| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.09555661729574773, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012740882306099697, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012740882306099697, | |
| "eval_loss": NaN, | |
| "eval_runtime": 147.3006, | |
| "eval_samples_per_second": 4.487, | |
| "eval_steps_per_second": 2.247, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0025481764612199395, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003822264691829909, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005096352922439879, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001999048221581858, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006370441153049849, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019961946980917456, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007644529383659818, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008918617614269788, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019848077530122083, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010192705844879758, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019762960071199333, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.011466794075489728, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012740882306099698, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001953716950748227, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014014970536709668, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.015289058767319636, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.016563146997929608, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000190630778703665, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.017837235228539576, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018870108331782217, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.019111323459149548, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.020385411689759516, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001843391445812886, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.021659499920369484, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001819152044288992, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.022933588150979456, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.024207676381589424, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001766044443118978, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.025481764612199396, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001737277336810124, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.026755852842809364, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.028029941073419336, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016755902076156604, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.029304029304029304, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016427876096865394, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.030578117534639272, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03185220576524924, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001573576436351046, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03185220576524924, | |
| "eval_loss": NaN, | |
| "eval_runtime": 147.6892, | |
| "eval_samples_per_second": 4.476, | |
| "eval_steps_per_second": 2.241, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.033126293995859216, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001537299608346824, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.034400382226469184, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03567447045707915, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014617486132350343, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03694855868768912, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014226182617406996, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.038222646918299095, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.039496735148909064, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013420201433256689, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.04077082337951903, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013007057995042732, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.042044911610129, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.04331899984073897, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012164396139381029, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.044593088071348944, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011736481776669306, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04586717630195891, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04714126453256888, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010871557427476583, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.04841535276317885, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010436193873653361, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.049689440993788817, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.05096352922439879, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.563806126346642e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05223761745500876, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.128442572523417e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.05351170568561873, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.054785793916228696, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.05605988214683867, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.835603860618972e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.05733397037744864, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05860805860805861, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.992942004957271e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.059882146838668576, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.579798566743314e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.061156235069278544, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06243032329988852, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.773817382593008e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06370441153049848, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.382513867649663e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06370441153049848, | |
| "eval_loss": NaN, | |
| "eval_runtime": 147.851, | |
| "eval_samples_per_second": 4.471, | |
| "eval_steps_per_second": 2.239, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06497849976110846, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.06625258799171843, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6270039165317605e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.0675266762223284, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.264235636489542e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.06880076445293837, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.07007485268354834, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5721239031346066e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.0713489409141583, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.244097923843398e-05, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.07262302914476827, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.07389711737537824, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6272266318987603e-05, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.07517120560598821, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.07644529383659819, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.07771938206720816, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.808479557110081e-05, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.07899347029781813, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.566085541871145e-05, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.0802675585284281, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.08154164675903806, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.129891668217783e-05, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.08281573498964803, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.369221296335006e-06, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.084089823220258, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.08536391145086797, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.030737921409169e-06, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.08663799968147794, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.628304925177318e-06, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.08791208791208792, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.08918617614269789, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3703992880066638e-06, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.09046026437330786, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5192246987791981e-06, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.09173435260391782, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.09300844083452779, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.805301908254455e-07, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.09428252906513776, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.517784181422019e-08, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.09555661729574773, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.09555661729574773, | |
| "eval_loss": NaN, | |
| "eval_runtime": 147.8368, | |
| "eval_samples_per_second": 4.471, | |
| "eval_steps_per_second": 2.239, | |
| "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": 1.054713575374848e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |