| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.5934065934065934, |
| "eval_steps": 500, |
| "global_step": 90, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.006593406593406593, |
| "grad_norm": 0.9548422694206238, |
| "learning_rate": 0.0, |
| "loss": 2.456, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.013186813186813187, |
| "grad_norm": 0.9033191800117493, |
| "learning_rate": 4e-05, |
| "loss": 2.7771, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.01978021978021978, |
| "grad_norm": 0.9564813375473022, |
| "learning_rate": 8e-05, |
| "loss": 2.7839, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.026373626373626374, |
| "grad_norm": 1.4111387729644775, |
| "learning_rate": 0.00012, |
| "loss": 3.2357, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.03296703296703297, |
| "grad_norm": 1.9880008697509766, |
| "learning_rate": 0.00016, |
| "loss": 3.5809, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.03956043956043956, |
| "grad_norm": 2.1871581077575684, |
| "learning_rate": 0.0002, |
| "loss": 2.9169, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.046153846153846156, |
| "grad_norm": 2.0554776191711426, |
| "learning_rate": 0.00019955654101995565, |
| "loss": 2.1632, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.05274725274725275, |
| "grad_norm": 1.8138749599456787, |
| "learning_rate": 0.00019911308203991133, |
| "loss": 1.6378, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.05934065934065934, |
| "grad_norm": 1.0925194025039673, |
| "learning_rate": 0.00019866962305986697, |
| "loss": 1.157, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.06593406593406594, |
| "grad_norm": 0.8452661633491516, |
| "learning_rate": 0.00019822616407982261, |
| "loss": 1.11, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.07252747252747253, |
| "grad_norm": 0.9047808051109314, |
| "learning_rate": 0.00019778270509977829, |
| "loss": 0.903, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.07912087912087912, |
| "grad_norm": 0.8229642510414124, |
| "learning_rate": 0.00019733924611973393, |
| "loss": 0.923, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.08571428571428572, |
| "grad_norm": 0.6836701035499573, |
| "learning_rate": 0.0001968957871396896, |
| "loss": 0.7578, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.09230769230769231, |
| "grad_norm": 0.7976304292678833, |
| "learning_rate": 0.00019645232815964525, |
| "loss": 0.7888, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.0989010989010989, |
| "grad_norm": 0.5903546214103699, |
| "learning_rate": 0.00019600886917960092, |
| "loss": 0.7382, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.1054945054945055, |
| "grad_norm": 0.5188648104667664, |
| "learning_rate": 0.00019556541019955653, |
| "loss": 0.7559, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.11208791208791209, |
| "grad_norm": 0.43109938502311707, |
| "learning_rate": 0.0001951219512195122, |
| "loss": 0.6449, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.11868131868131868, |
| "grad_norm": 0.5063297748565674, |
| "learning_rate": 0.00019467849223946785, |
| "loss": 0.7978, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.12527472527472527, |
| "grad_norm": 0.48597580194473267, |
| "learning_rate": 0.00019423503325942352, |
| "loss": 0.7311, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.13186813186813187, |
| "grad_norm": 0.4553968906402588, |
| "learning_rate": 0.00019379157427937917, |
| "loss": 0.7349, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.13846153846153847, |
| "grad_norm": 0.4415663778781891, |
| "learning_rate": 0.00019334811529933484, |
| "loss": 0.5978, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.14505494505494507, |
| "grad_norm": 0.44407373666763306, |
| "learning_rate": 0.00019290465631929045, |
| "loss": 0.6434, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.15164835164835164, |
| "grad_norm": 0.4405691623687744, |
| "learning_rate": 0.00019246119733924613, |
| "loss": 0.6702, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.15824175824175823, |
| "grad_norm": 0.45118415355682373, |
| "learning_rate": 0.00019201773835920177, |
| "loss": 0.6987, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.16483516483516483, |
| "grad_norm": 0.4140220582485199, |
| "learning_rate": 0.00019157427937915744, |
| "loss": 0.739, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.17142857142857143, |
| "grad_norm": 0.3368533253669739, |
| "learning_rate": 0.00019113082039911309, |
| "loss": 0.6759, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.17802197802197803, |
| "grad_norm": 0.32022058963775635, |
| "learning_rate": 0.00019068736141906876, |
| "loss": 0.5563, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.18461538461538463, |
| "grad_norm": 0.30251631140708923, |
| "learning_rate": 0.0001902439024390244, |
| "loss": 0.5916, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.1912087912087912, |
| "grad_norm": 0.33803412318229675, |
| "learning_rate": 0.00018980044345898005, |
| "loss": 0.5178, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.1978021978021978, |
| "grad_norm": 0.3477880656719208, |
| "learning_rate": 0.00018935698447893572, |
| "loss": 0.7149, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.2043956043956044, |
| "grad_norm": 0.4316825568675995, |
| "learning_rate": 0.00018891352549889136, |
| "loss": 0.6876, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.210989010989011, |
| "grad_norm": 0.3937191665172577, |
| "learning_rate": 0.00018847006651884703, |
| "loss": 0.6659, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.2175824175824176, |
| "grad_norm": 0.36258432269096375, |
| "learning_rate": 0.00018802660753880268, |
| "loss": 0.5481, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.22417582417582418, |
| "grad_norm": 0.4232417643070221, |
| "learning_rate": 0.00018758314855875832, |
| "loss": 0.6761, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.23076923076923078, |
| "grad_norm": 0.3215615749359131, |
| "learning_rate": 0.00018713968957871397, |
| "loss": 0.6068, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.23736263736263735, |
| "grad_norm": 0.3615092933177948, |
| "learning_rate": 0.00018669623059866964, |
| "loss": 0.5814, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.24395604395604395, |
| "grad_norm": 0.33303868770599365, |
| "learning_rate": 0.00018625277161862528, |
| "loss": 0.5659, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.25054945054945055, |
| "grad_norm": 0.34852537512779236, |
| "learning_rate": 0.00018580931263858095, |
| "loss": 0.5848, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.2571428571428571, |
| "grad_norm": 0.333442360162735, |
| "learning_rate": 0.0001853658536585366, |
| "loss": 0.5249, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.26373626373626374, |
| "grad_norm": 0.3381938636302948, |
| "learning_rate": 0.00018492239467849224, |
| "loss": 0.6407, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.2703296703296703, |
| "grad_norm": 0.3696731626987457, |
| "learning_rate": 0.0001844789356984479, |
| "loss": 0.6736, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.27692307692307694, |
| "grad_norm": 0.4098624587059021, |
| "learning_rate": 0.00018403547671840356, |
| "loss": 0.6643, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.2835164835164835, |
| "grad_norm": 0.3498683273792267, |
| "learning_rate": 0.0001835920177383592, |
| "loss": 0.5443, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.29010989010989013, |
| "grad_norm": 0.3131304383277893, |
| "learning_rate": 0.00018314855875831487, |
| "loss": 0.5232, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.2967032967032967, |
| "grad_norm": 0.39961516857147217, |
| "learning_rate": 0.00018270509977827052, |
| "loss": 0.7046, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.3032967032967033, |
| "grad_norm": 0.4616391360759735, |
| "learning_rate": 0.00018226164079822616, |
| "loss": 0.6706, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.3098901098901099, |
| "grad_norm": 0.38573798537254333, |
| "learning_rate": 0.00018181818181818183, |
| "loss": 0.6662, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.31648351648351647, |
| "grad_norm": 0.336185097694397, |
| "learning_rate": 0.00018137472283813748, |
| "loss": 0.5845, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.3230769230769231, |
| "grad_norm": 0.3926178216934204, |
| "learning_rate": 0.00018093126385809312, |
| "loss": 0.495, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.32967032967032966, |
| "grad_norm": 0.36642107367515564, |
| "learning_rate": 0.0001804878048780488, |
| "loss": 0.5075, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.3362637362637363, |
| "grad_norm": 0.4265896677970886, |
| "learning_rate": 0.00018004434589800444, |
| "loss": 0.6636, |
| "step": 51 |
| }, |
| { |
| "epoch": 0.34285714285714286, |
| "grad_norm": 0.4908406436443329, |
| "learning_rate": 0.00017960088691796008, |
| "loss": 0.6943, |
| "step": 52 |
| }, |
| { |
| "epoch": 0.34945054945054943, |
| "grad_norm": 0.3566623032093048, |
| "learning_rate": 0.00017915742793791575, |
| "loss": 0.5919, |
| "step": 53 |
| }, |
| { |
| "epoch": 0.35604395604395606, |
| "grad_norm": 0.3888160288333893, |
| "learning_rate": 0.0001787139689578714, |
| "loss": 0.7048, |
| "step": 54 |
| }, |
| { |
| "epoch": 0.3626373626373626, |
| "grad_norm": 0.3611518144607544, |
| "learning_rate": 0.00017827050997782707, |
| "loss": 0.505, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.36923076923076925, |
| "grad_norm": 0.3949228823184967, |
| "learning_rate": 0.00017782705099778271, |
| "loss": 0.6138, |
| "step": 56 |
| }, |
| { |
| "epoch": 0.3758241758241758, |
| "grad_norm": 0.4875071942806244, |
| "learning_rate": 0.00017738359201773839, |
| "loss": 0.7643, |
| "step": 57 |
| }, |
| { |
| "epoch": 0.3824175824175824, |
| "grad_norm": 0.44993212819099426, |
| "learning_rate": 0.000176940133037694, |
| "loss": 0.702, |
| "step": 58 |
| }, |
| { |
| "epoch": 0.389010989010989, |
| "grad_norm": 0.34542116522789, |
| "learning_rate": 0.00017649667405764967, |
| "loss": 0.5463, |
| "step": 59 |
| }, |
| { |
| "epoch": 0.3956043956043956, |
| "grad_norm": 0.42165201902389526, |
| "learning_rate": 0.00017605321507760532, |
| "loss": 0.5946, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.4021978021978022, |
| "grad_norm": 0.3682475984096527, |
| "learning_rate": 0.000175609756097561, |
| "loss": 0.5548, |
| "step": 61 |
| }, |
| { |
| "epoch": 0.4087912087912088, |
| "grad_norm": 0.36798593401908875, |
| "learning_rate": 0.00017516629711751663, |
| "loss": 0.3957, |
| "step": 62 |
| }, |
| { |
| "epoch": 0.4153846153846154, |
| "grad_norm": 0.4413401186466217, |
| "learning_rate": 0.0001747228381374723, |
| "loss": 0.6863, |
| "step": 63 |
| }, |
| { |
| "epoch": 0.421978021978022, |
| "grad_norm": 0.4089689552783966, |
| "learning_rate": 0.00017427937915742792, |
| "loss": 0.5794, |
| "step": 64 |
| }, |
| { |
| "epoch": 0.42857142857142855, |
| "grad_norm": 0.357327938079834, |
| "learning_rate": 0.0001738359201773836, |
| "loss": 0.5446, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.4351648351648352, |
| "grad_norm": 0.3936524987220764, |
| "learning_rate": 0.00017339246119733924, |
| "loss": 0.569, |
| "step": 66 |
| }, |
| { |
| "epoch": 0.44175824175824174, |
| "grad_norm": 0.4308718144893646, |
| "learning_rate": 0.0001729490022172949, |
| "loss": 0.608, |
| "step": 67 |
| }, |
| { |
| "epoch": 0.44835164835164837, |
| "grad_norm": 0.4803222417831421, |
| "learning_rate": 0.00017250554323725056, |
| "loss": 0.6635, |
| "step": 68 |
| }, |
| { |
| "epoch": 0.45494505494505494, |
| "grad_norm": 0.4282255470752716, |
| "learning_rate": 0.00017206208425720623, |
| "loss": 0.5607, |
| "step": 69 |
| }, |
| { |
| "epoch": 0.46153846153846156, |
| "grad_norm": 0.44135338068008423, |
| "learning_rate": 0.00017161862527716187, |
| "loss": 0.5048, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.46813186813186813, |
| "grad_norm": 0.5171645879745483, |
| "learning_rate": 0.00017117516629711752, |
| "loss": 0.6101, |
| "step": 71 |
| }, |
| { |
| "epoch": 0.4747252747252747, |
| "grad_norm": 0.4031164348125458, |
| "learning_rate": 0.0001707317073170732, |
| "loss": 0.5566, |
| "step": 72 |
| }, |
| { |
| "epoch": 0.48131868131868133, |
| "grad_norm": 0.35505273938179016, |
| "learning_rate": 0.00017028824833702883, |
| "loss": 0.6453, |
| "step": 73 |
| }, |
| { |
| "epoch": 0.4879120879120879, |
| "grad_norm": 0.3494785726070404, |
| "learning_rate": 0.0001698447893569845, |
| "loss": 0.6731, |
| "step": 74 |
| }, |
| { |
| "epoch": 0.4945054945054945, |
| "grad_norm": 0.4739617109298706, |
| "learning_rate": 0.00016940133037694015, |
| "loss": 0.5278, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.5010989010989011, |
| "grad_norm": 0.3757701814174652, |
| "learning_rate": 0.00016895787139689582, |
| "loss": 0.4467, |
| "step": 76 |
| }, |
| { |
| "epoch": 0.5076923076923077, |
| "grad_norm": 0.4467487633228302, |
| "learning_rate": 0.00016851441241685144, |
| "loss": 0.6486, |
| "step": 77 |
| }, |
| { |
| "epoch": 0.5142857142857142, |
| "grad_norm": 0.4626796543598175, |
| "learning_rate": 0.0001680709534368071, |
| "loss": 0.4425, |
| "step": 78 |
| }, |
| { |
| "epoch": 0.5208791208791209, |
| "grad_norm": 0.4805651307106018, |
| "learning_rate": 0.00016762749445676275, |
| "loss": 0.532, |
| "step": 79 |
| }, |
| { |
| "epoch": 0.5274725274725275, |
| "grad_norm": 0.6599902510643005, |
| "learning_rate": 0.00016718403547671842, |
| "loss": 0.6162, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.5340659340659341, |
| "grad_norm": 0.45104750990867615, |
| "learning_rate": 0.00016674057649667407, |
| "loss": 0.5708, |
| "step": 81 |
| }, |
| { |
| "epoch": 0.5406593406593406, |
| "grad_norm": 0.4385611414909363, |
| "learning_rate": 0.00016629711751662974, |
| "loss": 0.5711, |
| "step": 82 |
| }, |
| { |
| "epoch": 0.5472527472527473, |
| "grad_norm": 0.4250934422016144, |
| "learning_rate": 0.00016585365853658536, |
| "loss": 0.6049, |
| "step": 83 |
| }, |
| { |
| "epoch": 0.5538461538461539, |
| "grad_norm": 0.4899722635746002, |
| "learning_rate": 0.00016541019955654103, |
| "loss": 0.6084, |
| "step": 84 |
| }, |
| { |
| "epoch": 0.5604395604395604, |
| "grad_norm": 0.33061057329177856, |
| "learning_rate": 0.00016496674057649667, |
| "loss": 0.4669, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.567032967032967, |
| "grad_norm": 0.4679504632949829, |
| "learning_rate": 0.00016452328159645234, |
| "loss": 0.643, |
| "step": 86 |
| }, |
| { |
| "epoch": 0.5736263736263736, |
| "grad_norm": 0.32151514291763306, |
| "learning_rate": 0.000164079822616408, |
| "loss": 0.3998, |
| "step": 87 |
| }, |
| { |
| "epoch": 0.5802197802197803, |
| "grad_norm": 0.3151485323905945, |
| "learning_rate": 0.00016363636363636366, |
| "loss": 0.468, |
| "step": 88 |
| }, |
| { |
| "epoch": 0.5868131868131868, |
| "grad_norm": 0.3355564773082733, |
| "learning_rate": 0.0001631929046563193, |
| "loss": 0.4659, |
| "step": 89 |
| }, |
| { |
| "epoch": 0.5934065934065934, |
| "grad_norm": 0.4314066469669342, |
| "learning_rate": 0.00016274944567627495, |
| "loss": 0.5191, |
| "step": 90 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 456, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 15, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3.756018851704627e+16, |
| "train_batch_size": 22, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
