| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9951219512195122, | |
| "eval_steps": 500, | |
| "global_step": 102, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00975609756097561, | |
| "grad_norm": 6.261786177237342, | |
| "learning_rate": 9.090909090909092e-05, | |
| "loss": 1.1256, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04878048780487805, | |
| "grad_norm": 2.1112596954065914, | |
| "learning_rate": 0.00045454545454545455, | |
| "loss": 1.049, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0975609756097561, | |
| "grad_norm": 1.5895813487100507, | |
| "learning_rate": 0.0009090909090909091, | |
| "loss": 1.0974, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14634146341463414, | |
| "grad_norm": 0.32863787167794134, | |
| "learning_rate": 0.0009952402219937815, | |
| "loss": 0.9164, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1951219512195122, | |
| "grad_norm": 0.23963144918280163, | |
| "learning_rate": 0.0009760588329553571, | |
| "loss": 0.8434, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.24390243902439024, | |
| "grad_norm": 0.14493890865001488, | |
| "learning_rate": 0.0009427280128266049, | |
| "loss": 0.8011, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2926829268292683, | |
| "grad_norm": 0.12052712473534186, | |
| "learning_rate": 0.0008962384209755452, | |
| "loss": 0.7652, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.34146341463414637, | |
| "grad_norm": 0.0981844421832599, | |
| "learning_rate": 0.0008379718220723773, | |
| "loss": 0.7453, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3902439024390244, | |
| "grad_norm": 0.18540719570949135, | |
| "learning_rate": 0.0007696600172495997, | |
| "loss": 0.7317, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.43902439024390244, | |
| "grad_norm": 0.12172997652512386, | |
| "learning_rate": 0.0006933333714707094, | |
| "loss": 0.7179, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.4878048780487805, | |
| "grad_norm": 0.1050067175867305, | |
| "learning_rate": 0.0006112604669781572, | |
| "loss": 0.7047, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5365853658536586, | |
| "grad_norm": 0.0824375568337565, | |
| "learning_rate": 0.0005258806764421047, | |
| "loss": 0.6991, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.5853658536585366, | |
| "grad_norm": 0.09661916029526949, | |
| "learning_rate": 0.00043973165987233853, | |
| "loss": 0.6865, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.6341463414634146, | |
| "grad_norm": 0.07527219081930579, | |
| "learning_rate": 0.0003553739402317162, | |
| "loss": 0.6833, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.6829268292682927, | |
| "grad_norm": 0.07406811411334399, | |
| "learning_rate": 0.00027531479951641924, | |
| "loss": 0.6793, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.7317073170731707, | |
| "grad_norm": 0.21265879474641486, | |
| "learning_rate": 0.00020193375726538737, | |
| "loss": 0.6726, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.7804878048780488, | |
| "grad_norm": 0.06699755926217109, | |
| "learning_rate": 0.0001374118464283119, | |
| "loss": 0.6685, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.8292682926829268, | |
| "grad_norm": 0.0915919461803413, | |
| "learning_rate": 8.366678865639687e-05, | |
| "loss": 0.6716, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.8780487804878049, | |
| "grad_norm": 0.06490947271665126, | |
| "learning_rate": 4.2295995737316854e-05, | |
| "loss": 0.6692, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.926829268292683, | |
| "grad_norm": 0.1069137841001841, | |
| "learning_rate": 1.4529091286973995e-05, | |
| "loss": 0.6654, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.975609756097561, | |
| "grad_norm": 0.043578368206132125, | |
| "learning_rate": 1.1913638493762368e-06, | |
| "loss": 0.6674, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.9951219512195122, | |
| "eval_loss": 1.0117870569229126, | |
| "eval_runtime": 125.6267, | |
| "eval_samples_per_second": 20.871, | |
| "eval_steps_per_second": 0.653, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.9951219512195122, | |
| "step": 102, | |
| "total_flos": 128481799176192.0, | |
| "train_loss": 0.7558732021088693, | |
| "train_runtime": 2589.5829, | |
| "train_samples_per_second": 5.059, | |
| "train_steps_per_second": 0.039 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 102, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 128481799176192.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |