| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 151, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019945941475610623, | |
| "loss": 0.6627, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019784350367254322, | |
| "loss": 0.3933, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00019516973750305532, | |
| "loss": 0.2526, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0001914670242183795, | |
| "loss": 0.2494, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00018677539646179707, | |
| "loss": 0.1195, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00018114557872800905, | |
| "loss": 0.1413, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00017463843894486937, | |
| "loss": 0.1202, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00016732433038731242, | |
| "loss": 0.1129, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0001592823310385073, | |
| "loss": 0.1156, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00015059938862204127, | |
| "loss": 0.0889, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00014136938054879283, | |
| "loss": 0.0921, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0001316920989420703, | |
| "loss": 0.0577, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00012167217171462566, | |
| "loss": 0.0885, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00011141793136253986, | |
| "loss": 0.0795, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00010104024370624644, | |
| "loss": 0.0613, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.065130924199998e-05, | |
| "loss": 0.0661, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 8.036345006322359e-05, | |
| "loss": 0.0333, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 7.028789546718326e-05, | |
| "loss": 0.0512, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 6.053357937665237e-05, | |
| "loss": 0.0553, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 5.1205962578487155e-05, | |
| "loss": 0.0409, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 4.240589251272342e-05, | |
| "loss": 0.0592, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3.422851293981676e-05, | |
| "loss": 0.0536, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 2.6762235274383772e-05, | |
| "loss": 0.0275, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 2.008778270707944e-05, | |
| "loss": 0.0466, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.4277317449282834e-05, | |
| "loss": 0.0328, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 9.393660536564408e-06, | |
| "loss": 0.0299, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 5.489612626189245e-06, | |
| "loss": 0.0258, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.607383131993424e-06, | |
| "loss": 0.0374, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 7.781338686584927e-07, | |
| "loss": 0.037, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 2.164213936770576e-08, | |
| "loss": 0.0316, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 151, | |
| "total_flos": 6843505735041024.0, | |
| "train_loss": 0.1083572210361626, | |
| "train_runtime": 702.143, | |
| "train_samples_per_second": 3.439, | |
| "train_steps_per_second": 0.215 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 151, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "total_flos": 6843505735041024.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |