| { | |
| "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": 0.7209677419354839, | |
| "eval_loss": 3.2341866493225098, | |
| "eval_runtime": 2.427, | |
| "eval_samples_per_second": 1277.299, | |
| "eval_steps_per_second": 26.782, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 1.4758909853249476e-05, | |
| "loss": 3.7475, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8493548387096774, | |
| "eval_loss": 1.7498714923858643, | |
| "eval_runtime": 2.376, | |
| "eval_samples_per_second": 1304.714, | |
| "eval_steps_per_second": 27.357, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9016129032258065, | |
| "eval_loss": 0.9944729208946228, | |
| "eval_runtime": 2.401, | |
| "eval_samples_per_second": 1291.127, | |
| "eval_steps_per_second": 27.072, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 9.517819706498952e-06, | |
| "loss": 1.55, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9229032258064516, | |
| "eval_loss": 0.6697528958320618, | |
| "eval_runtime": 2.381, | |
| "eval_samples_per_second": 1301.974, | |
| "eval_steps_per_second": 27.299, | |
| "step": 1272 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 4.276729559748428e-06, | |
| "loss": 0.69, | |
| "step": 1500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1908, | |
| "num_train_epochs": 6, | |
| "save_steps": 500, | |
| "total_flos": 389479376069112.0, | |
| "trial_name": null, | |
| "trial_params": { | |
| "alpha": 0.14437383131434334, | |
| "num_train_epochs": 6, | |
| "temperature": 16 | |
| } | |
| } | |