| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 9.511627906976745, | |
| "eval_steps": 500, | |
| "global_step": 220, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.8604651162790697e-05, | |
| "loss": 0.8552, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 3.7209302325581394e-05, | |
| "loss": 0.8297, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 5.5813953488372095e-05, | |
| "loss": 0.7184, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 7.441860465116279e-05, | |
| "loss": 0.5912, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 9.30232558139535e-05, | |
| "loss": 0.4858, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 9.870801033591732e-05, | |
| "loss": 0.3593, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 9.664082687338501e-05, | |
| "loss": 0.2874, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 9.457364341085272e-05, | |
| "loss": 0.2558, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 9.250645994832042e-05, | |
| "loss": 0.2251, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 9.043927648578811e-05, | |
| "loss": 0.2109, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 8.837209302325582e-05, | |
| "loss": 0.1908, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 8.630490956072352e-05, | |
| "loss": 0.1828, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "learning_rate": 8.423772609819122e-05, | |
| "loss": 0.1676, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 8.217054263565892e-05, | |
| "loss": 0.1568, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 5.23, | |
| "learning_rate": 8.010335917312663e-05, | |
| "loss": 0.1521, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 5.42, | |
| "learning_rate": 7.803617571059432e-05, | |
| "loss": 0.145, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 6.09, | |
| "learning_rate": 7.596899224806202e-05, | |
| "loss": 0.1437, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 6.28, | |
| "learning_rate": 7.390180878552973e-05, | |
| "loss": 0.1293, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "learning_rate": 7.183462532299742e-05, | |
| "loss": 0.1352, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 6.976744186046513e-05, | |
| "loss": 0.1239, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 7.33, | |
| "learning_rate": 6.770025839793283e-05, | |
| "loss": 0.115, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 7.51, | |
| "learning_rate": 6.563307493540052e-05, | |
| "loss": 0.1224, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 8.19, | |
| "learning_rate": 6.356589147286823e-05, | |
| "loss": 0.1071, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 8.37, | |
| "learning_rate": 6.149870801033592e-05, | |
| "loss": 0.1047, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 9.05, | |
| "learning_rate": 5.943152454780362e-05, | |
| "loss": 0.1075, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 9.23, | |
| "learning_rate": 5.736434108527132e-05, | |
| "loss": 0.0985, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 9.42, | |
| "learning_rate": 5.5297157622739015e-05, | |
| "loss": 0.0937, | |
| "step": 216 | |
| } | |
| ], | |
| "logging_steps": 8, | |
| "max_steps": 430, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 5.365411759521792e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |