| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.21333333333333335, | |
| "global_step": 40, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.1764705882352942e-05, | |
| "loss": 1.9122, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2.3529411764705884e-05, | |
| "loss": 2.0707, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 3.529411764705883e-05, | |
| "loss": 1.9703, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.705882352941177e-05, | |
| "loss": 2.015, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 5.882352941176471e-05, | |
| "loss": 2.119, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 7.058823529411765e-05, | |
| "loss": 2.0515, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 8.23529411764706e-05, | |
| "loss": 1.7436, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.411764705882353e-05, | |
| "loss": 1.9326, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00010588235294117647, | |
| "loss": 2.0819, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00011764705882352942, | |
| "loss": 1.9965, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00012941176470588237, | |
| "loss": 2.0543, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0001411764705882353, | |
| "loss": 2.0461, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00015294117647058822, | |
| "loss": 2.311, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0001647058823529412, | |
| "loss": 1.8447, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00017647058823529413, | |
| "loss": 2.6263, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00018823529411764707, | |
| "loss": 2.6179, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0002, | |
| "loss": 2.535, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00019999833248118322, | |
| "loss": 2.5924, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00019999332998034514, | |
| "loss": 2.3562, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00019998499266432108, | |
| "loss": 2.2352, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00019997332081116373, | |
| "loss": 2.152, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00019995831481013374, | |
| "loss": 2.1149, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00019993997516168689, | |
| "loss": 2.1608, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0001999183024774573, | |
| "loss": 2.1593, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00019989329748023725, | |
| "loss": 2.2774, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00019986496100395275, | |
| "loss": 2.0355, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00019983329399363598, | |
| "loss": 1.9455, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0001997982975053936, | |
| "loss": 2.5648, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0001997599727063717, | |
| "loss": 2.3619, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00019971832087471676, | |
| "loss": 2.0888, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.000199673343399533, | |
| "loss": 1.9363, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00019962504178083618, | |
| "loss": 2.0259, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00019957341762950344, | |
| "loss": 1.8482, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0001995184726672197, | |
| "loss": 1.8542, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0001994602087264201, | |
| "loss": 1.9435, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00019939862775022893, | |
| "loss": 1.6559, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00019933373179239502, | |
| "loss": 1.9478, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0001992655230172229, | |
| "loss": 1.9417, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.000199194003699501, | |
| "loss": 1.9067, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00019911917622442537, | |
| "loss": 1.6106, | |
| "step": 40 | |
| } | |
| ], | |
| "max_steps": 561, | |
| "num_train_epochs": 3, | |
| "total_flos": 8111250272747520.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |