| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 25070, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2.9401675309134427e-05, | |
| "loss": 0.7213, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 2.8803350618268846e-05, | |
| "loss": 0.463, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 2.8205025927403272e-05, | |
| "loss": 0.4433, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 2.7606701236537695e-05, | |
| "loss": 0.3953, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 2.700837654567212e-05, | |
| "loss": 0.2915, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 2.641005185480654e-05, | |
| "loss": 0.3485, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 2.5811727163940966e-05, | |
| "loss": 0.3159, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 2.521340247307539e-05, | |
| "loss": 0.2976, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 2.4615077782209815e-05, | |
| "loss": 0.3095, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2.4016753091344235e-05, | |
| "loss": 0.2794, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 2.341842840047866e-05, | |
| "loss": 0.2936, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2.2820103709613083e-05, | |
| "loss": 0.2691, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2.222177901874751e-05, | |
| "loss": 0.2911, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 2.162345432788193e-05, | |
| "loss": 0.3109, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 2.1025129637016355e-05, | |
| "loss": 0.3147, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 2.042680494615078e-05, | |
| "loss": 0.2418, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.98284802552852e-05, | |
| "loss": 0.2512, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.9230155564419626e-05, | |
| "loss": 0.2615, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.863183087355405e-05, | |
| "loss": 0.2867, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.8033506182688475e-05, | |
| "loss": 0.2778, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.7435181491822894e-05, | |
| "loss": 0.2556, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1.683685680095732e-05, | |
| "loss": 0.2778, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.6238532110091743e-05, | |
| "loss": 0.2175, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.564020741922617e-05, | |
| "loss": 0.2036, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.504188272836059e-05, | |
| "loss": 0.2023, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 1.4443558037495015e-05, | |
| "loss": 0.1519, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 1.3845233346629439e-05, | |
| "loss": 0.1213, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 1.3246908655763862e-05, | |
| "loss": 0.1656, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 1.2648583964898285e-05, | |
| "loss": 0.1239, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 1.2050259274032709e-05, | |
| "loss": 0.1242, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 1.1451934583167132e-05, | |
| "loss": 0.0917, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 1.0853609892301556e-05, | |
| "loss": 0.0922, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 1.0255285201435979e-05, | |
| "loss": 0.1306, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 9.656960510570403e-06, | |
| "loss": 0.0843, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 9.058635819704826e-06, | |
| "loss": 0.1032, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 8.46031112883925e-06, | |
| "loss": 0.1202, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 7.861986437973673e-06, | |
| "loss": 0.1296, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 7.263661747108097e-06, | |
| "loss": 0.1354, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 6.665337056242521e-06, | |
| "loss": 0.1039, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 6.0670123653769444e-06, | |
| "loss": 0.0892, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 5.468687674511368e-06, | |
| "loss": 0.096, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 4.8703629836457915e-06, | |
| "loss": 0.1045, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 4.272038292780215e-06, | |
| "loss": 0.0965, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 3.673713601914639e-06, | |
| "loss": 0.0805, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 3.0753889110490626e-06, | |
| "loss": 0.1027, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 2.4770642201834866e-06, | |
| "loss": 0.1287, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 1.87873952931791e-06, | |
| "loss": 0.0844, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 1.2804148384523335e-06, | |
| "loss": 0.0861, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 6.820901475867571e-07, | |
| "loss": 0.1154, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 8.37654567211807e-08, | |
| "loss": 0.0838, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 25070, | |
| "total_flos": 9.312702234262733e+16, | |
| "train_loss": 0.2107836102126935, | |
| "train_runtime": 30875.5596, | |
| "train_samples_per_second": 3.248, | |
| "train_steps_per_second": 0.812 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 25070, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "total_flos": 9.312702234262733e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |