| { | |
| "best_global_step": 244, | |
| "best_metric": 0.25023409724235535, | |
| "best_model_checkpoint": "./lora_qwen32b_java_abdiff_v1/checkpoint-244", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 244, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.041109969167523124, | |
| "grad_norm": 0.8196802735328674, | |
| "learning_rate": 3.648648648648649e-06, | |
| "loss": 0.9434, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08221993833504625, | |
| "grad_norm": 0.44579723477363586, | |
| "learning_rate": 7.702702702702703e-06, | |
| "loss": 0.9215, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.12332990750256938, | |
| "grad_norm": 0.41646608710289, | |
| "learning_rate": 1.1756756756756757e-05, | |
| "loss": 0.8404, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1644398766700925, | |
| "grad_norm": 0.39053428173065186, | |
| "learning_rate": 1.5810810810810808e-05, | |
| "loss": 0.7482, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.20554984583761562, | |
| "grad_norm": 0.2627861797809601, | |
| "learning_rate": 1.9864864864864866e-05, | |
| "loss": 0.6263, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.24665981500513876, | |
| "grad_norm": 0.2621787488460541, | |
| "learning_rate": 2.3918918918918917e-05, | |
| "loss": 0.5306, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.28776978417266186, | |
| "grad_norm": 0.19896556437015533, | |
| "learning_rate": 2.7972972972972975e-05, | |
| "loss": 0.4205, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.328879753340185, | |
| "grad_norm": 0.20418603718280792, | |
| "learning_rate": 2.9772036474164135e-05, | |
| "loss": 0.3725, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.3699897225077081, | |
| "grad_norm": 0.16360916197299957, | |
| "learning_rate": 2.9316109422492404e-05, | |
| "loss": 0.3384, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.41109969167523125, | |
| "grad_norm": 0.13916964828968048, | |
| "learning_rate": 2.886018237082067e-05, | |
| "loss": 0.3088, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4522096608427544, | |
| "grad_norm": 0.15655504167079926, | |
| "learning_rate": 2.8404255319148935e-05, | |
| "loss": 0.2883, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.4933196300102775, | |
| "grad_norm": 0.1462835967540741, | |
| "learning_rate": 2.7948328267477204e-05, | |
| "loss": 0.2884, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.5344295991778006, | |
| "grad_norm": 0.1710139513015747, | |
| "learning_rate": 2.7492401215805473e-05, | |
| "loss": 0.2752, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.5755395683453237, | |
| "grad_norm": 0.17515398561954498, | |
| "learning_rate": 2.7036474164133738e-05, | |
| "loss": 0.2525, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.6166495375128469, | |
| "grad_norm": 0.16058574616909027, | |
| "learning_rate": 2.6580547112462007e-05, | |
| "loss": 0.2512, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.65775950668037, | |
| "grad_norm": 0.208830326795578, | |
| "learning_rate": 2.6124620060790272e-05, | |
| "loss": 0.2483, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.6988694758478932, | |
| "grad_norm": 0.15300804376602173, | |
| "learning_rate": 2.566869300911854e-05, | |
| "loss": 0.2448, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.7399794450154162, | |
| "grad_norm": 0.21872150897979736, | |
| "learning_rate": 2.521276595744681e-05, | |
| "loss": 0.2269, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.7810894141829393, | |
| "grad_norm": 0.14277832210063934, | |
| "learning_rate": 2.4756838905775076e-05, | |
| "loss": 0.2364, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.8221993833504625, | |
| "grad_norm": 0.1629635989665985, | |
| "learning_rate": 2.4300911854103345e-05, | |
| "loss": 0.2248, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.8633093525179856, | |
| "grad_norm": 0.170692577958107, | |
| "learning_rate": 2.3844984802431613e-05, | |
| "loss": 0.2077, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.9044193216855088, | |
| "grad_norm": 0.168124720454216, | |
| "learning_rate": 2.338905775075988e-05, | |
| "loss": 0.215, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.9455292908530318, | |
| "grad_norm": 0.1866914927959442, | |
| "learning_rate": 2.2933130699088144e-05, | |
| "loss": 0.1893, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.986639260020555, | |
| "grad_norm": 0.17521585524082184, | |
| "learning_rate": 2.2477203647416413e-05, | |
| "loss": 0.1922, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.25023409724235535, | |
| "eval_runtime": 335.9934, | |
| "eval_samples_per_second": 1.941, | |
| "eval_steps_per_second": 0.97, | |
| "step": 244 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 732, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.3597929863862886e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |