| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "global_step": 5972, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 2.9994976557267246e-05, | |
| "loss": 0.1243, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2.500167448091092e-05, | |
| "loss": 0.0185, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 0.016165828332304955, | |
| "eval_runtime": 163.7459, | |
| "eval_samples_per_second": 312.612, | |
| "eval_steps_per_second": 4.886, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2.0003348961821836e-05, | |
| "loss": 0.0155, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 0.016084061935544014, | |
| "eval_runtime": 163.9178, | |
| "eval_samples_per_second": 312.285, | |
| "eval_steps_per_second": 4.88, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.5005023442732755e-05, | |
| "loss": 0.0145, | |
| "step": 2985 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.018288077786564827, | |
| "eval_runtime": 163.9529, | |
| "eval_samples_per_second": 312.218, | |
| "eval_steps_per_second": 4.879, | |
| "step": 2985 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 1.000669792364367e-05, | |
| "loss": 0.0119, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_loss": 0.01668855920433998, | |
| "eval_runtime": 163.8788, | |
| "eval_samples_per_second": 312.359, | |
| "eval_steps_per_second": 4.882, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 5.008372404554588e-06, | |
| "loss": 0.0115, | |
| "step": 4975 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "eval_loss": 0.018202854320406914, | |
| "eval_runtime": 163.8281, | |
| "eval_samples_per_second": 312.456, | |
| "eval_steps_per_second": 4.883, | |
| "step": 4975 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.0046885465505694e-08, | |
| "loss": 0.0113, | |
| "step": 5970 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.017260808497667313, | |
| "eval_runtime": 163.906, | |
| "eval_samples_per_second": 312.307, | |
| "eval_steps_per_second": 4.881, | |
| "step": 5970 | |
| } | |
| ], | |
| "max_steps": 5972, | |
| "num_train_epochs": 2, | |
| "total_flos": 2.01113970314453e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |