{ "best_global_step": 244, "best_metric": 0.24269719421863556, "best_model_checkpoint": "./lora_qwen7b_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": 0.175823375582695, "learning_rate": 3.648648648648649e-06, "loss": 0.5537, "step": 10 }, { "epoch": 0.08221993833504625, "grad_norm": 0.12845267355442047, "learning_rate": 7.702702702702703e-06, "loss": 0.5427, "step": 20 }, { "epoch": 0.12332990750256938, "grad_norm": 0.13613902032375336, "learning_rate": 1.1756756756756757e-05, "loss": 0.5252, "step": 30 }, { "epoch": 0.1644398766700925, "grad_norm": 0.23862598836421967, "learning_rate": 1.5810810810810808e-05, "loss": 0.4838, "step": 40 }, { "epoch": 0.20554984583761562, "grad_norm": 0.2705032229423523, "learning_rate": 1.9864864864864866e-05, "loss": 0.395, "step": 50 }, { "epoch": 0.24665981500513876, "grad_norm": 0.10224032402038574, "learning_rate": 2.3918918918918917e-05, "loss": 0.3266, "step": 60 }, { "epoch": 0.28776978417266186, "grad_norm": 0.06852829456329346, "learning_rate": 2.7972972972972975e-05, "loss": 0.2972, "step": 70 }, { "epoch": 0.328879753340185, "grad_norm": 0.0726822167634964, "learning_rate": 2.9772036474164135e-05, "loss": 0.2954, "step": 80 }, { "epoch": 0.3699897225077081, "grad_norm": 0.06372971087694168, "learning_rate": 2.9316109422492404e-05, "loss": 0.277, "step": 90 }, { "epoch": 0.41109969167523125, "grad_norm": 0.05797314643859863, "learning_rate": 2.886018237082067e-05, "loss": 0.2666, "step": 100 }, { "epoch": 0.4522096608427544, "grad_norm": 0.062011413276195526, "learning_rate": 2.8404255319148935e-05, "loss": 0.2726, "step": 110 }, { "epoch": 0.4933196300102775, "grad_norm": 0.06568919867277145, "learning_rate": 2.7948328267477204e-05, "loss": 0.2705, "step": 120 }, { "epoch": 0.5344295991778006, "grad_norm": 0.06438654661178589, "learning_rate": 2.7492401215805473e-05, "loss": 0.2489, "step": 130 }, { "epoch": 0.5755395683453237, "grad_norm": 0.0740242451429367, "learning_rate": 2.7036474164133738e-05, "loss": 0.2513, "step": 140 }, { "epoch": 0.6166495375128469, "grad_norm": 0.0648876503109932, "learning_rate": 2.6580547112462007e-05, "loss": 0.2418, "step": 150 }, { "epoch": 0.65775950668037, "grad_norm": 0.0961170569062233, "learning_rate": 2.6124620060790272e-05, "loss": 0.2444, "step": 160 }, { "epoch": 0.6988694758478932, "grad_norm": 0.07387962192296982, "learning_rate": 2.566869300911854e-05, "loss": 0.245, "step": 170 }, { "epoch": 0.7399794450154162, "grad_norm": 0.0894966870546341, "learning_rate": 2.521276595744681e-05, "loss": 0.237, "step": 180 }, { "epoch": 0.7810894141829393, "grad_norm": 0.09798130393028259, "learning_rate": 2.4756838905775076e-05, "loss": 0.2486, "step": 190 }, { "epoch": 0.8221993833504625, "grad_norm": 0.14110679924488068, "learning_rate": 2.4300911854103345e-05, "loss": 0.2421, "step": 200 }, { "epoch": 0.8633093525179856, "grad_norm": 0.09954896569252014, "learning_rate": 2.3844984802431613e-05, "loss": 0.2265, "step": 210 }, { "epoch": 0.9044193216855088, "grad_norm": 0.1187966987490654, "learning_rate": 2.338905775075988e-05, "loss": 0.2277, "step": 220 }, { "epoch": 0.9455292908530318, "grad_norm": 0.11565206199884415, "learning_rate": 2.2933130699088144e-05, "loss": 0.2123, "step": 230 }, { "epoch": 0.986639260020555, "grad_norm": 0.13377656042575836, "learning_rate": 2.2477203647416413e-05, "loss": 0.2153, "step": 240 }, { "epoch": 1.0, "eval_loss": 0.24269719421863556, "eval_runtime": 48.0797, "eval_samples_per_second": 13.561, "eval_steps_per_second": 6.78, "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": 3.149570373234647e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }