| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.05, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1e-05, | |
| "loss": 1.8152, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 1.8217052221298218, | |
| "eval_runtime": 3139.8873, | |
| "eval_samples_per_second": 0.105, | |
| "eval_steps_per_second": 0.105, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2e-05, | |
| "loss": 1.8212, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 1.8069214820861816, | |
| "eval_runtime": 3158.5963, | |
| "eval_samples_per_second": 0.104, | |
| "eval_steps_per_second": 0.104, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 3e-05, | |
| "loss": 1.7827, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 1.7773431539535522, | |
| "eval_runtime": 3157.7474, | |
| "eval_samples_per_second": 0.104, | |
| "eval_steps_per_second": 0.104, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4e-05, | |
| "loss": 1.7508, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 1.7374451160430908, | |
| "eval_runtime": 3156.3204, | |
| "eval_samples_per_second": 0.104, | |
| "eval_steps_per_second": 0.104, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6906, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 1.699914813041687, | |
| "eval_runtime": 3153.2876, | |
| "eval_samples_per_second": 0.104, | |
| "eval_steps_per_second": 0.104, | |
| "step": 50 | |
| } | |
| ], | |
| "max_steps": 1000, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 3.2053420386942976e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |