developer_uid: bogoconic1
submission_id: chaiml-gy-exp59-dpo-gy-_79099_v1
model_name: chaiml-gy-exp59-dpo-gy-_79099_v1
model_group: ChaiML/gy-exp59-dpo-gy-d
status: torndown
timestamp: 2025-07-02T11:44:41+00:00
num_battles: 8023
num_wins: 3362
celo_rating: 1228.75
family_friendly_score: 0.7514000000000001
family_friendly_standard_error: 0.006112250649310776
submission_type: basic
model_repo: ChaiML/gy-exp59-dpo-gy-datamix-v2.5-orig-safe-grok-rerank-ep1
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.5905009426687492, 'latency_mean': 1.693301112651825, 'latency_p50': 1.7036010026931763, 'latency_p90': 1.853023600578308}, {'batch_size': 3, 'throughput': 1.0619496671151256, 'latency_mean': 2.8145401072502136, 'latency_p50': 2.8355787992477417, 'latency_p90': 3.0862791061401365}, {'batch_size': 5, 'throughput': 1.2808609028559195, 'latency_mean': 3.878415162563324, 'latency_p50': 3.90738582611084, 'latency_p90': 4.288370418548584}, {'batch_size': 6, 'throughput': 1.3373905218019142, 'latency_mean': 4.45584666967392, 'latency_p50': 4.452392339706421, 'latency_p90': 5.0201547861099245}, {'batch_size': 8, 'throughput': 1.4098588156802283, 'latency_mean': 5.634249490499497, 'latency_p50': 5.665392994880676, 'latency_p90': 6.261430478096008}, {'batch_size': 10, 'throughput': 1.430271244461223, 'latency_mean': 6.942815605401993, 'latency_p50': 6.8882763385772705, 'latency_p90': 7.977011370658874}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-gy-exp59-dpo-gy-_79099_v1
is_internal_developer: True
language_model: ChaiML/gy-exp59-dpo-gy-datamix-v2.5-orig-safe-grok-rerank-ep1
model_size: 13B
ranking_group: single
throughput_3p7s: 1.26
us_pacific_date: 2025-07-02
win_ratio: 0.41904524492085254
generation_params: {'temperature': 0.6, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['<|im_start|>', '\n', '<|im_end|>'], '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': 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-gy-exp59-dpo-gy-79099-v1-mkmlizer
Waiting for job on chaiml-gy-exp59-dpo-gy-79099-v1-mkmlizer to finish
chaiml-gy-exp59-dpo-gy-79099-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp59-dpo-gy-79099-v1-mkmlizer: ║ ║
chaiml-gy-exp59-dpo-gy-79099-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-gy-exp59-dpo-gy-79099-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-gy-exp59-dpo-gy-79099-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-gy-exp59-dpo-gy-79099-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-gy-exp59-dpo-gy-79099-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-gy-exp59-dpo-gy-79099-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-gy-exp59-dpo-gy-79099-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-gy-exp59-dpo-gy-79099-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-gy-exp59-dpo-gy-79099-v1-mkmlizer: ║ ║
chaiml-gy-exp59-dpo-gy-79099-v1-mkmlizer: ║ Version: 0.29.8 ║
chaiml-gy-exp59-dpo-gy-79099-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-gy-exp59-dpo-gy-79099-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-gy-exp59-dpo-gy-79099-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-gy-exp59-dpo-gy-79099-v1-mkmlizer: ║ ║
chaiml-gy-exp59-dpo-gy-79099-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-gy-exp59-dpo-gy-79099-v1-mkmlizer: ║ belonging to: ║
chaiml-gy-exp59-dpo-gy-79099-v1-mkmlizer: ║ ║
chaiml-gy-exp59-dpo-gy-79099-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-gy-exp59-dpo-gy-79099-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-gy-exp59-dpo-gy-79099-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-gy-exp59-dpo-gy-79099-v1-mkmlizer: ║ ║
chaiml-gy-exp59-dpo-gy-79099-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp59-dpo-gy-79099-v1-mkmlizer: Downloaded to shared memory in 42.049s
chaiml-gy-exp59-dpo-gy-79099-v1-mkmlizer: Checking if ChaiML/gy-exp59-dpo-gy-datamix-v2.5-orig-safe-grok-rerank-ep1 already exists in ChaiML
chaiml-gy-exp59-dpo-gy-79099-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpip9y9koz, device:0
chaiml-gy-exp59-dpo-gy-79099-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp59-dpo-gy-79099-v1-mkmlizer: quantized model in 30.331s
chaiml-gy-exp59-dpo-gy-79099-v1-mkmlizer: Processed model ChaiML/gy-exp59-dpo-gy-datamix-v2.5-orig-safe-grok-rerank-ep1 in 72.380s
chaiml-gy-exp59-dpo-gy-79099-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp59-dpo-gy-79099-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp59-dpo-gy-79099-v1/nvidia
chaiml-gy-exp59-dpo-gy-79099-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp59-dpo-gy-79099-v1/nvidia/special_tokens_map.json
chaiml-gy-exp59-dpo-gy-79099-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp59-dpo-gy-79099-v1/nvidia/config.json
chaiml-gy-exp59-dpo-gy-79099-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp59-dpo-gy-79099-v1/nvidia/tokenizer_config.json
chaiml-gy-exp59-dpo-gy-79099-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp59-dpo-gy-79099-v1/nvidia/tokenizer.json
chaiml-gy-exp59-dpo-gy-79099-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp59-dpo-gy-79099-v1/nvidia/flywheel_model.0.safetensors
Job chaiml-gy-exp59-dpo-gy-79099-v1-mkmlizer completed after 104.16s with status: succeeded
Stopping job with name chaiml-gy-exp59-dpo-gy-79099-v1-mkmlizer
Pipeline stage MKMLizer completed in 104.74s
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-gy-exp59-dpo-gy-79099-v1
Waiting for inference service chaiml-gy-exp59-dpo-gy-79099-v1 to be ready
Inference service chaiml-gy-exp59-dpo-gy-79099-v1 ready after 210.7337121963501s
Pipeline stage MKMLDeployer completed in 211.23s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9710674285888672s
Received healthy response to inference request in 1.672450304031372s
Received healthy response to inference request in 1.7892656326293945s
Received healthy response to inference request in 2.1956162452697754s
Received healthy response to inference request in 1.6945068836212158s
5 requests
0 failed requests
5th percentile: 1.676861619949341
10th percentile: 1.6812729358673095
20th percentile: 1.690095567703247
30th percentile: 1.7134586334228517
40th percentile: 1.751362133026123
50th percentile: 1.7892656326293945
60th percentile: 1.8619863510131835
70th percentile: 1.9347070693969726
80th percentile: 2.0159771919250487
90th percentile: 2.105796718597412
95th percentile: 2.150706481933594
99th percentile: 2.1866342926025393
mean time: 1.864581298828125
Pipeline stage StressChecker completed in 10.55s
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 0.65s
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-gy-exp59-dpo-gy-_79099_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-gy-exp59-dpo-gy-79099-v1-profiler
Waiting for inference service chaiml-gy-exp59-dpo-gy-79099-v1-profiler to be ready
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
Pipeline stage OfflineFamilyFriendlyScorer completed in 4888.36s
Shutdown handler de-registered
chaiml-gy-exp59-dpo-gy-_79099_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp59-dpo-gy-_79099_v1 status is now torndown due to DeploymentManager action