| { |
| "best_metric": 0.15741272270679474, |
| "best_model_checkpoint": "imdb_full/checkpoint-524", |
| "epoch": 5.0, |
| "eval_steps": 500, |
| "global_step": 655, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9204, |
| "eval_loss": 0.21770058572292328, |
| "eval_runtime": 78.2774, |
| "eval_samples_per_second": 319.377, |
| "eval_steps_per_second": 1.674, |
| "step": 131 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.92204, |
| "eval_loss": 0.19915565848350525, |
| "eval_runtime": 78.1566, |
| "eval_samples_per_second": 319.871, |
| "eval_steps_per_second": 1.676, |
| "step": 262 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.93932, |
| "eval_loss": 0.1659126728773117, |
| "eval_runtime": 78.3631, |
| "eval_samples_per_second": 319.028, |
| "eval_steps_per_second": 1.672, |
| "step": 393 |
| }, |
| { |
| "epoch": 3.82, |
| "grad_norm": 2.5449366569519043, |
| "learning_rate": 1.4198473282442749e-05, |
| "loss": 0.1895, |
| "step": 500 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.94728, |
| "eval_loss": 0.15741272270679474, |
| "eval_runtime": 78.2398, |
| "eval_samples_per_second": 319.53, |
| "eval_steps_per_second": 1.674, |
| "step": 524 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.94664, |
| "eval_loss": 0.17783348262310028, |
| "eval_runtime": 78.29, |
| "eval_samples_per_second": 319.326, |
| "eval_steps_per_second": 1.673, |
| "step": 655 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 655, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 500, |
| "total_flos": 6.5276215197696e+16, |
| "train_batch_size": 192, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
