| { | |
| "best_metric": 0.626257061958313, | |
| "best_model_checkpoint": "./training_output/checkpoint-100", | |
| "epoch": 3.4482758620689653, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0001913793103448276, | |
| "loss": 1.4859, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00018275862068965518, | |
| "loss": 1.2666, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.00017413793103448276, | |
| "loss": 1.0816, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.00016551724137931035, | |
| "loss": 0.699, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.00015689655172413793, | |
| "loss": 0.5932, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 0.00014827586206896554, | |
| "loss": 0.577, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 0.0001396551724137931, | |
| "loss": 0.2562, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 0.00013103448275862068, | |
| "loss": 0.2048, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 0.00012241379310344827, | |
| "loss": 0.1517, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 0.00011379310344827588, | |
| "loss": 0.1104, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "eval_accuracy": 0.7819548872180451, | |
| "eval_loss": 0.626257061958313, | |
| "eval_runtime": 1.9072, | |
| "eval_samples_per_second": 69.738, | |
| "eval_steps_per_second": 8.914, | |
| "step": 100 | |
| } | |
| ], | |
| "max_steps": 232, | |
| "num_train_epochs": 8, | |
| "total_flos": 1.2213065939971277e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |