| { | |
| "best_metric": 3.4194247722625732, | |
| "best_model_checkpoint": "output/yung-plague/checkpoint-27", | |
| "epoch": 3.0, | |
| "global_step": 27, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 5.668773501204858e-05, | |
| "loss": 4.0027, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 3.563796281814575, | |
| "eval_runtime": 0.6785, | |
| "eval_samples_per_second": 20.635, | |
| "eval_steps_per_second": 2.948, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.137086214086682e-06, | |
| "loss": 3.6612, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.00010290000000000001, | |
| "loss": 3.6102, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 3.4986250400543213, | |
| "eval_runtime": 0.687, | |
| "eval_samples_per_second": 20.38, | |
| "eval_steps_per_second": 2.911, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 0.0001211506487979619, | |
| "loss": 3.4843, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 1.6049351202038163e-05, | |
| "loss": 3.2793, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 3.4194247722625732, | |
| "eval_runtime": 0.6815, | |
| "eval_samples_per_second": 20.542, | |
| "eval_steps_per_second": 2.935, | |
| "step": 27 | |
| } | |
| ], | |
| "max_steps": 27, | |
| "num_train_epochs": 3, | |
| "total_flos": 27435663360000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |