developer_uid: NischayDnk
submission_id: chaiml-mistral32-deepse_43457_v2
model_name: chaiml-mistral32-deepse_43457_v2
model_group: ChaiML/mistral32_deepsee
status: torndown
timestamp: 2025-07-08T15:09:57+00:00
num_battles: 11571
num_wins: 6129
celo_rating: 1317.88
family_friendly_score: 0.4858
family_friendly_standard_error: 0.0070682156164056
submission_type: basic
model_repo: ChaiML/mistral32_deepseekgrokpref_cpos2_sfts11306_seq96_exp7
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 6
max_input_tokens: 1536
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.4879506936642417, 'latency_mean': 2.0492902004718783, 'latency_p50': 2.0410892963409424, 'latency_p90': 2.2623040437698365}, {'batch_size': 3, 'throughput': 0.9411575257837967, 'latency_mean': 3.1753016078472136, 'latency_p50': 3.1860679388046265, 'latency_p90': 3.5444741964340207}, {'batch_size': 5, 'throughput': 1.1934366589147893, 'latency_mean': 4.1784352684021, 'latency_p50': 4.175644159317017, 'latency_p90': 4.691386795043945}, {'batch_size': 6, 'throughput': 1.2714588217098621, 'latency_mean': 4.681781357526779, 'latency_p50': 4.671104669570923, 'latency_p90': 5.257805442810058}, {'batch_size': 8, 'throughput': 1.3942920322246732, 'latency_mean': 5.707061964273453, 'latency_p50': 5.730068564414978, 'latency_p90': 6.403197932243347}, {'batch_size': 10, 'throughput': 1.4551089869277787, 'latency_mean': 6.802044216394425, 'latency_p50': 6.841779708862305, 'latency_p90': 7.65567352771759}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-mistral32-deepse_43457_v2
is_internal_developer: False
language_model: ChaiML/mistral32_deepseekgrokpref_cpos2_sfts11306_seq96_exp7
model_size: 24B
ranking_group: single
throughput_3p7s: 1.09
us_pacific_date: 2025-07-08
win_ratio: 0.5296862846772102
generation_params: {'temperature': 0.65, 'top_p': 0.94, 'min_p': 0.025, 'top_k': 80, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['<|im_start|>', '<|im_end|>', '\n', '</s>', '###'], 'max_input_tokens': 1536, 'best_of': 6, 'max_output_tokens': 64}
formatter: {'memory_template': '<|system|>Family Friendly{memory}\n', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\nYou:{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', '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-mistral32-deepse-43457-v2-mkmlizer
Waiting for job on chaiml-mistral32-deepse-43457-v2-mkmlizer to finish
chaiml-mistral32-deepse-43457-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral32-deepse-43457-v2-mkmlizer: ║ ║
chaiml-mistral32-deepse-43457-v2-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-mistral32-deepse-43457-v2-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-mistral32-deepse-43457-v2-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-mistral32-deepse-43457-v2-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-mistral32-deepse-43457-v2-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-mistral32-deepse-43457-v2-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-mistral32-deepse-43457-v2-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-mistral32-deepse-43457-v2-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-mistral32-deepse-43457-v2-mkmlizer: ║ ║
chaiml-mistral32-deepse-43457-v2-mkmlizer: ║ Version: 0.29.15 ║
chaiml-mistral32-deepse-43457-v2-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-mistral32-deepse-43457-v2-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-mistral32-deepse-43457-v2-mkmlizer: ║ https://mk1.ai ║
chaiml-mistral32-deepse-43457-v2-mkmlizer: ║ ║
chaiml-mistral32-deepse-43457-v2-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-mistral32-deepse-43457-v2-mkmlizer: ║ belonging to: ║
chaiml-mistral32-deepse-43457-v2-mkmlizer: ║ ║
chaiml-mistral32-deepse-43457-v2-mkmlizer: ║ Chai Research Corp. ║
chaiml-mistral32-deepse-43457-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-mistral32-deepse-43457-v2-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-mistral32-deepse-43457-v2-mkmlizer: ║ ║
chaiml-mistral32-deepse-43457-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral32-deepse-43457-v2-mkmlizer: Downloaded to shared memory in 196.413s
chaiml-mistral32-deepse-43457-v2-mkmlizer: Checking if ChaiML/mistral32_deepseekgrokpref_cpos2_sfts11306_seq96_exp7 already exists in ChaiML
chaiml-mistral32-deepse-43457-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp1u73vywt, device:0
chaiml-mistral32-deepse-43457-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral32-deepse-43457-v2-mkmlizer: quantized model in 48.717s
chaiml-mistral32-deepse-43457-v2-mkmlizer: Processed model ChaiML/mistral32_deepseekgrokpref_cpos2_sfts11306_seq96_exp7 in 245.132s
chaiml-mistral32-deepse-43457-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral32-deepse-43457-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral32-deepse-43457-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral32-deepse-43457-v2/nvidia
chaiml-mistral32-deepse-43457-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral32-deepse-43457-v2/nvidia/config.json
chaiml-mistral32-deepse-43457-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral32-deepse-43457-v2/nvidia/special_tokens_map.json
chaiml-mistral32-deepse-43457-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral32-deepse-43457-v2/nvidia/tokenizer_config.json
chaiml-mistral32-deepse-43457-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral32-deepse-43457-v2/nvidia/tokenizer.json
chaiml-mistral32-deepse-43457-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mistral32-deepse-43457-v2/nvidia/flywheel_model.1.safetensors
chaiml-mistral32-deepse-43457-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral32-deepse-43457-v2/nvidia/flywheel_model.0.safetensors
Job chaiml-mistral32-deepse-43457-v2-mkmlizer completed after 280.69s with status: succeeded
Stopping job with name chaiml-mistral32-deepse-43457-v2-mkmlizer
Pipeline stage MKMLizer completed in 281.18s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.51s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mistral32-deepse-43457-v2
Waiting for inference service chaiml-mistral32-deepse-43457-v2 to be ready
Failed to get response for submission chaiml-mistral32-deepse_16364_v1: ('http://chaiml-mistral32-deepse-16364-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:34108->127.0.0.1:8080: read: connection reset by peer\n')
Inference service chaiml-mistral32-deepse-43457-v2 ready after 231.4330050945282s
Pipeline stage MKMLDeployer completed in 231.96s
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 3.0817489624023438s
Received healthy response to inference request in 1.8489675521850586s
Received healthy response to inference request in 2.077629804611206s
Received healthy response to inference request in 2.259906530380249s
5 requests
1 failed requests
5th percentile: 1.894700002670288
10th percentile: 1.9404324531555175
20th percentile: 2.0318973541259764
30th percentile: 2.114085149765015
40th percentile: 2.186995840072632
50th percentile: 2.259906530380249
60th percentile: 2.5886435031890866
70th percentile: 2.9173804759979247
80th percentile: 6.491369152069095
90th percentile: 13.31060953140259
95th percentile: 16.720229721069334
99th percentile: 19.447925872802735
mean time: 5.879620552062988
%s, retrying in %s seconds...
Received healthy response to inference request in 2.0163750648498535s
Received healthy response to inference request in 1.8757801055908203s
Received healthy response to inference request in 2.0230321884155273s
Received healthy response to inference request in 1.8497912883758545s
Received healthy response to inference request in 9.32569432258606s
5 requests
0 failed requests
5th percentile: 1.8549890518188477
10th percentile: 1.8601868152618408
20th percentile: 1.8705823421478271
30th percentile: 1.9038990974426269
40th percentile: 1.9601370811462402
50th percentile: 2.0163750648498535
60th percentile: 2.0190379142761232
70th percentile: 2.0217007637023925
80th percentile: 3.483564615249635
90th percentile: 6.404629468917847
95th percentile: 7.865161895751951
99th percentile: 9.033587837219239
mean time: 3.418134593963623
Pipeline stage StressChecker completed in 49.70s
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 0.90s
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 0.66s
Shutdown handler de-registered
chaiml-mistral32-deepse_43457_v2 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 3329.61s
Shutdown handler de-registered
chaiml-mistral32-deepse_43457_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral32-deepse_43457_v2 status is now torndown due to DeploymentManager action