chaiml-anthropic-40k-2_11629

developer_uid: NischayDnk

submission_id: chaiml-anthropic-40k-2_11629_v14

model_name: chaiml-anthropic-40k-2_11629_v14

model_group: ChaiML/anthropic_40k_249

status: torndown

timestamp: 2025-07-18T21:44:46+00:00

num_battles: 5719

num_wins: 2890

celo_rating: 1291.62

family_friendly_score: 0.4908

family_friendly_standard_error: 0.007069870720175865

submission_type: basic

model_repo: ChaiML/anthropic_40k_2496_bo8_85w_b4_l1_merged

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 768

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.6240896915143503, 'latency_mean': 1.6021911406517029, 'latency_p50': 1.6020463705062866, 'latency_p90': 1.7543593168258667}, {'batch_size': 3, 'throughput': 1.1913903144576197, 'latency_mean': 2.504938688278198, 'latency_p50': 2.5127967596054077, 'latency_p90': 2.738334584236145}, {'batch_size': 5, 'throughput': 1.4555904507166306, 'latency_mean': 3.4192508161067963, 'latency_p50': 3.425039529800415, 'latency_p90': 3.7880344152450562}, {'batch_size': 6, 'throughput': 1.5321545110031607, 'latency_mean': 3.8822548294067385, 'latency_p50': 3.9088751077651978, 'latency_p90': 4.3402492046356205}, {'batch_size': 8, 'throughput': 1.6170287573483961, 'latency_mean': 4.907696615457535, 'latency_p50': 4.933409690856934, 'latency_p90': 5.4637175559997555}, {'batch_size': 10, 'throughput': 1.6553468134548976, 'latency_mean': 5.992175707817077, 'latency_p50': 6.0912216901779175, 'latency_p90': 6.699106192588806}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-anthropic-40k-2_11629_v14

ineligible_reason: num_battles<10000

is_internal_developer: False

language_model: ChaiML/anthropic_40k_2496_bo8_85w_b4_l1_merged

model_size: 13B

ranking_group: single

throughput_3p7s: 1.52

us_pacific_date: 2025-07-18

win_ratio: 0.5053331001923413

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<|eot_id|>', 'You:', '<|end_of_text|>', '\n'], 'max_input_tokens': 768, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '### Response:\n{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 chaiml-anthropic-40k-2-11629-v14-mkmlizer
Waiting for job on chaiml-anthropic-40k-2-11629-v14-mkmlizer to finish
chaiml-anthropic-40k-2-11629-v14-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-anthropic-40k-2-11629-v14-mkmlizer: ║                                                                     ║
chaiml-anthropic-40k-2-11629-v14-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-anthropic-40k-2-11629-v14-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-anthropic-40k-2-11629-v14-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-anthropic-40k-2-11629-v14-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-anthropic-40k-2-11629-v14-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-anthropic-40k-2-11629-v14-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-anthropic-40k-2-11629-v14-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-anthropic-40k-2-11629-v14-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-anthropic-40k-2-11629-v14-mkmlizer: ║                                                                     ║
chaiml-anthropic-40k-2-11629-v14-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-anthropic-40k-2-11629-v14-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-anthropic-40k-2-11629-v14-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-anthropic-40k-2-11629-v14-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-anthropic-40k-2-11629-v14-mkmlizer: ║                                                                     ║
chaiml-anthropic-40k-2-11629-v14-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-anthropic-40k-2-11629-v14-mkmlizer: ║  belonging to:                                                      ║
chaiml-anthropic-40k-2-11629-v14-mkmlizer: ║                                                                     ║
chaiml-anthropic-40k-2-11629-v14-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-anthropic-40k-2-11629-v14-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-anthropic-40k-2-11629-v14-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-anthropic-40k-2-11629-v14-mkmlizer: ║                                                                     ║
chaiml-anthropic-40k-2-11629-v14-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-anthropic-40k-2-11629-v14-mkmlizer: Downloaded to shared memory in 81.342s
chaiml-anthropic-40k-2-11629-v14-mkmlizer: Checking if ChaiML/anthropic_40k_2496_bo8_85w_b4_l1_merged already exists in ChaiML
chaiml-anthropic-40k-2-11629-v14-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpl2z_i_3z, device:0
chaiml-anthropic-40k-2-11629-v14-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission blend_fader_2025-07-10: ('http://chaiml-cogito32b-dpos2-39363-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:58136->127.0.0.1:8080: read: connection reset by peer\n')
chaiml-anthropic-40k-2-11629-v14-mkmlizer: quantized model in 36.553s
chaiml-anthropic-40k-2-11629-v14-mkmlizer: Processed model ChaiML/anthropic_40k_2496_bo8_85w_b4_l1_merged in 117.895s
chaiml-anthropic-40k-2-11629-v14-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-anthropic-40k-2-11629-v14-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-anthropic-40k-2-11629-v14/nvidia
chaiml-anthropic-40k-2-11629-v14-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-anthropic-40k-2-11629-v14/nvidia/config.json
chaiml-anthropic-40k-2-11629-v14-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-anthropic-40k-2-11629-v14/nvidia/special_tokens_map.json
chaiml-anthropic-40k-2-11629-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-anthropic-40k-2-11629-v14/nvidia/tokenizer_config.json
chaiml-anthropic-40k-2-11629-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-anthropic-40k-2-11629-v14/nvidia/tokenizer.json
chaiml-anthropic-40k-2-11629-v14-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-anthropic-40k-2-11629-v14/nvidia/flywheel_model.0.safetensors
chaiml-anthropic-40k-2-11629-v14-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 22.13it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 27.81it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:14, 24.46it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:11, 31.01it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:14, 23.15it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:16, 19.98it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:13, 25.17it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:13, 25.01it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 27.66it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:12, 24.80it/s]
Loading 0:  13%|█▎        | 47/363 [00:01<00:10, 30.35it/s]
Loading 0:  14%|█▍        | 51/363 [00:02<00:12, 25.14it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:11, 27.65it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:10, 29.28it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:17, 17.55it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:13, 22.40it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:12, 22.70it/s]
Loading 0:  21%|██        | 77/363 [00:03<00:13, 21.61it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 26.57it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 23.94it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:09, 28.57it/s]
Loading 0:  26%|██▌       | 95/363 [00:03<00:10, 25.41it/s]
Loading 0:  28%|██▊       | 100/363 [00:03<00:08, 30.14it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:13, 18.94it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:10, 23.62it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:11, 22.29it/s]
Loading 0:  33%|███▎      | 118/363 [00:04<00:09, 27.14it/s]
Loading 0:  34%|███▎      | 122/363 [00:04<00:09, 24.61it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:07, 30.32it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:08, 28.74it/s]
Loading 0:  38%|███▊      | 137/363 [00:05<00:08, 27.69it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:07, 30.04it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:10, 20.60it/s]
Loading 0:  41%|████      | 149/363 [00:06<00:10, 20.26it/s]
Loading 0:  43%|████▎     | 156/363 [00:06<00:07, 26.51it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:07, 25.95it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:06, 28.34it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:07, 27.48it/s]
Loading 0:  47%|████▋     | 172/363 [00:06<00:06, 27.67it/s]
Loading 0:  48%|████▊     | 176/363 [00:07<00:07, 24.32it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:06, 28.97it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:09, 18.38it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 23.14it/s]
Loading 0:  53%|█████▎    | 194/363 [00:07<00:07, 21.70it/s]
Loading 0:  55%|█████▍    | 199/363 [00:07<00:06, 26.27it/s]
Loading 0:  56%|█████▌    | 203/363 [00:08<00:06, 23.83it/s]
Loading 0:  57%|█████▋    | 208/363 [00:08<00:05, 28.42it/s]
Loading 0:  58%|█████▊    | 212/363 [00:08<00:06, 25.13it/s]
Loading 0:  60%|█████▉    | 217/363 [00:08<00:04, 29.91it/s]
Loading 0:  61%|██████    | 222/363 [00:08<00:04, 31.14it/s]
Loading 0:  62%|██████▏   | 226/363 [00:09<00:06, 21.24it/s]
Loading 0:  63%|██████▎   | 230/363 [00:09<00:06, 20.78it/s]
Loading 0:  65%|██████▍   | 235/363 [00:09<00:04, 25.73it/s]
Loading 0:  66%|██████▌   | 239/363 [00:09<00:05, 23.80it/s]
Loading 0:  67%|██████▋   | 244/363 [00:09<00:04, 28.55it/s]
Loading 0:  68%|██████▊   | 248/363 [00:09<00:04, 25.41it/s]
Loading 0:  70%|██████▉   | 253/363 [00:10<00:03, 30.14it/s]
Loading 0:  71%|███████   | 257/363 [00:10<00:04, 26.38it/s]
Loading 0:  72%|███████▏  | 263/363 [00:10<00:04, 24.26it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:04, 21.54it/s]
Loading 0:  75%|███████▌  | 273/363 [00:10<00:03, 27.66it/s]
Loading 0:  76%|███████▋  | 277/363 [00:11<00:03, 26.97it/s]
Loading 0:  78%|███████▊  | 282/363 [00:11<00:02, 28.87it/s]
Loading 0:  79%|███████▉  | 286/363 [00:11<00:02, 27.64it/s]
Loading 0:  80%|████████  | 291/363 [00:11<00:02, 29.42it/s]
Loading 0:  81%|████████▏ | 295/363 [00:11<00:02, 28.18it/s]
Loading 0:  82%|████████▏ | 299/363 [00:11<00:02, 28.42it/s]
Loading 0:  84%|████████▎ | 304/363 [00:12<00:02, 23.77it/s]
Loading 0:  85%|████████▍ | 307/363 [00:12<00:02, 22.71it/s]
Loading 0:  86%|████████▌ | 311/363 [00:12<00:02, 21.64it/s]
Loading 0:  87%|████████▋ | 316/363 [00:12<00:01, 26.15it/s]
Loading 0:  88%|████████▊ | 320/363 [00:12<00:01, 24.13it/s]
Loading 0:  90%|█████████ | 327/363 [00:12<00:01, 30.59it/s]
Loading 0:  91%|█████████ | 331/363 [00:13<00:01, 29.23it/s]
Loading 0:  93%|█████████▎| 336/363 [00:13<00:00, 30.96it/s]
Loading 0:  94%|█████████▎| 340/363 [00:13<00:00, 29.42it/s]
Loading 0:  95%|█████████▍| 344/363 [00:13<00:01, 14.74it/s]
Loading 0:  96%|█████████▌| 348/363 [00:14<00:00, 16.04it/s]
Loading 0:  97%|█████████▋| 353/363 [00:14<00:00, 19.39it/s]
Loading 0:  98%|█████████▊| 357/363 [00:14<00:00, 20.02it/s]
                                                            
Job chaiml-anthropic-40k-2-11629-v14-mkmlizer completed after 333.86s with status: succeeded
Stopping job with name chaiml-anthropic-40k-2-11629-v14-mkmlizer
Pipeline stage MKMLizer completed in 334.40s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-anthropic-40k-2-11629-v14
Waiting for inference service chaiml-anthropic-40k-2-11629-v14 to be ready
Inference service chaiml-anthropic-40k-2-11629-v14 ready after 312.1571755409241s
Pipeline stage MKMLDeployer completed in 312.75s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5345418453216553s
Received healthy response to inference request in 2.006693124771118s
Received healthy response to inference request in 1.624025583267212s
Received healthy response to inference request in 1.4344587326049805s
Received healthy response to inference request in 1.7061631679534912s
5 requests
0 failed requests
5th percentile: 1.4723721027374268
10th percentile: 1.5102854728698731
20th percentile: 1.5861122131347656
30th percentile: 1.6404531002044678
40th percentile: 1.6733081340789795
50th percentile: 1.7061631679534912
60th percentile: 1.826375150680542
70th percentile: 1.9465871334075928
80th percentile: 2.1122628688812255
90th percentile: 2.3234023571014406
95th percentile: 2.428972101211548
99th percentile: 2.5134278964996337
mean time: 1.8611764907836914
Pipeline stage StressChecker completed in 11.18s
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 0.68s
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 0.67s
Shutdown handler de-registered
chaiml-anthropic-40k-2_11629_v14 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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2661.50s
Shutdown handler de-registered
chaiml-anthropic-40k-2_11629_v14 status is now inactive due to auto deactivation removed underperforming models
chaiml-anthropic-40k-2_11629_v14 status is now torndown due to DeploymentManager action
chaiml-anthropic-40k-2_11629_v14 status is now torndown due to DeploymentManager action