3TF-14B / eval_lighteval|math_500|0.log
volcanos's picture
Upload folder using huggingface_hub
c67ee0f
INFO 10-26 02:40:28 [__init__.py:235] Automatically detected platform cuda.
[2025-10-26 02:40:30,504] [ INFO]: --- INIT SEEDS --- (pipeline.py:249)
[2025-10-26 02:40:30,505] [ INFO]: --- LOADING TASKS --- (pipeline.py:210)
[2025-10-26 02:40:30,508] [ WARNING]: Careful, the task math_500 is using evaluation data to build the few shot examples. (lighteval_task.py:269)
[2025-10-26 02:40:34,976] [ INFO]: --- LOADING MODEL --- (pipeline.py:177)
`torch_dtype` is deprecated! Use `dtype` instead!
[2025-10-26 02:40:41,447] [ INFO]: Using max model len 32768 (config.py:1604)
[2025-10-26 02:40:41,951] [ INFO]: Chunked prefill is enabled with max_num_batched_tokens=2048. (config.py:2434)
INFO 10-26 02:40:46 [__init__.py:235] Automatically detected platform cuda.
INFO 10-26 02:40:47 [core.py:572] Waiting for init message from front-end.
INFO 10-26 02:40:47 [core.py:71] Initializing a V1 LLM engine (v0.10.0) with config: model='/mnt/public/wucanhui/outputs/Qwen3-14B-math-reasoning/checkpoint-2562', speculative_config=None, tokenizer='/mnt/public/wucanhui/outputs/Qwen3-14B-math-reasoning/checkpoint-2562', skip_tokenizer_init=False, tokenizer_mode=auto, revision=main, override_neuron_config={}, tokenizer_revision=main, trust_remote_code=False, dtype=torch.bfloat16, max_seq_len=32768, download_dir=None, load_format=LoadFormat.AUTO, tensor_parallel_size=1, pipeline_parallel_size=1, disable_custom_all_reduce=False, quantization=None, enforce_eager=True, kv_cache_dtype=auto, device_config=cuda, decoding_config=DecodingConfig(backend='auto', disable_fallback=False, disable_any_whitespace=False, disable_additional_properties=False, reasoning_backend=''), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None), seed=1234, served_model_name=/mnt/public/wucanhui/outputs/Qwen3-14B-math-reasoning/checkpoint-2562, num_scheduler_steps=1, multi_step_stream_outputs=True, enable_prefix_caching=True, chunked_prefill_enabled=True, use_async_output_proc=True, pooler_config=None, compilation_config={"level":0,"debug_dump_path":"","cache_dir":"","backend":"","custom_ops":[],"splitting_ops":[],"use_inductor":true,"compile_sizes":[],"inductor_compile_config":{"enable_auto_functionalized_v2":false},"inductor_passes":{},"use_cudagraph":true,"cudagraph_num_of_warmups":0,"cudagraph_capture_sizes":[],"cudagraph_copy_inputs":false,"full_cuda_graph":false,"max_capture_size":0,"local_cache_dir":null}
INFO 10-26 02:40:50 [parallel_state.py:1102] rank 0 in world size 1 is assigned as DP rank 0, PP rank 0, TP rank 0, EP rank 0
WARNING 10-26 02:40:50 [topk_topp_sampler.py:59] FlashInfer is not available. Falling back to the PyTorch-native implementation of top-p & top-k sampling. For the best performance, please install FlashInfer.
INFO 10-26 02:40:50 [gpu_model_runner.py:1843] Starting to load model /mnt/public/wucanhui/outputs/Qwen3-14B-math-reasoning/checkpoint-2562...
INFO 10-26 02:40:50 [gpu_model_runner.py:1875] Loading model from scratch...
INFO 10-26 02:40:50 [cuda.py:290] Using Flash Attention backend on V1 engine.
Loading safetensors checkpoint shards: 0% Completed | 0/6 [00:00<?, ?it/s]
Loading safetensors checkpoint shards: 17% Completed | 1/6 [00:36<03:01, 36.20s/it]
Loading safetensors checkpoint shards: 33% Completed | 2/6 [01:14<02:30, 37.72s/it]
Loading safetensors checkpoint shards: 50% Completed | 3/6 [01:50<01:49, 36.62s/it]
Loading safetensors checkpoint shards: 67% Completed | 4/6 [02:24<01:11, 35.85s/it]
Loading safetensors checkpoint shards: 83% Completed | 5/6 [03:01<00:35, 35.95s/it]
Loading safetensors checkpoint shards: 100% Completed | 6/6 [03:35<00:00, 35.39s/it]
Loading safetensors checkpoint shards: 100% Completed | 6/6 [03:35<00:00, 35.90s/it]
INFO 10-26 02:44:27 [default_loader.py:262] Loading weights took 216.40 seconds
INFO 10-26 02:44:27 [gpu_model_runner.py:1892] Model loading took 27.5185 GiB and 217.035510 seconds
INFO 10-26 02:44:28 [gpu_worker.py:255] Available KV cache memory: 97.63 GiB
INFO 10-26 02:44:28 [kv_cache_utils.py:833] GPU KV cache size: 639,792 tokens
INFO 10-26 02:44:28 [kv_cache_utils.py:837] Maximum concurrency for 32,768 tokens per request: 19.52x
INFO 10-26 02:44:29 [core.py:193] init engine (profile, create kv cache, warmup model) took 1.19 seconds
[2025-10-26 02:44:29,515] [ INFO]: [CACHING] Initializing data cache (cache_management.py:105)
[2025-10-26 02:44:29,521] [ INFO]: --- RUNNING MODEL --- (pipeline.py:330)
[2025-10-26 02:44:29,522] [ INFO]: Running SamplingMethod.GENERATIVE requests (pipeline.py:313)
[2025-10-26 02:44:45,633] [ INFO]: Cache: Starting to process 500/500 samples (not found in cache) for tasks lighteval|math_500|0 (3aecc7facae3926c, GENERATIVE) (cache_management.py:399)
[2025-10-26 02:44:45,636] [ WARNING]: You cannot select the number of dataset splits for a generative evaluation at the moment. Automatically inferring. (data.py:206)
Splits: 0%| | 0/1 [00:00<?, ?it/s][2025-10-26 02:44:45,773] [ WARNING]: context_size + max_new_tokens=33645 which is greater than self.max_length=32768. Truncating context to 0 tokens. (vllm_model.py:367)
Adding requests: 0%| | 0/500 [00:00<?, ?it/s]
Adding requests: 19%|β–ˆβ–‰ | 94/500 [00:00<00:01, 338.54it/s] Adding requests: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 500/500 [00:00<00:00, 1544.03it/s]
Processed prompts: 0%| | 0/2000 [00:00<?, ?it/s, est. speed input: 0.00 toks/s, output: 0.00 toks/s]
Processed prompts: 0%| | 4/2000 [00:06<53:11, 1.60s/it, est. speed input: 250.78 toks/s, output: 152.12 toks/s]
Processed prompts: 0%| | 8/2000 [00:12<49:12, 1.48s/it, est. speed input: 207.02 toks/s, output: 235.60 toks/s]
Processed prompts: 1%| | 12/2000 [00:16<42:09, 1.27s/it, est. speed input: 202.85 toks/s, output: 291.03 toks/s]
Processed prompts: 1%| | 16/2000 [00:19<37:15, 1.13s/it, est. speed input: 231.24 toks/s, output: 399.58 toks/s]
Processed prompts: 1%| | 20/2000 [00:24<37:46, 1.14s/it, est. speed input: 238.78 toks/s, output: 473.08 toks/s]
Processed prompts: 1%| | 24/2000 [00:26<29:28, 1.12it/s, est. speed input: 263.79 toks/s, output: 560.59 toks/s]
Processed prompts: 1%|▏ | 28/2000 [00:27<22:31, 1.46it/s, est. speed input: 300.14 toks/s, output: 694.04 toks/s]
Processed prompts: 2%|▏ | 32/2000 [00:35<36:08, 1.10s/it, est. speed input: 256.17 toks/s, output: 619.32 toks/s]
Processed prompts: 2%|▏ | 36/2000 [00:41<40:15, 1.23s/it, est. speed input: 303.83 toks/s, output: 608.55 toks/s]
Processed prompts: 2%|▏ | 40/2000 [00:44<36:20, 1.11s/it, est. speed input: 318.83 toks/s, output: 636.93 toks/s]
Processed prompts: 2%|▏ | 44/2000 [00:44<25:27, 1.28it/s, est. speed input: 336.32 toks/s, output: 677.24 toks/s]
Processed prompts: 2%|▏ | 48/2000 [00:45<19:28, 1.67it/s, est. speed input: 349.82 toks/s, output: 727.46 toks/s]
Processed prompts: 3%|β–Ž | 52/2000 [00:47<19:04, 1.70it/s, est. speed input: 349.49 toks/s, output: 823.31 toks/s]
Processed prompts: 3%|β–Ž | 56/2000 [00:53<27:52, 1.16it/s, est. speed input: 330.08 toks/s, output: 752.69 toks/s]
Processed prompts: 3%|β–Ž | 60/2000 [00:53<20:00, 1.62it/s, est. speed input: 342.68 toks/s, output: 824.11 toks/s]
Processed prompts: 3%|β–Ž | 64/2000 [01:02<35:06, 1.09s/it, est. speed input: 309.49 toks/s, output: 750.27 toks/s]
Processed prompts: 3%|β–Ž | 68/2000 [01:03<26:56, 1.20it/s, est. speed input: 322.67 toks/s, output: 866.73 toks/s]
Processed prompts: 4%|β–Ž | 72/2000 [01:05<22:26, 1.43it/s, est. speed input: 335.83 toks/s, output: 919.70 toks/s]
Processed prompts: 4%|▍ | 76/2000 [01:06<20:00, 1.60it/s, est. speed input: 337.89 toks/s, output: 979.54 toks/s]
Processed prompts: 4%|▍ | 80/2000 [01:08<17:24, 1.84it/s, est. speed input: 348.23 toks/s, output: 1067.83 toks/s]
Processed prompts: 4%|▍ | 84/2000 [01:10<16:37, 1.92it/s, est. speed input: 358.19 toks/s, output: 1170.19 toks/s]
Processed prompts: 4%|▍ | 88/2000 [01:13<19:33, 1.63it/s, est. speed input: 356.18 toks/s, output: 1193.16 toks/s]
Processed prompts: 5%|▍ | 92/2000 [01:14<15:14, 2.09it/s, est. speed input: 376.11 toks/s, output: 1305.41 toks/s]
Processed prompts: 5%|▍ | 96/2000 [01:14<11:26, 2.78it/s, est. speed input: 388.68 toks/s, output: 1396.95 toks/s]
Processed prompts: 5%|β–Œ | 100/2000 [01:14<08:55, 3.55it/s, est. speed input: 400.54 toks/s, output: 1444.53 toks/s]
Processed prompts: 5%|β–Œ | 104/2000 [01:14<06:33, 4.82it/s, est. speed input: 408.72 toks/s, output: 1454.87 toks/s]
Processed prompts: 5%|β–Œ | 108/2000 [01:16<07:42, 4.09it/s, est. speed input: 415.90 toks/s, output: 1461.20 toks/s]
Processed prompts: 6%|β–Œ | 112/2000 [01:16<07:04, 4.45it/s, est. speed input: 440.41 toks/s, output: 1582.36 toks/s]
Processed prompts: 6%|β–Œ | 116/2000 [01:17<05:31, 5.69it/s, est. speed input: 454.95 toks/s, output: 1661.43 toks/s]
Processed prompts: 6%|β–Œ | 120/2000 [01:19<08:53, 3.52it/s, est. speed input: 451.88 toks/s, output: 1646.44 toks/s]
Processed prompts: 6%|β–Œ | 124/2000 [01:19<06:37, 4.72it/s, est. speed input: 466.41 toks/s, output: 1737.67 toks/s]
Processed prompts: 6%|β–‹ | 128/2000 [01:21<09:30, 3.28it/s, est. speed input: 462.53 toks/s, output: 1710.89 toks/s]
Processed prompts: 7%|β–‹ | 132/2000 [01:31<30:11, 1.03it/s, est. speed input: 418.92 toks/s, output: 1538.05 toks/s]
Processed prompts: 7%|β–‹ | 136/2000 [01:35<29:02, 1.07it/s, est. speed input: 410.90 toks/s, output: 1498.45 toks/s]
Processed prompts: 7%|β–‹ | 140/2000 [01:39<30:57, 1.00it/s, est. speed input: 399.22 toks/s, output: 1476.93 toks/s]
Processed prompts: 7%|β–‹ | 144/2000 [01:41<24:39, 1.25it/s, est. speed input: 400.70 toks/s, output: 1483.85 toks/s]
Processed prompts: 7%|β–‹ | 148/2000 [01:41<19:24, 1.59it/s, est. speed input: 403.31 toks/s, output: 1481.55 toks/s]
Processed prompts: 8%|β–Š | 152/2000 [01:42<14:01, 2.19it/s, est. speed input: 411.85 toks/s, output: 1593.00 toks/s]
Processed prompts: 8%|β–Š | 156/2000 [01:44<15:01, 2.05it/s, est. speed input: 408.67 toks/s, output: 1570.19 toks/s]
Processed prompts: 8%|β–Š | 160/2000 [01:44<10:51, 2.83it/s, est. speed input: 417.00 toks/s, output: 1599.96 toks/s]
Processed prompts: 8%|β–Š | 164/2000 [01:51<23:35, 1.30it/s, est. speed input: 402.41 toks/s, output: 1628.30 toks/s]
Processed prompts: 8%|β–Š | 168/2000 [01:56<27:02, 1.13it/s, est. speed input: 392.10 toks/s, output: 1589.13 toks/s]
Processed prompts: 9%|β–Š | 172/2000 [01:57<21:19, 1.43it/s, est. speed input: 398.39 toks/s, output: 1658.06 toks/s]
Processed prompts: 9%|β–‰ | 176/2000 [02:04<30:42, 1.01s/it, est. speed input: 381.21 toks/s, output: 1583.34 toks/s]
Processed prompts: 9%|β–‰ | 180/2000 [02:04<22:09, 1.37it/s, est. speed input: 388.60 toks/s, output: 1599.25 toks/s]
Processed prompts: 9%|β–‰ | 184/2000 [02:12<34:15, 1.13s/it, est. speed input: 369.72 toks/s, output: 1535.08 toks/s]
Processed prompts: 9%|β–‰ | 188/2000 [02:15<30:13, 1.00s/it, est. speed input: 366.60 toks/s, output: 1515.81 toks/s]
Processed prompts: 10%|β–‰ | 192/2000 [02:16<22:31, 1.34it/s, est. speed input: 372.11 toks/s, output: 1632.66 toks/s]
Processed prompts: 10%|β–‰ | 196/2000 [02:18<20:00, 1.50it/s, est. speed input: 371.81 toks/s, output: 1618.05 toks/s]
Processed prompts: 10%|β–ˆ | 200/2000 [02:20<19:22, 1.55it/s, est. speed input: 371.06 toks/s, output: 1597.18 toks/s]
Processed prompts: 10%|β–ˆ | 204/2000 [02:21<15:04, 1.99it/s, est. speed input: 376.74 toks/s, output: 1643.41 toks/s]
Processed prompts: 10%|β–ˆ | 208/2000 [02:35<42:54, 1.44s/it, est. speed input: 346.66 toks/s, output: 1524.14 toks/s]
Processed prompts: 11%|β–ˆ | 212/2000 [02:36<31:10, 1.05s/it, est. speed input: 349.65 toks/s, output: 1535.51 toks/s]
Processed prompts: 11%|β–ˆ | 216/2000 [02:41<34:01, 1.14s/it, est. speed input: 342.84 toks/s, output: 1523.42 toks/s]
Processed prompts: 11%|β–ˆ | 220/2000 [02:47<36:34, 1.23s/it, est. speed input: 336.86 toks/s, output: 1535.15 toks/s]
Processed prompts: 11%|β–ˆ | 224/2000 [02:48<28:30, 1.04it/s, est. speed input: 339.15 toks/s, output: 1543.70 toks/s]
Processed prompts: 11%|β–ˆβ– | 228/2000 [02:50<23:51, 1.24it/s, est. speed input: 339.53 toks/s, output: 1534.09 toks/s]
Processed prompts: 12%|β–ˆβ– | 232/2000 [02:55<27:37, 1.07it/s, est. speed input: 337.50 toks/s, output: 1582.00 toks/s]
Processed prompts: 12%|β–ˆβ– | 236/2000 [02:56<22:15, 1.32it/s, est. speed input: 338.30 toks/s, output: 1581.45 toks/s]
Processed prompts: 12%|β–ˆβ– | 240/2000 [03:00<22:34, 1.30it/s, est. speed input: 336.74 toks/s, output: 1610.18 toks/s]
Processed prompts: 12%|β–ˆβ– | 244/2000 [03:04<25:44, 1.14it/s, est. speed input: 331.63 toks/s, output: 1583.08 toks/s]
Processed prompts: 12%|β–ˆβ– | 248/2000 [03:06<21:25, 1.36it/s, est. speed input: 331.96 toks/s, output: 1585.75 toks/s]
Processed prompts: 13%|β–ˆβ–Ž | 252/2000 [03:06<16:44, 1.74it/s, est. speed input: 335.01 toks/s, output: 1591.92 toks/s]
Processed prompts: 13%|β–ˆβ–Ž | 256/2000 [03:09<17:52, 1.63it/s, est. speed input: 334.39 toks/s, output: 1610.18 toks/s]
Processed prompts: 13%|β–ˆβ–Ž | 260/2000 [03:11<16:57, 1.71it/s, est. speed input: 334.03 toks/s, output: 1604.18 toks/s]
Processed prompts: 13%|β–ˆβ–Ž | 264/2000 [03:14<18:04, 1.60it/s, est. speed input: 333.05 toks/s, output: 1592.07 toks/s]
Processed prompts: 13%|β–ˆβ–Ž | 268/2000 [03:15<14:06, 2.05it/s, est. speed input: 334.84 toks/s, output: 1591.62 toks/s]
Processed prompts: 14%|β–ˆβ–Ž | 272/2000 [03:32<47:24, 1.65s/it, est. speed input: 311.07 toks/s, output: 1498.52 toks/s]
Processed prompts: 14%|β–ˆβ– | 276/2000 [03:32<33:30, 1.17s/it, est. speed input: 316.06 toks/s, output: 1579.83 toks/s]
Processed prompts: 14%|β–ˆβ– | 284/2000 [03:38<26:25, 1.08it/s, est. speed input: 314.33 toks/s, output: 1554.96 toks/s]
Processed prompts: 14%|β–ˆβ– | 288/2000 [03:43<28:43, 1.01s/it, est. speed input: 309.91 toks/s, output: 1525.92 toks/s]
Processed prompts: 15%|β–ˆβ– | 292/2000 [03:45<25:25, 1.12it/s, est. speed input: 309.32 toks/s, output: 1545.25 toks/s]
Processed prompts: 15%|β–ˆβ– | 296/2000 [03:50<27:35, 1.03it/s, est. speed input: 306.03 toks/s, output: 1521.19 toks/s]
Processed prompts: 15%|β–ˆβ–Œ | 300/2000 [03:50<20:28, 1.38it/s, est. speed input: 309.89 toks/s, output: 1579.88 toks/s]
Processed prompts: 15%|β–ˆβ–Œ | 304/2000 [03:50<15:07, 1.87it/s, est. speed input: 312.54 toks/s, output: 1599.35 toks/s]
Processed prompts: 15%|β–ˆβ–Œ | 308/2000 [03:51<13:10, 2.14it/s, est. speed input: 313.64 toks/s, output: 1599.43 toks/s]
Processed prompts: 16%|β–ˆβ–Œ | 312/2000 [03:55<16:18, 1.73it/s, est. speed input: 312.49 toks/s, output: 1584.71 toks/s]
Processed prompts: 16%|β–ˆβ–Œ | 316/2000 [03:58<16:58, 1.65it/s, est. speed input: 311.68 toks/s, output: 1583.66 toks/s]
Processed prompts: 16%|β–ˆβ–Œ | 320/2000 [04:02<21:07, 1.33it/s, est. speed input: 308.63 toks/s, output: 1559.88 toks/s]
Processed prompts: 16%|β–ˆβ–Œ | 324/2000 [04:02<15:53, 1.76it/s, est. speed input: 320.91 toks/s, output: 1656.12 toks/s]
Processed prompts: 16%|β–ˆβ–‹ | 328/2000 [04:06<17:39, 1.58it/s, est. speed input: 319.08 toks/s, output: 1640.77 toks/s]
Processed prompts: 17%|β–ˆβ–‹ | 332/2000 [04:08<17:57, 1.55it/s, est. speed input: 318.85 toks/s, output: 1652.23 toks/s]
Processed prompts: 17%|β–ˆβ–‹ | 336/2000 [04:09<13:37, 2.04it/s, est. speed input: 322.07 toks/s, output: 1733.10 toks/s]
Processed prompts: 17%|β–ˆβ–‹ | 340/2000 [04:12<16:05, 1.72it/s, est. speed input: 329.96 toks/s, output: 1826.91 toks/s]
Processed prompts: 17%|β–ˆβ–‹ | 344/2000 [04:13<13:22, 2.06it/s, est. speed input: 331.03 toks/s, output: 1824.01 toks/s]
Processed prompts: 17%|β–ˆβ–‹ | 348/2000 [04:21<25:19, 1.09it/s, est. speed input: 325.96 toks/s, output: 1858.60 toks/s]
Processed prompts: 18%|β–ˆβ–Š | 352/2000 [04:24<24:49, 1.11it/s, est. speed input: 323.80 toks/s, output: 1838.34 toks/s]
Processed prompts: 18%|β–ˆβ–Š | 356/2000 [04:28<25:42, 1.07it/s, est. speed input: 321.38 toks/s, output: 1841.31 toks/s]
Processed prompts: 18%|β–ˆβ–Š | 360/2000 [04:34<29:27, 1.08s/it, est. speed input: 316.99 toks/s, output: 1808.49 toks/s]
Processed prompts: 18%|β–ˆβ–Š | 364/2000 [04:35<21:50, 1.25it/s, est. speed input: 318.56 toks/s, output: 1809.25 toks/s]
Processed prompts: 18%|β–ˆβ–Š | 368/2000 [04:36<19:09, 1.42it/s, est. speed input: 319.27 toks/s, output: 1810.90 toks/s]
Processed prompts: 19%|β–ˆβ–Š | 372/2000 [04:38<16:50, 1.61it/s, est. speed input: 321.81 toks/s, output: 1876.38 toks/s]
Processed prompts: 19%|β–ˆβ–‰ | 376/2000 [04:39<14:05, 1.92it/s, est. speed input: 322.93 toks/s, output: 1876.93 toks/s]
Processed prompts: 19%|β–ˆβ–‰ | 380/2000 [04:46<23:56, 1.13it/s, est. speed input: 317.18 toks/s, output: 1844.00 toks/s]
Processed prompts: 19%|β–ˆβ–‰ | 384/2000 [04:47<19:03, 1.41it/s, est. speed input: 317.96 toks/s, output: 1840.32 toks/s]
Processed prompts: 19%|β–ˆβ–‰ | 388/2000 [04:53<25:13, 1.07it/s, est. speed input: 314.67 toks/s, output: 1846.02 toks/s]
Processed prompts: 20%|β–ˆβ–‰ | 392/2000 [04:59<29:01, 1.08s/it, est. speed input: 310.65 toks/s, output: 1834.56 toks/s]
Processed prompts: 20%|β–ˆβ–‰ | 396/2000 [05:04<30:35, 1.14s/it, est. speed input: 311.10 toks/s, output: 1890.47 toks/s]
Processed prompts: 20%|β–ˆβ–ˆ | 400/2000 [05:10<33:34, 1.26s/it, est. speed input: 307.11 toks/s, output: 1872.53 toks/s]
Processed prompts: 20%|β–ˆβ–ˆ | 404/2000 [05:18<37:58, 1.43s/it, est. speed input: 301.92 toks/s, output: 1832.08 toks/s]
Processed prompts: 20%|β–ˆβ–ˆ | 408/2000 [05:22<34:45, 1.31s/it, est. speed input: 300.81 toks/s, output: 1864.38 toks/s]
Processed prompts: 21%|β–ˆβ–ˆ | 412/2000 [05:33<47:15, 1.79s/it, est. speed input: 292.61 toks/s, output: 1818.59 toks/s]
Processed prompts: 21%|β–ˆβ–ˆ | 416/2000 [05:36<39:03, 1.48s/it, est. speed input: 293.88 toks/s, output: 1903.04 toks/s]
Processed prompts: 21%|β–ˆβ–ˆ | 420/2000 [05:46<47:07, 1.79s/it, est. speed input: 286.92 toks/s, output: 1852.69 toks/s]
Processed prompts: 21%|β–ˆβ–ˆ | 424/2000 [05:47<34:42, 1.32s/it, est. speed input: 287.74 toks/s, output: 1851.39 toks/s]
Processed prompts: 21%|β–ˆβ–ˆβ– | 428/2000 [05:50<30:17, 1.16s/it, est. speed input: 287.26 toks/s, output: 1853.75 toks/s]
Processed prompts: 22%|β–ˆβ–ˆβ– | 432/2000 [06:00<39:08, 1.50s/it, est. speed input: 281.99 toks/s, output: 1869.26 toks/s]
Processed prompts: 22%|β–ˆβ–ˆβ– | 436/2000 [06:02<31:42, 1.22s/it, est. speed input: 282.85 toks/s, output: 1919.26 toks/s]
Processed prompts: 22%|β–ˆβ–ˆβ– | 440/2000 [06:04<26:55, 1.04s/it, est. speed input: 284.13 toks/s, output: 1994.20 toks/s]
Processed prompts: 22%|β–ˆβ–ˆβ– | 444/2000 [06:09<27:43, 1.07s/it, est. speed input: 282.57 toks/s, output: 1984.79 toks/s]
Processed prompts: 22%|β–ˆβ–ˆβ– | 448/2000 [06:11<23:44, 1.09it/s, est. speed input: 282.47 toks/s, output: 1981.85 toks/s]
Processed prompts: 23%|β–ˆβ–ˆβ–Ž | 452/2000 [06:16<25:09, 1.03it/s, est. speed input: 280.78 toks/s, output: 1965.89 toks/s]
Processed prompts: 23%|β–ˆβ–ˆβ–Ž | 456/2000 [06:16<17:48, 1.45it/s, est. speed input: 282.55 toks/s, output: 1986.99 toks/s]
Processed prompts: 23%|β–ˆβ–ˆβ–Ž | 460/2000 [06:22<25:25, 1.01it/s, est. speed input: 279.24 toks/s, output: 1959.77 toks/s]
Processed prompts: 23%|β–ˆβ–ˆβ–Ž | 464/2000 [06:26<24:13, 1.06it/s, est. speed input: 278.44 toks/s, output: 1961.43 toks/s]
Processed prompts: 23%|β–ˆβ–ˆβ–Ž | 468/2000 [06:27<18:15, 1.40it/s, est. speed input: 279.34 toks/s, output: 1961.63 toks/s]
Processed prompts: 24%|β–ˆβ–ˆβ–Ž | 472/2000 [06:27<14:11, 1.79it/s, est. speed input: 280.60 toks/s, output: 1998.22 toks/s]
Processed prompts: 24%|β–ˆβ–ˆβ– | 476/2000 [06:34<23:27, 1.08it/s, est. speed input: 277.30 toks/s, output: 2007.39 toks/s]
Processed prompts: 24%|β–ˆβ–ˆβ– | 484/2000 [06:36<14:26, 1.75it/s, est. speed input: 279.67 toks/s, output: 2056.68 toks/s]
Processed prompts: 24%|β–ˆβ–ˆβ– | 488/2000 [06:39<15:41, 1.61it/s, est. speed input: 279.15 toks/s, output: 2048.23 toks/s]
Processed prompts: 25%|β–ˆβ–ˆβ– | 492/2000 [06:41<15:33, 1.62it/s, est. speed input: 279.16 toks/s, output: 2060.78 toks/s]
Processed prompts: 25%|β–ˆβ–ˆβ– | 496/2000 [06:42<13:14, 1.89it/s, est. speed input: 281.13 toks/s, output: 2145.14 toks/s]
Processed prompts: 25%|β–ˆβ–ˆβ–Œ | 500/2000 [06:44<12:36, 1.98it/s, est. speed input: 283.45 toks/s, output: 2245.18 toks/s]
Processed prompts: 25%|β–ˆβ–ˆβ–Œ | 504/2000 [06:46<12:34, 1.98it/s, est. speed input: 283.38 toks/s, output: 2238.29 toks/s]
Processed prompts: 25%|β–ˆβ–ˆβ–Œ | 508/2000 [06:49<13:35, 1.83it/s, est. speed input: 283.38 toks/s, output: 2229.21 toks/s]
Processed prompts: 26%|β–ˆβ–ˆβ–Œ | 516/2000 [06:52<12:10, 2.03it/s, est. speed input: 283.85 toks/s, output: 2226.62 toks/s]
Processed prompts: 26%|β–ˆβ–ˆβ–Œ | 520/2000 [07:01<22:28, 1.10it/s, est. speed input: 279.13 toks/s, output: 2183.85 toks/s]
Processed prompts: 26%|β–ˆβ–ˆβ–Œ | 524/2000 [07:02<18:22, 1.34it/s, est. speed input: 279.82 toks/s, output: 2185.82 toks/s]
Processed prompts: 26%|β–ˆβ–ˆβ–‹ | 528/2000 [07:03<14:26, 1.70it/s, est. speed input: 280.59 toks/s, output: 2185.06 toks/s]
Processed prompts: 27%|β–ˆβ–ˆβ–‹ | 536/2000 [07:11<19:41, 1.24it/s, est. speed input: 277.44 toks/s, output: 2149.81 toks/s]
Processed prompts: 27%|β–ˆβ–ˆβ–‹ | 540/2000 [07:13<17:49, 1.37it/s, est. speed input: 277.99 toks/s, output: 2151.35 toks/s]
Processed prompts: 27%|β–ˆβ–ˆβ–‹ | 544/2000 [07:15<16:00, 1.52it/s, est. speed input: 278.52 toks/s, output: 2152.48 toks/s]
Processed prompts: 27%|β–ˆβ–ˆβ–‹ | 548/2000 [07:17<14:51, 1.63it/s, est. speed input: 279.90 toks/s, output: 2215.88 toks/s]
Processed prompts: 28%|β–ˆβ–ˆβ–Š | 552/2000 [07:20<15:19, 1.58it/s, est. speed input: 279.56 toks/s, output: 2207.50 toks/s]
Processed prompts: 28%|β–ˆβ–ˆβ–Š | 556/2000 [07:23<16:39, 1.45it/s, est. speed input: 278.58 toks/s, output: 2193.54 toks/s]
Processed prompts: 28%|β–ˆβ–ˆβ–Š | 560/2000 [07:24<12:26, 1.93it/s, est. speed input: 279.73 toks/s, output: 2196.94 toks/s]
Processed prompts: 28%|β–ˆβ–ˆβ–Š | 564/2000 [07:37<31:13, 1.30s/it, est. speed input: 273.13 toks/s, output: 2139.13 toks/s]
Processed prompts: 28%|β–ˆβ–ˆβ–Š | 568/2000 [07:54<51:56, 2.18s/it, est. speed input: 264.46 toks/s, output: 2067.31 toks/s]
Processed prompts: 29%|β–ˆβ–ˆβ–Š | 572/2000 [07:55<38:03, 1.60s/it, est. speed input: 265.58 toks/s, output: 2110.88 toks/s]
Processed prompts: 29%|β–ˆβ–ˆβ–‰ | 576/2000 [07:55<28:03, 1.18s/it, est. speed input: 266.28 toks/s, output: 2111.63 toks/s]
Processed prompts: 29%|β–ˆβ–ˆβ–‰ | 580/2000 [07:56<20:29, 1.15it/s, est. speed input: 267.08 toks/s, output: 2113.36 toks/s]
Processed prompts: 29%|β–ˆβ–ˆβ–‰ | 584/2000 [07:57<16:45, 1.41it/s, est. speed input: 267.81 toks/s, output: 2132.53 toks/s]
Processed prompts: 29%|β–ˆβ–ˆβ–‰ | 588/2000 [08:00<16:37, 1.42it/s, est. speed input: 267.52 toks/s, output: 2129.85 toks/s]
Processed prompts: 30%|β–ˆβ–ˆβ–‰ | 592/2000 [08:06<22:30, 1.04it/s, est. speed input: 265.18 toks/s, output: 2104.46 toks/s]
Processed prompts: 30%|β–ˆβ–ˆβ–‰ | 596/2000 [08:07<16:55, 1.38it/s, est. speed input: 266.21 toks/s, output: 2132.50 toks/s]
Processed prompts: 30%|β–ˆβ–ˆβ–ˆ | 600/2000 [08:08<14:01, 1.66it/s, est. speed input: 266.80 toks/s, output: 2130.26 toks/s]
Processed prompts: 30%|β–ˆβ–ˆβ–ˆ | 604/2000 [08:09<11:13, 2.07it/s, est. speed input: 267.49 toks/s, output: 2139.76 toks/s]
Processed prompts: 30%|β–ˆβ–ˆβ–ˆ | 608/2000 [08:14<16:22, 1.42it/s, est. speed input: 265.84 toks/s, output: 2124.85 toks/s]
Processed prompts: 31%|β–ˆβ–ˆβ–ˆ | 612/2000 [08:15<13:13, 1.75it/s, est. speed input: 266.57 toks/s, output: 2126.43 toks/s]
Processed prompts: 31%|β–ˆβ–ˆβ–ˆ | 616/2000 [08:15<09:41, 2.38it/s, est. speed input: 267.56 toks/s, output: 2127.09 toks/s]
Processed prompts: 31%|β–ˆβ–ˆβ–ˆ | 620/2000 [08:17<09:52, 2.33it/s, est. speed input: 267.94 toks/s, output: 2127.73 toks/s]
Processed prompts: 31%|β–ˆβ–ˆβ–ˆ | 624/2000 [08:18<08:48, 2.60it/s, est. speed input: 268.84 toks/s, output: 2145.69 toks/s]
Processed prompts: 31%|β–ˆβ–ˆβ–ˆβ– | 628/2000 [08:19<08:03, 2.84it/s, est. speed input: 270.06 toks/s, output: 2173.91 toks/s]
Processed prompts: 32%|β–ˆβ–ˆβ–ˆβ– | 632/2000 [08:21<08:00, 2.85it/s, est. speed input: 270.32 toks/s, output: 2169.91 toks/s]
Processed prompts: 32%|β–ˆβ–ˆβ–ˆβ– | 636/2000 [08:29<20:05, 1.13it/s, est. speed input: 267.08 toks/s, output: 2144.95 toks/s]
Processed prompts: 32%|β–ˆβ–ˆβ–ˆβ– | 640/2000 [08:29<14:35, 1.55it/s, est. speed input: 268.08 toks/s, output: 2191.59 toks/s]
Processed prompts: 32%|β–ˆβ–ˆβ–ˆβ– | 644/2000 [08:33<16:32, 1.37it/s, est. speed input: 267.41 toks/s, output: 2183.48 toks/s]
Processed prompts: 32%|β–ˆβ–ˆβ–ˆβ– | 648/2000 [08:34<12:51, 1.75it/s, est. speed input: 268.30 toks/s, output: 2219.46 toks/s]
Processed prompts: 33%|β–ˆβ–ˆβ–ˆβ–Ž | 652/2000 [08:35<10:57, 2.05it/s, est. speed input: 268.89 toks/s, output: 2218.43 toks/s]
Processed prompts: 33%|β–ˆβ–ˆβ–ˆβ–Ž | 656/2000 [08:36<09:14, 2.42it/s, est. speed input: 269.74 toks/s, output: 2251.91 toks/s]
Processed prompts: 33%|β–ˆβ–ˆβ–ˆβ–Ž | 660/2000 [08:38<09:51, 2.27it/s, est. speed input: 269.65 toks/s, output: 2252.20 toks/s]
Processed prompts: 33%|β–ˆβ–ˆβ–ˆβ–Ž | 664/2000 [08:39<08:15, 2.69it/s, est. speed input: 270.14 toks/s, output: 2250.18 toks/s]
Processed prompts: 33%|β–ˆβ–ˆβ–ˆβ–Ž | 668/2000 [08:41<09:27, 2.35it/s, est. speed input: 270.76 toks/s, output: 2345.83 toks/s]
Processed prompts: 34%|β–ˆβ–ˆβ–ˆβ–Ž | 672/2000 [08:43<09:02, 2.45it/s, est. speed input: 271.61 toks/s, output: 2363.30 toks/s]
Processed prompts: 34%|β–ˆβ–ˆβ–ˆβ– | 676/2000 [08:47<12:54, 1.71it/s, est. speed input: 270.53 toks/s, output: 2346.96 toks/s]
Processed prompts: 34%|β–ˆβ–ˆβ–ˆβ– | 684/2000 [08:47<07:05, 3.09it/s, est. speed input: 272.52 toks/s, output: 2357.43 toks/s]
Processed prompts: 34%|β–ˆβ–ˆβ–ˆβ– | 688/2000 [08:48<06:50, 3.20it/s, est. speed input: 272.97 toks/s, output: 2354.65 toks/s]
Processed prompts: 35%|β–ˆβ–ˆβ–ˆβ– | 692/2000 [08:49<07:04, 3.08it/s, est. speed input: 273.54 toks/s, output: 2360.98 toks/s]
Processed prompts: 35%|β–ˆβ–ˆβ–ˆβ– | 696/2000 [08:49<05:17, 4.11it/s, est. speed input: 274.67 toks/s, output: 2382.42 toks/s]
Processed prompts: 35%|β–ˆβ–ˆβ–ˆβ–Œ | 700/2000 [08:52<08:01, 2.70it/s, est. speed input: 274.27 toks/s, output: 2373.53 toks/s]
Processed prompts: 35%|β–ˆβ–ˆβ–ˆβ–Œ | 704/2000 [08:54<07:58, 2.71it/s, est. speed input: 274.48 toks/s, output: 2371.75 toks/s]
Processed prompts: 35%|β–ˆβ–ˆβ–ˆβ–Œ | 708/2000 [08:56<09:20, 2.30it/s, est. speed input: 275.98 toks/s, output: 2454.46 toks/s]
Processed prompts: 36%|β–ˆβ–ˆβ–ˆβ–Œ | 712/2000 [08:57<08:53, 2.42it/s, est. speed input: 276.28 toks/s, output: 2475.03 toks/s]
Processed prompts: 36%|β–ˆβ–ˆβ–ˆβ–Œ | 716/2000 [09:00<09:28, 2.26it/s, est. speed input: 276.27 toks/s, output: 2471.43 toks/s]
Processed prompts: 36%|β–ˆβ–ˆβ–ˆβ–Œ | 720/2000 [09:06<17:05, 1.25it/s, est. speed input: 273.83 toks/s, output: 2444.82 toks/s]
Processed prompts: 36%|β–ˆβ–ˆβ–ˆβ–Œ | 724/2000 [09:07<13:09, 1.62it/s, est. speed input: 274.50 toks/s, output: 2447.98 toks/s]
Processed prompts: 36%|β–ˆβ–ˆβ–ˆβ–‹ | 728/2000 [09:09<12:11, 1.74it/s, est. speed input: 274.59 toks/s, output: 2442.26 toks/s]
Processed prompts: 37%|β–ˆβ–ˆβ–ˆβ–‹ | 732/2000 [09:09<09:18, 2.27it/s, est. speed input: 275.37 toks/s, output: 2443.12 toks/s]
Processed prompts: 37%|β–ˆβ–ˆβ–ˆβ–‹ | 736/2000 [09:12<11:21, 1.85it/s, est. speed input: 275.17 toks/s, output: 2470.61 toks/s]
Processed prompts: 37%|β–ˆβ–ˆβ–ˆβ–‹ | 740/2000 [09:15<12:24, 1.69it/s, est. speed input: 274.96 toks/s, output: 2504.64 toks/s]
Processed prompts: 37%|β–ˆβ–ˆβ–ˆβ–‹ | 744/2000 [09:16<10:04, 2.08it/s, est. speed input: 275.47 toks/s, output: 2502.28 toks/s]
Processed prompts: 37%|β–ˆβ–ˆβ–ˆβ–‹ | 748/2000 [09:17<08:42, 2.40it/s, est. speed input: 275.82 toks/s, output: 2500.60 toks/s]
Processed prompts: 38%|β–ˆβ–ˆβ–ˆβ–Š | 752/2000 [09:34<32:52, 1.58s/it, est. speed input: 268.69 toks/s, output: 2431.04 toks/s]
Processed prompts: 38%|β–ˆβ–ˆβ–ˆβ–Š | 756/2000 [09:36<25:27, 1.23s/it, est. speed input: 268.90 toks/s, output: 2431.00 toks/s]
Processed prompts: 38%|β–ˆβ–ˆβ–ˆβ–Š | 760/2000 [09:36<18:14, 1.13it/s, est. speed input: 269.80 toks/s, output: 2445.49 toks/s]
Processed prompts: 38%|β–ˆβ–ˆβ–ˆβ–Š | 764/2000 [09:41<20:42, 1.00s/it, est. speed input: 268.33 toks/s, output: 2428.43 toks/s]
Processed prompts: 38%|β–ˆβ–ˆβ–ˆβ–Š | 768/2000 [09:42<14:47, 1.39it/s, est. speed input: 269.26 toks/s, output: 2442.78 toks/s]
Processed prompts: 39%|β–ˆβ–ˆβ–ˆβ–Š | 772/2000 [09:47<17:53, 1.14it/s, est. speed input: 267.85 toks/s, output: 2424.21 toks/s]
Processed prompts: 39%|β–ˆβ–ˆβ–ˆβ–‰ | 776/2000 [09:49<16:01, 1.27it/s, est. speed input: 267.70 toks/s, output: 2416.20 toks/s]
Processed prompts: 39%|β–ˆβ–ˆβ–ˆβ–‰ | 780/2000 [09:49<11:55, 1.71it/s, est. speed input: 268.39 toks/s, output: 2419.50 toks/s]
Processed prompts: 39%|β–ˆβ–ˆβ–ˆβ–‰ | 784/2000 [09:50<08:42, 2.33it/s, est. speed input: 270.21 toks/s, output: 2493.58 toks/s]
Processed prompts: 39%|β–ˆβ–ˆβ–ˆβ–‰ | 788/2000 [09:50<07:13, 2.80it/s, est. speed input: 271.03 toks/s, output: 2502.96 toks/s]
Processed prompts: 40%|β–ˆβ–ˆβ–ˆβ–‰ | 792/2000 [09:51<06:27, 3.11it/s, est. speed input: 271.43 toks/s, output: 2502.81 toks/s]
Processed prompts: 40%|β–ˆβ–ˆβ–ˆβ–‰ | 796/2000 [09:57<13:37, 1.47it/s, est. speed input: 269.48 toks/s, output: 2478.97 toks/s]
Processed prompts: 40%|β–ˆβ–ˆβ–ˆβ–ˆ | 800/2000 [10:01<14:50, 1.35it/s, est. speed input: 268.68 toks/s, output: 2467.45 toks/s]
Processed prompts: 40%|β–ˆβ–ˆβ–ˆβ–ˆ | 804/2000 [10:02<11:30, 1.73it/s, est. speed input: 269.18 toks/s, output: 2466.95 toks/s]
Processed prompts: 40%|β–ˆβ–ˆβ–ˆβ–ˆ | 808/2000 [10:02<08:58, 2.22it/s, est. speed input: 269.83 toks/s, output: 2471.15 toks/s]
Processed prompts: 41%|β–ˆβ–ˆβ–ˆβ–ˆ | 812/2000 [10:05<10:38, 1.86it/s, est. speed input: 269.44 toks/s, output: 2464.69 toks/s]
Processed prompts: 41%|β–ˆβ–ˆβ–ˆβ–ˆ | 816/2000 [10:06<08:01, 2.46it/s, est. speed input: 270.31 toks/s, output: 2473.93 toks/s]
Processed prompts: 41%|β–ˆβ–ˆβ–ˆβ–ˆ | 820/2000 [10:15<18:47, 1.05it/s, est. speed input: 267.41 toks/s, output: 2448.04 toks/s]
Processed prompts: 41%|β–ˆβ–ˆβ–ˆβ–ˆ | 824/2000 [10:16<15:31, 1.26it/s, est. speed input: 267.66 toks/s, output: 2447.16 toks/s]
Processed prompts: 41%|β–ˆβ–ˆβ–ˆβ–ˆβ– | 828/2000 [10:21<18:06, 1.08it/s, est. speed input: 266.54 toks/s, output: 2458.90 toks/s]
Processed prompts: 42%|β–ˆβ–ˆβ–ˆβ–ˆβ– | 832/2000 [10:22<12:57, 1.50it/s, est. speed input: 267.37 toks/s, output: 2470.31 toks/s]
Processed prompts: 42%|β–ˆβ–ˆβ–ˆβ–ˆβ– | 836/2000 [10:25<14:40, 1.32it/s, est. speed input: 266.80 toks/s, output: 2478.04 toks/s]
Processed prompts: 42%|β–ˆβ–ˆβ–ˆβ–ˆβ– | 840/2000 [10:30<16:15, 1.19it/s, est. speed input: 265.81 toks/s, output: 2463.99 toks/s]
Processed prompts: 42%|β–ˆβ–ˆβ–ˆβ–ˆβ– | 844/2000 [10:36<20:50, 1.08s/it, est. speed input: 263.83 toks/s, output: 2446.94 toks/s]
Processed prompts: 42%|β–ˆβ–ˆβ–ˆβ–ˆβ– | 848/2000 [10:39<18:37, 1.03it/s, est. speed input: 263.66 toks/s, output: 2452.50 toks/s]
Processed prompts: 43%|β–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 852/2000 [10:42<16:51, 1.14it/s, est. speed input: 263.48 toks/s, output: 2454.39 toks/s]
Processed prompts: 43%|β–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 856/2000 [10:48<20:18, 1.06s/it, est. speed input: 262.02 toks/s, output: 2484.81 toks/s]
Processed prompts: 43%|β–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 860/2000 [10:55<23:58, 1.26s/it, est. speed input: 260.70 toks/s, output: 2557.21 toks/s]
Processed prompts: 43%|β–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 864/2000 [10:55<17:45, 1.07it/s, est. speed input: 261.26 toks/s, output: 2567.66 toks/s]
Processed prompts: 43%|β–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 868/2000 [10:59<17:42, 1.07it/s, est. speed input: 260.94 toks/s, output: 2619.34 toks/s]
Processed prompts: 44%|β–ˆβ–ˆβ–ˆβ–ˆβ– | 876/2000 [10:59<09:47, 1.91it/s, est. speed input: 262.62 toks/s, output: 2647.32 toks/s]
Processed prompts: 44%|β–ˆβ–ˆβ–ˆβ–ˆβ– | 880/2000 [10:59<07:31, 2.48it/s, est. speed input: 263.56 toks/s, output: 2672.45 toks/s]
Processed prompts: 44%|β–ˆβ–ˆβ–ˆβ–ˆβ– | 884/2000 [11:00<06:47, 2.74it/s, est. speed input: 264.13 toks/s, output: 2687.94 toks/s]
Processed prompts: 44%|β–ˆβ–ˆβ–ˆβ–ˆβ– | 888/2000 [11:04<09:41, 1.91it/s, est. speed input: 263.80 toks/s, output: 2695.26 toks/s]
Processed prompts: 45%|β–ˆβ–ˆβ–ˆβ–ˆβ– | 892/2000 [11:04<07:08, 2.59it/s, est. speed input: 264.57 toks/s, output: 2737.39 toks/s]
Processed prompts: 45%|β–ˆβ–ˆβ–ˆβ–ˆβ– | 896/2000 [11:05<06:10, 2.98it/s, est. speed input: 265.32 toks/s, output: 2789.01 toks/s]
Processed prompts: 45%|β–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 900/2000 [11:06<05:03, 3.63it/s, est. speed input: 265.81 toks/s, output: 2791.24 toks/s]
Processed prompts: 45%|β–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 904/2000 [11:08<06:23, 2.86it/s, est. speed input: 265.74 toks/s, output: 2783.25 toks/s]
Processed prompts: 45%|β–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 908/2000 [11:11<08:20, 2.18it/s, est. speed input: 265.35 toks/s, output: 2773.81 toks/s]
Processed prompts: 46%|β–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 912/2000 [11:17<14:54, 1.22it/s, est. speed input: 263.40 toks/s, output: 2748.74 toks/s]
Processed prompts: 46%|β–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 916/2000 [11:20<14:25, 1.25it/s, est. speed input: 263.14 toks/s, output: 2738.55 toks/s]
Processed prompts: 46%|β–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 920/2000 [11:21<10:20, 1.74it/s, est. speed input: 263.81 toks/s, output: 2747.91 toks/s]
Processed prompts: 46%|β–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 924/2000 [11:21<07:56, 2.26it/s, est. speed input: 264.37 toks/s, output: 2748.25 toks/s]
Processed prompts: 46%|β–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 928/2000 [11:25<11:01, 1.62it/s, est. speed input: 263.47 toks/s, output: 2734.76 toks/s]
Processed prompts: 47%|β–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 932/2000 [11:27<09:25, 1.89it/s, est. speed input: 263.77 toks/s, output: 2743.14 toks/s]
Processed prompts: 47%|β–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 936/2000 [11:44<29:56, 1.69s/it, est. speed input: 257.91 toks/s, output: 2680.47 toks/s]
Processed prompts: 47%|β–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 940/2000 [11:45<21:25, 1.21s/it, est. speed input: 258.62 toks/s, output: 2681.41 toks/s]
Processed prompts: 47%|β–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 944/2000 [11:49<20:49, 1.18s/it, est. speed input: 257.66 toks/s, output: 2667.95 toks/s]
Processed prompts: 48%|β–ˆβ–ˆβ–ˆβ–ˆβ–Š | 952/2000 [11:49<11:24, 1.53it/s, est. speed input: 258.97 toks/s, output: 2693.08 toks/s]
Processed prompts: 48%|β–ˆβ–ˆβ–ˆβ–ˆβ–Š | 956/2000 [11:53<12:37, 1.38it/s, est. speed input: 258.30 toks/s, output: 2679.86 toks/s]
Processed prompts: 48%|β–ˆβ–ˆβ–ˆβ–ˆβ–Š | 960/2000 [11:55<11:32, 1.50it/s, est. speed input: 258.38 toks/s, output: 2676.37 toks/s]
Processed prompts: 48%|β–ˆβ–ˆβ–ˆβ–ˆβ–Š | 964/2000 [12:01<15:40, 1.10it/s, est. speed input: 256.94 toks/s, output: 2681.22 toks/s]
Processed prompts: 48%|β–ˆβ–ˆβ–ˆβ–ˆβ–Š | 968/2000 [12:04<14:52, 1.16it/s, est. speed input: 256.93 toks/s, output: 2726.92 toks/s]
Processed prompts: 49%|β–ˆβ–ˆβ–ˆβ–ˆβ–Š | 972/2000 [12:06<12:53, 1.33it/s, est. speed input: 256.96 toks/s, output: 2724.26 toks/s]
Processed prompts: 49%|β–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 976/2000 [12:09<12:14, 1.39it/s, est. speed input: 256.76 toks/s, output: 2717.76 toks/s]
Processed prompts: 49%|β–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 980/2000 [12:09<09:18, 1.83it/s, est. speed input: 257.31 toks/s, output: 2718.01 toks/s]
Processed prompts: 49%|β–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 984/2000 [12:20<19:55, 1.18s/it, est. speed input: 254.22 toks/s, output: 2679.93 toks/s]
Processed prompts: 49%|β–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 988/2000 [12:23<17:12, 1.02s/it, est. speed input: 254.10 toks/s, output: 2673.63 toks/s]
Processed prompts: 50%|β–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 992/2000 [12:24<13:36, 1.23it/s, est. speed input: 254.45 toks/s, output: 2671.30 toks/s]
Processed prompts: 50%|β–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 996/2000 [12:27<13:34, 1.23it/s, est. speed input: 254.08 toks/s, output: 2665.73 toks/s]
Processed prompts: 50%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 1000/2000 [12:31<13:53, 1.20it/s, est. speed input: 253.57 toks/s, output: 2655.93 toks/s]
Processed prompts: 50%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 1004/2000 [12:31<10:02, 1.65it/s, est. speed input: 254.35 toks/s, output: 2687.51 toks/s]
Processed prompts: 50%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 1008/2000 [12:33<09:04, 1.82it/s, est. speed input: 254.61 toks/s, output: 2691.20 toks/s]
Processed prompts: 51%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 1012/2000 [12:33<07:01, 2.34it/s, est. speed input: 255.14 toks/s, output: 2699.64 toks/s]
Processed prompts: 51%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 1016/2000 [12:36<08:29, 1.93it/s, est. speed input: 254.96 toks/s, output: 2699.55 toks/s]
Processed prompts: 51%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 1020/2000 [12:37<06:35, 2.48it/s, est. speed input: 255.47 toks/s, output: 2703.58 toks/s]
Processed prompts: 51%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 1024/2000 [12:37<05:24, 3.01it/s, est. speed input: 255.97 toks/s, output: 2704.47 toks/s]
Processed prompts: 51%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1028/2000 [12:41<07:52, 2.06it/s, est. speed input: 256.23 toks/s, output: 2776.43 toks/s]
Processed prompts: 52%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1032/2000 [12:44<09:25, 1.71it/s, est. speed input: 255.78 toks/s, output: 2768.83 toks/s]
Processed prompts: 52%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1036/2000 [12:47<10:26, 1.54it/s, est. speed input: 255.52 toks/s, output: 2769.60 toks/s]
Processed prompts: 52%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1040/2000 [12:50<10:44, 1.49it/s, est. speed input: 255.27 toks/s, output: 2801.33 toks/s]
Processed prompts: 52%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1044/2000 [12:51<09:03, 1.76it/s, est. speed input: 255.40 toks/s, output: 2799.15 toks/s]
Processed prompts: 52%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1048/2000 [12:52<06:44, 2.35it/s, est. speed input: 256.12 toks/s, output: 2843.69 toks/s]
Processed prompts: 53%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 1052/2000 [12:57<10:38, 1.48it/s, est. speed input: 255.09 toks/s, output: 2827.18 toks/s]
Processed prompts: 53%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 1056/2000 [12:57<07:36, 2.07it/s, est. speed input: 255.69 toks/s, output: 2829.63 toks/s]
Processed prompts: 53%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 1060/2000 [13:01<09:58, 1.57it/s, est. speed input: 255.04 toks/s, output: 2819.58 toks/s]
Processed prompts: 53%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 1064/2000 [13:08<15:29, 1.01it/s, est. speed input: 253.63 toks/s, output: 2841.62 toks/s]
Processed prompts: 53%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 1068/2000 [13:09<11:22, 1.37it/s, est. speed input: 254.13 toks/s, output: 2845.81 toks/s]
Processed prompts: 54%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 1072/2000 [13:09<08:06, 1.91it/s, est. speed input: 254.68 toks/s, output: 2847.04 toks/s]
Processed prompts: 54%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1076/2000 [13:10<07:06, 2.17it/s, est. speed input: 254.96 toks/s, output: 2843.83 toks/s]
Processed prompts: 54%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1080/2000 [13:10<05:07, 2.99it/s, est. speed input: 255.52 toks/s, output: 2845.21 toks/s]
Processed prompts: 54%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1080/2000 [13:20<05:07, 2.99it/s, est. speed input: 255.52 toks/s, output: 2845.21 toks/s]
Processed prompts: 54%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1084/2000 [13:27<22:46, 1.49s/it, est. speed input: 250.96 toks/s, output: 2796.96 toks/s]
Processed prompts: 54%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1088/2000 [13:29<18:10, 1.20s/it, est. speed input: 251.10 toks/s, output: 2800.23 toks/s]
Processed prompts: 55%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1092/2000 [13:33<16:53, 1.12s/it, est. speed input: 250.61 toks/s, output: 2789.10 toks/s]
Processed prompts: 55%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1096/2000 [13:33<12:18, 1.22it/s, est. speed input: 251.04 toks/s, output: 2789.80 toks/s]
Processed prompts: 55%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 1100/2000 [13:35<10:56, 1.37it/s, est. speed input: 250.94 toks/s, output: 2786.43 toks/s]
Processed prompts: 55%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 1104/2000 [13:36<08:20, 1.79it/s, est. speed input: 251.40 toks/s, output: 2785.45 toks/s]
Processed prompts: 55%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 1108/2000 [13:43<13:09, 1.13it/s, est. speed input: 250.11 toks/s, output: 2771.79 toks/s]
Processed prompts: 56%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 1112/2000 [13:43<09:46, 1.51it/s, est. speed input: 250.53 toks/s, output: 2771.12 toks/s]
Processed prompts: 56%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 1116/2000 [13:51<15:10, 1.03s/it, est. speed input: 248.91 toks/s, output: 2768.07 toks/s]
Processed prompts: 56%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 1120/2000 [13:54<13:56, 1.05it/s, est. speed input: 248.77 toks/s, output: 2787.06 toks/s]
Processed prompts: 56%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 1124/2000 [13:59<15:07, 1.04s/it, est. speed input: 248.03 toks/s, output: 2789.38 toks/s]
Processed prompts: 56%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 1128/2000 [14:03<14:47, 1.02s/it, est. speed input: 247.45 toks/s, output: 2779.66 toks/s]
Processed prompts: 57%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 1132/2000 [14:12<20:45, 1.43s/it, est. speed input: 245.32 toks/s, output: 2751.09 toks/s]
Processed prompts: 57%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 1136/2000 [14:13<14:50, 1.03s/it, est. speed input: 245.87 toks/s, output: 2751.99 toks/s]
Processed prompts: 57%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 1140/2000 [14:15<13:19, 1.08it/s, est. speed input: 245.70 toks/s, output: 2745.07 toks/s]
Processed prompts: 57%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 1144/2000 [14:17<11:25, 1.25it/s, est. speed input: 245.65 toks/s, output: 2740.07 toks/s]
Processed prompts: 57%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 1148/2000 [14:19<10:08, 1.40it/s, est. speed input: 245.70 toks/s, output: 2735.05 toks/s]
Processed prompts: 58%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 1152/2000 [14:22<10:05, 1.40it/s, est. speed input: 245.47 toks/s, output: 2733.35 toks/s]
Processed prompts: 58%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 1156/2000 [14:24<08:30, 1.65it/s, est. speed input: 245.72 toks/s, output: 2743.16 toks/s]
Processed prompts: 58%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 1160/2000 [14:28<10:24, 1.35it/s, est. speed input: 245.10 toks/s, output: 2738.24 toks/s]
Processed prompts: 58%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 1164/2000 [14:28<07:29, 1.86it/s, est. speed input: 245.64 toks/s, output: 2741.35 toks/s]
Processed prompts: 58%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 1168/2000 [14:29<06:38, 2.09it/s, est. speed input: 245.89 toks/s, output: 2738.29 toks/s]
Processed prompts: 59%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 1172/2000 [14:33<08:16, 1.67it/s, est. speed input: 245.48 toks/s, output: 2728.18 toks/s]
Processed prompts: 59%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 1180/2000 [14:35<05:52, 2.32it/s, est. speed input: 246.16 toks/s, output: 2741.17 toks/s]
Processed prompts: 59%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 1184/2000 [14:40<08:41, 1.56it/s, est. speed input: 245.33 toks/s, output: 2727.98 toks/s]
Processed prompts: 59%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 1188/2000 [14:43<09:18, 1.45it/s, est. speed input: 245.10 toks/s, output: 2730.58 toks/s]
Processed prompts: 60%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 1192/2000 [14:44<07:07, 1.89it/s, est. speed input: 245.50 toks/s, output: 2731.23 toks/s]
Processed prompts: 60%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 1196/2000 [14:44<05:21, 2.50it/s, est. speed input: 246.15 toks/s, output: 2739.61 toks/s]
Processed prompts: 60%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 1200/2000 [14:44<03:55, 3.40it/s, est. speed input: 246.77 toks/s, output: 2741.64 toks/s]
Processed prompts: 60%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 1204/2000 [14:50<08:30, 1.56it/s, est. speed input: 245.69 toks/s, output: 2725.99 toks/s]
Processed prompts: 60%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 1208/2000 [14:50<06:24, 2.06it/s, est. speed input: 246.09 toks/s, output: 2726.71 toks/s]
Processed prompts: 61%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 1212/2000 [14:51<05:01, 2.62it/s, est. speed input: 246.50 toks/s, output: 2737.27 toks/s]
Processed prompts: 61%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 1216/2000 [14:52<04:02, 3.24it/s, est. speed input: 246.89 toks/s, output: 2738.85 toks/s]
Processed prompts: 61%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 1224/2000 [14:52<02:37, 4.94it/s, est. speed input: 247.77 toks/s, output: 2744.74 toks/s]
Processed prompts: 61%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1228/2000 [14:57<06:01, 2.14it/s, est. speed input: 246.87 toks/s, output: 2730.52 toks/s]
Processed prompts: 62%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1232/2000 [14:58<04:41, 2.73it/s, est. speed input: 247.27 toks/s, output: 2730.87 toks/s]
Processed prompts: 62%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1236/2000 [14:59<04:21, 2.92it/s, est. speed input: 247.51 toks/s, output: 2730.13 toks/s]
Processed prompts: 62%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1240/2000 [15:01<04:51, 2.61it/s, est. speed input: 247.57 toks/s, output: 2731.89 toks/s]
Processed prompts: 62%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1244/2000 [15:02<04:59, 2.53it/s, est. speed input: 247.76 toks/s, output: 2740.08 toks/s]
Processed prompts: 62%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1248/2000 [15:09<09:20, 1.34it/s, est. speed input: 246.49 toks/s, output: 2722.53 toks/s]
Processed prompts: 63%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 1252/2000 [15:12<09:09, 1.36it/s, est. speed input: 246.26 toks/s, output: 2716.35 toks/s]
Processed prompts: 63%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 1256/2000 [15:13<08:06, 1.53it/s, est. speed input: 246.42 toks/s, output: 2731.95 toks/s]
Processed prompts: 63%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 1260/2000 [15:15<07:08, 1.73it/s, est. speed input: 246.57 toks/s, output: 2740.60 toks/s]
Processed prompts: 63%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 1264/2000 [15:19<08:20, 1.47it/s, est. speed input: 246.13 toks/s, output: 2730.88 toks/s]
Processed prompts: 63%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 1268/2000 [15:20<07:25, 1.64it/s, est. speed input: 246.20 toks/s, output: 2727.85 toks/s]
Processed prompts: 64%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 1272/2000 [15:21<05:53, 2.06it/s, est. speed input: 246.63 toks/s, output: 2741.02 toks/s]
Processed prompts: 64%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1276/2000 [15:22<04:45, 2.53it/s, est. speed input: 247.06 toks/s, output: 2741.68 toks/s]
Processed prompts: 64%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1280/2000 [15:26<06:59, 1.72it/s, est. speed input: 246.56 toks/s, output: 2742.16 toks/s]
Processed prompts: 64%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1284/2000 [15:26<05:02, 2.37it/s, est. speed input: 247.05 toks/s, output: 2743.10 toks/s]
Processed prompts: 64%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1288/2000 [15:27<04:04, 2.91it/s, est. speed input: 247.39 toks/s, output: 2745.41 toks/s]
Processed prompts: 65%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1292/2000 [15:28<03:38, 3.24it/s, est. speed input: 247.68 toks/s, output: 2743.86 toks/s]
Processed prompts: 65%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1296/2000 [15:30<04:05, 2.87it/s, est. speed input: 247.72 toks/s, output: 2740.64 toks/s]
Processed prompts: 65%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 1300/2000 [15:31<03:46, 3.10it/s, est. speed input: 247.89 toks/s, output: 2741.09 toks/s]
Processed prompts: 65%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 1304/2000 [15:31<02:59, 3.88it/s, est. speed input: 248.26 toks/s, output: 2741.23 toks/s]
Processed prompts: 66%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 1312/2000 [15:34<03:19, 3.45it/s, est. speed input: 248.74 toks/s, output: 2749.57 toks/s]
Processed prompts: 66%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 1316/2000 [15:34<02:33, 4.45it/s, est. speed input: 249.18 toks/s, output: 2755.13 toks/s]
Processed prompts: 66%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 1320/2000 [15:38<05:16, 2.15it/s, est. speed input: 248.47 toks/s, output: 2746.01 toks/s]
Processed prompts: 66%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 1324/2000 [15:39<03:56, 2.86it/s, est. speed input: 248.98 toks/s, output: 2747.08 toks/s]
Processed prompts: 66%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 1328/2000 [15:42<05:55, 1.89it/s, est. speed input: 248.45 toks/s, output: 2737.23 toks/s]
Processed prompts: 67%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 1332/2000 [15:44<05:33, 2.00it/s, est. speed input: 248.54 toks/s, output: 2735.67 toks/s]
Processed prompts: 67%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 1336/2000 [15:47<06:08, 1.80it/s, est. speed input: 248.41 toks/s, output: 2750.11 toks/s]
Processed prompts: 67%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 1340/2000 [15:48<05:01, 2.19it/s, est. speed input: 248.71 toks/s, output: 2754.20 toks/s]
Processed prompts: 67%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 1344/2000 [15:49<04:27, 2.45it/s, est. speed input: 248.86 toks/s, output: 2751.98 toks/s]
Processed prompts: 67%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 1348/2000 [15:50<03:44, 2.91it/s, est. speed input: 249.19 toks/s, output: 2751.91 toks/s]
Processed prompts: 68%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 1356/2000 [15:51<02:32, 4.22it/s, est. speed input: 249.96 toks/s, output: 2757.27 toks/s]
Processed prompts: 68%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 1360/2000 [15:51<02:06, 5.08it/s, est. speed input: 250.33 toks/s, output: 2757.37 toks/s]
Processed prompts: 68%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 1364/2000 [15:51<01:50, 5.78it/s, est. speed input: 250.77 toks/s, output: 2772.78 toks/s]
Processed prompts: 68%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 1368/2000 [15:55<03:42, 2.84it/s, est. speed input: 250.45 toks/s, output: 2765.33 toks/s]
Processed prompts: 69%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 1372/2000 [15:56<03:46, 2.78it/s, est. speed input: 250.57 toks/s, output: 2763.65 toks/s]
Processed prompts: 69%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 1376/2000 [16:01<06:09, 1.69it/s, est. speed input: 249.80 toks/s, output: 2752.38 toks/s]
Processed prompts: 69%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 1380/2000 [16:04<06:34, 1.57it/s, est. speed input: 249.50 toks/s, output: 2745.99 toks/s]
Processed prompts: 69%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 1384/2000 [16:06<06:05, 1.69it/s, est. speed input: 249.54 toks/s, output: 2743.12 toks/s]
Processed prompts: 69%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 1388/2000 [16:07<04:56, 2.07it/s, est. speed input: 249.76 toks/s, output: 2742.15 toks/s]
Processed prompts: 70%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 1392/2000 [16:07<03:53, 2.61it/s, est. speed input: 250.14 toks/s, output: 2744.00 toks/s]
Processed prompts: 70%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 1396/2000 [16:08<02:51, 3.52it/s, est. speed input: 250.60 toks/s, output: 2744.99 toks/s]
Processed prompts: 70%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 1404/2000 [16:13<04:34, 2.17it/s, est. speed input: 250.22 toks/s, output: 2735.64 toks/s]
Processed prompts: 70%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 1408/2000 [16:13<03:46, 2.61it/s, est. speed input: 250.54 toks/s, output: 2735.19 toks/s]
Processed prompts: 71%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 1412/2000 [16:16<04:21, 2.25it/s, est. speed input: 250.41 toks/s, output: 2735.15 toks/s]
Processed prompts: 71%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 1416/2000 [16:18<04:31, 2.15it/s, est. speed input: 250.36 toks/s, output: 2732.09 toks/s]
Processed prompts: 71%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 1420/2000 [16:19<03:44, 2.59it/s, est. speed input: 250.60 toks/s, output: 2730.89 toks/s]
Processed prompts: 71%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 1424/2000 [16:20<03:42, 2.59it/s, est. speed input: 250.87 toks/s, output: 2743.51 toks/s]
Processed prompts: 71%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1428/2000 [16:21<03:27, 2.76it/s, est. speed input: 251.04 toks/s, output: 2741.46 toks/s]
Processed prompts: 72%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1432/2000 [16:22<02:42, 3.50it/s, est. speed input: 251.40 toks/s, output: 2741.35 toks/s]
Processed prompts: 72%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1440/2000 [16:23<02:02, 4.58it/s, est. speed input: 252.17 toks/s, output: 2771.99 toks/s]
Processed prompts: 72%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1444/2000 [16:24<01:49, 5.06it/s, est. speed input: 252.53 toks/s, output: 2773.96 toks/s]
Processed prompts: 72%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1448/2000 [16:24<01:31, 6.01it/s, est. speed input: 252.94 toks/s, output: 2783.17 toks/s]
Processed prompts: 73%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 1452/2000 [16:29<04:05, 2.24it/s, est. speed input: 252.17 toks/s, output: 2771.10 toks/s]
Processed prompts: 73%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 1468/2000 [16:30<02:02, 4.34it/s, est. speed input: 253.86 toks/s, output: 2814.77 toks/s]
Processed prompts: 74%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 1472/2000 [16:31<01:53, 4.63it/s, est. speed input: 254.29 toks/s, output: 2830.51 toks/s]
Processed prompts: 74%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1476/2000 [16:32<02:15, 3.88it/s, est. speed input: 254.33 toks/s, output: 2826.88 toks/s]
Processed prompts: 74%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1480/2000 [16:33<02:03, 4.21it/s, est. speed input: 254.63 toks/s, output: 2826.53 toks/s]
Processed prompts: 74%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1484/2000 [16:34<02:00, 4.27it/s, est. speed input: 254.83 toks/s, output: 2826.23 toks/s]
Processed prompts: 74%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1488/2000 [16:35<01:52, 4.56it/s, est. speed input: 255.12 toks/s, output: 2826.05 toks/s]
Processed prompts: 75%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1492/2000 [16:35<01:32, 5.48it/s, est. speed input: 255.57 toks/s, output: 2829.23 toks/s]
Processed prompts: 75%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1496/2000 [16:37<02:04, 4.05it/s, est. speed input: 255.59 toks/s, output: 2825.27 toks/s]
Processed prompts: 75%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 1500/2000 [16:37<01:48, 4.62it/s, est. speed input: 255.92 toks/s, output: 2825.38 toks/s]
Processed prompts: 75%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 1504/2000 [16:38<01:45, 4.71it/s, est. speed input: 256.20 toks/s, output: 2824.18 toks/s]
Processed prompts: 75%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 1508/2000 [16:40<02:13, 3.69it/s, est. speed input: 256.19 toks/s, output: 2820.59 toks/s]
Processed prompts: 76%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 1512/2000 [16:40<01:49, 4.44it/s, est. speed input: 256.54 toks/s, output: 2820.19 toks/s]
Processed prompts: 76%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 1516/2000 [16:41<01:36, 5.02it/s, est. speed input: 256.97 toks/s, output: 2823.77 toks/s]
Processed prompts: 76%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 1520/2000 [16:42<01:48, 4.44it/s, est. speed input: 257.10 toks/s, output: 2821.43 toks/s]
Processed prompts: 76%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 1524/2000 [16:44<02:15, 3.51it/s, est. speed input: 257.13 toks/s, output: 2817.97 toks/s]
Processed prompts: 76%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 1528/2000 [16:46<02:47, 2.82it/s, est. speed input: 257.05 toks/s, output: 2813.27 toks/s]
Processed prompts: 77%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 1536/2000 [16:46<01:42, 4.53it/s, est. speed input: 257.89 toks/s, output: 2848.25 toks/s]
Processed prompts: 77%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 1540/2000 [16:47<01:48, 4.22it/s, est. speed input: 258.01 toks/s, output: 2846.19 toks/s]
Processed prompts: 77%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 1544/2000 [16:48<01:41, 4.48it/s, est. speed input: 258.28 toks/s, output: 2845.14 toks/s]
Processed prompts: 77%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 1548/2000 [16:53<03:35, 2.09it/s, est. speed input: 257.49 toks/s, output: 2834.16 toks/s]
Processed prompts: 78%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 1552/2000 [16:53<02:38, 2.82it/s, est. speed input: 257.87 toks/s, output: 2835.35 toks/s]
Processed prompts: 78%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 1556/2000 [16:55<02:51, 2.60it/s, est. speed input: 257.85 toks/s, output: 2832.58 toks/s]
Processed prompts: 78%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 1560/2000 [16:55<02:07, 3.45it/s, est. speed input: 258.27 toks/s, output: 2832.77 toks/s]
Processed prompts: 78%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 1564/2000 [16:56<02:04, 3.49it/s, est. speed input: 258.43 toks/s, output: 2832.02 toks/s]
Processed prompts: 78%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 1568/2000 [16:57<02:06, 3.42it/s, est. speed input: 258.55 toks/s, output: 2830.47 toks/s]
Processed prompts: 79%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 1572/2000 [16:57<01:34, 4.52it/s, est. speed input: 258.99 toks/s, output: 2831.24 toks/s]
Processed prompts: 79%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 1576/2000 [17:01<02:46, 2.54it/s, est. speed input: 258.64 toks/s, output: 2823.57 toks/s]
Processed prompts: 79%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 1580/2000 [17:01<02:11, 3.19it/s, est. speed input: 258.98 toks/s, output: 2825.93 toks/s]
Processed prompts: 79%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 1588/2000 [17:02<01:22, 4.98it/s, est. speed input: 259.74 toks/s, output: 2830.27 toks/s]
Processed prompts: 80%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 1592/2000 [17:02<01:09, 5.89it/s, est. speed input: 260.07 toks/s, output: 2831.20 toks/s]
Processed prompts: 80%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 1596/2000 [17:04<01:48, 3.72it/s, est. speed input: 259.95 toks/s, output: 2825.70 toks/s]
Processed prompts: 80%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 1600/2000 [17:05<01:29, 4.45it/s, est. speed input: 260.36 toks/s, output: 2846.05 toks/s]
Processed prompts: 80%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 1604/2000 [17:06<01:43, 3.82it/s, est. speed input: 260.44 toks/s, output: 2842.98 toks/s]
Processed prompts: 80%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 1608/2000 [17:06<01:16, 5.13it/s, est. speed input: 260.88 toks/s, output: 2844.41 toks/s]
Processed prompts: 81%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 1612/2000 [17:07<01:30, 4.31it/s, est. speed input: 261.03 toks/s, output: 2845.66 toks/s]
Processed prompts: 81%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 1616/2000 [17:09<01:50, 3.46it/s, est. speed input: 261.06 toks/s, output: 2854.54 toks/s]
Processed prompts: 81%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 1620/2000 [17:11<02:06, 3.02it/s, est. speed input: 261.15 toks/s, output: 2864.88 toks/s]
Processed prompts: 81%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 1624/2000 [17:14<02:56, 2.13it/s, est. speed input: 260.78 toks/s, output: 2857.11 toks/s]
Processed prompts: 81%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1628/2000 [17:14<02:06, 2.93it/s, est. speed input: 261.38 toks/s, output: 2895.90 toks/s]
Processed prompts: 82%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1632/2000 [17:16<02:07, 2.90it/s, est. speed input: 261.47 toks/s, output: 2893.01 toks/s]
Processed prompts: 82%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1636/2000 [17:17<02:12, 2.74it/s, est. speed input: 261.52 toks/s, output: 2889.72 toks/s]
Processed prompts: 82%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1640/2000 [17:18<01:49, 3.28it/s, est. speed input: 261.80 toks/s, output: 2888.91 toks/s]
Processed prompts: 82%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1644/2000 [17:19<01:52, 3.17it/s, est. speed input: 261.88 toks/s, output: 2892.40 toks/s]
Processed prompts: 82%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1648/2000 [17:20<01:34, 3.73it/s, est. speed input: 262.14 toks/s, output: 2892.07 toks/s]
Processed prompts: 83%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 1652/2000 [17:20<01:10, 4.97it/s, est. speed input: 262.55 toks/s, output: 2892.80 toks/s]
Processed prompts: 83%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 1656/2000 [17:21<01:04, 5.30it/s, est. speed input: 262.81 toks/s, output: 2893.42 toks/s]
Processed prompts: 83%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 1660/2000 [17:21<01:03, 5.32it/s, est. speed input: 263.03 toks/s, output: 2892.99 toks/s]
Processed prompts: 83%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 1664/2000 [17:22<00:48, 6.92it/s, est. speed input: 263.55 toks/s, output: 2928.69 toks/s]
Processed prompts: 83%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 1668/2000 [17:22<00:37, 8.94it/s, est. speed input: 263.95 toks/s, output: 2929.85 toks/s]
Processed prompts: 84%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 1672/2000 [17:22<00:39, 8.38it/s, est. speed input: 264.25 toks/s, output: 2929.45 toks/s]
Processed prompts: 84%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1676/2000 [17:25<01:29, 3.62it/s, est. speed input: 264.04 toks/s, output: 2923.76 toks/s]
Processed prompts: 84%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1680/2000 [17:25<01:15, 4.27it/s, est. speed input: 264.37 toks/s, output: 2925.93 toks/s]
Processed prompts: 84%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1684/2000 [17:27<01:29, 3.53it/s, est. speed input: 264.38 toks/s, output: 2922.16 toks/s]
Processed prompts: 84%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1688/2000 [17:28<01:35, 3.28it/s, est. speed input: 264.42 toks/s, output: 2919.26 toks/s]
Processed prompts: 85%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1692/2000 [17:29<01:11, 4.31it/s, est. speed input: 264.74 toks/s, output: 2919.83 toks/s]
Processed prompts: 85%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 1696/2000 [17:29<01:03, 4.81it/s, est. speed input: 265.02 toks/s, output: 2918.94 toks/s]
Processed prompts: 85%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 1700/2000 [17:31<01:20, 3.74it/s, est. speed input: 265.04 toks/s, output: 2915.67 toks/s]
Processed prompts: 85%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 1704/2000 [17:31<00:57, 5.13it/s, est. speed input: 265.45 toks/s, output: 2916.50 toks/s]
Processed prompts: 85%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 1708/2000 [17:33<01:16, 3.84it/s, est. speed input: 265.44 toks/s, output: 2913.49 toks/s]
Processed prompts: 86%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 1716/2000 [17:34<00:53, 5.31it/s, est. speed input: 266.06 toks/s, output: 2916.13 toks/s]
Processed prompts: 86%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 1720/2000 [17:34<00:46, 6.04it/s, est. speed input: 266.35 toks/s, output: 2915.64 toks/s]
Processed prompts: 86%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 1724/2000 [17:36<01:13, 3.73it/s, est. speed input: 266.16 toks/s, output: 2910.24 toks/s]
Processed prompts: 86%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 1728/2000 [17:37<01:02, 4.38it/s, est. speed input: 266.42 toks/s, output: 2909.50 toks/s]
Processed prompts: 87%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 1736/2000 [17:37<00:40, 6.58it/s, est. speed input: 267.20 toks/s, output: 2913.43 toks/s]
Processed prompts: 87%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 1740/2000 [17:37<00:33, 7.74it/s, est. speed input: 267.51 toks/s, output: 2913.15 toks/s]
Processed prompts: 87%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 1744/2000 [17:38<00:33, 7.65it/s, est. speed input: 267.94 toks/s, output: 2947.12 toks/s]
Processed prompts: 87%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 1748/2000 [17:38<00:26, 9.56it/s, est. speed input: 268.30 toks/s, output: 2947.69 toks/s]
Processed prompts: 88%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 1752/2000 [17:38<00:24, 10.29it/s, est. speed input: 268.62 toks/s, output: 2949.05 toks/s]
Processed prompts: 88%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 1756/2000 [17:38<00:19, 12.73it/s, est. speed input: 269.03 toks/s, output: 2950.13 toks/s]
Processed prompts: 88%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 1764/2000 [17:39<00:19, 11.95it/s, est. speed input: 269.62 toks/s, output: 2950.86 toks/s]
Processed prompts: 88%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 1768/2000 [17:40<00:34, 6.78it/s, est. speed input: 269.72 toks/s, output: 2951.72 toks/s]
Processed prompts: 89%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 1772/2000 [17:41<00:26, 8.49it/s, est. speed input: 270.09 toks/s, output: 2952.16 toks/s]
Processed prompts: 89%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 1776/2000 [17:41<00:23, 9.54it/s, est. speed input: 270.42 toks/s, output: 2952.23 toks/s]
Processed prompts: 89%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 1780/2000 [17:42<00:26, 8.38it/s, est. speed input: 270.66 toks/s, output: 2951.46 toks/s]
Processed prompts: 89%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 1784/2000 [17:42<00:29, 7.20it/s, est. speed input: 270.89 toks/s, output: 2957.50 toks/s]
Processed prompts: 89%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 1788/2000 [17:43<00:28, 7.52it/s, est. speed input: 271.18 toks/s, output: 2957.11 toks/s]
Processed prompts: 90%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 1792/2000 [17:43<00:22, 9.28it/s, est. speed input: 271.53 toks/s, output: 2957.38 toks/s]
Processed prompts: 90%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 1796/2000 [17:44<00:26, 7.59it/s, est. speed input: 271.75 toks/s, output: 2956.46 toks/s]
Processed prompts: 90%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 1800/2000 [17:45<00:33, 6.00it/s, est. speed input: 271.96 toks/s, output: 2958.67 toks/s]
Processed prompts: 90%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 1804/2000 [17:45<00:31, 6.23it/s, est. speed input: 272.18 toks/s, output: 2957.89 toks/s]
Processed prompts: 90%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 1808/2000 [17:47<00:40, 4.77it/s, est. speed input: 272.24 toks/s, output: 2954.96 toks/s]
Processed prompts: 91%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 1816/2000 [17:47<00:23, 7.81it/s, est. speed input: 272.96 toks/s, output: 2958.40 toks/s]
Processed prompts: 91%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 1820/2000 [17:47<00:19, 9.27it/s, est. speed input: 273.49 toks/s, output: 3002.45 toks/s]
Processed prompts: 91%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–| 1828/2000 [17:48<00:16, 10.38it/s, est. speed input: 274.15 toks/s, output: 3004.04 toks/s]
Processed prompts: 92%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–| 1832/2000 [17:49<00:24, 6.78it/s, est. speed input: 274.21 toks/s, output: 3001.19 toks/s]
Processed prompts: 92%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–| 1836/2000 [17:49<00:22, 7.34it/s, est. speed input: 274.50 toks/s, output: 3000.83 toks/s]
Processed prompts: 92%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–| 1840/2000 [17:50<00:22, 6.97it/s, est. speed input: 274.70 toks/s, output: 2999.58 toks/s]
Processed prompts: 92%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–| 1848/2000 [17:51<00:16, 9.03it/s, est. speed input: 275.40 toks/s, output: 3012.58 toks/s]
Processed prompts: 93%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž| 1856/2000 [17:51<00:10, 13.32it/s, est. speed input: 276.12 toks/s, output: 3014.19 toks/s]
Processed prompts: 93%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž| 1864/2000 [17:52<00:12, 10.88it/s, est. speed input: 276.72 toks/s, output: 3019.42 toks/s]
Processed prompts: 94%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž| 1872/2000 [17:52<00:10, 12.10it/s, est. speed input: 277.33 toks/s, output: 3020.38 toks/s]
Processed prompts: 94%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–| 1876/2000 [17:53<00:11, 10.98it/s, est. speed input: 277.61 toks/s, output: 3022.19 toks/s]
Processed prompts: 94%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–| 1880/2000 [17:53<00:13, 9.10it/s, est. speed input: 277.78 toks/s, output: 3021.22 toks/s]
Processed prompts: 94%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–| 1884/2000 [17:54<00:13, 8.58it/s, est. speed input: 278.05 toks/s, output: 3020.95 toks/s]
Processed prompts: 94%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–| 1888/2000 [17:58<00:37, 3.01it/s, est. speed input: 277.51 toks/s, output: 3021.06 toks/s]
Processed prompts: 95%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–| 1892/2000 [17:58<00:29, 3.67it/s, est. speed input: 277.77 toks/s, output: 3021.53 toks/s]
Processed prompts: 95%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–| 1896/2000 [17:59<00:24, 4.24it/s, est. speed input: 277.99 toks/s, output: 3021.64 toks/s]
Processed prompts: 95%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ| 1900/2000 [17:59<00:18, 5.41it/s, est. speed input: 278.34 toks/s, output: 3023.17 toks/s]
Processed prompts: 95%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ| 1904/2000 [18:01<00:25, 3.74it/s, est. speed input: 278.30 toks/s, output: 3022.17 toks/s]
Processed prompts: 95%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ| 1908/2000 [18:03<00:30, 3.03it/s, est. speed input: 278.20 toks/s, output: 3020.70 toks/s]
Processed prompts: 96%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ| 1912/2000 [18:06<00:42, 2.07it/s, est. speed input: 277.78 toks/s, output: 3024.82 toks/s]
Processed prompts: 96%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ| 1916/2000 [18:09<00:44, 1.87it/s, est. speed input: 277.49 toks/s, output: 3022.39 toks/s]
Processed prompts: 96%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ| 1920/2000 [18:10<00:39, 2.05it/s, est. speed input: 277.61 toks/s, output: 3040.21 toks/s]
Processed prompts: 96%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ| 1924/2000 [18:20<01:22, 1.09s/it, est. speed input: 275.52 toks/s, output: 3017.25 toks/s]
Processed prompts: 96%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹| 1928/2000 [18:22<01:01, 1.17it/s, est. speed input: 275.70 toks/s, output: 3047.42 toks/s]
Processed prompts: 97%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹| 1932/2000 [18:40<02:13, 1.96s/it, est. speed input: 271.64 toks/s, output: 3008.64 toks/s]
Processed prompts: 97%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹| 1936/2000 [18:44<01:46, 1.67s/it, est. speed input: 271.29 toks/s, output: 3053.36 toks/s]
Processed prompts: 97%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹| 1940/2000 [18:44<01:13, 1.22s/it, est. speed input: 271.52 toks/s, output: 3058.19 toks/s]
Processed prompts: 97%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹| 1944/2000 [18:45<00:50, 1.12it/s, est. speed input: 271.87 toks/s, output: 3072.38 toks/s]
Processed prompts: 97%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹| 1948/2000 [19:02<01:38, 1.89s/it, est. speed input: 268.33 toks/s, output: 3044.08 toks/s]
Processed prompts: 98%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š| 1952/2000 [19:12<01:40, 2.09s/it, est. speed input: 266.63 toks/s, output: 3070.06 toks/s]
Processed prompts: 98%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š| 1956/2000 [19:22<01:35, 2.17s/it, est. speed input: 264.90 toks/s, output: 3067.99 toks/s]
Processed prompts: 98%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š| 1960/2000 [19:24<01:09, 1.73s/it, est. speed input: 264.81 toks/s, output: 3094.60 toks/s]
Processed prompts: 98%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š| 1964/2000 [19:28<00:53, 1.49s/it, est. speed input: 264.32 toks/s, output: 3100.84 toks/s]
Processed prompts: 98%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š| 1968/2000 [19:29<00:36, 1.15s/it, est. speed input: 264.71 toks/s, output: 3152.24 toks/s]
Processed prompts: 99%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š| 1972/2000 [19:45<00:54, 1.93s/it, est. speed input: 261.71 toks/s, output: 3124.91 toks/s]
Processed prompts: 99%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰| 1976/2000 [20:48<02:25, 6.08s/it, est. speed input: 248.96 toks/s, output: 2998.85 toks/s]
Processed prompts: 99%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰| 1980/2000 [20:54<01:34, 4.74s/it, est. speed input: 248.23 toks/s, output: 3034.21 toks/s]
Processed prompts: 99%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰| 1984/2000 [21:32<01:38, 6.18s/it, est. speed input: 241.24 toks/s, output: 2967.21 toks/s]
Processed prompts: 99%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰| 1988/2000 [21:51<01:08, 5.73s/it, est. speed input: 238.23 toks/s, output: 2960.15 toks/s]
Processed prompts: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰| 1992/2000 [22:23<00:51, 6.41s/it, est. speed input: 232.97 toks/s, output: 2949.91 toks/s]
Processed prompts: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰| 1996/2000 [23:34<00:39, 9.82s/it, est. speed input: 221.61 toks/s, output: 2830.03 toks/s]
Processed prompts: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 2000/2000 [25:56<00:00, 17.49s/it, est. speed input: 201.72 toks/s, output: 2603.08 toks/s]
Processed prompts: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 2000/2000 [25:56<00:00, 17.49s/it, est. speed input: 201.72 toks/s, output: 2603.08 toks/s] Processed prompts: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 2000/2000 [25:56<00:00, 1.29it/s, est. speed input: 201.72 toks/s, output: 2603.08 toks/s]
Splits: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 1/1 [25:56<00:00, 1556.49s/it] Splits: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 1/1 [25:56<00:00, 1556.49s/it]
Creating parquet from Arrow format: 0%| | 0/1 [00:00<?, ?ba/s] Creating parquet from Arrow format: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 1/1 [00:00<00:00, 3.90ba/s] Creating parquet from Arrow format: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 1/1 [00:00<00:00, 3.89ba/s]
[2025-10-26 03:10:53,817] [ INFO]: Cached 500 samples of lighteval|math_500|0 (3aecc7facae3926c, GENERATIVE) at /mnt/public/wucanhui/outputs/Qwen3-14B-math-reasoning/checkpoint-2562/081b5a149587018c/lighteval|math_500|0/3aecc7facae3926c/GENERATIVE.parquet. (cache_management.py:345)
Generating train split: 0 examples [00:00, ? examples/s] Generating train split: 500 examples [00:00, 3409.17 examples/s] Generating train split: 500 examples [00:00, 3367.58 examples/s]
[rank0]:[W1026 03:11:03.786488099 ProcessGroupNCCL.cpp:1479] Warning: WARNING: destroy_process_group() was not called before program exit, which can leak resources. For more info, please see https://pytorch.org/docs/stable/distributed.html#shutdown (function operator())
[2025-10-26 03:11:04,702] [ INFO]: --- POST-PROCESSING MODEL RESPONSES --- (pipeline.py:344)
[2025-10-26 03:11:04,711] [ INFO]: --- COMPUTING METRICS --- (pipeline.py:371)
[2025-10-26 03:11:04,755] [ WARNING]: n undefined in the pass@k. We assume it's the same as the sample's number of predictions. (metrics_sample.py:1302)
[2025-10-26 03:11:09,287] [ INFO]: --- DISPLAYING RESULTS --- (pipeline.py:432)
[2025-10-26 03:11:09,300] [ INFO]: --- SAVING AND PUSHING RESULTS --- (pipeline.py:422)
[2025-10-26 03:11:09,301] [ INFO]: Saving experiment tracker (evaluation_tracker.py:246)
[2025-10-26 03:11:11,741] [ INFO]: Saving results to /mnt/public/wucanhui/lighteval/results/results/mnt/public/wucanhui/outputs/Qwen3-14B-math-reasoning/checkpoint-2562/results_2025-10-26T03-11-09.302144.json (evaluation_tracker.py:310)
| Task |Version| Metric |Value | |Stderr|
|--------------------|-------|-------------|-----:|---|-----:|
|all | |avg@k_with_k |0.9425|Β± |0.0076|
| | |pass@k_with_k|0.9900|Β± |0.0045|
|lighteval:math_500:0| |avg@k_with_k |0.9425|Β± |0.0076|
| | |pass@k_with_k|0.9900|Β± |0.0045|