| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.06194507536650836, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008259343382201115, | |
| "grad_norm": 1677.547119140625, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 103.096, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008259343382201115, | |
| "eval_loss": 13.492105484008789, | |
| "eval_runtime": 244.2801, | |
| "eval_samples_per_second": 4.176, | |
| "eval_steps_per_second": 2.088, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001651868676440223, | |
| "grad_norm": 1696.8392333984375, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 105.2538, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0024778030146603344, | |
| "grad_norm": 941.0369873046875, | |
| "learning_rate": 0.0001, | |
| "loss": 66.4773, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003303737352880446, | |
| "grad_norm": 699.8087768554688, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 29.6233, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0041296716911005575, | |
| "grad_norm": 504.3501892089844, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 9.9401, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004955606029320669, | |
| "grad_norm": 1.2597764730453491, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.0057, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005781540367540781, | |
| "grad_norm": 0.005221178755164146, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006607474705760892, | |
| "grad_norm": 0.026343591511249542, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 0.0001, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007433409043981004, | |
| "grad_norm": 0.6239492297172546, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.0002, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008259343382201115, | |
| "grad_norm": 0.001214036368764937, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009085277720421227, | |
| "grad_norm": 0.0005943904398009181, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.009911212058641337, | |
| "grad_norm": 0.00028382017626427114, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01073714639686145, | |
| "grad_norm": 0.00030877735116519034, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.011563080735081561, | |
| "grad_norm": 0.00028087597456760705, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.012389015073301672, | |
| "grad_norm": 0.00024960265727713704, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.013214949411521784, | |
| "grad_norm": 0.0001821557671064511, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.014040883749741896, | |
| "grad_norm": 0.00019730778876692057, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.014866818087962008, | |
| "grad_norm": 0.0001254954986507073, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.015692752426182118, | |
| "grad_norm": 0.00014692585682496428, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01651868676440223, | |
| "grad_norm": 0.00016185363347176462, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.017344621102622342, | |
| "grad_norm": 0.00012402540596667677, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.018170555440842454, | |
| "grad_norm": 8.475293725496158e-05, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.018996489779062563, | |
| "grad_norm": 7.959387585287914e-05, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.019822424117282675, | |
| "grad_norm": 7.412952982122079e-05, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.020648358455502787, | |
| "grad_norm": 5.231930845184252e-05, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.020648358455502787, | |
| "eval_loss": 4.6826649224840367e-08, | |
| "eval_runtime": 246.3015, | |
| "eval_samples_per_second": 4.141, | |
| "eval_steps_per_second": 2.071, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0214742927937229, | |
| "grad_norm": 6.69602959533222e-05, | |
| "learning_rate": 7.68649804173412e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.02230022713194301, | |
| "grad_norm": 5.6196640798589215e-05, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.023126161470163123, | |
| "grad_norm": 4.406289372127503e-05, | |
| "learning_rate": 7.308743066175172e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.023952095808383235, | |
| "grad_norm": 6.054918412701227e-05, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.024778030146603344, | |
| "grad_norm": 3.9682545320829377e-05, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.025603964484823456, | |
| "grad_norm": 4.490738865570165e-05, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.026429898823043568, | |
| "grad_norm": 3.491883762762882e-05, | |
| "learning_rate": 6.503528997521366e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.02725583316126368, | |
| "grad_norm": 3.7224541301839054e-05, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.02808176749948379, | |
| "grad_norm": 3.5606222809292376e-05, | |
| "learning_rate": 6.0821980696905146e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.028907701837703904, | |
| "grad_norm": 3.647877383627929e-05, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.029733636175924016, | |
| "grad_norm": 4.453373549040407e-05, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.030559570514144124, | |
| "grad_norm": 3.978102540713735e-05, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.031385504852364236, | |
| "grad_norm": 3.958147135563195e-05, | |
| "learning_rate": 5.218096936826681e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.03221143919058435, | |
| "grad_norm": 4.5364879042608663e-05, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.03303737352880446, | |
| "grad_norm": 4.673544754041359e-05, | |
| "learning_rate": 4.781903063173321e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03386330786702457, | |
| "grad_norm": 4.447162427823059e-05, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.034689242205244684, | |
| "grad_norm": 4.427820385899395e-05, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.035515176543464796, | |
| "grad_norm": 4.0053564589470625e-05, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.03634111088168491, | |
| "grad_norm": 4.3088726670248434e-05, | |
| "learning_rate": 3.917801930309486e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.03716704521990502, | |
| "grad_norm": 4.5698117901338264e-05, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.037992979558125126, | |
| "grad_norm": 5.060286639491096e-05, | |
| "learning_rate": 3.4964710024786354e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.03881891389634524, | |
| "grad_norm": 5.1584192988229915e-05, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.03964484823456535, | |
| "grad_norm": 5.470534597407095e-05, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.04047078257278546, | |
| "grad_norm": 5.4673917475156486e-05, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.041296716911005574, | |
| "grad_norm": 5.439592860057019e-05, | |
| "learning_rate": 2.6912569338248315e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.041296716911005574, | |
| "eval_loss": 2.423142397844913e-08, | |
| "eval_runtime": 245.9876, | |
| "eval_samples_per_second": 4.147, | |
| "eval_steps_per_second": 2.073, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.042122651249225686, | |
| "grad_norm": 0.00018684551469050348, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.0429485855874458, | |
| "grad_norm": 0.000440300878835842, | |
| "learning_rate": 2.3135019582658802e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.04377451992566591, | |
| "grad_norm": 0.0004225766460876912, | |
| "learning_rate": 2.132117818244771e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.04460045426388602, | |
| "grad_norm": 0.0001671666104812175, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.045426388602106134, | |
| "grad_norm": 0.0016776153352111578, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.046252322940326246, | |
| "grad_norm": 5.6094853789545596e-05, | |
| "learning_rate": 1.622048961921699e-05, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.04707825727854636, | |
| "grad_norm": 6.723932892782614e-05, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.04790419161676647, | |
| "grad_norm": 0.00029996901866979897, | |
| "learning_rate": 1.3136133159493802e-05, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.04873012595498658, | |
| "grad_norm": 5.901329132029787e-05, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.04955606029320669, | |
| "grad_norm": 0.0002947987522929907, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0503819946314268, | |
| "grad_norm": 4.6376018872251734e-05, | |
| "learning_rate": 9.042397785550405e-06, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.05120792896964691, | |
| "grad_norm": 4.3167357944184914e-05, | |
| "learning_rate": 7.830427709355725e-06, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.05203386330786702, | |
| "grad_norm": 0.000724351208191365, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.052859797646087135, | |
| "grad_norm": 3.387459219084121e-05, | |
| "learning_rate": 5.649458341088915e-06, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.05368573198430725, | |
| "grad_norm": 4.283706221031025e-05, | |
| "learning_rate": 4.684610648167503e-06, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.05451166632252736, | |
| "grad_norm": 3.590101550798863e-05, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.05533760066074747, | |
| "grad_norm": 3.176596146658994e-05, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.05616353499896758, | |
| "grad_norm": 4.798637019121088e-05, | |
| "learning_rate": 2.314152462588659e-06, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.056989469337187695, | |
| "grad_norm": 4.3243224354228005e-05, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.05781540367540781, | |
| "grad_norm": 3.807907341979444e-05, | |
| "learning_rate": 1.1851996440033319e-06, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.05864133801362792, | |
| "grad_norm": 3.945823846152052e-05, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.05946727235184803, | |
| "grad_norm": 3.7366255128290504e-05, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.06029320669006814, | |
| "grad_norm": 3.241099329898134e-05, | |
| "learning_rate": 1.9026509541272275e-07, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.06111914102828825, | |
| "grad_norm": 3.987809031968936e-05, | |
| "learning_rate": 4.7588920907110094e-08, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.06194507536650836, | |
| "grad_norm": 3.887756975018419e-05, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.06194507536650836, | |
| "eval_loss": 1.59335264982019e-08, | |
| "eval_runtime": 245.9135, | |
| "eval_samples_per_second": 4.148, | |
| "eval_steps_per_second": 2.074, | |
| "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": 1.0626483425692877e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |