developer_uid: cloudyu
submission_id: cloudyu-chaiml-nemo-dpo-v17_v12
model_name: cloudyu-chaiml-nemo-dpo-v17_v4
model_group: cloudyu/ChaiML-Nemo-DPO-
status: inactive
timestamp: 2024-12-09T01:34:27+00:00
num_battles: 17736
num_wins: 9195
celo_rating: 1276.69
family_friendly_score: 0.5492
family_friendly_standard_error: 0.007036751523252757
submission_type: basic
model_repo: cloudyu/ChaiML-Nemo-DPO-V17
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6099198313474319, 'latency_mean': 1.6394648277759551, 'latency_p50': 1.6440258026123047, 'latency_p90': 1.7958078145980834}, {'batch_size': 3, 'throughput': 1.1486359772502213, 'latency_mean': 2.608003134727478, 'latency_p50': 2.617632269859314, 'latency_p90': 2.9286123275756837}, {'batch_size': 5, 'throughput': 1.3969215213548274, 'latency_mean': 3.5572694540023804, 'latency_p50': 3.5271676778793335, 'latency_p90': 4.032775664329529}, {'batch_size': 6, 'throughput': 1.4746659216240896, 'latency_mean': 4.044352307319641, 'latency_p50': 4.032878398895264, 'latency_p90': 4.596282744407654}, {'batch_size': 8, 'throughput': 1.5187002632067297, 'latency_mean': 5.23311294555664, 'latency_p50': 5.229403614997864, 'latency_p90': 5.920905661582947}, {'batch_size': 10, 'throughput': 1.5695465172132599, 'latency_mean': 6.323517769575119, 'latency_p50': 6.395993232727051, 'latency_p90': 7.176361870765686}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: cloudyu-chaiml-nemo-dpo-v17_v4
is_internal_developer: False
language_model: cloudyu/ChaiML-Nemo-DPO-V17
model_size: 13B
ranking_group: single
throughput_3p7s: 1.43
us_pacific_date: 2024-12-08
win_ratio: 0.5184370771312584
generation_params: {'temperature': 1.25, 'top_p': 0.99, 'min_p': 0.01, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', '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 cloudyu-chaiml-nemo-dpo-v17-v12-mkmlizer
Waiting for job on cloudyu-chaiml-nemo-dpo-v17-v12-mkmlizer to finish
cloudyu-chaiml-nemo-dpo-v17-v12-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-chaiml-nemo-dpo-v17-v12-mkmlizer: ║     _____            __           __                                ║
cloudyu-chaiml-nemo-dpo-v17-v12-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-chaiml-nemo-dpo-v17-v12-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-chaiml-nemo-dpo-v17-v12-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-chaiml-nemo-dpo-v17-v12-mkmlizer: ║       /___/                                                         ║
cloudyu-chaiml-nemo-dpo-v17-v12-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v17-v12-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-chaiml-nemo-dpo-v17-v12-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-chaiml-nemo-dpo-v17-v12-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-chaiml-nemo-dpo-v17-v12-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v17-v12-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-chaiml-nemo-dpo-v17-v12-mkmlizer: ║  belonging to:                                                      ║
cloudyu-chaiml-nemo-dpo-v17-v12-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v17-v12-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-chaiml-nemo-dpo-v17-v12-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-chaiml-nemo-dpo-v17-v12-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-chaiml-nemo-dpo-v17-v12-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v17-v12-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-chaiml-nemo-dpo-v17-v12-mkmlizer: Downloaded to shared memory in 49.884s
cloudyu-chaiml-nemo-dpo-v17-v12-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_m6stwgf, device:0
cloudyu-chaiml-nemo-dpo-v17-v12-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-chaiml-nemo-dpo-v17-v12-mkmlizer: quantized model in 37.236s
cloudyu-chaiml-nemo-dpo-v17-v12-mkmlizer: Processed model cloudyu/ChaiML-Nemo-DPO-V17 in 87.120s
cloudyu-chaiml-nemo-dpo-v17-v12-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-chaiml-nemo-dpo-v17-v12-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-chaiml-nemo-dpo-v17-v12-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v17-v12
cloudyu-chaiml-nemo-dpo-v17-v12-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v17-v12/config.json
cloudyu-chaiml-nemo-dpo-v17-v12-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v17-v12/special_tokens_map.json
cloudyu-chaiml-nemo-dpo-v17-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v17-v12/tokenizer_config.json
cloudyu-chaiml-nemo-dpo-v17-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v17-v12/tokenizer.json
cloudyu-chaiml-nemo-dpo-v17-v12-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v17-v12/flywheel_model.0.safetensors
Job cloudyu-chaiml-nemo-dpo-v17-v12-mkmlizer completed after 114.88s with status: succeeded
Stopping job with name cloudyu-chaiml-nemo-dpo-v17-v12-mkmlizer
Pipeline stage MKMLizer completed in 115.39s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cloudyu-chaiml-nemo-dpo-v17-v12
Waiting for inference service cloudyu-chaiml-nemo-dpo-v17-v12 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service cloudyu-chaiml-nemo-dpo-v17-v12 ready after 171.16096448898315s
Pipeline stage MKMLDeployer completed in 171.71s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.7058544158935547s
Received healthy response to inference request in 1.8301913738250732s
Received healthy response to inference request in 1.9968233108520508s
Received healthy response to inference request in 1.8904354572296143s
5 requests
1 failed requests
5th percentile: 1.8422401905059815
10th percentile: 1.8542890071868896
20th percentile: 1.878386640548706
30th percentile: 1.9117130279541015
40th percentile: 1.9542681694030761
50th percentile: 1.9968233108520508
60th percentile: 2.2804357528686525
70th percentile: 2.564048194885254
80th percentile: 6.191516685485842
90th percentile: 13.162841224670412
95th percentile: 16.64850349426269
99th percentile: 19.437033309936524
mean time: 5.711494064331054
%s, retrying in %s seconds...
Received healthy response to inference request in 1.6381487846374512s
Received healthy response to inference request in 1.928056240081787s
Received healthy response to inference request in 1.967721700668335s
Received healthy response to inference request in 1.6657185554504395s
Received healthy response to inference request in 1.6778819561004639s
5 requests
0 failed requests
5th percentile: 1.6436627388000489
10th percentile: 1.6491766929626466
20th percentile: 1.6602046012878418
30th percentile: 1.6681512355804444
40th percentile: 1.6730165958404541
50th percentile: 1.6778819561004639
60th percentile: 1.7779516696929931
70th percentile: 1.8780213832855224
80th percentile: 1.9359893321990966
90th percentile: 1.951855516433716
95th percentile: 1.9597886085510254
99th percentile: 1.966135082244873
mean time: 1.7755054473876952
Pipeline stage StressChecker completed in 39.99s
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 2.09s
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 2.22s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v17_v12 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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cloudyu-chaiml-nemo-dpo-v17-v12-profiler
Waiting for inference service cloudyu-chaiml-nemo-dpo-v17-v12-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 2699.30s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v17_v12 status is now inactive due to auto deactivation removed underperforming models