| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 11787, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.9151607703402055e-05, | |
| "loss": 1.5519, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.8303215406804106e-05, | |
| "loss": 1.35, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.745482311020616e-05, | |
| "loss": 1.2666, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.6606430813608214e-05, | |
| "loss": 1.2182, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.5758038517010267e-05, | |
| "loss": 1.1894, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.490964622041232e-05, | |
| "loss": 1.2037, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1.4061253923814373e-05, | |
| "loss": 1.1514, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 1.3212861627216427e-05, | |
| "loss": 1.113, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 1.2364469330618477e-05, | |
| "loss": 1.018, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 1.1516077034020531e-05, | |
| "loss": 1.0139, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.0667684737422585e-05, | |
| "loss": 1.0093, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 9.819292440824639e-06, | |
| "loss": 1.0084, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 8.970900144226691e-06, | |
| "loss": 1.0089, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 8.122507847628745e-06, | |
| "loss": 0.9934, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 7.274115551030797e-06, | |
| "loss": 0.9786, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 6.425723254432851e-06, | |
| "loss": 0.9493, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 5.577330957834903e-06, | |
| "loss": 0.9069, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 4.728938661236957e-06, | |
| "loss": 0.9056, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 3.88054636463901e-06, | |
| "loss": 0.9129, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 3.0321540680410622e-06, | |
| "loss": 0.929, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 2.1837617714431156e-06, | |
| "loss": 0.9058, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 1.3353694748451684e-06, | |
| "loss": 0.9086, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 4.869771782472216e-07, | |
| "loss": 0.9055, | |
| "step": 11500 | |
| } | |
| ], | |
| "max_steps": 11787, | |
| "num_train_epochs": 3, | |
| "total_flos": 4684090101792768.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |