developer_uid: cloudyu
submission_id: cloudyu-nemo-dpo-v20_v6
model_name: cloudyu-nemo-dpo-v20_v1
model_group: cloudyu/Nemo-DPO-V20
status: inactive
timestamp: 2024-12-17T05:14:04+00:00
num_battles: 15949
num_wins: 8433
celo_rating: 1282.45
family_friendly_score: 0.5631999999999999
family_friendly_standard_error: 0.007014353284515972
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': 0.6138549176646162, 'latency_mean': 1.6289886462688445, 'latency_p50': 1.6241508722305298, 'latency_p90': 1.7900349855422975}, {'batch_size': 3, 'throughput': 1.1242481870486662, 'latency_mean': 2.6618684792518614, 'latency_p50': 2.6431552171707153, 'latency_p90': 2.9478400707244874}, {'batch_size': 5, 'throughput': 1.3569122594366145, 'latency_mean': 3.665529390573502, 'latency_p50': 3.6589425802230835, 'latency_p90': 4.075573134422302}, {'batch_size': 6, 'throughput': 1.428591061881388, 'latency_mean': 4.183798906803131, 'latency_p50': 4.189402103424072, 'latency_p90': 4.64176561832428}, {'batch_size': 8, 'throughput': 1.4885577000124308, 'latency_mean': 5.349126776456833, 'latency_p50': 5.342832803726196, 'latency_p90': 6.047684264183045}, {'batch_size': 10, 'throughput': 1.5301606495685005, 'latency_mean': 6.490471231937408, 'latency_p50': 6.519620060920715, 'latency_p90': 7.300588798522949}]
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: 1.37
us_pacific_date: 2024-12-16
win_ratio: 0.528747883879867
generation_params: {'temperature': 0.99, '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-nemo-dpo-v20-v6-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v20-v6-mkmlizer to finish
cloudyu-nemo-dpo-v20-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v20-v6-mkmlizer: ║ _____ __ __ ║
cloudyu-nemo-dpo-v20-v6-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cloudyu-nemo-dpo-v20-v6-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cloudyu-nemo-dpo-v20-v6-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cloudyu-nemo-dpo-v20-v6-mkmlizer: ║ /___/ ║
cloudyu-nemo-dpo-v20-v6-mkmlizer: ║ ║
cloudyu-nemo-dpo-v20-v6-mkmlizer: ║ Version: 0.11.12 ║
cloudyu-nemo-dpo-v20-v6-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cloudyu-nemo-dpo-v20-v6-mkmlizer: ║ https://mk1.ai ║
cloudyu-nemo-dpo-v20-v6-mkmlizer: ║ ║
cloudyu-nemo-dpo-v20-v6-mkmlizer: ║ The license key for the current software has been verified as ║
cloudyu-nemo-dpo-v20-v6-mkmlizer: ║ belonging to: ║
cloudyu-nemo-dpo-v20-v6-mkmlizer: ║ ║
cloudyu-nemo-dpo-v20-v6-mkmlizer: ║ Chai Research Corp. ║
cloudyu-nemo-dpo-v20-v6-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cloudyu-nemo-dpo-v20-v6-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cloudyu-nemo-dpo-v20-v6-mkmlizer: ║ ║
cloudyu-nemo-dpo-v20-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v20-v6-mkmlizer: Downloaded to shared memory in 32.247s
cloudyu-nemo-dpo-v20-v6-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpcgysq88b, device:0
cloudyu-nemo-dpo-v20-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v20-v6-mkmlizer: quantized model in 36.414s
cloudyu-nemo-dpo-v20-v6-mkmlizer: Processed model cloudyu/Nemo-DPO-V20 in 68.661s
cloudyu-nemo-dpo-v20-v6-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v20-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v20-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v6
cloudyu-nemo-dpo-v20-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v6/config.json
cloudyu-nemo-dpo-v20-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v6/special_tokens_map.json
cloudyu-nemo-dpo-v20-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v6/tokenizer_config.json
cloudyu-nemo-dpo-v20-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v6/tokenizer.json
cloudyu-nemo-dpo-v20-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v6/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v20-v6-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:12, 27.58it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:07, 49.56it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 47.78it/s] Loading 0: 7%|▋ | 25/363 [00:00<00:06, 49.17it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 49.70it/s] Loading 0: 10%|█ | 37/363 [00:00<00:07, 46.15it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 44.75it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 50.01it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 47.99it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 36.20it/s] Loading 0: 18%|█▊ | 66/363 [00:01<00:08, 36.28it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 40.46it/s] Loading 0: 21%|██ | 77/363 [00:01<00:06, 42.11it/s] Loading 0: 23%|██▎ | 82/363 [00:01<00:07, 35.96it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:06, 44.11it/s] Loading 0: 26%|██▌ | 95/363 [00:02<00:06, 42.05it/s] Loading 0: 28%|██▊ | 100/363 [00:02<00:07, 33.93it/s] Loading 0: 30%|███ | 109/363 [00:02<00:05, 45.10it/s] Loading 0: 32%|███▏ | 115/363 [00:02<00:06, 40.79it/s] Loading 0: 33%|███▎ | 120/363 [00:02<00:06, 39.91it/s] Loading 0: 35%|███▍ | 126/363 [00:02<00:05, 43.81it/s] Loading 0: 36%|███▋ | 132/363 [00:03<00:05, 43.87it/s] Loading 0: 38%|███▊ | 137/363 [00:03<00:05, 43.89it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 33.37it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 34.26it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 33.80it/s] Loading 0: 43%|████▎ | 157/363 [00:03<00:04, 41.21it/s] Loading 0: 45%|████▍ | 163/363 [00:03<00:04, 42.00it/s] Loading 0: 46%|████▋ | 168/363 [00:04<00:04, 42.96it/s] Loading 0: 48%|████▊ | 175/363 [00:04<00:03, 48.46it/s] Loading 0: 50%|████▉ | 181/363 [00:04<00:03, 47.29it/s] Loading 0: 51%|█████ | 186/363 [00:04<00:03, 46.40it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 50.67it/s] Loading 0: 55%|█████▍ | 199/363 [00:04<00:03, 48.63it/s] Loading 0: 56%|█████▌ | 204/363 [00:04<00:03, 46.91it/s] Loading 0: 58%|█████▊ | 211/363 [00:04<00:02, 51.59it/s] Loading 0: 60%|█████▉ | 217/363 [00:05<00:03, 47.97it/s] Loading 0: 61%|██████▏ | 223/363 [00:05<00:03, 36.11it/s] Loading 0: 63%|██████▎ | 228/363 [00:05<00:03, 35.37it/s] Loading 0: 64%|██████▍ | 232/363 [00:05<00:03, 34.96it/s] Loading 0: 66%|██████▌ | 238/363 [00:05<00:03, 39.08it/s] Loading 0: 67%|██████▋ | 243/363 [00:05<00:02, 41.43it/s] Loading 0: 68%|██████▊ | 248/363 [00:05<00:03, 35.37it/s] Loading 0: 70%|███████ | 255/363 [00:06<00:02, 42.98it/s] Loading 0: 72%|███████▏ | 260/363 [00:06<00:02, 43.12it/s] Loading 0: 73%|███████▎ | 265/363 [00:06<00:02, 44.08it/s] Loading 0: 74%|███████▍ | 270/363 [00:06<00:02, 45.18it/s] Loading 0: 76%|███████▌ | 275/363 [00:06<00:02, 35.81it/s] Loading 0: 78%|███████▊ | 282/363 [00:06<00:01, 42.11it/s] Loading 0: 79%|███████▉ | 287/363 [00:06<00:01, 41.94it/s] Loading 0: 80%|████████ | 292/363 [00:06<00:01, 42.58it/s] Loading 0: 82%|████████▏ | 297/363 [00:07<00:01, 43.90it/s] Loading 0: 83%|████████▎ | 302/363 [00:07<00:01, 45.49it/s] Loading 0: 85%|████████▍ | 307/363 [00:14<00:23, 2.35it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:15, 3.26it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:08, 5.31it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:05, 7.22it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:03, 9.27it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 13.20it/s] Loading 0: 95%|█████████▍| 344/363 [00:14<00:01, 16.63it/s] Loading 0: 96%|█████████▌| 349/363 [00:14<00:00, 19.87it/s] Loading 0: 98%|█████████▊| 356/363 [00:15<00:00, 25.98it/s] Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 29.27it/s]
Job cloudyu-nemo-dpo-v20-v6-mkmlizer completed after 95.41s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v20-v6-mkmlizer
Pipeline stage MKMLizer completed in 95.92s
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-v6
Waiting for inference service cloudyu-nemo-dpo-v20-v6 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
Inference service cloudyu-nemo-dpo-v20-v6 ready after 231.30803537368774s
Pipeline stage MKMLDeployer completed in 231.84s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6308610439300537s
Received healthy response to inference request in 2.0160367488861084s
Received healthy response to inference request in 1.8280391693115234s
Received healthy response to inference request in 2.2206809520721436s
Received healthy response to inference request in 1.6590890884399414s
5 requests
0 failed requests
5th percentile: 1.6928791046142577
10th percentile: 1.7266691207885743
20th percentile: 1.7942491531372071
30th percentile: 1.8656386852264404
40th percentile: 1.9408377170562745
50th percentile: 2.0160367488861084
60th percentile: 2.0978944301605225
70th percentile: 2.1797521114349365
80th percentile: 2.3027169704437256
90th percentile: 2.4667890071868896
95th percentile: 2.5488250255584717
99th percentile: 2.614453840255737
mean time: 2.0709414005279543
Pipeline stage StressChecker completed in 11.76s
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 2.45s
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 2.30s
Shutdown handler de-registered
cloudyu-nemo-dpo-v20_v6 status is now deployed due to DeploymentManager action
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 3046.75s
Shutdown handler de-registered
cloudyu-nemo-dpo-v20_v6 status is now inactive due to auto deactivation removed underperforming models