| { | |
| "best_metric": 2.4029204845428467, | |
| "best_model_checkpoint": "./outputs/checkpoint-800", | |
| "epoch": 0.5828779599271403, | |
| "eval_steps": 100, | |
| "global_step": 800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0002, | |
| "loss": 2.7194, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.617887258529663, | |
| "eval_runtime": 205.5207, | |
| "eval_samples_per_second": 30.527, | |
| "eval_steps_per_second": 3.82, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0002, | |
| "loss": 2.5817, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 2.5672028064727783, | |
| "eval_runtime": 205.4308, | |
| "eval_samples_per_second": 30.541, | |
| "eval_steps_per_second": 3.821, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0002, | |
| "loss": 2.54, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 2.5315635204315186, | |
| "eval_runtime": 205.1897, | |
| "eval_samples_per_second": 30.577, | |
| "eval_steps_per_second": 3.826, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0002, | |
| "loss": 2.5136, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 2.4977593421936035, | |
| "eval_runtime": 204.833, | |
| "eval_samples_per_second": 30.63, | |
| "eval_steps_per_second": 3.832, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4701, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 2.472073554992676, | |
| "eval_runtime": 205.144, | |
| "eval_samples_per_second": 30.583, | |
| "eval_steps_per_second": 3.827, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4445, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 2.4433655738830566, | |
| "eval_runtime": 204.9978, | |
| "eval_samples_per_second": 30.605, | |
| "eval_steps_per_second": 3.829, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4276, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 2.4212682247161865, | |
| "eval_runtime": 204.9092, | |
| "eval_samples_per_second": 30.618, | |
| "eval_steps_per_second": 3.831, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4062, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 2.4029204845428467, | |
| "eval_runtime": 205.0316, | |
| "eval_samples_per_second": 30.6, | |
| "eval_steps_per_second": 3.829, | |
| "step": 800 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 4116, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 2.349160133935104e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |