| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.8328611898017, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.3375, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.2223, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.00015877852522924732, | |
| "loss": 1.2106, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.1748, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1717, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.1584, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.1628, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 1.1258, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 4.8943483704846475e-06, | |
| "loss": 1.1116, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 0.0, | |
| "loss": 1.1235, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 1000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 1.4835578655744e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |