| { | |
| "best_metric": 1.9889769554138184, | |
| "best_model_checkpoint": "output/miyagi/checkpoint-120", | |
| "epoch": 1.0, | |
| "global_step": 120, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0001366131174902434, | |
| "loss": 2.5015, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00013486251168343008, | |
| "loss": 2.2103, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00013197813593027427, | |
| "loss": 2.3049, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0001280093426996125, | |
| "loss": 2.2693, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00012302403914397873, | |
| "loss": 2.0156, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00011710752518939715, | |
| "loss": 2.1099, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00011036103402999824, | |
| "loss": 2.0083, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00010290000000000001, | |
| "loss": 2.046, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 9.485208346024516e-05, | |
| "loss": 1.8954, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 8.635498649403293e-05, | |
| "loss": 2.2916, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 7.755409678629555e-05, | |
| "loss": 1.9975, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 6.86e-05, | |
| "loss": 2.045, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 5.964590321370448e-05, | |
| "loss": 1.9664, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 5.084501350596707e-05, | |
| "loss": 1.8793, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.2347916539754844e-05, | |
| "loss": 2.014, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.4300000000000014e-05, | |
| "loss": 1.9299, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.6838965970001764e-05, | |
| "loss": 1.9819, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 2.0092474810602843e-05, | |
| "loss": 2.051, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.4175960856021275e-05, | |
| "loss": 1.9671, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.190657300387505e-06, | |
| "loss": 1.8122, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 5.22186406972573e-06, | |
| "loss": 1.8996, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 2.3374883165699215e-06, | |
| "loss": 2.0356, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 5.868825097566078e-07, | |
| "loss": 1.8357, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.0548, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.9889769554138184, | |
| "eval_runtime": 8.2484, | |
| "eval_samples_per_second": 20.489, | |
| "eval_steps_per_second": 2.667, | |
| "step": 120 | |
| } | |
| ], | |
| "max_steps": 120, | |
| "num_train_epochs": 1, | |
| "total_flos": 125158883328000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |