| { | |
| "best_metric": 0.4769541323184967, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.7850834151128557, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.015701668302257114, | |
| "grad_norm": 170.09814453125, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8636, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.015701668302257114, | |
| "eval_loss": 2.6159276962280273, | |
| "eval_runtime": 16.4424, | |
| "eval_samples_per_second": 26.152, | |
| "eval_steps_per_second": 3.284, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03140333660451423, | |
| "grad_norm": 524.267333984375, | |
| "learning_rate": 0.0001, | |
| "loss": 4.8384, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.047105004906771344, | |
| "grad_norm": 317.7803039550781, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.5844, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06280667320902845, | |
| "grad_norm": 2709.66552734375, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 7.6382, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07850834151128558, | |
| "grad_norm": 314.3463134765625, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.7676, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.09421000981354269, | |
| "grad_norm": 239.6953125, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.5485, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1099116781157998, | |
| "grad_norm": 130.650146484375, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.1849, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1256133464180569, | |
| "grad_norm": 88.36298370361328, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.8632, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.14131501472031405, | |
| "grad_norm": 74.64122772216797, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.7533, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.15701668302257116, | |
| "grad_norm": 71.6720962524414, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.7462, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17271835132482827, | |
| "grad_norm": 66.8488998413086, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.6773, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.18842001962708538, | |
| "grad_norm": 62.52133560180664, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.811, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2041216879293425, | |
| "grad_norm": 46.03673553466797, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.7991, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2198233562315996, | |
| "grad_norm": 72.63166046142578, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.222, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.23552502453385674, | |
| "grad_norm": 159.1966094970703, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.0858, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2512266928361138, | |
| "grad_norm": 56.10406494140625, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.5513, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.26692836113837093, | |
| "grad_norm": 38.8935661315918, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.5061, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.2826300294406281, | |
| "grad_norm": 57.85786437988281, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.5194, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2983316977428852, | |
| "grad_norm": 37.94969940185547, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.4684, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.3140333660451423, | |
| "grad_norm": 34.73514938354492, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.4928, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3297350343473994, | |
| "grad_norm": 40.22306442260742, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.5344, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.34543670264965654, | |
| "grad_norm": 29.065454483032227, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.5823, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.36113837095191365, | |
| "grad_norm": 28.179121017456055, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.4906, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.37684003925417076, | |
| "grad_norm": 29.916444778442383, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.5275, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.39254170755642787, | |
| "grad_norm": 22.734882354736328, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.4979, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.39254170755642787, | |
| "eval_loss": 0.58062744140625, | |
| "eval_runtime": 16.7696, | |
| "eval_samples_per_second": 25.642, | |
| "eval_steps_per_second": 3.22, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.408243375858685, | |
| "grad_norm": 36.78559112548828, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8095, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.4239450441609421, | |
| "grad_norm": 91.48822784423828, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.3609, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.4396467124631992, | |
| "grad_norm": 112.85855102539062, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.45, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.4553483807654563, | |
| "grad_norm": 35.0981559753418, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.4484, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.47105004906771347, | |
| "grad_norm": 35.688232421875, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.5243, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4867517173699706, | |
| "grad_norm": 26.68511962890625, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.4155, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.5024533856722276, | |
| "grad_norm": 31.952564239501953, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.4639, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5181550539744848, | |
| "grad_norm": 29.325927734375, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.4836, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5338567222767419, | |
| "grad_norm": 27.150094985961914, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.4913, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.549558390578999, | |
| "grad_norm": 23.984006881713867, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.4835, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5652600588812562, | |
| "grad_norm": 25.365285873413086, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.5018, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5809617271835132, | |
| "grad_norm": 23.533668518066406, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.5084, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5966633954857704, | |
| "grad_norm": 20.562366485595703, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.5959, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.6123650637880275, | |
| "grad_norm": 59.9564208984375, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.678, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6280667320902846, | |
| "grad_norm": 125.5207748413086, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.0832, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6437684003925417, | |
| "grad_norm": 31.455310821533203, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.4804, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.6594700686947988, | |
| "grad_norm": 30.415761947631836, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.4456, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6751717369970559, | |
| "grad_norm": 31.347658157348633, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.479, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6908734052993131, | |
| "grad_norm": 24.028074264526367, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.4125, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.7065750736015701, | |
| "grad_norm": 27.257251739501953, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.4285, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7222767419038273, | |
| "grad_norm": 35.830406188964844, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.519, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.7379784102060843, | |
| "grad_norm": 24.885379791259766, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.4369, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.7536800785083415, | |
| "grad_norm": 27.403444290161133, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.5016, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.7693817468105987, | |
| "grad_norm": 26.06789779663086, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.4896, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.7850834151128557, | |
| "grad_norm": 18.390460968017578, | |
| "learning_rate": 0.0, | |
| "loss": 0.4831, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7850834151128557, | |
| "eval_loss": 0.4769541323184967, | |
| "eval_runtime": 16.4718, | |
| "eval_samples_per_second": 26.105, | |
| "eval_steps_per_second": 3.278, | |
| "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": 6.715371720246559e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |