| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.06487187804086929, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0025948751216347712, | |
| "grad_norm": 114.6451644897461, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 86.6227, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0025948751216347712, | |
| "eval_loss": 11.188401222229004, | |
| "eval_runtime": 240.2405, | |
| "eval_samples_per_second": 1.353, | |
| "eval_steps_per_second": 0.678, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0051897502432695424, | |
| "grad_norm": 110.34148406982422, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 86.6639, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007784625364904314, | |
| "grad_norm": 140.974365234375, | |
| "learning_rate": 0.0001, | |
| "loss": 86.2836, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010379500486539085, | |
| "grad_norm": 107.53729248046875, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 76.8209, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.012974375608173857, | |
| "grad_norm": 58.06427001953125, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 70.0069, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015569250729808628, | |
| "grad_norm": 63.29356384277344, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 53.7268, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.018164125851443398, | |
| "grad_norm": 64.70842742919922, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 43.4032, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02075900097307817, | |
| "grad_norm": 66.98622131347656, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 30.8297, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02335387609471294, | |
| "grad_norm": 75.47815704345703, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 19.1012, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.025948751216347713, | |
| "grad_norm": 59.91986083984375, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 7.854, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.028543626337982485, | |
| "grad_norm": 61.32648468017578, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 5.9719, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.031138501459617256, | |
| "grad_norm": 50.40642547607422, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.8169, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03373337658125203, | |
| "grad_norm": 39.5262336730957, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 3.6317, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.036328251702886796, | |
| "grad_norm": 34.03517150878906, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 2.619, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03892312682452157, | |
| "grad_norm": 40.00255584716797, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.9728, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04151800194615634, | |
| "grad_norm": 62.94084167480469, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 2.668, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.044112877067791115, | |
| "grad_norm": 64.5201416015625, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 3.8366, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04670775218942588, | |
| "grad_norm": 39.453330993652344, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.834, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04930262731106066, | |
| "grad_norm": 74.45320892333984, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 3.1071, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.051897502432695426, | |
| "grad_norm": 119.65555572509766, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 5.0249, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.054492377554330194, | |
| "grad_norm": 57.47029113769531, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.8011, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05708725267596497, | |
| "grad_norm": 23.485986709594727, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 1.008, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05968212779759974, | |
| "grad_norm": 15.74601936340332, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 0.6645, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06227700291923451, | |
| "grad_norm": 35.179073333740234, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 3.0041, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06487187804086929, | |
| "grad_norm": 35.2408332824707, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 1.1321, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06487187804086929, | |
| "eval_loss": 0.19091396033763885, | |
| "eval_runtime": 240.1741, | |
| "eval_samples_per_second": 1.353, | |
| "eval_steps_per_second": 0.679, | |
| "step": 25 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.28697269714944e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |