| { | |
| "best_metric": 1.7794197797775269, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.06406149903907751, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012812299807815502, | |
| "grad_norm": 1.0244836807250977, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2082, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012812299807815502, | |
| "eval_loss": 2.5637834072113037, | |
| "eval_runtime": 59.3261, | |
| "eval_samples_per_second": 88.629, | |
| "eval_steps_per_second": 11.091, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0025624599615631004, | |
| "grad_norm": 1.187942385673523, | |
| "learning_rate": 0.0001, | |
| "loss": 2.3303, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003843689942344651, | |
| "grad_norm": 1.2177941799163818, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.4246, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005124919923126201, | |
| "grad_norm": 1.1537481546401978, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.207, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0064061499039077515, | |
| "grad_norm": 1.2492258548736572, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.1005, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007687379884689302, | |
| "grad_norm": 0.7698009610176086, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.9847, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008968609865470852, | |
| "grad_norm": 0.7553490400314331, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.9535, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010249839846252402, | |
| "grad_norm": 0.6572031378746033, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.0092, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.011531069827033953, | |
| "grad_norm": 0.6678457856178284, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.0178, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012812299807815503, | |
| "grad_norm": 0.6247608065605164, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.8962, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014093529788597053, | |
| "grad_norm": 0.6198277473449707, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.9442, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.015374759769378604, | |
| "grad_norm": 0.6582549810409546, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.846, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.016655989750160152, | |
| "grad_norm": 0.6814655661582947, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.8514, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.017937219730941704, | |
| "grad_norm": 0.7516040205955505, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.7569, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.019218449711723255, | |
| "grad_norm": 0.6319171786308289, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.7732, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.020499679692504803, | |
| "grad_norm": 0.5802849531173706, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.793, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.021780909673286355, | |
| "grad_norm": 0.5104497671127319, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.8069, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.023062139654067906, | |
| "grad_norm": 0.4878818988800049, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.8869, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.024343369634849454, | |
| "grad_norm": 0.4552346467971802, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.7964, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.025624599615631006, | |
| "grad_norm": 0.44769924879074097, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.8788, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.026905829596412557, | |
| "grad_norm": 0.4843851923942566, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.8568, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.028187059577194105, | |
| "grad_norm": 0.5058475136756897, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.9361, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.029468289557975657, | |
| "grad_norm": 0.5572724938392639, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.8221, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03074951953875721, | |
| "grad_norm": 0.5803532004356384, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.8784, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.032030749519538756, | |
| "grad_norm": 0.8900609016418457, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.8837, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.032030749519538756, | |
| "eval_loss": 1.797715187072754, | |
| "eval_runtime": 59.4126, | |
| "eval_samples_per_second": 88.5, | |
| "eval_steps_per_second": 11.075, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.033311979500320305, | |
| "grad_norm": 0.42451655864715576, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7534, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03459320948110186, | |
| "grad_norm": 0.4029790759086609, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.6702, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03587443946188341, | |
| "grad_norm": 0.4106031656265259, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.7286, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.037155669442664956, | |
| "grad_norm": 0.40695980191230774, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.7776, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.03843689942344651, | |
| "grad_norm": 0.41555243730545044, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.8432, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03971812940422806, | |
| "grad_norm": 0.4222233295440674, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.7395, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.04099935938500961, | |
| "grad_norm": 0.4671240448951721, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.7829, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.04228058936579116, | |
| "grad_norm": 0.40571528673171997, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.8406, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.04356181934657271, | |
| "grad_norm": 0.4159633219242096, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.84, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.04484304932735426, | |
| "grad_norm": 0.4444989562034607, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.7806, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04612427930813581, | |
| "grad_norm": 0.44324401021003723, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.8427, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04740550928891736, | |
| "grad_norm": 0.5288540720939636, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.8759, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.04868673926969891, | |
| "grad_norm": 0.4690561294555664, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.7791, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.049967969250480464, | |
| "grad_norm": 0.41271162033081055, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.6678, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.05124919923126201, | |
| "grad_norm": 0.398227721452713, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.7866, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05253042921204356, | |
| "grad_norm": 0.4064875841140747, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.8097, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.053811659192825115, | |
| "grad_norm": 0.3928537368774414, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.6876, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.05509288917360666, | |
| "grad_norm": 0.3979778289794922, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.8318, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.05637411915438821, | |
| "grad_norm": 0.38359037041664124, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.8171, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.057655349135169766, | |
| "grad_norm": 0.40605178475379944, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.829, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.058936579115951314, | |
| "grad_norm": 0.3973970413208008, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.8294, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.06021780909673286, | |
| "grad_norm": 0.4090547263622284, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.8194, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.06149903907751442, | |
| "grad_norm": 0.41120144724845886, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.7599, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06278026905829596, | |
| "grad_norm": 0.46502575278282166, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.7705, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06406149903907751, | |
| "grad_norm": 0.6171591281890869, | |
| "learning_rate": 0.0, | |
| "loss": 1.807, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06406149903907751, | |
| "eval_loss": 1.7794197797775269, | |
| "eval_runtime": 59.439, | |
| "eval_samples_per_second": 88.46, | |
| "eval_steps_per_second": 11.07, | |
| "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": 1.059536353886208e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |