layout-xlm-base-finetuned-with-DocLayNet-base-at-linelevel-ml384
/
checkpoint-6300
/trainer_state.json
| { | |
| "best_metric": 0.7336375680847931, | |
| "best_model_checkpoint": "DocLayNet/layout-xlm-base-finetuned-DocLayNet-base_lines_ml384-v1/checkpoint-6300", | |
| "epoch": 2.617366015787287, | |
| "global_step": 6300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.12, | |
| "eval_accuracy": 0.8412902144953226, | |
| "eval_f1": 0.13109765966400155, | |
| "eval_loss": 0.5185014605522156, | |
| "eval_precision": 0.14371894960965223, | |
| "eval_recall": 0.1205141938939475, | |
| "eval_runtime": 363.2958, | |
| "eval_samples_per_second": 5.648, | |
| "eval_steps_per_second": 0.355, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.372060857538036e-05, | |
| "loss": 0.9231, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_accuracy": 0.8751371332529899, | |
| "eval_f1": 0.5030902012034086, | |
| "eval_loss": 0.4107707738876343, | |
| "eval_precision": 0.4636655625815517, | |
| "eval_recall": 0.5498422900672499, | |
| "eval_runtime": 366.1838, | |
| "eval_samples_per_second": 5.604, | |
| "eval_steps_per_second": 0.352, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_accuracy": 0.8887072454995973, | |
| "eval_f1": 0.520614670919107, | |
| "eval_loss": 0.3911038935184479, | |
| "eval_precision": 0.5076044552496184, | |
| "eval_recall": 0.5343093495209189, | |
| "eval_runtime": 358.5079, | |
| "eval_samples_per_second": 5.724, | |
| "eval_steps_per_second": 0.36, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.9159741458910434e-05, | |
| "loss": 0.369, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_accuracy": 0.8723944681931917, | |
| "eval_f1": 0.5365372697053354, | |
| "eval_loss": 0.41175082325935364, | |
| "eval_precision": 0.5093875367745386, | |
| "eval_recall": 0.5667440338034875, | |
| "eval_runtime": 370.2231, | |
| "eval_samples_per_second": 5.543, | |
| "eval_steps_per_second": 0.348, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.7620806401969838e-05, | |
| "loss": 0.2737, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_accuracy": 0.8960354303687331, | |
| "eval_f1": 0.6032919847328244, | |
| "eval_loss": 0.33280590176582336, | |
| "eval_precision": 0.6045538755752107, | |
| "eval_recall": 0.6020353508302089, | |
| "eval_runtime": 369.9685, | |
| "eval_samples_per_second": 5.546, | |
| "eval_steps_per_second": 0.349, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_accuracy": 0.9185901350526106, | |
| "eval_f1": 0.640386343216532, | |
| "eval_loss": 0.2983764410018921, | |
| "eval_precision": 0.6061765800244512, | |
| "eval_recall": 0.6786883294649765, | |
| "eval_runtime": 366.7561, | |
| "eval_samples_per_second": 5.595, | |
| "eval_steps_per_second": 0.352, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.6084949215143123e-05, | |
| "loss": 0.2542, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_accuracy": 0.9162879176822183, | |
| "eval_f1": 0.6593356503902912, | |
| "eval_loss": 0.3114674985408783, | |
| "eval_precision": 0.6323842832941691, | |
| "eval_recall": 0.6886865440695114, | |
| "eval_runtime": 356.8285, | |
| "eval_samples_per_second": 5.751, | |
| "eval_steps_per_second": 0.362, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.919752052270062, | |
| "eval_f1": 0.6536656236030397, | |
| "eval_loss": 0.2877778708934784, | |
| "eval_precision": 0.6160408657643899, | |
| "eval_recall": 0.6961852050229126, | |
| "eval_runtime": 352.6194, | |
| "eval_samples_per_second": 5.819, | |
| "eval_steps_per_second": 0.366, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 1.4546014158202526e-05, | |
| "loss": 0.1938, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_accuracy": 0.9165257053918363, | |
| "eval_f1": 0.6752131725962951, | |
| "eval_loss": 0.34137091040611267, | |
| "eval_precision": 0.6672865694194223, | |
| "eval_recall": 0.6833303576742248, | |
| "eval_runtime": 349.7664, | |
| "eval_samples_per_second": 5.867, | |
| "eval_steps_per_second": 0.369, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 1.3007079101261929e-05, | |
| "loss": 0.1581, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_accuracy": 0.9193251152459752, | |
| "eval_f1": 0.6871282417320962, | |
| "eval_loss": 0.3610578179359436, | |
| "eval_precision": 0.6867605968729564, | |
| "eval_recall": 0.6874962804261144, | |
| "eval_runtime": 346.075, | |
| "eval_samples_per_second": 5.929, | |
| "eval_steps_per_second": 0.373, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "eval_accuracy": 0.9256291916839153, | |
| "eval_f1": 0.6821629855293222, | |
| "eval_loss": 0.2762657403945923, | |
| "eval_precision": 0.6987891648982649, | |
| "eval_recall": 0.6663095875736476, | |
| "eval_runtime": 342.8929, | |
| "eval_samples_per_second": 5.984, | |
| "eval_steps_per_second": 0.376, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 1.1471221914435212e-05, | |
| "loss": 0.1428, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_accuracy": 0.9287285383081404, | |
| "eval_f1": 0.7083662914511712, | |
| "eval_loss": 0.306523859500885, | |
| "eval_precision": 0.7245907761249767, | |
| "eval_recall": 0.6928524668214009, | |
| "eval_runtime": 342.9768, | |
| "eval_samples_per_second": 5.983, | |
| "eval_steps_per_second": 0.376, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "eval_accuracy": 0.9193764557741881, | |
| "eval_f1": 0.6812402542881132, | |
| "eval_loss": 0.29422909021377563, | |
| "eval_precision": 0.6865518283469326, | |
| "eval_recall": 0.6760102362673333, | |
| "eval_runtime": 340.2288, | |
| "eval_samples_per_second": 6.031, | |
| "eval_steps_per_second": 0.379, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 9.932286857494614e-06, | |
| "loss": 0.1025, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "eval_accuracy": 0.9346597203832706, | |
| "eval_f1": 0.7223092684102689, | |
| "eval_loss": 0.2989632189273834, | |
| "eval_precision": 0.7315227342081172, | |
| "eval_recall": 0.7133250014878295, | |
| "eval_runtime": 368.8508, | |
| "eval_samples_per_second": 5.563, | |
| "eval_steps_per_second": 0.35, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 8.393351800554018e-06, | |
| "loss": 0.1225, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_accuracy": 0.9360324039797016, | |
| "eval_f1": 0.7047921954799842, | |
| "eval_loss": 0.2729274332523346, | |
| "eval_precision": 0.7248993457473578, | |
| "eval_recall": 0.6857703981431887, | |
| "eval_runtime": 366.3118, | |
| "eval_samples_per_second": 5.602, | |
| "eval_steps_per_second": 0.352, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_accuracy": 0.9395776025594604, | |
| "eval_f1": 0.7221742349457059, | |
| "eval_loss": 0.2825567126274109, | |
| "eval_precision": 0.7496957663485557, | |
| "eval_recall": 0.6966017972981016, | |
| "eval_runtime": 379.1173, | |
| "eval_samples_per_second": 5.413, | |
| "eval_steps_per_second": 0.34, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 6.85441674361342e-06, | |
| "loss": 0.108, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "eval_accuracy": 0.9301336475013375, | |
| "eval_f1": 0.7193125072581582, | |
| "eval_loss": 0.3070518672466278, | |
| "eval_precision": 0.7022277648659373, | |
| "eval_recall": 0.7372493007201095, | |
| "eval_runtime": 371.7164, | |
| "eval_samples_per_second": 5.52, | |
| "eval_steps_per_second": 0.347, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "eval_accuracy": 0.9334356541053508, | |
| "eval_f1": 0.7243484735666419, | |
| "eval_loss": 0.29993483424186707, | |
| "eval_precision": 0.7250178869544479, | |
| "eval_recall": 0.7236802951853836, | |
| "eval_runtime": 373.5258, | |
| "eval_samples_per_second": 5.494, | |
| "eval_steps_per_second": 0.345, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 5.315481686672823e-06, | |
| "loss": 0.0799, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "eval_accuracy": 0.9382346424267317, | |
| "eval_f1": 0.7253808324337292, | |
| "eval_loss": 0.2709857225418091, | |
| "eval_precision": 0.7310365669386522, | |
| "eval_recall": 0.7198119383443433, | |
| "eval_runtime": 362.6803, | |
| "eval_samples_per_second": 5.658, | |
| "eval_steps_per_second": 0.356, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 3.7765466297322255e-06, | |
| "loss": 0.0793, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "eval_accuracy": 0.9328519933635612, | |
| "eval_f1": 0.7228055311809738, | |
| "eval_loss": 0.32012131810188293, | |
| "eval_precision": 0.7351963560260988, | |
| "eval_recall": 0.7108254478366959, | |
| "eval_runtime": 358.4508, | |
| "eval_samples_per_second": 5.725, | |
| "eval_steps_per_second": 0.36, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "eval_accuracy": 0.9373375342495366, | |
| "eval_f1": 0.7336375680847931, | |
| "eval_loss": 0.30349481105804443, | |
| "eval_precision": 0.7259643398205338, | |
| "eval_recall": 0.7414747366541689, | |
| "eval_runtime": 356.5492, | |
| "eval_samples_per_second": 5.755, | |
| "eval_steps_per_second": 0.362, | |
| "step": 6300 | |
| } | |
| ], | |
| "max_steps": 7221, | |
| "num_train_epochs": 3, | |
| "total_flos": 2.0401375422887424e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |