| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "global_step": 8335, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.7000599880024e-05, | |
| "loss": 0.2124, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.4001199760047995e-05, | |
| "loss": 0.1387, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 4.100179964007199e-05, | |
| "loss": 0.1202, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.800239952009598e-05, | |
| "loss": 0.0785, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 3.500299940011998e-05, | |
| "loss": 0.0632, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 3.2003599280143974e-05, | |
| "loss": 0.0647, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 2.9004199160167967e-05, | |
| "loss": 0.0554, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 2.6004799040191963e-05, | |
| "loss": 0.0355, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 2.300539892021596e-05, | |
| "loss": 0.0335, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 2.0005998800239953e-05, | |
| "loss": 0.0318, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 1.700659868026395e-05, | |
| "loss": 0.0136, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 1.4007198560287942e-05, | |
| "loss": 0.0193, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 1.1007798440311939e-05, | |
| "loss": 0.0145, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 8.008398320335933e-06, | |
| "loss": 0.0086, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 5.008998200359928e-06, | |
| "loss": 0.0059, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 2.009598080383923e-06, | |
| "loss": 0.0052, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 8335, | |
| "total_flos": 1404947975153976.0, | |
| "train_loss": 0.054277180967462514, | |
| "train_runtime": 938.8043, | |
| "train_samples_per_second": 106.518, | |
| "train_steps_per_second": 8.878 | |
| } | |
| ], | |
| "max_steps": 8335, | |
| "num_train_epochs": 5, | |
| "total_flos": 1404947975153976.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |