Instructions to use keepsloading/icml_repro_scratch with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use keepsloading/icml_repro_scratch with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="keepsloading/icml_repro_scratch")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("keepsloading/icml_repro_scratch")
model = AutoModelForCausalLM.from_pretrained("keepsloading/icml_repro_scratch", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use keepsloading/icml_repro_scratch with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "keepsloading/icml_repro_scratch"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "keepsloading/icml_repro_scratch",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/keepsloading/icml_repro_scratch

SGLang

How to use keepsloading/icml_repro_scratch with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "keepsloading/icml_repro_scratch" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "keepsloading/icml_repro_scratch",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "keepsloading/icml_repro_scratch" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "keepsloading/icml_repro_scratch",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use keepsloading/icml_repro_scratch with Docker Model Runner:
```
docker model run hf.co/keepsloading/icml_repro_scratch
```

icml_repro_scratch / outputs /eval /logs /vanilla /ruler_a.log

keepsloading

Upload folder using huggingface_hub

6a26953 verified 29 days ago

Raw

History Blame Contribute Delete

53.6 kB

	2026-07-18:14:17:11 WARNING [config.evaluate_config:281] --limit SHOULD ONLY BE USED FOR TESTING. REAL METRICS SHOULD NOT BE COMPUTED USING LIMIT.
	2026-07-18:14:17:15 INFO [_cli.run:376] Selected Tasks: ['niah_single_1', 'niah_single_3', 'niah_multikey_2', 'niah_multiquery', 'ruler_vt', 'ruler_fwe', 'ruler_qa_hotpot']
	2026-07-18:14:17:16 INFO [evaluator:211] Setting random seed to 0 \| Setting numpy seed to 1234 \| Setting torch manual seed to 1234 \| Setting fewshot manual seed to 1234
	2026-07-18:14:17:16 INFO [evaluator:236] Initializing hf model, with arguments: {'pretrained': '/workspace', 'trust_remote_code': True, 'dtype': 'bfloat16', 'max_length': 16384, 'attn_implementation': 'sdpa'}
	2026-07-18:14:17:20 INFO [models.huggingface:161] Using device 'cuda:0'
	2026-07-18:14:17:20 INFO [models.huggingface:423] Model parallel was set to False, max memory was not set, and device map was set to {'': 'cuda:0'}
	2026-07-18:14:17:29 WARNING [api.task:856] niah_single_1: Custom kwargs can be passed to `--metadata` in console (as json string) or to the TaskManager.
	For example --metadata='{"max_seq_lengths":[4096, 8192]}'. For details see task Readme.
	2026-07-18:14:17:29 INFO [tasks.ruler.common_utils:26] Using tokenizer /workspace for synthetic tasks.

	Generating synthetic samples: repeat \| 8192: 0%\| \| 0/500 [00:00<?, ?it/s][A
	Generating synthetic samples: repeat \| 8192: 11%\|█▏ \| 57/500 [00:01<00:07, 56.50it/s][A
	Generating synthetic samples: repeat \| 8192: 23%\|██▎ \| 114/500 [00:02<00:06, 56.05it/s][A
	Generating synthetic samples: repeat \| 8192: 34%\|███▍ \| 171/500 [00:03<00:05, 55.36it/s][A
	Generating synthetic samples: repeat \| 8192: 45%\|████▌ \| 227/500 [00:04<00:04, 55.19it/s][A
	Generating synthetic samples: repeat \| 8192: 57%\|█████▋ \| 283/500 [00:05<00:03, 55.10it/s][A
	Generating synthetic samples: repeat \| 8192: 68%\|██████▊ \| 339/500 [00:06<00:02, 55.08it/s][A
	Generating synthetic samples: repeat \| 8192: 79%\|███████▉ \| 396/500 [00:07<00:01, 55.44it/s][A
	Generating synthetic samples: repeat \| 8192: 90%\|█████████ \| 452/500 [00:08<00:00, 55.35it/s][A Generating synthetic samples: repeat \| 8192: 100%\|██████████\| 500/500 [00:09<00:00, 55.34it/s]
	2026-07-18:14:17:39 WARNING [api.task:856] niah_single_3: Custom kwargs can be passed to `--metadata` in console (as json string) or to the TaskManager.
	For example --metadata='{"max_seq_lengths":[4096, 8192]}'. For details see task Readme.

	essays.parquet: 0%\| \| 0.00/1.19M [00:00<?, ?B/s][A essays.parquet: 100%\|██████████\| 1.19M/1.19M [00:00<00:00, 4.34MB/s]

	Generating train split: 0%\| \| 0/218 [00:00<?, ? examples/s][A Generating train split: 100%\|██████████\| 218/218 [00:00<00:00, 16342.71 examples/s]

	Generating synthetic samples: essay \| 8192: 0%\| \| 0/500 [00:00<?, ?it/s][A
	Generating synthetic samples: essay \| 8192: 11%\|█ \| 54/500 [00:01<00:08, 53.43it/s][A
	Generating synthetic samples: essay \| 8192: 22%\|██▏ \| 108/500 [00:02<00:07, 52.72it/s][A
	Generating synthetic samples: essay \| 8192: 32%\|███▏ \| 162/500 [00:03<00:06, 53.10it/s][A
	Generating synthetic samples: essay \| 8192: 43%\|████▎ \| 216/500 [00:04<00:05, 53.06it/s][A
	Generating synthetic samples: essay \| 8192: 54%\|█████▍ \| 270/500 [00:05<00:04, 53.09it/s][A
	Generating synthetic samples: essay \| 8192: 65%\|██████▌ \| 325/500 [00:06<00:03, 53.45it/s][A
	Generating synthetic samples: essay \| 8192: 76%\|███████▌ \| 380/500 [00:07<00:02, 53.88it/s][A
	Generating synthetic samples: essay \| 8192: 87%\|████████▋ \| 435/500 [00:08<00:01, 54.08it/s][A
	Generating synthetic samples: essay \| 8192: 98%\|█████████▊\| 490/500 [00:09<00:00, 53.95it/s][A Generating synthetic samples: essay \| 8192: 100%\|██████████\| 500/500 [00:09<00:00, 53.60it/s]
	2026-07-18:14:17:50 WARNING [api.task:856] niah_multikey_2: Custom kwargs can be passed to `--metadata` in console (as json string) or to the TaskManager.
	For example --metadata='{"max_seq_lengths":[4096, 8192]}'. For details see task Readme.

	Generating synthetic samples: needle \| 8192: 0%\| \| 0/500 [00:00<?, ?it/s][A
	Generating synthetic samples: needle \| 8192: 13%\|█▎ \| 64/500 [00:01<00:06, 63.24it/s][A
	Generating synthetic samples: needle \| 8192: 26%\|██▌ \| 128/500 [00:02<00:05, 63.21it/s][A
	Generating synthetic samples: needle \| 8192: 38%\|███▊ \| 192/500 [00:03<00:04, 62.90it/s][A
	Generating synthetic samples: needle \| 8192: 52%\|█████▏ \| 258/500 [00:04<00:03, 63.68it/s][A
	Generating synthetic samples: needle \| 8192: 65%\|██████▍ \| 323/500 [00:05<00:02, 63.97it/s][A
	Generating synthetic samples: needle \| 8192: 78%\|███████▊ \| 390/500 [00:06<00:01, 64.80it/s][A
	Generating synthetic samples: needle \| 8192: 92%\|█████████▏\| 458/500 [00:07<00:00, 65.62it/s][A Generating synthetic samples: needle \| 8192: 100%\|██████████\| 500/500 [00:07<00:00, 64.74it/s]
	2026-07-18:14:17:58 WARNING [api.task:856] niah_multiquery: Custom kwargs can be passed to `--metadata` in console (as json string) or to the TaskManager.
	For example --metadata='{"max_seq_lengths":[4096, 8192]}'. For details see task Readme.

	Generating synthetic samples: essay \| 8192: 0%\| \| 0/500 [00:00<?, ?it/s][A
	Generating synthetic samples: essay \| 8192: 11%\|█ \| 55/500 [00:01<00:08, 54.29it/s][A
	Generating synthetic samples: essay \| 8192: 22%\|██▏ \| 110/500 [00:02<00:07, 54.00it/s][A
	Generating synthetic samples: essay \| 8192: 33%\|███▎ \| 165/500 [00:03<00:06, 52.38it/s][A
	Generating synthetic samples: essay \| 8192: 44%\|████▎ \| 218/500 [00:04<00:05, 51.12it/s][A
	Generating synthetic samples: essay \| 8192: 54%\|█████▍ \| 270/500 [00:05<00:04, 51.20it/s][A
	Generating synthetic samples: essay \| 8192: 64%\|██████▍ \| 322/500 [00:06<00:03, 51.14it/s][A
	Generating synthetic samples: essay \| 8192: 75%\|███████▌ \| 376/500 [00:07<00:02, 51.95it/s][A
	Generating synthetic samples: essay \| 8192: 86%\|████████▌ \| 429/500 [00:08<00:01, 51.90it/s][A
	Generating synthetic samples: essay \| 8192: 96%\|█████████▌\| 481/500 [00:09<00:00, 51.30it/s][A Generating synthetic samples: essay \| 8192: 100%\|██████████\| 500/500 [00:09<00:00, 51.70it/s]
	2026-07-18:14:18:08 WARNING [api.task:856] ruler_vt: Custom kwargs can be passed to `--metadata` in console (as json string) or to the TaskManager.
	For example --metadata='{"max_seq_lengths":[4096, 8192]}'. For details see task Readme.
	2026-07-18:14:18:08 INFO [tasks.ruler.common_utils:26] Using tokenizer /workspace for synthetic tasks.
	Max length 500 \| Current length 307 \| Noises: 5
	Max length 500 \| Current length 410 \| Noises: 10
	Max length 500 \| Current length 531 \| Noises: 15
	Num noises: 10

	0%\| \| 0/1 [00:00<?, ?it/s][A 100%\|██████████\| 1/1 [00:00<00:00, 939.79it/s]
	Max length 8192 \| Current length 791 \| Noises: 10
	Max length 8192 \| Current length 1025 \| Noises: 20
	Max length 8192 \| Current length 1273 \| Noises: 30
	Max length 8192 \| Current length 1510 \| Noises: 40
	Max length 8192 \| Current length 1749 \| Noises: 50
	Max length 8192 \| Current length 1996 \| Noises: 60
	Max length 8192 \| Current length 2231 \| Noises: 70
	Max length 8192 \| Current length 2473 \| Noises: 80
	Max length 8192 \| Current length 2705 \| Noises: 90
	Max length 8192 \| Current length 2953 \| Noises: 100
	Max length 8192 \| Current length 3186 \| Noises: 110
	Max length 8192 \| Current length 3431 \| Noises: 120
	Max length 8192 \| Current length 3671 \| Noises: 130
	Max length 8192 \| Current length 3916 \| Noises: 140
	Max length 8192 \| Current length 4149 \| Noises: 150
	Max length 8192 \| Current length 4386 \| Noises: 160
	Max length 8192 \| Current length 4630 \| Noises: 170
	Max length 8192 \| Current length 4871 \| Noises: 180
	Max length 8192 \| Current length 5110 \| Noises: 190
	Max length 8192 \| Current length 5349 \| Noises: 200
	Max length 8192 \| Current length 5590 \| Noises: 210
	Max length 8192 \| Current length 5832 \| Noises: 220
	Max length 8192 \| Current length 6070 \| Noises: 230
	Max length 8192 \| Current length 6311 \| Noises: 240
	Max length 8192 \| Current length 6544 \| Noises: 250
	Max length 8192 \| Current length 6791 \| Noises: 260
	Max length 8192 \| Current length 7031 \| Noises: 270
	Max length 8192 \| Current length 7271 \| Noises: 280
	Max length 8192 \| Current length 7513 \| Noises: 290
	Max length 8192 \| Current length 7751 \| Noises: 300
	Max length 8192 \| Current length 7986 \| Noises: 310
	Max length 8192 \| Current length 8230 \| Noises: 320
	Num noises: 310

	0%\| \| 0/500 [00:00<?, ?it/s][A
	12%\|█▏ \| 59/500 [00:01<00:07, 58.56it/s][A
	24%\|██▎ \| 118/500 [00:02<00:06, 57.94it/s][A
	35%\|███▌ \| 176/500 [00:03<00:05, 57.91it/s][A
	47%\|████▋ \| 234/500 [00:04<00:04, 56.14it/s][A
	58%\|█████▊ \| 291/500 [00:05<00:03, 55.52it/s][A
	69%\|██████▉ \| 347/500 [00:06<00:02, 54.63it/s][A
	80%\|████████ \| 402/500 [00:07<00:01, 54.48it/s][A
	91%\|█████████▏\| 457/500 [00:08<00:00, 54.48it/s][A 100%\|██████████\| 500/500 [00:09<00:00, 55.38it/s]
	2026-07-18:14:18:18 WARNING [api.task:856] ruler_fwe: Custom kwargs can be passed to `--metadata` in console (as json string) or to the TaskManager.
	For example --metadata='{"max_seq_lengths":[4096, 8192]}'. For details see task Readme.

	Generating FWE Samples \| 8192: 0%\| \| 0/500 [00:00<?, ?it/s][A
	Generating FWE Samples \| 8192: 8%\|▊ \| 40/500 [00:01<00:11, 39.74it/s][A
	Generating FWE Samples \| 8192: 16%\|█▌ \| 81/500 [00:02<00:10, 40.12it/s][A
	Generating FWE Samples \| 8192: 24%\|██▍ \| 122/500 [00:03<00:09, 39.79it/s][A
	Generating FWE Samples \| 8192: 32%\|███▏ \| 162/500 [00:04<00:08, 39.25it/s][A
	Generating FWE Samples \| 8192: 40%\|████ \| 202/500 [00:05<00:07, 38.10it/s][A
	Generating FWE Samples \| 8192: 48%\|████▊ \| 241/500 [00:06<00:07, 36.79it/s][A
	Generating FWE Samples \| 8192: 56%\|█████▌ \| 278/500 [00:07<00:06, 36.23it/s][A
	Generating FWE Samples \| 8192: 63%\|██████▎ \| 315/500 [00:08<00:05, 36.28it/s][A
	Generating FWE Samples \| 8192: 70%\|███████ \| 352/500 [00:09<00:04, 36.25it/s][A
	Generating FWE Samples \| 8192: 78%\|███████▊ \| 389/500 [00:10<00:03, 35.93it/s][A
	Generating FWE Samples \| 8192: 85%\|████████▌ \| 426/500 [00:11<00:02, 36.05it/s][A
	Generating FWE Samples \| 8192: 93%\|█████████▎\| 463/500 [00:12<00:01, 35.81it/s][A
	Generating FWE Samples \| 8192: 100%\|█████████▉\| 499/500 [00:13<00:00, 35.80it/s][A Generating FWE Samples \| 8192: 100%\|██████████\| 500/500 [00:13<00:00, 36.80it/s]
	2026-07-18:14:18:32 WARNING [api.task:856] ruler_qa_hotpot: Custom kwargs can be passed to `--metadata` in console (as json string) or to the TaskManager.
	For example --metadata='{"max_seq_lengths":[4096, 8192]}'. For details see task Readme.

	Generating QA Samples \| 8192: 0%\| \| 0/500 [00:00<?, ?it/s][A
	Generating QA Samples \| 8192: 5%\|▍ \| 23/500 [00:01<00:21, 22.17it/s][A
	Generating QA Samples \| 8192: 10%\|▉ \| 48/500 [00:02<00:19, 23.58it/s][A
	Generating QA Samples \| 8192: 14%\|█▍ \| 72/500 [00:03<00:18, 23.42it/s][A
	Generating QA Samples \| 8192: 19%\|█▉ \| 96/500 [00:04<00:17, 23.56it/s][A
	Generating QA Samples \| 8192: 24%\|██▍ \| 121/500 [00:05<00:15, 23.92it/s][A
	Generating QA Samples \| 8192: 29%\|██▉ \| 147/500 [00:06<00:14, 24.37it/s][A
	Generating QA Samples \| 8192: 34%\|███▍ \| 172/500 [00:07<00:13, 24.55it/s][A
	Generating QA Samples \| 8192: 39%\|███▉ \| 197/500 [00:08<00:12, 24.24it/s][A
	Generating QA Samples \| 8192: 44%\|████▍ \| 222/500 [00:09<00:11, 24.10it/s][A
	Generating QA Samples \| 8192: 49%\|████▉ \| 247/500 [00:10<00:10, 23.96it/s][A
	Generating QA Samples \| 8192: 54%\|█████▍ \| 271/500 [00:11<00:09, 23.39it/s][A
	Generating QA Samples \| 8192: 59%\|█████▉ \| 297/500 [00:12<00:08, 23.94it/s][A
	Generating QA Samples \| 8192: 65%\|██████▍ \| 323/500 [00:13<00:07, 24.31it/s][A
	Generating QA Samples \| 8192: 70%\|██████▉ \| 348/500 [00:14<00:06, 23.74it/s][A
	Generating QA Samples \| 8192: 74%\|███████▍ \| 372/500 [00:15<00:05, 23.74it/s][A
	Generating QA Samples \| 8192: 79%\|███████▉ \| 396/500 [00:16<00:04, 23.77it/s][A
	Generating QA Samples \| 8192: 84%\|████████▍ \| 422/500 [00:17<00:03, 24.25it/s][A
	Generating QA Samples \| 8192: 89%\|████████▉ \| 447/500 [00:18<00:02, 24.01it/s][A
	Generating QA Samples \| 8192: 94%\|█████████▍\| 472/500 [00:19<00:01, 24.22it/s][A
	Generating QA Samples \| 8192: 99%\|█████████▉\| 497/500 [00:20<00:00, 23.74it/s][A Generating QA Samples \| 8192: 100%\|██████████\| 500/500 [00:20<00:00, 23.90it/s]
	2026-07-18:14:18:55 INFO [tasks:700] Selected tasks:
	2026-07-18:14:18:55 INFO [tasks:691] Task: ruler_qa_hotpot (ruler/qa_hotpot.yaml)
	2026-07-18:14:18:55 INFO [tasks:691] Task: ruler_fwe (ruler/fwe.yaml)
	2026-07-18:14:18:55 INFO [tasks:691] Task: ruler_vt (ruler/vt.yaml)
	2026-07-18:14:18:55 INFO [tasks:691] Task: niah_multiquery (ruler/niah_multiquery.yaml)
	2026-07-18:14:18:55 INFO [tasks:691] Task: niah_multikey_2 (ruler/niah_multikey_2.yaml)
	2026-07-18:14:18:55 INFO [tasks:691] Task: niah_single_3 (ruler/niah_single_3.yaml)
	2026-07-18:14:18:55 INFO [tasks:691] Task: niah_single_1 (ruler/niah_single_1.yaml)
	2026-07-18:14:18:55 INFO [evaluator:314] ruler_qa_hotpot: Using gen_kwargs: {'do_sample': False, 'temperature': 0.0, 'max_gen_toks': 32, 'until': []}
	2026-07-18:14:18:55 INFO [evaluator:314] ruler_fwe: Using gen_kwargs: {'do_sample': False, 'temperature': 0.0, 'max_gen_toks': 50, 'until': []}
	2026-07-18:14:18:55 INFO [evaluator:314] ruler_vt: Using gen_kwargs: {'do_sample': False, 'temperature': 0.0, 'max_gen_toks': 30, 'until': []}
	2026-07-18:14:18:55 INFO [evaluator:314] niah_multiquery: Using gen_kwargs: {'do_sample': False, 'temperature': 0.0, 'max_gen_toks': 128, 'until': []}
	2026-07-18:14:18:55 INFO [evaluator:314] niah_multikey_2: Using gen_kwargs: {'do_sample': False, 'temperature': 0.0, 'max_gen_toks': 128, 'until': []}
	2026-07-18:14:18:55 INFO [evaluator:314] niah_single_3: Using gen_kwargs: {'do_sample': False, 'temperature': 0.0, 'max_gen_toks': 128, 'until': []}
	2026-07-18:14:18:55 INFO [evaluator:314] niah_single_1: Using gen_kwargs: {'do_sample': False, 'temperature': 0.0, 'max_gen_toks': 128, 'until': []}
	2026-07-18:14:18:55 INFO [api.task:311] Building contexts for ruler_qa_hotpot on rank 0...

	0%\| \| 0/20 [00:00<?, ?it/s][A 100%\|██████████\| 20/20 [00:00<00:00, 890.78it/s]
	2026-07-18:14:18:55 INFO [api.task:311] Building contexts for ruler_fwe on rank 0...

	0%\| \| 0/20 [00:00<?, ?it/s][A 100%\|██████████\| 20/20 [00:00<00:00, 27.23it/s]
	2026-07-18:14:18:56 INFO [api.task:311] Building contexts for ruler_vt on rank 0...

	0%\| \| 0/20 [00:00<?, ?it/s][A 100%\|██████████\| 20/20 [00:00<00:00, 1111.88it/s]
	2026-07-18:14:18:56 INFO [api.task:311] Building contexts for niah_multiquery on rank 0...

	0%\| \| 0/20 [00:00<?, ?it/s][A 100%\|██████████\| 20/20 [00:00<00:00, 1060.84it/s]
	2026-07-18:14:18:56 INFO [api.task:311] Building contexts for niah_multikey_2 on rank 0...

	0%\| \| 0/20 [00:00<?, ?it/s][A 100%\|██████████\| 20/20 [00:00<00:00, 1124.90it/s]
	2026-07-18:14:18:56 INFO [api.task:311] Building contexts for niah_single_3 on rank 0...

	0%\| \| 0/20 [00:00<?, ?it/s][A 100%\|██████████\| 20/20 [00:00<00:00, 1082.43it/s]
	2026-07-18:14:18:56 INFO [api.task:311] Building contexts for niah_single_1 on rank 0...

	0%\| \| 0/20 [00:00<?, ?it/s][A 100%\|██████████\| 20/20 [00:00<00:00, 1113.64it/s]
	2026-07-18:14:18:56 INFO [evaluator:584] Running generate_until requests

	Running generate_until requests: 0%\| \| 0/140 [00:00<?, ?it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 1%\| \| 1/140 [00:02<05:45, 2.49s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 1%\|▏ \| 2/140 [00:04<04:25, 1.93s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 2%\|▏ \| 3/140 [00:05<03:59, 1.75s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 3%\|▎ \| 4/140 [00:07<03:45, 1.66s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 4%\|▎ \| 5/140 [00:08<03:37, 1.61s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 4%\|▍ \| 6/140 [00:10<03:31, 1.58s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 5%\|▌ \| 7/140 [00:11<03:27, 1.56s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 6%\|▌ \| 8/140 [00:13<03:24, 1.55s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 6%\|▋ \| 9/140 [00:14<03:21, 1.54s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 7%\|▋ \| 10/140 [00:16<03:18, 1.53s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 8%\|▊ \| 11/140 [00:17<03:16, 1.52s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 9%\|▊ \| 12/140 [00:19<03:14, 1.52s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 9%\|▉ \| 13/140 [00:20<03:11, 1.51s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 10%\|█ \| 14/140 [00:22<03:09, 1.50s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 11%\|█ \| 15/140 [00:23<03:06, 1.50s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 11%\|█▏ \| 16/140 [00:25<03:04, 1.49s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 12%\|█▏ \| 17/140 [00:26<03:02, 1.48s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 13%\|█▎ \| 18/140 [00:28<03:01, 1.49s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 14%\|█▎ \| 19/140 [00:29<02:59, 1.48s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 14%\|█▍ \| 20/140 [00:31<02:57, 1.48s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 15%\|█▌ \| 21/140 [00:33<03:32, 1.78s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 16%\|█▌ \| 22/140 [00:35<03:47, 1.92s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 16%\|█▋ \| 23/140 [00:38<03:57, 2.03s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 17%\|█▋ \| 24/140 [00:40<04:03, 2.10s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 18%\|█▊ \| 25/140 [00:42<04:06, 2.15s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 19%\|█▊ \| 26/140 [00:44<04:08, 2.18s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 19%\|█▉ \| 27/140 [00:47<04:09, 2.21s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 20%\|██ \| 28/140 [00:49<04:08, 2.22s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 21%\|██ \| 29/140 [00:51<04:07, 2.23s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 21%\|██▏ \| 30/140 [00:53<04:06, 2.24s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 22%\|██▏ \| 31/140 [00:56<04:04, 2.24s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 23%\|██▎ \| 32/140 [00:58<04:03, 2.25s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 24%\|██▎ \| 33/140 [01:00<04:00, 2.25s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 24%\|██▍ \| 34/140 [01:02<03:58, 2.25s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 25%\|██▌ \| 35/140 [01:05<03:56, 2.25s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 26%\|██▌ \| 36/140 [01:07<03:54, 2.26s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 26%\|██▋ \| 37/140 [01:09<03:52, 2.26s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 27%\|██▋ \| 38/140 [01:11<03:49, 2.25s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 28%\|██▊ \| 39/140 [01:14<03:47, 2.25s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 29%\|██▊ \| 40/140 [01:16<03:44, 2.25s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 29%\|██▉ \| 41/140 [01:18<03:29, 2.11s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 30%\|███ \| 42/140 [01:19<03:07, 1.91s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 31%\|███ \| 43/140 [01:21<02:52, 1.78s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 31%\|███▏ \| 44/140 [01:22<02:41, 1.68s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 32%\|███▏ \| 45/140 [01:24<02:32, 1.61s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 33%\|███▎ \| 46/140 [01:25<02:26, 1.56s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 34%\|███▎ \| 47/140 [01:26<02:22, 1.53s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 34%\|███▍ \| 48/140 [01:28<02:19, 1.51s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 35%\|███▌ \| 49/140 [01:29<02:15, 1.49s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 36%\|███▌ \| 50/140 [01:31<02:13, 1.48s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 36%\|███▋ \| 51/140 [01:32<02:11, 1.48s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 37%\|███▋ \| 52/140 [01:34<02:08, 1.46s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 38%\|███▊ \| 53/140 [01:35<02:06, 1.46s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 39%\|███▊ \| 54/140 [01:37<02:04, 1.45s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 39%\|███▉ \| 55/140 [01:38<02:03, 1.45s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 40%\|████ \| 56/140 [01:39<02:01, 1.45s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 41%\|████ \| 57/140 [01:41<01:59, 1.45s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 41%\|████▏ \| 58/140 [01:42<01:58, 1.44s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 42%\|████▏ \| 59/140 [01:44<01:56, 1.44s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 43%\|████▎ \| 60/140 [01:45<01:55, 1.44s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 44%\|████▎ \| 61/140 [01:52<04:00, 3.05s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 44%\|████▍ \| 62/140 [01:58<04:54, 3.78s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 45%\|████▌ \| 63/140 [02:03<05:30, 4.29s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 46%\|████▌ \| 64/140 [02:08<05:53, 4.65s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 46%\|████▋ \| 65/140 [02:14<06:07, 4.90s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 47%\|████▋ \| 66/140 [02:19<06:15, 5.08s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 48%\|████▊ \| 67/140 [02:25<06:19, 5.20s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 49%\|████▊ \| 68/140 [02:30<06:20, 5.29s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 49%\|████▉ \| 69/140 [02:36<06:19, 5.34s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 50%\|█████ \| 70/140 [02:41<06:17, 5.39s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 51%\|█████ \| 71/140 [02:47<06:13, 5.41s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 51%\|█████▏ \| 72/140 [02:52<06:09, 5.43s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 52%\|█████▏ \| 73/140 [02:58<06:05, 5.45s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 53%\|█████▎ \| 74/140 [03:03<06:00, 5.46s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 54%\|█████▎ \| 75/140 [03:09<05:55, 5.47s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 54%\|█████▍ \| 76/140 [03:14<05:49, 5.47s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 55%\|█████▌ \| 77/140 [03:20<05:44, 5.47s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 56%\|█████▌ \| 78/140 [03:25<05:39, 5.48s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 56%\|█████▋ \| 79/140 [03:31<05:34, 5.48s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 57%\|█████▋ \| 80/140 [03:36<05:28, 5.48s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 58%\|█████▊ \| 81/140 [03:42<05:23, 5.48s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 59%\|█████▊ \| 82/140 [03:47<05:17, 5.48s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 59%\|█████▉ \| 83/140 [03:53<05:12, 5.48s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 60%\|██████ \| 84/140 [03:58<05:07, 5.48s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 61%\|██████ \| 85/140 [04:04<05:02, 5.50s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 61%\|██████▏ \| 86/140 [04:09<04:57, 5.51s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 62%\|██████▏ \| 87/140 [04:15<04:52, 5.52s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 63%\|██████▎ \| 88/140 [04:20<04:47, 5.52s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 64%\|██████▎ \| 89/140 [04:26<04:41, 5.52s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 64%\|██████▍ \| 90/140 [04:31<04:36, 5.53s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 65%\|██████▌ \| 91/140 [04:37<04:30, 5.53s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 66%\|██████▌ \| 92/140 [04:42<04:25, 5.52s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 66%\|██████▋ \| 93/140 [04:48<04:19, 5.52s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 67%\|██████▋ \| 94/140 [04:53<04:13, 5.52s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 68%\|██████▊ \| 95/140 [04:59<04:08, 5.52s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 69%\|██████▊ \| 96/140 [05:04<04:02, 5.52s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 69%\|██████▉ \| 97/140 [05:10<03:57, 5.53s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 70%\|███████ \| 98/140 [05:15<03:51, 5.51s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 71%\|███████ \| 99/140 [05:21<03:45, 5.51s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 71%\|███████▏ \| 100/140 [05:26<03:40, 5.50s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 72%\|███████▏ \| 101/140 [05:32<03:34, 5.50s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 73%\|███████▎ \| 102/140 [05:37<03:28, 5.49s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 74%\|███████▎ \| 103/140 [05:43<03:23, 5.49s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 74%\|███████▍ \| 104/140 [05:48<03:17, 5.49s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 75%\|███████▌ \| 105/140 [05:54<03:12, 5.49s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 76%\|███████▌ \| 106/140 [05:59<03:06, 5.49s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 76%\|███████▋ \| 107/140 [06:05<03:01, 5.50s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 77%\|███████▋ \| 108/140 [06:10<02:55, 5.49s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 78%\|███████▊ \| 109/140 [06:16<02:49, 5.48s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 79%\|███████▊ \| 110/140 [06:21<02:44, 5.48s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 79%\|███████▉ \| 111/140 [06:27<02:38, 5.48s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 80%\|████████ \| 112/140 [06:32<02:33, 5.47s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 81%\|████████ \| 113/140 [06:38<02:27, 5.47s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 81%\|████████▏ \| 114/140 [06:43<02:22, 5.47s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 82%\|████████▏ \| 115/140 [06:49<02:16, 5.47s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 83%\|████████▎ \| 116/140 [06:54<02:11, 5.47s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 84%\|████████▎ \| 117/140 [07:00<02:05, 5.47s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 84%\|████████▍ \| 118/140 [07:05<02:00, 5.47s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 85%\|████████▌ \| 119/140 [07:11<01:55, 5.48s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 86%\|████████▌ \| 120/140 [07:16<01:49, 5.48s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 86%\|████████▋ \| 121/140 [07:21<01:44, 5.48s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 87%\|████████▋ \| 122/140 [07:27<01:38, 5.48s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 88%\|████████▊ \| 123/140 [07:32<01:33, 5.48s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 89%\|████████▊ \| 124/140 [07:38<01:27, 5.47s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 89%\|████████▉ \| 125/140 [07:43<01:22, 5.47s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 90%\|█████████ \| 126/140 [07:49<01:16, 5.47s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 91%\|█████████ \| 127/140 [07:54<01:11, 5.47s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 91%\|█████████▏\| 128/140 [07:59<01:03, 5.27s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 92%\|█████████▏\| 129/140 [08:03<00:54, 4.96s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 93%\|█████████▎\| 130/140 [08:08<00:47, 4.74s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 94%\|█████████▎\| 131/140 [08:12<00:41, 4.58s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 94%\|█████████▍\| 132/140 [08:16<00:35, 4.47s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 95%\|█████████▌\| 133/140 [08:20<00:30, 4.40s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 96%\|█████████▌\| 134/140 [08:24<00:26, 4.35s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 96%\|█████████▋\| 135/140 [08:29<00:21, 4.31s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 97%\|█████████▋\| 136/140 [08:33<00:17, 4.28s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 98%\|█████████▊\| 137/140 [08:37<00:12, 4.27s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 99%\|█████████▊\| 138/140 [08:41<00:08, 4.25s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 99%\|█████████▉\| 139/140 [08:46<00:04, 4.24s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.

	Running generate_until requests: 100%\|██████████\| 140/140 [08:50<00:00, 4.24s/it][A Running generate_until requests: 100%\|██████████\| 140/140 [08:50<00:00, 3.79s/it]
	2026-07-18:14:27:50 INFO [loggers.evaluation_tracker:247] Saving results aggregated
	2026-07-18:14:27:50 INFO [loggers.evaluation_tracker:119] Saving per-task samples to /workspace/outputs/eval/vanilla/ruler8k_splits/a/lm_eval/__workspace/*.jsonl
	hf ({'pretrained': '/workspace', 'dtype': 'bfloat16', 'max_length': 16384, 'attn_implementation': 'sdpa'}), gen_kwargs: ({}), limit: 20.0, num_fewshot: None, batch_size: 1
	\| Tasks \|Version\|Filter\|n-shot\|Metric\| \| Value \| \|Stderr\|
	\|---------------\|------:\|------\|-----:\|-----:\|---\|------:\|---\|------\|
	\|niah_multikey_2\| 1\|none \| 0\| 4096\|↑ \|-1.0000\|± \| N/A\|
	\| \| \|none \| 0\| 8192\|↑ \| 1.0000\|± \| N/A\|
	\|niah_multiquery\| 1\|none \| 0\| 4096\|↑ \|-1.0000\|± \| N/A\|
	\| \| \|none \| 0\| 8192\|↑ \| 0.9875\|± \| N/A\|
	\|niah_single_1 \| 1\|none \| 0\| 4096\|↑ \|-1.0000\|± \| N/A\|
	\| \| \|none \| 0\| 8192\|↑ \| 1.0000\|± \| N/A\|
	\|niah_single_3 \| 1\|none \| 0\| 4096\|↑ \|-1.0000\|± \| N/A\|
	\| \| \|none \| 0\| 8192\|↑ \| 1.0000\|± \| N/A\|
	\|ruler_fwe \| 1\|none \| 0\| 4096\|↑ \|-1.0000\|± \| N/A\|
	\| \| \|none \| 0\| 8192\|↑ \| 0.7667\|± \| N/A\|
	\|ruler_qa_hotpot\| 1\|none \| 0\| 4096\|↑ \|-1.0000\|± \| N/A\|
	\| \| \|none \| 0\| 8192\|↑ \| 0.4500\|± \| N/A\|
	\|ruler_vt \| 1\|none \| 0\| 4096\|↑ \|-1.0000\|± \| N/A\|
	\| \| \|none \| 0\| 8192\|↑ \| 0.8600\|± \| N/A\|