developer_uid: rirv938
submission_id: chaiml-4d70-fd43-linear-w01_v14
model_name: chaiml-4d70-fd43-linear-w01_v14
model_group: ChaiML/4d70-fd43-linear-
status: torndown
timestamp: 2025-12-12T18:26:55+00:00
num_battles: 6518
num_wins: 3326
celo_rating: 1306.16
family_friendly_score: 0.513
family_friendly_standard_error: 0.007068677386894949
submission_type: basic
model_repo: ChaiML/4d70-fd43-linear-w01
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1800
max_output_tokens: 74
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.6273240290229107, 'latency_mean': 1.5939483797550202, 'latency_p50': 1.591894268989563, 'latency_p90': 1.7393802404403687}, {'batch_size': 3, 'throughput': 1.2456642484311466, 'latency_mean': 2.4030155789852143, 'latency_p50': 2.4102883338928223, 'latency_p90': 2.621349811553955}, {'batch_size': 5, 'throughput': 1.552292948839709, 'latency_mean': 3.202370346784592, 'latency_p50': 3.1942700147628784, 'latency_p90': 3.5112936973571776}, {'batch_size': 6, 'throughput': 1.661019803368241, 'latency_mean': 3.581993879079819, 'latency_p50': 3.584674596786499, 'latency_p90': 4.072545599937439}, {'batch_size': 8, 'throughput': 1.8184792161654917, 'latency_mean': 4.364115401506424, 'latency_p50': 4.3624643087387085, 'latency_p90': 4.866367769241333}, {'batch_size': 10, 'throughput': 1.8919749293780985, 'latency_mean': 5.230698528289795, 'latency_p50': 5.270765066146851, 'latency_p90': 5.965076208114624}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: chaiml-4d70-fd43-linear-w01_v14
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/4d70-fd43-linear-w01
model_size: 13B
ranking_group: single
throughput_3p7s: 1.7
us_pacific_date: 2025-11-26
win_ratio: 0.5102792267566738
generation_params: {'temperature': 0.65, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.08, 'frequency_penalty': 0.08, 'stopping_words': ['<|im_start|>', '\n', '###', '<|im_end|>', '</s>'], 'max_input_tokens': 1800, 'best_of': 8, 'max_output_tokens': 74}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': True}
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-4d70-fd43-linear-w01-v14-mkmlizer
Waiting for job on chaiml-4d70-fd43-linear-w01-v14-mkmlizer to finish
chaiml-4d70-fd43-linear-w01-v14-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-4d70-fd43-linear-w01-v14-mkmlizer: ║ ║
chaiml-4d70-fd43-linear-w01-v14-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-4d70-fd43-linear-w01-v14-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-4d70-fd43-linear-w01-v14-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-4d70-fd43-linear-w01-v14-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-4d70-fd43-linear-w01-v14-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-4d70-fd43-linear-w01-v14-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-4d70-fd43-linear-w01-v14-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-4d70-fd43-linear-w01-v14-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-4d70-fd43-linear-w01-v14-mkmlizer: ║ ║
chaiml-4d70-fd43-linear-w01-v14-mkmlizer: ║ Version: 0.30.2 ║
chaiml-4d70-fd43-linear-w01-v14-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-4d70-fd43-linear-w01-v14-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-4d70-fd43-linear-w01-v14-mkmlizer: ║ https://mk1.ai ║
chaiml-4d70-fd43-linear-w01-v14-mkmlizer: ║ ║
chaiml-4d70-fd43-linear-w01-v14-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-4d70-fd43-linear-w01-v14-mkmlizer: ║ belonging to: ║
chaiml-4d70-fd43-linear-w01-v14-mkmlizer: ║ ║
chaiml-4d70-fd43-linear-w01-v14-mkmlizer: ║ Chai Research Corp. ║
chaiml-4d70-fd43-linear-w01-v14-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-4d70-fd43-linear-w01-v14-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-4d70-fd43-linear-w01-v14-mkmlizer: ║ ║
chaiml-4d70-fd43-linear-w01-v14-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-4d70-fd43-linear-w01-v14-mkmlizer: Downloaded to shared memory in 26.493s
chaiml-4d70-fd43-linear-w01-v14-mkmlizer: Checking if ChaiML/4d70-fd43-linear-w01 already exists in ChaiML
chaiml-4d70-fd43-linear-w01-v14-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3iuev8wg, device:0
chaiml-4d70-fd43-linear-w01-v14-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission chaiml-02f4-69d4-linear-w01_v8: ('http://guanaco-model-mesh-load-balancer.model-mesh.k2.chaiverse.com/models/chaiml-02f4-69d4-linear-w01_v8/predict', '{"detail":"503, message=\'Attempt to decode JSON with unexpected mimetype: text/plain\', url=\'http://10.3.204.171:8080/models/chaiml-02f4-69d4-linear-w01_v8/predict\'"}')
chaiml-4d70-fd43-linear-w01-v14-mkmlizer: quantized model in 26.581s
chaiml-4d70-fd43-linear-w01-v14-mkmlizer: Processed model ChaiML/4d70-fd43-linear-w01 in 53.074s
chaiml-4d70-fd43-linear-w01-v14-mkmlizer: creating bucket guanaco-mkml-models
chaiml-4d70-fd43-linear-w01-v14-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-4d70-fd43-linear-w01-v14-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-4d70-fd43-linear-w01-v14/nvidia
chaiml-4d70-fd43-linear-w01-v14-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-4d70-fd43-linear-w01-v14/nvidia/config.json
chaiml-4d70-fd43-linear-w01-v14-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-4d70-fd43-linear-w01-v14/nvidia/special_tokens_map.json
chaiml-4d70-fd43-linear-w01-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-4d70-fd43-linear-w01-v14/nvidia/tokenizer_config.json
chaiml-4d70-fd43-linear-w01-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-4d70-fd43-linear-w01-v14/nvidia/tokenizer.json
chaiml-4d70-fd43-linear-w01-v14-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-4d70-fd43-linear-w01-v14/nvidia/flywheel_model.0.safetensors
chaiml-4d70-fd43-linear-w01-v14-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 2/363 [00:05<16:25, 2.73s/it] Loading 0: 2%|▏ | 6/363 [00:05<04:22, 1.36it/s] Loading 0: 4%|▍ | 14/363 [00:05<01:25, 4.06it/s] Loading 0: 6%|▌ | 20/363 [00:05<00:51, 6.61it/s] Loading 0: 7%|▋ | 25/363 [00:05<00:36, 9.28it/s] Loading 0: 9%|▉ | 32/363 [00:06<00:23, 14.20it/s] Loading 0: 10%|█ | 38/363 [00:06<00:17, 18.61it/s] Loading 0: 12%|█▏ | 44/363 [00:06<00:16, 19.40it/s] Loading 0: 14%|█▍ | 51/363 [00:06<00:12, 24.13it/s] Loading 0: 16%|█▋ | 59/363 [00:06<00:09, 32.14it/s] Loading 0: 18%|█▊ | 65/363 [00:06<00:08, 35.34it/s] Loading 0: 20%|█▉ | 71/363 [00:06<00:07, 39.41it/s] Loading 0: 21%|██▏ | 78/363 [00:07<00:07, 40.64it/s] Loading 0: 24%|██▎ | 86/363 [00:07<00:05, 48.60it/s] Loading 0: 25%|██▌ | 92/363 [00:07<00:05, 48.80it/s] Loading 0: 27%|██▋ | 98/363 [00:07<00:05, 50.07it/s] Loading 0: 29%|██▉ | 105/363 [00:07<00:05, 48.04it/s] Loading 0: 31%|███▏ | 114/363 [00:07<00:04, 50.60it/s] Loading 0: 33%|███▎ | 121/363 [00:07<00:05, 43.25it/s] Loading 0: 35%|███▍ | 126/363 [00:08<00:05, 44.26it/s] Loading 0: 36%|███▋ | 132/363 [00:08<00:05, 42.21it/s] Loading 0: 39%|███▉ | 141/363 [00:08<00:04, 46.70it/s] Loading 0: 41%|████ | 149/363 [00:08<00:03, 53.76it/s] Loading 0: 43%|████▎ | 155/363 [00:08<00:03, 52.73it/s] Loading 0: 44%|████▍ | 161/363 [00:08<00:03, 53.30it/s] Loading 0: 46%|████▋ | 168/363 [00:08<00:03, 49.87it/s] Loading 0: 48%|████▊ | 176/363 [00:09<00:03, 56.66it/s] Loading 0: 50%|█████ | 182/363 [00:09<00:03, 54.33it/s] Loading 0: 52%|█████▏ | 188/363 [00:09<00:03, 54.03it/s] Loading 0: 54%|█████▎ | 195/363 [00:09<00:03, 50.51it/s] Loading 0: 56%|█████▌ | 202/363 [00:09<00:03, 42.33it/s] Loading 0: 57%|█████▋ | 208/363 [00:09<00:03, 45.77it/s] Loading 0: 59%|█████▊ | 213/363 [00:09<00:03, 42.47it/s] Loading 0: 61%|██████ | 221/363 [00:09<00:02, 50.82it/s] Loading 0: 63%|██████▎ | 227/363 [00:10<00:02, 48.91it/s] Loading 0: 64%|██████▍ | 233/363 [00:10<00:02, 48.80it/s] Loading 0: 66%|██████▌ | 240/363 [00:10<00:02, 47.12it/s] Loading 0: 68%|██████▊ | 248/363 [00:10<00:02, 54.76it/s] Loading 0: 70%|██████▉ | 254/363 [00:10<00:02, 47.90it/s] Loading 0: 72%|███████▏ | 260/363 [00:10<00:02, 47.09it/s] Loading 0: 73%|███████▎ | 266/363 [00:10<00:01, 50.09it/s] Loading 0: 75%|███████▍ | 272/363 [00:11<00:01, 47.12it/s] Loading 0: 76%|███████▋ | 277/363 [00:11<00:01, 47.07it/s] Loading 0: 78%|███████▊ | 283/363 [00:11<00:02, 38.50it/s] Loading 0: 79%|███████▉ | 288/363 [00:11<00:01, 39.90it/s] Loading 0: 81%|████████ | 294/363 [00:11<00:01, 39.07it/s] Loading 0: 83%|████████▎ | 303/363 [00:11<00:01, 44.40it/s] Loading 0: 86%|████████▌ | 311/363 [00:11<00:00, 52.02it/s] Loading 0: 87%|████████▋ | 317/363 [00:12<00:00, 49.78it/s] Loading 0: 89%|████████▉ | 323/363 [00:12<00:00, 51.44it/s] Loading 0: 91%|█████████ | 330/363 [00:12<00:00, 49.60it/s] Loading 0: 93%|█████████▎| 338/363 [00:12<00:00, 56.74it/s] Loading 0: 95%|█████████▍| 344/363 [00:12<00:00, 54.32it/s] Loading 0: 96%|█████████▋| 350/363 [00:12<00:00, 54.53it/s] Loading 0: 98%|█████████▊| 357/363 [00:12<00:00, 50.06it/s]
Job chaiml-4d70-fd43-linear-w01-v14-mkmlizer completed after 145.76s with status: succeeded
Stopping job with name chaiml-4d70-fd43-linear-w01-v14-mkmlizer
Pipeline stage MKMLizer completed in 146.27s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-4d70-fd43-linear-w01-v14
Waiting for inference service chaiml-4d70-fd43-linear-w01-v14 to be ready
Inference service chaiml-4d70-fd43-linear-w01-v14 ready after 161.38419222831726s
Pipeline stage MKMLDeployer completed in 162.12s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8696913719177246s
Received healthy response to inference request in 1.4546856880187988s
Received healthy response to inference request in 1.890489101409912s
Received healthy response to inference request in 1.7575085163116455s
Received healthy response to inference request in 1.513063907623291s
5 requests
0 failed requests
5th percentile: 1.4663613319396973
10th percentile: 1.4780369758605958
20th percentile: 1.5013882637023925
30th percentile: 1.561952829360962
40th percentile: 1.6597306728363037
50th percentile: 1.7575085163116455
60th percentile: 1.802381658554077
70th percentile: 1.8472548007965088
80th percentile: 1.8738509178161622
90th percentile: 1.8821700096130372
95th percentile: 1.8863295555114745
99th percentile: 1.8896571922302245
mean time: 1.6970877170562744
Pipeline stage StressChecker completed in 10.09s
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 0.61s
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 0.63s
Shutdown handler de-registered
chaiml-4d70-fd43-linear-w01_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 2807.58s
Shutdown handler de-registered
chaiml-4d70-fd43-linear-w01_v14 status is now inactive due to auto deactivation removed underperforming models
chaiml-4d70-fd43-linear-w01_v14 status is now torndown due to DeploymentManager action