| { |
| "best_global_step": 3960, |
| "best_metric": 0.0027947870548814535, |
| "best_model_checkpoint": "/content/drive/MyDrive/evo_CodeT5plus_frozenEnc/checkpoint-3960", |
| "epoch": 18.0, |
| "eval_steps": 500, |
| "global_step": 3960, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 1.1201924085617065, |
| "learning_rate": 5e-05, |
| "loss": 0.508801997791637, |
| "step": 220 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.031036050990223885, |
| "eval_runtime": 16.9632, |
| "eval_samples_per_second": 12.969, |
| "eval_steps_per_second": 6.485, |
| "step": 220 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.11240009218454361, |
| "learning_rate": 5e-05, |
| "loss": 0.1055341200395064, |
| "step": 440 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.022242471575737, |
| "eval_runtime": 17.2794, |
| "eval_samples_per_second": 12.732, |
| "eval_steps_per_second": 6.366, |
| "step": 440 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.7675652503967285, |
| "learning_rate": 5e-05, |
| "loss": 0.06234081441705877, |
| "step": 660 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.01632743328809738, |
| "eval_runtime": 17.1769, |
| "eval_samples_per_second": 12.808, |
| "eval_steps_per_second": 6.404, |
| "step": 660 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.07149142771959305, |
| "learning_rate": 5e-05, |
| "loss": 0.04255591739307751, |
| "step": 880 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.00789650809019804, |
| "eval_runtime": 17.0577, |
| "eval_samples_per_second": 12.897, |
| "eval_steps_per_second": 6.449, |
| "step": 880 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.41593658924102783, |
| "learning_rate": 5e-05, |
| "loss": 0.03280660672621293, |
| "step": 1100 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 0.010357110761106014, |
| "eval_runtime": 16.9345, |
| "eval_samples_per_second": 12.991, |
| "eval_steps_per_second": 6.496, |
| "step": 1100 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 0.0010334457037970424, |
| "learning_rate": 5e-05, |
| "loss": 0.024871245297518642, |
| "step": 1320 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 0.006158643402159214, |
| "eval_runtime": 17.2443, |
| "eval_samples_per_second": 12.758, |
| "eval_steps_per_second": 6.379, |
| "step": 1320 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 1.1123638153076172, |
| "learning_rate": 5e-05, |
| "loss": 0.02346384958787398, |
| "step": 1540 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_loss": 0.007988177239894867, |
| "eval_runtime": 16.944, |
| "eval_samples_per_second": 12.984, |
| "eval_steps_per_second": 6.492, |
| "step": 1540 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 0.02058124728500843, |
| "learning_rate": 5e-05, |
| "loss": 0.018623479929837313, |
| "step": 1760 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_loss": 0.0052207051776349545, |
| "eval_runtime": 17.0998, |
| "eval_samples_per_second": 12.866, |
| "eval_steps_per_second": 6.433, |
| "step": 1760 |
| }, |
| { |
| "epoch": 9.0, |
| "grad_norm": 0.010896311141550541, |
| "learning_rate": 5e-05, |
| "loss": 0.0202510573647239, |
| "step": 1980 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_loss": 0.010862304829061031, |
| "eval_runtime": 16.5148, |
| "eval_samples_per_second": 13.321, |
| "eval_steps_per_second": 6.661, |
| "step": 1980 |
| }, |
| { |
| "epoch": 10.0, |
| "grad_norm": 0.00067019002744928, |
| "learning_rate": 5e-05, |
| "loss": 0.018236663124778053, |
| "step": 2200 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_loss": 0.003377651795744896, |
| "eval_runtime": 16.608, |
| "eval_samples_per_second": 13.247, |
| "eval_steps_per_second": 6.623, |
| "step": 2200 |
| }, |
| { |
| "epoch": 11.0, |
| "grad_norm": 0.001838264986872673, |
| "learning_rate": 5e-05, |
| "loss": 0.01725634444843639, |
| "step": 2420 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_loss": 0.012781262397766113, |
| "eval_runtime": 16.5932, |
| "eval_samples_per_second": 13.258, |
| "eval_steps_per_second": 6.629, |
| "step": 2420 |
| }, |
| { |
| "epoch": 12.0, |
| "grad_norm": 0.0013156271306797862, |
| "learning_rate": 5e-05, |
| "loss": 0.00876567309552973, |
| "step": 2640 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_loss": 0.005950805265456438, |
| "eval_runtime": 16.5031, |
| "eval_samples_per_second": 13.331, |
| "eval_steps_per_second": 6.665, |
| "step": 2640 |
| }, |
| { |
| "epoch": 13.0, |
| "grad_norm": 0.010019246488809586, |
| "learning_rate": 5e-05, |
| "loss": 0.011685315045443448, |
| "step": 2860 |
| }, |
| { |
| "epoch": 13.0, |
| "eval_loss": 0.0038430262356996536, |
| "eval_runtime": 16.4244, |
| "eval_samples_per_second": 13.395, |
| "eval_steps_per_second": 6.697, |
| "step": 2860 |
| }, |
| { |
| "epoch": 14.0, |
| "grad_norm": 0.007604538928717375, |
| "learning_rate": 5e-05, |
| "loss": 0.007304735075343739, |
| "step": 3080 |
| }, |
| { |
| "epoch": 14.0, |
| "eval_loss": 0.006216138135641813, |
| "eval_runtime": 16.422, |
| "eval_samples_per_second": 13.397, |
| "eval_steps_per_second": 6.698, |
| "step": 3080 |
| }, |
| { |
| "epoch": 15.0, |
| "grad_norm": 0.00034067651722580194, |
| "learning_rate": 5e-05, |
| "loss": 0.0061811084097081965, |
| "step": 3300 |
| }, |
| { |
| "epoch": 15.0, |
| "eval_loss": 0.003704946953803301, |
| "eval_runtime": 16.6472, |
| "eval_samples_per_second": 13.215, |
| "eval_steps_per_second": 6.608, |
| "step": 3300 |
| }, |
| { |
| "epoch": 16.0, |
| "grad_norm": 0.00039539029239676893, |
| "learning_rate": 5e-05, |
| "loss": 0.005046481435949152, |
| "step": 3520 |
| }, |
| { |
| "epoch": 16.0, |
| "eval_loss": 0.0054435427300632, |
| "eval_runtime": 16.5747, |
| "eval_samples_per_second": 13.273, |
| "eval_steps_per_second": 6.637, |
| "step": 3520 |
| }, |
| { |
| "epoch": 17.0, |
| "grad_norm": 0.0006793063948862255, |
| "learning_rate": 5e-05, |
| "loss": 0.005749529600143433, |
| "step": 3740 |
| }, |
| { |
| "epoch": 17.0, |
| "eval_loss": 0.004094177391380072, |
| "eval_runtime": 16.5162, |
| "eval_samples_per_second": 13.32, |
| "eval_steps_per_second": 6.66, |
| "step": 3740 |
| }, |
| { |
| "epoch": 18.0, |
| "grad_norm": 0.0004089501453563571, |
| "learning_rate": 5e-05, |
| "loss": 0.004834394563328136, |
| "step": 3960 |
| }, |
| { |
| "epoch": 18.0, |
| "eval_loss": 0.0027947870548814535, |
| "eval_runtime": 16.4672, |
| "eval_samples_per_second": 13.36, |
| "eval_steps_per_second": 6.68, |
| "step": 3960 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 4400, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 20, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 3, |
| "early_stopping_threshold": 0.001 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 2 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.84867909490688e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
