developer_uid: cloudyu
submission_id: cloudyu-chaiml-nemo-dpo-v3_v1
model_name: cloudyu-chaiml-nemo-dpo-v3_v1
model_group: cloudyu/ChaiML-Nemo-DPO-
status: inactive
timestamp: 2024-11-24T07:07:28+00:00
num_battles: 19735
num_wins: 9607
celo_rating: 1248.38
family_friendly_score: 0.5771999999999999
family_friendly_standard_error: 0.0069862745437035325
submission_type: basic
model_repo: cloudyu/ChaiML-Nemo-DPO-V3
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6156008908020983, 'latency_mean': 1.6243272721767426, 'latency_p50': 1.6295408010482788, 'latency_p90': 1.7898449420928955}, {'batch_size': 3, 'throughput': 1.1351266101971644, 'latency_mean': 2.6342823016643524, 'latency_p50': 2.618568539619446, 'latency_p90': 2.891227602958679}, {'batch_size': 5, 'throughput': 1.381999878475858, 'latency_mean': 3.6061539566516876, 'latency_p50': 3.590410828590393, 'latency_p90': 4.026088428497315}, {'batch_size': 6, 'throughput': 1.4491458937180977, 'latency_mean': 4.113637982606888, 'latency_p50': 4.125617146492004, 'latency_p90': 4.650018954277038}, {'batch_size': 8, 'throughput': 1.5116575743605936, 'latency_mean': 5.256815832853317, 'latency_p50': 5.316892623901367, 'latency_p90': 5.905812191963196}, {'batch_size': 10, 'throughput': 1.548778189537221, 'latency_mean': 6.402556357383728, 'latency_p50': 6.405139446258545, 'latency_p90': 7.234859609603882}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: cloudyu-chaiml-nemo-dpo-v3_v1
is_internal_developer: False
language_model: cloudyu/ChaiML-Nemo-DPO-V3
model_size: 13B
ranking_group: single
throughput_3p7s: 1.4
us_pacific_date: 2024-11-23
win_ratio: 0.486800101342792
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, '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-v3-v1-mkmlizer
Waiting for job on cloudyu-chaiml-nemo-dpo-v3-v1-mkmlizer to finish
cloudyu-chaiml-nemo-dpo-v3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-chaiml-nemo-dpo-v3-v1-mkmlizer: ║ _____ __ __ ║
cloudyu-chaiml-nemo-dpo-v3-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cloudyu-chaiml-nemo-dpo-v3-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cloudyu-chaiml-nemo-dpo-v3-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cloudyu-chaiml-nemo-dpo-v3-v1-mkmlizer: ║ /___/ ║
cloudyu-chaiml-nemo-dpo-v3-v1-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v3-v1-mkmlizer: ║ Version: 0.11.12 ║
cloudyu-chaiml-nemo-dpo-v3-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cloudyu-chaiml-nemo-dpo-v3-v1-mkmlizer: ║ https://mk1.ai ║
cloudyu-chaiml-nemo-dpo-v3-v1-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v3-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cloudyu-chaiml-nemo-dpo-v3-v1-mkmlizer: ║ belonging to: ║
cloudyu-chaiml-nemo-dpo-v3-v1-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v3-v1-mkmlizer: ║ Chai Research Corp. ║
cloudyu-chaiml-nemo-dpo-v3-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cloudyu-chaiml-nemo-dpo-v3-v1-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cloudyu-chaiml-nemo-dpo-v3-v1-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-chaiml-nemo-dpo-v3-v1-mkmlizer: Downloaded to shared memory in 47.897s
cloudyu-chaiml-nemo-dpo-v3-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpciftn59w, device:0
cloudyu-chaiml-nemo-dpo-v3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
cloudyu-chaiml-nemo-dpo-v3-v1-mkmlizer: quantized model in 36.915s
cloudyu-chaiml-nemo-dpo-v3-v1-mkmlizer: Processed model cloudyu/ChaiML-Nemo-DPO-V3 in 84.812s
cloudyu-chaiml-nemo-dpo-v3-v1-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-chaiml-nemo-dpo-v3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-chaiml-nemo-dpo-v3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v3-v1
cloudyu-chaiml-nemo-dpo-v3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v3-v1/config.json
cloudyu-chaiml-nemo-dpo-v3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v3-v1/special_tokens_map.json
cloudyu-chaiml-nemo-dpo-v3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v3-v1/tokenizer_config.json
cloudyu-chaiml-nemo-dpo-v3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v3-v1/tokenizer.json
cloudyu-chaiml-nemo-dpo-v3-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:13, 26.11it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:07, 44.80it/s] Loading 0: 5%|▍ | 18/363 [00:00<00:07, 46.17it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:08, 39.65it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:07, 46.20it/s] Loading 0: 10%|█ | 37/363 [00:00<00:07, 43.81it/s] Loading 0: 12%|█▏ | 42/363 [00:01<00:07, 41.46it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:06, 45.63it/s] Loading 0: 15%|█▍ | 53/363 [00:01<00:06, 44.67it/s] Loading 0: 16%|█▋ | 59/363 [00:01<00:06, 48.60it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:10, 29.53it/s] Loading 0: 20%|█▉ | 71/363 [00:01<00:08, 34.68it/s] Loading 0: 21%|██ | 76/363 [00:01<00:07, 37.09it/s] Loading 0: 22%|██▏ | 81/363 [00:02<00:07, 39.95it/s] Loading 0: 24%|██▍ | 87/363 [00:02<00:06, 40.05it/s] Loading 0: 25%|██▌ | 92/363 [00:02<00:06, 40.03it/s] Loading 0: 27%|██▋ | 98/363 [00:02<00:05, 44.33it/s] Loading 0: 28%|██▊ | 103/363 [00:02<00:05, 43.80it/s] Loading 0: 30%|██▉ | 108/363 [00:02<00:05, 45.09it/s] Loading 0: 31%|███ | 113/363 [00:02<00:06, 39.13it/s] Loading 0: 33%|███▎ | 118/363 [00:02<00:06, 38.77it/s] Loading 0: 35%|███▍ | 126/363 [00:03<00:05, 46.32it/s] Loading 0: 36%|███▌ | 131/363 [00:03<00:04, 46.81it/s] Loading 0: 37%|███▋ | 136/363 [00:03<00:05, 38.83it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:07, 30.39it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 31.52it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 30.79it/s] Loading 0: 43%|████▎ | 156/363 [00:03<00:05, 36.99it/s] Loading 0: 44%|████▍ | 161/363 [00:04<00:05, 38.51it/s] Loading 0: 46%|████▌ | 166/363 [00:04<00:04, 41.02it/s] Loading 0: 47%|████▋ | 172/363 [00:04<00:04, 40.78it/s] Loading 0: 49%|████▉ | 177/363 [00:04<00:04, 40.94it/s] Loading 0: 50%|█████ | 183/363 [00:04<00:04, 44.45it/s] Loading 0: 52%|█████▏ | 188/363 [00:04<00:03, 44.43it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 43.35it/s] Loading 0: 55%|█████▍ | 199/363 [00:04<00:04, 40.82it/s] Loading 0: 56%|█████▌ | 204/363 [00:05<00:03, 40.50it/s] Loading 0: 58%|█████▊ | 211/363 [00:05<00:03, 45.87it/s] Loading 0: 60%|█████▉ | 217/363 [00:05<00:03, 43.82it/s] Loading 0: 61%|██████▏ | 223/363 [00:05<00:04, 32.51it/s] Loading 0: 63%|██████▎ | 227/363 [00:05<00:04, 32.87it/s] Loading 0: 64%|██████▎ | 231/363 [00:05<00:04, 32.28it/s] Loading 0: 66%|██████▌ | 238/363 [00:06<00:03, 39.10it/s] Loading 0: 67%|██████▋ | 244/363 [00:06<00:03, 39.61it/s] Loading 0: 69%|██████▊ | 249/363 [00:06<00:02, 39.49it/s] Loading 0: 71%|███████ | 256/363 [00:06<00:02, 44.42it/s] Loading 0: 72%|███████▏ | 262/363 [00:06<00:02, 43.63it/s] Loading 0: 74%|███████▎ | 267/363 [00:06<00:02, 42.83it/s] Loading 0: 75%|███████▌ | 273/363 [00:06<00:01, 46.75it/s] Loading 0: 77%|███████▋ | 278/363 [00:06<00:01, 45.03it/s] Loading 0: 78%|███████▊ | 283/363 [00:07<00:01, 45.28it/s] Loading 0: 79%|███████▉ | 288/363 [00:07<00:01, 46.03it/s] Loading 0: 81%|████████ | 293/363 [00:07<00:01, 38.58it/s] Loading 0: 83%|████████▎ | 301/363 [00:07<00:01, 47.91it/s] Loading 0: 85%|████████▍ | 307/363 [00:14<00:20, 2.73it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:14, 3.61it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:07, 5.61it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:04, 7.49it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:03, 9.44it/s] Loading 0: 93%|█████████▎| 338/363 [00:15<00:01, 13.28it/s] Loading 0: 95%|█████████▍| 344/363 [00:15<00:01, 16.69it/s] Loading 0: 96%|█████████▌| 349/363 [00:15<00:00, 19.89it/s] Loading 0: 98%|█████████▊| 356/363 [00:15<00:00, 25.86it/s] Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 29.27it/s]
Job cloudyu-chaiml-nemo-dpo-v3-v1-mkmlizer completed after 114.19s with status: succeeded
Stopping job with name cloudyu-chaiml-nemo-dpo-v3-v1-mkmlizer
Pipeline stage MKMLizer completed in 114.70s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cloudyu-chaiml-nemo-dpo-v3-v1
Waiting for inference service cloudyu-chaiml-nemo-dpo-v3-v1 to be ready
Failed to get response for submission chaiml-lexical-nemov8-1k1e5_v52: ('http://chaiml-lexical-nemov8-1k1e5-v52-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:46164->127.0.0.1:8080: read: connection reset by peer\n')
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service cloudyu-chaiml-nemo-dpo-v3-v1 ready after 110.82090663909912s
Pipeline stage MKMLDeployer completed in 111.38s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3944077491760254s
Received healthy response to inference request in 1.9662127494812012s
Received healthy response to inference request in 1.8669390678405762s
Received healthy response to inference request in 1.8373310565948486s
Received healthy response to inference request in 1.8422083854675293s
5 requests
0 failed requests
5th percentile: 1.8383065223693849
10th percentile: 1.8392819881439209
20th percentile: 1.841232919692993
30th percentile: 1.8471545219421386
40th percentile: 1.8570467948913574
50th percentile: 1.8669390678405762
60th percentile: 1.906648540496826
70th percentile: 1.9463580131530762
80th percentile: 2.051851749420166
90th percentile: 2.2231297492980957
95th percentile: 2.3087687492370605
99th percentile: 2.3772799491882326
mean time: 1.9814198017120361
Pipeline stage StressChecker completed in 11.33s
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 2.46s
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 2.41s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v3_v1 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 2792.95s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v3_v1 status is now inactive due to auto deactivation removed underperforming models