| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006626978429185213, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.835971238913618e-05, | |
| "grad_norm": 7.248940944671631, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 13.7553, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.835971238913618e-05, | |
| "eval_loss": 1.725895643234253, | |
| "eval_runtime": 3262.1613, | |
| "eval_samples_per_second": 2.922, | |
| "eval_steps_per_second": 1.461, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00017671942477827236, | |
| "grad_norm": 7.458225250244141, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 12.4906, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0002650791371674085, | |
| "grad_norm": 6.321793079376221, | |
| "learning_rate": 0.0002, | |
| "loss": 11.5012, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0003534388495565447, | |
| "grad_norm": 9.489212989807129, | |
| "learning_rate": 0.0001999048221581858, | |
| "loss": 13.5893, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0004417985619456809, | |
| "grad_norm": 12.038861274719238, | |
| "learning_rate": 0.00019961946980917456, | |
| "loss": 12.3484, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000530158274334817, | |
| "grad_norm": 11.484659194946289, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 9.3533, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0006185179867239533, | |
| "grad_norm": 12.574488639831543, | |
| "learning_rate": 0.00019848077530122083, | |
| "loss": 13.1227, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0007068776991130894, | |
| "grad_norm": 7.006253242492676, | |
| "learning_rate": 0.00019762960071199333, | |
| "loss": 8.7693, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0007952374115022256, | |
| "grad_norm": 8.56486701965332, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 7.7995, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0008835971238913618, | |
| "grad_norm": 17.155717849731445, | |
| "learning_rate": 0.0001953716950748227, | |
| "loss": 10.8552, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0009719568362804979, | |
| "grad_norm": 10.860207557678223, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 7.9845, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.001060316548669634, | |
| "grad_norm": 12.276436805725098, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 9.3655, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0011486762610587703, | |
| "grad_norm": 9.900433540344238, | |
| "learning_rate": 0.000190630778703665, | |
| "loss": 7.6518, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0012370359734479065, | |
| "grad_norm": 22.209026336669922, | |
| "learning_rate": 0.00018870108331782217, | |
| "loss": 11.3195, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0013253956858370426, | |
| "grad_norm": 10.000041007995605, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 7.4449, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0014137553982261789, | |
| "grad_norm": 7.811529159545898, | |
| "learning_rate": 0.0001843391445812886, | |
| "loss": 7.2741, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.001502115110615315, | |
| "grad_norm": 11.153886795043945, | |
| "learning_rate": 0.0001819152044288992, | |
| "loss": 7.8857, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0015904748230044512, | |
| "grad_norm": 8.829802513122559, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 7.9645, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0016788345353935872, | |
| "grad_norm": 10.067511558532715, | |
| "learning_rate": 0.0001766044443118978, | |
| "loss": 7.8328, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0017671942477827235, | |
| "grad_norm": 8.730874061584473, | |
| "learning_rate": 0.0001737277336810124, | |
| "loss": 6.224, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0018555539601718596, | |
| "grad_norm": 7.1686482429504395, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 7.4556, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0019439136725609958, | |
| "grad_norm": 14.39596176147461, | |
| "learning_rate": 0.00016755902076156604, | |
| "loss": 9.5076, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.002032273384950132, | |
| "grad_norm": 13.380977630615234, | |
| "learning_rate": 0.00016427876096865394, | |
| "loss": 11.2546, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.002120633097339268, | |
| "grad_norm": 9.951498985290527, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 7.8094, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0022089928097284045, | |
| "grad_norm": 9.973763465881348, | |
| "learning_rate": 0.0001573576436351046, | |
| "loss": 7.7583, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0022089928097284045, | |
| "eval_loss": 1.0112781524658203, | |
| "eval_runtime": 3277.0799, | |
| "eval_samples_per_second": 2.908, | |
| "eval_steps_per_second": 1.454, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0022973525221175405, | |
| "grad_norm": 8.621397018432617, | |
| "learning_rate": 0.0001537299608346824, | |
| "loss": 8.2647, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0023857122345066766, | |
| "grad_norm": 7.926273345947266, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 6.7474, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.002474071946895813, | |
| "grad_norm": 15.168147087097168, | |
| "learning_rate": 0.00014617486132350343, | |
| "loss": 8.1838, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.002562431659284949, | |
| "grad_norm": 8.807183265686035, | |
| "learning_rate": 0.00014226182617406996, | |
| "loss": 8.526, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.002650791371674085, | |
| "grad_norm": 9.189704895019531, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 7.7897, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0027391510840632212, | |
| "grad_norm": 6.538626194000244, | |
| "learning_rate": 0.00013420201433256689, | |
| "loss": 7.312, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0028275107964523577, | |
| "grad_norm": 5.638582706451416, | |
| "learning_rate": 0.00013007057995042732, | |
| "loss": 6.1696, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0029158705088414938, | |
| "grad_norm": 7.880610942840576, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 8.8579, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.00300423022123063, | |
| "grad_norm": 13.92683219909668, | |
| "learning_rate": 0.00012164396139381029, | |
| "loss": 6.6829, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.003092589933619766, | |
| "grad_norm": 7.7009596824646, | |
| "learning_rate": 0.00011736481776669306, | |
| "loss": 6.8181, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0031809496460089024, | |
| "grad_norm": 11.020742416381836, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 7.513, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0032693093583980384, | |
| "grad_norm": 9.45319652557373, | |
| "learning_rate": 0.00010871557427476583, | |
| "loss": 8.3329, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0033576690707871745, | |
| "grad_norm": 8.341961860656738, | |
| "learning_rate": 0.00010436193873653361, | |
| "loss": 6.6867, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0034460287831763105, | |
| "grad_norm": 9.635961532592773, | |
| "learning_rate": 0.0001, | |
| "loss": 7.9651, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.003534388495565447, | |
| "grad_norm": 9.390765190124512, | |
| "learning_rate": 9.563806126346642e-05, | |
| "loss": 6.406, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.003622748207954583, | |
| "grad_norm": 6.492102146148682, | |
| "learning_rate": 9.128442572523417e-05, | |
| "loss": 7.1606, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.003711107920343719, | |
| "grad_norm": 12.913923263549805, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 8.1131, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0037994676327328556, | |
| "grad_norm": 9.559767723083496, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 7.4009, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0038878273451219917, | |
| "grad_norm": 10.509035110473633, | |
| "learning_rate": 7.835603860618972e-05, | |
| "loss": 5.1785, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.003976187057511128, | |
| "grad_norm": 5.890124320983887, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 5.0357, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.004064546769900264, | |
| "grad_norm": 13.03221321105957, | |
| "learning_rate": 6.992942004957271e-05, | |
| "loss": 8.2949, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0041529064822894, | |
| "grad_norm": 6.9972453117370605, | |
| "learning_rate": 6.579798566743314e-05, | |
| "loss": 6.611, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.004241266194678536, | |
| "grad_norm": 18.20701026916504, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 7.0064, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.004329625907067673, | |
| "grad_norm": 9.751326560974121, | |
| "learning_rate": 5.773817382593008e-05, | |
| "loss": 6.5294, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.004417985619456809, | |
| "grad_norm": 7.42352294921875, | |
| "learning_rate": 5.382513867649663e-05, | |
| "loss": 5.4843, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.004417985619456809, | |
| "eval_loss": 0.9495617747306824, | |
| "eval_runtime": 3283.7601, | |
| "eval_samples_per_second": 2.902, | |
| "eval_steps_per_second": 1.451, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.004506345331845945, | |
| "grad_norm": 7.406082630157471, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 7.7452, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.004594705044235081, | |
| "grad_norm": 10.304743766784668, | |
| "learning_rate": 4.6270039165317605e-05, | |
| "loss": 8.5386, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.004683064756624217, | |
| "grad_norm": 8.669404983520508, | |
| "learning_rate": 4.264235636489542e-05, | |
| "loss": 7.5627, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.004771424469013353, | |
| "grad_norm": 11.453923225402832, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 11.6111, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.004859784181402489, | |
| "grad_norm": 9.022344589233398, | |
| "learning_rate": 3.5721239031346066e-05, | |
| "loss": 7.1967, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.004948143893791626, | |
| "grad_norm": 8.07685375213623, | |
| "learning_rate": 3.244097923843398e-05, | |
| "loss": 6.9913, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.005036503606180762, | |
| "grad_norm": 18.292648315429688, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 7.267, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.005124863318569898, | |
| "grad_norm": 6.400746822357178, | |
| "learning_rate": 2.6272266318987603e-05, | |
| "loss": 5.9861, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.005213223030959034, | |
| "grad_norm": 6.002554893493652, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 5.5134, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.00530158274334817, | |
| "grad_norm": 8.174169540405273, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 6.7454, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.005389942455737306, | |
| "grad_norm": 9.708706855773926, | |
| "learning_rate": 1.808479557110081e-05, | |
| "loss": 7.318, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.0054783021681264425, | |
| "grad_norm": 7.366970062255859, | |
| "learning_rate": 1.566085541871145e-05, | |
| "loss": 7.1856, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.0055666618805155785, | |
| "grad_norm": 8.115883827209473, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 6.7277, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.0056550215929047154, | |
| "grad_norm": 7.192087173461914, | |
| "learning_rate": 1.129891668217783e-05, | |
| "loss": 5.8814, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.0057433813052938515, | |
| "grad_norm": 10.194598197937012, | |
| "learning_rate": 9.369221296335006e-06, | |
| "loss": 7.0609, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.0058317410176829875, | |
| "grad_norm": 8.331764221191406, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 6.5664, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.005920100730072124, | |
| "grad_norm": 9.948031425476074, | |
| "learning_rate": 6.030737921409169e-06, | |
| "loss": 7.0316, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.00600846044246126, | |
| "grad_norm": 7.982971668243408, | |
| "learning_rate": 4.628304925177318e-06, | |
| "loss": 7.4487, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.006096820154850396, | |
| "grad_norm": 16.90338897705078, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 11.6838, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.006185179867239532, | |
| "grad_norm": 6.867629528045654, | |
| "learning_rate": 2.3703992880066638e-06, | |
| "loss": 7.1539, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.006273539579628669, | |
| "grad_norm": 7.886899471282959, | |
| "learning_rate": 1.5192246987791981e-06, | |
| "loss": 6.606, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.006361899292017805, | |
| "grad_norm": 7.660629749298096, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 9.0877, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.006450259004406941, | |
| "grad_norm": 11.299578666687012, | |
| "learning_rate": 3.805301908254455e-07, | |
| "loss": 8.0606, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.006538618716796077, | |
| "grad_norm": 7.190691947937012, | |
| "learning_rate": 9.517784181422019e-08, | |
| "loss": 8.8902, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.006626978429185213, | |
| "grad_norm": 7.750818729400635, | |
| "learning_rate": 0.0, | |
| "loss": 6.2261, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.006626978429185213, | |
| "eval_loss": 0.9349557757377625, | |
| "eval_runtime": 3279.205, | |
| "eval_samples_per_second": 2.906, | |
| "eval_steps_per_second": 1.453, | |
| "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": 1.9043369091072e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |