| { | |
| "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": 0.7293548387096774, | |
| "eval_loss": 3.176466703414917, | |
| "eval_runtime": 2.372, | |
| "eval_samples_per_second": 1306.914, | |
| "eval_steps_per_second": 27.403, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 1.650593990216632e-05, | |
| "loss": 3.7036, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8590322580645161, | |
| "eval_loss": 1.5857902765274048, | |
| "eval_runtime": 2.418, | |
| "eval_samples_per_second": 1282.05, | |
| "eval_steps_per_second": 26.882, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9109677419354839, | |
| "eval_loss": 0.7998820543289185, | |
| "eval_runtime": 2.461, | |
| "eval_samples_per_second": 1259.651, | |
| "eval_steps_per_second": 26.412, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 1.3011879804332637e-05, | |
| "loss": 1.3611, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9338709677419355, | |
| "eval_loss": 0.4834734797477722, | |
| "eval_runtime": 2.399, | |
| "eval_samples_per_second": 1292.206, | |
| "eval_steps_per_second": 27.095, | |
| "step": 1272 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 9.517819706498952e-06, | |
| "loss": 0.4625, | |
| "step": 1500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2862, | |
| "num_train_epochs": 9, | |
| "save_steps": 500, | |
| "total_flos": 472108083521340.0, | |
| "trial_name": null, | |
| "trial_params": { | |
| "alpha": 0.47830413160685104, | |
| "num_train_epochs": 9, | |
| "temperature": 3 | |
| } | |
| } | |