| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.11857121683711279, |
| "eval_steps": 50, |
| "global_step": 400, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.01, |
| "learning_rate": 2.3869346733668342e-05, |
| "loss": 1.7706, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.01, |
| "eval_loss": 1.6274527311325073, |
| "eval_runtime": 2691.0986, |
| "eval_samples_per_second": 5.73, |
| "eval_steps_per_second": 0.358, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.03, |
| "learning_rate": 2.2613065326633167e-05, |
| "loss": 1.5912, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.03, |
| "eval_loss": 1.5995770692825317, |
| "eval_runtime": 2694.2411, |
| "eval_samples_per_second": 5.724, |
| "eval_steps_per_second": 0.358, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.04, |
| "learning_rate": 2.135678391959799e-05, |
| "loss": 1.5518, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.04, |
| "eval_loss": 1.5821588039398193, |
| "eval_runtime": 2684.3159, |
| "eval_samples_per_second": 5.745, |
| "eval_steps_per_second": 0.359, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 2.0100502512562815e-05, |
| "loss": 1.5279, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.06, |
| "eval_loss": 1.5699576139450073, |
| "eval_runtime": 2686.6745, |
| "eval_samples_per_second": 5.74, |
| "eval_steps_per_second": 0.359, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.07, |
| "learning_rate": 1.884422110552764e-05, |
| "loss": 1.5335, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.07, |
| "eval_loss": 1.563302755355835, |
| "eval_runtime": 2703.1674, |
| "eval_samples_per_second": 5.705, |
| "eval_steps_per_second": 0.357, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.09, |
| "learning_rate": 1.7587939698492464e-05, |
| "loss": 1.5505, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.09, |
| "eval_loss": 1.5592865943908691, |
| "eval_runtime": 2692.6951, |
| "eval_samples_per_second": 5.727, |
| "eval_steps_per_second": 0.358, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 1.6331658291457288e-05, |
| "loss": 1.5241, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.1, |
| "eval_loss": 1.5557039976119995, |
| "eval_runtime": 2694.2866, |
| "eval_samples_per_second": 5.724, |
| "eval_steps_per_second": 0.358, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.12, |
| "learning_rate": 1.507537688442211e-05, |
| "loss": 1.5386, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.12, |
| "eval_loss": 1.5525078773498535, |
| "eval_runtime": 2696.0209, |
| "eval_samples_per_second": 5.72, |
| "eval_steps_per_second": 0.358, |
| "step": 400 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 1000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 50, |
| "total_flos": 4.107986141184e+17, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
