| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.734375, |
| "eval_steps": 50, |
| "global_step": 350, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.39, |
| "learning_rate": 2.203166226912929e-05, |
| "loss": 0.9534, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.39, |
| "eval_loss": 0.8879762887954712, |
| "eval_runtime": 42.6156, |
| "eval_samples_per_second": 11.733, |
| "eval_steps_per_second": 1.478, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.78, |
| "learning_rate": 1.8733509234828498e-05, |
| "loss": 0.6574, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.78, |
| "eval_loss": 0.8240162134170532, |
| "eval_runtime": 42.6096, |
| "eval_samples_per_second": 11.734, |
| "eval_steps_per_second": 1.479, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.17, |
| "learning_rate": 1.5435356200527706e-05, |
| "loss": 0.5719, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.17, |
| "eval_loss": 0.7294898629188538, |
| "eval_runtime": 42.6078, |
| "eval_samples_per_second": 11.735, |
| "eval_steps_per_second": 1.479, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.56, |
| "learning_rate": 1.2137203166226914e-05, |
| "loss": 0.5111, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.56, |
| "eval_loss": 0.7228932976722717, |
| "eval_runtime": 42.5975, |
| "eval_samples_per_second": 11.738, |
| "eval_steps_per_second": 1.479, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.95, |
| "learning_rate": 8.839050131926122e-06, |
| "loss": 0.5079, |
| "step": 250 |
| }, |
| { |
| "epoch": 1.95, |
| "eval_loss": 0.7160211205482483, |
| "eval_runtime": 42.5998, |
| "eval_samples_per_second": 11.737, |
| "eval_steps_per_second": 1.479, |
| "step": 250 |
| }, |
| { |
| "epoch": 2.34, |
| "learning_rate": 5.540897097625329e-06, |
| "loss": 0.4994, |
| "step": 300 |
| }, |
| { |
| "epoch": 2.34, |
| "eval_loss": 0.7144750952720642, |
| "eval_runtime": 42.5955, |
| "eval_samples_per_second": 11.738, |
| "eval_steps_per_second": 1.479, |
| "step": 300 |
| }, |
| { |
| "epoch": 2.73, |
| "learning_rate": 2.2427440633245386e-06, |
| "loss": 0.4927, |
| "step": 350 |
| }, |
| { |
| "epoch": 2.73, |
| "eval_loss": 0.7128794193267822, |
| "eval_runtime": 42.6003, |
| "eval_samples_per_second": 11.737, |
| "eval_steps_per_second": 1.479, |
| "step": 350 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 384, |
| "num_train_epochs": 3, |
| "save_steps": 50, |
| "total_flos": 9.814033664437125e+17, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
