| { | |
| "best_metric": 4.119277477264404, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.18948365703458075, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0037896731406916154, | |
| "grad_norm": 0.9953848123550415, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7304, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0037896731406916154, | |
| "eval_loss": 4.723026275634766, | |
| "eval_runtime": 12.9737, | |
| "eval_samples_per_second": 137.046, | |
| "eval_steps_per_second": 17.189, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007579346281383231, | |
| "grad_norm": 1.4914480447769165, | |
| "learning_rate": 0.0001, | |
| "loss": 2.7373, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.011369019422074847, | |
| "grad_norm": 1.8038101196289062, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 4.6117, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.015158692562766462, | |
| "grad_norm": 1.5669078826904297, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 5.1387, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.018948365703458078, | |
| "grad_norm": 1.5052076578140259, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 5.1593, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.022738038844149693, | |
| "grad_norm": 1.5272639989852905, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 5.3344, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.026527711984841308, | |
| "grad_norm": 1.5586494207382202, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 5.2152, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.030317385125532923, | |
| "grad_norm": 1.652699589729309, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 5.1525, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03410705826622454, | |
| "grad_norm": 1.5505369901657104, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 4.6545, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.037896731406916156, | |
| "grad_norm": 2.3943397998809814, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 4.7806, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04168640454760777, | |
| "grad_norm": 1.8680907487869263, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 4.4046, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.045476077688299386, | |
| "grad_norm": 1.8995227813720703, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 4.5933, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.049265750828991, | |
| "grad_norm": 1.7265771627426147, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.782, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.053055423969682616, | |
| "grad_norm": 2.496830940246582, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.1817, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.05684509711037423, | |
| "grad_norm": 1.4836934804916382, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 3.2797, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.060634770251065846, | |
| "grad_norm": 1.671715259552002, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 4.3823, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.06442444339175746, | |
| "grad_norm": 1.3735142946243286, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 4.7603, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.06821411653244908, | |
| "grad_norm": 1.169889211654663, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 5.0192, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0720037896731407, | |
| "grad_norm": 1.1001461744308472, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 4.9702, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.07579346281383231, | |
| "grad_norm": 1.3348885774612427, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 5.0232, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07958313595452392, | |
| "grad_norm": 1.5157945156097412, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 4.7808, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.08337280909521554, | |
| "grad_norm": 1.5866591930389404, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 4.7957, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.08716248223590715, | |
| "grad_norm": 1.6837295293807983, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 4.5376, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.09095215537659877, | |
| "grad_norm": 1.8283494710922241, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 3.8775, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.09474182851729038, | |
| "grad_norm": 1.6003742218017578, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 4.1355, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09474182851729038, | |
| "eval_loss": 4.174348831176758, | |
| "eval_runtime": 12.9589, | |
| "eval_samples_per_second": 137.203, | |
| "eval_steps_per_second": 17.208, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.098531501657982, | |
| "grad_norm": 1.338786244392395, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6085, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.10232117479867361, | |
| "grad_norm": 1.6358585357666016, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 2.5005, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.10611084793936523, | |
| "grad_norm": 1.4135583639144897, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 3.917, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.10990052108005685, | |
| "grad_norm": 1.4380085468292236, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 4.5706, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.11369019422074846, | |
| "grad_norm": 1.3726202249526978, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 4.7089, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11747986736144007, | |
| "grad_norm": 1.3679202795028687, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 4.9696, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.12126954050213169, | |
| "grad_norm": 1.321190595626831, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 4.851, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1250592136428233, | |
| "grad_norm": 1.140480399131775, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 4.8612, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.12884888678351492, | |
| "grad_norm": 1.1631203889846802, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 4.8108, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.13263855992420653, | |
| "grad_norm": 1.0778998136520386, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 4.8189, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.13642823306489815, | |
| "grad_norm": 1.1311537027359009, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 4.3828, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.14021790620558977, | |
| "grad_norm": 1.38828706741333, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 3.9515, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.1440075793462814, | |
| "grad_norm": 0.7054423093795776, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.7414, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.147797252486973, | |
| "grad_norm": 0.8138367533683777, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.888, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.15158692562766463, | |
| "grad_norm": 0.8110458254814148, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 3.0565, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.15537659876835622, | |
| "grad_norm": 0.8825802803039551, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 4.4384, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.15916627190904784, | |
| "grad_norm": 0.8777433037757874, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 4.6368, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.16295594504973945, | |
| "grad_norm": 0.827991247177124, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 4.7561, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.16674561819043107, | |
| "grad_norm": 0.8807438015937805, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 4.9173, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1705352913311227, | |
| "grad_norm": 0.8597086668014526, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 4.9188, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1743249644718143, | |
| "grad_norm": 0.9487287998199463, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 4.7576, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.17811463761250593, | |
| "grad_norm": 1.1659538745880127, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 4.5699, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.18190431075319755, | |
| "grad_norm": 1.2881485223770142, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 4.1091, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.18569398389388916, | |
| "grad_norm": 1.6247484683990479, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 3.8837, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.18948365703458075, | |
| "grad_norm": 1.713950276374817, | |
| "learning_rate": 0.0, | |
| "loss": 3.9417, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.18948365703458075, | |
| "eval_loss": 4.119277477264404, | |
| "eval_runtime": 12.9421, | |
| "eval_samples_per_second": 137.382, | |
| "eval_steps_per_second": 17.231, | |
| "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 | |
| } | |