| { |
| "best_metric": 0.9403839488366372, |
| "best_model_checkpoint": "model_saves/xlnet-large_spell_10k_1_p3/checkpoint-536", |
| "epoch": 5.0, |
| "global_step": 1340, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9398304989993179, |
| "eval_loss": 0.44720619916915894, |
| "eval_runtime": 4.8402, |
| "eval_samples_per_second": 905.343, |
| "eval_steps_per_second": 7.231, |
| "step": 268 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9403839488366372, |
| "eval_loss": 0.4755527377128601, |
| "eval_runtime": 4.859, |
| "eval_samples_per_second": 901.824, |
| "eval_steps_per_second": 7.203, |
| "step": 536 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9397354621585662, |
| "eval_loss": 0.5032013058662415, |
| "eval_runtime": 4.8256, |
| "eval_samples_per_second": 908.071, |
| "eval_steps_per_second": 7.253, |
| "step": 804 |
| }, |
| { |
| "epoch": 3.73, |
| "learning_rate": 1e-05, |
| "loss": 0.2921, |
| "step": 1000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.939014300249332, |
| "eval_loss": 0.5414313673973083, |
| "eval_runtime": 4.863, |
| "eval_samples_per_second": 901.091, |
| "eval_steps_per_second": 7.197, |
| "step": 1072 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9388801305918, |
| "eval_loss": 0.6039970517158508, |
| "eval_runtime": 4.8364, |
| "eval_samples_per_second": 906.048, |
| "eval_steps_per_second": 7.237, |
| "step": 1340 |
| }, |
| { |
| "epoch": 5.0, |
| "step": 1340, |
| "total_flos": 2.157187052863488e+16, |
| "train_loss": 0.26465964530830954, |
| "train_runtime": 554.7047, |
| "train_samples_per_second": 927.629, |
| "train_steps_per_second": 7.247 |
| } |
| ], |
| "max_steps": 4020, |
| "num_train_epochs": 15, |
| "total_flos": 2.157187052863488e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
