| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.031545741324921134, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006309148264984227, | |
| "grad_norm": 7.026068687438965, | |
| "learning_rate": 1e-05, | |
| "loss": 53.7506, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006309148264984227, | |
| "eval_loss": 3.462547779083252, | |
| "eval_runtime": 51.3608, | |
| "eval_samples_per_second": 5.199, | |
| "eval_steps_per_second": 2.609, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012618296529968454, | |
| "grad_norm": 7.256462574005127, | |
| "learning_rate": 2e-05, | |
| "loss": 54.2197, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.012618296529968454, | |
| "eval_loss": 3.448944091796875, | |
| "eval_runtime": 21.0442, | |
| "eval_samples_per_second": 12.688, | |
| "eval_steps_per_second": 6.368, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01892744479495268, | |
| "grad_norm": 6.963824272155762, | |
| "learning_rate": 3e-05, | |
| "loss": 54.6442, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.025236593059936908, | |
| "grad_norm": 7.627413749694824, | |
| "learning_rate": 4e-05, | |
| "loss": 55.8553, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.025236593059936908, | |
| "eval_loss": 3.4388527870178223, | |
| "eval_runtime": 23.945, | |
| "eval_samples_per_second": 11.151, | |
| "eval_steps_per_second": 5.596, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.031545741324921134, | |
| "grad_norm": 7.284046649932861, | |
| "learning_rate": 5e-05, | |
| "loss": 52.5808, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6189185916469248.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |