| { | |
| "best_metric": 1.8749154806137085, | |
| "best_model_checkpoint": "output/miyagi/checkpoint-242", | |
| "epoch": 2.0, | |
| "global_step": 242, | |
| "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 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.8863365650177002, | |
| "eval_runtime": 6.9627, | |
| "eval_samples_per_second": 23.123, | |
| "eval_steps_per_second": 3.016, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 3.696176693910321e-07, | |
| "loss": 1.993, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 1.8643657094774288e-06, | |
| "loss": 1.8125, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 4.482209545216786e-06, | |
| "loss": 1.9934, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 8.179093411846335e-06, | |
| "loss": 1.8632, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 1.2892802350719696e-05, | |
| "loss": 2.0066, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 1.8544009226529548e-05, | |
| "loss": 2.0706, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 2.5037609725814876e-05, | |
| "loss": 1.9308, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 3.2264322870026065e-05, | |
| "loss": 1.8125, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 4.0102530108070535e-05, | |
| "loss": 1.8868, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 4.842032203820096e-05, | |
| "loss": 1.9685, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 5.70777183149067e-05, | |
| "loss": 1.9188, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 6.592902338193754e-05, | |
| "loss": 1.9786, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 7.482527838676297e-05, | |
| "loss": 1.8686, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 8.361676801313241e-05, | |
| "loss": 1.9975, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 9.215554004418502e-05, | |
| "loss": 1.851, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.00010029789525431117, | |
| "loss": 1.8228, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 0.0001079068057273095, | |
| "loss": 1.8039, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.0001148542209028974, | |
| "loss": 1.9549, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.00012102322254305531, | |
| "loss": 1.9539, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.000126309992352219, | |
| "loss": 1.8849, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.00013062555913818553, | |
| "loss": 1.9122, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.00013389729611071438, | |
| "loss": 1.9664, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.00013607014311974643, | |
| "loss": 1.8078, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.00013710753326415926, | |
| "loss": 1.8547, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.8749154806137085, | |
| "eval_runtime": 7.1382, | |
| "eval_samples_per_second": 22.555, | |
| "eval_steps_per_second": 2.942, | |
| "step": 242 | |
| } | |
| ], | |
| "max_steps": 242, | |
| "num_train_epochs": 2, | |
| "total_flos": 252146810880000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |