developer_uid: rirv938
submission_id: rirv938-anthropic-beta-_39265_v1
model_name: rirv938-anthropic-beta-_39265_v1
model_group: rirv938/anthropic_beta_2
status: torndown
timestamp: 2024-12-29T17:50:26+00:00
num_battles: 15125
num_wins: 7907
celo_rating: 1285.35
family_friendly_score: 0.5972
family_friendly_standard_error: 0.006936168394726299
submission_type: basic
model_repo: rirv938/anthropic_beta_2_40k_1248_bo8_v2
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.7179674676879685, 'latency_mean': 1.3927565658092498, 'latency_p50': 1.4032419919967651, 'latency_p90': 1.54115469455719}, {'batch_size': 5, 'throughput': 2.139553167221892, 'latency_mean': 2.3210578572750094, 'latency_p50': 2.319814085960388, 'latency_p90': 2.6063455820083616}, {'batch_size': 10, 'throughput': 2.8486467470452053, 'latency_mean': 3.481085603237152, 'latency_p50': 3.4635543823242188, 'latency_p90': 3.900213623046875}, {'batch_size': 15, 'throughput': 3.1126398716765102, 'latency_mean': 4.752876988649368, 'latency_p50': 4.730963826179504, 'latency_p90': 5.430299115180969}, {'batch_size': 20, 'throughput': 3.2130688914966177, 'latency_mean': 6.122307139635086, 'latency_p50': 6.073385834693909, 'latency_p90': 7.115358519554138}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-anthropic-beta-_39265_v1
is_internal_developer: True
language_model: rirv938/anthropic_beta_2_40k_1248_bo8_v2
model_size: 13B
ranking_group: single
throughput_3p7s: 2.94
us_pacific_date: 2024-12-29
win_ratio: 0.5227768595041322
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '####', 'Bot:', 'User:', 'You:', '<|im_end|>', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 4, '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 rirv938-anthropic-beta-39265-v1-mkmlizer
Waiting for job on rirv938-anthropic-beta-39265-v1-mkmlizer to finish
rirv938-anthropic-beta-39265-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-beta-39265-v1-mkmlizer: ║ _____ __ __ ║
rirv938-anthropic-beta-39265-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rirv938-anthropic-beta-39265-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rirv938-anthropic-beta-39265-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rirv938-anthropic-beta-39265-v1-mkmlizer: ║ /___/ ║
rirv938-anthropic-beta-39265-v1-mkmlizer: ║ ║
rirv938-anthropic-beta-39265-v1-mkmlizer: ║ Version: 0.11.12 ║
rirv938-anthropic-beta-39265-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rirv938-anthropic-beta-39265-v1-mkmlizer: ║ https://mk1.ai ║
rirv938-anthropic-beta-39265-v1-mkmlizer: ║ ║
rirv938-anthropic-beta-39265-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-anthropic-beta-39265-v1-mkmlizer: ║ belonging to: ║
rirv938-anthropic-beta-39265-v1-mkmlizer: ║ ║
rirv938-anthropic-beta-39265-v1-mkmlizer: ║ Chai Research Corp. ║
rirv938-anthropic-beta-39265-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-anthropic-beta-39265-v1-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
rirv938-anthropic-beta-39265-v1-mkmlizer: ║ ║
rirv938-anthropic-beta-39265-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-beta-39265-v1-mkmlizer: Downloaded to shared memory in 98.772s
rirv938-anthropic-beta-39265-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpw8fg_twz, device:0
rirv938-anthropic-beta-39265-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-beta-39265-v1-mkmlizer: quantized model in 41.527s
rirv938-anthropic-beta-39265-v1-mkmlizer: Processed model rirv938/anthropic_beta_2_40k_1248_bo8_v2 in 140.300s
rirv938-anthropic-beta-39265-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-beta-39265-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-beta-39265-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-beta-39265-v1
rirv938-anthropic-beta-39265-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-beta-39265-v1/special_tokens_map.json
rirv938-anthropic-beta-39265-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-beta-39265-v1/config.json
rirv938-anthropic-beta-39265-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-beta-39265-v1/tokenizer_config.json
rirv938-anthropic-beta-39265-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-beta-39265-v1/tokenizer.json
rirv938-anthropic-beta-39265-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-beta-39265-v1/flywheel_model.0.safetensors
Job rirv938-anthropic-beta-39265-v1-mkmlizer completed after 166.67s with status: succeeded
Stopping job with name rirv938-anthropic-beta-39265-v1-mkmlizer
Pipeline stage MKMLizer completed in 167.16s
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-beta-39265-v1
Waiting for inference service rirv938-anthropic-beta-39265-v1 to be ready
Failed to get response for submission rirv938-anthropic-beta-_68706_v1: ('http://rirv938-anthropic-beta-68706-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission rirv938-anthropic-beta-_68706_v1: ('http://rirv938-anthropic-beta-68706-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Inference service rirv938-anthropic-beta-39265-v1 ready after 311.9156885147095s
Pipeline stage MKMLDeployer completed in 312.47s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8535301685333252s
Received healthy response to inference request in 1.3955121040344238s
Received healthy response to inference request in 1.510660171508789s
Received healthy response to inference request in 1.9262316226959229s
Received healthy response to inference request in 1.5114471912384033s
5 requests
0 failed requests
5th percentile: 1.418541717529297
10th percentile: 1.44157133102417
20th percentile: 1.487630558013916
30th percentile: 1.510817575454712
40th percentile: 1.5111323833465575
50th percentile: 1.5114471912384033
60th percentile: 1.648280382156372
70th percentile: 1.7851135730743408
80th percentile: 1.8680704593658448
90th percentile: 1.8971510410308838
95th percentile: 1.9116913318634032
99th percentile: 1.9233235645294189
mean time: 1.6394762516021728
Pipeline stage StressChecker completed in 9.47s
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 0.70s
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
rirv938-anthropic-beta-_39265_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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-anthropic-beta-39265-v1-profiler
Waiting for inference service rirv938-anthropic-beta-39265-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 2303.86s
Shutdown handler de-registered
rirv938-anthropic-beta-_39265_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-beta-_39265_v1 status is now torndown due to DeploymentManager action
rirv938-anthropic-beta-_39265_v1 status is now torndown due to DeploymentManager action
rirv938-anthropic-beta-_39265_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1