| { | |
| "best_metric": 0.3467291593551636, | |
| "best_model_checkpoint": "./models/e5_weighted_3\\checkpoint-21170", | |
| "epoch": 10.0, | |
| "eval_steps": 4234, | |
| "global_step": 21170, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.6739985346794128, | |
| "learning_rate": 1.8e-05, | |
| "loss": 0.4895, | |
| "step": 4234 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6055607917059378, | |
| "eval_f1_0: ": 0.0, | |
| "eval_f1_1: ": 0.7543293219841503, | |
| "eval_loss": 0.4801671504974365, | |
| "eval_precision_0: ": 0.0, | |
| "eval_precision_1: ": 0.6055607917059378, | |
| "eval_recall_0: ": 0.0, | |
| "eval_recall_1: ": 1.0, | |
| "eval_runtime": 695.7116, | |
| "eval_samples_per_second": 3.05, | |
| "eval_steps_per_second": 3.05, | |
| "step": 4234 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 1.520650863647461, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.474, | |
| "step": 8468 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.6710650329877474, | |
| "eval_f1_0: ": 0.3102766798418972, | |
| "eval_f1_1: ": 0.7840346534653465, | |
| "eval_loss": 0.4519682228565216, | |
| "eval_precision_0: ": 0.8971428571428571, | |
| "eval_precision_1: ": 0.6507447354904982, | |
| "eval_recall_0: ": 0.1875746714456392, | |
| "eval_recall_1: ": 0.9859922178988327, | |
| "eval_runtime": 685.0371, | |
| "eval_samples_per_second": 3.098, | |
| "eval_steps_per_second": 3.098, | |
| "step": 8468 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.5096299648284912, | |
| "learning_rate": 1.4e-05, | |
| "loss": 0.4505, | |
| "step": 12702 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.7445805843543827, | |
| "eval_f1_0: ": 0.5505804311774462, | |
| "eval_f1_1: ": 0.8215931533903884, | |
| "eval_loss": 0.42401960492134094, | |
| "eval_precision_0: ": 0.8997289972899729, | |
| "eval_precision_1: ": 0.7119224187107815, | |
| "eval_recall_0: ": 0.3966547192353644, | |
| "eval_recall_1: ": 0.9712062256809338, | |
| "eval_runtime": 684.6385, | |
| "eval_samples_per_second": 3.099, | |
| "eval_steps_per_second": 3.099, | |
| "step": 12702 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.8480051755905151, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.418, | |
| "step": 16936 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8044297832233742, | |
| "eval_f1_0: ": 0.7182620502376104, | |
| "eval_f1_1: ": 0.85023457235655, | |
| "eval_loss": 0.37760457396507263, | |
| "eval_precision_0: ": 0.8317610062893082, | |
| "eval_precision_1: ": 0.7927321668909825, | |
| "eval_recall_0: ": 0.6320191158900836, | |
| "eval_recall_1: ": 0.9167315175097276, | |
| "eval_runtime": 680.6302, | |
| "eval_samples_per_second": 3.118, | |
| "eval_steps_per_second": 3.118, | |
| "step": 16936 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.9994410872459412, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3911, | |
| "step": 21170 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.8185673892554194, | |
| "eval_f1_0: ": 0.752411575562701, | |
| "eval_f1_1: ": 0.8568240981777613, | |
| "eval_loss": 0.3467291593551636, | |
| "eval_precision_0: ": 0.8147632311977716, | |
| "eval_precision_1: ": 0.8205128205128205, | |
| "eval_recall_0: ": 0.6989247311827957, | |
| "eval_recall_1: ": 0.8964980544747082, | |
| "eval_runtime": 673.4114, | |
| "eval_samples_per_second": 3.151, | |
| "eval_steps_per_second": 3.151, | |
| "step": 21170 | |
| } | |
| ], | |
| "logging_steps": 4234, | |
| "max_steps": 42340, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "save_steps": 4234, | |
| "total_flos": 2.448451500060672e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |