| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0033489337832067717, | |
| "eval_steps": 500, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.697867566413543e-05, | |
| "grad_norm": 11.202531814575195, | |
| "learning_rate": 0.0001, | |
| "loss": 9.3451, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00013395735132827087, | |
| "grad_norm": 14.230999946594238, | |
| "learning_rate": 0.0002, | |
| "loss": 9.1198, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0002009360269924063, | |
| "grad_norm": 9.925089836120605, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 10.1381, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00026791470265654174, | |
| "grad_norm": 9.510652542114258, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 7.5019, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00033489337832067715, | |
| "grad_norm": 6.61540412902832, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 6.3718, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0004018720539848126, | |
| "grad_norm": 7.274428367614746, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 7.7984, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.000468850729648948, | |
| "grad_norm": 7.099924087524414, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 6.7624, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0005358294053130835, | |
| "grad_norm": 5.519874572753906, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 5.4764, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006028080809772189, | |
| "grad_norm": 11.996742248535156, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 3.9885, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0006697867566413543, | |
| "grad_norm": 11.48196792602539, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 9.2482, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007367654323054897, | |
| "grad_norm": 5.304096221923828, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 6.2764, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0008037441079696252, | |
| "grad_norm": 9.102093696594238, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 6.9416, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0008707227836337606, | |
| "grad_norm": 6.1233696937561035, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 4.4378, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.000937701459297896, | |
| "grad_norm": 7.5049052238464355, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 6.3169, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0010046801349620316, | |
| "grad_norm": 6.807133674621582, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 6.1685, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.001071658810626167, | |
| "grad_norm": 7.475444316864014, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 6.9925, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0011386374862903024, | |
| "grad_norm": 5.890412330627441, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 8.3801, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0012056161619544378, | |
| "grad_norm": 8.594086647033691, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 5.0054, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0012725948376185732, | |
| "grad_norm": 5.71251916885376, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 7.2484, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0013395735132827086, | |
| "grad_norm": 5.218650817871094, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 6.1231, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.001406552188946844, | |
| "grad_norm": 6.071516513824463, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 5.5233, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0014735308646109794, | |
| "grad_norm": 10.335101127624512, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 6.0461, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0015405095402751148, | |
| "grad_norm": 4.438607215881348, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 6.0407, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0016074882159392504, | |
| "grad_norm": 4.374053478240967, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 5.6196, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0016744668916033858, | |
| "grad_norm": 4.783155918121338, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 4.7725, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0017414455672675213, | |
| "grad_norm": 3.8684911727905273, | |
| "learning_rate": 0.0001, | |
| "loss": 3.5878, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0018084242429316567, | |
| "grad_norm": 4.367851257324219, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 7.1051, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.001875402918595792, | |
| "grad_norm": 4.9980268478393555, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 7.2694, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0019423815942599275, | |
| "grad_norm": 5.458781719207764, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 7.0591, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.002009360269924063, | |
| "grad_norm": 8.886860847473145, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 6.4029, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0020763389455881985, | |
| "grad_norm": 3.7991790771484375, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 3.7206, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.002143317621252334, | |
| "grad_norm": 5.644777774810791, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 4.2581, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0022102962969164693, | |
| "grad_norm": 3.7327921390533447, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 6.5899, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0022772749725806047, | |
| "grad_norm": 5.269270896911621, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 6.5028, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.00234425364824474, | |
| "grad_norm": 5.034127235412598, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 6.2797, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0024112323239088755, | |
| "grad_norm": 3.2906177043914795, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 4.7258, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.002478210999573011, | |
| "grad_norm": 7.394106388092041, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 4.7602, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0025451896752371464, | |
| "grad_norm": 5.268815040588379, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 7.6848, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0026121683509012818, | |
| "grad_norm": 6.3915228843688965, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 5.938, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.002679147026565417, | |
| "grad_norm": 4.054184436798096, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 6.9761, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0027461257022295526, | |
| "grad_norm": 15.989738464355469, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 8.2326, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.002813104377893688, | |
| "grad_norm": 4.472428798675537, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 6.3508, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0028800830535578234, | |
| "grad_norm": 5.130801677703857, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 5.0871, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.002947061729221959, | |
| "grad_norm": 4.2026047706604, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 6.9424, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0030140404048860942, | |
| "grad_norm": 3.842496156692505, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 3.4285, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0030810190805502296, | |
| "grad_norm": 6.607271671295166, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 6.3277, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0031479977562143655, | |
| "grad_norm": 5.300103664398193, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 7.2682, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.003214976431878501, | |
| "grad_norm": 4.57429838180542, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 4.5145, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0032819551075426363, | |
| "grad_norm": 4.920131206512451, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 3.9698, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0033489337832067717, | |
| "grad_norm": 3.9643123149871826, | |
| "learning_rate": 0.0, | |
| "loss": 5.5299, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "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": 6.53458201903104e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |