| { | |
| "best_metric": 0.68604809, | |
| "best_model_checkpoint": "/mnt/cachenew/yangzekang/wsdm_lym/swift_wsdm/output/solar-10-7b-instruct-v1/v16-20240206-224659/checkpoint-1700", | |
| "epoch": 1.9144144144144144, | |
| "eval_steps": 1700, | |
| "global_step": 1700, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "acc": 0.67516661, | |
| "epoch": 0.0, | |
| "learning_rate": 9.345794392523364e-07, | |
| "loss": 1.46797299, | |
| "step": 1 | |
| }, | |
| { | |
| "acc": 0.75109008, | |
| "epoch": 0.11, | |
| "learning_rate": 9.252336448598131e-05, | |
| "loss": 0.95041487, | |
| "step": 100 | |
| }, | |
| { | |
| "acc": 0.78118393, | |
| "epoch": 0.23, | |
| "learning_rate": 9.732946298984034e-05, | |
| "loss": 0.77567642, | |
| "step": 200 | |
| }, | |
| { | |
| "acc": 0.7877877, | |
| "epoch": 0.34, | |
| "learning_rate": 9.44267053701016e-05, | |
| "loss": 0.74909355, | |
| "step": 300 | |
| }, | |
| { | |
| "acc": 0.79176422, | |
| "epoch": 0.45, | |
| "learning_rate": 9.152394775036285e-05, | |
| "loss": 0.73760468, | |
| "step": 400 | |
| }, | |
| { | |
| "acc": 0.79222595, | |
| "epoch": 0.56, | |
| "learning_rate": 8.86211901306241e-05, | |
| "loss": 0.7364447, | |
| "step": 500 | |
| }, | |
| { | |
| "acc": 0.79083496, | |
| "epoch": 0.68, | |
| "learning_rate": 8.571843251088535e-05, | |
| "loss": 0.73439293, | |
| "step": 600 | |
| }, | |
| { | |
| "acc": 0.79402649, | |
| "epoch": 0.79, | |
| "learning_rate": 8.281567489114659e-05, | |
| "loss": 0.72485077, | |
| "step": 700 | |
| }, | |
| { | |
| "acc": 0.79223618, | |
| "epoch": 0.9, | |
| "learning_rate": 7.991291727140784e-05, | |
| "loss": 0.72585098, | |
| "step": 800 | |
| }, | |
| { | |
| "acc": 0.79309059, | |
| "epoch": 1.01, | |
| "learning_rate": 7.701015965166909e-05, | |
| "loss": 0.72296776, | |
| "step": 900 | |
| }, | |
| { | |
| "acc": 0.81269135, | |
| "epoch": 1.13, | |
| "learning_rate": 7.410740203193034e-05, | |
| "loss": 0.63562035, | |
| "step": 1000 | |
| }, | |
| { | |
| "acc": 0.81135025, | |
| "epoch": 1.24, | |
| "learning_rate": 7.12046444121916e-05, | |
| "loss": 0.64014206, | |
| "step": 1100 | |
| }, | |
| { | |
| "acc": 0.81407928, | |
| "epoch": 1.35, | |
| "learning_rate": 6.830188679245283e-05, | |
| "loss": 0.63201023, | |
| "step": 1200 | |
| }, | |
| { | |
| "acc": 0.81421555, | |
| "epoch": 1.46, | |
| "learning_rate": 6.539912917271409e-05, | |
| "loss": 0.63163139, | |
| "step": 1300 | |
| }, | |
| { | |
| "acc": 0.8152887, | |
| "epoch": 1.58, | |
| "learning_rate": 6.252539912917271e-05, | |
| "loss": 0.62755238, | |
| "step": 1400 | |
| }, | |
| { | |
| "acc": 0.81437424, | |
| "epoch": 1.69, | |
| "learning_rate": 5.9622641509433966e-05, | |
| "loss": 0.63001236, | |
| "step": 1500 | |
| }, | |
| { | |
| "acc": 0.81545654, | |
| "epoch": 1.8, | |
| "learning_rate": 5.671988388969521e-05, | |
| "loss": 0.63001003, | |
| "step": 1600 | |
| }, | |
| { | |
| "acc": 0.81814987, | |
| "epoch": 1.91, | |
| "learning_rate": 5.381712626995646e-05, | |
| "loss": 0.61697731, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "eval_acc": 0.8107640736405236, | |
| "eval_loss": 0.6860480904579163, | |
| "eval_runtime": 19.4827, | |
| "eval_samples_per_second": 7.391, | |
| "eval_steps_per_second": 3.696, | |
| "step": 1700 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 3552, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 1700, | |
| "total_flos": 2.357496784244179e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |