| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.55, | |
| "eval_steps": 500, | |
| "global_step": 33, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 1.3421, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 1.3481, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.4063, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.3044, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 1.264, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2187, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.9074074074074075e-05, | |
| "loss": 1.345, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.814814814814815e-05, | |
| "loss": 1.2374, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.722222222222222e-05, | |
| "loss": 1.388, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 1.2398, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.5370370370370374e-05, | |
| "loss": 1.2157, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 1.1396, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 4.351851851851852e-05, | |
| "loss": 1.1824, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 4.259259259259259e-05, | |
| "loss": 1.2468, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 1.17, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 4.074074074074074e-05, | |
| "loss": 1.2504, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 3.981481481481482e-05, | |
| "loss": 1.1699, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 1.1979, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 3.7962962962962964e-05, | |
| "loss": 1.1994, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 1.1363, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 3.611111111111111e-05, | |
| "loss": 1.1799, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 3.518518518518519e-05, | |
| "loss": 1.1419, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 3.425925925925926e-05, | |
| "loss": 1.099, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.122, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 3.240740740740741e-05, | |
| "loss": 1.1069, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 3.148148148148148e-05, | |
| "loss": 1.1937, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 3.055555555555556e-05, | |
| "loss": 1.1516, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 2.962962962962963e-05, | |
| "loss": 1.034, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 2.8703703703703706e-05, | |
| "loss": 1.0439, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 1.1027, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 2.6851851851851855e-05, | |
| "loss": 1.1097, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 2.5925925925925925e-05, | |
| "loss": 1.1121, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.1438, | |
| "step": 33 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 60, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 2680896116183040.0, | |
| "train_batch_size": 5, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |