| { | |
| "best_metric": 1.581311821937561, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.9060022650056625, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01812004530011325, | |
| "grad_norm": 3.353853464126587, | |
| "learning_rate": 5e-05, | |
| "loss": 2.8413, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01812004530011325, | |
| "eval_loss": 3.0799570083618164, | |
| "eval_runtime": 5.4479, | |
| "eval_samples_per_second": 68.283, | |
| "eval_steps_per_second": 8.627, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0362400906002265, | |
| "grad_norm": 3.207507848739624, | |
| "learning_rate": 0.0001, | |
| "loss": 2.8953, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.05436013590033975, | |
| "grad_norm": 3.2653355598449707, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.8512, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.072480181200453, | |
| "grad_norm": 2.8341968059539795, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.5232, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.09060022650056625, | |
| "grad_norm": 2.4388608932495117, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.4585, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1087202718006795, | |
| "grad_norm": 2.7728500366210938, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.2371, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.12684031710079274, | |
| "grad_norm": 2.378784418106079, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.2098, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.144960362400906, | |
| "grad_norm": 2.1482527256011963, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.0943, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.16308040770101925, | |
| "grad_norm": 1.8638383150100708, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.9817, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1812004530011325, | |
| "grad_norm": 2.0654704570770264, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.8742, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.19932049830124576, | |
| "grad_norm": 2.1612489223480225, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.866, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.217440543601359, | |
| "grad_norm": 2.3690574169158936, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.8765, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.23556058890147225, | |
| "grad_norm": 2.7848353385925293, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.9321, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2536806342015855, | |
| "grad_norm": 2.7931432723999023, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.9226, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.2718006795016987, | |
| "grad_norm": 1.4447989463806152, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.8, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.289920724801812, | |
| "grad_norm": 1.5375866889953613, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.7758, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.30804077010192527, | |
| "grad_norm": 1.5753406286239624, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.7916, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3261608154020385, | |
| "grad_norm": 1.5804219245910645, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.8195, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.34428086070215175, | |
| "grad_norm": 1.3650116920471191, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.7344, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.362400906002265, | |
| "grad_norm": 1.371211051940918, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.6936, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.38052095130237823, | |
| "grad_norm": 1.268407940864563, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.7248, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3986409966024915, | |
| "grad_norm": 1.227617621421814, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.6816, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.41676104190260477, | |
| "grad_norm": 1.3453476428985596, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.5177, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.434881087202718, | |
| "grad_norm": 1.6464775800704956, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.6804, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.45300113250283125, | |
| "grad_norm": 2.041501522064209, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.6316, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.45300113250283125, | |
| "eval_loss": 1.6654880046844482, | |
| "eval_runtime": 5.4794, | |
| "eval_samples_per_second": 67.891, | |
| "eval_steps_per_second": 8.578, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4711211778029445, | |
| "grad_norm": 2.542720079421997, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7668, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.48924122310305773, | |
| "grad_norm": 2.1035008430480957, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.6622, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.507361268403171, | |
| "grad_norm": 1.6165552139282227, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.6098, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.5254813137032842, | |
| "grad_norm": 1.1599594354629517, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.7074, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.5436013590033975, | |
| "grad_norm": 1.094414234161377, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.5716, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5617214043035108, | |
| "grad_norm": 1.1352035999298096, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.6661, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.579841449603624, | |
| "grad_norm": 1.135955810546875, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.6262, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5979614949037373, | |
| "grad_norm": 1.227918028831482, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.6239, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.6160815402038505, | |
| "grad_norm": 1.2326364517211914, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.5764, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.6342015855039638, | |
| "grad_norm": 1.126684308052063, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.5883, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.652321630804077, | |
| "grad_norm": 1.3494774103164673, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.5888, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.6704416761041903, | |
| "grad_norm": 1.6403988599777222, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.4864, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.6885617214043035, | |
| "grad_norm": 1.1846927404403687, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.6079, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.7066817667044167, | |
| "grad_norm": 0.950275182723999, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.6306, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.72480181200453, | |
| "grad_norm": 1.0314114093780518, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.6489, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7429218573046432, | |
| "grad_norm": 1.047741174697876, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.5711, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.7610419026047565, | |
| "grad_norm": 0.9879609942436218, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.5778, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.7791619479048698, | |
| "grad_norm": 1.109057068824768, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.6443, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.797281993204983, | |
| "grad_norm": 1.013243317604065, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.6006, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.8154020385050963, | |
| "grad_norm": 0.9669159650802612, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.5514, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.8335220838052095, | |
| "grad_norm": 1.0670894384384155, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.5702, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.8516421291053228, | |
| "grad_norm": 1.054745078086853, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.5336, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.869762174405436, | |
| "grad_norm": 1.253612995147705, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.6048, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.8878822197055493, | |
| "grad_norm": 1.2807451486587524, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.5269, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.9060022650056625, | |
| "grad_norm": 2.344367504119873, | |
| "learning_rate": 0.0, | |
| "loss": 1.64, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.9060022650056625, | |
| "eval_loss": 1.581311821937561, | |
| "eval_runtime": 5.5382, | |
| "eval_samples_per_second": 67.17, | |
| "eval_steps_per_second": 8.486, | |
| "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": 2.95300912644096e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |