| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.034587995930824, |
| "eval_steps": 500, |
| "global_step": 2000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.508646998982706, |
| "grad_norm": 0.5738646984100342, |
| "learning_rate": 6.779661016949152e-05, |
| "loss": 0.4728, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.508646998982706, |
| "eval_loss": 0.1229739561676979, |
| "eval_runtime": 42.7422, |
| "eval_samples_per_second": 1.872, |
| "eval_steps_per_second": 1.872, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.017293997965412, |
| "grad_norm": 0.17700934410095215, |
| "learning_rate": 0.00013559322033898305, |
| "loss": 0.1138, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.017293997965412, |
| "eval_loss": 0.10153152793645859, |
| "eval_runtime": 42.5835, |
| "eval_samples_per_second": 1.879, |
| "eval_steps_per_second": 1.879, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.53, |
| "grad_norm": 0.1444922387599945, |
| "learning_rate": 6.779661016949152e-05, |
| "loss": 0.0726, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.53, |
| "eval_loss": 0.06399567425251007, |
| "eval_runtime": 37.8818, |
| "eval_samples_per_second": 2.112, |
| "eval_steps_per_second": 2.112, |
| "step": 1500 |
| }, |
| { |
| "epoch": 2.03, |
| "grad_norm": 0.7290983200073242, |
| "learning_rate": 0.00013559322033898305, |
| "loss": 0.0614, |
| "step": 2000 |
| }, |
| { |
| "epoch": 2.03, |
| "eval_loss": 0.06189391762018204, |
| "eval_runtime": 37.9392, |
| "eval_samples_per_second": 2.109, |
| "eval_steps_per_second": 2.109, |
| "step": 2000 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 49150, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 50, |
| "save_steps": 500, |
| "total_flos": 1.767441615125714e+17, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
