| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.007050860204945004, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 9.401146939926671e-05, | |
| "grad_norm": 1.0696098804473877, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 2.3106, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.401146939926671e-05, | |
| "eval_loss": 3.1381921768188477, | |
| "eval_runtime": 306.7613, | |
| "eval_samples_per_second": 29.202, | |
| "eval_steps_per_second": 14.601, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00018802293879853342, | |
| "grad_norm": 1.1547324657440186, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 2.3901, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0002820344081978001, | |
| "grad_norm": 1.1568049192428589, | |
| "learning_rate": 0.0001, | |
| "loss": 2.4531, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00037604587759706683, | |
| "grad_norm": 1.295903205871582, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 2.5252, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00047005734699633354, | |
| "grad_norm": 1.3080066442489624, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 2.5252, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005640688163956002, | |
| "grad_norm": 1.4140979051589966, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.2832, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.000658080285794867, | |
| "grad_norm": 1.2049480676651, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 2.1834, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0007520917551941337, | |
| "grad_norm": 1.691810131072998, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 2.1438, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0008461032245934004, | |
| "grad_norm": 1.4161789417266846, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.9656, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0009401146939926671, | |
| "grad_norm": 1.1197580099105835, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 1.8062, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001034126163391934, | |
| "grad_norm": 1.2883065938949585, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.8325, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0011281376327912005, | |
| "grad_norm": 1.2502721548080444, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.7662, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0012221491021904673, | |
| "grad_norm": 1.160671353340149, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 1.6167, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.001316160571589734, | |
| "grad_norm": 1.2814849615097046, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 1.5443, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0014101720409890007, | |
| "grad_norm": 1.3020795583724976, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.4767, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0015041835103882673, | |
| "grad_norm": 1.122304081916809, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 1.3664, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0015981949797875341, | |
| "grad_norm": 1.0071494579315186, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 1.2036, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0016922064491868007, | |
| "grad_norm": 1.019412875175476, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.2946, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0017862179185860676, | |
| "grad_norm": 1.3061738014221191, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 1.2691, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0018802293879853342, | |
| "grad_norm": 1.2895138263702393, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 1.2012, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0019742408573846008, | |
| "grad_norm": 1.0393970012664795, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.9289, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.002068252326783868, | |
| "grad_norm": 1.161494255065918, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 1.0573, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0021622637961831344, | |
| "grad_norm": 1.2825669050216675, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 1.0959, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.002256275265582401, | |
| "grad_norm": 1.2384896278381348, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.9377, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0023502867349816676, | |
| "grad_norm": 1.1488481760025024, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 0.9027, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0023502867349816676, | |
| "eval_loss": 0.9509760737419128, | |
| "eval_runtime": 306.6139, | |
| "eval_samples_per_second": 29.216, | |
| "eval_steps_per_second": 14.608, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0024442982043809346, | |
| "grad_norm": 1.5596882104873657, | |
| "learning_rate": 7.68649804173412e-05, | |
| "loss": 0.996, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.002538309673780201, | |
| "grad_norm": 1.2554572820663452, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.7677, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.002632321143179468, | |
| "grad_norm": 1.1897380352020264, | |
| "learning_rate": 7.308743066175172e-05, | |
| "loss": 0.8327, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0027263326125787344, | |
| "grad_norm": 1.1996997594833374, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 0.7552, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0028203440819780014, | |
| "grad_norm": 1.190172553062439, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.6472, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002914355551377268, | |
| "grad_norm": 1.0043503046035767, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 0.5782, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0030083670207765346, | |
| "grad_norm": 0.9340465068817139, | |
| "learning_rate": 6.503528997521366e-05, | |
| "loss": 0.5787, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0031023784901758012, | |
| "grad_norm": 1.2603780031204224, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.6059, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0031963899595750683, | |
| "grad_norm": 1.4247483015060425, | |
| "learning_rate": 6.0821980696905146e-05, | |
| "loss": 0.6423, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.003290401428974335, | |
| "grad_norm": 0.9418686032295227, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.522, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0033844128983736015, | |
| "grad_norm": 1.142016887664795, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.6962, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.003478424367772868, | |
| "grad_norm": 1.1568361520767212, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 0.5529, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.003572435837172135, | |
| "grad_norm": 1.2142870426177979, | |
| "learning_rate": 5.218096936826681e-05, | |
| "loss": 0.4753, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0036664473065714017, | |
| "grad_norm": 1.2301100492477417, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5065, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0037604587759706683, | |
| "grad_norm": 1.3371412754058838, | |
| "learning_rate": 4.781903063173321e-05, | |
| "loss": 0.4529, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0038544702453699353, | |
| "grad_norm": 0.9668884873390198, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 0.4737, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0039484817147692015, | |
| "grad_norm": 1.0440391302108765, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.5063, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.004042493184168469, | |
| "grad_norm": 1.243342638015747, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.3832, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.004136504653567736, | |
| "grad_norm": 1.4090092182159424, | |
| "learning_rate": 3.917801930309486e-05, | |
| "loss": 0.6327, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.004230516122967002, | |
| "grad_norm": 1.3914059400558472, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.4771, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.004324527592366269, | |
| "grad_norm": 1.1954938173294067, | |
| "learning_rate": 3.4964710024786354e-05, | |
| "loss": 0.4217, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.004418539061765535, | |
| "grad_norm": 1.7103815078735352, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 0.4914, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.004512550531164802, | |
| "grad_norm": 1.5357106924057007, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.456, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.004606562000564069, | |
| "grad_norm": 1.7698625326156616, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 0.4604, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.004700573469963335, | |
| "grad_norm": 2.5681278705596924, | |
| "learning_rate": 2.6912569338248315e-05, | |
| "loss": 0.4387, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.004700573469963335, | |
| "eval_loss": 0.6145913004875183, | |
| "eval_runtime": 306.57, | |
| "eval_samples_per_second": 29.22, | |
| "eval_steps_per_second": 14.61, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.004794584939362603, | |
| "grad_norm": 3.4442198276519775, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.8815, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.004888596408761869, | |
| "grad_norm": 3.3648104667663574, | |
| "learning_rate": 2.3135019582658802e-05, | |
| "loss": 0.8969, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.004982607878161136, | |
| "grad_norm": 3.168910503387451, | |
| "learning_rate": 2.132117818244771e-05, | |
| "loss": 0.8597, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.005076619347560402, | |
| "grad_norm": 3.004520893096924, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.8053, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.005170630816959669, | |
| "grad_norm": 2.8128843307495117, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 0.8096, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.005264642286358936, | |
| "grad_norm": 2.4147465229034424, | |
| "learning_rate": 1.622048961921699e-05, | |
| "loss": 0.7316, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.005358653755758202, | |
| "grad_norm": 2.472194194793701, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.7932, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.005452665225157469, | |
| "grad_norm": 1.9689332246780396, | |
| "learning_rate": 1.3136133159493802e-05, | |
| "loss": 0.6655, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.005546676694556736, | |
| "grad_norm": 1.9256327152252197, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 0.6854, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.005640688163956003, | |
| "grad_norm": 1.5773730278015137, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.5794, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0057346996333552695, | |
| "grad_norm": 1.4215878248214722, | |
| "learning_rate": 9.042397785550405e-06, | |
| "loss": 0.6325, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.005828711102754536, | |
| "grad_norm": 1.2316890954971313, | |
| "learning_rate": 7.830427709355725e-06, | |
| "loss": 0.5846, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.005922722572153803, | |
| "grad_norm": 1.1193468570709229, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.513, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.006016734041553069, | |
| "grad_norm": 1.1295101642608643, | |
| "learning_rate": 5.649458341088915e-06, | |
| "loss": 0.4793, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.006110745510952336, | |
| "grad_norm": 0.9580612778663635, | |
| "learning_rate": 4.684610648167503e-06, | |
| "loss": 0.5239, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.0062047569803516025, | |
| "grad_norm": 1.2913953065872192, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.4928, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.00629876844975087, | |
| "grad_norm": 1.0162431001663208, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.5664, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.0063927799191501366, | |
| "grad_norm": 0.7663949728012085, | |
| "learning_rate": 2.314152462588659e-06, | |
| "loss": 0.4712, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.006486791388549403, | |
| "grad_norm": 0.8022221922874451, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.4734, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.00658080285794867, | |
| "grad_norm": 0.9547379016876221, | |
| "learning_rate": 1.1851996440033319e-06, | |
| "loss": 0.5119, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.006674814327347936, | |
| "grad_norm": 0.7708539366722107, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 0.4543, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.006768825796747203, | |
| "grad_norm": 0.9734583497047424, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.5059, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.0068628372661464696, | |
| "grad_norm": 0.8569084405899048, | |
| "learning_rate": 1.9026509541272275e-07, | |
| "loss": 0.5209, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.006956848735545736, | |
| "grad_norm": 0.8591418266296387, | |
| "learning_rate": 4.7588920907110094e-08, | |
| "loss": 0.5359, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.007050860204945004, | |
| "grad_norm": 0.8256073594093323, | |
| "learning_rate": 0.0, | |
| "loss": 0.5314, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.007050860204945004, | |
| "eval_loss": 0.5117783546447754, | |
| "eval_runtime": 306.801, | |
| "eval_samples_per_second": 29.198, | |
| "eval_steps_per_second": 14.599, | |
| "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": 1.56265573515264e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |