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 /babilong.log

keepsloading

Upload folder using huggingface_hub

6a26953 verified 27 days ago

Raw

History Blame Contribute Delete

58.7 kB

	2026-07-18:14:38:06 WARNING [config.evaluate_config:281] --limit SHOULD ONLY BE USED FOR TESTING. REAL METRICS SHOULD NOT BE COMPUTED USING LIMIT.
	2026-07-18:14:38:10 INFO [_cli.run:376] Selected Tasks: ['babilong_longctx']
	2026-07-18:14:38:11 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
	2026-07-18:14:38:11 INFO [evaluator:236] Initializing hf model, with arguments: {'pretrained': '/workspace', 'trust_remote_code': True, 'dtype': 'bfloat16', 'max_length': 16384, 'attn_implementation': 'sdpa'}
	2026-07-18:14:38:15 INFO [models.huggingface:161] Using device 'cuda:0'
	2026-07-18:14:38:15 INFO [models.huggingface:423] Model parallel was set to False, max memory was not set, and device map was set to {'': 'cuda:0'}
	2026-07-18:14:38:17 WARNING [api.task:856] babilong_qa5: 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.

	README.md: 0%\| \| 0.00/12.0k [00:00<?, ?B/s][A README.md: 100%\|██████████\| 12.0k/12.0k [00:00<00:00, 46.5MB/s]

	8k/qa1-00000-of-00001.parquet: 0%\| \| 0.00/18.8M [00:00<?, ?B/s][A 8k/qa1-00000-of-00001.parquet: 100%\|██████████\| 18.8M/18.8M [00:00<00:00, 36.4MB/s]

	8k/qa2-00000-of-00001.parquet: 0%\| \| 0.00/18.6M [00:00<?, ?B/s][A 8k/qa2-00000-of-00001.parquet: 100%\|██████████\| 18.6M/18.6M [00:00<00:00, 73.1MB/s]

	8k/qa3-00000-of-00001.parquet: 0%\| \| 0.00/18.5M [00:00<?, ?B/s][A 8k/qa3-00000-of-00001.parquet: 100%\|██████████\| 18.5M/18.5M [00:00<00:00, 35.1MB/s]

	8k/qa4-00000-of-00001.parquet: 0%\| \| 0.00/18.8M [00:00<?, ?B/s][A 8k/qa4-00000-of-00001.parquet: 100%\|██████████\| 18.8M/18.8M [00:00<00:00, 63.1MB/s]

	8k/qa5-00000-of-00001.parquet: 0%\| \| 0.00/18.7M [00:00<?, ?B/s][A 8k/qa5-00000-of-00001.parquet: 100%\|██████████\| 18.7M/18.7M [00:00<00:00, 67.9MB/s]

	Generating qa1 split: 0%\| \| 0/1000 [00:00<?, ? examples/s][A Generating qa1 split: 100%\|██████████\| 1000/1000 [00:00<00:00, 5788.82 examples/s]

	Generating qa2 split: 0%\| \| 0/999 [00:00<?, ? examples/s][A Generating qa2 split: 100%\|██████████\| 999/999 [00:00<00:00, 9726.55 examples/s]

	Generating qa3 split: 0%\| \| 0/999 [00:00<?, ? examples/s][A Generating qa3 split: 100%\|██████████\| 999/999 [00:00<00:00, 10002.34 examples/s]

	Generating qa4 split: 0%\| \| 0/999 [00:00<?, ? examples/s][A Generating qa4 split: 100%\|██████████\| 999/999 [00:00<00:00, 10155.80 examples/s]

	Generating qa5 split: 0%\| \| 0/999 [00:00<?, ? examples/s][A Generating qa5 split: 100%\|██████████\| 999/999 [00:00<00:00, 11153.79 examples/s]
	2026-07-18:14:38:20 WARNING [api.task:856] babilong_qa4: 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.
	2026-07-18:14:38:20 WARNING [api.task:856] babilong_qa3: 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.
	2026-07-18:14:38:20 WARNING [api.task:856] babilong_qa2: 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.
	2026-07-18:14:38:20 WARNING [api.task:856] babilong_qa1: 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.
	2026-07-18:14:38:20 INFO [tasks:700] Selected tasks:
	2026-07-18:14:38:20 INFO [tasks:703] Group: babilong_longctx
	2026-07-18:14:38:20 INFO [tasks:726] ConfigurableGroup(group=babilong_longctx,group_alias=None): {'babilong_qa1': ConfigurableTask(task_name=babilong_qa1,output_type=generate_until,num_fewshot=2,num_samples=1000), 'babilong_qa2': ConfigurableTask(task_name=babilong_qa2,output_type=generate_until,num_fewshot=2,num_samples=999), 'babilong_qa3': ConfigurableTask(task_name=babilong_qa3,output_type=generate_until,num_fewshot=2,num_samples=999), 'babilong_qa4': ConfigurableTask(task_name=babilong_qa4,output_type=generate_until,num_fewshot=2,num_samples=999), 'babilong_qa5': ConfigurableTask(task_name=babilong_qa5,output_type=generate_until,num_fewshot=2,num_samples=999)}
	2026-07-18:14:38:20 INFO [evaluator:314] babilong_qa1: Using gen_kwargs: {'do_sample': False, 'temperature': 0.0, 'max_gen_toks': 16, 'until': []}
	2026-07-18:14:38:20 WARNING [evaluator:333] Overwriting default num_fewshot of babilong_qa1 from 2 to 2
	2026-07-18:14:38:20 INFO [evaluator:314] babilong_qa2: Using gen_kwargs: {'do_sample': False, 'temperature': 0.0, 'max_gen_toks': 16, 'until': []}
	2026-07-18:14:38:20 WARNING [evaluator:333] Overwriting default num_fewshot of babilong_qa2 from 2 to 2
	2026-07-18:14:38:20 INFO [evaluator:314] babilong_qa3: Using gen_kwargs: {'do_sample': False, 'temperature': 0.0, 'max_gen_toks': 16, 'until': []}
	2026-07-18:14:38:20 WARNING [evaluator:333] Overwriting default num_fewshot of babilong_qa3 from 2 to 2
	2026-07-18:14:38:20 INFO [evaluator:314] babilong_qa4: Using gen_kwargs: {'do_sample': False, 'temperature': 0.0, 'max_gen_toks': 16, 'until': []}
	2026-07-18:14:38:20 WARNING [evaluator:333] Overwriting default num_fewshot of babilong_qa4 from 2 to 2
	2026-07-18:14:38:20 INFO [evaluator:314] babilong_qa5: Using gen_kwargs: {'do_sample': False, 'temperature': 0.0, 'max_gen_toks': 16, 'until': []}
	2026-07-18:14:38:20 WARNING [evaluator:333] Overwriting default num_fewshot of babilong_qa5 from 2 to 2
	2026-07-18:14:38:20 INFO [api.task:311] Building contexts for babilong_qa1 on rank 0...

	0%\| \| 0/50 [00:00<?, ?it/s][A 100%\|██████████\| 50/50 [00:00<00:00, 251.53it/s]
	2026-07-18:14:38:20 INFO [api.task:311] Building contexts for babilong_qa2 on rank 0...

	0%\| \| 0/50 [00:00<?, ?it/s][A 100%\|██████████\| 50/50 [00:00<00:00, 370.37it/s]
	2026-07-18:14:38:21 INFO [api.task:311] Building contexts for babilong_qa3 on rank 0...

	0%\| \| 0/50 [00:00<?, ?it/s][A 100%\|██████████\| 50/50 [00:00<00:00, 360.63it/s]
	2026-07-18:14:38:21 INFO [api.task:311] Building contexts for babilong_qa4 on rank 0...

	0%\| \| 0/50 [00:00<?, ?it/s][A 100%\|██████████\| 50/50 [00:00<00:00, 372.64it/s]
	2026-07-18:14:38:21 INFO [api.task:311] Building contexts for babilong_qa5 on rank 0...

	0%\| \| 0/50 [00:00<?, ?it/s][A 100%\|██████████\| 50/50 [00:00<00:00, 372.31it/s]
	2026-07-18:14:38:21 INFO [evaluator:584] Running generate_until requests

	Running generate_until requests: 0%\| \| 0/250 [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: 0%\| \| 1/250 [00:05<22:46, 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.
	The 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%\| \| 3/250 [00:06<08:04, 1.96s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|▏ \| 5/250 [00:08<05:24, 1.33s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|▎ \| 7/250 [00:09<04:20, 1.07s/it][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|▎ \| 9/250 [00:11<03:46, 1.06it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|▍ \| 11/250 [00:12<03:26, 1.16it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|▌ \| 13/250 [00:14<03:14, 1.22it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|▌ \| 15/250 [00:15<03:05, 1.27it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|▋ \| 17/250 [00:17<02:59, 1.30it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|▊ \| 19/250 [00:18<02:54, 1.32it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|▊ \| 21/250 [00:20<02:50, 1.34it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|▉ \| 23/250 [00:21<02:48, 1.35it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|█ \| 25/250 [00:22<02:45, 1.36it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|█ \| 27/250 [00:24<02:43, 1.36it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|█▏ \| 29/250 [00:25<02:41, 1.37it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|█▏ \| 31/250 [00:27<02:39, 1.37it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|█▎ \| 33/250 [00:28<02:38, 1.37it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|█▍ \| 35/250 [00:30<02:36, 1.37it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|█▍ \| 37/250 [00:31<02:34, 1.38it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|█▌ \| 39/250 [00:33<02:33, 1.38it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|█▋ \| 41/250 [00:34<02:31, 1.38it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|█▋ \| 43/250 [00:35<02:29, 1.38it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|█▊ \| 45/250 [00:37<02:28, 1.38it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|█▉ \| 47/250 [00:38<02:26, 1.38it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|█▉ \| 49/250 [00:40<02:25, 1.38it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|██ \| 51/250 [00:41<02:24, 1.38it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|██ \| 53/250 [00:43<02:22, 1.38it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|██▏ \| 55/250 [00:44<02:20, 1.38it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|██▎ \| 57/250 [00:46<02:19, 1.39it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|██▎ \| 59/250 [00:47<02:17, 1.38it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|██▍ \| 61/250 [00:48<02:16, 1.39it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|██▌ \| 63/250 [00:50<02:14, 1.39it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|██▌ \| 65/250 [00:51<02:13, 1.39it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|██▋ \| 67/250 [00:53<02:11, 1.39it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|██▊ \| 69/250 [00:54<02:10, 1.39it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|██▊ \| 71/250 [00:56<02:08, 1.39it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|██▉ \| 73/250 [00:57<02:07, 1.39it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|███ \| 75/250 [00:59<02:06, 1.39it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|███ \| 77/250 [01:00<02:04, 1.39it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|███▏ \| 79/250 [01:01<02:03, 1.38it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|███▏ \| 81/250 [01:03<02:02, 1.38it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|███▎ \| 83/250 [01:04<02:00, 1.38it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|███▍ \| 85/250 [01:06<01:59, 1.38it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|███▍ \| 87/250 [01:07<01:57, 1.38it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|███▌ \| 89/250 [01:09<01:56, 1.38it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|███▋ \| 91/250 [01:10<01:54, 1.39it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|███▋ \| 93/250 [01:12<01:53, 1.38it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|███▊ \| 95/250 [01:13<01:51, 1.38it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|███▉ \| 97/250 [01:14<01:50, 1.38it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|███▉ \| 99/250 [01:16<01:49, 1.38it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|████ \| 101/250 [01:17<01:50, 1.34it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|████ \| 103/250 [01:19<01:48, 1.36it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|████▏ \| 105/250 [01:20<01:46, 1.36it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|████▎ \| 107/250 [01:22<01:44, 1.36it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|████▎ \| 109/250 [01:23<01:42, 1.37it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|████▍ \| 111/250 [01:25<01:41, 1.38it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|████▌ \| 113/250 [01:26<01:39, 1.37it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|████▌ \| 115/250 [01:28<01:38, 1.38it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|████▋ \| 117/250 [01:29<01:36, 1.38it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|████▊ \| 119/250 [01:31<01:34, 1.38it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|████▊ \| 121/250 [01:32<01:34, 1.37it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|████▉ \| 123/250 [01:33<01:32, 1.38it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|█████ \| 125/250 [01:35<01:30, 1.38it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|█████ \| 127/250 [01:36<01:29, 1.38it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|█████▏ \| 129/250 [01:38<01:27, 1.38it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|█████▏ \| 131/250 [01:39<01:26, 1.38it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|█████▎ \| 133/250 [01:41<01:24, 1.38it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|█████▍ \| 135/250 [01:42<01:23, 1.38it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|█████▍ \| 137/250 [01:44<01:21, 1.39it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|█████▌ \| 139/250 [01:45<01:19, 1.39it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|█████▋ \| 141/250 [01:46<01:18, 1.39it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|█████▋ \| 143/250 [01:48<01:16, 1.39it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|█████▊ \| 145/250 [01:49<01:15, 1.39it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|█████▉ \| 147/250 [01:51<01:14, 1.39it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|█████▉ \| 149/250 [01:52<01:12, 1.39it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|██████ \| 151/250 [01:54<01:11, 1.39it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|██████ \| 153/250 [01:55<01:09, 1.39it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|██████▏ \| 155/250 [01:57<01:08, 1.39it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|██████▎ \| 157/250 [01:58<01:06, 1.39it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|██████▎ \| 159/250 [01:59<01:05, 1.39it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|██████▍ \| 161/250 [02:01<01:04, 1.39it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|██████▌ \| 163/250 [02:02<01:02, 1.39it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|██████▌ \| 165/250 [02:04<01:01, 1.39it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|██████▋ \| 167/250 [02:05<00:59, 1.39it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|██████▊ \| 169/250 [02:07<00:58, 1.39it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|██████▊ \| 171/250 [02:08<00:56, 1.39it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|██████▉ \| 173/250 [02:09<00:55, 1.39it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|███████ \| 175/250 [02:11<00:53, 1.39it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|███████ \| 177/250 [02:12<00:52, 1.39it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|███████▏ \| 179/250 [02:14<00:50, 1.39it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|███████▏ \| 181/250 [02:15<00:49, 1.39it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|███████▎ \| 183/250 [02:17<00:48, 1.39it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|███████▍ \| 185/250 [02:18<00:46, 1.39it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|███████▍ \| 187/250 [02:19<00:45, 1.40it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|███████▌ \| 189/250 [02:21<00:43, 1.40it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|███████▋ \| 191/250 [02:22<00:42, 1.40it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|███████▋ \| 193/250 [02:24<00:40, 1.40it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|███████▊ \| 195/250 [02:25<00:39, 1.40it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|███████▉ \| 197/250 [02:27<00:37, 1.40it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|███████▉ \| 199/250 [02:28<00:36, 1.40it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|████████ \| 201/250 [02:30<00:35, 1.40it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|████████ \| 203/250 [02:31<00:33, 1.39it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|████████▏ \| 205/250 [02:32<00:32, 1.39it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|████████▎ \| 207/250 [02:34<00:30, 1.40it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|████████▎ \| 209/250 [02:35<00:29, 1.41it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|████████▍ \| 211/250 [02:37<00:27, 1.41it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|████████▌ \| 213/250 [02:38<00:26, 1.42it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|████████▌ \| 215/250 [02:39<00:24, 1.42it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|████████▋ \| 217/250 [02:41<00:23, 1.42it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|████████▊ \| 219/250 [02:42<00:21, 1.42it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|████████▊ \| 221/250 [02:44<00:20, 1.42it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|████████▉ \| 223/250 [02:45<00:18, 1.42it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|█████████ \| 225/250 [02:46<00:17, 1.43it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|█████████ \| 227/250 [02:48<00:16, 1.43it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|█████████▏\| 229/250 [02:49<00:14, 1.43it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|█████████▏\| 231/250 [02:51<00:13, 1.44it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|█████████▎\| 233/250 [02:52<00:11, 1.44it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|█████████▍\| 235/250 [02:53<00:10, 1.44it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|█████████▍\| 237/250 [02:55<00:08, 1.45it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|█████████▌\| 239/250 [02:56<00:07, 1.46it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|█████████▋\| 241/250 [02:57<00:06, 1.46it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|█████████▋\| 243/250 [02:59<00:04, 1.47it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|█████████▊\| 245/250 [03:00<00:03, 1.47it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|█████████▉\| 247/250 [03:01<00:02, 1.49it/s][AThe following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
	The 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%\|█████████▉\| 249/250 [03:03<00:00, 1.50it/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: 100%\|██████████\| 250/250 [03:03<00:00, 1.36it/s]
	2026-07-18:14:41:29 INFO [loggers.evaluation_tracker:247] Saving results aggregated
	2026-07-18:14:41:29 INFO [loggers.evaluation_tracker:119] Saving per-task samples to /workspace/outputs/eval/vanilla/babilong8k_qa1_qa5_n50/__workspace/*.jsonl
	hf ({'pretrained': '/workspace', 'dtype': 'bfloat16', 'max_length': 16384, 'attn_implementation': 'sdpa'}), gen_kwargs: ({}), limit: 50.0, num_fewshot: 2, batch_size: 1
	\| Tasks \|Version\|Filter\|n-shot\|Metric\| \|Value\| \|Stderr\|
	\|----------------\|------:\|------\|-----:\|------\|---\|----:\|---\|-----:\|
	\|babilong_longctx\| 0\|none \| \|acc \|↑ \| 0.60\|± \|0.0295\|
	\| - babilong_qa1 \| 0\|none \| 2\|acc \|↑ \| 0.68\|± \|0.0666\|
	\| - babilong_qa2 \| 0\|none \| 2\|acc \|↑ \| 0.48\|± \|0.0714\|
	\| - babilong_qa3 \| 0\|none \| 2\|acc \|↑ \| 0.34\|± \|0.0677\|
	\| - babilong_qa4 \| 0\|none \| 2\|acc \|↑ \| 0.72\|± \|0.0641\|
	\| - babilong_qa5 \| 0\|none \| 2\|acc \|↑ \| 0.78\|± \|0.0592\|

	\| Groups \|Version\|Filter\|n-shot\|Metric\| \|Value\| \|Stderr\|
	\|----------------\|------:\|------\|------\|------\|---\|----:\|---\|-----:\|
	\|babilong_longctx\| 0\|none \| \|acc \|↑ \| 0.6\|± \|0.0295\|