| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04324947740214806, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005766596986953074, | |
| "grad_norm": 0.5187491774559021, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.8061, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005766596986953074, | |
| "eval_loss": 0.7736253142356873, | |
| "eval_runtime": 802.3416, | |
| "eval_samples_per_second": 1.821, | |
| "eval_steps_per_second": 0.911, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011533193973906149, | |
| "grad_norm": 0.48624253273010254, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.8548, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0017299790960859224, | |
| "grad_norm": 0.428561806678772, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5315, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0023066387947812297, | |
| "grad_norm": 0.43896380066871643, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 0.7549, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0028832984934765373, | |
| "grad_norm": 0.3388628661632538, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 0.655, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003459958192171845, | |
| "grad_norm": 0.3486120104789734, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.6753, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004036617890867152, | |
| "grad_norm": 0.37648850679397583, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 0.6459, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0046132775895624594, | |
| "grad_norm": 0.4131505787372589, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 0.5957, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005189937288257767, | |
| "grad_norm": 0.46566611528396606, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.6302, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0057665969869530745, | |
| "grad_norm": 0.3140219449996948, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 0.6051, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006343256685648382, | |
| "grad_norm": 0.2500462532043457, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.6843, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00691991638434369, | |
| "grad_norm": 0.30054011940956116, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.6803, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.007496576083038996, | |
| "grad_norm": 0.3195454776287079, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 0.557, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.008073235781734304, | |
| "grad_norm": 0.294595867395401, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 0.7265, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.008649895480429612, | |
| "grad_norm": 0.3167280852794647, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.8634, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009226555179124919, | |
| "grad_norm": 0.2780252993106842, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 0.7195, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.009803214877820226, | |
| "grad_norm": 0.2810973823070526, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 0.6641, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.010379874576515534, | |
| "grad_norm": 0.2534291446208954, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.7635, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01095653427521084, | |
| "grad_norm": 0.25898292660713196, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.6175, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.011533193973906149, | |
| "grad_norm": 0.2497512251138687, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 0.6251, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.012109853672601456, | |
| "grad_norm": 0.3540191352367401, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.7004, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.012686513371296764, | |
| "grad_norm": 0.25450509786605835, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 0.6049, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01326317306999207, | |
| "grad_norm": 0.33254560828208923, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 0.5982, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.01383983276868738, | |
| "grad_norm": 0.33598387241363525, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.9153, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.014416492467382686, | |
| "grad_norm": 0.23375222086906433, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 0.677, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.014416492467382686, | |
| "eval_loss": 0.670843780040741, | |
| "eval_runtime": 804.822, | |
| "eval_samples_per_second": 1.815, | |
| "eval_steps_per_second": 0.908, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.014993152166077993, | |
| "grad_norm": 0.3155810236930847, | |
| "learning_rate": 7.68649804173412e-05, | |
| "loss": 0.9014, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.015569811864773301, | |
| "grad_norm": 0.3011918067932129, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.4967, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.016146471563468608, | |
| "grad_norm": 0.3234626054763794, | |
| "learning_rate": 7.308743066175172e-05, | |
| "loss": 0.6157, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.016723131262163914, | |
| "grad_norm": 0.28305330872535706, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 0.6846, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.017299790960859224, | |
| "grad_norm": 0.2650391161441803, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.6766, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01787645065955453, | |
| "grad_norm": 0.2921651005744934, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 0.4771, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.018453110358249838, | |
| "grad_norm": 0.26164016127586365, | |
| "learning_rate": 6.503528997521366e-05, | |
| "loss": 0.6642, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.019029770056945144, | |
| "grad_norm": 0.28726956248283386, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.5747, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.01960642975564045, | |
| "grad_norm": 0.3075750470161438, | |
| "learning_rate": 6.0821980696905146e-05, | |
| "loss": 0.5039, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.02018308945433576, | |
| "grad_norm": 0.2462749481201172, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.5682, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.020759749153031068, | |
| "grad_norm": 0.3078925311565399, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.6167, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.021336408851726375, | |
| "grad_norm": 0.30313003063201904, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 0.6987, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.02191306855042168, | |
| "grad_norm": 0.30238619446754456, | |
| "learning_rate": 5.218096936826681e-05, | |
| "loss": 0.6085, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.02248972824911699, | |
| "grad_norm": 0.34323957562446594, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6488, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.023066387947812298, | |
| "grad_norm": 0.3006385862827301, | |
| "learning_rate": 4.781903063173321e-05, | |
| "loss": 0.5428, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.023643047646507605, | |
| "grad_norm": 0.28719136118888855, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 0.6068, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.02421970734520291, | |
| "grad_norm": 0.34415391087532043, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.6461, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.024796367043898218, | |
| "grad_norm": 0.257804811000824, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.6974, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.025373026742593528, | |
| "grad_norm": 0.3095720112323761, | |
| "learning_rate": 3.917801930309486e-05, | |
| "loss": 0.7856, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.025949686441288835, | |
| "grad_norm": 0.3070933520793915, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.8322, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02652634613998414, | |
| "grad_norm": 0.28544628620147705, | |
| "learning_rate": 3.4964710024786354e-05, | |
| "loss": 0.591, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.027103005838679448, | |
| "grad_norm": 0.3209655284881592, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 0.9191, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.02767966553737476, | |
| "grad_norm": 0.30374830961227417, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.5097, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.028256325236070065, | |
| "grad_norm": 0.41248422861099243, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 0.6574, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.028832984934765372, | |
| "grad_norm": 0.3581903576850891, | |
| "learning_rate": 2.6912569338248315e-05, | |
| "loss": 0.8603, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.028832984934765372, | |
| "eval_loss": 0.6622347831726074, | |
| "eval_runtime": 804.7816, | |
| "eval_samples_per_second": 1.815, | |
| "eval_steps_per_second": 0.908, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02940964463346068, | |
| "grad_norm": 0.2843848168849945, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.7885, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.029986304332155985, | |
| "grad_norm": 0.2316364049911499, | |
| "learning_rate": 2.3135019582658802e-05, | |
| "loss": 0.662, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.030562964030851295, | |
| "grad_norm": 0.2592354118824005, | |
| "learning_rate": 2.132117818244771e-05, | |
| "loss": 0.7197, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.031139623729546602, | |
| "grad_norm": 0.20807218551635742, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.4957, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.03171628342824191, | |
| "grad_norm": 0.22142092883586884, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 0.516, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.032292943126937215, | |
| "grad_norm": 0.2078356295824051, | |
| "learning_rate": 1.622048961921699e-05, | |
| "loss": 0.565, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.032869602825632525, | |
| "grad_norm": 0.24698881804943085, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.9348, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.03344626252432783, | |
| "grad_norm": 0.19391882419586182, | |
| "learning_rate": 1.3136133159493802e-05, | |
| "loss": 0.6557, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.03402292222302314, | |
| "grad_norm": 0.22842319309711456, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 0.8331, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.03459958192171845, | |
| "grad_norm": 0.2654271125793457, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.6458, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.03517624162041375, | |
| "grad_norm": 0.23442628979682922, | |
| "learning_rate": 9.042397785550405e-06, | |
| "loss": 0.5227, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.03575290131910906, | |
| "grad_norm": 0.24609215557575226, | |
| "learning_rate": 7.830427709355725e-06, | |
| "loss": 0.5817, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.036329561017804365, | |
| "grad_norm": 0.23174376785755157, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.9031, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.036906220716499676, | |
| "grad_norm": 0.2596435248851776, | |
| "learning_rate": 5.649458341088915e-06, | |
| "loss": 0.712, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.037482880415194986, | |
| "grad_norm": 0.21098394691944122, | |
| "learning_rate": 4.684610648167503e-06, | |
| "loss": 0.7175, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.03805954011389029, | |
| "grad_norm": 0.22552695870399475, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.6059, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.0386361998125856, | |
| "grad_norm": 0.2653113305568695, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.5966, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.0392128595112809, | |
| "grad_norm": 0.22038479149341583, | |
| "learning_rate": 2.314152462588659e-06, | |
| "loss": 0.7124, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.03978951920997621, | |
| "grad_norm": 0.22684645652770996, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.6121, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.04036617890867152, | |
| "grad_norm": 0.2504723370075226, | |
| "learning_rate": 1.1851996440033319e-06, | |
| "loss": 0.6044, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.040942838607366826, | |
| "grad_norm": 0.26648664474487305, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 0.6483, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.041519498306062136, | |
| "grad_norm": 0.2237248718738556, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.5942, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.04209615800475744, | |
| "grad_norm": 0.22325119376182556, | |
| "learning_rate": 1.9026509541272275e-07, | |
| "loss": 0.6714, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.04267281770345275, | |
| "grad_norm": 0.2624514400959015, | |
| "learning_rate": 4.7588920907110094e-08, | |
| "loss": 0.7899, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.04324947740214806, | |
| "grad_norm": 0.2703254520893097, | |
| "learning_rate": 0.0, | |
| "loss": 0.5225, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.04324947740214806, | |
| "eval_loss": 0.6601256728172302, | |
| "eval_runtime": 803.8545, | |
| "eval_samples_per_second": 1.817, | |
| "eval_steps_per_second": 0.909, | |
| "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": 2.148511261875241e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |