| /workspace/bina02-ppocr/.venv/lib/python3.12/site-packages/paddle/utils/cpp_extension/extension_utils.py:712: UserWarning: No ccache found. Please be aware that recompiling all source files may be required. You can download and install ccache from: https://github.com/ccache/ccache/blob/master/doc/INSTALL.md |
| warnings.warn(warning_message) |
| LAUNCH INFO 2026-07-25 18:18:03,894 ----------- Configuration ---------------------- |
| LAUNCH INFO 2026-07-25 18:18:03,894 auto_cluster_config: 0 |
| LAUNCH INFO 2026-07-25 18:18:03,894 auto_parallel_config: None |
| LAUNCH INFO 2026-07-25 18:18:03,894 auto_tuner_json: None |
| LAUNCH INFO 2026-07-25 18:18:03,894 devices: 0,1,2,3,4,5,6,7 |
| LAUNCH INFO 2026-07-25 18:18:03,894 elastic_level: -1 |
| LAUNCH INFO 2026-07-25 18:18:03,894 elastic_timeout: 30 |
| LAUNCH INFO 2026-07-25 18:18:03,894 enable_gpu_log: True |
| LAUNCH INFO 2026-07-25 18:18:03,894 gloo_port: 6767 |
| LAUNCH INFO 2026-07-25 18:18:03,894 host: None |
| LAUNCH INFO 2026-07-25 18:18:03,894 ips: None |
| LAUNCH INFO 2026-07-25 18:18:03,894 job_id: default |
| LAUNCH INFO 2026-07-25 18:18:03,894 legacy: False |
| LAUNCH INFO 2026-07-25 18:18:03,894 log_dir: /workspace/bina02-ppocr/training/stage-007/distributed-logs |
| LAUNCH INFO 2026-07-25 18:18:03,894 log_level: INFO |
| LAUNCH INFO 2026-07-25 18:18:03,894 log_overwrite: False |
| LAUNCH INFO 2026-07-25 18:18:03,894 master: None |
| LAUNCH INFO 2026-07-25 18:18:03,894 max_restart: 3 |
| LAUNCH INFO 2026-07-25 18:18:03,894 nnodes: 1 |
| LAUNCH INFO 2026-07-25 18:18:03,894 nproc_per_node: None |
| LAUNCH INFO 2026-07-25 18:18:03,894 rank: -1 |
| LAUNCH INFO 2026-07-25 18:18:03,894 run_mode: collective |
| LAUNCH INFO 2026-07-25 18:18:03,894 server_num: None |
| LAUNCH INFO 2026-07-25 18:18:03,894 servers: |
| LAUNCH INFO 2026-07-25 18:18:03,894 sort_ip: False |
| LAUNCH INFO 2026-07-25 18:18:03,894 start_port: 6070 |
| LAUNCH INFO 2026-07-25 18:18:03,894 trainer_num: None |
| LAUNCH INFO 2026-07-25 18:18:03,894 trainers: |
| LAUNCH INFO 2026-07-25 18:18:03,894 training_script: /workspace/bina02-ppocr/PaddleOCR/tools/train.py |
| LAUNCH INFO 2026-07-25 18:18:03,894 training_script_args: ['-c', '/workspace/bina02-ppocr/training/stage-007/input_config.yml'] |
| LAUNCH INFO 2026-07-25 18:18:03,894 with_gloo: 1 |
| LAUNCH INFO 2026-07-25 18:18:03,894 -------------------------------------------------- |
| LAUNCH INFO 2026-07-25 18:18:03,896 Job: default, mode collective, replicas 1[1:1], elastic False |
| LAUNCH INFO 2026-07-25 18:18:03,897 Run Pod: eihcwy, replicas 8, status ready |
| LAUNCH INFO 2026-07-25 18:18:04,128 Watching Pod: eihcwy, replicas 8, status running |
| /workspace/bina02-ppocr/.venv/lib/python3.12/site-packages/paddle/utils/cpp_extension/extension_utils.py:712: UserWarning: No ccache found. Please be aware that recompiling all source files may be required. You can download and install ccache from: https://github.com/ccache/ccache/blob/master/doc/INSTALL.md |
| warnings.warn(warning_message) |
| Skipping import of the encryption module. |
| [2026/07/25 18:18:11] ppocr INFO: Architecture : |
| [2026/07/25 18:18:11] ppocr INFO: Backbone : |
| [2026/07/25 18:18:11] ppocr INFO: force_pool_width : True |
| [2026/07/25 18:18:11] ppocr INFO: model_size : medium |
| [2026/07/25 18:18:11] ppocr INFO: name : PPLCNetV4 |
| [2026/07/25 18:18:11] ppocr INFO: train_pool_width : 96 |
| [2026/07/25 18:18:11] ppocr INFO: Head : |
| [2026/07/25 18:18:11] ppocr INFO: head_list : |
| [2026/07/25 18:18:11] ppocr INFO: CTCHead : |
| [2026/07/25 18:18:11] ppocr INFO: Head : |
| [2026/07/25 18:18:11] ppocr INFO: fc_decay : 1e-05 |
| [2026/07/25 18:18:11] ppocr INFO: Neck : |
| [2026/07/25 18:18:11] ppocr INFO: depth : 2 |
| [2026/07/25 18:18:11] ppocr INFO: dims : 192 |
| [2026/07/25 18:18:11] ppocr INFO: local_kernel : 7 |
| [2026/07/25 18:18:11] ppocr INFO: mlp_ratio : 4.0 |
| [2026/07/25 18:18:11] ppocr INFO: name : lightsvtr |
| [2026/07/25 18:18:11] ppocr INFO: use_guide : False |
| [2026/07/25 18:18:11] ppocr INFO: NRTRHead : |
| [2026/07/25 18:18:11] ppocr INFO: max_text_length : 128 |
| [2026/07/25 18:18:11] ppocr INFO: nrtr_dim : 512 |
| [2026/07/25 18:18:11] ppocr INFO: name : MultiHead |
| [2026/07/25 18:18:11] ppocr INFO: Transform : None |
| [2026/07/25 18:18:11] ppocr INFO: algorithm : SVTR_LCNet |
| [2026/07/25 18:18:11] ppocr INFO: model_type : rec |
| [2026/07/25 18:18:11] ppocr INFO: Eval : |
| [2026/07/25 18:18:11] ppocr INFO: dataset : |
| [2026/07/25 18:18:11] ppocr INFO: data_dir : / |
| [2026/07/25 18:18:11] ppocr INFO: label_file_list : ['/workspace/bina02-ppocr/stream/datasets/chunk-007/eval_ctc.txt'] |
| [2026/07/25 18:18:11] ppocr INFO: name : SimpleDataSet |
| [2026/07/25 18:18:11] ppocr INFO: transforms : |
| [2026/07/25 18:18:11] ppocr INFO: DecodeImage : |
| [2026/07/25 18:18:11] ppocr INFO: channel_first : False |
| [2026/07/25 18:18:11] ppocr INFO: img_mode : BGR |
| [2026/07/25 18:18:11] ppocr INFO: MultiLabelEncode : |
| [2026/07/25 18:18:11] ppocr INFO: gtc_encode : NRTRLabelEncode |
| [2026/07/25 18:18:11] ppocr INFO: RecResizeImg : |
| [2026/07/25 18:18:11] ppocr INFO: image_shape : [3, 48, 768] |
| [2026/07/25 18:18:11] ppocr INFO: padding : False |
| [2026/07/25 18:18:11] ppocr INFO: KeepKeys : |
| [2026/07/25 18:18:11] ppocr INFO: keep_keys : ['image', 'label_ctc', 'label_gtc', 'length', 'valid_ratio'] |
| [2026/07/25 18:18:11] ppocr INFO: loader : |
| [2026/07/25 18:18:11] ppocr INFO: batch_size_per_card : 32 |
| [2026/07/25 18:18:11] ppocr INFO: drop_last : False |
| [2026/07/25 18:18:11] ppocr INFO: num_workers : 4 |
| [2026/07/25 18:18:11] ppocr INFO: shuffle : False |
| [2026/07/25 18:18:11] ppocr INFO: Global : |
| [2026/07/25 18:18:11] ppocr INFO: cal_metric_during_train : False |
| [2026/07/25 18:18:11] ppocr INFO: character_dict_path : /workspace/bina02-ppocr/stream/datasets/chunk-007/persian_arabic_bina02_dict.txt |
| [2026/07/25 18:18:11] ppocr INFO: checkpoints : None |
| [2026/07/25 18:18:11] ppocr INFO: d2s_train_image_shape : [3, 48, 768] |
| [2026/07/25 18:18:11] ppocr INFO: debug : False |
| [2026/07/25 18:18:11] ppocr INFO: distributed : True |
| [2026/07/25 18:18:11] ppocr INFO: epoch_num : 1 |
| [2026/07/25 18:18:11] ppocr INFO: eval_batch_step : [0, 100] |
| [2026/07/25 18:18:11] ppocr INFO: freeze_batch_norm : True |
| [2026/07/25 18:18:11] ppocr INFO: infer_img : doc/imgs_words/ch/word_1.jpg |
| [2026/07/25 18:18:11] ppocr INFO: infer_mode : False |
| [2026/07/25 18:18:11] ppocr INFO: log_smooth_window : 20 |
| [2026/07/25 18:18:11] ppocr INFO: max_text_length : 128 |
| [2026/07/25 18:18:11] ppocr INFO: model_name : PP-OCRv6_medium_rec |
| [2026/07/25 18:18:11] ppocr INFO: pretrained_model : /workspace/bina02-ppocr/training/stage-006/best_accuracy |
| [2026/07/25 18:18:11] ppocr INFO: print_batch_step : 20 |
| [2026/07/25 18:18:11] ppocr INFO: save_epoch_step : 1 |
| [2026/07/25 18:18:11] ppocr INFO: save_inference_dir : None |
| [2026/07/25 18:18:11] ppocr INFO: save_model_dir : /workspace/bina02-ppocr/training/stage-007 |
| [2026/07/25 18:18:11] ppocr INFO: save_res_path : /workspace/bina02-ppocr/training/stage-007/predicts.txt |
| [2026/07/25 18:18:11] ppocr INFO: trainable_parameter_prefixes : ['head.ctc_head.fc.'] |
| [2026/07/25 18:18:11] ppocr INFO: use_gpu : True |
| [2026/07/25 18:18:11] ppocr INFO: use_space_char : True |
| [2026/07/25 18:18:11] ppocr INFO: use_visualdl : False |
| [2026/07/25 18:18:11] ppocr INFO: Loss : |
| [2026/07/25 18:18:11] ppocr INFO: loss_config_list : |
| [2026/07/25 18:18:11] ppocr INFO: CTCLoss : None |
| [2026/07/25 18:18:11] ppocr INFO: NRTRLoss : None |
| [2026/07/25 18:18:11] ppocr INFO: name : MultiLoss |
| [2026/07/25 18:18:11] ppocr INFO: weight_1 : 1.0 |
| [2026/07/25 18:18:11] ppocr INFO: weight_2 : 0.0 |
| [2026/07/25 18:18:11] ppocr INFO: Metric : |
| [2026/07/25 18:18:11] ppocr INFO: ignore_space : False |
| [2026/07/25 18:18:11] ppocr INFO: main_indicator : norm_edit_dis |
| [2026/07/25 18:18:11] ppocr INFO: name : RecMetric |
| [2026/07/25 18:18:11] ppocr INFO: Optimizer : |
| [2026/07/25 18:18:11] ppocr INFO: beta1 : 0.9 |
| [2026/07/25 18:18:11] ppocr INFO: beta2 : 0.999 |
| [2026/07/25 18:18:11] ppocr INFO: lr : |
| [2026/07/25 18:18:11] ppocr INFO: learning_rate : 1e-05 |
| [2026/07/25 18:18:11] ppocr INFO: name : Cosine |
| [2026/07/25 18:18:11] ppocr INFO: warmup_epoch : 0 |
| [2026/07/25 18:18:11] ppocr INFO: name : Adam |
| [2026/07/25 18:18:11] ppocr INFO: regularizer : |
| [2026/07/25 18:18:11] ppocr INFO: factor : 0.0 |
| [2026/07/25 18:18:11] ppocr INFO: name : L2 |
| [2026/07/25 18:18:11] ppocr INFO: PostProcess : |
| [2026/07/25 18:18:11] ppocr INFO: name : CTCLabelDecode |
| [2026/07/25 18:18:11] ppocr INFO: Train : |
| [2026/07/25 18:18:11] ppocr INFO: dataset : |
| [2026/07/25 18:18:11] ppocr INFO: data_dir : / |
| [2026/07/25 18:18:11] ppocr INFO: ds_width : False |
| [2026/07/25 18:18:11] ppocr INFO: ext_op_transform_idx : 1 |
| [2026/07/25 18:18:11] ppocr INFO: label_file_list : ['/workspace/bina02-ppocr/stream/datasets/chunk-007/train_ctc.txt'] |
| [2026/07/25 18:18:11] ppocr INFO: name : MultiScaleDataSet |
| [2026/07/25 18:18:11] ppocr INFO: padding : False |
| [2026/07/25 18:18:11] ppocr INFO: ratio_list : [1.0] |
| [2026/07/25 18:18:11] ppocr INFO: transforms : |
| [2026/07/25 18:18:11] ppocr INFO: DecodeImage : |
| [2026/07/25 18:18:11] ppocr INFO: channel_first : False |
| [2026/07/25 18:18:11] ppocr INFO: img_mode : BGR |
| [2026/07/25 18:18:11] ppocr INFO: RecConAug : |
| [2026/07/25 18:18:11] ppocr INFO: ext_data_num : 0 |
| [2026/07/25 18:18:11] ppocr INFO: image_shape : [48, 768, 3] |
| [2026/07/25 18:18:11] ppocr INFO: max_text_length : 128 |
| [2026/07/25 18:18:11] ppocr INFO: prob : 0.0 |
| [2026/07/25 18:18:11] ppocr INFO: RecAug : None |
| [2026/07/25 18:18:11] ppocr INFO: MultiLabelEncode : |
| [2026/07/25 18:18:11] ppocr INFO: gtc_encode : NRTRLabelEncode |
| [2026/07/25 18:18:11] ppocr INFO: KeepKeys : |
| [2026/07/25 18:18:11] ppocr INFO: keep_keys : ['image', 'label_ctc', 'label_gtc', 'length', 'valid_ratio'] |
| [2026/07/25 18:18:11] ppocr INFO: loader : |
| [2026/07/25 18:18:11] ppocr INFO: batch_size_per_card : 32 |
| [2026/07/25 18:18:11] ppocr INFO: drop_last : False |
| [2026/07/25 18:18:11] ppocr INFO: num_workers : 4 |
| [2026/07/25 18:18:11] ppocr INFO: shuffle : True |
| [2026/07/25 18:18:11] ppocr INFO: sampler : |
| [2026/07/25 18:18:11] ppocr INFO: divided_factor : [8, 16] |
| [2026/07/25 18:18:11] ppocr INFO: first_bs : 32 |
| [2026/07/25 18:18:11] ppocr INFO: fix_bs : True |
| [2026/07/25 18:18:11] ppocr INFO: is_training : True |
| [2026/07/25 18:18:11] ppocr INFO: name : MultiScaleSampler |
| [2026/07/25 18:18:11] ppocr INFO: scales : [[768, 48]] |
| [2026/07/25 18:18:11] ppocr INFO: profiler_options : None |
| [2026/07/25 18:18:11] ppocr INFO: train with paddle 3.3.0 and device Place(gpu:0) |
| ======================= Modified FLAGS detected ======================= |
| FLAGS(name='FLAGS_cudnn_deterministic', current_value=True, default_value=False) |
| FLAGS(name='FLAGS_enable_pir_in_executor', current_value=True, default_value=False) |
| FLAGS(name='FLAGS_cusparse_dir', current_value='/workspace/bina02-ppocr/.venv/lib/python3.12/site-packages/paddle/../nvidia/cusparse/lib', default_value='') |
| FLAGS(name='FLAGS_cusolver_dir', current_value='/workspace/bina02-ppocr/.venv/lib/python3.12/site-packages/paddle/../nvidia/cusolver/lib', default_value='') |
| FLAGS(name='FLAGS_nvidia_package_dir', current_value='/workspace/bina02-ppocr/.venv/lib/python3.12/site-packages/paddle/../nvidia', default_value='') |
| FLAGS(name='FLAGS_curand_dir', current_value='/workspace/bina02-ppocr/.venv/lib/python3.12/site-packages/paddle/../nvidia/curand/lib', default_value='') |
| FLAGS(name='FLAGS_cublas_dir', current_value='/workspace/bina02-ppocr/.venv/lib/python3.12/site-packages/paddle/../nvidia/cublas/lib', default_value='') |
| FLAGS(name='FLAGS_selected_gpus', current_value='0', default_value='') |
| FLAGS(name='FLAGS_cuda_cccl_dir', current_value='/workspace/bina02-ppocr/.venv/lib/python3.12/site-packages/paddle/../nvidia/cuda_cccl/include/', default_value='') |
| FLAGS(name='FLAGS_nccl_dir', current_value='/workspace/bina02-ppocr/.venv/lib/python3.12/site-packages/paddle/../nvidia/nccl/lib', default_value='') |
| FLAGS(name='FLAGS_cupti_dir', current_value='/workspace/bina02-ppocr/.venv/lib/python3.12/site-packages/paddle/../nvidia/cuda_cupti/lib', default_value='') |
| FLAGS(name='FLAGS_cudnn_dir', current_value='/workspace/bina02-ppocr/.venv/lib/python3.12/site-packages/paddle/../nvidia/cudnn/lib', default_value='') |
| ======================================================================= |
| I0725 18:18:11.076189 128134 tcp_store.cc:336] create libuv server at port: 43941 |
| I0725 18:18:11.076768 128134 tcp_utils.cc:132] Successfully connected to 172.17.0.2:43941 |
| I0725 18:18:13.962779 128134 process_group_nccl.cc:155] ProcessGroupNCCL pg_timeout_ 1800000 |
| I0725 18:18:13.962853 128134 process_group_nccl.cc:156] ProcessGroupNCCL nccl_comm_init_option_ 0 |
| [2026/07/25 18:18:13] ppocr INFO: Initialize indexs of datasets:['/workspace/bina02-ppocr/stream/datasets/chunk-007/train_ctc.txt'] |
| [2026/07/25 18:18:14] ppocr INFO: Initialize indexs of datasets:['/workspace/bina02-ppocr/stream/datasets/chunk-007/eval_ctc.txt'] |
| W0725 18:18:14.176976 128134 gpu_resources.cc:116] Please NOTE: device: 0, GPU Compute Capability: 12.0, Driver API Version: 13.0, Runtime API Version: 13.0 |
| [2026/07/25 18:18:14] ppocr INFO: froze 61 BatchNorm layers with pretrained global statistics |
| [2026/07/25 18:18:14] ppocr INFO: selective training enabled: 2 trainable tensors, 438 frozen tensors; head.ctc_head.fc.weight, head.ctc_head.fc.bias |
| [2026-07-25 18:18:14,561] [ INFO] optimizer.py:254 - If regularizer of a Parameter has been set by 'paddle.ParamAttr' or 'static.WeightNormParamAttr' already. The weight_decay[0.0] in Optimizer will not take effect, and it will only be applied to other Parameters! |
| [2026/07/25 18:18:14] ppocr INFO: train dataloader has 391 iters |
| [2026/07/25 18:18:14] ppocr INFO: valid dataloader has 128 iters |
| [2026/07/25 18:18:14] ppocr INFO: load pretrain successful from /workspace/bina02-ppocr/training/stage-006/best_accuracy |
| [2026/07/25 18:18:15] ppocr INFO: During the training process, after the 0th iteration, an evaluation is run every 100 iterations |
| [2026/07/25 18:18:20] ppocr INFO: epoch: [1/1], global_step: 20, lr: 0.000010, CTCLoss: 54.069864, NRTRLoss: 0.000000, loss: 54.069864, avg_reader_cost: 0.09074 s, avg_batch_cost: 0.22503 s, avg_samples: 32.0, ips: 142.20142 samples/s, eta: 0:01:23, max_mem_reserved: 1045 MB, max_mem_allocated: 656 MB |
| [2026/07/25 18:18:23] ppocr INFO: epoch: [1/1], global_step: 40, lr: 0.000010, CTCLoss: 57.698181, NRTRLoss: 0.000000, loss: 57.698181, avg_reader_cost: 0.01444 s, avg_batch_cost: 0.09926 s, avg_samples: 32.0, ips: 322.37935 samples/s, eta: 0:00:56, max_mem_reserved: 1045 MB, max_mem_allocated: 656 MB |
| [2026/07/25 18:18:26] ppocr INFO: epoch: [1/1], global_step: 60, lr: 0.000010, CTCLoss: 57.867037, NRTRLoss: 0.000000, loss: 57.867037, avg_reader_cost: 0.00136 s, avg_batch_cost: 0.07532 s, avg_samples: 32.0, ips: 424.85406 samples/s, eta: 0:00:44, max_mem_reserved: 1045 MB, max_mem_allocated: 656 MB |
| [2026/07/25 18:18:28] ppocr INFO: epoch: [1/1], global_step: 80, lr: 0.000009, CTCLoss: 55.285238, NRTRLoss: 0.000000, loss: 55.285238, avg_reader_cost: 0.00137 s, avg_batch_cost: 0.08291 s, avg_samples: 32.0, ips: 385.94836 samples/s, eta: 0:00:37, max_mem_reserved: 1045 MB, max_mem_allocated: 656 MB |
| [2026/07/25 18:18:31] ppocr INFO: epoch: [1/1], global_step: 100, lr: 0.000009, CTCLoss: 57.460367, NRTRLoss: 0.000000, loss: 57.460367, avg_reader_cost: 0.00646 s, avg_batch_cost: 0.08112 s, avg_samples: 32.0, ips: 394.45928 samples/s, eta: 0:00:32, max_mem_reserved: 1045 MB, max_mem_allocated: 656 MB |
|
|
| eval model:: 0%| | 0/128 [00:00<?, ?it/s] |
| eval model:: 1%| | 1/128 [00:00<00:50, 2.52it/s] |
| eval model:: 2%|β | 3/128 [00:00<00:19, 6.40it/s] |
| eval model:: 4%|β | 5/128 [00:00<00:14, 8.43it/s] |
| eval model:: 5%|β | 7/128 [00:00<00:12, 9.60it/s] |
| eval model:: 7%|β | 9/128 [00:01<00:11, 10.44it/s] |
| eval model:: 9%|β | 11/128 [00:01<00:10, 11.03it/s] |
| eval model:: 10%|β | 13/128 [00:01<00:09, 11.91it/s] |
| eval model:: 12%|ββ | 15/128 [00:01<00:09, 11.89it/s] |
| eval model:: 13%|ββ | 17/128 [00:01<00:09, 11.91it/s] |
| eval model:: 15%|ββ | 19/128 [00:01<00:09, 11.68it/s] |
| eval model:: 16%|ββ | 21/128 [00:02<00:08, 12.18it/s] |
| eval model:: 18%|ββ | 23/128 [00:02<00:08, 12.72it/s] |
| eval model:: 20%|ββ | 25/128 [00:02<00:07, 12.88it/s] |
| eval model:: 21%|ββ | 27/128 [00:02<00:07, 13.00it/s] |
| eval model:: 23%|βββ | 29/128 [00:02<00:07, 13.03it/s] |
| eval model:: 24%|βββ | 31/128 [00:02<00:07, 13.05it/s] |
| eval model:: 26%|βββ | 33/128 [00:02<00:07, 13.37it/s] |
| eval model:: 27%|βββ | 35/128 [00:03<00:07, 13.18it/s] |
| eval model:: 29%|βββ | 37/128 [00:03<00:06, 13.07it/s] |
| eval model:: 30%|βββ | 39/128 [00:03<00:06, 13.36it/s] |
| eval model:: 32%|ββββ | 41/128 [00:03<00:06, 13.48it/s] |
| eval model:: 34%|ββββ | 43/128 [00:03<00:06, 13.64it/s] |
| eval model:: 35%|ββββ | 45/128 [00:03<00:06, 13.67it/s] |
| eval model:: 37%|ββββ | 47/128 [00:03<00:05, 13.79it/s] |
| eval model:: 38%|ββββ | 49/128 [00:04<00:05, 13.84it/s] |
| eval model:: 40%|ββββ | 51/128 [00:04<00:05, 13.93it/s] |
| eval model:: 41%|βββββ | 53/128 [00:04<00:05, 13.96it/s] |
| eval model:: 43%|βββββ | 55/128 [00:04<00:05, 14.03it/s] |
| eval model:: 45%|βββββ | 57/128 [00:04<00:05, 14.03it/s] |
| eval model:: 46%|βββββ | 59/128 [00:04<00:04, 14.03it/s] |
| eval model:: 48%|βββββ | 61/128 [00:04<00:04, 14.06it/s] |
| eval model:: 49%|βββββ | 63/128 [00:05<00:04, 14.09it/s] |
| eval model:: 51%|βββββ | 65/128 [00:05<00:04, 14.05it/s] |
| eval model:: 52%|ββββββ | 67/128 [00:05<00:04, 14.05it/s] |
| eval model:: 54%|ββββββ | 69/128 [00:05<00:04, 13.97it/s] |
| eval model:: 55%|ββββββ | 71/128 [00:05<00:04, 14.00it/s] |
| eval model:: 57%|ββββββ | 73/128 [00:05<00:03, 13.96it/s] |
| eval model:: 59%|ββββββ | 75/128 [00:05<00:03, 13.93it/s] |
| eval model:: 60%|ββββββ | 77/128 [00:06<00:03, 14.00it/s] |
| eval model:: 62%|βββββββ | 79/128 [00:06<00:03, 13.39it/s] |
| eval model:: 63%|βββββββ | 81/128 [00:06<00:03, 12.94it/s] |
| eval model:: 65%|βββββββ | 83/128 [00:06<00:03, 12.68it/s] |
| eval model:: 66%|βββββββ | 85/128 [00:06<00:03, 12.30it/s] |
| eval model:: 68%|βββββββ | 87/128 [00:06<00:03, 11.79it/s] |
| eval model:: 70%|βββββββ | 89/128 [00:07<00:03, 11.68it/s] |
| eval model:: 71%|βββββββ | 91/128 [00:07<00:03, 12.32it/s] |
| eval model:: 73%|ββββββββ | 93/128 [00:07<00:02, 11.73it/s] |
| eval model:: 74%|ββββββββ | 95/128 [00:07<00:02, 12.12it/s] |
| eval model:: 76%|ββββββββ | 97/128 [00:07<00:02, 12.47it/s] |
| eval model:: 77%|ββββββββ | 99/128 [00:07<00:02, 12.71it/s] |
| eval model:: 79%|ββββββββ | 101/128 [00:08<00:02, 13.11it/s] |
| eval model:: 80%|ββββββββ | 103/128 [00:08<00:01, 13.18it/s] |
| eval model:: 82%|βββββββββ | 105/128 [00:08<00:01, 13.21it/s] |
| eval model:: 84%|βββββββββ | 107/128 [00:08<00:01, 13.26it/s] |
| eval model:: 85%|βββββββββ | 109/128 [00:08<00:01, 13.51it/s] |
| eval model:: 87%|βββββββββ | 111/128 [00:08<00:01, 13.39it/s] |
| eval model:: 88%|βββββββββ | 113/128 [00:08<00:01, 13.53it/s] |
| eval model:: 90%|βββββββββ | 115/128 [00:09<00:00, 13.69it/s] |
| eval model:: 91%|ββββββββββ| 117/128 [00:09<00:00, 13.75it/s] |
| eval model:: 93%|ββββββββββ| 119/128 [00:09<00:00, 13.86it/s] |
| eval model:: 95%|ββββββββββ| 121/128 [00:09<00:00, 13.89it/s] |
| eval model:: 96%|ββββββββββ| 123/128 [00:09<00:00, 13.64it/s] |
| eval model:: 98%|ββββββββββ| 125/128 [00:09<00:00, 13.81it/s] |
| eval model:: 99%|ββββββββββ| 127/128 [00:09<00:00, 13.89it/s] |
| eval model:: 100%|ββββββββββ| 128/128 [00:10<00:00, 12.66it/s] |
| [2026/07/25 18:18:41] ppocr INFO: cur metric, acc: 0.8486328104281426, norm_edit_dis: 0.9878907467826298, fps: 448.9321704838909 |
| [2026/07/25 18:18:41] ppocr INFO: save best model is to /workspace/bina02-ppocr/training/stage-007/best_accuracy |
| [2026/07/25 18:18:41] ppocr INFO: best metric, norm_edit_dis: 0.9878907467826298, is_float16: False, acc: 0.8486328104281426, fps: 448.9321704838909, best_epoch: 1 |
| [2026/07/25 18:18:44] ppocr INFO: epoch: [1/1], global_step: 120, lr: 0.000008, CTCLoss: 55.602468, NRTRLoss: 0.000000, loss: 55.602468, avg_reader_cost: 0.00923 s, avg_batch_cost: 0.09156 s, avg_samples: 32.0, ips: 349.49316 samples/s, eta: 0:00:29, max_mem_reserved: 1045 MB, max_mem_allocated: 672 MB |
| [2026/07/25 18:18:46] ppocr INFO: epoch: [1/1], global_step: 140, lr: 0.000008, CTCLoss: 50.380356, NRTRLoss: 0.000000, loss: 50.380356, avg_reader_cost: 0.00788 s, avg_batch_cost: 0.08466 s, avg_samples: 32.0, ips: 378.00006 samples/s, eta: 0:00:26, max_mem_reserved: 1045 MB, max_mem_allocated: 672 MB |
| [2026/07/25 18:18:49] ppocr INFO: epoch: [1/1], global_step: 160, lr: 0.000007, CTCLoss: 59.276169, NRTRLoss: 0.000000, loss: 59.276169, avg_reader_cost: 0.00925 s, avg_batch_cost: 0.09206 s, avg_samples: 32.0, ips: 347.59239 samples/s, eta: 0:00:24, max_mem_reserved: 1045 MB, max_mem_allocated: 672 MB |
| [2026/07/25 18:18:51] ppocr INFO: epoch: [1/1], global_step: 180, lr: 0.000006, CTCLoss: 54.049324, NRTRLoss: 0.000000, loss: 54.049324, avg_reader_cost: 0.01121 s, avg_batch_cost: 0.09121 s, avg_samples: 32.0, ips: 350.84727 samples/s, eta: 0:00:21, max_mem_reserved: 1045 MB, max_mem_allocated: 672 MB |
| [2026/07/25 18:18:54] ppocr INFO: epoch: [1/1], global_step: 200, lr: 0.000005, CTCLoss: 59.166794, NRTRLoss: 0.000000, loss: 59.166794, avg_reader_cost: 0.00180 s, avg_batch_cost: 0.08229 s, avg_samples: 32.0, ips: 388.85965 samples/s, eta: 0:00:19, max_mem_reserved: 1045 MB, max_mem_allocated: 672 MB |
|
|
| eval model:: 0%| | 0/128 [00:00<?, ?it/s] |
| eval model:: 1%| | 1/128 [00:00<01:04, 1.97it/s] |
| eval model:: 2%|β | 3/128 [00:00<00:23, 5.24it/s] |
| eval model:: 4%|β | 5/128 [00:00<00:16, 7.58it/s] |
| eval model:: 5%|β | 7/128 [00:00<00:12, 9.40it/s] |
| eval model:: 7%|β | 9/128 [00:01<00:11, 10.47it/s] |
| eval model:: 9%|β | 11/128 [00:01<00:10, 11.27it/s] |
| eval model:: 10%|β | 13/128 [00:01<00:09, 11.84it/s] |
| eval model:: 12%|ββ | 15/128 [00:01<00:09, 12.49it/s] |
| eval model:: 13%|ββ | 17/128 [00:01<00:08, 12.54it/s] |
| eval model:: 15%|ββ | 19/128 [00:01<00:08, 12.97it/s] |
| eval model:: 16%|ββ | 21/128 [00:02<00:08, 13.20it/s] |
| eval model:: 18%|ββ | 23/128 [00:02<00:07, 13.46it/s] |
| eval model:: 20%|ββ | 25/128 [00:02<00:07, 13.59it/s] |
| eval model:: 21%|ββ | 27/128 [00:02<00:07, 13.70it/s] |
| eval model:: 23%|βββ | 29/128 [00:02<00:07, 13.68it/s] |
| eval model:: 24%|βββ | 31/128 [00:02<00:07, 13.64it/s] |
| eval model:: 26%|βββ | 33/128 [00:02<00:06, 13.60it/s] |
| eval model:: 27%|βββ | 35/128 [00:03<00:06, 13.60it/s] |
| eval model:: 29%|βββ | 37/128 [00:03<00:06, 13.63it/s] |
| eval model:: 30%|βββ | 39/128 [00:03<00:06, 13.66it/s] |
| eval model:: 32%|ββββ | 41/128 [00:03<00:06, 13.68it/s] |
| eval model:: 34%|ββββ | 43/128 [00:03<00:06, 13.70it/s] |
| eval model:: 35%|ββββ | 45/128 [00:03<00:06, 13.51it/s] |
| eval model:: 37%|ββββ | 47/128 [00:03<00:05, 13.52it/s] |
| eval model:: 38%|ββββ | 49/128 [00:04<00:05, 13.54it/s] |
| eval model:: 40%|ββββ | 51/128 [00:04<00:05, 13.60it/s] |
| eval model:: 41%|βββββ | 53/128 [00:04<00:05, 13.70it/s] |
| eval model:: 43%|βββββ | 55/128 [00:04<00:05, 13.74it/s] |
| eval model:: 45%|βββββ | 57/128 [00:04<00:05, 13.74it/s] |
| eval model:: 46%|βββββ | 59/128 [00:04<00:05, 13.19it/s] |
| eval model:: 48%|βββββ | 61/128 [00:05<00:05, 12.01it/s] |
| eval model:: 49%|βββββ | 63/128 [00:05<00:05, 11.54it/s] |
| eval model:: 51%|βββββ | 65/128 [00:05<00:05, 11.26it/s] |
| eval model:: 52%|ββββββ | 67/128 [00:05<00:05, 11.43it/s] |
| eval model:: 54%|ββββββ | 69/128 [00:05<00:04, 12.07it/s] |
| eval model:: 55%|ββββββ | 71/128 [00:05<00:04, 11.99it/s] |
| eval model:: 57%|ββββββ | 73/128 [00:06<00:04, 11.78it/s] |
| eval model:: 59%|ββββββ | 75/128 [00:06<00:04, 11.94it/s] |
| eval model:: 60%|ββββββ | 77/128 [00:06<00:04, 12.19it/s] |
| eval model:: 62%|βββββββ | 79/128 [00:06<00:03, 12.44it/s] |
| eval model:: 63%|βββββββ | 81/128 [00:06<00:03, 12.87it/s] |
| eval model:: 65%|βββββββ | 83/128 [00:06<00:03, 12.93it/s] |
| eval model:: 66%|βββββββ | 85/128 [00:06<00:03, 12.90it/s] |
| eval model:: 68%|βββββββ | 87/128 [00:07<00:03, 12.93it/s] |
| eval model:: 70%|βββββββ | 89/128 [00:07<00:02, 13.24it/s] |
| eval model:: 71%|βββββββ | 91/128 [00:07<00:02, 13.21it/s] |
| eval model:: 73%|ββββββββ | 93/128 [00:07<00:02, 13.37it/s] |
| eval model:: 74%|ββββββββ | 95/128 [00:07<00:02, 13.41it/s] |
| eval model:: 76%|ββββββββ | 97/128 [00:07<00:02, 13.59it/s] |
| eval model:: 77%|ββββββββ | 99/128 [00:07<00:02, 13.68it/s] |
| eval model:: 79%|ββββββββ | 101/128 [00:08<00:01, 13.68it/s] |
| eval model:: 80%|ββββββββ | 103/128 [00:08<00:01, 13.81it/s] |
| eval model:: 82%|βββββββββ | 105/128 [00:08<00:01, 13.79it/s] |
| eval model:: 84%|βββββββββ | 107/128 [00:08<00:01, 13.81it/s] |
| eval model:: 85%|βββββββββ | 109/128 [00:08<00:01, 13.77it/s] |
| eval model:: 87%|βββββββββ | 111/128 [00:08<00:01, 13.77it/s] |
| eval model:: 88%|βββββββββ | 113/128 [00:09<00:01, 13.80it/s] |
| eval model:: 90%|βββββββββ | 115/128 [00:09<00:00, 13.89it/s] |
| eval model:: 91%|ββββββββββ| 117/128 [00:09<00:00, 13.83it/s] |
| eval model:: 93%|ββββββββββ| 119/128 [00:09<00:00, 13.95it/s] |
| eval model:: 95%|ββββββββββ| 121/128 [00:09<00:00, 13.93it/s] |
| eval model:: 96%|ββββββββββ| 123/128 [00:09<00:00, 13.97it/s] |
| eval model:: 98%|ββββββββββ| 125/128 [00:09<00:00, 13.23it/s] |
| eval model:: 99%|ββββββββββ| 127/128 [00:10<00:00, 12.93it/s] |
| eval model:: 100%|ββββββββββ| 128/128 [00:10<00:00, 12.44it/s] |
| [2026/07/25 18:19:04] ppocr INFO: cur metric, acc: 0.8479003885549308, norm_edit_dis: 0.9879553178895327, fps: 445.954525271044 |
| [2026/07/25 18:19:05] ppocr INFO: save best model is to /workspace/bina02-ppocr/training/stage-007/best_accuracy |
| [2026/07/25 18:19:05] ppocr INFO: best metric, norm_edit_dis: 0.9879553178895327, is_float16: False, acc: 0.8479003885549308, fps: 445.954525271044, best_epoch: 1 |
| [2026/07/25 18:19:07] ppocr INFO: epoch: [1/1], global_step: 220, lr: 0.000004, CTCLoss: 54.075153, NRTRLoss: 0.000000, loss: 54.075153, avg_reader_cost: 0.00153 s, avg_batch_cost: 0.08233 s, avg_samples: 32.0, ips: 388.66963 samples/s, eta: 0:00:16, max_mem_reserved: 1045 MB, max_mem_allocated: 672 MB |
| [2026/07/25 18:19:10] ppocr INFO: epoch: [1/1], global_step: 240, lr: 0.000004, CTCLoss: 52.616846, NRTRLoss: 0.000000, loss: 52.616846, avg_reader_cost: 0.00494 s, avg_batch_cost: 0.08323 s, avg_samples: 32.0, ips: 384.48355 samples/s, eta: 0:00:14, max_mem_reserved: 1045 MB, max_mem_allocated: 672 MB |
| [2026/07/25 18:19:12] ppocr INFO: epoch: [1/1], global_step: 260, lr: 0.000003, CTCLoss: 57.685877, NRTRLoss: 0.000000, loss: 57.685877, avg_reader_cost: 0.02811 s, avg_batch_cost: 0.10503 s, avg_samples: 32.0, ips: 304.66617 samples/s, eta: 0:00:12, max_mem_reserved: 1045 MB, max_mem_allocated: 672 MB |
| [2026/07/25 18:19:15] ppocr INFO: epoch: [1/1], global_step: 280, lr: 0.000002, CTCLoss: 55.714092, NRTRLoss: 0.000000, loss: 55.714092, avg_reader_cost: 0.02759 s, avg_batch_cost: 0.10373 s, avg_samples: 32.0, ips: 308.50647 samples/s, eta: 0:00:10, max_mem_reserved: 1045 MB, max_mem_allocated: 672 MB |
| [2026/07/25 18:19:17] ppocr INFO: epoch: [1/1], global_step: 300, lr: 0.000002, CTCLoss: 49.928257, NRTRLoss: 0.000000, loss: 49.928257, avg_reader_cost: 0.01243 s, avg_batch_cost: 0.09403 s, avg_samples: 32.0, ips: 340.30618 samples/s, eta: 0:00:08, max_mem_reserved: 1045 MB, max_mem_allocated: 672 MB |
|
|
| eval model:: 0%| | 0/128 [00:00<?, ?it/s] |
| eval model:: 1%| | 1/128 [00:00<00:50, 2.51it/s] |
| eval model:: 2%|β | 3/128 [00:00<00:19, 6.32it/s] |
| eval model:: 4%|β | 5/128 [00:00<00:14, 8.65it/s] |
| eval model:: 5%|β | 7/128 [00:00<00:11, 10.26it/s] |
| eval model:: 7%|β | 9/128 [00:00<00:10, 11.35it/s] |
| eval model:: 9%|β | 11/128 [00:01<00:09, 12.05it/s] |
| eval model:: 10%|β | 13/128 [00:01<00:09, 12.56it/s] |
| eval model:: 12%|ββ | 15/128 [00:01<00:08, 12.92it/s] |
| eval model:: 13%|ββ | 17/128 [00:01<00:08, 13.15it/s] |
| eval model:: 15%|ββ | 19/128 [00:01<00:08, 13.30it/s] |
| eval model:: 16%|ββ | 21/128 [00:01<00:07, 13.43it/s] |
| eval model:: 18%|ββ | 23/128 [00:02<00:07, 13.51it/s] |
| eval model:: 20%|ββ | 25/128 [00:02<00:07, 13.56it/s] |
| eval model:: 21%|ββ | 27/128 [00:02<00:07, 13.57it/s] |
| eval model:: 23%|βββ | 29/128 [00:02<00:07, 13.61it/s] |
| eval model:: 24%|βββ | 31/128 [00:02<00:07, 13.61it/s] |
| eval model:: 26%|βββ | 33/128 [00:02<00:06, 13.61it/s] |
| eval model:: 27%|βββ | 35/128 [00:02<00:06, 13.31it/s] |
| eval model:: 29%|βββ | 37/128 [00:03<00:07, 12.77it/s] |
| eval model:: 30%|βββ | 39/128 [00:03<00:07, 12.26it/s] |
| eval model:: 32%|ββββ | 41/128 [00:03<00:07, 11.87it/s] |
| eval model:: 34%|ββββ | 43/128 [00:03<00:07, 11.49it/s] |
| eval model:: 35%|ββββ | 45/128 [00:03<00:07, 11.56it/s] |
| eval model:: 37%|ββββ | 47/128 [00:03<00:06, 12.20it/s] |
| eval model:: 38%|ββββ | 49/128 [00:04<00:06, 12.16it/s] |
| eval model:: 40%|ββββ | 51/128 [00:04<00:06, 12.48it/s] |
| eval model:: 41%|βββββ | 53/128 [00:04<00:06, 12.47it/s] |
| eval model:: 43%|βββββ | 55/128 [00:04<00:05, 12.67it/s] |
| eval model:: 45%|βββββ | 57/128 [00:04<00:05, 13.07it/s] |
| eval model:: 46%|βββββ | 59/128 [00:04<00:05, 12.85it/s] |
| eval model:: 48%|βββββ | 61/128 [00:05<00:05, 12.90it/s] |
| eval model:: 49%|βββββ | 63/128 [00:05<00:05, 12.98it/s] |
| eval model:: 51%|βββββ | 65/128 [00:05<00:04, 13.08it/s] |
| eval model:: 52%|ββββββ | 67/128 [00:05<00:04, 13.42it/s] |
| eval model:: 54%|ββββββ | 69/128 [00:05<00:04, 13.40it/s] |
| eval model:: 55%|ββββββ | 71/128 [00:05<00:04, 13.57it/s] |
| eval model:: 57%|ββββββ | 73/128 [00:05<00:03, 13.76it/s] |
| eval model:: 59%|ββββββ | 75/128 [00:06<00:03, 13.84it/s] |
| eval model:: 60%|ββββββ | 77/128 [00:06<00:03, 13.90it/s] |
| eval model:: 62%|βββββββ | 79/128 [00:06<00:03, 13.85it/s] |
| eval model:: 63%|βββββββ | 81/128 [00:06<00:03, 13.95it/s] |
| eval model:: 65%|βββββββ | 83/128 [00:06<00:03, 13.94it/s] |
| eval model:: 66%|βββββββ | 85/128 [00:06<00:03, 13.95it/s] |
| eval model:: 68%|βββββββ | 87/128 [00:06<00:02, 13.97it/s] |
| eval model:: 70%|βββββββ | 89/128 [00:07<00:02, 14.00it/s] |
| eval model:: 71%|βββββββ | 91/128 [00:07<00:02, 13.97it/s] |
| eval model:: 73%|ββββββββ | 93/128 [00:07<00:02, 14.02it/s] |
| eval model:: 74%|ββββββββ | 95/128 [00:07<00:02, 14.06it/s] |
| eval model:: 76%|ββββββββ | 97/128 [00:07<00:02, 14.02it/s] |
| eval model:: 77%|ββββββββ | 99/128 [00:07<00:02, 14.01it/s] |
| eval model:: 79%|ββββββββ | 101/128 [00:07<00:01, 13.75it/s] |
| eval model:: 80%|ββββββββ | 103/128 [00:08<00:01, 13.88it/s] |
| eval model:: 82%|βββββββββ | 105/128 [00:08<00:01, 13.29it/s] |
| eval model:: 84%|βββββββββ | 107/128 [00:08<00:01, 12.75it/s] |
| eval model:: 85%|βββββββββ | 109/128 [00:08<00:01, 12.44it/s] |
| eval model:: 87%|βββββββββ | 111/128 [00:08<00:01, 11.97it/s] |
| eval model:: 88%|βββββββββ | 113/128 [00:08<00:01, 12.04it/s] |
| eval model:: 90%|βββββββββ | 115/128 [00:09<00:01, 12.56it/s] |
| eval model:: 91%|ββββββββββ| 117/128 [00:09<00:00, 12.38it/s] |
| eval model:: 93%|ββββββββββ| 119/128 [00:09<00:00, 12.27it/s] |
| eval model:: 95%|ββββββββββ| 121/128 [00:09<00:00, 12.58it/s] |
| eval model:: 96%|ββββββββββ| 123/128 [00:09<00:00, 12.77it/s] |
| eval model:: 98%|ββββββββββ| 125/128 [00:09<00:00, 13.18it/s] |
| eval model:: 99%|ββββββββββ| 127/128 [00:09<00:00, 13.24it/s] |
| eval model:: 100%|ββββββββββ| 128/128 [00:10<00:00, 12.56it/s] |
| [2026/07/25 18:19:27] ppocr INFO: cur metric, acc: 0.8474121073061228, norm_edit_dis: 0.9879260147210178, fps: 447.33463429373097 |
| [2026/07/25 18:19:27] ppocr INFO: best metric, norm_edit_dis: 0.9879553178895327, is_float16: False, acc: 0.8479003885549308, fps: 445.954525271044, best_epoch: 1 |
| LAUNCH INFO 2026-07-25 18:19:28,198 Terminating with signal 2 |
| LAUNCH INFO 2026-07-25 18:19:28,258 Force quit in 10 seconds... |
| LAUNCH INFO 2026-07-25 18:19:38,225 Force quit in 10 seconds... |
|
|