| { | |
| "best_metric": 0.331796795129776, | |
| "best_model_checkpoint": "SpanBERT/spanbert-base-cased/subtaskB/42/checkpoint-3552", | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 7104, | |
| "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 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 2.7477477477477483e-05, | |
| "loss": 0.0907, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 2.4662162162162162e-05, | |
| "loss": 0.0807, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 2.1846846846846845e-05, | |
| "loss": 0.0807, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_f1": 0.8860340701112206, | |
| "eval_loss": 0.5412303805351257, | |
| "eval_runtime": 89.0561, | |
| "eval_samples_per_second": 159.517, | |
| "eval_steps_per_second": 4.986, | |
| "step": 5328 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 1.9031531531531532e-05, | |
| "loss": 0.0633, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 1.6216216216216218e-05, | |
| "loss": 0.0457, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 1.3400900900900901e-05, | |
| "loss": 0.0396, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 1.0585585585585586e-05, | |
| "loss": 0.0312, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_f1": 0.9003238068421794, | |
| "eval_loss": 0.6021693348884583, | |
| "eval_runtime": 89.2552, | |
| "eval_samples_per_second": 159.162, | |
| "eval_steps_per_second": 4.975, | |
| "step": 7104 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 8880, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 5.980308082023629e+16, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |