| { | |
| "best_metric": 3.378286361694336, | |
| "best_model_checkpoint": "output/marillion/checkpoint-34", | |
| "epoch": 1.0, | |
| "global_step": 34, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0001300082017869573, | |
| "loss": 3.9789, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.000109940736055617, | |
| "loss": 3.5443, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 8.120521692221673e-05, | |
| "loss": 3.4392, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.982671888105512e-05, | |
| "loss": 3.3047, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 2.2384478845846175e-05, | |
| "loss": 3.6777, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.6324050628611986e-06, | |
| "loss": 3.5335, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 3.378286361694336, | |
| "eval_runtime": 0.6447, | |
| "eval_samples_per_second": 76.005, | |
| "eval_steps_per_second": 10.858, | |
| "step": 34 | |
| } | |
| ], | |
| "max_steps": 34, | |
| "num_train_epochs": 1, | |
| "total_flos": 35535716352000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |