| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.13917884481558804, | |
| "eval_steps": 500, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0027835768963117608, | |
| "grad_norm": 27.78145408630371, | |
| "learning_rate": 0.0001, | |
| "loss": 9.1058, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0055671537926235215, | |
| "grad_norm": 28.777965545654297, | |
| "learning_rate": 0.0002, | |
| "loss": 9.0809, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.008350730688935281, | |
| "grad_norm": 26.920738220214844, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 6.4678, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.011134307585247043, | |
| "grad_norm": 87.16817474365234, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 2.2991, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013917884481558803, | |
| "grad_norm": 13.363322257995605, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 0.3409, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.016701461377870562, | |
| "grad_norm": 0.07291214913129807, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 0.0011, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.019485038274182326, | |
| "grad_norm": 0.0013751479564234614, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.022268615170494086, | |
| "grad_norm": 0.0007626891601830721, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.025052192066805846, | |
| "grad_norm": 0.007106999401003122, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.027835768963117607, | |
| "grad_norm": 0.015031544491648674, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.030619345859429367, | |
| "grad_norm": 0.0005385365802794695, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.033402922755741124, | |
| "grad_norm": 5.490898609161377, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 0.2958, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03618649965205289, | |
| "grad_norm": 3.0343241691589355, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 0.1383, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03897007654836465, | |
| "grad_norm": 2.5563437588971283e-07, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04175365344467641, | |
| "grad_norm": 1.0416483746666927e-06, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04453723034098817, | |
| "grad_norm": 3.3582866191864014, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 0.0539, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04732080723729993, | |
| "grad_norm": 2.731654967647046e-05, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05010438413361169, | |
| "grad_norm": 0.00023694017727393657, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05288796102992345, | |
| "grad_norm": 7.17986536026001, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 0.1399, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.055671537926235214, | |
| "grad_norm": 0.0030062685254961252, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05845511482254697, | |
| "grad_norm": 0.004294949118047953, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.061238691718858734, | |
| "grad_norm": 0.002961142221465707, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.06402226861517049, | |
| "grad_norm": 0.0030834635253995657, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06680584551148225, | |
| "grad_norm": 0.005313623696565628, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06958942240779402, | |
| "grad_norm": 0.002946143038570881, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07237299930410578, | |
| "grad_norm": 0.004986815620213747, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.07515657620041753, | |
| "grad_norm": 0.014825048856437206, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 0.0001, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0779401530967293, | |
| "grad_norm": 0.020950036123394966, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 0.0001, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.08072372999304106, | |
| "grad_norm": 0.010169435292482376, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.08350730688935282, | |
| "grad_norm": 0.005563807673752308, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08629088378566457, | |
| "grad_norm": 0.0033290411811321974, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.08907446068197634, | |
| "grad_norm": 0.0016648604068905115, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0918580375782881, | |
| "grad_norm": 0.0010142697719857097, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.09464161447459986, | |
| "grad_norm": 0.00054915965301916, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.09742519137091162, | |
| "grad_norm": 0.00043891073437407613, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.10020876826722339, | |
| "grad_norm": 0.00028968678088858724, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.10299234516353514, | |
| "grad_norm": 0.0002959763223771006, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.1057759220598469, | |
| "grad_norm": 0.00021965286578051746, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.10855949895615867, | |
| "grad_norm": 0.00015132376574911177, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.11134307585247043, | |
| "grad_norm": 0.3647041320800781, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 0.002, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11412665274878218, | |
| "grad_norm": 9.909908112604171e-05, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.11691022964509394, | |
| "grad_norm": 0.00010844790085684508, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.11969380654140571, | |
| "grad_norm": 8.147337939590216e-05, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.12247738343771747, | |
| "grad_norm": 2.1904272216488607e-05, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.12526096033402923, | |
| "grad_norm": 4.966600681655109e-05, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.12804453723034098, | |
| "grad_norm": 9.887644409900531e-05, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.13082811412665274, | |
| "grad_norm": 7.535777695011348e-05, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.1336116910229645, | |
| "grad_norm": 3.8577378290938213e-05, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.13639526791927628, | |
| "grad_norm": 6.952096737222746e-05, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.13917884481558804, | |
| "grad_norm": 7.99436165834777e-05, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "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": 7.56725029231657e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |