| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 32.608695652173914, | |
| "eval_steps": 500, | |
| "global_step": 4500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 1.3459627329192546e-05, | |
| "loss": 0.1006, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 7.25, | |
| "learning_rate": 1.1906832298136646e-05, | |
| "loss": 0.012, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 10.87, | |
| "learning_rate": 1.0354037267080746e-05, | |
| "loss": 0.0043, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 14.49, | |
| "learning_rate": 8.801242236024846e-06, | |
| "loss": 0.001, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 18.12, | |
| "learning_rate": 7.248447204968944e-06, | |
| "loss": 0.0001, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 21.74, | |
| "learning_rate": 5.6956521739130435e-06, | |
| "loss": 0.0001, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 25.36, | |
| "learning_rate": 4.1428571428571435e-06, | |
| "loss": 0.0, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 28.99, | |
| "learning_rate": 2.5900621118012422e-06, | |
| "loss": 0.0, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 32.61, | |
| "learning_rate": 1.0372670807453418e-06, | |
| "loss": 0.0, | |
| "step": 4500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 4830, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 35, | |
| "save_steps": 500, | |
| "total_flos": 1.883471089464115e+16, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |