| { | |
| "best_metric": 0.8858029733703643, | |
| "best_model_checkpoint": "./results1/output/checkpoint-554460", | |
| "epoch": 2.0, | |
| "global_step": 554460, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.787836344379806e-06, | |
| "loss": 0.4724, | |
| "step": 277230 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8809251522860411, | |
| "eval_loss": 0.55721116065979, | |
| "eval_runtime": 500.703, | |
| "eval_samples_per_second": 85.574, | |
| "eval_steps_per_second": 21.394, | |
| "step": 277230 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 3.1926775545288493e-06, | |
| "loss": 0.3483, | |
| "step": 554460 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8858029733703643, | |
| "eval_loss": 0.5279836058616638, | |
| "eval_runtime": 500.7272, | |
| "eval_samples_per_second": 85.57, | |
| "eval_steps_per_second": 21.393, | |
| "step": 554460 | |
| } | |
| ], | |
| "max_steps": 1108920, | |
| "num_train_epochs": 4, | |
| "total_flos": 2.6662097583706835e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |