| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 848, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9.950235849056605e-06, | |
| "loss": 6.539, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 6.494007587432861, | |
| "eval_runtime": 2.5292, | |
| "eval_samples_per_second": 267.281, | |
| "eval_steps_per_second": 33.608, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 9.900235849056603e-06, | |
| "loss": 6.4697, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 6.410468101501465, | |
| "eval_runtime": 2.6306, | |
| "eval_samples_per_second": 256.98, | |
| "eval_steps_per_second": 32.313, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 9.850235849056604e-06, | |
| "loss": 6.3924, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 6.319283962249756, | |
| "eval_runtime": 2.6112, | |
| "eval_samples_per_second": 258.881, | |
| "eval_steps_per_second": 32.552, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 9.800235849056604e-06, | |
| "loss": 6.3093, | |
| "step": 848 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 6.226834297180176, | |
| "eval_runtime": 2.5547, | |
| "eval_samples_per_second": 264.612, | |
| "eval_steps_per_second": 33.272, | |
| "step": 848 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 42400, | |
| "num_train_epochs": 200, | |
| "save_steps": 500, | |
| "total_flos": 1137839826710832.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |