rirv938-anthropic-10k-3_55800

developer_uid: rirv938

submission_id: rirv938-anthropic-10k-3_55800_v1

model_name: rirv938-anthropic-10k-3_55800_v1

model_group: rirv938/anthropic_10k_31

status: torndown

timestamp: 2025-01-02T04:06:30+00:00

num_battles: 14770

num_wins: 7507

celo_rating: 1279.86

family_friendly_score: 0.6044

family_friendly_standard_error: 0.006915209902815677

submission_type: basic

model_repo: rirv938/anthropic_10k_312_bo8_80w_dpo5_v2

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 768

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6493823085103502, 'latency_mean': 1.539828748703003, 'latency_p50': 1.5298194885253906, 'latency_p90': 1.7257237672805785}, {'batch_size': 3, 'throughput': 1.2509680057729093, 'latency_mean': 2.3937482976913453, 'latency_p50': 2.4114726781845093, 'latency_p90': 2.628545904159546}, {'batch_size': 5, 'throughput': 1.552609934607451, 'latency_mean': 3.208759993314743, 'latency_p50': 3.2390133142471313, 'latency_p90': 3.5542125701904297}, {'batch_size': 6, 'throughput': 1.643517789205755, 'latency_mean': 3.626190655231476, 'latency_p50': 3.6266285181045532, 'latency_p90': 4.093436765670776}, {'batch_size': 8, 'throughput': 1.7298883875369289, 'latency_mean': 4.60684406876564, 'latency_p50': 4.597821950912476, 'latency_p90': 5.286862921714783}, {'batch_size': 10, 'throughput': 1.8025606875164388, 'latency_mean': 5.496375299692154, 'latency_p50': 5.481871247291565, 'latency_p90': 6.313048791885376}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rirv938-anthropic-10k-3_55800_v1

is_internal_developer: True

language_model: rirv938/anthropic_10k_312_bo8_80w_dpo5_v2

model_size: 13B

ranking_group: single

throughput_3p7s: 1.66

us_pacific_date: 2025-01-01

win_ratio: 0.5082599864590386

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>', '<|end_of_text|>', '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': '### Response:\n{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 rirv938-anthropic-10k-3-55800-v1-mkmlizer
Waiting for job on rirv938-anthropic-10k-3-55800-v1-mkmlizer to finish
rirv938-anthropic-10k-3-55800-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-10k-3-55800-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-10k-3-55800-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-10k-3-55800-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-10k-3-55800-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-10k-3-55800-v1-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-10k-3-55800-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-10k-3-55800-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
rirv938-anthropic-10k-3-55800-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-10k-3-55800-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-10k-3-55800-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-10k-3-55800-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-10k-3-55800-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-10k-3-55800-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-10k-3-55800-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-10k-3-55800-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-10k-3-55800-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
rirv938-anthropic-10k-3-55800-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-10k-3-55800-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-10k-3-55800-v1-mkmlizer: Downloaded to shared memory in 101.974s
rirv938-anthropic-10k-3-55800-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpyivwapb8, device:0
rirv938-anthropic-10k-3-55800-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-10k-3-55800-v1-mkmlizer: quantized model in 56.030s
rirv938-anthropic-10k-3-55800-v1-mkmlizer: Processed model rirv938/anthropic_10k_312_bo8_80w_dpo5_v2 in 158.004s
rirv938-anthropic-10k-3-55800-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-10k-3-55800-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-10k-3-55800-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-10k-3-55800-v1
rirv938-anthropic-10k-3-55800-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-10k-3-55800-v1/config.json
rirv938-anthropic-10k-3-55800-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-10k-3-55800-v1/special_tokens_map.json
rirv938-anthropic-10k-3-55800-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-10k-3-55800-v1/tokenizer_config.json
rirv938-anthropic-10k-3-55800-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-10k-3-55800-v1/tokenizer.json
Job rirv938-anthropic-10k-3-55800-v1-mkmlizer completed after 219.73s with status: succeeded
Stopping job with name rirv938-anthropic-10k-3-55800-v1-mkmlizer
Pipeline stage MKMLizer completed in 220.20s
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 rirv938-anthropic-10k-3-55800-v1
Waiting for inference service rirv938-anthropic-10k-3-55800-v1 to be ready
Failed to get response for submission function_gidef_2024-11-26: ('http://chaiml-llama-8b-multihea-7878-v5-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:32968->127.0.0.1:8080: read: connection reset by peer\n')
Inference service rirv938-anthropic-10k-3-55800-v1 ready after 341.2097110748291s
Pipeline stage MKMLDeployer completed in 341.76s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8129355907440186s
Received healthy response to inference request in 1.7015702724456787s
Received healthy response to inference request in 1.6634347438812256s
Received healthy response to inference request in 1.4048848152160645s
Received healthy response to inference request in 1.5706558227539062s
5 requests
0 failed requests
5th percentile: 1.4380390167236328
10th percentile: 1.471193218231201
20th percentile: 1.537501621246338
30th percentile: 1.58921160697937
40th percentile: 1.6263231754302978
50th percentile: 1.6634347438812256
60th percentile: 1.6786889553070068
70th percentile: 1.693943166732788
80th percentile: 1.7238433361053467
90th percentile: 1.7683894634246826
95th percentile: 1.7906625270843506
99th percentile: 1.808480978012085
mean time: 1.6306962490081787
Pipeline stage StressChecker completed in 9.46s
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 0.76s
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
rirv938-anthropic-10k-3_55800_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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-anthropic-10k-3-55800-v1-profiler
Waiting for inference service rirv938-anthropic-10k-3-55800-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2544.21s
Shutdown handler de-registered
rirv938-anthropic-10k-3_55800_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-10k-3_55800_v1 status is now torndown due to DeploymentManager action
rirv938-anthropic-10k-3_55800_v1 status is now torndown due to DeploymentManager action
rirv938-anthropic-10k-3_55800_v1 status is now torndown due to DeploymentManager action

ChatRequest

Bot Name

Generation Params

Prompt Formatter

ChatMessage 1

Sender

Message

User Message