| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006916346785627831, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00013832693571255662, | |
| "grad_norm": 0.7460320591926575, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.0622, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00013832693571255662, | |
| "eval_loss": 0.3660264313220978, | |
| "eval_runtime": 470.1985, | |
| "eval_samples_per_second": 25.895, | |
| "eval_steps_per_second": 12.948, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00027665387142511324, | |
| "grad_norm": 0.5172986388206482, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.0654, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00041498080713766987, | |
| "grad_norm": 0.3715982437133789, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0601, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005533077428502265, | |
| "grad_norm": 0.22900886833667755, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 0.1241, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0006916346785627831, | |
| "grad_norm": 0.15617172420024872, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 0.1584, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008299616142753397, | |
| "grad_norm": 0.22854697704315186, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.2273, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0009682885499878964, | |
| "grad_norm": 0.2444339096546173, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 0.1921, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.001106615485700453, | |
| "grad_norm": 0.21913830935955048, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 0.2113, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0012449424214130097, | |
| "grad_norm": 0.1947929710149765, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.231, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0013832693571255662, | |
| "grad_norm": 0.18104974925518036, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 0.2594, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001521596292838123, | |
| "grad_norm": 0.18011099100112915, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.2716, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0016599232285506795, | |
| "grad_norm": 0.2006697952747345, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.3017, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0017982501642632362, | |
| "grad_norm": 0.19725461304187775, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 0.3147, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0019365770999757927, | |
| "grad_norm": 0.20050567388534546, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 0.3898, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0020749040356883492, | |
| "grad_norm": 0.18300771713256836, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.2822, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002213230971400906, | |
| "grad_norm": 0.16420985758304596, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 0.2893, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0023515579071134627, | |
| "grad_norm": 0.1584509164094925, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 0.283, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0024898848428260194, | |
| "grad_norm": 0.18125592172145844, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.3069, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0026282117785385757, | |
| "grad_norm": 0.16136623919010162, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.2682, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0027665387142511324, | |
| "grad_norm": 0.14875389635562897, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 0.2303, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002904865649963689, | |
| "grad_norm": 0.15708525478839874, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.2628, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.003043192585676246, | |
| "grad_norm": 0.16460222005844116, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 0.2652, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0031815195213888026, | |
| "grad_norm": 0.15555903315544128, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 0.2429, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.003319846457101359, | |
| "grad_norm": 0.18757903575897217, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.3733, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0034581733928139157, | |
| "grad_norm": 0.18898479640483856, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 0.301, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0034581733928139157, | |
| "eval_loss": 0.26305505633354187, | |
| "eval_runtime": 469.7372, | |
| "eval_samples_per_second": 25.921, | |
| "eval_steps_per_second": 12.96, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0035965003285264724, | |
| "grad_norm": 0.19418561458587646, | |
| "learning_rate": 7.68649804173412e-05, | |
| "loss": 0.3394, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.003734827264239029, | |
| "grad_norm": 0.17552641034126282, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.3258, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0038731541999515854, | |
| "grad_norm": 0.19901876151561737, | |
| "learning_rate": 7.308743066175172e-05, | |
| "loss": 0.3147, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.004011481135664142, | |
| "grad_norm": 0.20790669322013855, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 0.3242, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0041498080713766984, | |
| "grad_norm": 0.21712379157543182, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.3609, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004288135007089256, | |
| "grad_norm": 0.1990925520658493, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 0.3226, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.004426461942801812, | |
| "grad_norm": 0.20528583228588104, | |
| "learning_rate": 6.503528997521366e-05, | |
| "loss": 0.319, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.004564788878514369, | |
| "grad_norm": 0.20410776138305664, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.2925, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.004703115814226925, | |
| "grad_norm": 0.19837261736392975, | |
| "learning_rate": 6.0821980696905146e-05, | |
| "loss": 0.2745, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.004841442749939482, | |
| "grad_norm": 0.22647859156131744, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.3222, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.004979769685652039, | |
| "grad_norm": 0.20827357470989227, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.3405, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.005118096621364595, | |
| "grad_norm": 0.22090105712413788, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 0.3558, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.005256423557077151, | |
| "grad_norm": 0.22308292984962463, | |
| "learning_rate": 5.218096936826681e-05, | |
| "loss": 0.3127, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.005394750492789709, | |
| "grad_norm": 0.21499277651309967, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3221, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.005533077428502265, | |
| "grad_norm": 0.24013201892375946, | |
| "learning_rate": 4.781903063173321e-05, | |
| "loss": 0.3376, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.005671404364214822, | |
| "grad_norm": 0.24089254438877106, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 0.2831, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.005809731299927378, | |
| "grad_norm": 0.23052391409873962, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.2879, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.005948058235639935, | |
| "grad_norm": 0.2739996314048767, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.3677, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.006086385171352492, | |
| "grad_norm": 0.2731296718120575, | |
| "learning_rate": 3.917801930309486e-05, | |
| "loss": 0.288, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.006224712107065048, | |
| "grad_norm": 0.26021909713745117, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.2641, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.006363039042777605, | |
| "grad_norm": 0.2645817995071411, | |
| "learning_rate": 3.4964710024786354e-05, | |
| "loss": 0.293, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0065013659784901616, | |
| "grad_norm": 0.30752235651016235, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 0.3216, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.006639692914202718, | |
| "grad_norm": 0.3008212745189667, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.2964, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.006778019849915275, | |
| "grad_norm": 0.3753189146518707, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 0.3555, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.006916346785627831, | |
| "grad_norm": 0.47307515144348145, | |
| "learning_rate": 2.6912569338248315e-05, | |
| "loss": 0.3284, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.006916346785627831, | |
| "eval_loss": 0.24489927291870117, | |
| "eval_runtime": 470.1026, | |
| "eval_samples_per_second": 25.901, | |
| "eval_steps_per_second": 12.95, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9837211652456448.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |