| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.002944741917910411, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.9263225572138815e-05, | |
| "grad_norm": 16.53192710876465, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 3.6605, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.9263225572138815e-05, | |
| "eval_loss": 3.731626272201538, | |
| "eval_runtime": 2304.5028, | |
| "eval_samples_per_second": 9.307, | |
| "eval_steps_per_second": 4.653, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.852645114427763e-05, | |
| "grad_norm": 19.084394454956055, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 3.7609, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00011778967671641644, | |
| "grad_norm": 13.099997520446777, | |
| "learning_rate": 0.0002, | |
| "loss": 2.7956, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00015705290228855526, | |
| "grad_norm": 9.987568855285645, | |
| "learning_rate": 0.0001999048221581858, | |
| "loss": 1.528, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00019631612786069407, | |
| "grad_norm": 6.246072292327881, | |
| "learning_rate": 0.00019961946980917456, | |
| "loss": 0.4466, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0002355793534328329, | |
| "grad_norm": 0.9562373757362366, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 0.0189, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002748425790049717, | |
| "grad_norm": 0.07823207974433899, | |
| "learning_rate": 0.00019848077530122083, | |
| "loss": 0.0009, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0003141058045771105, | |
| "grad_norm": 9.684601783752441, | |
| "learning_rate": 0.00019762960071199333, | |
| "loss": 0.0253, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00035336903014924933, | |
| "grad_norm": 0.009641322307288647, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 0.0001, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00039263225572138815, | |
| "grad_norm": 0.03295723348855972, | |
| "learning_rate": 0.0001953716950748227, | |
| "loss": 0.0002, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00043189548129352696, | |
| "grad_norm": 1.8471201658248901, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 0.0208, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0004711587068656658, | |
| "grad_norm": 2.772557020187378, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 0.0095, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0005104219324378046, | |
| "grad_norm": 0.0034740748815238476, | |
| "learning_rate": 0.000190630778703665, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0005496851580099434, | |
| "grad_norm": 0.0018053193343803287, | |
| "learning_rate": 0.00018870108331782217, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0005889483835820823, | |
| "grad_norm": 0.001508252345956862, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.000628211609154221, | |
| "grad_norm": 0.001372707192786038, | |
| "learning_rate": 0.0001843391445812886, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0006674748347263599, | |
| "grad_norm": 0.0011158657725900412, | |
| "learning_rate": 0.0001819152044288992, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0007067380602984987, | |
| "grad_norm": 84.22279357910156, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 0.0303, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0007460012858706375, | |
| "grad_norm": 0.0011357753537595272, | |
| "learning_rate": 0.0001766044443118978, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0007852645114427763, | |
| "grad_norm": 0.0009733820916153491, | |
| "learning_rate": 0.0001737277336810124, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0008245277370149152, | |
| "grad_norm": 0.0008526451420038939, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0008637909625870539, | |
| "grad_norm": 0.0012607588432729244, | |
| "learning_rate": 0.00016755902076156604, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0009030541881591928, | |
| "grad_norm": 10.768465042114258, | |
| "learning_rate": 0.00016427876096865394, | |
| "loss": 0.0027, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0009423174137313316, | |
| "grad_norm": 0.0007196764345280826, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0009815806393034703, | |
| "grad_norm": 0.0006661998922936618, | |
| "learning_rate": 0.0001573576436351046, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0009815806393034703, | |
| "eval_loss": 0.0005611914093606174, | |
| "eval_runtime": 2318.7094, | |
| "eval_samples_per_second": 9.25, | |
| "eval_steps_per_second": 4.625, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0010208438648756093, | |
| "grad_norm": 0.0007277107215486467, | |
| "learning_rate": 0.0001537299608346824, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.001060107090447748, | |
| "grad_norm": 0.0006697736098431051, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0010993703160198868, | |
| "grad_norm": 0.0029933627229183912, | |
| "learning_rate": 0.00014617486132350343, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0011386335415920256, | |
| "grad_norm": 0.035499222576618195, | |
| "learning_rate": 0.00014226182617406996, | |
| "loss": 0.0001, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0011778967671641646, | |
| "grad_norm": 0.10762330144643784, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 0.0002, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0012171599927363033, | |
| "grad_norm": 0.0013505893293768167, | |
| "learning_rate": 0.00013420201433256689, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.001256423218308442, | |
| "grad_norm": 0.001411484437994659, | |
| "learning_rate": 0.00013007057995042732, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0012956864438805808, | |
| "grad_norm": 0.0007225474109873176, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0013349496694527198, | |
| "grad_norm": 0.0009576158481650054, | |
| "learning_rate": 0.00012164396139381029, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0013742128950248586, | |
| "grad_norm": 0.0016589387087151408, | |
| "learning_rate": 0.00011736481776669306, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0014134761205969973, | |
| "grad_norm": 0.001446246518753469, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.001452739346169136, | |
| "grad_norm": 0.0017250552773475647, | |
| "learning_rate": 0.00010871557427476583, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.001492002571741275, | |
| "grad_norm": 0.0012471925001591444, | |
| "learning_rate": 0.00010436193873653361, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0015312657973134138, | |
| "grad_norm": 0.0012117830337956548, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0015705290228855526, | |
| "grad_norm": 0.0012083291076123714, | |
| "learning_rate": 9.563806126346642e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0016097922484576914, | |
| "grad_norm": 0.000552519632037729, | |
| "learning_rate": 9.128442572523417e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0016490554740298303, | |
| "grad_norm": 0.0005032281042076647, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.001688318699601969, | |
| "grad_norm": 0.0005083618452772498, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0017275819251741078, | |
| "grad_norm": 0.000337311445036903, | |
| "learning_rate": 7.835603860618972e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0017668451507462466, | |
| "grad_norm": 0.0011383501114323735, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0018061083763183856, | |
| "grad_norm": 0.0006025996990501881, | |
| "learning_rate": 6.992942004957271e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0018453716018905243, | |
| "grad_norm": 0.0002779973146971315, | |
| "learning_rate": 6.579798566743314e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.001884634827462663, | |
| "grad_norm": 0.0003003528981935233, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0019238980530348019, | |
| "grad_norm": 0.00026264195912517607, | |
| "learning_rate": 5.773817382593008e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0019631612786069406, | |
| "grad_norm": 0.00046483968617394567, | |
| "learning_rate": 5.382513867649663e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0019631612786069406, | |
| "eval_loss": 0.0007199626415967941, | |
| "eval_runtime": 2318.0998, | |
| "eval_samples_per_second": 9.252, | |
| "eval_steps_per_second": 4.626, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0020024245041790796, | |
| "grad_norm": 0.00016967965348158032, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.0020416877297512186, | |
| "grad_norm": 0.00023787225654814392, | |
| "learning_rate": 4.6270039165317605e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.002080950955323357, | |
| "grad_norm": 0.00023337510356213897, | |
| "learning_rate": 4.264235636489542e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.002120214180895496, | |
| "grad_norm": 0.0002012766053667292, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.0021594774064676346, | |
| "grad_norm": 0.00024241099890787154, | |
| "learning_rate": 3.5721239031346066e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.0021987406320397736, | |
| "grad_norm": 0.000289903546217829, | |
| "learning_rate": 3.244097923843398e-05, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.0022380038576119126, | |
| "grad_norm": 0.00017998011026065797, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.002277267083184051, | |
| "grad_norm": 0.00022262134007178247, | |
| "learning_rate": 2.6272266318987603e-05, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.00231653030875619, | |
| "grad_norm": 0.000276467326330021, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.002355793534328329, | |
| "grad_norm": 0.00016941240755841136, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0023950567599004676, | |
| "grad_norm": 0.0001846144295996055, | |
| "learning_rate": 1.808479557110081e-05, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.0024343199854726066, | |
| "grad_norm": 0.000201681352336891, | |
| "learning_rate": 1.566085541871145e-05, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.002473583211044745, | |
| "grad_norm": 0.0002414260379737243, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.002512846436616884, | |
| "grad_norm": 0.00019271476776339114, | |
| "learning_rate": 1.129891668217783e-05, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.002552109662189023, | |
| "grad_norm": 0.00026961477124132216, | |
| "learning_rate": 9.369221296335006e-06, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.0025913728877611617, | |
| "grad_norm": 0.0002070392220048234, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.0026306361133333006, | |
| "grad_norm": 0.00019015038560610265, | |
| "learning_rate": 6.030737921409169e-06, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.0026698993389054396, | |
| "grad_norm": 0.00013412888802122325, | |
| "learning_rate": 4.628304925177318e-06, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.002709162564477578, | |
| "grad_norm": 0.0001483526430092752, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.002748425790049717, | |
| "grad_norm": 0.00013009592657908797, | |
| "learning_rate": 2.3703992880066638e-06, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0027876890156218557, | |
| "grad_norm": 0.00021120438759680837, | |
| "learning_rate": 1.5192246987791981e-06, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.0028269522411939947, | |
| "grad_norm": 0.0002538190165068954, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.0028662154667661336, | |
| "grad_norm": 0.00025384288164786994, | |
| "learning_rate": 3.805301908254455e-07, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.002905478692338272, | |
| "grad_norm": 0.00015469672507606447, | |
| "learning_rate": 9.517784181422019e-08, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.002944741917910411, | |
| "grad_norm": 0.0003116559819318354, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.002944741917910411, | |
| "eval_loss": 0.0007300978759303689, | |
| "eval_runtime": 2317.0561, | |
| "eval_samples_per_second": 9.257, | |
| "eval_steps_per_second": 4.628, | |
| "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": 2.95132603613184e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |