| { | |
| "best_metric": 6.917191028594971, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.1621621621621623, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.043243243243243246, | |
| "grad_norm": 0.12368408590555191, | |
| "learning_rate": 5e-05, | |
| "loss": 6.9372, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.043243243243243246, | |
| "eval_loss": 6.937686920166016, | |
| "eval_runtime": 0.1284, | |
| "eval_samples_per_second": 1215.029, | |
| "eval_steps_per_second": 155.773, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08648648648648649, | |
| "grad_norm": 0.11058807373046875, | |
| "learning_rate": 0.0001, | |
| "loss": 6.9388, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.12972972972972974, | |
| "grad_norm": 0.11697812378406525, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 6.937, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.17297297297297298, | |
| "grad_norm": 0.1206204742193222, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 6.9377, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.21621621621621623, | |
| "grad_norm": 0.12281688302755356, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 6.9352, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2594594594594595, | |
| "grad_norm": 0.16030272841453552, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 6.933, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3027027027027027, | |
| "grad_norm": 0.10940645635128021, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 6.9347, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.34594594594594597, | |
| "grad_norm": 0.11407100409269333, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 6.9353, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3891891891891892, | |
| "grad_norm": 0.1260599046945572, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 6.9339, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.43243243243243246, | |
| "grad_norm": 0.12227915972471237, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 6.9325, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4756756756756757, | |
| "grad_norm": 0.129599466919899, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 6.9295, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.518918918918919, | |
| "grad_norm": 0.1695713847875595, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 6.9278, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5621621621621622, | |
| "grad_norm": 0.11723753809928894, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 6.9322, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.6054054054054054, | |
| "grad_norm": 0.12526081502437592, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 6.9299, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.6486486486486487, | |
| "grad_norm": 0.13085179030895233, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 6.9283, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6918918918918919, | |
| "grad_norm": 0.12904198467731476, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 6.9278, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.7351351351351352, | |
| "grad_norm": 0.13451868295669556, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 6.9272, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.7783783783783784, | |
| "grad_norm": 0.16107550263404846, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 6.925, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.8216216216216217, | |
| "grad_norm": 0.12943188846111298, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 6.9278, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.8648648648648649, | |
| "grad_norm": 0.12963256239891052, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 6.9268, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.9081081081081082, | |
| "grad_norm": 0.13904154300689697, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 6.9253, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.9513513513513514, | |
| "grad_norm": 0.1439041644334793, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 6.9235, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.9945945945945946, | |
| "grad_norm": 0.14458626508712769, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 6.9223, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.037837837837838, | |
| "grad_norm": 0.25089070200920105, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 13.1139, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.0810810810810811, | |
| "grad_norm": 0.13710176944732666, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 6.8319, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0810810810810811, | |
| "eval_loss": 6.922355651855469, | |
| "eval_runtime": 0.131, | |
| "eval_samples_per_second": 1190.662, | |
| "eval_steps_per_second": 152.649, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.1243243243243244, | |
| "grad_norm": 0.14169707894325256, | |
| "learning_rate": 5e-05, | |
| "loss": 6.9437, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.1675675675675676, | |
| "grad_norm": 0.15641377866268158, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 6.9905, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.2108108108108109, | |
| "grad_norm": 0.1642267405986786, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 6.8949, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.2540540540540541, | |
| "grad_norm": 0.1128983348608017, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 5.5863, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.2972972972972974, | |
| "grad_norm": 0.16381703317165375, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 8.229, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.3405405405405406, | |
| "grad_norm": 0.14603477716445923, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 6.893, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.3837837837837839, | |
| "grad_norm": 0.16026656329631805, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 6.9852, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.427027027027027, | |
| "grad_norm": 0.1536598801612854, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 6.9091, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.4702702702702704, | |
| "grad_norm": 0.15081219375133514, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 6.9582, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.5135135135135136, | |
| "grad_norm": 0.1353471279144287, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 6.4464, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.5567567567567568, | |
| "grad_norm": 0.1591843217611313, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 7.344, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.15149177610874176, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 6.8545, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.6432432432432433, | |
| "grad_norm": 0.15297028422355652, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 6.97, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.6864864864864866, | |
| "grad_norm": 0.1657475382089615, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 6.996, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.7297297297297298, | |
| "grad_norm": 0.16660283505916595, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 6.991, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.772972972972973, | |
| "grad_norm": 0.16040071845054626, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 6.5794, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.8162162162162163, | |
| "grad_norm": 0.15271268784999847, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 7.0738, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.8594594594594596, | |
| "grad_norm": 0.14652898907661438, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 6.9184, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.9027027027027028, | |
| "grad_norm": 0.16251295804977417, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 6.9841, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.945945945945946, | |
| "grad_norm": 0.15599997341632843, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 6.9053, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.9891891891891893, | |
| "grad_norm": 0.17976956069469452, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 7.2866, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.0324324324324325, | |
| "grad_norm": 0.3074623942375183, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 12.6789, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.075675675675676, | |
| "grad_norm": 0.14891654253005981, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 6.8518, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.118918918918919, | |
| "grad_norm": 0.15843117237091064, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 6.8739, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.1621621621621623, | |
| "grad_norm": 0.1670803725719452, | |
| "learning_rate": 0.0, | |
| "loss": 7.058, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.1621621621621623, | |
| "eval_loss": 6.917191028594971, | |
| "eval_runtime": 0.1313, | |
| "eval_samples_per_second": 1188.467, | |
| "eval_steps_per_second": 152.368, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 5755884503040.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |