| { | |
| "best_metric": 0.8266480641785839, | |
| "best_model_checkpoint": "retrieval_model/run-0/checkpoint-4452", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 4452, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.8075065847895588e-06, | |
| "loss": 0.4825, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.73720841332139e-06, | |
| "loss": 0.3777, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.666910241853221e-06, | |
| "loss": 0.3516, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.5966120703850521e-06, | |
| "loss": 0.3194, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 1.5263138989168832e-06, | |
| "loss": 0.3394, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.4560157274487143e-06, | |
| "loss": 0.3201, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.3857175559805454e-06, | |
| "loss": 0.3128, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1.3154193845123765e-06, | |
| "loss": 0.3316, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_f1": 0.8266480641785839, | |
| "eval_loss": 0.306449294090271, | |
| "eval_runtime": 15.3165, | |
| "eval_samples_per_second": 258.283, | |
| "eval_steps_per_second": 8.096, | |
| "step": 4452 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 13356, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 4721514792264768.0, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 1.8778047562577277e-06, | |
| "num_train_epochs": 3, | |
| "per_device_train_batch_size": 16, | |
| "seed": 37 | |
| } | |
| } | |