| { | |
| "best_metric": 2.7185754776000977, | |
| "best_model_checkpoint": "../Modelos/bloomz_QG_SQUAD/checkpoint-500", | |
| "epoch": 0.36531348463400154, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.8082664012908936, | |
| "eval_runtime": 75.8818, | |
| "eval_samples_per_second": 139.296, | |
| "eval_steps_per_second": 34.83, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.692033290863037, | |
| "eval_runtime": 75.8713, | |
| "eval_samples_per_second": 139.315, | |
| "eval_steps_per_second": 34.835, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 2.698404312133789, | |
| "eval_runtime": 75.8537, | |
| "eval_samples_per_second": 139.347, | |
| "eval_steps_per_second": 34.843, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 2.6990063190460205, | |
| "eval_runtime": 75.8436, | |
| "eval_samples_per_second": 139.366, | |
| "eval_steps_per_second": 34.848, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 2.6953232288360596, | |
| "eval_runtime": 75.859, | |
| "eval_samples_per_second": 139.337, | |
| "eval_steps_per_second": 34.841, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 2.6985721588134766, | |
| "eval_runtime": 75.8584, | |
| "eval_samples_per_second": 139.339, | |
| "eval_steps_per_second": 34.841, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 2.703632116317749, | |
| "eval_runtime": 75.8692, | |
| "eval_samples_per_second": 139.319, | |
| "eval_steps_per_second": 34.836, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 2.713385581970215, | |
| "eval_runtime": 75.8665, | |
| "eval_samples_per_second": 139.324, | |
| "eval_steps_per_second": 34.838, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 2.7052266597747803, | |
| "eval_runtime": 75.8449, | |
| "eval_samples_per_second": 139.363, | |
| "eval_steps_per_second": 34.847, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 4.395711500974659e-05, | |
| "loss": 2.3203, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 2.7185754776000977, | |
| "eval_runtime": 75.8537, | |
| "eval_samples_per_second": 139.347, | |
| "eval_steps_per_second": 34.843, | |
| "step": 500 | |
| } | |
| ], | |
| "max_steps": 4104, | |
| "num_train_epochs": 3, | |
| "total_flos": 1.65432208130048e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |