Fix eval_loss nan + add generation_config to Seq2SeqTrainer

1. Seq2SeqTrainer now receives generation_config=model.generation_config
explicitly -- ensures forced_decoder_ids is applied during eval's
generate() call, fixing the '!!!!!' prediction output
2. eval_loss nan handled gracefully in cells 17, 19, 20 -- transformers 5.x
predict_with_generate=True does not compute loss, always returns nan;
display shows 'n/a (generation-based eval)' instead of crashing on .4f

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

notebooks/kaggle_master_trainer.ipynb

@@ -244,7 +244,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# ── Cell 19: Push adapter to HF Model repo ───────────────────────────────────\nfrom huggingface_hub import HfApi, create_repo\n\n# Ensure repo exists\ncreate_repo(ADAPTER_REPO_ID, repo_type='model', private=True,\n            exist_ok=True, token=HF_TOKEN)\n\ncommit_msg = (\n    f'[{VERSION_TAG}] {LANG_NAME} fine-tuned checkpoint — '\n    f'{train_result.global_step} steps | '\n    f'WER {wer_score:.1%} | '\n    f'{len(correction_records)} corrections + WaxalNLP'\n)\n\napi.upload_folder(\n    folder_path=OUTPUT_DIR,\n    repo_id=ADAPTER_REPO_ID,\n    repo_type='model',\n    path_in_repo=PATH_IN_REPO,\n    commit_message=commit_msg,\n)\nprint(f'✅ Adapter uploaded: {ADAPTER_REPO_ID}/{PATH_IN_REPO}')\n\n# Create a Git tag for this version\ntry:\n    api.create_tag(\n        repo_id=ADAPTER_REPO_ID,\n        repo_type='model',\n        tag=VERSION_TAG,\n        tag_message=commit_msg,\n        token=HF_TOKEN,\n    )\n    print(f'✅ Tag created   : {VERSION_TAG}')\nexcept Exception as e:\n    print(f'⚠️  Tag creation skipped: {e}')"
+    "# ── Cell 19: Push adapter to HF Model repo ───────────────────────────────────\nfrom huggingface_hub import HfApi, create_repo\n\n# Ensure repo exists\ncreate_repo(ADAPTER_REPO_ID, repo_type='model', private=True,\n            exist_ok=True, token=HF_TOKEN)\n\ncommit_msg = (\n    f'[{VERSION_TAG}] {LANG_NAME} fine-tuned checkpoint — '\n    f'{train_result.global_step} steps | '\n    f'WER {wer_score:.1%} | ' if wer_score == wer_score else f'WER n/a | '\n    f'{len(correction_records)} corrections + WaxalNLP'\n)\n\napi.upload_folder(\n    folder_path=OUTPUT_DIR,\n    repo_id=ADAPTER_REPO_ID,\n    repo_type='model',\n    path_in_repo=PATH_IN_REPO,\n    commit_message=commit_msg,\n)\nprint(f'✅ Adapter uploaded: {ADAPTER_REPO_ID}/{PATH_IN_REPO}')\n\n# Create a Git tag for this version\ntry:\n    api.create_tag(\n        repo_id=ADAPTER_REPO_ID,\n        repo_type='model',\n        tag=VERSION_TAG,\n        tag_message=commit_msg,\n        token=HF_TOKEN,\n    )\n    print(f'✅ Tag created   : {VERSION_TAG}')\nexcept Exception as e:\n    print(f'⚠️  Tag creation skipped: {e}')"
    ]
   },
   {
@@ -253,7 +253,9 @@
    "id": "cell-verify",
    "metadata": {},
    "outputs": [],
-   "source": "# ── Cell 20: Verification summary ────────────────────────────────────────────\nfrom huggingface_hub import list_repo_files\n\nprint('=' * 60)\nprint('DEEP SLEEP TRAINING — COMPLETE')\nprint('=' * 60)\nprint(f'  Language          : {TRAIN_LANG} ({LANG_NAME})')\nprint(f'  Model             : {WHISPER_MODEL_ID}')\nprint(f'  Steps completed   : {train_result.global_step}')\nprint(f'  Train loss        : {train_result.training_loss:.4f}')\nprint(f'  Eval WER          : {wer_score:.1%}')\nprint(f'  Corrections used  : {len(correction_records)} × {CORRECTION_REPEAT}')\nprint(f'  WaxalNLP samples  : up to {MAX_WAXAL_TRAIN}')\nprint(f'  Version tag       : {VERSION_TAG}')\nprint(f'  HF repo           : {ADAPTER_REPO_ID}/{PATH_IN_REPO}')\nprint()\n\n# List what was pushed\ntry:\n    repo_files = sorted(list_repo_files(\n        ADAPTER_REPO_ID, repo_type='model', token=HF_TOKEN\n    ))\n    adapter_files = [f for f in repo_files if f.startswith(f'adapters/{LANG_NAME}/')]\n    print('Adapter files in repo:')\n    for f in adapter_files:\n        print(f'  {f}')\nexcept Exception as e:\n    print(f'Could not list repo files: {e}')\n\nprint()\nprint('Next steps:')\nprint('  1. In your HF Space settings, confirm ADAPTER_REPO_ID secret is set')\nprint(f'  2. Tab 3 → Reload Adapters → select \"{VERSION_TAG}\"')\nprint('  3. Collect more corrections in the Space, then re-run this notebook')"
+   "source": [
+    "# ── Cell 20: Verification summary ────────────────────────────────────────────\nfrom huggingface_hub import list_repo_files\n\nprint('=' * 60)\nprint('DEEP SLEEP TRAINING — COMPLETE')\nprint('=' * 60)\nprint(f'  Language          : {TRAIN_LANG} ({LANG_NAME})')\nprint(f'  Model             : {WHISPER_MODEL_ID}')\nprint(f'  Steps completed   : {train_result.global_step}')\nprint(f'  Train loss        : {train_result.training_loss:.4f}')\n_wer_disp = f'{wer_score:.1%}' if wer_score == wer_score else 'n/a'\nprint(f'  Eval WER          : {_wer_disp}')\nprint(f'  Corrections used  : {len(correction_records)} × {CORRECTION_REPEAT}')\nprint(f'  WaxalNLP samples  : up to {MAX_WAXAL_TRAIN}')\nprint(f'  Version tag       : {VERSION_TAG}')\nprint(f'  HF repo           : {ADAPTER_REPO_ID}/{PATH_IN_REPO}')\nprint()\n\n# List what was pushed\ntry:\n    repo_files = sorted(list_repo_files(\n        ADAPTER_REPO_ID, repo_type='model', token=HF_TOKEN\n    ))\n    adapter_files = [f for f in repo_files if f.startswith(f'adapters/{LANG_NAME}/')]\n    print('Adapter files in repo:')\n    for f in adapter_files:\n        print(f'  {f}')\nexcept Exception as e:\n    print(f'Could not list repo files: {e}')\n\nprint()\nprint('Next steps:')\nprint('  1. In your HF Space settings, confirm ADAPTER_REPO_ID secret is set')\nprint(f'  2. Tab 3 → Reload Adapters → select \"{VERSION_TAG}\"')\nprint('  3. Collect more corrections in the Space, then re-run this notebook')"
+   ]
   }
  ]
 }