developer_uid: bogoconic1
submission_id: chaiml-gy-exp22-sftqwen_85596_v1
model_name: chaiml-gy-exp22-sftqwen_85596_v1
model_group: ChaiML/gy-exp22-sftqwen2
status: torndown
timestamp: 2025-06-27T06:44:50+00:00
num_battles: 6967
num_wins: 3239
celo_rating: 1252.59
family_friendly_score: 0.5436000000000001
family_friendly_standard_error: 0.007044132877792696
submission_type: basic
model_repo: ChaiML/gy-exp22-sftqwen25-7b-gy-1266-1301-7850-pref-grok-ctx2500-96tok-onlylast-ep2
model_architecture: Qwen2ForCausalLM
model_num_parameters: 7615487488.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.8723221594825153, 'latency_mean': 1.146182551383972, 'latency_p50': 1.1498607397079468, 'latency_p90': 1.2696241378784179}, {'batch_size': 4, 'throughput': 1.8303837180028426, 'latency_mean': 2.1758696746826174, 'latency_p50': 2.169369339942932, 'latency_p90': 2.425405406951904}, {'batch_size': 5, 'throughput': 1.9763941680995547, 'latency_mean': 2.5177475738525392, 'latency_p50': 2.5109745264053345, 'latency_p90': 2.816700267791748}, {'batch_size': 8, 'throughput': 2.173064459360012, 'latency_mean': 3.6527631378173826, 'latency_p50': 3.67730975151062, 'latency_p90': 4.065970158576965}, {'batch_size': 10, 'throughput': 2.2235998930384953, 'latency_mean': 4.450666913986206, 'latency_p50': 4.4458247423172, 'latency_p90': 5.034627914428711}, {'batch_size': 12, 'throughput': 2.25041038777456, 'latency_mean': 5.280779855251312, 'latency_p50': 5.228497624397278, 'latency_p90': 5.925209212303161}, {'batch_size': 15, 'throughput': 2.2861569198942373, 'latency_mean': 6.468900129795075, 'latency_p50': 6.455405831336975, 'latency_p90': 7.237784743309021}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-gy-exp22-sftqwen_85596_v1
is_internal_developer: True
language_model: ChaiML/gy-exp22-sftqwen25-7b-gy-1266-1301-7850-pref-grok-ctx2500-96tok-onlylast-ep2
model_size: 8B
ranking_group: single
throughput_3p7s: 2.19
us_pacific_date: 2025-06-26
win_ratio: 0.4649059853595522
generation_params: {'temperature': 0.8, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['\n', '<|im_end|>', '<|im_start|>'], 'max_input_tokens': 1024, 'best_of': 8, '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': 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-gy-exp22-sftqwen-85596-v1-mkmlizer
Waiting for job on chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer to finish
chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer: ║ ║
chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer: ║ ║
chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer: ║ Version: 0.29.3 ║
chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer: ║ ║
chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer: ║ belonging to: ║
chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer: ║ ║
chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer: ║ ║
chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer: Downloaded to shared memory in 27.934s
chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer: Checking if ChaiML/gy-exp22-sftqwen25-7b-gy-1266-1301-7850-pref-grok-ctx2500-96tok-onlylast-ep2 already exists in ChaiML
chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3iusx3_f, device:0
chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer: quantized model in 22.413s
chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer: Processed model ChaiML/gy-exp22-sftqwen25-7b-gy-1266-1301-7850-pref-grok-ctx2500-96tok-onlylast-ep2 in 50.347s
chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp22-sftqwen-85596-v1
chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp22-sftqwen-85596-v1/config.json
chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-gy-exp22-sftqwen-85596-v1/added_tokens.json
chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp22-sftqwen-85596-v1/special_tokens_map.json
chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp22-sftqwen-85596-v1/tokenizer_config.json
chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-gy-exp22-sftqwen-85596-v1/merges.txt
chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-gy-exp22-sftqwen-85596-v1/vocab.json
chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp22-sftqwen-85596-v1/tokenizer.json
chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp22-sftqwen-85596-v1/flywheel_model.0.safetensors
Job chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer completed after 75.52s with status: succeeded
Stopping job with name chaiml-gy-exp22-sftqwen-85596-v1-mkmlizer
Pipeline stage MKMLizer completed in 76.16s
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-gy-exp22-sftqwen-85596-v1
Waiting for inference service chaiml-gy-exp22-sftqwen-85596-v1 to be ready
Inference service chaiml-gy-exp22-sftqwen-85596-v1 ready after 150.9456045627594s
Pipeline stage MKMLDeployer completed in 151.80s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8656213283538818s
Received healthy response to inference request in 1.2180442810058594s
Received healthy response to inference request in 1.2673816680908203s
Received healthy response to inference request in 1.3293745517730713s
Received healthy response to inference request in 1.2301640510559082s
5 requests
0 failed requests
5th percentile: 1.220468235015869
10th percentile: 1.2228921890258788
20th percentile: 1.2277400970458985
30th percentile: 1.2376075744628907
40th percentile: 1.2524946212768555
50th percentile: 1.2673816680908203
60th percentile: 1.2921788215637207
70th percentile: 1.316975975036621
80th percentile: 1.4366239070892335
90th percentile: 1.6511226177215577
95th percentile: 1.7583719730377196
99th percentile: 1.8441714572906494
mean time: 1.3821171760559081
Pipeline stage StressChecker completed in 8.16s
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 0.71s
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 0.65s
Shutdown handler de-registered
chaiml-gy-exp22-sftqwen_85596_v1 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 2773.66s
Shutdown handler de-registered
chaiml-gy-exp22-sftqwen_85596_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp22-sftqwen_85596_v1 status is now torndown due to DeploymentManager action