| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.9975144987572495, | |
| "global_step": 7540, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7525, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.0001, | |
| "loss": 0.692, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6752, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.6349760890007019, | |
| "eval_runtime": 199.764, | |
| "eval_samples_per_second": 16.084, | |
| "eval_steps_per_second": 1.006, | |
| "step": 1508 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5067, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5211, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5151, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.5905311703681946, | |
| "eval_runtime": 198.2597, | |
| "eval_samples_per_second": 16.206, | |
| "eval_steps_per_second": 1.014, | |
| "step": 3017 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3746, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3784, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3839, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.6004335284233093, | |
| "eval_runtime": 198.543, | |
| "eval_samples_per_second": 16.183, | |
| "eval_steps_per_second": 1.012, | |
| "step": 4526 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2699, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2732, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2841, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.6339293122291565, | |
| "eval_runtime": 198.2785, | |
| "eval_samples_per_second": 16.204, | |
| "eval_steps_per_second": 1.014, | |
| "step": 6035 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1973, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1981, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2083, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.6874634027481079, | |
| "eval_runtime": 198.2649, | |
| "eval_samples_per_second": 16.206, | |
| "eval_steps_per_second": 1.014, | |
| "step": 7540 | |
| } | |
| ], | |
| "max_steps": 7540, | |
| "num_train_epochs": 5, | |
| "total_flos": 31701581365248.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |