| { | |
| "best_metric": 0.09137263894081116, | |
| "best_model_checkpoint": "data/models/gene/final/checkpoint-11915", | |
| "epoch": 1.0, | |
| "global_step": 11915, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.082182123373897e-05, | |
| "loss": 0.1639, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 8.684364246747798e-05, | |
| "loss": 0.1393, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 8.286546370121695e-05, | |
| "loss": 0.1309, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 7.888728493495594e-05, | |
| "loss": 0.1286, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 7.490910616869493e-05, | |
| "loss": 0.1222, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 7.093092740243391e-05, | |
| "loss": 0.1202, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 6.695274863617289e-05, | |
| "loss": 0.1166, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 6.297456986991188e-05, | |
| "loss": 0.1164, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 5.8996391103650865e-05, | |
| "loss": 0.1099, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 5.501821233738984e-05, | |
| "loss": 0.1101, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 5.1040033571128834e-05, | |
| "loss": 0.1096, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.7061854804867815e-05, | |
| "loss": 0.1088, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.3083676038606796e-05, | |
| "loss": 0.1055, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 3.9105497272345784e-05, | |
| "loss": 0.1027, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.512731850608477e-05, | |
| "loss": 0.0961, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.114913973982375e-05, | |
| "loss": 0.1026, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.7170960973562734e-05, | |
| "loss": 0.1005, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 2.3192782207301722e-05, | |
| "loss": 0.1002, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.9214603441040703e-05, | |
| "loss": 0.1008, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.523642467477969e-05, | |
| "loss": 0.0947, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1.1258245908518674e-05, | |
| "loss": 0.0935, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 7.2800671422576585e-06, | |
| "loss": 0.0961, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.301888375996643e-06, | |
| "loss": 0.0926, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9433962264150944, | |
| "eval_f1": 0.6666666666666666, | |
| "eval_loss": 0.09137263894081116, | |
| "eval_precision": 0.5, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 1.5459, | |
| "eval_samples_per_second": 1.294, | |
| "eval_steps_per_second": 0.647, | |
| "step": 11915 | |
| } | |
| ], | |
| "max_steps": 11915, | |
| "num_train_epochs": 1, | |
| "total_flos": 4.981092847655731e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |