| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 189, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.79, |
| "grad_norm": 1.3655260801315308, |
| "learning_rate": 9.059690028579284e-05, |
| "loss": 2.2708, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.9815729856491089, |
| "eval_runtime": 13.5787, |
| "eval_samples_per_second": 7.364, |
| "eval_steps_per_second": 0.957, |
| "step": 63 |
| }, |
| { |
| "epoch": 1.59, |
| "grad_norm": 1.725501537322998, |
| "learning_rate": 6.592433251258423e-05, |
| "loss": 1.898, |
| "step": 100 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 1.9519867897033691, |
| "eval_runtime": 13.5864, |
| "eval_samples_per_second": 7.36, |
| "eval_steps_per_second": 0.957, |
| "step": 126 |
| }, |
| { |
| "epoch": 2.38, |
| "grad_norm": 2.334561347961426, |
| "learning_rate": 3.5262241279454785e-05, |
| "loss": 1.781, |
| "step": 150 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 1.9462159872055054, |
| "eval_runtime": 13.583, |
| "eval_samples_per_second": 7.362, |
| "eval_steps_per_second": 0.957, |
| "step": 189 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 252, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "save_steps": 500, |
| "total_flos": 2.612791192682496e+16, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
