{ "best_metric": 11.935626029968262, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.45454545454545453, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00909090909090909, "grad_norm": 0.01608029194176197, "learning_rate": 5e-05, "loss": 11.9324, "step": 1 }, { "epoch": 0.00909090909090909, "eval_loss": 11.940053939819336, "eval_runtime": 1.5662, "eval_samples_per_second": 473.119, "eval_steps_per_second": 59.379, "step": 1 }, { "epoch": 0.01818181818181818, "grad_norm": 0.02258393168449402, "learning_rate": 0.0001, "loss": 11.9359, "step": 2 }, { "epoch": 0.02727272727272727, "grad_norm": 0.030102215707302094, "learning_rate": 9.989294616193017e-05, "loss": 11.9359, "step": 3 }, { "epoch": 0.03636363636363636, "grad_norm": 0.032274406403303146, "learning_rate": 9.957224306869053e-05, "loss": 11.9355, "step": 4 }, { "epoch": 0.045454545454545456, "grad_norm": 0.03438561409711838, "learning_rate": 9.903926402016153e-05, "loss": 11.9362, "step": 5 }, { "epoch": 0.05454545454545454, "grad_norm": 0.04045461118221283, "learning_rate": 9.829629131445342e-05, "loss": 11.9368, "step": 6 }, { "epoch": 0.06363636363636363, "grad_norm": 0.047913480550050735, "learning_rate": 9.73465064747553e-05, "loss": 11.9366, "step": 7 }, { "epoch": 0.07272727272727272, "grad_norm": 0.053709082305431366, "learning_rate": 9.619397662556435e-05, "loss": 11.9372, "step": 8 }, { "epoch": 0.08181818181818182, "grad_norm": 0.0566636361181736, "learning_rate": 9.484363707663442e-05, "loss": 11.9387, "step": 9 }, { "epoch": 0.09090909090909091, "grad_norm": 0.08057867735624313, "learning_rate": 9.330127018922194e-05, "loss": 11.9402, "step": 10 }, { "epoch": 0.1, "grad_norm": 0.10093028843402863, "learning_rate": 9.157348061512727e-05, "loss": 11.9424, "step": 11 }, { "epoch": 0.10909090909090909, "grad_norm": 0.14354851841926575, "learning_rate": 8.966766701456177e-05, "loss": 11.9462, "step": 12 }, { "epoch": 0.11818181818181818, "grad_norm": 0.027024338021874428, "learning_rate": 8.759199037394887e-05, "loss": 11.9336, "step": 13 }, { "epoch": 0.12727272727272726, "grad_norm": 0.02432507835328579, "learning_rate": 8.535533905932738e-05, "loss": 11.9336, "step": 14 }, { "epoch": 0.13636363636363635, "grad_norm": 0.02735907770693302, "learning_rate": 8.296729075500344e-05, "loss": 11.9341, "step": 15 }, { "epoch": 0.14545454545454545, "grad_norm": 0.03903603553771973, "learning_rate": 8.043807145043604e-05, "loss": 11.935, "step": 16 }, { "epoch": 0.15454545454545454, "grad_norm": 0.048470769077539444, "learning_rate": 7.777851165098012e-05, "loss": 11.9355, "step": 17 }, { "epoch": 0.16363636363636364, "grad_norm": 0.04781801626086235, "learning_rate": 7.500000000000001e-05, "loss": 11.9348, "step": 18 }, { "epoch": 0.17272727272727273, "grad_norm": 0.05441196262836456, "learning_rate": 7.211443451095007e-05, "loss": 11.936, "step": 19 }, { "epoch": 0.18181818181818182, "grad_norm": 0.06806536018848419, "learning_rate": 6.91341716182545e-05, "loss": 11.9368, "step": 20 }, { "epoch": 0.19090909090909092, "grad_norm": 0.0760565996170044, "learning_rate": 6.607197326515808e-05, "loss": 11.9363, "step": 21 }, { "epoch": 0.2, "grad_norm": 0.09045607596635818, "learning_rate": 6.294095225512603e-05, "loss": 11.9379, "step": 22 }, { "epoch": 0.20909090909090908, "grad_norm": 0.11760573089122772, "learning_rate": 5.9754516100806423e-05, "loss": 11.9389, "step": 23 }, { "epoch": 0.21818181818181817, "grad_norm": 0.1573444902896881, "learning_rate": 5.6526309611002594e-05, "loss": 11.9414, "step": 24 }, { "epoch": 0.22727272727272727, "grad_norm": 0.22445236146450043, "learning_rate": 5.327015646150716e-05, "loss": 11.9451, "step": 25 }, { "epoch": 0.22727272727272727, "eval_loss": 11.936861991882324, "eval_runtime": 1.5784, "eval_samples_per_second": 469.454, "eval_steps_per_second": 58.919, "step": 25 }, { "epoch": 0.23636363636363636, "grad_norm": 0.0292927585542202, "learning_rate": 5e-05, "loss": 11.9327, "step": 26 }, { "epoch": 0.24545454545454545, "grad_norm": 0.03722061589360237, "learning_rate": 4.6729843538492847e-05, "loss": 11.9332, "step": 27 }, { "epoch": 0.2545454545454545, "grad_norm": 0.044527411460876465, "learning_rate": 4.347369038899744e-05, "loss": 11.9345, "step": 28 }, { "epoch": 0.2636363636363636, "grad_norm": 0.053151361644268036, "learning_rate": 4.0245483899193595e-05, "loss": 11.9343, "step": 29 }, { "epoch": 0.2727272727272727, "grad_norm": 0.06710100173950195, "learning_rate": 3.705904774487396e-05, "loss": 11.9334, "step": 30 }, { "epoch": 0.2818181818181818, "grad_norm": 0.076243557035923, "learning_rate": 3.392802673484193e-05, "loss": 11.9344, "step": 31 }, { "epoch": 0.2909090909090909, "grad_norm": 0.08258321136236191, "learning_rate": 3.086582838174551e-05, "loss": 11.9334, "step": 32 }, { "epoch": 0.3, "grad_norm": 0.09955097734928131, "learning_rate": 2.7885565489049946e-05, "loss": 11.9343, "step": 33 }, { "epoch": 0.3090909090909091, "grad_norm": 0.1071547418832779, "learning_rate": 2.500000000000001e-05, "loss": 11.9362, "step": 34 }, { "epoch": 0.3181818181818182, "grad_norm": 0.1243717148900032, "learning_rate": 2.2221488349019903e-05, "loss": 11.9368, "step": 35 }, { "epoch": 0.32727272727272727, "grad_norm": 0.16296078264713287, "learning_rate": 1.9561928549563968e-05, "loss": 11.9391, "step": 36 }, { "epoch": 0.33636363636363636, "grad_norm": 0.21441270411014557, "learning_rate": 1.703270924499656e-05, "loss": 11.9406, "step": 37 }, { "epoch": 0.34545454545454546, "grad_norm": 0.04862441122531891, "learning_rate": 1.4644660940672627e-05, "loss": 11.9328, "step": 38 }, { "epoch": 0.35454545454545455, "grad_norm": 0.04332125559449196, "learning_rate": 1.2408009626051137e-05, "loss": 11.9323, "step": 39 }, { "epoch": 0.36363636363636365, "grad_norm": 0.05594014376401901, "learning_rate": 1.0332332985438248e-05, "loss": 11.934, "step": 40 }, { "epoch": 0.37272727272727274, "grad_norm": 0.05566423013806343, "learning_rate": 8.426519384872733e-06, "loss": 11.9332, "step": 41 }, { "epoch": 0.38181818181818183, "grad_norm": 0.07062508165836334, "learning_rate": 6.698729810778065e-06, "loss": 11.9331, "step": 42 }, { "epoch": 0.39090909090909093, "grad_norm": 0.07907385379076004, "learning_rate": 5.156362923365588e-06, "loss": 11.9336, "step": 43 }, { "epoch": 0.4, "grad_norm": 0.07872168719768524, "learning_rate": 3.8060233744356633e-06, "loss": 11.9339, "step": 44 }, { "epoch": 0.4090909090909091, "grad_norm": 0.10365702956914902, "learning_rate": 2.653493525244721e-06, "loss": 11.9346, "step": 45 }, { "epoch": 0.41818181818181815, "grad_norm": 0.11274810880422592, "learning_rate": 1.70370868554659e-06, "loss": 11.9352, "step": 46 }, { "epoch": 0.42727272727272725, "grad_norm": 0.1331714540719986, "learning_rate": 9.607359798384785e-07, "loss": 11.9345, "step": 47 }, { "epoch": 0.43636363636363634, "grad_norm": 0.1528213769197464, "learning_rate": 4.277569313094809e-07, "loss": 11.9377, "step": 48 }, { "epoch": 0.44545454545454544, "grad_norm": 0.20465974509716034, "learning_rate": 1.0705383806982606e-07, "loss": 11.9391, "step": 49 }, { "epoch": 0.45454545454545453, "grad_norm": 0.28759765625, "learning_rate": 0.0, "loss": 11.9426, "step": 50 }, { "epoch": 0.45454545454545453, "eval_loss": 11.935626029968262, "eval_runtime": 1.5987, "eval_samples_per_second": 463.505, "eval_steps_per_second": 58.173, "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": 1046077833216.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }