| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.009538647419795872, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001271819655972783, | |
| "grad_norm": 14.686725616455078, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 5.7949, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001271819655972783, | |
| "eval_loss": 5.837724208831787, | |
| "eval_runtime": 1012.7963, | |
| "eval_samples_per_second": 6.538, | |
| "eval_steps_per_second": 3.269, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002543639311945566, | |
| "grad_norm": 14.532427787780762, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 5.9049, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0003815458967918349, | |
| "grad_norm": 14.580315589904785, | |
| "learning_rate": 0.0001, | |
| "loss": 5.5549, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005087278623891132, | |
| "grad_norm": 12.386919975280762, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 5.2155, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0006359098279863915, | |
| "grad_norm": 8.52061939239502, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 3.5045, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0007630917935836698, | |
| "grad_norm": 7.900720596313477, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.7008, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0008902737591809482, | |
| "grad_norm": 8.71509838104248, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 2.4308, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0010174557247782264, | |
| "grad_norm": 5.258134841918945, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 2.1263, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0011446376903755048, | |
| "grad_norm": 5.729340076446533, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.1367, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.001271819655972783, | |
| "grad_norm": 7.960080623626709, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 2.0017, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0013990016215700615, | |
| "grad_norm": 4.6670241355896, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 2.021, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0015261835871673397, | |
| "grad_norm": 4.256051063537598, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.9393, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0016533655527646179, | |
| "grad_norm": 6.798515319824219, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 1.8432, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0017805475183618963, | |
| "grad_norm": 5.227590084075928, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 1.7585, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0019077294839591745, | |
| "grad_norm": 4.927859306335449, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.8781, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0020349114495564528, | |
| "grad_norm": 6.839364051818848, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 1.7892, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.002162093415153731, | |
| "grad_norm": 8.424290657043457, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 1.9716, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0022892753807510096, | |
| "grad_norm": 3.870750904083252, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.734, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0024164573463482876, | |
| "grad_norm": 3.9411606788635254, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 1.7441, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.002543639311945566, | |
| "grad_norm": 4.28488302230835, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 1.5066, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0026708212775428445, | |
| "grad_norm": 2.7083420753479004, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.6947, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.002798003243140123, | |
| "grad_norm": 3.216218948364258, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 1.7181, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.002925185208737401, | |
| "grad_norm": 3.545102119445801, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 1.5627, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0030523671743346793, | |
| "grad_norm": 5.308266639709473, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.81, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0031795491399319578, | |
| "grad_norm": 2.468996286392212, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 1.6267, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0031795491399319578, | |
| "eval_loss": 1.6478782892227173, | |
| "eval_runtime": 1016.413, | |
| "eval_samples_per_second": 6.515, | |
| "eval_steps_per_second": 3.258, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0033067311055292358, | |
| "grad_norm": 2.405796766281128, | |
| "learning_rate": 7.68649804173412e-05, | |
| "loss": 1.6712, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.003433913071126514, | |
| "grad_norm": 2.1344990730285645, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.657, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0035610950367237926, | |
| "grad_norm": 3.931316375732422, | |
| "learning_rate": 7.308743066175172e-05, | |
| "loss": 1.7584, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.003688277002321071, | |
| "grad_norm": 2.662752628326416, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 1.605, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.003815458967918349, | |
| "grad_norm": 3.1903748512268066, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.6863, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0039426409335156275, | |
| "grad_norm": 2.342129945755005, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 1.5341, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0040698228991129055, | |
| "grad_norm": 2.9486243724823, | |
| "learning_rate": 6.503528997521366e-05, | |
| "loss": 1.6403, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.004197004864710184, | |
| "grad_norm": 2.807129383087158, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.6695, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.004324186830307462, | |
| "grad_norm": 2.300341844558716, | |
| "learning_rate": 6.0821980696905146e-05, | |
| "loss": 1.5375, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.00445136879590474, | |
| "grad_norm": 5.008623123168945, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 1.7217, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.004578550761502019, | |
| "grad_norm": 3.538121461868286, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.6573, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.004705732727099297, | |
| "grad_norm": 2.3192837238311768, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 1.4853, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.004832914692696575, | |
| "grad_norm": 2.5325701236724854, | |
| "learning_rate": 5.218096936826681e-05, | |
| "loss": 1.5451, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.004960096658293854, | |
| "grad_norm": 2.0213067531585693, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6081, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.005087278623891132, | |
| "grad_norm": 3.6637330055236816, | |
| "learning_rate": 4.781903063173321e-05, | |
| "loss": 1.7933, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.005214460589488411, | |
| "grad_norm": 2.7776637077331543, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 1.4603, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.005341642555085689, | |
| "grad_norm": 3.7768895626068115, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.6809, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.005468824520682967, | |
| "grad_norm": 3.5375547409057617, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 1.6731, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.005596006486280246, | |
| "grad_norm": 2.548534393310547, | |
| "learning_rate": 3.917801930309486e-05, | |
| "loss": 1.6962, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.005723188451877524, | |
| "grad_norm": 1.7797907590866089, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.6327, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.005850370417474802, | |
| "grad_norm": 1.6917822360992432, | |
| "learning_rate": 3.4964710024786354e-05, | |
| "loss": 1.543, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.005977552383072081, | |
| "grad_norm": 2.2675538063049316, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 1.6209, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.006104734348669359, | |
| "grad_norm": 1.9940866231918335, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.5505, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.006231916314266637, | |
| "grad_norm": 1.4850102663040161, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 1.6082, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0063590982798639156, | |
| "grad_norm": 1.984756350517273, | |
| "learning_rate": 2.6912569338248315e-05, | |
| "loss": 1.6368, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0063590982798639156, | |
| "eval_loss": 1.5464518070220947, | |
| "eval_runtime": 1017.6554, | |
| "eval_samples_per_second": 6.507, | |
| "eval_steps_per_second": 3.254, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0064862802454611936, | |
| "grad_norm": 2.5585479736328125, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.6511, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.0066134622110584716, | |
| "grad_norm": 3.03650164604187, | |
| "learning_rate": 2.3135019582658802e-05, | |
| "loss": 1.465, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.00674064417665575, | |
| "grad_norm": 2.079188108444214, | |
| "learning_rate": 2.132117818244771e-05, | |
| "loss": 1.5449, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.006867826142253028, | |
| "grad_norm": 2.6188244819641113, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.5621, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.006995008107850306, | |
| "grad_norm": 2.1260628700256348, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 1.5848, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.007122190073447585, | |
| "grad_norm": 1.6332706212997437, | |
| "learning_rate": 1.622048961921699e-05, | |
| "loss": 1.5695, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.007249372039044863, | |
| "grad_norm": 2.4522626399993896, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.6052, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.007376554004642142, | |
| "grad_norm": 2.603383779525757, | |
| "learning_rate": 1.3136133159493802e-05, | |
| "loss": 1.6324, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.00750373597023942, | |
| "grad_norm": 2.176748752593994, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 1.3584, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.007630917935836698, | |
| "grad_norm": 2.0545296669006348, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.5658, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.007758099901433977, | |
| "grad_norm": 2.176485061645508, | |
| "learning_rate": 9.042397785550405e-06, | |
| "loss": 1.5229, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.007885281867031255, | |
| "grad_norm": 2.3088207244873047, | |
| "learning_rate": 7.830427709355725e-06, | |
| "loss": 1.4633, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.008012463832628533, | |
| "grad_norm": 3.608034372329712, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.6021, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.008139645798225811, | |
| "grad_norm": 1.7870920896530151, | |
| "learning_rate": 5.649458341088915e-06, | |
| "loss": 1.5331, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.00826682776382309, | |
| "grad_norm": 2.5201566219329834, | |
| "learning_rate": 4.684610648167503e-06, | |
| "loss": 1.5798, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.008394009729420369, | |
| "grad_norm": 3.3685851097106934, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.6904, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.008521191695017647, | |
| "grad_norm": 4.109929084777832, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 1.6286, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.008648373660614925, | |
| "grad_norm": 3.135014533996582, | |
| "learning_rate": 2.314152462588659e-06, | |
| "loss": 1.5616, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.008775555626212203, | |
| "grad_norm": 2.6625030040740967, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.5772, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.00890273759180948, | |
| "grad_norm": 2.5769317150115967, | |
| "learning_rate": 1.1851996440033319e-06, | |
| "loss": 1.4481, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.00902991955740676, | |
| "grad_norm": 2.8375887870788574, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 1.6209, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.009157101523004038, | |
| "grad_norm": 2.410177707672119, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.6444, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.009284283488601316, | |
| "grad_norm": 2.377715826034546, | |
| "learning_rate": 1.9026509541272275e-07, | |
| "loss": 1.5977, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.009411465454198594, | |
| "grad_norm": 2.3886666297912598, | |
| "learning_rate": 4.7588920907110094e-08, | |
| "loss": 1.6901, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.009538647419795872, | |
| "grad_norm": 2.8022537231445312, | |
| "learning_rate": 0.0, | |
| "loss": 1.3744, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.009538647419795872, | |
| "eval_loss": 1.5396223068237305, | |
| "eval_runtime": 1016.8842, | |
| "eval_samples_per_second": 6.512, | |
| "eval_steps_per_second": 3.256, | |
| "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": 3.01589487157248e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |