junhua024-chai-02-full-06

developer_uid: junhua024

submission_id: junhua024-chai-02-full-06_v3

model_name: junhua024-chai-02-full-06_v3

model_group: junhua024/chai_02-full_0

status: torndown

timestamp: 2025-07-15T21:20:08+00:00

num_battles: 7055

num_wins: 3279

celo_rating: 1262.57

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: junhua024/chai_02-full_06

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.5972320137338712, 'latency_mean': 1.6742381393909453, 'latency_p50': 1.6779028177261353, 'latency_p90': 1.8475600242614747}, {'batch_size': 3, 'throughput': 1.0639485335332164, 'latency_mean': 2.8118336951732634, 'latency_p50': 2.8198498487472534, 'latency_p90': 3.106099009513855}, {'batch_size': 5, 'throughput': 1.2849651208340842, 'latency_mean': 3.874074442386627, 'latency_p50': 3.856752038002014, 'latency_p90': 4.377994108200073}, {'batch_size': 6, 'throughput': 1.345340304207862, 'latency_mean': 4.440233730077743, 'latency_p50': 4.429076433181763, 'latency_p90': 4.965942239761352}, {'batch_size': 8, 'throughput': 1.4025068645210526, 'latency_mean': 5.678020724058151, 'latency_p50': 5.690169811248779, 'latency_p90': 6.3413453817367555}, {'batch_size': 10, 'throughput': 1.4360277697232944, 'latency_mean': 6.89796679019928, 'latency_p50': 6.972714781761169, 'latency_p90': 7.7528078794479365}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-02-full-06_v3

is_internal_developer: False

language_model: junhua024/chai_02-full_06

model_size: 13B

ranking_group: single

throughput_3p7s: 1.26

us_pacific_date: 2025-07-15

win_ratio: 0.46477675407512403

generation_params: {'temperature': 1.0, 'top_p': 0.88, 'min_p': 0.3, 'top_k': 10, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '{memory} What nuanced feelings lie behind these words?', 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}

Resubmit model

Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name junhua024-chai-02-full-06-v3-mkmlizer
Waiting for job on junhua024-chai-02-full-06-v3-mkmlizer to finish
junhua024-chai-02-full-06-v3-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-06-v3-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-06-v3-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
Failed to get response for submission junhua024-chai-02-full-06_v1: HTTPConnectionPool(host='junhua024-chai-02-full-06-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-02-full-06-v3-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-06-v3-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-06-v3-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-06-v3-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-06-v3-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-06-v3-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-06-v3-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
Failed to get response for submission junhua024-chai-02-full-06_v1: HTTPConnectionPool(host='junhua024-chai-02-full-06-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-02-full-06-v3-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-06-v3-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-06-v3-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-06-v3-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-06-v3-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-06-v3-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-06-v3-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-06-v3-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-06-v3-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-06-v3-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-06-v3-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-06-v3-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-06-v3-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-06-v3-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-06-v3-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-06-v3-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-06-v3-mkmlizer: Downloaded to shared memory in 76.717s
junhua024-chai-02-full-06-v3-mkmlizer: Checking if junhua024/chai_02-full_06 already exists in ChaiML
junhua024-chai-02-full-06-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpd0ukvio1, device:0
junhua024-chai-02-full-06-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-02-full-06-v3-mkmlizer: quantized model in 32.042s
junhua024-chai-02-full-06-v3-mkmlizer: Processed model junhua024/chai_02-full_06 in 108.848s
junhua024-chai-02-full-06-v3-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-02-full-06-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-02-full-06-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-02-full-06-v3/nvidia
junhua024-chai-02-full-06-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-02-full-06-v3/nvidia/special_tokens_map.json
junhua024-chai-02-full-06-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-02-full-06-v3/nvidia/config.json
junhua024-chai-02-full-06-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-02-full-06-v3/nvidia/tokenizer_config.json
junhua024-chai-02-full-06-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-02-full-06-v3/nvidia/tokenizer.json
junhua024-chai-02-full-06-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-02-full-06-v3/nvidia/flywheel_model.0.safetensors
junhua024-chai-02-full-06-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:00<00:24, 14.91it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:21, 17.01it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:12, 28.84it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:11, 30.15it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 32.51it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 46.01it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:09, 35.91it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:09, 34.95it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:07, 39.31it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:09, 33.79it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:09, 33.25it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 35.26it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:08, 34.06it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:07, 37.31it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:07, 36.01it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 33.97it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:07, 38.54it/s]
Loading 0:  26%|██▌       | 93/363 [00:02<00:07, 37.86it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:07, 34.68it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:07, 35.16it/s]
Loading 0:  29%|██▉       | 105/363 [00:03<00:07, 33.35it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:06, 40.14it/s]
Loading 0:  32%|███▏      | 117/363 [00:03<00:07, 31.42it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:07, 32.56it/s]
Loading 0:  35%|███▌      | 128/363 [00:03<00:06, 33.97it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:07, 32.68it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 33.60it/s]
Loading 0:  39%|███▉      | 143/363 [00:04<00:06, 33.66it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:06, 34.01it/s]
Loading 0:  43%|████▎     | 157/363 [00:04<00:04, 43.39it/s]
Loading 0:  45%|████▍     | 162/363 [00:04<00:05, 33.66it/s]
Loading 0:  46%|████▌     | 167/363 [00:04<00:05, 33.02it/s]
Loading 0:  48%|████▊     | 176/363 [00:05<00:04, 38.51it/s]
Loading 0:  50%|████▉     | 181/363 [00:05<00:05, 32.79it/s]
Loading 0:  51%|█████     | 185/363 [00:05<00:05, 32.14it/s]
Loading 0:  53%|█████▎    | 191/363 [00:05<00:05, 34.19it/s]
Loading 0:  54%|█████▎    | 195/363 [00:05<00:05, 33.59it/s]
Loading 0:  55%|█████▌    | 200/363 [00:05<00:04, 36.04it/s]
Loading 0:  56%|█████▌    | 204/363 [00:05<00:04, 36.62it/s]
Loading 0:  57%|█████▋    | 208/363 [00:06<00:04, 32.45it/s]
Loading 0:  58%|█████▊    | 212/363 [00:06<00:04, 30.27it/s]
Loading 0:  60%|██████    | 218/363 [00:06<00:03, 36.85it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:03, 36.08it/s]
Loading 0:  63%|██████▎   | 227/363 [00:06<00:03, 35.50it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:03, 33.42it/s]
Loading 0:  66%|██████▌   | 239/363 [00:06<00:03, 40.79it/s]
Loading 0:  67%|██████▋   | 244/363 [00:07<00:03, 34.44it/s]
Loading 0:  68%|██████▊   | 248/363 [00:07<00:03, 33.97it/s]
Loading 0:  70%|██████▉   | 254/363 [00:07<00:03, 35.83it/s]
Loading 0:  71%|███████   | 258/363 [00:07<00:03, 33.02it/s]
Loading 0:  72%|███████▏  | 263/363 [00:07<00:02, 36.59it/s]
Loading 0:  74%|███████▍  | 268/363 [00:07<00:02, 35.70it/s]
Loading 0:  75%|███████▍  | 272/363 [00:07<00:02, 36.60it/s]
Loading 0:  76%|███████▌  | 276/363 [00:07<00:02, 33.05it/s]
Loading 0:  77%|███████▋  | 281/363 [00:08<00:02, 35.24it/s]
Loading 0:  79%|███████▉  | 286/363 [00:08<00:02, 31.58it/s]
Loading 0:  80%|███████▉  | 290/363 [00:08<00:02, 31.60it/s]
Loading 0:  81%|████████  | 294/363 [00:08<00:02, 30.15it/s]
Loading 0:  83%|████████▎ | 301/363 [00:08<00:01, 39.06it/s]
Loading 0:  84%|████████▍ | 306/363 [00:08<00:01, 28.67it/s]
Loading 0:  86%|████████▌ | 311/363 [00:09<00:01, 30.23it/s]
Loading 0:  87%|████████▋ | 317/363 [00:09<00:01, 32.16it/s]
Loading 0:  88%|████████▊ | 321/363 [00:09<00:01, 31.54it/s]
Loading 0:  90%|█████████ | 327/363 [00:09<00:01, 33.05it/s]
Loading 0:  91%|█████████▏| 332/363 [00:09<00:00, 33.23it/s]
Loading 0:  93%|█████████▎| 338/363 [00:09<00:00, 34.98it/s]
Loading 0:  95%|█████████▌| 345/363 [00:09<00:00, 42.50it/s]
Loading 0:  96%|█████████▋| 350/363 [00:10<00:00, 24.52it/s]
Loading 0:  98%|█████████▊| 354/363 [00:10<00:00, 26.37it/s]
Loading 0:  99%|█████████▊| 358/363 [00:10<00:00, 26.72it/s]
                                                            
Job junhua024-chai-02-full-06-v3-mkmlizer completed after 137.17s with status: succeeded
Stopping job with name junhua024-chai-02-full-06-v3-mkmlizer
Pipeline stage MKMLizer completed in 137.65s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-02-full-06-v3
Waiting for inference service junhua024-chai-02-full-06-v3 to be ready
Failed to get response for submission junhua024-chai-02-full-06_v1: HTTPConnectionPool(host='junhua024-chai-02-full-06-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service junhua024-chai-02-full-06-v3 ready after 251.54230856895447s
Pipeline stage MKMLDeployer completed in 252.01s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.567074775695801s
Received healthy response to inference request in 1.8848917484283447s
Received healthy response to inference request in 1.589740514755249s
Received healthy response to inference request in 1.8730442523956299s
5 requests
1 failed requests
5th percentile: 1.6464012622833253
10th percentile: 1.7030620098114013
20th percentile: 1.8163835048675536
30th percentile: 1.875413751602173
40th percentile: 1.8801527500152588
50th percentile: 1.8848917484283447
60th percentile: 2.157764959335327
70th percentile: 2.430638170242309
80th percentile: 6.0855645179748565
90th percentile: 13.122544002532962
95th percentile: 16.64103374481201
99th percentile: 19.455825538635253
mean time: 5.614854955673218
%s, retrying in %s seconds...
Received healthy response to inference request in 2.0495805740356445s
Received healthy response to inference request in 1.7804961204528809s
Received healthy response to inference request in 2.319502592086792s
Received healthy response to inference request in 2.0980794429779053s
Received healthy response to inference request in 1.723484754562378s
5 requests
0 failed requests
5th percentile: 1.7348870277404784
10th percentile: 1.7462893009185791
20th percentile: 1.7690938472747804
30th percentile: 1.8343130111694337
40th percentile: 1.941946792602539
50th percentile: 2.0495805740356445
60th percentile: 2.0689801216125487
70th percentile: 2.088379669189453
80th percentile: 2.1423640727996824
90th percentile: 2.230933332443237
95th percentile: 2.275217962265015
99th percentile: 2.3106456661224364
mean time: 1.9942286968231202
Pipeline stage StressChecker completed in 40.79s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.93s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.82s
Shutdown handler de-registered
junhua024-chai-02-full-06_v3 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
junhua024-chai-02-full-06_v3 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-02-full-06_v3 status is now torndown due to DeploymentManager action
junhua024-chai-02-full-06_v3 status is now torndown due to DeploymentManager action