| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 4028, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.7517378351539228e-05, | |
| "loss": 0.2967, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.5034756703078453e-05, | |
| "loss": 0.1741, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.2552135054617678e-05, | |
| "loss": 0.1583, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.0069513406156904e-05, | |
| "loss": 0.1125, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 7.586891757696128e-06, | |
| "loss": 0.1219, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 5.104270109235353e-06, | |
| "loss": 0.1132, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 2.621648460774578e-06, | |
| "loss": 0.0685, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1.390268123138034e-07, | |
| "loss": 0.0517, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.05255265533924103, | |
| "eval_runtime": 408.8132, | |
| "eval_samples_per_second": 9.853, | |
| "eval_steps_per_second": 2.463, | |
| "step": 4028 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 4028, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 1.281958958822976e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |