| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9759036144578315, | |
| "eval_steps": 150, | |
| "global_step": 41, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 1.2314, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 1.4026, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 1.8531, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 1.3763, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00015, | |
| "loss": 0.961, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 1.2005, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 1.1054, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 1.0114, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00027, | |
| "loss": 1.1386, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9856, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00029990862405286433, | |
| "loss": 0.7562, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0002996346075389736, | |
| "loss": 1.0498, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00029917828430524096, | |
| "loss": 1.2559, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0002985402103112355, | |
| "loss": 1.0074, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0002977211629518312, | |
| "loss": 1.0239, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.0002967221401100708, | |
| "loss": 1.3441, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0002955443589413994, | |
| "loss": 1.1692, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.0002941892543907478, | |
| "loss": 1.3764, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 0.9064, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.0002909538931178862, | |
| "loss": 1.4608, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.0002890775781850181, | |
| "loss": 1.0947, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.0002870318186463901, | |
| "loss": 1.113, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.000284819106944875, | |
| "loss": 0.9546, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.000282442138928839, | |
| "loss": 1.1469, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.0002799038105676658, | |
| "loss": 1.3102, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.00027720721442346387, | |
| "loss": 1.4763, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.0002743556358832562, | |
| "loss": 1.0281, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 1.0988, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.00026820161304100823, | |
| "loss": 1.1848, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.00026490666646784665, | |
| "loss": 0.9901, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 0.00026147172382160914, | |
| "loss": 0.8676, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.00025790097005079764, | |
| "loss": 1.0521, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.0002541987555688496, | |
| "loss": 1.0436, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 0.0002503695909538287, | |
| "loss": 0.9511, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 0.0002464181414529809, | |
| "loss": 1.2208, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.0002423492212988487, | |
| "loss": 1.1128, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.00023816778784387094, | |
| "loss": 1.114, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.00023387893552061199, | |
| "loss": 0.9318, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.0002294878896349807, | |
| "loss": 1.6424, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.000225, | |
| "loss": 0.7759, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.00022042073441788358, | |
| "loss": 0.8061, | |
| "step": 41 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 1.0588396984467456e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |