| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.716981132075472, | |
| "eval_steps": 500, | |
| "global_step": 1500, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6316129032258064, | |
| "eval_loss": 0.24114057421684265, | |
| "eval_runtime": 5.7071, | |
| "eval_samples_per_second": 543.181, | |
| "eval_steps_per_second": 11.389, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 1.371069182389937e-05, | |
| "loss": 0.3777, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.817741935483871, | |
| "eval_loss": 0.11946031451225281, | |
| "eval_runtime": 5.9789, | |
| "eval_samples_per_second": 518.489, | |
| "eval_steps_per_second": 10.872, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8670967741935484, | |
| "eval_loss": 0.08118218928575516, | |
| "eval_runtime": 5.7219, | |
| "eval_samples_per_second": 541.779, | |
| "eval_steps_per_second": 11.36, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 7.421383647798742e-06, | |
| "loss": 0.1378, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.885483870967742, | |
| "eval_loss": 0.06668733805418015, | |
| "eval_runtime": 5.7092, | |
| "eval_samples_per_second": 542.982, | |
| "eval_steps_per_second": 11.385, | |
| "step": 1272 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 1.1320754716981133e-06, | |
| "loss": 0.0954, | |
| "step": 1500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1590, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 390310534917408.0, | |
| "train_batch_size": 48, | |
| "trial_name": null, | |
| "trial_params": { | |
| "alpha": 0.759039271861527, | |
| "num_train_epochs": 5, | |
| "temperature": 5 | |
| } | |
| } | |