developer_uid: cloudyu
submission_id: cloudyu-nemo-dpo-v20_v2
model_name: cloudyu-nemo-dpo-v20_v1
model_group: cloudyu/Nemo-DPO-V20
status: inactive
timestamp: 2024-12-16T14:11:46+00:00
num_battles: 14175
num_wins: 7439
celo_rating: 1280.37
family_friendly_score: 0.5624
family_friendly_standard_error: 0.007015785629564233
submission_type: basic
model_repo: cloudyu/Nemo-DPO-V20
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6150652193131083, 'latency_mean': 1.6257541584968567, 'latency_p50': 1.6232229471206665, 'latency_p90': 1.789939260482788}, {'batch_size': 3, 'throughput': 1.1474746859276987, 'latency_mean': 2.609482923746109, 'latency_p50': 2.5987387895584106, 'latency_p90': 2.860051131248474}, {'batch_size': 5, 'throughput': 1.387155423974442, 'latency_mean': 3.591857078075409, 'latency_p50': 3.631060004234314, 'latency_p90': 3.968585658073425}, {'batch_size': 6, 'throughput': 1.4660027802821245, 'latency_mean': 4.064659057855606, 'latency_p50': 4.081573843955994, 'latency_p90': 4.505732846260071}, {'batch_size': 8, 'throughput': 1.5372376480073842, 'latency_mean': 5.179775013923645, 'latency_p50': 5.2050840854644775, 'latency_p90': 5.826881170272827}, {'batch_size': 10, 'throughput': 1.5689628347088065, 'latency_mean': 6.323661870956421, 'latency_p50': 6.336176633834839, 'latency_p90': 7.055754590034485}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: cloudyu-nemo-dpo-v20_v1
is_internal_developer: False
language_model: cloudyu/Nemo-DPO-V20
model_size: 13B
ranking_group: single
throughput_3p7s: 1.41
us_pacific_date: 2024-12-16
win_ratio: 0.5247971781305114
generation_params: {'temperature': 0.95, 'top_p': 0.95, '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-nemo-dpo-v20-v2-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v20-v2-mkmlizer to finish
cloudyu-nemo-dpo-v20-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v20-v2-mkmlizer: ║ _____ __ __ ║
cloudyu-nemo-dpo-v20-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cloudyu-nemo-dpo-v20-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cloudyu-nemo-dpo-v20-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cloudyu-nemo-dpo-v20-v2-mkmlizer: ║ /___/ ║
cloudyu-nemo-dpo-v20-v2-mkmlizer: ║ ║
cloudyu-nemo-dpo-v20-v2-mkmlizer: ║ Version: 0.11.12 ║
cloudyu-nemo-dpo-v20-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cloudyu-nemo-dpo-v20-v2-mkmlizer: ║ https://mk1.ai ║
cloudyu-nemo-dpo-v20-v2-mkmlizer: ║ ║
cloudyu-nemo-dpo-v20-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cloudyu-nemo-dpo-v20-v2-mkmlizer: ║ belonging to: ║
cloudyu-nemo-dpo-v20-v2-mkmlizer: ║ ║
cloudyu-nemo-dpo-v20-v2-mkmlizer: ║ Chai Research Corp. ║
cloudyu-nemo-dpo-v20-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cloudyu-nemo-dpo-v20-v2-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cloudyu-nemo-dpo-v20-v2-mkmlizer: ║ ║
cloudyu-nemo-dpo-v20-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v20-v2-mkmlizer: Downloaded to shared memory in 35.926s
cloudyu-nemo-dpo-v20-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpeh3kbyrj, device:0
cloudyu-nemo-dpo-v20-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v20-v2-mkmlizer: quantized model in 35.852s
cloudyu-nemo-dpo-v20-v2-mkmlizer: Processed model cloudyu/Nemo-DPO-V20 in 71.778s
cloudyu-nemo-dpo-v20-v2-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v20-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v20-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v2
cloudyu-nemo-dpo-v20-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v2/config.json
cloudyu-nemo-dpo-v20-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v2/special_tokens_map.json
cloudyu-nemo-dpo-v20-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v2/tokenizer.json
cloudyu-nemo-dpo-v20-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v2/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v20-v2-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:11, 30.36it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:06, 50.92it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 45.58it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:07, 44.64it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 51.05it/s] Loading 0: 10%|█ | 37/363 [00:00<00:06, 47.26it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 44.97it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 49.85it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 46.17it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 35.32it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:08, 34.73it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 40.90it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:07, 39.96it/s] Loading 0: 23%|██▎ | 83/363 [00:01<00:06, 40.35it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:06, 45.45it/s] Loading 0: 26%|██▌ | 95/363 [00:02<00:05, 46.35it/s] Loading 0: 28%|██▊ | 100/363 [00:02<00:07, 36.08it/s] Loading 0: 29%|██▉ | 107/363 [00:02<00:05, 43.43it/s] Loading 0: 31%|███ | 112/363 [00:02<00:05, 44.80it/s] Loading 0: 32%|███▏ | 117/363 [00:02<00:05, 43.39it/s] Loading 0: 34%|███▍ | 123/363 [00:02<00:05, 40.95it/s] Loading 0: 35%|███▌ | 128/363 [00:03<00:05, 41.13it/s] Loading 0: 37%|███▋ | 135/363 [00:03<00:04, 46.60it/s] Loading 0: 39%|███▉ | 141/363 [00:03<00:05, 42.45it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 31.83it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 31.89it/s] Loading 0: 43%|████▎ | 157/363 [00:03<00:05, 38.38it/s] Loading 0: 45%|████▍ | 163/363 [00:03<00:05, 38.69it/s] Loading 0: 46%|████▋ | 168/363 [00:04<00:05, 38.75it/s] Loading 0: 48%|████▊ | 175/363 [00:04<00:04, 43.82it/s] Loading 0: 50%|████▉ | 181/363 [00:04<00:04, 42.09it/s] Loading 0: 51%|█████ | 186/363 [00:04<00:04, 41.06it/s] Loading 0: 53%|█████▎ | 192/363 [00:04<00:03, 45.46it/s] Loading 0: 54%|█████▍ | 197/363 [00:04<00:03, 44.55it/s] Loading 0: 56%|█████▌ | 202/363 [00:04<00:03, 44.12it/s] Loading 0: 57%|█████▋ | 208/363 [00:04<00:03, 41.92it/s] Loading 0: 59%|█████▊ | 213/363 [00:05<00:03, 42.03it/s] Loading 0: 60%|██████ | 218/363 [00:05<00:03, 43.42it/s] Loading 0: 61%|██████▏ | 223/363 [00:05<00:04, 34.34it/s] Loading 0: 63%|██████▎ | 227/363 [00:05<00:03, 34.53it/s] Loading 0: 64%|██████▎ | 231/363 [00:05<00:03, 33.45it/s] Loading 0: 66%|██████▌ | 238/363 [00:05<00:03, 40.47it/s] Loading 0: 67%|██████▋ | 244/363 [00:05<00:02, 39.90it/s] Loading 0: 69%|██████▊ | 249/363 [00:06<00:02, 40.20it/s] Loading 0: 70%|███████ | 255/363 [00:06<00:02, 44.40it/s] Loading 0: 72%|███████▏ | 260/363 [00:06<00:02, 44.55it/s] Loading 0: 73%|███████▎ | 265/363 [00:06<00:02, 45.46it/s] Loading 0: 74%|███████▍ | 270/363 [00:06<00:02, 46.08it/s] Loading 0: 76%|███████▌ | 275/363 [00:06<00:02, 36.77it/s] Loading 0: 78%|███████▊ | 283/363 [00:06<00:01, 45.18it/s] Loading 0: 79%|███████▉ | 288/363 [00:06<00:01, 46.25it/s] Loading 0: 81%|████████ | 293/363 [00:07<00:01, 38.17it/s] Loading 0: 82%|████████▏ | 299/363 [00:07<00:01, 42.89it/s] Loading 0: 84%|████████▎ | 304/363 [00:13<00:22, 2.59it/s] Loading 0: 85%|████████▍ | 308/363 [00:14<00:16, 3.32it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:11, 4.31it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:06, 7.14it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:03, 9.56it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:02, 12.11it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 16.85it/s] Loading 0: 94%|█████████▍| 343/363 [00:14<00:00, 20.39it/s] Loading 0: 96%|█████████▌| 348/363 [00:14<00:00, 21.84it/s] Loading 0: 98%|█████████▊| 355/363 [00:15<00:00, 28.05it/s] Loading 0: 99%|█████████▉| 360/363 [00:15<00:00, 30.53it/s]
Job cloudyu-nemo-dpo-v20-v2-mkmlizer completed after 104.62s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v20-v2-mkmlizer
Pipeline stage MKMLizer completed in 105.10s
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-v20-v2
Waiting for inference service cloudyu-nemo-dpo-v20-v2 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-nemo-dpo-v20-v2 ready after 220.83805990219116s
Pipeline stage MKMLDeployer completed in 221.32s
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
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 3.18894624710083s
Received healthy response to inference request in 2.5418756008148193s
Received healthy response to inference request in 2.08339786529541s
Received healthy response to inference request in 2.0972368717193604s
5 requests
1 failed requests
5th percentile: 2.0861656665802
10th percentile: 2.0889334678649902
20th percentile: 2.0944690704345703
30th percentile: 2.186164617538452
40th percentile: 2.3640201091766357
50th percentile: 2.5418756008148193
60th percentile: 2.8007038593292237
70th percentile: 3.0595321178436277
80th percentile: 6.576746797561649
90th percentile: 13.352347898483277
95th percentile: 16.74014844894409
99th percentile: 19.450388889312745
mean time: 6.007881116867066
%s, retrying in %s seconds...
Received healthy response to inference request in 1.9985377788543701s
Received healthy response to inference request in 1.7692508697509766s
Received healthy response to inference request in 1.7214643955230713s
Received healthy response to inference request in 1.8741786479949951s
Received healthy response to inference request in 1.804753303527832s
5 requests
0 failed requests
5th percentile: 1.7310216903686524
10th percentile: 1.7405789852142335
20th percentile: 1.7596935749053955
30th percentile: 1.7763513565063476
40th percentile: 1.7905523300170898
50th percentile: 1.804753303527832
60th percentile: 1.8325234413146974
70th percentile: 1.8602935791015625
80th percentile: 1.8990504741668701
90th percentile: 1.9487941265106201
95th percentile: 1.9736659526824951
99th percentile: 1.9935634136199951
mean time: 1.833636999130249
Pipeline stage StressChecker completed in 41.99s
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 2.40s
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 2.34s
Shutdown handler de-registered
cloudyu-nemo-dpo-v20_v2 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 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cloudyu-nemo-dpo-v20-v2-profiler
Waiting for inference service cloudyu-nemo-dpo-v20-v2-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 3180.17s
Shutdown handler de-registered
cloudyu-nemo-dpo-v20_v2 status is now inactive due to auto deactivation removed underperforming models