| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.898876404494382, | |
| "eval_steps": 500, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1e-05, | |
| "loss": 1.6702, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.5e-05, | |
| "loss": 1.5262, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2e-05, | |
| "loss": 1.8831, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.6531, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 3e-05, | |
| "loss": 1.6833, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 3.5e-05, | |
| "loss": 1.7288, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4e-05, | |
| "loss": 1.5015, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.5e-05, | |
| "loss": 1.6876, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6648, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.998766400914329e-05, | |
| "loss": 1.8044, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.995066821070679e-05, | |
| "loss": 1.6566, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.9889049115077005e-05, | |
| "loss": 1.6917, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.980286753286195e-05, | |
| "loss": 1.6271, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.9692208514878444e-05, | |
| "loss": 1.7478, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.9557181268217227e-05, | |
| "loss": 1.606, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.939791904846869e-05, | |
| "loss": 1.6176, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.9214579028215776e-05, | |
| "loss": 1.7205, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.900734214192358e-05, | |
| "loss": 1.5682, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.877641290737884e-05, | |
| "loss": 1.6807, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.852201922385564e-05, | |
| "loss": 1.6137, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.8244412147206284e-05, | |
| "loss": 1.6352, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.794386564209953e-05, | |
| "loss": 1.5979, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.762067631165049e-05, | |
| "loss": 1.6163, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.72751631047092e-08, | |
| "loss": 1.6513, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.5667160778366258e-05, | |
| "loss": 1.5181, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 3.102787330029076e-05, | |
| "loss": 1.544, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.610819813755038e-05, | |
| "loss": 1.4473, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.567701435686404e-05, | |
| "loss": 1.6461, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.522542485937369e-05, | |
| "loss": 1.519, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.4753875309392266e-05, | |
| "loss": 1.5967, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.426283106939474e-05, | |
| "loss": 1.6351, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.375277674076149e-05, | |
| "loss": 1.5408, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.3224215685535294e-05, | |
| "loss": 1.6087, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 4.267766952966369e-05, | |
| "loss": 1.5753, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 4.211367764821722e-05, | |
| "loss": 1.6771, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 4.1532796633091296e-05, | |
| "loss": 1.5738, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 4.093559974371725e-05, | |
| "loss": 1.5405, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.0322676341324415e-05, | |
| "loss": 1.614, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.969463130731183e-05, | |
| "loss": 1.6264, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.905208444630327e-05, | |
| "loss": 1.5959, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.8395669874474915e-05, | |
| "loss": 1.5935, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 3.7726035393759285e-05, | |
| "loss": 1.502, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 3.704384185254288e-05, | |
| "loss": 1.6214, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 3.634976249348867e-05, | |
| "loss": 1.5852, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 3.564448228912682e-05, | |
| "loss": 1.7603, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3.4928697265869515e-05, | |
| "loss": 1.4935, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 3.4203113817116957e-05, | |
| "loss": 1.5517, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 3.346844800613229e-05, | |
| "loss": 1.6087, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3.2725424859373694e-08, | |
| "loss": 1.5613, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1.0679575735427564e-05, | |
| "loss": 1.597, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 110, | |
| "num_train_epochs": 2, | |
| "save_steps": 25, | |
| "total_flos": 1.7737955558227968e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |