| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 3741, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.331729484095162e-05, | |
| "loss": 1.7279, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.663458968190324e-05, | |
| "loss": 1.5155, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2.995188452285485e-05, | |
| "loss": 1.4301, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.326917936380647e-05, | |
| "loss": 1.3448, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.658647420475809e-05, | |
| "loss": 1.2982, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 9.903769045709705e-06, | |
| "loss": 1.2323, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.2210638866613206e-06, | |
| "loss": 1.2036, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 3741, | |
| "total_flos": 1.70456184471552e+16, | |
| "train_loss": 1.3809210790793738, | |
| "train_runtime": 2386.364, | |
| "train_samples_per_second": 6.271, | |
| "train_steps_per_second": 1.568 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 3741, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 1.70456184471552e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |