| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.9504950495049505, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.27145588397979736, | |
| "learning_rate": 0.00019876883405951377, | |
| "loss": 1.4266, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.269089013338089, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.8104, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 0.296158105134964, | |
| "learning_rate": 0.0001891006524188368, | |
| "loss": 0.7768, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 0.3121841847896576, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.7581, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 0.3815813362598419, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.7181, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "grad_norm": 0.395882248878479, | |
| "learning_rate": 0.00015877852522924732, | |
| "loss": 0.7148, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "grad_norm": 0.3826078772544861, | |
| "learning_rate": 0.00014539904997395468, | |
| "loss": 0.7116, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "grad_norm": 0.42428573966026306, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.7189, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "grad_norm": 0.45111292600631714, | |
| "learning_rate": 0.0001156434465040231, | |
| "loss": 0.6538, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "grad_norm": 0.519710898399353, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6567, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "grad_norm": 0.5772411823272705, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.6599, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "grad_norm": 0.5229880809783936, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.6554, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "grad_norm": 0.5204843282699585, | |
| "learning_rate": 5.4600950026045326e-05, | |
| "loss": 0.6174, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "grad_norm": 0.5765883326530457, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.6014, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "grad_norm": 0.6551887392997742, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.6136, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "grad_norm": 0.6366761922836304, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.6126, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "grad_norm": 0.6372557878494263, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.5769, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "grad_norm": 0.6376144886016846, | |
| "learning_rate": 4.8943483704846475e-06, | |
| "loss": 0.5865, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "grad_norm": 0.6038933396339417, | |
| "learning_rate": 1.231165940486234e-06, | |
| "loss": 0.5776, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "grad_norm": 0.6120941042900085, | |
| "learning_rate": 0.0, | |
| "loss": 0.5869, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 1000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 2.0899255999524864e+16, | |
| "train_batch_size": 7, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |