submission_id: cloudyu-chaiml-nemo-dpo-v6_v1
developer_uid: cloudyu
best_of: 8
celo_rating: 1262.96
display_name: cloudyu-chaiml-nemo-dpo-v6_v1
family_friendly_score: 0.5584
family_friendly_standard_error: 0.007022669577874214
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}
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}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: cloudyu/ChaiML-Nemo-DPO-V6
latencies: [{'batch_size': 1, 'throughput': 0.6259349370018457, 'latency_mean': 1.5975207948684693, 'latency_p50': 1.5984811782836914, 'latency_p90': 1.761886715888977}, {'batch_size': 3, 'throughput': 1.1452260294509844, 'latency_mean': 2.606390093564987, 'latency_p50': 2.5970340967178345, 'latency_p90': 2.891778492927551}, {'batch_size': 5, 'throughput': 1.3983720092112963, 'latency_mean': 3.5579649066925048, 'latency_p50': 3.537082076072693, 'latency_p90': 4.0063241720199585}, {'batch_size': 6, 'throughput': 1.4542429520767457, 'latency_mean': 4.098771699666977, 'latency_p50': 4.160648941993713, 'latency_p90': 4.577400732040405}, {'batch_size': 8, 'throughput': 1.530896822158443, 'latency_mean': 5.204573360681533, 'latency_p50': 5.238419532775879, 'latency_p90': 5.8288291692733765}, {'batch_size': 10, 'throughput': 1.572847789837466, 'latency_mean': 6.320976966619492, 'latency_p50': 6.33896791934967, 'latency_p90': 7.122144246101379}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: cloudyu/ChaiML-Nemo-DPO-
model_name: cloudyu-chaiml-nemo-dpo-v6_v1
model_num_parameters: 12772070400.0
model_repo: cloudyu/ChaiML-Nemo-DPO-V6
model_size: 13B
num_battles: 17116
num_wins: 8595
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.42
timestamp: 2024-11-24T10:48:08+00:00
us_pacific_date: 2024-11-24
win_ratio: 0.5021617200280439
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-v6-v1-mkmlizer
Waiting for job on cloudyu-chaiml-nemo-dpo-v6-v1-mkmlizer to finish
Connection pool is full, discarding connection: %s. Connection pool size: %s
cloudyu-chaiml-nemo-dpo-v6-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-chaiml-nemo-dpo-v6-v1-mkmlizer: ║ _____ __ __ ║
cloudyu-chaiml-nemo-dpo-v6-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cloudyu-chaiml-nemo-dpo-v6-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cloudyu-chaiml-nemo-dpo-v6-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cloudyu-chaiml-nemo-dpo-v6-v1-mkmlizer: ║ /___/ ║
cloudyu-chaiml-nemo-dpo-v6-v1-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v6-v1-mkmlizer: ║ Version: 0.11.12 ║
cloudyu-chaiml-nemo-dpo-v6-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cloudyu-chaiml-nemo-dpo-v6-v1-mkmlizer: ║ https://mk1.ai ║
cloudyu-chaiml-nemo-dpo-v6-v1-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v6-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cloudyu-chaiml-nemo-dpo-v6-v1-mkmlizer: ║ belonging to: ║
cloudyu-chaiml-nemo-dpo-v6-v1-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v6-v1-mkmlizer: ║ Chai Research Corp. ║
cloudyu-chaiml-nemo-dpo-v6-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cloudyu-chaiml-nemo-dpo-v6-v1-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cloudyu-chaiml-nemo-dpo-v6-v1-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v6-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-chaiml-nemo-dpo-v6-v1-mkmlizer: Downloaded to shared memory in 46.159s
cloudyu-chaiml-nemo-dpo-v6-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmppba9kyeu, device:0
cloudyu-chaiml-nemo-dpo-v6-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-chaiml-nemo-dpo-v6-v1-mkmlizer: quantized model in 37.958s
cloudyu-chaiml-nemo-dpo-v6-v1-mkmlizer: Processed model cloudyu/ChaiML-Nemo-DPO-V6 in 84.117s
cloudyu-chaiml-nemo-dpo-v6-v1-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-chaiml-nemo-dpo-v6-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-chaiml-nemo-dpo-v6-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v1
cloudyu-chaiml-nemo-dpo-v6-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v1/config.json
cloudyu-chaiml-nemo-dpo-v6-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v1/special_tokens_map.json
cloudyu-chaiml-nemo-dpo-v6-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v1/tokenizer_config.json
cloudyu-chaiml-nemo-dpo-v6-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v1/tokenizer.json
cloudyu-chaiml-nemo-dpo-v6-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v1/flywheel_model.0.safetensors
cloudyu-chaiml-nemo-dpo-v6-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:12, 27.56it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:07, 48.50it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 45.96it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:07, 44.70it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 50.72it/s] Loading 0: 10%|█ | 37/363 [00:00<00:06, 48.06it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 44.93it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 49.72it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:07, 43.03it/s] Loading 0: 17%|█▋ | 60/363 [00:01<00:07, 43.05it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:11, 25.81it/s] Loading 0: 20%|█▉ | 71/363 [00:01<00:09, 30.67it/s] Loading 0: 21%|██ | 75/363 [00:01<00:09, 31.08it/s] Loading 0: 22%|██▏ | 80/363 [00:02<00:08, 34.55it/s] Loading 0: 23%|██▎ | 85/363 [00:02<00:07, 35.07it/s] Loading 0: 25%|██▍ | 89/363 [00:02<00:07, 35.87it/s] Loading 0: 26%|██▌ | 93/363 [00:02<00:08, 33.58it/s] Loading 0: 27%|██▋ | 97/363 [00:02<00:07, 33.84it/s] Loading 0: 28%|██▊ | 101/363 [00:02<00:08, 31.00it/s] Loading 0: 29%|██▉ | 106/363 [00:02<00:07, 33.78it/s] Loading 0: 31%|███ | 112/363 [00:02<00:06, 37.67it/s] Loading 0: 32%|███▏ | 116/363 [00:03<00:06, 35.32it/s] Loading 0: 33%|███▎ | 120/363 [00:03<00:07, 33.56it/s] Loading 0: 34%|███▍ | 124/363 [00:03<00:06, 35.03it/s] Loading 0: 35%|███▌ | 128/363 [00:03<00:07, 32.31it/s] Loading 0: 36%|███▋ | 132/363 [00:03<00:06, 33.91it/s] Loading 0: 37%|███▋ | 136/363 [00:03<00:07, 30.71it/s] Loading 0: 39%|███▉ | 142/363 [00:04<00:08, 24.96it/s] Loading 0: 40%|███▉ | 145/363 [00:04<00:09, 24.13it/s] Loading 0: 41%|████ | 149/363 [00:04<00:08, 24.45it/s] Loading 0: 42%|████▏ | 154/363 [00:04<00:07, 29.60it/s] Loading 0: 44%|████▎ | 158/363 [00:04<00:07, 29.06it/s] Loading 0: 45%|████▍ | 163/363 [00:04<00:05, 33.64it/s] Loading 0: 46%|████▌ | 167/363 [00:04<00:06, 30.89it/s] Loading 0: 47%|████▋ | 172/363 [00:04<00:05, 34.64it/s] Loading 0: 48%|████▊ | 176/363 [00:05<00:05, 32.25it/s] Loading 0: 50%|█████ | 183/363 [00:05<00:04, 39.00it/s] Loading 0: 52%|█████▏ | 188/363 [00:05<00:04, 38.12it/s] Loading 0: 53%|█████▎ | 192/363 [00:05<00:04, 37.78it/s] Loading 0: 54%|█████▍ | 196/363 [00:05<00:04, 36.18it/s] Loading 0: 55%|█████▌ | 201/363 [00:05<00:04, 37.42it/s] Loading 0: 56%|█████▋ | 205/363 [00:05<00:04, 35.02it/s] Loading 0: 58%|█████▊ | 210/363 [00:05<00:04, 38.02it/s] Loading 0: 59%|█████▉ | 214/363 [00:06<00:03, 37.35it/s] Loading 0: 61%|██████ | 220/363 [00:06<00:03, 43.12it/s] Loading 0: 62%|██████▏ | 225/363 [00:06<00:05, 27.12it/s] Loading 0: 63%|██████▎ | 230/363 [00:06<00:04, 30.18it/s] Loading 0: 66%|██████▌ | 238/363 [00:06<00:03, 39.20it/s] Loading 0: 67%|██████▋ | 243/363 [00:06<00:02, 41.07it/s] Loading 0: 68%|██████▊ | 248/363 [00:07<00:03, 36.21it/s] Loading 0: 70%|███████ | 255/363 [00:07<00:02, 43.30it/s] Loading 0: 72%|███████▏ | 260/363 [00:07<00:02, 42.90it/s] Loading 0: 73%|███████▎ | 265/363 [00:07<00:02, 41.81it/s] Loading 0: 74%|███████▍ | 270/363 [00:07<00:02, 41.02it/s] Loading 0: 76%|███████▌ | 275/363 [00:07<00:02, 31.71it/s] Loading 0: 78%|███████▊ | 282/363 [00:07<00:02, 38.36it/s] Loading 0: 79%|███████▉ | 287/363 [00:08<00:01, 38.45it/s] Loading 0: 80%|████████ | 292/363 [00:08<00:01, 38.43it/s] Loading 0: 82%|████████▏ | 297/363 [00:08<00:01, 39.32it/s] Loading 0: 83%|████████▎ | 302/363 [00:08<00:01, 39.46it/s] Loading 0: 85%|████████▍ | 307/363 [00:15<00:24, 2.32it/s] Loading 0: 86%|████████▌ | 312/363 [00:15<00:15, 3.22it/s] Loading 0: 88%|████████▊ | 320/363 [00:15<00:08, 5.25it/s] Loading 0: 90%|████████▉ | 326/363 [00:15<00:05, 7.09it/s] Loading 0: 91%|█████████ | 331/363 [00:15<00:03, 9.05it/s] Loading 0: 93%|█████████▎| 337/363 [00:16<00:02, 12.31it/s] Loading 0: 94%|█████████▍| 342/363 [00:16<00:01, 15.18it/s] Loading 0: 96%|█████████▌| 347/363 [00:16<00:00, 18.47it/s] Loading 0: 97%|█████████▋| 352/363 [00:16<00:00, 22.37it/s] Loading 0: 98%|█████████▊| 357/363 [00:16<00:00, 23.55it/s]
Job cloudyu-chaiml-nemo-dpo-v6-v1-mkmlizer completed after 114.57s with status: succeeded
Stopping job with name cloudyu-chaiml-nemo-dpo-v6-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.11s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cloudyu-chaiml-nemo-dpo-v6-v1
Waiting for inference service cloudyu-chaiml-nemo-dpo-v6-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
Inference service cloudyu-chaiml-nemo-dpo-v6-v1 ready after 120.45346021652222s
Pipeline stage MKMLDeployer completed in 120.95s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.323671340942383s
Received healthy response to inference request in 1.8785266876220703s
Received healthy response to inference request in 2.0852882862091064s
Received healthy response to inference request in 1.6568307876586914s
Received healthy response to inference request in 1.907674789428711s
5 requests
0 failed requests
5th percentile: 1.7011699676513672
10th percentile: 1.745509147644043
20th percentile: 1.8341875076293945
30th percentile: 1.8843563079833985
40th percentile: 1.8960155487060546
50th percentile: 1.907674789428711
60th percentile: 1.9787201881408691
70th percentile: 2.0497655868530273
80th percentile: 2.1329648971557615
90th percentile: 2.228318119049072
95th percentile: 2.2759947299957277
99th percentile: 2.314136018753052
mean time: 1.9703983783721923
Pipeline stage StressChecker completed in 11.27s
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 2.20s
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 2.51s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v6_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 2852.88s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v6_v1 status is now inactive due to auto deactivation removed underperforming models