| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0848329048843186, | |
| "eval_steps": 400, | |
| "global_step": 1200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019903980796159233, | |
| "loss": 1.2412, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00019803960792158433, | |
| "loss": 1.2101, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00019703940788157634, | |
| "loss": 1.1308, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00019603920784156832, | |
| "loss": 1.1847, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00019503900780156033, | |
| "loss": 1.183, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0001940388077615523, | |
| "loss": 1.1129, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00019303860772154432, | |
| "loss": 1.2248, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00019203840768153632, | |
| "loss": 1.1082, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0001910382076415283, | |
| "loss": 1.2025, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0001900380076015203, | |
| "loss": 1.2208, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.0001890378075615123, | |
| "loss": 1.1124, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.0001880376075215043, | |
| "loss": 1.0934, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.00018703740748149633, | |
| "loss": 1.2967, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.0001860372074414883, | |
| "loss": 1.1463, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.00018503700740148032, | |
| "loss": 1.1978, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.0001840368073614723, | |
| "loss": 1.0147, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "eval_loss": 0.8289958238601685, | |
| "eval_runtime": 1938.2766, | |
| "eval_samples_per_second": 0.401, | |
| "eval_steps_per_second": 0.051, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.0001830366073214643, | |
| "loss": 0.7315, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.0001820364072814563, | |
| "loss": 0.8464, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.0001810362072414483, | |
| "loss": 0.7709, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.0001800360072014403, | |
| "loss": 0.8396, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.00017903580716143228, | |
| "loss": 0.7598, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.00017803560712142429, | |
| "loss": 0.7829, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 0.0001770354070814163, | |
| "loss": 0.8044, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.0001760352070414083, | |
| "loss": 0.7746, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.0001750350070014003, | |
| "loss": 0.8287, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.0001740348069613923, | |
| "loss": 0.7134, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.0001730346069213843, | |
| "loss": 0.7763, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.00017203440688137627, | |
| "loss": 0.8097, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.00017103420684136828, | |
| "loss": 0.8152, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.0001700340068013603, | |
| "loss": 0.7876, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.00016903380676135227, | |
| "loss": 0.7261, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 0.00016803360672134428, | |
| "loss": 0.3176, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "eval_loss": 0.2893330454826355, | |
| "eval_runtime": 1936.9393, | |
| "eval_samples_per_second": 0.401, | |
| "eval_steps_per_second": 0.051, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 0.00016703340668133626, | |
| "loss": 0.3089, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 0.00016603320664132826, | |
| "loss": 0.3265, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 0.00016503300660132027, | |
| "loss": 0.2873, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 0.00016403280656131228, | |
| "loss": 0.3553, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 0.00016303260652130428, | |
| "loss": 0.3184, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 0.00016203240648129626, | |
| "loss": 0.2688, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 0.00016103220644128827, | |
| "loss": 0.2998, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 0.00016003200640128028, | |
| "loss": 0.283, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 0.00015903180636127226, | |
| "loss": 0.313, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 0.00015803160632126427, | |
| "loss": 0.3122, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 0.00015703140628125625, | |
| "loss": 0.2782, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 0.00015603120624124825, | |
| "loss": 0.2886, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 0.00015503100620124026, | |
| "loss": 0.2898, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 0.00015403080616123224, | |
| "loss": 0.2956, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 0.00015303060612122427, | |
| "loss": 0.2609, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 0.00015203040608121625, | |
| "loss": 0.115, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "eval_loss": 0.10693752020597458, | |
| "eval_runtime": 1938.4879, | |
| "eval_samples_per_second": 0.401, | |
| "eval_steps_per_second": 0.051, | |
| "step": 1200 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 5000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 13, | |
| "save_steps": 400, | |
| "total_flos": 2.0361775954431836e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |