developer_uid: cloudyu
submission_id: cloudyu-nemo-dpo-v13_v1
model_name: cloudyu-nemo-dpo-v13_v1
model_group: cloudyu/Nemo-DPO-v13
status: inactive
timestamp: 2024-11-28T09:58:13+00:00
num_battles: 19260
num_wins: 9157
celo_rating: 1246.86
family_friendly_score: 0.5756
family_friendly_standard_error: 0.00698977310075227
submission_type: basic
model_repo: cloudyu/Nemo-DPO-v13
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6100248224438295, 'latency_mean': 1.639104276895523, 'latency_p50': 1.6518198251724243, 'latency_p90': 1.822160816192627}, {'batch_size': 3, 'throughput': 1.1163192682624798, 'latency_mean': 2.6734136927127836, 'latency_p50': 2.6704208850860596, 'latency_p90': 2.93586893081665}, {'batch_size': 5, 'throughput': 1.3471779463387221, 'latency_mean': 3.693798757791519, 'latency_p50': 3.7137842178344727, 'latency_p90': 4.129527688026428}, {'batch_size': 6, 'throughput': 1.4061686541445684, 'latency_mean': 4.245568486452103, 'latency_p50': 4.2704222202301025, 'latency_p90': 4.739450836181641}, {'batch_size': 8, 'throughput': 1.4638443979736424, 'latency_mean': 5.440896426439285, 'latency_p50': 5.4095698595047, 'latency_p90': 6.09665265083313}, {'batch_size': 10, 'throughput': 1.5060078418794458, 'latency_mean': 6.595643702745438, 'latency_p50': 6.623599648475647, 'latency_p90': 7.464761400222779}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: cloudyu-nemo-dpo-v13_v1
is_internal_developer: False
language_model: cloudyu/Nemo-DPO-v13
model_size: 13B
ranking_group: single
throughput_3p7s: 1.35
us_pacific_date: 2024-11-28
win_ratio: 0.47544132917964693
generation_params: {'temperature': 0.95, 'top_p': 0.95, 'min_p': 0.05, '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-nemo-dpo-v13-v1-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v13-v1-mkmlizer to finish
cloudyu-nemo-dpo-v13-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v13-v1-mkmlizer: ║ _____ __ __ ║
cloudyu-nemo-dpo-v13-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cloudyu-nemo-dpo-v13-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cloudyu-nemo-dpo-v13-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cloudyu-nemo-dpo-v13-v1-mkmlizer: ║ /___/ ║
cloudyu-nemo-dpo-v13-v1-mkmlizer: ║ ║
cloudyu-nemo-dpo-v13-v1-mkmlizer: ║ Version: 0.11.12 ║
cloudyu-nemo-dpo-v13-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cloudyu-nemo-dpo-v13-v1-mkmlizer: ║ https://mk1.ai ║
cloudyu-nemo-dpo-v13-v1-mkmlizer: ║ ║
cloudyu-nemo-dpo-v13-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cloudyu-nemo-dpo-v13-v1-mkmlizer: ║ belonging to: ║
cloudyu-nemo-dpo-v13-v1-mkmlizer: ║ ║
cloudyu-nemo-dpo-v13-v1-mkmlizer: ║ Chai Research Corp. ║
cloudyu-nemo-dpo-v13-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cloudyu-nemo-dpo-v13-v1-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cloudyu-nemo-dpo-v13-v1-mkmlizer: ║ ║
cloudyu-nemo-dpo-v13-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v13-v1-mkmlizer: Downloaded to shared memory in 46.008s
cloudyu-nemo-dpo-v13-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpu3xrds82, device:0
cloudyu-nemo-dpo-v13-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v13-v1-mkmlizer: quantized model in 36.884s
cloudyu-nemo-dpo-v13-v1-mkmlizer: Processed model cloudyu/Nemo-DPO-v13 in 82.893s
cloudyu-nemo-dpo-v13-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v13-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v13-v1
cloudyu-nemo-dpo-v13-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v13-v1/config.json
cloudyu-nemo-dpo-v13-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v13-v1/special_tokens_map.json
cloudyu-nemo-dpo-v13-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v13-v1/tokenizer_config.json
cloudyu-nemo-dpo-v13-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v13-v1/tokenizer.json
cloudyu-nemo-dpo-v13-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v13-v1/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v13-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:12, 28.38it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:07, 49.51it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:08, 42.90it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:08, 41.12it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 47.81it/s] Loading 0: 10%|█ | 37/363 [00:00<00:07, 45.17it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 43.74it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 49.05it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 45.89it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 34.09it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:08, 33.13it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 39.30it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:07, 39.90it/s] Loading 0: 23%|██▎ | 83/363 [00:02<00:06, 40.02it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:06, 45.26it/s] Loading 0: 26%|██▋ | 96/363 [00:02<00:06, 43.32it/s] Loading 0: 28%|██▊ | 101/363 [00:02<00:06, 41.29it/s] Loading 0: 29%|██▉ | 106/363 [00:02<00:05, 43.32it/s] Loading 0: 31%|███ | 112/363 [00:02<00:05, 46.37it/s] Loading 0: 32%|███▏ | 117/363 [00:02<00:05, 44.42it/s] Loading 0: 34%|███▎ | 122/363 [00:02<00:05, 45.27it/s] Loading 0: 35%|███▍ | 127/363 [00:03<00:06, 35.63it/s] Loading 0: 37%|███▋ | 134/363 [00:03<00:05, 42.78it/s] Loading 0: 38%|███▊ | 139/363 [00:03<00:05, 43.16it/s] Loading 0: 40%|███▉ | 144/363 [00:03<00:08, 26.54it/s] Loading 0: 41%|████ | 149/363 [00:03<00:07, 28.74it/s] Loading 0: 43%|████▎ | 156/363 [00:03<00:05, 36.35it/s] Loading 0: 44%|████▍ | 161/363 [00:04<00:05, 37.34it/s] Loading 0: 46%|████▌ | 166/363 [00:04<00:05, 38.63it/s] Loading 0: 47%|████▋ | 171/363 [00:04<00:04, 39.56it/s] Loading 0: 48%|████▊ | 176/363 [00:04<00:05, 32.97it/s] Loading 0: 50%|█████ | 183/363 [00:04<00:04, 39.85it/s] Loading 0: 52%|█████▏ | 188/363 [00:04<00:04, 40.53it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:04, 42.43it/s] Loading 0: 55%|█████▍ | 198/363 [00:04<00:03, 43.58it/s] Loading 0: 56%|█████▌ | 203/363 [00:05<00:04, 34.89it/s] Loading 0: 58%|█████▊ | 211/363 [00:05<00:03, 43.26it/s] Loading 0: 60%|█████▉ | 217/363 [00:05<00:03, 42.02it/s] Loading 0: 61%|██████ | 222/363 [00:05<00:03, 41.82it/s] Loading 0: 63%|██████▎ | 227/363 [00:05<00:04, 27.73it/s] Loading 0: 64%|██████▎ | 231/363 [00:06<00:04, 28.05it/s] Loading 0: 65%|██████▌ | 237/363 [00:06<00:03, 34.05it/s] Loading 0: 67%|██████▋ | 242/363 [00:06<00:03, 35.56it/s] Loading 0: 68%|██████▊ | 247/363 [00:06<00:03, 37.50it/s] Loading 0: 69%|██████▉ | 252/363 [00:06<00:02, 40.12it/s] Loading 0: 71%|███████ | 257/363 [00:06<00:03, 34.12it/s] Loading 0: 73%|███████▎ | 264/363 [00:06<00:02, 41.92it/s] Loading 0: 74%|███████▍ | 269/363 [00:06<00:02, 41.53it/s] Loading 0: 75%|███████▌ | 274/363 [00:07<00:02, 41.54it/s] Loading 0: 77%|███████▋ | 279/363 [00:07<00:01, 42.38it/s] Loading 0: 78%|███████▊ | 284/363 [00:07<00:02, 33.92it/s] Loading 0: 80%|████████ | 291/363 [00:07<00:01, 41.54it/s] Loading 0: 82%|████████▏ | 296/363 [00:07<00:01, 40.68it/s] Loading 0: 83%|████████▎ | 301/363 [00:07<00:01, 42.37it/s] Loading 0: 84%|████████▍ | 306/363 [00:14<00:23, 2.42it/s] Loading 0: 85%|████████▌ | 310/363 [00:14<00:16, 3.14it/s] Loading 0: 87%|████████▋ | 314/363 [00:14<00:11, 4.13it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:07, 6.14it/s] Loading 0: 89%|████████▉ | 324/363 [00:15<00:05, 7.75it/s] Loading 0: 91%|█████████ | 329/363 [00:15<00:03, 10.42it/s] Loading 0: 92%|█████████▏| 334/363 [00:15<00:02, 13.78it/s] Loading 0: 93%|█████████▎| 339/363 [00:15<00:01, 16.30it/s] Loading 0: 96%|█████████▌| 347/363 [00:15<00:00, 23.73it/s] Loading 0: 97%|█████████▋| 352/363 [00:15<00:00, 27.60it/s] Loading 0: 98%|█████████▊| 357/363 [00:15<00:00, 27.57it/s]
Job cloudyu-nemo-dpo-v13-v1-mkmlizer completed after 114.57s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v13-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.05s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cloudyu-nemo-dpo-v13-v1
Waiting for inference service cloudyu-nemo-dpo-v13-v1 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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
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-nemo-dpo-v13-v1 ready after 130.44685220718384s
Pipeline stage MKMLDeployer completed in 130.96s
run pipeline stage %s
Running pipeline stage StressChecker
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
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 2.3328118324279785s
Received healthy response to inference request in 1.8682162761688232s
Received healthy response to inference request in 1.3430743217468262s
Received healthy response to inference request in 1.721524953842163s
5 requests
1 failed requests
5th percentile: 1.4187644481658936
10th percentile: 1.494454574584961
20th percentile: 1.6458348274230956
30th percentile: 1.750863218307495
40th percentile: 1.8095397472381591
50th percentile: 1.8682162761688232
60th percentile: 2.0540544986724854
70th percentile: 2.2398927211761475
80th percentile: 5.892569494247439
90th percentile: 13.012084817886354
95th percentile: 16.571842479705808
99th percentile: 19.419648609161378
mean time: 5.479445505142212
%s, retrying in %s seconds...
Received healthy response to inference request in 1.5892412662506104s
Received healthy response to inference request in 1.9028522968292236s
Received healthy response to inference request in 1.5568835735321045s
Received healthy response to inference request in 1.6287124156951904s
Received healthy response to inference request in 1.7692291736602783s
5 requests
0 failed requests
5th percentile: 1.5633551120758056
10th percentile: 1.5698266506195069
20th percentile: 1.5827697277069093
30th percentile: 1.5971354961395263
40th percentile: 1.6129239559173585
50th percentile: 1.6287124156951904
60th percentile: 1.6849191188812256
70th percentile: 1.7411258220672607
80th percentile: 1.7959537982940674
90th percentile: 1.8494030475616454
95th percentile: 1.8761276721954345
99th percentile: 1.8975073719024658
mean time: 1.6893837451934814
Pipeline stage StressChecker completed in 38.47s
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 2.50s
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 2.31s
Shutdown handler de-registered
cloudyu-nemo-dpo-v13_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 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cloudyu-nemo-dpo-v13-v1-profiler
Waiting for inference service cloudyu-nemo-dpo-v13-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 3100.41s
Shutdown handler de-registered
cloudyu-nemo-dpo-v13_v1 status is now inactive due to auto deactivation removed underperforming models