developer_uid: rirv938
submission_id: chaiml-anthropic-grpo-4_59715_v1
model_name: chaiml-anthropic-grpo-4_59715_v1
model_group: ChaiML/anthropic_grpo_40
status: torndown
timestamp: 2025-05-15T22:52:25+00:00
num_battles: 5913
num_wins: 3252
celo_rating: 1324.76
family_friendly_score: 0.5542
family_friendly_standard_error: 0.007029400543431851
submission_type: basic
model_repo: ChaiML/anthropic_grpo_40k_cp888_95ff_20ww2_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': 0.6469968110505808, 'latency_mean': 1.5455383944511414, 'latency_p50': 1.539588212966919, 'latency_p90': 1.725915503501892}, {'batch_size': 3, 'throughput': 1.2373307593998857, 'latency_mean': 2.4234475791454315, 'latency_p50': 2.4203399419784546, 'latency_p90': 2.6616355180740356}, {'batch_size': 5, 'throughput': 1.5324220377241222, 'latency_mean': 3.24302494764328, 'latency_p50': 3.217372417449951, 'latency_p90': 3.624362754821777}, {'batch_size': 6, 'throughput': 1.622547746544721, 'latency_mean': 3.668964967727661, 'latency_p50': 3.6682575941085815, 'latency_p90': 4.117830204963684}, {'batch_size': 8, 'throughput': 1.7268764544323407, 'latency_mean': 4.5917597305774684, 'latency_p50': 4.588817238807678, 'latency_p90': 5.205841684341431}, {'batch_size': 10, 'throughput': 1.7723278622395287, 'latency_mean': 5.5818124294281, 'latency_p50': 5.586091041564941, 'latency_p90': 6.3990442752838135}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-anthropic-grpo-4_59715_v1
is_internal_developer: True
language_model: ChaiML/anthropic_grpo_40k_cp888_95ff_20ww2_merged
model_size: 13B
ranking_group: single
throughput_3p7s: 1.64
us_pacific_date: 2025-05-15
win_ratio: 0.549974632166413
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '###', 'You:'], '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': '{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-grpo-4-59715-v1-mkmlizer
Waiting for job on chaiml-anthropic-grpo-4-59715-v1-mkmlizer to finish
chaiml-anthropic-grpo-4-59715-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-anthropic-grpo-4-59715-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-anthropic-grpo-4-59715-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-anthropic-grpo-4-59715-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-anthropic-grpo-4-59715-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-anthropic-grpo-4-59715-v1-mkmlizer: ║       /___/                                                         ║
chaiml-anthropic-grpo-4-59715-v1-mkmlizer: ║                                                                     ║
chaiml-anthropic-grpo-4-59715-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-anthropic-grpo-4-59715-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-anthropic-grpo-4-59715-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-anthropic-grpo-4-59715-v1-mkmlizer: ║                                                                     ║
chaiml-anthropic-grpo-4-59715-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-anthropic-grpo-4-59715-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-anthropic-grpo-4-59715-v1-mkmlizer: ║                                                                     ║
chaiml-anthropic-grpo-4-59715-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-anthropic-grpo-4-59715-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-anthropic-grpo-4-59715-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-anthropic-grpo-4-59715-v1-mkmlizer: ║                                                                     ║
chaiml-anthropic-grpo-4-59715-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-anthropic-grpo-4-59715-v1-mkmlizer: Downloaded to shared memory in 71.938s
chaiml-anthropic-grpo-4-59715-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp7pfjznh3, device:0
chaiml-anthropic-grpo-4-59715-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-anthropic-grpo-4-59715-v1-mkmlizer: quantized model in 44.847s
chaiml-anthropic-grpo-4-59715-v1-mkmlizer: Processed model ChaiML/anthropic_grpo_40k_cp888_95ff_20ww2_merged in 116.786s
chaiml-anthropic-grpo-4-59715-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-anthropic-grpo-4-59715-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-anthropic-grpo-4-59715-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-anthropic-grpo-4-59715-v1
chaiml-anthropic-grpo-4-59715-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-anthropic-grpo-4-59715-v1/config.json
chaiml-anthropic-grpo-4-59715-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-anthropic-grpo-4-59715-v1/special_tokens_map.json
chaiml-anthropic-grpo-4-59715-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-anthropic-grpo-4-59715-v1/tokenizer_config.json
chaiml-anthropic-grpo-4-59715-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-anthropic-grpo-4-59715-v1/tokenizer.json
chaiml-anthropic-grpo-4-59715-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-anthropic-grpo-4-59715-v1/flywheel_model.0.safetensors
Job chaiml-anthropic-grpo-4-59715-v1-mkmlizer completed after 144.97s with status: succeeded
Stopping job with name chaiml-anthropic-grpo-4-59715-v1-mkmlizer
Pipeline stage MKMLizer completed in 145.56s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-anthropic-grpo-4-59715-v1
Waiting for inference service chaiml-anthropic-grpo-4-59715-v1 to be ready
Inference service chaiml-anthropic-grpo-4-59715-v1 ready after 130.59468936920166s
Pipeline stage MKMLDeployer completed in 131.21s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1713829040527344s
Received healthy response to inference request in 1.6234240531921387s
Received healthy response to inference request in 1.6750867366790771s
Received healthy response to inference request in 1.7747983932495117s
Received healthy response to inference request in 1.729137897491455s
5 requests
0 failed requests
5th percentile: 1.6337565898895263
10th percentile: 1.644089126586914
20th percentile: 1.6647541999816895
30th percentile: 1.6858969688415528
40th percentile: 1.707517433166504
50th percentile: 1.729137897491455
60th percentile: 1.7474020957946776
70th percentile: 1.7656662940979004
80th percentile: 1.8541152954101563
90th percentile: 2.0127490997314452
95th percentile: 2.0920660018920896
99th percentile: 2.1555195236206055
mean time: 1.7947659969329834
Pipeline stage StressChecker completed in 10.32s
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 0.74s
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 0.70s
Shutdown handler de-registered
chaiml-anthropic-grpo-4_59715_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 2472.75s
Shutdown handler de-registered
chaiml-anthropic-grpo-4_59715_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-anthropic-grpo-4_59715_v1 status is now torndown due to DeploymentManager action