| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9714285714285715, | |
| "eval_steps": 25, | |
| "global_step": 13, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.22857142857142856, | |
| "grad_norm": 90.97411346435547, | |
| "learning_rate": 9.85470908713026e-05, | |
| "loss": 8.3858, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.22857142857142856, | |
| "eval_loss": 7.6959943771362305, | |
| "eval_runtime": 1.3147, | |
| "eval_samples_per_second": 22.82, | |
| "eval_steps_per_second": 3.043, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.45714285714285713, | |
| "grad_norm": 113.5341567993164, | |
| "learning_rate": 9.42728012826605e-05, | |
| "loss": 7.8089, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.6857142857142857, | |
| "grad_norm": 159.55125427246094, | |
| "learning_rate": 8.742553740855506e-05, | |
| "loss": 6.6231, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.9142857142857143, | |
| "grad_norm": 114.18114471435547, | |
| "learning_rate": 7.840323733655778e-05, | |
| "loss": 5.5534, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 111.18988037109375, | |
| "learning_rate": 6.773024435212678e-05, | |
| "loss": 4.441, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.3714285714285714, | |
| "grad_norm": 90.13815307617188, | |
| "learning_rate": 5.602683401276615e-05, | |
| "loss": 3.7047, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 86.33097839355469, | |
| "learning_rate": 4.397316598723385e-05, | |
| "loss": 3.1481, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 1.8285714285714287, | |
| "grad_norm": 54.378997802734375, | |
| "learning_rate": 3.226975564787322e-05, | |
| "loss": 2.7065, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 2.057142857142857, | |
| "grad_norm": 51.004852294921875, | |
| "learning_rate": 2.1596762663442218e-05, | |
| "loss": 2.5423, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 2.2857142857142856, | |
| "grad_norm": 50.672977447509766, | |
| "learning_rate": 1.257446259144494e-05, | |
| "loss": 2.1898, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.5142857142857142, | |
| "grad_norm": 50.242897033691406, | |
| "learning_rate": 5.727198717339511e-06, | |
| "loss": 2.1095, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 2.742857142857143, | |
| "grad_norm": 57.482181549072266, | |
| "learning_rate": 1.4529091286973995e-06, | |
| "loss": 2.0856, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 2.9714285714285715, | |
| "grad_norm": 52.67997360229492, | |
| "learning_rate": 0.0, | |
| "loss": 2.0969, | |
| "step": 13 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 13, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": 1.367380642014167e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |