| { |
| "best_metric": 4.4292988777160645, |
| "best_model_checkpoint": "gen_test/checkpoint-3", |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 3, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_loss": 4.76393461227417, |
| "eval_runtime": 0.5527, |
| "eval_samples_per_second": 180.921, |
| "eval_steps_per_second": 1.809, |
| "step": 1 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 4.551311016082764, |
| "eval_runtime": 0.5172, |
| "eval_samples_per_second": 193.34, |
| "eval_steps_per_second": 1.933, |
| "step": 2 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 4.4292988777160645, |
| "eval_runtime": 0.5054, |
| "eval_samples_per_second": 197.849, |
| "eval_steps_per_second": 1.978, |
| "step": 3 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 4, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "save_steps": 500, |
| "total_flos": 156775219200000.0, |
| "train_batch_size": 128, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
