| { |
| "code_git_commit": "74754fb604f870ae385ad41ad3686a41128e358a", |
| "code_git_dirty": "unknown", |
| "condition": "cpt_pan_formosan_to_language", |
| "cuda_visible_devices": "0", |
| "dataset_version": "dataset_v1", |
| "dev_corpus": "", |
| "dev_hours": 8.249778, |
| "dev_language": "amis", |
| "dev_rows": 3601, |
| "dev_scope": "language_pooled", |
| "device": "cuda", |
| "effective_eval_every_steps": 21573, |
| "effective_max_steps": 107862, |
| "eval_batch_size": 8, |
| "eval_corpus": "", |
| "eval_every_steps": 21573, |
| "eval_language": "amis", |
| "eval_scope": "language_pooled", |
| "generated_at": "2026-06-30T00:39:07+00:00", |
| "hostname": "g010", |
| "max_steps": 1000, |
| "model_family": "xlsr53", |
| "model_id": "/scratch/scheppat/projects/tacl_formosan_asr/runs_xlsr_cpt_downstream_v1/xlsr53_cpt_pan_formosan_direct_train-all_eval-all-all-corpora_dataset_v1_split_v2_formosan_safe_v1_seed13/best_model", |
| "model_revision": "", |
| "normalization_version": "formosan_safe_v1", |
| "package_freeze": [ |
| "absl-py==2.4.0", |
| "accelerate==1.1.1", |
| "aiohappyeyeballs==2.6.2", |
| "aiohttp==3.14.1", |
| "aiosignal==1.4.0", |
| "async-timeout==5.0.1", |
| "attrs==26.1.0", |
| "audioread==3.1.0", |
| "certifi==2026.6.17", |
| "cffi==2.0.0", |
| "charset-normalizer==3.4.7", |
| "click==8.4.1", |
| "datasets==3.1.0", |
| "decorator==5.3.1", |
| "dill==0.3.8", |
| "evaluate==0.4.3", |
| "filelock==3.29.0", |
| "frozenlist==1.8.0", |
| "fsspec==2024.9.0", |
| "grpcio==1.81.1", |
| "hf-xet==1.5.1", |
| "huggingface_hub==0.36.2", |
| "idna==3.18", |
| "Jinja2==3.1.6", |
| "jiwer==3.0.5", |
| "joblib==1.5.3", |
| "lazy-loader==0.5", |
| "librosa==0.10.2.post1", |
| "llvmlite==0.47.0", |
| "Markdown==3.10.2", |
| "MarkupSafe==3.0.3", |
| "mpmath==1.3.0", |
| "msgpack==1.2.1", |
| "multidict==6.7.1", |
| "multiprocess==0.70.16", |
| "networkx==3.4.2", |
| "numba==0.65.1", |
| "numpy==2.2.6", |
| "nvidia-cublas-cu12==12.4.5.8", |
| "nvidia-cuda-cupti-cu12==12.4.127", |
| "nvidia-cuda-nvrtc-cu12==12.4.127", |
| "nvidia-cuda-runtime-cu12==12.4.127", |
| "nvidia-cudnn-cu12==9.1.0.70", |
| "nvidia-cufft-cu12==11.2.1.3", |
| "nvidia-curand-cu12==10.3.5.147", |
| "nvidia-cusolver-cu12==11.6.1.9", |
| "nvidia-cusparse-cu12==12.3.1.170", |
| "nvidia-nccl-cu12==2.21.5", |
| "nvidia-nvjitlink-cu12==12.4.127", |
| "nvidia-nvtx-cu12==12.4.127", |
| "packaging @ file:///home/conda/feedstock_root/build_artifacts/bld/rattler-build_packaging_1777103621/work", |
| "pandas==2.3.3", |
| "platformdirs==4.10.0", |
| "pooch==1.9.0", |
| "propcache==0.5.2", |
| "protobuf==7.35.1", |
| "psutil==7.2.2", |
| "pyarrow==24.0.0", |
| "pycparser==3.0", |
| "python-dateutil==2.9.0.post0", |
| "pytz==2026.2", |
| "PyYAML==6.0.3", |
| "RapidFuzz==3.14.5", |
| "regex==2026.5.9", |
| "requests==2.34.2", |
| "safetensors==0.8.0", |
| "scikit-learn==1.7.2", |
| "scipy==1.15.3", |
| "sentencepiece==0.2.0", |
| "six==1.17.0", |
| "soundfile==0.12.1", |
| "soxr==1.1.0", |
| "sympy==1.13.1", |
| "tensorboard==2.18.0", |
| "tensorboard-data-server==0.7.2", |
| "threadpoolctl==3.6.0", |
| "tokenizers==0.20.3", |
| "torch==2.5.1+cu124", |
| "torchaudio==2.5.1+cu124", |
| "tqdm==4.68.3", |
| "transformers==4.46.3", |
| "triton==3.1.0", |
| "typing_extensions==4.15.0", |
| "tzdata==2026.2", |
| "urllib3==2.7.0", |
| "Werkzeug==3.1.8", |
| "xxhash==3.7.0", |
| "yarl==1.24.2" |
| ], |
| "package_freeze_count": 88, |
| "pretraining_checkpoint_path": "/scratch/scheppat/projects/tacl_formosan_asr/runs_cpt/xlsr_cpt_pan_train_only_v1/final_model", |
| "pretraining_condition": "cpt_train_only", |
| "pretraining_manifest": "/projects/prudlab/tacl_formosan_asr/experiments/cpt_manifests/dataset_v1_split_v2_train_only/pan_formosan/train.tsv", |
| "pretraining_model_revision": "c3f9d884181a224a6ac87bf8885c84d1cff3384f", |
| "pretraining_run_id": "xlsr_cpt_pan_train_only_v1", |
| "pretraining_source_policy": "train_only_no_dev_no_test", |
| "python_argv": [ |
| "/projects/prudlab/tacl_formosan_asr/code/tacl_pipeline/src/tacl_formosan_asr/train_ctc_asr.py", |
| "--source-root", |
| "/projects/prudlab/hunter_formosan_audio", |
| "--run-dir", |
| "/projects/prudlab/tacl_formosan_asr/experiments/manifests/gate6_xlsr_cpt_downstream_matrix/xlsr53_cpt_pan_formosan_to_language_train-amis_eval-amis-all-corpora_dataset_v1_split_v2_formosan_safe_v1_seed13", |
| "--vocab-json", |
| "/projects/prudlab/tacl_formosan_asr/vocabularies/ctc_dataset_v1_split_v2_formosan_safe_v1/pan_formosan/vocab.json", |
| "--out-dir", |
| "/scratch/scheppat/projects/tacl_formosan_asr/runs_xlsr_cpt_downstream_v1/xlsr53_cpt_pan_formosan_to_language_train-amis_eval-amis-all-corpora_dataset_v1_split_v2_formosan_safe_v1_seed13", |
| "--run-id", |
| "xlsr53_cpt_pan_formosan_to_language_train-amis_eval-amis-all-corpora_dataset_v1_split_v2_formosan_safe_v1_seed13", |
| "--model-id", |
| "/scratch/scheppat/projects/tacl_formosan_asr/runs_xlsr_cpt_downstream_v1/xlsr53_cpt_pan_formosan_direct_train-all_eval-all-all-corpora_dataset_v1_split_v2_formosan_safe_v1_seed13/best_model", |
| "--model-revision", |
| "", |
| "--seed", |
| "13", |
| "--max-steps", |
| "1000", |
| "--train-epochs", |
| "30", |
| "--train-batch-size", |
| "8", |
| "--eval-batch-size", |
| "8", |
| "--learning-rate", |
| "1e-4", |
| "--eval-every-steps", |
| "0", |
| "--max-eval-batches", |
| "0", |
| "--max-train-rows", |
| "0", |
| "--max-dev-rows", |
| "0", |
| "--max-test-rows", |
| "0", |
| "--save-best-model" |
| ], |
| "python_executable": "/scratch/scheppat/projects/tacl_formosan_asr/conda/tacl_asr_py310/bin/python", |
| "python_version": "3.10.20 | packaged by conda-forge | (main, Jun 11 2026, 03:31:56) [GCC 14.3.0]", |
| "requested_eval_every_steps": 0, |
| "run_dir": "/projects/prudlab/tacl_formosan_asr/experiments/manifests/gate6_xlsr_cpt_downstream_matrix/xlsr53_cpt_pan_formosan_to_language_train-amis_eval-amis-all-corpora_dataset_v1_split_v2_formosan_safe_v1_seed13", |
| "run_id": "xlsr53_cpt_pan_formosan_to_language_train-amis_eval-amis-all-corpora_dataset_v1_split_v2_formosan_safe_v1_seed13", |
| "seed": 13, |
| "slurm_job_id": "2646836", |
| "slurm_job_name": "tacl_ctc_registry_array", |
| "split_version": "split_v2", |
| "status": "planned", |
| "tacl_code_version_file": "74754fb604f870ae385ad41ad3686a41128e358a", |
| "test_hours": 8.249753, |
| "test_rows": 3601, |
| "train_batch_size": 8, |
| "train_corpus": "", |
| "train_corpus_counts": { |
| "Bible": 8236, |
| "ILRDF": 4539, |
| "NTU": 516, |
| "ePark1": 3500, |
| "ePark2": 2193, |
| "ePark3": 9779 |
| }, |
| "train_epochs": 30.0, |
| "train_hours": 66.029626, |
| "train_language": "amis", |
| "train_rows": 28763, |
| "train_scope": "language_pooled", |
| "vocab_json": "/projects/prudlab/tacl_formosan_asr/vocabularies/ctc_dataset_v1_split_v2_formosan_safe_v1/pan_formosan/vocab.json", |
| "vocab_scope": "pan_formosan" |
| } |
|
|
