| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006385492161808372, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.513989549077829e-05, | |
| "grad_norm": 0.25134968757629395, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 10.379, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.513989549077829e-05, | |
| "eval_loss": 10.380301475524902, | |
| "eval_runtime": 74.4197, | |
| "eval_samples_per_second": 132.908, | |
| "eval_steps_per_second": 66.461, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00017027979098155658, | |
| "grad_norm": 0.1832198202610016, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 10.3956, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00025541968647233487, | |
| "grad_norm": 0.18218618631362915, | |
| "learning_rate": 0.0001, | |
| "loss": 10.4058, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00034055958196311316, | |
| "grad_norm": 0.14622487127780914, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 10.3894, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00042569947745389145, | |
| "grad_norm": 0.16691172122955322, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 10.3782, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005108393729446697, | |
| "grad_norm": 0.11237431317567825, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 10.3841, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.000595979268435448, | |
| "grad_norm": 0.09124422818422318, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 10.377, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0006811191639262263, | |
| "grad_norm": 0.09104663878679276, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 10.3816, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0007662590594170046, | |
| "grad_norm": 0.13115987181663513, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 10.3722, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0008513989549077829, | |
| "grad_norm": 0.10072201490402222, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 10.3786, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0009365388503985611, | |
| "grad_norm": 0.11183115094900131, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 10.3775, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0010216787458893395, | |
| "grad_norm": 0.11006626486778259, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.3698, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0011068186413801177, | |
| "grad_norm": 0.08694112300872803, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 10.3705, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.001191958536870896, | |
| "grad_norm": 0.09846315532922745, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 10.3719, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0012770984323616742, | |
| "grad_norm": 0.10194522142410278, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.3706, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0013622383278524526, | |
| "grad_norm": 0.10767930746078491, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 10.3689, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0014473782233432309, | |
| "grad_norm": 0.10827472060918808, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 10.365, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0015325181188340091, | |
| "grad_norm": 0.11412804573774338, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 10.3739, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0016176580143247873, | |
| "grad_norm": 0.11290401220321655, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 10.3862, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0017027979098155658, | |
| "grad_norm": 0.13899609446525574, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 10.3814, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.001787937805306344, | |
| "grad_norm": 0.15274837613105774, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.3626, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0018730777007971223, | |
| "grad_norm": 0.1402570605278015, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 10.3692, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0019582175962879005, | |
| "grad_norm": 0.11785771697759628, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 10.3679, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.002043357491778679, | |
| "grad_norm": 0.13151095807552338, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 10.383, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.002128497387269457, | |
| "grad_norm": 0.1171712800860405, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 10.3711, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.002128497387269457, | |
| "eval_loss": 10.371925354003906, | |
| "eval_runtime": 74.1945, | |
| "eval_samples_per_second": 133.312, | |
| "eval_steps_per_second": 66.663, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0022136372827602354, | |
| "grad_norm": 0.1304478943347931, | |
| "learning_rate": 7.68649804173412e-05, | |
| "loss": 10.3695, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.002298777178251014, | |
| "grad_norm": 0.1295875608921051, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 10.3707, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.002383917073741792, | |
| "grad_norm": 0.11449471116065979, | |
| "learning_rate": 7.308743066175172e-05, | |
| "loss": 10.3833, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0024690569692325704, | |
| "grad_norm": 0.1458948850631714, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 10.37, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0025541968647233484, | |
| "grad_norm": 0.12886323034763336, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.3815, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002639336760214127, | |
| "grad_norm": 0.11445284634828568, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 10.3738, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0027244766557049053, | |
| "grad_norm": 0.12730805575847626, | |
| "learning_rate": 6.503528997521366e-05, | |
| "loss": 10.3677, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0028096165511956833, | |
| "grad_norm": 0.175711527466774, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 10.3789, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0028947564466864618, | |
| "grad_norm": 0.1383206993341446, | |
| "learning_rate": 6.0821980696905146e-05, | |
| "loss": 10.3737, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0029798963421772398, | |
| "grad_norm": 0.14329196512699127, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 10.3724, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0030650362376680182, | |
| "grad_norm": 0.1304287165403366, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 10.3729, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0031501761331587967, | |
| "grad_norm": 0.15487420558929443, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 10.3613, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0032353160286495747, | |
| "grad_norm": 0.16208356618881226, | |
| "learning_rate": 5.218096936826681e-05, | |
| "loss": 10.3589, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.003320455924140353, | |
| "grad_norm": 0.16646641492843628, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3753, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0034055958196311316, | |
| "grad_norm": 0.1642124056816101, | |
| "learning_rate": 4.781903063173321e-05, | |
| "loss": 10.3586, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0034907357151219096, | |
| "grad_norm": 0.16558325290679932, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 10.3625, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.003575875610612688, | |
| "grad_norm": 0.18477176129817963, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 10.3724, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.003661015506103466, | |
| "grad_norm": 0.13750387728214264, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 10.3534, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0037461554015942445, | |
| "grad_norm": 0.15226051211357117, | |
| "learning_rate": 3.917801930309486e-05, | |
| "loss": 10.3561, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.003831295297085023, | |
| "grad_norm": 0.16481082141399384, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 10.3705, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.003916435192575801, | |
| "grad_norm": 0.16374343633651733, | |
| "learning_rate": 3.4964710024786354e-05, | |
| "loss": 10.3746, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0040015750880665795, | |
| "grad_norm": 0.1810373067855835, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 10.3756, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.004086714983557358, | |
| "grad_norm": 0.15905612707138062, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 10.3727, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.004171854879048136, | |
| "grad_norm": 0.20548060536384583, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 10.374, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.004256994774538914, | |
| "grad_norm": 0.2801133990287781, | |
| "learning_rate": 2.6912569338248315e-05, | |
| "loss": 10.3681, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.004256994774538914, | |
| "eval_loss": 10.362723350524902, | |
| "eval_runtime": 74.015, | |
| "eval_samples_per_second": 133.635, | |
| "eval_steps_per_second": 66.824, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.004342134670029692, | |
| "grad_norm": 0.30174604058265686, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 10.3665, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.004427274565520471, | |
| "grad_norm": 0.28722646832466125, | |
| "learning_rate": 2.3135019582658802e-05, | |
| "loss": 10.3836, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.004512414461011249, | |
| "grad_norm": 0.26923665404319763, | |
| "learning_rate": 2.132117818244771e-05, | |
| "loss": 10.3838, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.004597554356502028, | |
| "grad_norm": 0.23828227818012238, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 10.3684, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.004682694251992805, | |
| "grad_norm": 0.15467457473278046, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 10.3714, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.004767834147483584, | |
| "grad_norm": 0.19631482660770416, | |
| "learning_rate": 1.622048961921699e-05, | |
| "loss": 10.3534, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.004852974042974362, | |
| "grad_norm": 0.14511145651340485, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 10.3593, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.004938113938465141, | |
| "grad_norm": 0.15094733238220215, | |
| "learning_rate": 1.3136133159493802e-05, | |
| "loss": 10.3621, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.005023253833955919, | |
| "grad_norm": 0.1429455578327179, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 10.3636, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.005108393729446697, | |
| "grad_norm": 0.19595345854759216, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 10.3623, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.005193533624937475, | |
| "grad_norm": 0.16804875433444977, | |
| "learning_rate": 9.042397785550405e-06, | |
| "loss": 10.3713, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.005278673520428254, | |
| "grad_norm": 0.18887090682983398, | |
| "learning_rate": 7.830427709355725e-06, | |
| "loss": 10.3459, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.005363813415919032, | |
| "grad_norm": 0.19332559406757355, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 10.364, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.005448953311409811, | |
| "grad_norm": 0.1675790250301361, | |
| "learning_rate": 5.649458341088915e-06, | |
| "loss": 10.3672, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.005534093206900588, | |
| "grad_norm": 0.1676328331232071, | |
| "learning_rate": 4.684610648167503e-06, | |
| "loss": 10.361, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.005619233102391367, | |
| "grad_norm": 0.1370442807674408, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 10.3716, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.005704372997882145, | |
| "grad_norm": 0.19722534716129303, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 10.3465, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.0057895128933729235, | |
| "grad_norm": 0.18959833681583405, | |
| "learning_rate": 2.314152462588659e-06, | |
| "loss": 10.3577, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.005874652788863702, | |
| "grad_norm": 0.17572325468063354, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 10.372, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.0059597926843544795, | |
| "grad_norm": 0.2337626963853836, | |
| "learning_rate": 1.1851996440033319e-06, | |
| "loss": 10.346, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.006044932579845258, | |
| "grad_norm": 0.19222278892993927, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 10.363, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.0061300724753360365, | |
| "grad_norm": 0.1720466911792755, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 10.3667, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.006215212370826815, | |
| "grad_norm": 0.15600402653217316, | |
| "learning_rate": 1.9026509541272275e-07, | |
| "loss": 10.3616, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.006300352266317593, | |
| "grad_norm": 0.14834241569042206, | |
| "learning_rate": 4.7588920907110094e-08, | |
| "loss": 10.3698, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.006385492161808372, | |
| "grad_norm": 0.16144375503063202, | |
| "learning_rate": 0.0, | |
| "loss": 10.374, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.006385492161808372, | |
| "eval_loss": 10.360559463500977, | |
| "eval_runtime": 74.232, | |
| "eval_samples_per_second": 133.244, | |
| "eval_steps_per_second": 66.629, | |
| "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": 8767452217344.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |