| { |
| "best_metric": 0.9402330079719138, |
| "best_model_checkpoint": "model_saves/electra-large_lemon_5k_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": 0.9401211999239705, |
| "eval_loss": 0.434908002614975, |
| "eval_runtime": 3.4108, |
| "eval_samples_per_second": 1284.754, |
| "eval_steps_per_second": 10.262, |
| "step": 268 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9402330079719138, |
| "eval_loss": 0.4419630169868469, |
| "eval_runtime": 3.4081, |
| "eval_samples_per_second": 1285.766, |
| "eval_steps_per_second": 10.27, |
| "step": 536 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9394000380147363, |
| "eval_loss": 0.46554210782051086, |
| "eval_runtime": 3.3982, |
| "eval_samples_per_second": 1289.512, |
| "eval_steps_per_second": 10.3, |
| "step": 804 |
| }, |
| { |
| "epoch": 3.73, |
| "learning_rate": 1e-05, |
| "loss": 0.3514, |
| "step": 1000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9382092823041402, |
| "eval_loss": 0.4920196235179901, |
| "eval_runtime": 3.3984, |
| "eval_samples_per_second": 1289.443, |
| "eval_steps_per_second": 10.299, |
| "step": 1072 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9382707767305091, |
| "eval_loss": 0.5161693096160889, |
| "eval_runtime": 3.3981, |
| "eval_samples_per_second": 1289.557, |
| "eval_steps_per_second": 10.3, |
| "step": 1340 |
| }, |
| { |
| "epoch": 5.0, |
| "step": 1340, |
| "total_flos": 1.7368569444564992e+16, |
| "train_loss": 0.3237331105701959, |
| "train_runtime": 398.8479, |
| "train_samples_per_second": 1290.116, |
| "train_steps_per_second": 10.079 |
| } |
| ], |
| "max_steps": 4020, |
| "num_train_epochs": 15, |
| "total_flos": 1.7368569444564992e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
