{ "best_metric": 0.8159454464912415, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.29895366218236175, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.005979073243647235, "grad_norm": 1.0753231048583984, "learning_rate": 5e-05, "loss": 2.6085, "step": 1 }, { "epoch": 0.005979073243647235, "eval_loss": 2.679072380065918, "eval_runtime": 9.2659, "eval_samples_per_second": 121.629, "eval_steps_per_second": 15.217, "step": 1 }, { "epoch": 0.01195814648729447, "grad_norm": 1.1164913177490234, "learning_rate": 0.0001, "loss": 2.606, "step": 2 }, { "epoch": 0.017937219730941704, "grad_norm": 1.1199455261230469, "learning_rate": 9.989294616193017e-05, "loss": 2.5675, "step": 3 }, { "epoch": 0.02391629297458894, "grad_norm": 1.0659465789794922, "learning_rate": 9.957224306869053e-05, "loss": 2.4704, "step": 4 }, { "epoch": 0.029895366218236172, "grad_norm": 1.0874993801116943, "learning_rate": 9.903926402016153e-05, "loss": 2.3747, "step": 5 }, { "epoch": 0.03587443946188341, "grad_norm": 1.0592572689056396, "learning_rate": 9.829629131445342e-05, "loss": 2.1872, "step": 6 }, { "epoch": 0.04185351270553064, "grad_norm": 1.0288424491882324, "learning_rate": 9.73465064747553e-05, "loss": 2.0218, "step": 7 }, { "epoch": 0.04783258594917788, "grad_norm": 0.964034914970398, "learning_rate": 9.619397662556435e-05, "loss": 1.8934, "step": 8 }, { "epoch": 0.053811659192825115, "grad_norm": 0.9067386388778687, "learning_rate": 9.484363707663442e-05, "loss": 1.7613, "step": 9 }, { "epoch": 0.059790732436472344, "grad_norm": 0.875987708568573, "learning_rate": 9.330127018922194e-05, "loss": 1.7118, "step": 10 }, { "epoch": 0.06576980568011959, "grad_norm": 0.8584564328193665, "learning_rate": 9.157348061512727e-05, "loss": 1.7108, "step": 11 }, { "epoch": 0.07174887892376682, "grad_norm": 0.8755573630332947, "learning_rate": 8.966766701456177e-05, "loss": 1.6767, "step": 12 }, { "epoch": 0.07772795216741404, "grad_norm": 0.7942352890968323, "learning_rate": 8.759199037394887e-05, "loss": 1.5869, "step": 13 }, { "epoch": 0.08370702541106129, "grad_norm": 0.7313013672828674, "learning_rate": 8.535533905932738e-05, "loss": 1.3916, "step": 14 }, { "epoch": 0.08968609865470852, "grad_norm": 0.7297770380973816, "learning_rate": 8.296729075500344e-05, "loss": 1.2703, "step": 15 }, { "epoch": 0.09566517189835576, "grad_norm": 0.7625865340232849, "learning_rate": 8.043807145043604e-05, "loss": 1.2765, "step": 16 }, { "epoch": 0.10164424514200299, "grad_norm": 0.7098815441131592, "learning_rate": 7.777851165098012e-05, "loss": 1.1746, "step": 17 }, { "epoch": 0.10762331838565023, "grad_norm": 0.6497551202774048, "learning_rate": 7.500000000000001e-05, "loss": 1.1205, "step": 18 }, { "epoch": 0.11360239162929746, "grad_norm": 0.5867015719413757, "learning_rate": 7.211443451095007e-05, "loss": 1.0144, "step": 19 }, { "epoch": 0.11958146487294469, "grad_norm": 0.6049321889877319, "learning_rate": 6.91341716182545e-05, "loss": 1.0283, "step": 20 }, { "epoch": 0.12556053811659193, "grad_norm": 0.6885931491851807, "learning_rate": 6.607197326515808e-05, "loss": 1.0738, "step": 21 }, { "epoch": 0.13153961136023917, "grad_norm": 0.6182365417480469, "learning_rate": 6.294095225512603e-05, "loss": 1.0135, "step": 22 }, { "epoch": 0.1375186846038864, "grad_norm": 0.6049491763114929, "learning_rate": 5.9754516100806423e-05, "loss": 0.9173, "step": 23 }, { "epoch": 0.14349775784753363, "grad_norm": 0.6933227777481079, "learning_rate": 5.6526309611002594e-05, "loss": 1.0891, "step": 24 }, { "epoch": 0.14947683109118087, "grad_norm": 0.7998446226119995, "learning_rate": 5.327015646150716e-05, "loss": 1.1267, "step": 25 }, { "epoch": 0.14947683109118087, "eval_loss": 0.9570152163505554, "eval_runtime": 9.2344, "eval_samples_per_second": 122.044, "eval_steps_per_second": 15.269, "step": 25 }, { "epoch": 0.1554559043348281, "grad_norm": 0.6872985363006592, "learning_rate": 5e-05, "loss": 1.029, "step": 26 }, { "epoch": 0.16143497757847533, "grad_norm": 0.632942259311676, "learning_rate": 4.6729843538492847e-05, "loss": 0.9259, "step": 27 }, { "epoch": 0.16741405082212257, "grad_norm": 0.5986387133598328, "learning_rate": 4.347369038899744e-05, "loss": 0.8612, "step": 28 }, { "epoch": 0.17339312406576982, "grad_norm": 0.6099429130554199, "learning_rate": 4.0245483899193595e-05, "loss": 0.8646, "step": 29 }, { "epoch": 0.17937219730941703, "grad_norm": 0.5303110480308533, "learning_rate": 3.705904774487396e-05, "loss": 0.8294, "step": 30 }, { "epoch": 0.18535127055306427, "grad_norm": 0.5066549777984619, "learning_rate": 3.392802673484193e-05, "loss": 0.8879, "step": 31 }, { "epoch": 0.19133034379671152, "grad_norm": 0.530630350112915, "learning_rate": 3.086582838174551e-05, "loss": 0.8317, "step": 32 }, { "epoch": 0.19730941704035873, "grad_norm": 0.3913431465625763, "learning_rate": 2.7885565489049946e-05, "loss": 0.8476, "step": 33 }, { "epoch": 0.20328849028400597, "grad_norm": 0.38945111632347107, "learning_rate": 2.500000000000001e-05, "loss": 0.8998, "step": 34 }, { "epoch": 0.20926756352765322, "grad_norm": 0.36714988946914673, "learning_rate": 2.2221488349019903e-05, "loss": 0.7483, "step": 35 }, { "epoch": 0.21524663677130046, "grad_norm": 0.41465187072753906, "learning_rate": 1.9561928549563968e-05, "loss": 0.8728, "step": 36 }, { "epoch": 0.22122571001494767, "grad_norm": 0.5536110401153564, "learning_rate": 1.703270924499656e-05, "loss": 0.9151, "step": 37 }, { "epoch": 0.22720478325859492, "grad_norm": 0.6803256869316101, "learning_rate": 1.4644660940672627e-05, "loss": 1.0324, "step": 38 }, { "epoch": 0.23318385650224216, "grad_norm": 0.38136497139930725, "learning_rate": 1.2408009626051137e-05, "loss": 0.7947, "step": 39 }, { "epoch": 0.23916292974588937, "grad_norm": 0.39119410514831543, "learning_rate": 1.0332332985438248e-05, "loss": 0.7218, "step": 40 }, { "epoch": 0.24514200298953662, "grad_norm": 0.3474106192588806, "learning_rate": 8.426519384872733e-06, "loss": 0.762, "step": 41 }, { "epoch": 0.25112107623318386, "grad_norm": 0.3799263834953308, "learning_rate": 6.698729810778065e-06, "loss": 0.7763, "step": 42 }, { "epoch": 0.2571001494768311, "grad_norm": 0.34402114152908325, "learning_rate": 5.156362923365588e-06, "loss": 0.7772, "step": 43 }, { "epoch": 0.26307922272047835, "grad_norm": 0.31651434302330017, "learning_rate": 3.8060233744356633e-06, "loss": 0.7316, "step": 44 }, { "epoch": 0.26905829596412556, "grad_norm": 0.33870384097099304, "learning_rate": 2.653493525244721e-06, "loss": 0.8084, "step": 45 }, { "epoch": 0.2750373692077728, "grad_norm": 0.32227766513824463, "learning_rate": 1.70370868554659e-06, "loss": 0.8132, "step": 46 }, { "epoch": 0.28101644245142005, "grad_norm": 0.31585749983787537, "learning_rate": 9.607359798384785e-07, "loss": 0.7976, "step": 47 }, { "epoch": 0.28699551569506726, "grad_norm": 0.32487156987190247, "learning_rate": 4.277569313094809e-07, "loss": 0.8213, "step": 48 }, { "epoch": 0.2929745889387145, "grad_norm": 0.40243586897850037, "learning_rate": 1.0705383806982606e-07, "loss": 0.8709, "step": 49 }, { "epoch": 0.29895366218236175, "grad_norm": 0.5789146423339844, "learning_rate": 0.0, "loss": 0.9765, "step": 50 }, { "epoch": 0.29895366218236175, "eval_loss": 0.8159454464912415, "eval_runtime": 9.2521, "eval_samples_per_second": 121.81, "eval_steps_per_second": 15.24, "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": 8.396670163641958e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }