| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.96, | |
| "global_step": 110, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.5535714285714286e-05, | |
| "loss": 9.5247, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 9.106889724731445, | |
| "eval_runtime": 10.9192, | |
| "eval_samples_per_second": 45.791, | |
| "eval_steps_per_second": 2.931, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.107142857142857e-05, | |
| "loss": 8.9275, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 8.750078201293945, | |
| "eval_runtime": 10.9208, | |
| "eval_samples_per_second": 45.784, | |
| "eval_steps_per_second": 2.93, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 3.6607142857142853e-05, | |
| "loss": 8.607, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 8.482429504394531, | |
| "eval_runtime": 10.9198, | |
| "eval_samples_per_second": 45.788, | |
| "eval_steps_per_second": 2.93, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.2142857142857144e-05, | |
| "loss": 8.3321, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 8.233388900756836, | |
| "eval_runtime": 10.9137, | |
| "eval_samples_per_second": 45.814, | |
| "eval_steps_per_second": 2.932, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 2.767857142857143e-05, | |
| "loss": 8.1348, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_loss": 8.06030559539795, | |
| "eval_runtime": 10.9143, | |
| "eval_samples_per_second": 45.811, | |
| "eval_steps_per_second": 2.932, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 2.3214285714285715e-05, | |
| "loss": 8.1555, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_loss": 7.913366317749023, | |
| "eval_runtime": 10.9187, | |
| "eval_samples_per_second": 45.793, | |
| "eval_steps_per_second": 2.931, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 1.8750000000000002e-05, | |
| "loss": 7.8179, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_loss": 7.809637546539307, | |
| "eval_runtime": 10.9216, | |
| "eval_samples_per_second": 45.781, | |
| "eval_steps_per_second": 2.93, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 7.7208, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "eval_loss": 7.679474353790283, | |
| "eval_runtime": 10.9236, | |
| "eval_samples_per_second": 45.773, | |
| "eval_steps_per_second": 2.929, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 9.821428571428573e-06, | |
| "loss": 7.6457, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 7.6539998054504395, | |
| "eval_runtime": 10.9201, | |
| "eval_samples_per_second": 45.787, | |
| "eval_steps_per_second": 2.93, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 5.357142857142857e-06, | |
| "loss": 7.568, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "eval_loss": 7.568892478942871, | |
| "eval_runtime": 10.9247, | |
| "eval_samples_per_second": 45.768, | |
| "eval_steps_per_second": 2.929, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 8.928571428571428e-07, | |
| "loss": 7.5441, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "eval_loss": 7.546835899353027, | |
| "eval_runtime": 10.9233, | |
| "eval_samples_per_second": 45.774, | |
| "eval_steps_per_second": 2.93, | |
| "step": 110 | |
| } | |
| ], | |
| "max_steps": 112, | |
| "num_train_epochs": 2, | |
| "total_flos": 2321466448896000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |