| { |
| "best_global_step": 400, |
| "best_metric": 0.8451923512067675, |
| "best_model_checkpoint": "taskA-unixcoder-focal/checkpoint-400", |
| "epoch": 0.04894163709776092, |
| "eval_steps": 100, |
| "global_step": 400, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.001223540927444023, |
| "grad_norm": 0.1898110806941986, |
| "learning_rate": 3.6734693877551025e-07, |
| "loss": 0.4422, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.002447081854888046, |
| "grad_norm": 0.3350900411605835, |
| "learning_rate": 7.346938775510205e-07, |
| "loss": 0.4323, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.003670622782332069, |
| "grad_norm": 0.3723449110984802, |
| "learning_rate": 1.142857142857143e-06, |
| "loss": 0.4362, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.004894163709776092, |
| "grad_norm": 0.3299769461154938, |
| "learning_rate": 1.5510204081632654e-06, |
| "loss": 0.4191, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.006117704637220115, |
| "grad_norm": 0.26681044697761536, |
| "learning_rate": 1.9591836734693877e-06, |
| "loss": 0.4289, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.007341245564664138, |
| "grad_norm": 0.30233338475227356, |
| "learning_rate": 2.3673469387755103e-06, |
| "loss": 0.4083, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.008564786492108161, |
| "grad_norm": 0.31031334400177, |
| "learning_rate": 2.775510204081633e-06, |
| "loss": 0.404, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.009788327419552184, |
| "grad_norm": 0.2552475035190582, |
| "learning_rate": 3.183673469387755e-06, |
| "loss": 0.3889, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.011011868346996207, |
| "grad_norm": 0.3131052553653717, |
| "learning_rate": 3.5918367346938777e-06, |
| "loss": 0.3813, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.01223540927444023, |
| "grad_norm": 0.3377229571342468, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 0.3727, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.01223540927444023, |
| "eval_accuracy": 0.6961, |
| "eval_f1_weighted": 0.6955947095331424, |
| "eval_loss": 0.15026023983955383, |
| "eval_macro_f1": 0.6959280508399847, |
| "eval_precision": 0.7019396279846728, |
| "eval_recall": 0.6961, |
| "eval_runtime": 789.7648, |
| "eval_samples_per_second": 126.62, |
| "eval_steps_per_second": 0.99, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.013458950201884253, |
| "grad_norm": 0.3366774618625641, |
| "learning_rate": 4.408163265306123e-06, |
| "loss": 0.3671, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.014682491129328276, |
| "grad_norm": 0.33491575717926025, |
| "learning_rate": 4.816326530612245e-06, |
| "loss": 0.3498, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.0159060320567723, |
| "grad_norm": 0.4119006097316742, |
| "learning_rate": 5.2244897959183684e-06, |
| "loss": 0.3409, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.017129572984216322, |
| "grad_norm": 0.2964725196361542, |
| "learning_rate": 5.63265306122449e-06, |
| "loss": 0.3433, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.018353113911660345, |
| "grad_norm": 0.3075334429740906, |
| "learning_rate": 6.040816326530613e-06, |
| "loss": 0.3298, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.019576654839104368, |
| "grad_norm": 0.33718687295913696, |
| "learning_rate": 6.4489795918367345e-06, |
| "loss": 0.3297, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.02080019576654839, |
| "grad_norm": 0.2809618413448334, |
| "learning_rate": 6.857142857142858e-06, |
| "loss": 0.3275, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.022023736693992414, |
| "grad_norm": 0.37805014848709106, |
| "learning_rate": 7.2653061224489805e-06, |
| "loss": 0.3201, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.023247277621436437, |
| "grad_norm": 0.2940429151058197, |
| "learning_rate": 7.673469387755102e-06, |
| "loss": 0.3042, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.02447081854888046, |
| "grad_norm": 0.3286060690879822, |
| "learning_rate": 8.081632653061225e-06, |
| "loss": 0.3071, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.02447081854888046, |
| "eval_accuracy": 0.77807, |
| "eval_f1_weighted": 0.7781129395311969, |
| "eval_loss": 0.12153773754835129, |
| "eval_macro_f1": 0.7780651598452646, |
| "eval_precision": 0.7808306361972198, |
| "eval_recall": 0.77807, |
| "eval_runtime": 792.7157, |
| "eval_samples_per_second": 126.149, |
| "eval_steps_per_second": 0.986, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.025694359476324483, |
| "grad_norm": 0.33857154846191406, |
| "learning_rate": 8.489795918367347e-06, |
| "loss": 0.2964, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.026917900403768506, |
| "grad_norm": 0.2752092182636261, |
| "learning_rate": 8.89795918367347e-06, |
| "loss": 0.3, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.02814144133121253, |
| "grad_norm": 0.4952544569969177, |
| "learning_rate": 9.306122448979593e-06, |
| "loss": 0.294, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.029364982258656552, |
| "grad_norm": 0.37926042079925537, |
| "learning_rate": 9.714285714285715e-06, |
| "loss": 0.2964, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.030588523186100575, |
| "grad_norm": 0.3222455680370331, |
| "learning_rate": 1.0122448979591836e-05, |
| "loss": 0.283, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.0318120641135446, |
| "grad_norm": 0.2930658459663391, |
| "learning_rate": 1.053061224489796e-05, |
| "loss": 0.2793, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.03303560504098862, |
| "grad_norm": 0.4313414692878723, |
| "learning_rate": 1.0938775510204083e-05, |
| "loss": 0.2728, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.034259145968432644, |
| "grad_norm": 0.37351569533348083, |
| "learning_rate": 1.1346938775510206e-05, |
| "loss": 0.2752, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.035482686895876664, |
| "grad_norm": 0.22772285342216492, |
| "learning_rate": 1.1755102040816328e-05, |
| "loss": 0.274, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.03670622782332069, |
| "grad_norm": 0.15888753533363342, |
| "learning_rate": 1.2163265306122449e-05, |
| "loss": 0.264, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.03670622782332069, |
| "eval_accuracy": 0.82326, |
| "eval_f1_weighted": 0.8227034206790359, |
| "eval_loss": 0.10234300792217255, |
| "eval_macro_f1": 0.8230100448030374, |
| "eval_precision": 0.8338333810964687, |
| "eval_recall": 0.82326, |
| "eval_runtime": 789.0168, |
| "eval_samples_per_second": 126.74, |
| "eval_steps_per_second": 0.991, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.03792976875076471, |
| "grad_norm": 0.23560188710689545, |
| "learning_rate": 1.2571428571428572e-05, |
| "loss": 0.2753, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.039153309678208736, |
| "grad_norm": 0.18699614703655243, |
| "learning_rate": 1.2979591836734696e-05, |
| "loss": 0.2565, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.040376850605652756, |
| "grad_norm": 0.24035991728305817, |
| "learning_rate": 1.3387755102040818e-05, |
| "loss": 0.2716, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.04160039153309678, |
| "grad_norm": 0.15309660136699677, |
| "learning_rate": 1.3795918367346941e-05, |
| "loss": 0.2515, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.0428239324605408, |
| "grad_norm": 0.3382055461406708, |
| "learning_rate": 1.4204081632653062e-05, |
| "loss": 0.2597, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.04404747338798483, |
| "grad_norm": 0.24439455568790436, |
| "learning_rate": 1.4612244897959185e-05, |
| "loss": 0.247, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.04527101431542885, |
| "grad_norm": 0.26233720779418945, |
| "learning_rate": 1.5020408163265307e-05, |
| "loss": 0.2431, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.046494555242872875, |
| "grad_norm": 0.20477451384067535, |
| "learning_rate": 1.5387755102040818e-05, |
| "loss": 0.2538, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.047718096170316894, |
| "grad_norm": 0.2765439748764038, |
| "learning_rate": 1.5795918367346942e-05, |
| "loss": 0.2404, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.04894163709776092, |
| "grad_norm": 0.13196279108524323, |
| "learning_rate": 1.6204081632653063e-05, |
| "loss": 0.2393, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.04894163709776092, |
| "eval_accuracy": 0.84563, |
| "eval_f1_weighted": 0.8448128964509274, |
| "eval_loss": 0.09028046578168869, |
| "eval_macro_f1": 0.8451923512067675, |
| "eval_precision": 0.861024732271907, |
| "eval_recall": 0.84563, |
| "eval_runtime": 787.6067, |
| "eval_samples_per_second": 126.967, |
| "eval_steps_per_second": 0.993, |
| "step": 400 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 8173, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 3, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 0 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 6789830069452800.0, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
