| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.11916583912611718, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0015888778550148957, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015888778550148957, | |
| "eval_loss": NaN, | |
| "eval_runtime": 125.2901, | |
| "eval_samples_per_second": 4.23, | |
| "eval_steps_per_second": 2.115, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0031777557100297915, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004766633565044687, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006355511420059583, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001999048221581858, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.007944389275074478, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019961946980917456, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009533267130089375, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01112214498510427, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019848077530122083, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.012711022840119166, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019762960071199333, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.014299900695134062, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.015888778550148957, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001953716950748227, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01747765640516385, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01906653426017875, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.020655412115193644, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000190630778703665, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.02224428997020854, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018870108331782217, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.023833167825223437, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02542204568023833, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001843391445812886, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.027010923535253226, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001819152044288992, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.028599801390268124, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03018867924528302, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001766044443118978, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.031777557100297914, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001737277336810124, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03336643495531281, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0349553128103277, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016755902076156604, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.036544190665342605, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016427876096865394, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0381330685203575, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.039721946375372394, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001573576436351046, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.039721946375372394, | |
| "eval_loss": NaN, | |
| "eval_runtime": 126.2145, | |
| "eval_samples_per_second": 4.199, | |
| "eval_steps_per_second": 2.1, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04131082423038729, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001537299608346824, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.04289970208540218, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.04448857994041708, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014617486132350343, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.04607745779543198, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014226182617406996, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.047666335650446874, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04925521350546177, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013420201433256689, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.05084409136047666, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013007057995042732, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.05243296921549156, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.05402184707050645, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012164396139381029, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.05561072492552135, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011736481776669306, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.05719960278053625, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.058788480635551144, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010871557427476583, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.06037735849056604, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010436193873653361, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.06196623634558093, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.06355511420059583, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.563806126346642e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06514399205561072, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.128442572523417e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.06673286991062562, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.06832174776564051, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0699106256206554, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.835603860618972e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.07149950347567031, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.07308838133068521, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.992942004957271e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0746772591857001, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.579798566743314e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.076266137040715, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0778550148957299, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.773817382593008e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.07944389275074479, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.382513867649663e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07944389275074479, | |
| "eval_loss": NaN, | |
| "eval_runtime": 126.0889, | |
| "eval_samples_per_second": 4.203, | |
| "eval_steps_per_second": 2.102, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08103277060575968, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.08262164846077458, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6270039165317605e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.08421052631578947, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.264235636489542e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.08579940417080437, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.08738828202581926, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5721239031346066e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.08897715988083416, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.244097923843398e-05, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.09056603773584905, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.09215491559086396, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6272266318987603e-05, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.09374379344587885, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.09533267130089375, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.09692154915590864, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.808479557110081e-05, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.09851042701092354, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.566085541871145e-05, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.10009930486593843, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.10168818272095333, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.129891668217783e-05, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.10327706057596822, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.369221296335006e-06, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.10486593843098312, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.10645481628599801, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.030737921409169e-06, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.1080436941410129, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.628304925177318e-06, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.1096325719960278, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.1112214498510427, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3703992880066638e-06, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1128103277060576, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5192246987791981e-06, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.1143992055610725, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.11598808341608739, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.805301908254455e-07, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.11757696127110229, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.517784181422019e-08, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.11916583912611718, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.11916583912611718, | |
| "eval_loss": NaN, | |
| "eval_runtime": 126.0102, | |
| "eval_samples_per_second": 4.206, | |
| "eval_steps_per_second": 2.103, | |
| "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": 1.038999181244498e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |