| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.2175637393767706, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00039999999999999996, | |
| "loss": 2.303, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0005999749289566311, | |
| "loss": 2.2906, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.000599774385751269, | |
| "loss": 2.3184, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0005993734334103396, | |
| "loss": 2.3182, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0005987723399838027, | |
| "loss": 2.3544, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0005979715073225829, | |
| "loss": 2.3228, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.000596971470809918, | |
| "loss": 2.3045, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0005957728990034388, | |
| "loss": 2.2987, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0005943765931882153, | |
| "loss": 2.3255, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.000592783486841071, | |
| "loss": 2.3216, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.000590994645006523, | |
| "loss": 2.3319, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.000589011263584764, | |
| "loss": 2.3746, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0005868346685321638, | |
| "loss": 2.384, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0005844663149748229, | |
| "loss": 2.3483, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0005819077862357724, | |
| "loss": 2.3436, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0005791607927764706, | |
| "loss": 2.3331, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0005762271710533015, | |
| "loss": 2.3593, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.000573108882289844, | |
| "loss": 2.283, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0005698080111657278, | |
| "loss": 2.3239, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0005663267644229568, | |
| "loss": 2.3732, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0005626674693906273, | |
| "loss": 2.3756, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0005588325724290324, | |
| "loss": 2.3442, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0005548246372941892, | |
| "loss": 2.3337, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0005506463434238809, | |
| "loss": 2.3417, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0005463004841463656, | |
| "loss": 2.3193, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.0005417899648129422, | |
| "loss": 2.3054, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0005371178008556277, | |
| "loss": 2.3434, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.0005322871157712397, | |
| "loss": 2.3201, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0005273011390332353, | |
| "loss": 2.3137, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.0005221632039327013, | |
| "loss": 2.329, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.0005168767453499378, | |
| "loss": 2.3401, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.0005114452974581268, | |
| "loss": 2.3118, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00050587249136062, | |
| "loss": 2.3207, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0005001620526634258, | |
| "loss": 2.3203, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.0004943177989845176, | |
| "loss": 2.3345, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.0004883436374016295, | |
| "loss": 2.3096, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.000482243561840245, | |
| "loss": 2.3224, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.00047602165040352534, | |
| "loss": 2.3391, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.00046968206264596157, | |
| "loss": 2.3305, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.00046322903679257474, | |
| "loss": 2.3762, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.0004566668869055215, | |
| "loss": 2.3577, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.00045, | |
| "loss": 3.1011, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.0004432328331113847, | |
| "loss": 2.228, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.00043636991031555014, | |
| "loss": 2.159, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.00042941581970437604, | |
| "loss": 2.282, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.00042237521031845504, | |
| "loss": 2.282, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.00041525278903905525, | |
| "loss": 2.2421, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.00040805331744141307, | |
| "loss": 2.2593, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.0004007816086114626, | |
| "loss": 2.2961, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.00039344252392812737, | |
| "loss": 2.1614, | |
| "step": 100 | |
| } | |
| ], | |
| "max_steps": 246, | |
| "num_train_epochs": 3, | |
| "total_flos": 9.509605029875548e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |