| { | |
| "best_metric": 0.6928467154502869, | |
| "best_model_checkpoint": "./indicBERTClassifier/checkpoint-2000", | |
| "epoch": 4.0, | |
| "global_step": 2000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.7427, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.6978471279144287, | |
| "eval_runtime": 15.9862, | |
| "eval_samples_per_second": 125.108, | |
| "eval_steps_per_second": 31.277, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.7037, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.701702892780304, | |
| "eval_runtime": 20.3617, | |
| "eval_samples_per_second": 98.224, | |
| "eval_steps_per_second": 24.556, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.7023, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.698264479637146, | |
| "eval_runtime": 16.271, | |
| "eval_samples_per_second": 122.918, | |
| "eval_steps_per_second": 30.73, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.6995, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.6928467154502869, | |
| "eval_runtime": 16.1542, | |
| "eval_samples_per_second": 123.807, | |
| "eval_steps_per_second": 30.952, | |
| "step": 2000 | |
| } | |
| ], | |
| "max_steps": 2500, | |
| "num_train_epochs": 5, | |
| "total_flos": 526222110720000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |