| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.058519457719691796, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007802594362625573, | |
| "grad_norm": 0.3376312553882599, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.4989, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007802594362625573, | |
| "eval_loss": 0.8446513414382935, | |
| "eval_runtime": 321.1678, | |
| "eval_samples_per_second": 3.363, | |
| "eval_steps_per_second": 1.681, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015605188725251145, | |
| "grad_norm": 0.4070318341255188, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.6737, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002340778308787672, | |
| "grad_norm": 0.4004059433937073, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5249, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003121037745050229, | |
| "grad_norm": 0.43589961528778076, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 0.6278, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0039012971813127866, | |
| "grad_norm": 0.5050280690193176, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 0.6549, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004681556617575344, | |
| "grad_norm": 0.40668612718582153, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.5572, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005461816053837901, | |
| "grad_norm": 0.4934292733669281, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 0.6219, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006242075490100458, | |
| "grad_norm": 0.5753898620605469, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 0.5658, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007022334926363016, | |
| "grad_norm": 0.5027673840522766, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.6963, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007802594362625573, | |
| "grad_norm": 0.47841089963912964, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 0.6117, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00858285379888813, | |
| "grad_norm": 0.4685758948326111, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.561, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.009363113235150688, | |
| "grad_norm": 0.5550876259803772, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.7298, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.010143372671413246, | |
| "grad_norm": 0.48063692450523376, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 0.7098, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.010923632107675801, | |
| "grad_norm": 0.4520593583583832, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 0.6776, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.011703891543938359, | |
| "grad_norm": 0.5039393305778503, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.8103, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.012484150980200916, | |
| "grad_norm": 0.4985882043838501, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 0.702, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.013264410416463474, | |
| "grad_norm": 0.4833678603172302, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 0.7118, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.014044669852726031, | |
| "grad_norm": 0.45505037903785706, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.6413, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.014824929288988589, | |
| "grad_norm": 0.5279719829559326, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.7873, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.015605188725251146, | |
| "grad_norm": 0.5257707834243774, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 0.7481, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.016385448161513702, | |
| "grad_norm": 0.5363844633102417, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.7771, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01716570759777626, | |
| "grad_norm": 0.5524177551269531, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 0.8244, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.017945967034038817, | |
| "grad_norm": 0.5710583329200745, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 0.7883, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.018726226470301376, | |
| "grad_norm": 0.5935850739479065, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.8224, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.019506485906563932, | |
| "grad_norm": 0.6716726422309875, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 0.9925, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.019506485906563932, | |
| "eval_loss": 0.7827931642532349, | |
| "eval_runtime": 323.3131, | |
| "eval_samples_per_second": 3.34, | |
| "eval_steps_per_second": 1.67, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02028674534282649, | |
| "grad_norm": 0.7108809351921082, | |
| "learning_rate": 7.68649804173412e-05, | |
| "loss": 0.8741, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.021067004779089047, | |
| "grad_norm": 0.7109420299530029, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.9355, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.021847264215351603, | |
| "grad_norm": 0.6290819048881531, | |
| "learning_rate": 7.308743066175172e-05, | |
| "loss": 0.8823, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.022627523651614162, | |
| "grad_norm": 0.6449434161186218, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 0.8747, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.023407783087876718, | |
| "grad_norm": 0.7190560102462769, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.9264, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.024188042524139277, | |
| "grad_norm": 0.6574559807777405, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 0.8356, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.024968301960401833, | |
| "grad_norm": 0.6734890937805176, | |
| "learning_rate": 6.503528997521366e-05, | |
| "loss": 0.9268, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.025748561396664392, | |
| "grad_norm": 0.7330193519592285, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.8603, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.026528820832926948, | |
| "grad_norm": 0.7113292813301086, | |
| "learning_rate": 6.0821980696905146e-05, | |
| "loss": 0.8205, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.027309080269189507, | |
| "grad_norm": 0.6743346452713013, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.8219, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.028089339705452063, | |
| "grad_norm": 0.6742866039276123, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.8635, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.02886959914171462, | |
| "grad_norm": 0.7305226922035217, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 0.818, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.029649858577977178, | |
| "grad_norm": 0.6999145150184631, | |
| "learning_rate": 5.218096936826681e-05, | |
| "loss": 0.8282, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.030430118014239733, | |
| "grad_norm": 0.6912006139755249, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7905, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.031210377450502293, | |
| "grad_norm": 0.7328338623046875, | |
| "learning_rate": 4.781903063173321e-05, | |
| "loss": 0.8069, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03199063688676485, | |
| "grad_norm": 0.7178049087524414, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 0.7919, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.032770896323027404, | |
| "grad_norm": 0.7273955941200256, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.8151, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.03355115575928996, | |
| "grad_norm": 0.7298927307128906, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.8524, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.03433141519555252, | |
| "grad_norm": 0.740074872970581, | |
| "learning_rate": 3.917801930309486e-05, | |
| "loss": 0.8144, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.03511167463181508, | |
| "grad_norm": 0.7409592866897583, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.8217, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.035891934068077634, | |
| "grad_norm": 0.757175087928772, | |
| "learning_rate": 3.4964710024786354e-05, | |
| "loss": 0.7642, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.03667219350434019, | |
| "grad_norm": 0.8015655875205994, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 0.7827, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.03745245294060275, | |
| "grad_norm": 0.7460522651672363, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.7761, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.038232712376865305, | |
| "grad_norm": 0.8603819608688354, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 0.7828, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.039012971813127864, | |
| "grad_norm": 1.0592442750930786, | |
| "learning_rate": 2.6912569338248315e-05, | |
| "loss": 0.8512, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.039012971813127864, | |
| "eval_loss": 0.7553926706314087, | |
| "eval_runtime": 323.1681, | |
| "eval_samples_per_second": 3.342, | |
| "eval_steps_per_second": 1.671, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03979323124939042, | |
| "grad_norm": 0.2862579822540283, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.507, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.04057349068565298, | |
| "grad_norm": 0.3461783230304718, | |
| "learning_rate": 2.3135019582658802e-05, | |
| "loss": 0.5549, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.041353750121915535, | |
| "grad_norm": 0.4043627977371216, | |
| "learning_rate": 2.132117818244771e-05, | |
| "loss": 0.6321, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.042134009558178094, | |
| "grad_norm": 0.37553367018699646, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.571, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.04291426899444065, | |
| "grad_norm": 0.36022651195526123, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 0.5375, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.043694528430703206, | |
| "grad_norm": 0.4114338457584381, | |
| "learning_rate": 1.622048961921699e-05, | |
| "loss": 0.6081, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.044474787866965765, | |
| "grad_norm": 0.3871912956237793, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.6099, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.045255047303228324, | |
| "grad_norm": 0.40150532126426697, | |
| "learning_rate": 1.3136133159493802e-05, | |
| "loss": 0.6333, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.04603530673949088, | |
| "grad_norm": 0.49420806765556335, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 0.773, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.046815566175753436, | |
| "grad_norm": 0.42875587940216064, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.5722, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.047595825612015995, | |
| "grad_norm": 0.4141090512275696, | |
| "learning_rate": 9.042397785550405e-06, | |
| "loss": 0.6371, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.048376085048278554, | |
| "grad_norm": 0.42042094469070435, | |
| "learning_rate": 7.830427709355725e-06, | |
| "loss": 0.6135, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.04915634448454111, | |
| "grad_norm": 0.4620630145072937, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.7216, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.049936603920803666, | |
| "grad_norm": 0.47221145033836365, | |
| "learning_rate": 5.649458341088915e-06, | |
| "loss": 0.6438, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.050716863357066225, | |
| "grad_norm": 0.4742897152900696, | |
| "learning_rate": 4.684610648167503e-06, | |
| "loss": 0.7366, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.051497122793328784, | |
| "grad_norm": 0.4719804525375366, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.6938, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.052277382229591336, | |
| "grad_norm": 0.49254298210144043, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.7749, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.053057641665853895, | |
| "grad_norm": 0.521112859249115, | |
| "learning_rate": 2.314152462588659e-06, | |
| "loss": 0.7219, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.053837901102116455, | |
| "grad_norm": 0.5138411521911621, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.832, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.054618160538379014, | |
| "grad_norm": 0.5415810942649841, | |
| "learning_rate": 1.1851996440033319e-06, | |
| "loss": 0.8144, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.055398419974641566, | |
| "grad_norm": 0.6076228022575378, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 0.9642, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.056178679410904125, | |
| "grad_norm": 0.5630006194114685, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.7559, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.056958938847166685, | |
| "grad_norm": 0.608703076839447, | |
| "learning_rate": 1.9026509541272275e-07, | |
| "loss": 0.8729, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.05773919828342924, | |
| "grad_norm": 0.569412887096405, | |
| "learning_rate": 4.7588920907110094e-08, | |
| "loss": 0.7729, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.058519457719691796, | |
| "grad_norm": 0.6440850496292114, | |
| "learning_rate": 0.0, | |
| "loss": 0.8444, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.058519457719691796, | |
| "eval_loss": 0.7578212022781372, | |
| "eval_runtime": 323.0666, | |
| "eval_samples_per_second": 3.343, | |
| "eval_steps_per_second": 1.671, | |
| "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": 1.163503502056489e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |