| { | |
| "best_metric": 0.331796795129776, | |
| "best_model_checkpoint": "SpanBERT/spanbert-base-cased/subtaskB/42/checkpoint-3552", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 3552, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.718468468468469e-05, | |
| "loss": 0.7363, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.4369369369369375e-05, | |
| "loss": 0.3567, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 4.1554054054054055e-05, | |
| "loss": 0.2911, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_f1": 0.8780092918485147, | |
| "eval_loss": 0.36068207025527954, | |
| "eval_runtime": 89.1907, | |
| "eval_samples_per_second": 159.277, | |
| "eval_steps_per_second": 4.978, | |
| "step": 1776 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 3.873873873873874e-05, | |
| "loss": 0.2167, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 3.592342342342343e-05, | |
| "loss": 0.1731, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 3.310810810810811e-05, | |
| "loss": 0.1675, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 3.0292792792792797e-05, | |
| "loss": 0.148, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_f1": 0.9015204843024074, | |
| "eval_loss": 0.331796795129776, | |
| "eval_runtime": 89.0059, | |
| "eval_samples_per_second": 159.607, | |
| "eval_steps_per_second": 4.988, | |
| "step": 3552 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 8880, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 2.9901540410118144e+16, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |