| { | |
| "best_metric": 0.35179558396339417, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.5908419497784343, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.011816838995568686, | |
| "grad_norm": 12.808429718017578, | |
| "learning_rate": 5e-05, | |
| "loss": 13.139, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011816838995568686, | |
| "eval_loss": 12.234064102172852, | |
| "eval_runtime": 24.2913, | |
| "eval_samples_per_second": 23.465, | |
| "eval_steps_per_second": 2.964, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.023633677991137372, | |
| "grad_norm": 12.65912914276123, | |
| "learning_rate": 0.0001, | |
| "loss": 13.0875, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03545051698670606, | |
| "grad_norm": 13.654474258422852, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 13.0209, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.047267355982274745, | |
| "grad_norm": 11.395278930664062, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 10.2698, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.059084194977843424, | |
| "grad_norm": 9.340927124023438, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 8.5188, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07090103397341212, | |
| "grad_norm": 15.237786293029785, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 5.6717, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0827178729689808, | |
| "grad_norm": 16.42193031311035, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 4.2989, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.09453471196454949, | |
| "grad_norm": 13.018158912658691, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.9802, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.10635155096011817, | |
| "grad_norm": 24.382726669311523, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.1977, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.11816838995568685, | |
| "grad_norm": 23.346149444580078, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.1563, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12998522895125553, | |
| "grad_norm": 8.26559066772461, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.4439, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.14180206794682423, | |
| "grad_norm": 8.023841857910156, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.5377, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1536189069423929, | |
| "grad_norm": 17.758037567138672, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.9574, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1654357459379616, | |
| "grad_norm": 20.18980598449707, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.755, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.17725258493353027, | |
| "grad_norm": 10.446304321289062, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.6288, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.18906942392909898, | |
| "grad_norm": 3.0844123363494873, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.4419, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.20088626292466766, | |
| "grad_norm": 1.4150352478027344, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.3912, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.21270310192023634, | |
| "grad_norm": 3.2957334518432617, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.3835, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.22451994091580502, | |
| "grad_norm": 2.989173412322998, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.3655, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2363367799113737, | |
| "grad_norm": 2.752204179763794, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.3695, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2481536189069424, | |
| "grad_norm": 2.2246530055999756, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.3761, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.25997045790251105, | |
| "grad_norm": 1.6964706182479858, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.3587, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2717872968980798, | |
| "grad_norm": 0.9301137924194336, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.3584, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.28360413589364847, | |
| "grad_norm": 3.3053698539733887, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.381, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.29542097488921715, | |
| "grad_norm": 3.8575143814086914, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.3833, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.29542097488921715, | |
| "eval_loss": 0.3561660051345825, | |
| "eval_runtime": 24.0035, | |
| "eval_samples_per_second": 23.747, | |
| "eval_steps_per_second": 3.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3072378138847858, | |
| "grad_norm": 0.7805519700050354, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3636, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3190546528803545, | |
| "grad_norm": 3.7027106285095215, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.3872, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3308714918759232, | |
| "grad_norm": 0.6524713039398193, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.3544, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.34268833087149186, | |
| "grad_norm": 0.9396346807479858, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.3462, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.35450516986706054, | |
| "grad_norm": 1.9516257047653198, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.3545, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3663220088626292, | |
| "grad_norm": 0.5772966742515564, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.3595, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.37813884785819796, | |
| "grad_norm": 0.86551433801651, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.3441, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.38995568685376664, | |
| "grad_norm": 0.8409296870231628, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.3684, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.4017725258493353, | |
| "grad_norm": 2.4118385314941406, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.3616, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.413589364844904, | |
| "grad_norm": 0.6091898679733276, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.3364, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4254062038404727, | |
| "grad_norm": 0.6151113510131836, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.3399, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.43722304283604135, | |
| "grad_norm": 1.0913517475128174, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.3344, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.44903988183161003, | |
| "grad_norm": 2.2895851135253906, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.3643, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.4608567208271787, | |
| "grad_norm": 4.044822692871094, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.4437, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.4726735598227474, | |
| "grad_norm": 3.535907506942749, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.4124, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4844903988183161, | |
| "grad_norm": 3.7408993244171143, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.419, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.4963072378138848, | |
| "grad_norm": 3.162598133087158, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.3991, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5081240768094535, | |
| "grad_norm": 1.1125186681747437, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.3423, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5199409158050221, | |
| "grad_norm": 0.45383548736572266, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.3333, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5317577548005908, | |
| "grad_norm": 1.0506929159164429, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.3556, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5435745937961596, | |
| "grad_norm": 1.0979819297790527, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.3554, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5553914327917282, | |
| "grad_norm": 2.562333822250366, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.3518, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5672082717872969, | |
| "grad_norm": 0.9119501113891602, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.3309, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5790251107828656, | |
| "grad_norm": 1.5554051399230957, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.3076, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.5908419497784343, | |
| "grad_norm": 3.618457317352295, | |
| "learning_rate": 0.0, | |
| "loss": 0.3793, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5908419497784343, | |
| "eval_loss": 0.35179558396339417, | |
| "eval_runtime": 23.9788, | |
| "eval_samples_per_second": 23.771, | |
| "eval_steps_per_second": 3.003, | |
| "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": 3.7091737698146714e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |