| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.999023320368054, | |
| "global_step": 2733, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.998862506715891e-06, | |
| "loss": 2.3408, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.951193630803286e-06, | |
| "loss": 2.2705, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 9.834073214196232e-06, | |
| "loss": 2.2454, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 9.649144132125768e-06, | |
| "loss": 2.2308, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.399000427690736e-06, | |
| "loss": 2.222, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 2.1795129776000977, | |
| "eval_runtime": 134.9568, | |
| "eval_samples_per_second": 47.771, | |
| "eval_steps_per_second": 11.945, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 9.087150924613952e-06, | |
| "loss": 2.2111, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 8.717970008158547e-06, | |
| "loss": 2.2157, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 8.296636264611935e-06, | |
| "loss": 2.1904, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 7.829059840055622e-06, | |
| "loss": 2.1934, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 7.321799537376213e-06, | |
| "loss": 2.1122, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "eval_loss": 2.1545722484588623, | |
| "eval_runtime": 135.1839, | |
| "eval_samples_per_second": 47.691, | |
| "eval_steps_per_second": 11.924, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 6.781970814417049e-06, | |
| "loss": 2.0764, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 6.217145973801762e-06, | |
| "loss": 2.0787, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 5.635247944490186e-06, | |
| "loss": 2.0785, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 5.044439145017379e-06, | |
| "loss": 2.0739, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 4.453006987356882e-06, | |
| "loss": 2.0817, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "eval_loss": 2.139988422393799, | |
| "eval_runtime": 135.0241, | |
| "eval_samples_per_second": 47.747, | |
| "eval_steps_per_second": 11.939, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 3.869247627472021e-06, | |
| "loss": 2.0758, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 3.3013495932132446e-06, | |
| "loss": 2.0758, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 2.7572789219399587e-06, | |
| "loss": 2.0732, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 2.2446674190680336e-06, | |
| "loss": 2.0324, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 1.7707056049662669e-06, | |
| "loss": 2.0075, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "eval_loss": 2.139112949371338, | |
| "eval_runtime": 135.0198, | |
| "eval_samples_per_second": 47.749, | |
| "eval_steps_per_second": 11.939, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 1.3420418518604827e-06, | |
| "loss": 1.9987, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 9.646891255752928e-07, | |
| "loss": 2.0033, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 6.439406402687365e-07, | |
| "loss": 2.0071, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 3.8429560929037044e-07, | |
| "loss": 1.9992, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 1.893961336727451e-07, | |
| "loss": 2.0045, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "eval_loss": 2.137310743331909, | |
| "eval_runtime": 134.9818, | |
| "eval_samples_per_second": 47.762, | |
| "eval_steps_per_second": 11.942, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 6.197611353601918e-08, | |
| "loss": 1.9924, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 3.822899037286276e-09, | |
| "loss": 1.997, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 2733, | |
| "total_flos": 1.3361242101108096e+18, | |
| "train_loss": 2.1056736130614966, | |
| "train_runtime": 28254.5864, | |
| "train_samples_per_second": 12.393, | |
| "train_steps_per_second": 0.097 | |
| } | |
| ], | |
| "max_steps": 2733, | |
| "num_train_epochs": 3, | |
| "total_flos": 1.3361242101108096e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |