eval_runtime": 67.5492, | |
| "eval_samples_per_second": 8.675, | |
| "eval_steps_per_second": 1.095, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.29906542056074764, | |
| "grad_norm": 0.7918073534965515, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1562, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.310567936736161, | |
| "grad_norm": 1.0403803586959839, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.1705, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.32207045291157443, | |
| "grad_norm": 0.5075483918190002, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.1533, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3335729690869878, | |
| "grad_norm": 0.8391026258468628, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.1679, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.34507548526240117, | |
| "grad_norm": 0.4457230269908905, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.1445, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.35657800143781454, | |
| "grad_norm": 0.723479151725769, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.1551, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.3680805176132279, | |
| "grad_norm": 0.5515746474266052, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.1417, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.3795830337886413, | |
| "grad_norm": 0.33850058913230896, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.14, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.39108554996405465, | |
| "grad_norm": 0.4152383804321289, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.1405, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.402588066139468, | |
| "grad_norm": 0.3818333148956299, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.1378, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4140905823148814, | |
| "grad_norm": 0.5444033145904541, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.1445, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.42559309849029475, | |
| "grad_norm": 0.40225115418434143, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.1175, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.4370956146657081, | |
| "grad_norm": 0.41632404923439026, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.1086, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.4485981308411215, | |
| "grad_norm": 0.4659530818462372, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.1495, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.46010064701653486, | |
| "grad_norm": 0.7380015254020691, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.1556, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4716031631919482, | |
| "grad_norm": 0.6908935308456421, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.1627, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.4831056793673616, | |
| "grad_norm": 0.39957094192504883, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.1222, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.49460819554277496, | |
| "grad_norm": 0.3861657381057739, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.1154, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5061107117181883, | |
| "grad_norm": 0.4914008378982544, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.1446, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5176132278936018, | |
| "grad_norm": 0.28890010714530945, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.137, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5291157440690151, | |
| "grad_norm": 0.32409754395484924, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.1171, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5406182602444285, | |
| "grad_norm": 0.48606187105178833, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.1439, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5521207764198418, | |
| "grad_norm": 0.34273761510849, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.11, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5636232925952552, | |
| "grad_norm": 0.4657009243965149, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.1021, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.5751258087706685, | |
| "grad_norm": 0.5568671226501465, | |
| "learning_rate": 0.0, | |
| "loss": 1.0781, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5751258087706685, | |
| "eval_loss": 1.1276211738586426, | |
| "eval_runtime": 67.5325, | |
| "eval_samples_per_second": 8.677, | |
| "eval_steps_per_second": 1.096, | |
| "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": 6.631381723512832e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |