| { | |
| "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": 0.613225806451613, | |
| "eval_loss": 0.216511532664299, | |
| "eval_runtime": 5.3192, | |
| "eval_samples_per_second": 582.789, | |
| "eval_steps_per_second": 12.22, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 1.650593990216632e-05, | |
| "loss": 0.344, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8422580645161291, | |
| "eval_loss": 0.10201937705278397, | |
| "eval_runtime": 5.5385, | |
| "eval_samples_per_second": 559.715, | |
| "eval_steps_per_second": 11.736, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8958064516129032, | |
| "eval_loss": 0.06630504131317139, | |
| "eval_runtime": 5.3733, | |
| "eval_samples_per_second": 576.928, | |
| "eval_steps_per_second": 12.097, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 1.3011879804332637e-05, | |
| "loss": 0.1177, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9032258064516129, | |
| "eval_loss": 0.04941314831376076, | |
| "eval_runtime": 5.5059, | |
| "eval_samples_per_second": 563.03, | |
| "eval_steps_per_second": 11.805, | |
| "step": 1272 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 9.517819706498952e-06, | |
| "loss": 0.0731, | |
| "step": 1500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2862, | |
| "num_train_epochs": 9, | |
| "save_steps": 500, | |
| "total_flos": 389479376069112.0, | |
| "trial_name": null, | |
| "trial_params": { | |
| "alpha": 0.36417360726124803, | |
| "num_train_epochs": 9, | |
| "temperature": 7 | |
| } | |
| } | |