2026-07-23:22:03:14 WARNING  [config.evaluate_config:287] --limit SHOULD ONLY BE USED FOR TESTING. REAL METRICS SHOULD NOT BE COMPUTED USING LIMIT.
2026-07-23:22:03:21 INFO     [_cli.run:388] Selected Tasks: ['mmlu_pro', 'gpqa_diamond_zeroshot', 'minerva_math500', 'ifeval', 'gsm8k_cot_zeroshot']
2026-07-23:22:03:23 INFO     [evaluator:214] Setting random seed to 0 | Setting numpy seed to 1234 | Setting torch manual seed to 1234 | Setting fewshot manual seed to 1234
2026-07-23:22:03:23 WARNING  [evaluator:226] generation_kwargs: {'max_gen_toks': 1280} specified through cli, these settings will update set parameters in yaml tasks. Ensure 'do_sample=True' for non-greedy decoding!
2026-07-23:22:03:23 INFO     [evaluator:239] Initializing local-chat-completions model, with arguments: {'model': 'student', 'base_url': 'http://127.0.0.1:8399/v1/chat/completions', 'num_concurrent': 32, 'tokenized_requests': False, 'max_retries': 3}
2026-07-23:22:03:23 INFO     [models.api_models:179] Using max length 2048 - 1
2026-07-23:22:03:23 INFO     [models.api_models:200] Using tokenizer None
2026-07-23:22:03:38 INFO     [evaluator_utils:446] Selected tasks:
2026-07-23:22:03:38 INFO     [evaluator_utils:462] Group: mmlu_pro
2026-07-23:22:03:38 INFO     [evaluator_utils:470]   Task: mmlu_pro_biology (mmlu_pro/mmlu_pro_biology.yaml)
2026-07-23:22:03:38 INFO     [evaluator_utils:470]   Task: mmlu_pro_business (mmlu_pro/mmlu_pro_business.yaml)
2026-07-23:22:03:38 INFO     [evaluator_utils:470]   Task: mmlu_pro_chemistry (mmlu_pro/mmlu_pro_chemistry.yaml)
2026-07-23:22:03:38 INFO     [evaluator_utils:470]   Task: mmlu_pro_computer_science (mmlu_pro/mmlu_pro_computer_science.yaml)
2026-07-23:22:03:38 INFO     [evaluator_utils:470]   Task: mmlu_pro_economics (mmlu_pro/mmlu_pro_economics.yaml)
2026-07-23:22:03:38 INFO     [evaluator_utils:470]   Task: mmlu_pro_engineering (mmlu_pro/mmlu_pro_engineering.yaml)
2026-07-23:22:03:38 INFO     [evaluator_utils:470]   Task: mmlu_pro_health (mmlu_pro/mmlu_pro_health.yaml)
2026-07-23:22:03:38 INFO     [evaluator_utils:470]   Task: mmlu_pro_history (mmlu_pro/mmlu_pro_history.yaml)
2026-07-23:22:03:38 INFO     [evaluator_utils:470]   Task: mmlu_pro_law (mmlu_pro/mmlu_pro_law.yaml)
2026-07-23:22:03:38 INFO     [evaluator_utils:470]   Task: mmlu_pro_math (mmlu_pro/mmlu_pro_math.yaml)
2026-07-23:22:03:38 INFO     [evaluator_utils:470]   Task: mmlu_pro_other (mmlu_pro/mmlu_pro_other.yaml)
2026-07-23:22:03:38 INFO     [evaluator_utils:470]   Task: mmlu_pro_philosophy (mmlu_pro/mmlu_pro_philosophy.yaml)
2026-07-23:22:03:38 INFO     [evaluator_utils:470]   Task: mmlu_pro_physics (mmlu_pro/mmlu_pro_physics.yaml)
2026-07-23:22:03:38 INFO     [evaluator_utils:470]   Task: mmlu_pro_psychology (mmlu_pro/mmlu_pro_psychology.yaml)
2026-07-23:22:03:38 INFO     [evaluator_utils:480] Task: gpqa_diamond_zeroshot (gpqa/zeroshot/gpqa_diamond_zeroshot.yaml)
2026-07-23:22:03:38 INFO     [evaluator_utils:480] Task: gsm8k_cot_zeroshot (gsm8k/gsm8k-cot-zeroshot.yaml)
2026-07-23:22:03:38 INFO     [evaluator_utils:480] Task: ifeval (ifeval/ifeval.yaml)
2026-07-23:22:03:38 INFO     [evaluator_utils:480] Task: minerva_math500 (minerva_math/minerva_math500.yaml)
2026-07-23:22:03:38 INFO     [evaluator:314] mmlu_pro_biology: Using gen_kwargs: {'until': ['Question:'], 'max_gen_toks': 1280, 'do_sample': False, 'temperature': 0.0}
2026-07-23:22:03:38 INFO     [evaluator:314] mmlu_pro_business: Using gen_kwargs: {'until': ['Question:'], 'max_gen_toks': 1280, 'do_sample': False, 'temperature': 0.0}
2026-07-23:22:03:38 INFO     [evaluator:314] mmlu_pro_chemistry: Using gen_kwargs: {'until': ['Question:'], 'max_gen_toks': 1280, 'do_sample': False, 'temperature': 0.0}
2026-07-23:22:03:38 INFO     [evaluator:314] mmlu_pro_computer_science: Using gen_kwargs: {'until': ['Question:'], 'max_gen_toks': 1280, 'do_sample': False, 'temperature': 0.0}
2026-07-23:22:03:38 INFO     [evaluator:314] mmlu_pro_economics: Using gen_kwargs: {'until': ['Question:'], 'max_gen_toks': 1280, 'do_sample': False, 'temperature': 0.0}
2026-07-23:22:03:38 INFO     [evaluator:314] mmlu_pro_engineering: Using gen_kwargs: {'until': ['Question:'], 'max_gen_toks': 1280, 'do_sample': False, 'temperature': 0.0}
2026-07-23:22:03:38 INFO     [evaluator:314] mmlu_pro_health: Using gen_kwargs: {'until': ['Question:'], 'max_gen_toks': 1280, 'do_sample': False, 'temperature': 0.0}
2026-07-23:22:03:38 INFO     [evaluator:314] mmlu_pro_history: Using gen_kwargs: {'until': ['Question:'], 'max_gen_toks': 1280, 'do_sample': False, 'temperature': 0.0}
2026-07-23:22:03:38 INFO     [evaluator:314] mmlu_pro_law: Using gen_kwargs: {'until': ['Question:'], 'max_gen_toks': 1280, 'do_sample': False, 'temperature': 0.0}
2026-07-23:22:03:38 INFO     [evaluator:314] mmlu_pro_math: Using gen_kwargs: {'until': ['Question:'], 'max_gen_toks': 1280, 'do_sample': False, 'temperature': 0.0}
2026-07-23:22:03:38 INFO     [evaluator:314] mmlu_pro_other: Using gen_kwargs: {'until': ['Question:'], 'max_gen_toks': 1280, 'do_sample': False, 'temperature': 0.0}
2026-07-23:22:03:38 INFO     [evaluator:314] mmlu_pro_philosophy: Using gen_kwargs: {'until': ['Question:'], 'max_gen_toks': 1280, 'do_sample': False, 'temperature': 0.0}
2026-07-23:22:03:38 INFO     [evaluator:314] mmlu_pro_physics: Using gen_kwargs: {'until': ['Question:'], 'max_gen_toks': 1280, 'do_sample': False, 'temperature': 0.0}
2026-07-23:22:03:38 INFO     [evaluator:314] mmlu_pro_psychology: Using gen_kwargs: {'until': ['Question:'], 'max_gen_toks': 1280, 'do_sample': False, 'temperature': 0.0}
2026-07-23:22:03:38 INFO     [evaluator:314] minerva_math500: Using gen_kwargs: {'until': ['Problem:'], 'do_sample': False, 'temperature': 0.0, 'max_gen_toks': 1280}
2026-07-23:22:03:38 INFO     [evaluator:314] ifeval: Using gen_kwargs: {'until': [], 'do_sample': False, 'temperature': 0.0, 'max_gen_toks': 1280}
2026-07-23:22:03:38 INFO     [evaluator:314] gsm8k_cot_zeroshot: Using gen_kwargs: {'until': ['Q:', '</s>', '<|im_end|>'], 'do_sample': False, 'max_gen_toks': 1280}
2026-07-23:22:03:38 INFO     [api.task:312] Building contexts for mmlu_pro_biology on rank 0...

  0%|          | 0/10 [00:00<?, ?it/s]
100%|██████████| 10/10 [00:00<00:00, 2818.56it/s]
2026-07-23:22:03:38 INFO     [api.task:312] Building contexts for mmlu_pro_business on rank 0...

  0%|          | 0/10 [00:00<?, ?it/s]
100%|██████████| 10/10 [00:00<00:00, 3266.34it/s]
2026-07-23:22:03:38 INFO     [api.task:312] Building contexts for mmlu_pro_chemistry on rank 0...

  0%|          | 0/10 [00:00<?, ?it/s]
100%|██████████| 10/10 [00:00<00:00, 3143.92it/s]
2026-07-23:22:03:38 INFO     [api.task:312] Building contexts for mmlu_pro_computer_science on rank 0...

  0%|          | 0/10 [00:00<?, ?it/s]
100%|██████████| 10/10 [00:00<00:00, 3098.40it/s]
2026-07-23:22:03:38 INFO     [api.task:312] Building contexts for mmlu_pro_economics on rank 0...

  0%|          | 0/10 [00:00<?, ?it/s]
100%|██████████| 10/10 [00:00<00:00, 3152.19it/s]
2026-07-23:22:03:38 INFO     [api.task:312] Building contexts for mmlu_pro_engineering on rank 0...

  0%|          | 0/10 [00:00<?, ?it/s]
100%|██████████| 10/10 [00:00<00:00, 3118.44it/s]
2026-07-23:22:03:38 INFO     [api.task:312] Building contexts for mmlu_pro_health on rank 0...

  0%|          | 0/10 [00:00<?, ?it/s]
100%|██████████| 10/10 [00:00<00:00, 3194.93it/s]
2026-07-23:22:03:38 INFO     [api.task:312] Building contexts for mmlu_pro_history on rank 0...

  0%|          | 0/10 [00:00<?, ?it/s]
100%|██████████| 10/10 [00:00<00:00, 2920.82it/s]
2026-07-23:22:03:38 INFO     [api.task:312] Building contexts for mmlu_pro_law on rank 0...

  0%|          | 0/10 [00:00<?, ?it/s]
100%|██████████| 10/10 [00:00<00:00, 3091.55it/s]
2026-07-23:22:03:38 INFO     [api.task:312] Building contexts for mmlu_pro_math on rank 0...

  0%|          | 0/10 [00:00<?, ?it/s]
100%|██████████| 10/10 [00:00<00:00, 3118.67it/s]
2026-07-23:22:03:38 INFO     [api.task:312] Building contexts for mmlu_pro_other on rank 0...

  0%|          | 0/10 [00:00<?, ?it/s]
100%|██████████| 10/10 [00:00<00:00, 3178.47it/s]
2026-07-23:22:03:38 INFO     [api.task:312] Building contexts for mmlu_pro_philosophy on rank 0...

  0%|          | 0/10 [00:00<?, ?it/s]
100%|██████████| 10/10 [00:00<00:00, 3224.16it/s]
2026-07-23:22:03:38 INFO     [api.task:312] Building contexts for mmlu_pro_physics on rank 0...

  0%|          | 0/10 [00:00<?, ?it/s]
100%|██████████| 10/10 [00:00<00:00, 3251.65it/s]
2026-07-23:22:03:38 INFO     [api.task:312] Building contexts for mmlu_pro_psychology on rank 0...

  0%|          | 0/10 [00:00<?, ?it/s]
100%|██████████| 10/10 [00:00<00:00, 3155.98it/s]
2026-07-23:22:03:38 INFO     [api.task:312] Building contexts for gpqa_diamond_zeroshot on rank 0...

  0%|          | 0/10 [00:00<?, ?it/s]
100%|██████████| 10/10 [00:00<00:00, 1607.07it/s]
2026-07-23:22:03:38 INFO     [api.task:312] Building contexts for minerva_math500 on rank 0...

  0%|          | 0/10 [00:00<?, ?it/s]
100%|██████████| 10/10 [00:00<00:00, 397.11it/s]
2026-07-23:22:03:39 INFO     [api.task:312] Building contexts for ifeval on rank 0...

  0%|          | 0/10 [00:00<?, ?it/s]
100%|██████████| 10/10 [00:00<00:00, 54330.36it/s]
2026-07-23:22:03:39 INFO     [api.task:312] Building contexts for gsm8k_cot_zeroshot on rank 0...

  0%|          | 0/10 [00:00<?, ?it/s]
100%|██████████| 10/10 [00:00<00:00, 1762.24it/s]
2026-07-23:22:03:39 INFO     [evaluator:585] Running generate_until requests
2026-07-23:22:03:39 INFO     [models.api_models:747] Tokenized requests are disabled. Context + generation length is not checked.

Requesting API:   0%|          | 0/140 [00:00<?, ?it/s]
Requesting API:   1%|          | 1/140 [00:04<09:19,  4.03s/it]
Requesting API:   3%|▎         | 4/140 [00:04<02:04,  1.09it/s]
Requesting API:   4%|▎         | 5/140 [00:04<01:40,  1.35it/s]
Requesting API:   4%|▍         | 6/140 [00:05<01:32,  1.44it/s]
Requesting API:   5%|▌         | 7/140 [00:05<01:16,  1.74it/s]
Requesting API:   6%|▋         | 9/140 [00:06<00:49,  2.64it/s]
Requesting API:   7%|▋         | 10/140 [00:06<00:55,  2.35it/s]
Requesting API:   9%|▊         | 12/140 [00:06<00:39,  3.23it/s]
Requesting API:  10%|█         | 14/140 [00:07<00:31,  4.04it/s]
Requesting API:  11%|█         | 15/140 [00:07<00:31,  3.91it/s]
Requesting API:  12%|█▏        | 17/140 [00:07<00:26,  4.70it/s]
Requesting API:  13%|█▎        | 18/140 [00:08<00:35,  3.48it/s]
Requesting API:  14%|█▎        | 19/140 [00:08<00:34,  3.49it/s]
Requesting API:  16%|█▌        | 22/140 [00:08<00:22,  5.23it/s]
Requesting API:  16%|█▋        | 23/140 [00:09<00:24,  4.79it/s]
Requesting API:  17%|█▋        | 24/140 [00:09<00:26,  4.44it/s]
Requesting API:  19%|█▉        | 27/140 [00:10<00:23,  4.82it/s]
Requesting API:  20%|██        | 28/140 [00:10<00:30,  3.64it/s]
Requesting API:  22%|██▏       | 31/140 [00:11<00:25,  4.23it/s]
Requesting API:  24%|██▎       | 33/140 [00:11<00:22,  4.79it/s]
Requesting API:  25%|██▌       | 35/140 [00:11<00:19,  5.29it/s]
Requesting API:  27%|██▋       | 38/140 [00:11<00:15,  6.55it/s]
Requesting API:  29%|██▉       | 41/140 [00:12<00:13,  7.59it/s]
Requesting API:  30%|███       | 42/140 [00:12<00:15,  6.50it/s]
Requesting API:  31%|███       | 43/140 [00:12<00:17,  5.67it/s]
Requesting API:  31%|███▏      | 44/140 [00:13<00:18,  5.07it/s]
Requesting API:  32%|███▏      | 45/140 [00:13<00:20,  4.63it/s]
Requesting API:  33%|███▎      | 46/140 [00:14<00:34,  2.72it/s]
Requesting API:  34%|███▎      | 47/140 [00:14<00:32,  2.88it/s]
Requesting API:  35%|███▌      | 49/140 [00:15<00:34,  2.61it/s]
Requesting API:  37%|███▋      | 52/140 [00:15<00:21,  4.05it/s]
Requesting API:  38%|███▊      | 53/140 [00:15<00:22,  3.92it/s]
Requesting API:  40%|████      | 56/140 [00:16<00:15,  5.41it/s]
Requesting API:  41%|████      | 57/140 [00:16<00:16,  4.95it/s]
Requesting API:  41%|████▏     | 58/140 [00:17<00:22,  3.61it/s]
Requesting API:  42%|████▏     | 59/140 [00:17<00:27,  2.91it/s]
Requesting API:  43%|████▎     | 60/140 [00:19<00:54,  1.48it/s]
Requesting API:  44%|████▎     | 61/140 [00:19<00:45,  1.73it/s]
Requesting API:  45%|████▌     | 63/140 [00:20<00:35,  2.19it/s]
Requesting API:  46%|████▋     | 65/140 [00:20<00:25,  2.94it/s]
Requesting API:  47%|████▋     | 66/140 [00:21<00:39,  1.87it/s]
Requesting API:  50%|█████     | 70/140 [00:22<00:20,  3.47it/s]
Requesting API:  51%|█████▏    | 72/140 [00:22<00:19,  3.45it/s]
Requesting API:  54%|█████▎    | 75/140 [00:23<00:14,  4.60it/s]
Requesting API:  54%|█████▍    | 76/140 [00:23<00:14,  4.38it/s]
Requesting API:  56%|█████▋    | 79/140 [00:24<00:17,  3.46it/s]
Requesting API:  57%|█████▋    | 80/140 [00:24<00:17,  3.52it/s]
Requesting API:  59%|█████▊    | 82/140 [00:25<00:16,  3.50it/s]
Requesting API:  59%|█████▉    | 83/140 [00:25<00:14,  3.83it/s]
Requesting API:  61%|██████    | 85/140 [00:25<00:12,  4.52it/s]
Requesting API:  62%|██████▏   | 87/140 [00:26<00:11,  4.57it/s]
Requesting API:  63%|██████▎   | 88/140 [00:26<00:13,  3.86it/s]
Requesting API:  64%|██████▍   | 90/140 [00:26<00:10,  4.56it/s]
Requesting API:  65%|██████▌   | 91/140 [00:27<00:12,  3.82it/s]
Requesting API:  66%|██████▋   | 93/140 [00:27<00:09,  4.83it/s]
Requesting API:  69%|██████▊   | 96/140 [00:27<00:07,  5.81it/s]
Requesting API:  69%|██████▉   | 97/140 [00:28<00:08,  5.20it/s]
Requesting API:  70%|███████   | 98/140 [00:28<00:11,  3.73it/s]
Requesting API:  71%|███████   | 99/140 [00:29<00:10,  3.82it/s]
Requesting API:  76%|███████▌  | 106/140 [00:29<00:04,  7.12it/s]
Requesting API:  76%|███████▋  | 107/140 [00:29<00:05,  6.30it/s]
Requesting API:  77%|███████▋  | 108/140 [00:30<00:05,  5.62it/s]
Requesting API:  78%|███████▊  | 109/140 [00:30<00:07,  4.03it/s]
Requesting API:  79%|███████▉  | 111/140 [00:31<00:06,  4.83it/s]
Requesting API:  81%|████████  | 113/140 [00:31<00:04,  5.83it/s]
Requesting API:  83%|████████▎ | 116/140 [00:31<00:03,  7.78it/s]
Requesting API:  84%|████████▎ | 117/140 [00:31<00:02,  8.07it/s]
Requesting API:  85%|████████▌ | 119/140 [00:31<00:02,  9.94it/s]
Requesting API:  86%|████████▋ | 121/140 [00:31<00:01,  9.96it/s]
Requesting API:  88%|████████▊ | 123/140 [00:32<00:01, 10.03it/s]
Requesting API:  90%|█████████ | 126/140 [00:32<00:01, 10.07it/s]
Requesting API:  91%|█████████▏| 128/140 [00:32<00:01,  7.95it/s]
Requesting API:  92%|█████████▏| 129/140 [00:33<00:02,  5.04it/s]
Requesting API:  93%|█████████▎| 130/140 [00:33<00:02,  4.30it/s]
Requesting API:  94%|█████████▎| 131/140 [00:34<00:02,  4.09it/s]
Requesting API:  94%|█████████▍| 132/140 [00:34<00:02,  3.96it/s]
Requesting API:  95%|█████████▌| 133/140 [00:34<00:01,  3.86it/s]
Requesting API:  96%|█████████▋| 135/140 [00:35<00:01,  3.74it/s]
Requesting API:  97%|█████████▋| 136/140 [00:36<00:02,  2.00it/s]
Requesting API:  98%|█████████▊| 137/140 [00:37<00:02,  1.49it/s]
Requesting API:  99%|█████████▊| 138/140 [00:37<00:01,  1.68it/s]
Requesting API:  99%|█████████▉| 139/140 [00:41<00:01,  1.32s/it]
Requesting API: 100%|██████████| 140/140 [00:48<00:00,  2.99s/it]
Requesting API: 100%|██████████| 140/140 [00:48<00:00,  2.88it/s]

Requesting API:   0%|          | 0/10 [00:00<?, ?it/s]
Requesting API:  10%|█         | 1/10 [00:00<00:05,  1.56it/s]
Requesting API:  30%|███       | 3/10 [00:00<00:01,  3.72it/s]
Requesting API:  50%|█████     | 5/10 [00:01<00:01,  4.67it/s]
Requesting API: 100%|██████████| 10/10 [00:01<00:00, 10.09it/s]
Requesting API: 100%|██████████| 10/10 [00:01<00:00,  7.01it/s]

Requesting API:   0%|          | 0/10 [00:00<?, ?it/s]
Requesting API:  10%|█         | 1/10 [00:00<00:07,  1.17it/s]
Requesting API:  20%|██        | 2/10 [00:03<00:16,  2.09s/it]
Requesting API:  30%|███       | 3/10 [00:05<00:11,  1.71s/it]
Requesting API:  40%|████      | 4/10 [00:10<00:18,  3.09s/it]
Requesting API:  50%|█████     | 5/10 [00:20<00:28,  5.76s/it]
Requesting API:  60%|██████    | 6/10 [00:32<00:31,  7.86s/it]
Requesting API:  70%|███████   | 7/10 [01:54<01:36, 32.04s/it]
Requesting API: 100%|██████████| 10/10 [01:54<00:00, 11.45s/it]

Requesting API:   0%|          | 0/10 [00:00<?, ?it/s]
Requesting API:  10%|█         | 1/10 [00:00<00:04,  2.07it/s]
Requesting API:  40%|████      | 4/10 [00:01<00:01,  3.51it/s]
Requesting API:  60%|██████    | 6/10 [00:11<00:09,  2.48s/it]
Requesting API:  70%|███████   | 7/10 [00:12<00:05,  1.95s/it]
Requesting API:  80%|████████  | 8/10 [00:21<00:07,  3.90s/it]
Requesting API:  90%|█████████ | 9/10 [01:02<00:13, 13.69s/it]
Requesting API: 100%|██████████| 10/10 [01:53<00:00, 23.90s/it]
Requesting API: 100%|██████████| 10/10 [01:53<00:00, 11.33s/it]
2026-07-23:22:08:16 INFO     [evaluator:585] Running loglikelihood requests
Traceback (most recent call last):
  File "/home/henry/Documents/PythonProjects/variable-reap/.venv/bin/lm_eval", line 10, in <module>
    sys.exit(cli_evaluate())
             ^^^^^^^^^^^^^^
  File "/home/henry/Documents/PythonProjects/variable-reap/.venv/lib/python3.12/site-packages/lm_eval/__main__.py", line 10, in cli_evaluate
    parser.execute(args)
  File "/home/henry/Documents/PythonProjects/variable-reap/.venv/lib/python3.12/site-packages/lm_eval/_cli/harness.py", line 60, in execute
    args.func(args)
  File "/home/henry/Documents/PythonProjects/variable-reap/.venv/lib/python3.12/site-packages/lm_eval/_cli/run.py", line 391, in _execute
    results = simple_evaluate(
              ^^^^^^^^^^^^^^^^
  File "/home/henry/Documents/PythonProjects/variable-reap/.venv/lib/python3.12/site-packages/lm_eval/utils.py", line 575, in _wrapper
    return fn(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^
  File "/home/henry/Documents/PythonProjects/variable-reap/.venv/lib/python3.12/site-packages/lm_eval/evaluator.py", line 358, in simple_evaluate
    results = evaluate(
              ^^^^^^^^^
  File "/home/henry/Documents/PythonProjects/variable-reap/.venv/lib/python3.12/site-packages/lm_eval/utils.py", line 575, in _wrapper
    return fn(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^
  File "/home/henry/Documents/PythonProjects/variable-reap/.venv/lib/python3.12/site-packages/lm_eval/evaluator.py", line 596, in evaluate
    resps = getattr(lm, reqtype)(cloned_reqs)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/henry/Documents/PythonProjects/variable-reap/.venv/lib/python3.12/site-packages/lm_eval/models/openai_completions.py", line 239, in loglikelihood
    raise NotImplementedError(
NotImplementedError: Loglikelihood is not supported for chat completions. Consider using the completions API instead.