| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 124, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.08113590263691683, |
| "grad_norm": 226.23838806152344, |
| "learning_rate": 4.978612153434527e-06, |
| "loss": 7.567501831054687, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.16227180527383367, |
| "grad_norm": 47.0637092590332, |
| "learning_rate": 4.809698831278217e-06, |
| "loss": 2.347845268249512, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.2434077079107505, |
| "grad_norm": 28.71527862548828, |
| "learning_rate": 4.4833833507280884e-06, |
| "loss": 1.9790664672851563, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.32454361054766734, |
| "grad_norm": 18.502519607543945, |
| "learning_rate": 4.021903572521802e-06, |
| "loss": 1.9121383666992187, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.4056795131845842, |
| "grad_norm": 16.341705322265625, |
| "learning_rate": 3.4567085809127247e-06, |
| "loss": 1.8831947326660157, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.486815415821501, |
| "grad_norm": 18.711566925048828, |
| "learning_rate": 2.82631548055013e-06, |
| "loss": 1.7617910385131836, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.5679513184584178, |
| "grad_norm": 17.04507064819336, |
| "learning_rate": 2.173684519449872e-06, |
| "loss": 1.8086307525634766, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.6490872210953347, |
| "grad_norm": 12.945286750793457, |
| "learning_rate": 1.5432914190872757e-06, |
| "loss": 1.7495216369628905, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.7302231237322515, |
| "grad_norm": 18.343416213989258, |
| "learning_rate": 9.780964274781984e-07, |
| "loss": 1.8054061889648438, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.8113590263691683, |
| "grad_norm": 41.2520751953125, |
| "learning_rate": 5.166166492719124e-07, |
| "loss": 1.854791259765625, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.8924949290060852, |
| "grad_norm": 61.88145446777344, |
| "learning_rate": 1.9030116872178317e-07, |
| "loss": 1.733109474182129, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.973630831643002, |
| "grad_norm": 19.958646774291992, |
| "learning_rate": 2.1387846565474047e-08, |
| "loss": 1.8175289154052734, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 124, |
| "total_flos": 756286140448768.0, |
| "train_loss": 2.33440653739437, |
| "train_runtime": 12466.658, |
| "train_samples_per_second": 0.316, |
| "train_steps_per_second": 0.01 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 124, |
| "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": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 756286140448768.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
