| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.023937761819269897, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003191701575902653, | |
| "grad_norm": 74.66423797607422, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 11.8509, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003191701575902653, | |
| "eval_loss": 12.318764686584473, | |
| "eval_runtime": 286.3176, | |
| "eval_samples_per_second": 36.861, | |
| "eval_steps_per_second": 4.61, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006383403151805306, | |
| "grad_norm": 71.02066802978516, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 11.9938, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0009575104727707959, | |
| "grad_norm": 59.003684997558594, | |
| "learning_rate": 0.0001, | |
| "loss": 9.6107, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0012766806303610612, | |
| "grad_norm": 73.98766326904297, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 3.6539, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0015958507879513266, | |
| "grad_norm": 7.199901580810547, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 0.8517, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0019150209455415918, | |
| "grad_norm": 3.2114429473876953, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.1353, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002234191103131857, | |
| "grad_norm": 108.24579620361328, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 3.1604, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0025533612607221224, | |
| "grad_norm": 14.213573455810547, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 0.293, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002872531418312388, | |
| "grad_norm": 3.7268381118774414, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.2232, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003191701575902653, | |
| "grad_norm": 1.227923035621643, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 0.0856, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0035108717334929184, | |
| "grad_norm": 14.622164726257324, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.3813, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0038300418910831835, | |
| "grad_norm": 5.4367194175720215, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.1709, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004149212048673449, | |
| "grad_norm": 1.4004822969436646, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 0.1118, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.004468382206263714, | |
| "grad_norm": 0.2667771279811859, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 0.0067, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0047875523638539795, | |
| "grad_norm": 2.9109885692596436, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.2121, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005106722521444245, | |
| "grad_norm": 1.8067930936813354, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 0.1049, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00542589267903451, | |
| "grad_norm": 0.8027642965316772, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 0.0282, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.005745062836624776, | |
| "grad_norm": 1.0130234956741333, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.0292, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.006064232994215041, | |
| "grad_norm": 1.2449007034301758, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.0761, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.006383403151805306, | |
| "grad_norm": 1.0734630823135376, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 0.0299, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0067025733093955715, | |
| "grad_norm": 0.5908615589141846, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0137, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.007021743466985837, | |
| "grad_norm": 0.6940059661865234, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 0.0322, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.007340913624576102, | |
| "grad_norm": 1.4336614608764648, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 0.1108, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.007660083782166367, | |
| "grad_norm": 2.7778196334838867, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.0822, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.007979253939756632, | |
| "grad_norm": 1.1669725179672241, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 0.0476, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007979253939756632, | |
| "eval_loss": 0.03445420786738396, | |
| "eval_runtime": 286.9529, | |
| "eval_samples_per_second": 36.78, | |
| "eval_steps_per_second": 4.6, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.008298424097346898, | |
| "grad_norm": 1.6094774007797241, | |
| "learning_rate": 7.68649804173412e-05, | |
| "loss": 0.0902, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.008617594254937163, | |
| "grad_norm": 0.9928753972053528, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0321, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.008936764412527429, | |
| "grad_norm": 0.8845332264900208, | |
| "learning_rate": 7.308743066175172e-05, | |
| "loss": 0.0358, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.009255934570117695, | |
| "grad_norm": 0.6543906331062317, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 0.0209, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.009575104727707959, | |
| "grad_norm": 0.648944079875946, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0231, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.009894274885298225, | |
| "grad_norm": 1.3208541870117188, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 0.06, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.01021344504288849, | |
| "grad_norm": 0.25852757692337036, | |
| "learning_rate": 6.503528997521366e-05, | |
| "loss": 0.0066, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.010532615200478756, | |
| "grad_norm": 0.7767801284790039, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.0324, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.01085178535806902, | |
| "grad_norm": 0.7248371243476868, | |
| "learning_rate": 6.0821980696905146e-05, | |
| "loss": 0.0134, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.011170955515659286, | |
| "grad_norm": 0.9914122223854065, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.0302, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.011490125673249552, | |
| "grad_norm": 0.7037466764450073, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.0148, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.011809295830839816, | |
| "grad_norm": 0.8041982650756836, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 0.0064, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.012128465988430082, | |
| "grad_norm": 0.8569905757904053, | |
| "learning_rate": 5.218096936826681e-05, | |
| "loss": 0.0107, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.012447636146020347, | |
| "grad_norm": 0.8578211665153503, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0098, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.012766806303610613, | |
| "grad_norm": 1.557311773300171, | |
| "learning_rate": 4.781903063173321e-05, | |
| "loss": 0.0157, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.013085976461200877, | |
| "grad_norm": 1.648313283920288, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 0.036, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.013405146618791143, | |
| "grad_norm": 1.1188888549804688, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.0183, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.013724316776381409, | |
| "grad_norm": 0.10944560170173645, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.0013, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.014043486933971673, | |
| "grad_norm": 0.8294479846954346, | |
| "learning_rate": 3.917801930309486e-05, | |
| "loss": 0.0061, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.01436265709156194, | |
| "grad_norm": 0.2965063452720642, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0023, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.014681827249152204, | |
| "grad_norm": 0.07751064747571945, | |
| "learning_rate": 3.4964710024786354e-05, | |
| "loss": 0.0007, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.01500099740674247, | |
| "grad_norm": 2.2420613765716553, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 0.0523, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.015320167564332734, | |
| "grad_norm": 0.05525254085659981, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0009, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.015639337721923, | |
| "grad_norm": 0.6241516470909119, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 0.0039, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.015958507879513265, | |
| "grad_norm": 0.018162360414862633, | |
| "learning_rate": 2.6912569338248315e-05, | |
| "loss": 0.0004, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.015958507879513265, | |
| "eval_loss": 0.03291398659348488, | |
| "eval_runtime": 286.6445, | |
| "eval_samples_per_second": 36.819, | |
| "eval_steps_per_second": 4.605, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.016277678037103532, | |
| "grad_norm": 0.6963501572608948, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0272, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.016596848194693797, | |
| "grad_norm": 1.651873230934143, | |
| "learning_rate": 2.3135019582658802e-05, | |
| "loss": 0.0693, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.01691601835228406, | |
| "grad_norm": 3.7848258018493652, | |
| "learning_rate": 2.132117818244771e-05, | |
| "loss": 0.0339, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.017235188509874325, | |
| "grad_norm": 0.4375050663948059, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.0031, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.017554358667464593, | |
| "grad_norm": 3.5927422046661377, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 0.0997, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.017873528825054857, | |
| "grad_norm": 2.43323016166687, | |
| "learning_rate": 1.622048961921699e-05, | |
| "loss": 0.0267, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.01819269898264512, | |
| "grad_norm": 0.128454327583313, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0019, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.01851186914023539, | |
| "grad_norm": 0.32172662019729614, | |
| "learning_rate": 1.3136133159493802e-05, | |
| "loss": 0.003, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.018831039297825654, | |
| "grad_norm": 2.459465265274048, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 0.02, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.019150209455415918, | |
| "grad_norm": 1.4478123188018799, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0096, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.019469379613006182, | |
| "grad_norm": 1.4985058307647705, | |
| "learning_rate": 9.042397785550405e-06, | |
| "loss": 0.0774, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.01978854977059645, | |
| "grad_norm": 2.816249370574951, | |
| "learning_rate": 7.830427709355725e-06, | |
| "loss": 0.0525, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.020107719928186715, | |
| "grad_norm": 2.870896339416504, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.1261, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.02042689008577698, | |
| "grad_norm": 0.29331719875335693, | |
| "learning_rate": 5.649458341088915e-06, | |
| "loss": 0.0018, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.020746060243367247, | |
| "grad_norm": 2.912463426589966, | |
| "learning_rate": 4.684610648167503e-06, | |
| "loss": 0.0731, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.02106523040095751, | |
| "grad_norm": 1.086990237236023, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0129, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.021384400558547775, | |
| "grad_norm": 3.1444857120513916, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.0484, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.02170357071613804, | |
| "grad_norm": 0.1576186716556549, | |
| "learning_rate": 2.314152462588659e-06, | |
| "loss": 0.0021, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.022022740873728307, | |
| "grad_norm": 1.069075107574463, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0609, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.022341911031318572, | |
| "grad_norm": 1.1245722770690918, | |
| "learning_rate": 1.1851996440033319e-06, | |
| "loss": 0.118, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.022661081188908836, | |
| "grad_norm": 1.8234457969665527, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 0.0816, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.022980251346499104, | |
| "grad_norm": 0.014433772303164005, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0004, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.023299421504089368, | |
| "grad_norm": 2.4126806259155273, | |
| "learning_rate": 1.9026509541272275e-07, | |
| "loss": 0.0283, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.023618591661679633, | |
| "grad_norm": 0.9039496779441833, | |
| "learning_rate": 4.7588920907110094e-08, | |
| "loss": 0.006, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.023937761819269897, | |
| "grad_norm": 1.8179197311401367, | |
| "learning_rate": 0.0, | |
| "loss": 0.0769, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.023937761819269897, | |
| "eval_loss": 0.02614620514214039, | |
| "eval_runtime": 286.7682, | |
| "eval_samples_per_second": 36.803, | |
| "eval_steps_per_second": 4.603, | |
| "step": 75 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.476062712987648e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |