| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.3157894736842106, | |
| "eval_steps": 50, | |
| "global_step": 15, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 40.61452865600586, | |
| "learning_rate": 5e-06, | |
| "loss": 7.6156, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "eval_loss": 7.460348129272461, | |
| "eval_runtime": 0.305, | |
| "eval_samples_per_second": 26.225, | |
| "eval_steps_per_second": 13.113, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 45.25710678100586, | |
| "learning_rate": 1e-05, | |
| "loss": 7.4887, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.631578947368421, | |
| "grad_norm": 38.9701042175293, | |
| "learning_rate": 1.5e-05, | |
| "loss": 7.3729, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 36.8065071105957, | |
| "learning_rate": 2e-05, | |
| "loss": 7.1707, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.1052631578947367, | |
| "grad_norm": 53.15061569213867, | |
| "learning_rate": 2.5e-05, | |
| "loss": 9.2525, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.3157894736842106, | |
| "grad_norm": 40.54500961303711, | |
| "learning_rate": 3e-05, | |
| "loss": 4.7627, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.526315789473684, | |
| "grad_norm": 30.872224807739258, | |
| "learning_rate": 3.5e-05, | |
| "loss": 3.718, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 1.736842105263158, | |
| "grad_norm": 16.013864517211914, | |
| "learning_rate": 4e-05, | |
| "loss": 1.9134, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.9473684210526314, | |
| "grad_norm": 14.20248794555664, | |
| "learning_rate": 4.5e-05, | |
| "loss": 1.8485, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 2.2105263157894735, | |
| "grad_norm": 6.013535499572754, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7526, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.4210526315789473, | |
| "grad_norm": 5.041408538818359, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.7743, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 2.6315789473684212, | |
| "grad_norm": 5.818096160888672, | |
| "learning_rate": 6e-05, | |
| "loss": 0.7937, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 2.8421052631578947, | |
| "grad_norm": 4.261025428771973, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 0.6571, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 3.1052631578947367, | |
| "grad_norm": 7.1626081466674805, | |
| "learning_rate": 7e-05, | |
| "loss": 0.9942, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 3.3157894736842106, | |
| "grad_norm": 3.8936729431152344, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.52, | |
| "step": 15 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 15, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4082170960281600.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |