| { | |
| "best_metric": 0.5492420196533203, | |
| "best_model_checkpoint": "output_pipe/H3K36me3/origin/checkpoint-200", | |
| "epoch": 4.0, | |
| "eval_steps": 200, | |
| "global_step": 436, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.9174311926605505, | |
| "grad_norm": 117693.7421875, | |
| "learning_rate": 2.61139896373057e-05, | |
| "loss": 0.6221, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.834862385321101, | |
| "grad_norm": 116578.09375, | |
| "learning_rate": 1.8341968911917098e-05, | |
| "loss": 0.4876, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.834862385321101, | |
| "eval_accuracy": 0.7287844036697247, | |
| "eval_f1": 0.7280921038752821, | |
| "eval_loss": 0.5492420196533203, | |
| "eval_matthews_correlation": 0.45658863624288465, | |
| "eval_precision": 0.7279104558673231, | |
| "eval_recall": 0.7286788269024161, | |
| "eval_runtime": 2.9078, | |
| "eval_samples_per_second": 1199.551, | |
| "eval_steps_per_second": 4.815, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.7522935779816513, | |
| "grad_norm": 232886.5, | |
| "learning_rate": 1.0569948186528496e-05, | |
| "loss": 0.3139, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.669724770642202, | |
| "grad_norm": 299264.625, | |
| "learning_rate": 2.7979274611398963e-06, | |
| "loss": 0.1326, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.669724770642202, | |
| "eval_accuracy": 0.694954128440367, | |
| "eval_f1": 0.6946279268548363, | |
| "eval_loss": 1.1083674430847168, | |
| "eval_matthews_correlation": 0.4032476523392284, | |
| "eval_precision": 0.7029578254285642, | |
| "eval_recall": 0.7002985950082683, | |
| "eval_runtime": 2.9237, | |
| "eval_samples_per_second": 1193.01, | |
| "eval_steps_per_second": 4.788, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "step": 436, | |
| "total_flos": 2.7611321199630336e+16, | |
| "train_loss": 0.36331664750335413, | |
| "train_runtime": 268.1728, | |
| "train_samples_per_second": 416.209, | |
| "train_steps_per_second": 1.626 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 436, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.7611321199630336e+16, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } |