| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 9.994413407821229, |
| "global_step": 890, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.12, |
| "learning_rate": 7.5238095238095236e-06, |
| "loss": 0.6478, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.12, |
| "eval_accuracy": 0.7528795599937439, |
| "eval_loss": 0.5890260338783264, |
| "eval_runtime": 6.3154, |
| "eval_samples_per_second": 151.217, |
| "eval_steps_per_second": 9.501, |
| "step": 100 |
| }, |
| { |
| "epoch": 2.25, |
| "learning_rate": 6.571428571428571e-06, |
| "loss": 0.5013, |
| "step": 200 |
| }, |
| { |
| "epoch": 2.25, |
| "eval_accuracy": 0.7706806063652039, |
| "eval_loss": 0.5872902870178223, |
| "eval_runtime": 6.2684, |
| "eval_samples_per_second": 152.353, |
| "eval_steps_per_second": 9.572, |
| "step": 200 |
| }, |
| { |
| "epoch": 3.37, |
| "learning_rate": 5.6190476190476185e-06, |
| "loss": 0.388, |
| "step": 300 |
| }, |
| { |
| "epoch": 3.37, |
| "eval_accuracy": 0.7602094411849976, |
| "eval_loss": 0.6993213891983032, |
| "eval_runtime": 6.3121, |
| "eval_samples_per_second": 151.298, |
| "eval_steps_per_second": 9.506, |
| "step": 300 |
| }, |
| { |
| "epoch": 4.49, |
| "learning_rate": 4.666666666666667e-06, |
| "loss": 0.3169, |
| "step": 400 |
| }, |
| { |
| "epoch": 4.49, |
| "eval_accuracy": 0.7874345779418945, |
| "eval_loss": 0.6773470640182495, |
| "eval_runtime": 6.2982, |
| "eval_samples_per_second": 151.63, |
| "eval_steps_per_second": 9.527, |
| "step": 400 |
| }, |
| { |
| "epoch": 5.61, |
| "learning_rate": 3.714285714285714e-06, |
| "loss": 0.2693, |
| "step": 500 |
| }, |
| { |
| "epoch": 5.61, |
| "eval_accuracy": 0.7706806063652039, |
| "eval_loss": 0.717186450958252, |
| "eval_runtime": 6.3196, |
| "eval_samples_per_second": 151.116, |
| "eval_steps_per_second": 9.494, |
| "step": 500 |
| }, |
| { |
| "epoch": 6.74, |
| "learning_rate": 2.7619047619047616e-06, |
| "loss": 0.2396, |
| "step": 600 |
| }, |
| { |
| "epoch": 6.74, |
| "eval_accuracy": 0.7801046967506409, |
| "eval_loss": 0.7397065758705139, |
| "eval_runtime": 6.2974, |
| "eval_samples_per_second": 151.649, |
| "eval_steps_per_second": 9.528, |
| "step": 600 |
| }, |
| { |
| "epoch": 7.86, |
| "learning_rate": 1.8095238095238095e-06, |
| "loss": 0.2284, |
| "step": 700 |
| }, |
| { |
| "epoch": 7.86, |
| "eval_accuracy": 0.754973828792572, |
| "eval_loss": 0.8096243143081665, |
| "eval_runtime": 6.3109, |
| "eval_samples_per_second": 151.325, |
| "eval_steps_per_second": 9.507, |
| "step": 700 |
| }, |
| { |
| "epoch": 8.98, |
| "learning_rate": 8.57142857142857e-07, |
| "loss": 0.2207, |
| "step": 800 |
| }, |
| { |
| "epoch": 8.98, |
| "eval_accuracy": 0.7654450535774231, |
| "eval_loss": 0.7827323079109192, |
| "eval_runtime": 6.3145, |
| "eval_samples_per_second": 151.239, |
| "eval_steps_per_second": 9.502, |
| "step": 800 |
| }, |
| { |
| "epoch": 9.99, |
| "step": 890, |
| "total_flos": 1.3329504276375552e+16, |
| "train_loss": 0.33834649632486063, |
| "train_runtime": 677.9414, |
| "train_samples_per_second": 42.216, |
| "train_steps_per_second": 1.313 |
| } |
| ], |
| "max_steps": 890, |
| "num_train_epochs": 10, |
| "total_flos": 1.3329504276375552e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
