| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.43077864463821325, | |
| "global_step": 88, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.000980392156862745, | |
| "loss": 2.5451, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0009607843137254903, | |
| "loss": 2.4286, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0009411764705882353, | |
| "loss": 2.3441, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0009215686274509804, | |
| "loss": 2.2542, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0009019607843137256, | |
| "loss": 2.2205, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0008823529411764706, | |
| "loss": 2.294, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0008627450980392158, | |
| "loss": 2.2184, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0008431372549019609, | |
| "loss": 2.2811, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0008235294117647058, | |
| "loss": 2.2013, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.000803921568627451, | |
| "loss": 2.2134, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.000784313725490196, | |
| "loss": 2.1704, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0007647058823529411, | |
| "loss": 2.2088, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0007450980392156863, | |
| "loss": 2.1733, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0007254901960784313, | |
| "loss": 2.1753, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0007058823529411765, | |
| "loss": 2.1444, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0006862745098039216, | |
| "loss": 2.1432, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0006666666666666666, | |
| "loss": 2.1687, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0006470588235294118, | |
| "loss": 2.1211, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0006274509803921569, | |
| "loss": 2.1503, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0006078431372549019, | |
| "loss": 2.1357, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0005980392156862745, | |
| "loss": 2.1429, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0005882352941176471, | |
| "loss": 2.0443, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0005784313725490196, | |
| "loss": 2.0832, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0005686274509803922, | |
| "loss": 2.1285, | |
| "step": 88 | |
| } | |
| ], | |
| "max_steps": 204, | |
| "num_train_epochs": 1, | |
| "total_flos": 3.8867912194535424e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |