| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.984771573604061, | |
| "eval_steps": 500, | |
| "global_step": 147, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.20304568527918782, | |
| "grad_norm": 32.67877197265625, | |
| "learning_rate": 4.8239436619718316e-05, | |
| "loss": 3.4262, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.40609137055837563, | |
| "grad_norm": 18.402006149291992, | |
| "learning_rate": 4.471830985915493e-05, | |
| "loss": 2.8928, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6091370558375635, | |
| "grad_norm": 48.83979415893555, | |
| "learning_rate": 4.119718309859155e-05, | |
| "loss": 2.3612, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.8121827411167513, | |
| "grad_norm": 6.010754585266113, | |
| "learning_rate": 3.767605633802817e-05, | |
| "loss": 2.2193, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.015228426395939, | |
| "grad_norm": 5.850377559661865, | |
| "learning_rate": 3.4154929577464786e-05, | |
| "loss": 2.0969, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.218274111675127, | |
| "grad_norm": 8.595719337463379, | |
| "learning_rate": 3.063380281690141e-05, | |
| "loss": 2.0547, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.4213197969543148, | |
| "grad_norm": 9.501204490661621, | |
| "learning_rate": 2.711267605633803e-05, | |
| "loss": 1.9979, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.6243654822335025, | |
| "grad_norm": 6.856517791748047, | |
| "learning_rate": 2.359154929577465e-05, | |
| "loss": 1.9259, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.8274111675126905, | |
| "grad_norm": 13.690930366516113, | |
| "learning_rate": 2.007042253521127e-05, | |
| "loss": 1.9244, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.030456852791878, | |
| "grad_norm": 10.869937896728516, | |
| "learning_rate": 1.6549295774647887e-05, | |
| "loss": 1.8519, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.233502538071066, | |
| "grad_norm": 12.451278686523438, | |
| "learning_rate": 1.3028169014084506e-05, | |
| "loss": 1.8955, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.436548223350254, | |
| "grad_norm": 9.575093269348145, | |
| "learning_rate": 9.507042253521127e-06, | |
| "loss": 1.7803, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.6395939086294415, | |
| "grad_norm": 6.249921798706055, | |
| "learning_rate": 5.9859154929577465e-06, | |
| "loss": 1.8202, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.8426395939086295, | |
| "grad_norm": 8.334336280822754, | |
| "learning_rate": 2.464788732394366e-06, | |
| "loss": 1.8493, | |
| "step": 140 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 147, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 1000000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4746645092499456.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |