| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9389671361502347, |
| "eval_steps": 500, |
| "global_step": 200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.05, |
| "learning_rate": 0.0002, |
| "loss": 2.5379, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.09, |
| "learning_rate": 0.00019014778325123153, |
| "loss": 2.1519, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.14, |
| "learning_rate": 0.00018029556650246307, |
| "loss": 1.8117, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 0.0001704433497536946, |
| "loss": 1.6147, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.23, |
| "learning_rate": 0.00016059113300492613, |
| "loss": 1.5671, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 0.00015073891625615765, |
| "loss": 1.5016, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.33, |
| "learning_rate": 0.00014088669950738917, |
| "loss": 1.454, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 0.00013103448275862068, |
| "loss": 1.4734, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 0.00012118226600985223, |
| "loss": 1.4959, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.47, |
| "learning_rate": 0.00011133004926108374, |
| "loss": 1.4655, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.52, |
| "learning_rate": 0.00010147783251231529, |
| "loss": 1.4204, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.56, |
| "learning_rate": 9.16256157635468e-05, |
| "loss": 1.3835, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.61, |
| "learning_rate": 8.177339901477834e-05, |
| "loss": 1.4424, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.66, |
| "learning_rate": 7.192118226600985e-05, |
| "loss": 1.4117, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.7, |
| "learning_rate": 6.206896551724138e-05, |
| "loss": 1.445, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.75, |
| "learning_rate": 5.2216748768472914e-05, |
| "loss": 1.428, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.8, |
| "learning_rate": 4.236453201970443e-05, |
| "loss": 1.3874, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.85, |
| "learning_rate": 3.251231527093596e-05, |
| "loss": 1.4699, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.89, |
| "learning_rate": 2.266009852216749e-05, |
| "loss": 1.4248, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.94, |
| "learning_rate": 1.2807881773399016e-05, |
| "loss": 1.4369, |
| "step": 200 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 213, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 100, |
| "total_flos": 3.24970513170432e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
