developer_uid: cloudyu
submission_id: cloudyu-nemo-dpo-v23_v1
model_name: cloudyu-nemo-dpo-v23_v1
model_group: cloudyu/Nemo-DPO-V23
status: torndown
timestamp: 2025-01-10T06:20:26+00:00
num_battles: 7959
num_wins: 4110
celo_rating: 1274.41
family_friendly_score: 0.579
family_friendly_standard_error: 0.006982248921371967
submission_type: basic
model_repo: cloudyu/Nemo-DPO-V23
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6144034476193457, 'latency_mean': 1.6275412011146546, 'latency_p50': 1.6318615674972534, 'latency_p90': 1.7975469827651978}, {'batch_size': 3, 'throughput': 1.1451406885273114, 'latency_mean': 2.6069427835941315, 'latency_p50': 2.610946774482727, 'latency_p90': 2.829147720336914}, {'batch_size': 5, 'throughput': 1.3632647920215644, 'latency_mean': 3.643236312866211, 'latency_p50': 3.670146107673645, 'latency_p90': 4.054275488853454}, {'batch_size': 6, 'throughput': 1.4464823392237776, 'latency_mean': 4.1269960272312165, 'latency_p50': 4.15249228477478, 'latency_p90': 4.652853393554688}, {'batch_size': 8, 'throughput': 1.5114240276012005, 'latency_mean': 5.271308441162109, 'latency_p50': 5.282905340194702, 'latency_p90': 5.93916175365448}, {'batch_size': 10, 'throughput': 1.5515624641378623, 'latency_mean': 6.398291767835617, 'latency_p50': 6.378500819206238, 'latency_p90': 7.3463242769241335}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: cloudyu-nemo-dpo-v23_v1
is_internal_developer: False
language_model: cloudyu/Nemo-DPO-V23
model_size: 13B
ranking_group: single
throughput_3p7s: 1.38
us_pacific_date: 2025-01-09
win_ratio: 0.5163965322276668
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-v23-v1-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v23-v1-mkmlizer to finish
cloudyu-nemo-dpo-v23-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v23-v1-mkmlizer: ║ _____ __ __ ║
cloudyu-nemo-dpo-v23-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cloudyu-nemo-dpo-v23-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cloudyu-nemo-dpo-v23-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cloudyu-nemo-dpo-v23-v1-mkmlizer: ║ /___/ ║
cloudyu-nemo-dpo-v23-v1-mkmlizer: ║ ║
cloudyu-nemo-dpo-v23-v1-mkmlizer: ║ Version: 0.11.12 ║
cloudyu-nemo-dpo-v23-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cloudyu-nemo-dpo-v23-v1-mkmlizer: ║ https://mk1.ai ║
cloudyu-nemo-dpo-v23-v1-mkmlizer: ║ ║
cloudyu-nemo-dpo-v23-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cloudyu-nemo-dpo-v23-v1-mkmlizer: ║ belonging to: ║
cloudyu-nemo-dpo-v23-v1-mkmlizer: ║ ║
cloudyu-nemo-dpo-v23-v1-mkmlizer: ║ Chai Research Corp. ║
cloudyu-nemo-dpo-v23-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cloudyu-nemo-dpo-v23-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
cloudyu-nemo-dpo-v23-v1-mkmlizer: ║ ║
cloudyu-nemo-dpo-v23-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v23-v1-mkmlizer: Downloaded to shared memory in 49.933s
cloudyu-nemo-dpo-v23-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3tuqmriu, device:0
cloudyu-nemo-dpo-v23-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v23-v1-mkmlizer: quantized model in 36.068s
cloudyu-nemo-dpo-v23-v1-mkmlizer: Processed model cloudyu/Nemo-DPO-V23 in 86.001s
cloudyu-nemo-dpo-v23-v1-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v23-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v23-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v23-v1
cloudyu-nemo-dpo-v23-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v23-v1/config.json
cloudyu-nemo-dpo-v23-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v23-v1/special_tokens_map.json
cloudyu-nemo-dpo-v23-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v23-v1/tokenizer_config.json
cloudyu-nemo-dpo-v23-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v23-v1/tokenizer.json
cloudyu-nemo-dpo-v23-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v23-v1/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v23-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 2/363 [00:06<18:08, 3.02s/it] Loading 0: 2%|▏ | 6/363 [00:06<04:49, 1.23it/s] Loading 0: 4%|▎ | 13/363 [00:06<01:43, 3.40it/s] Loading 0: 5%|▌ | 19/363 [00:06<00:59, 5.83it/s] Loading 0: 7%|▋ | 24/363 [00:06<00:42, 8.07it/s] Loading 0: 9%|▉ | 32/363 [00:06<00:25, 13.20it/s] Loading 0: 10%|█ | 37/363 [00:06<00:19, 16.54it/s] Loading 0: 12%|█▏ | 42/363 [00:07<00:20, 15.69it/s] Loading 0: 14%|█▍ | 50/363 [00:07<00:13, 22.54it/s] Loading 0: 15%|█▌ | 55/363 [00:07<00:11, 26.09it/s] Loading 0: 17%|█▋ | 60/363 [00:07<00:11, 26.61it/s] Loading 0: 18%|█▊ | 67/363 [00:07<00:08, 33.96it/s] Loading 0: 20%|█▉ | 72/363 [00:07<00:08, 36.20it/s] Loading 0: 21%|██ | 77/363 [00:07<00:07, 37.17it/s] Loading 0: 23%|██▎ | 82/363 [00:08<00:07, 39.17it/s] Loading 0: 24%|██▍ | 87/363 [00:08<00:08, 34.28it/s] Loading 0: 26%|██▌ | 95/363 [00:08<00:06, 42.79it/s] Loading 0: 28%|██▊ | 100/363 [00:08<00:05, 44.40it/s] Loading 0: 29%|██▉ | 105/363 [00:08<00:06, 37.40it/s] Loading 0: 31%|███ | 112/363 [00:08<00:05, 44.36it/s] Loading 0: 32%|███▏ | 117/363 [00:08<00:05, 43.06it/s] Loading 0: 34%|███▎ | 122/363 [00:09<00:07, 30.97it/s] Loading 0: 35%|███▍ | 126/363 [00:09<00:07, 32.57it/s] Loading 0: 36%|███▌ | 131/363 [00:09<00:06, 35.40it/s] Loading 0: 37%|███▋ | 136/363 [00:09<00:06, 37.45it/s] Loading 0: 39%|███▉ | 141/363 [00:09<00:06, 32.66it/s] Loading 0: 41%|████ | 148/363 [00:09<00:05, 39.35it/s] Loading 0: 42%|████▏ | 153/363 [00:09<00:05, 39.82it/s] Loading 0: 44%|████▎ | 158/363 [00:09<00:04, 41.32it/s] Loading 0: 45%|████▌ | 164/363 [00:10<00:04, 40.65it/s] Loading 0: 47%|████▋ | 169/363 [00:10<00:04, 39.58it/s] Loading 0: 48%|████▊ | 175/363 [00:10<00:04, 44.08it/s] Loading 0: 50%|████▉ | 180/363 [00:10<00:04, 43.75it/s] Loading 0: 51%|█████ | 185/363 [00:10<00:04, 43.02it/s] Loading 0: 53%|█████▎ | 191/363 [00:10<00:04, 41.67it/s] Loading 0: 54%|█████▍ | 196/363 [00:10<00:04, 40.14it/s] Loading 0: 56%|█████▌ | 202/363 [00:11<00:04, 32.66it/s] Loading 0: 57%|█████▋ | 206/363 [00:11<00:04, 33.28it/s] Loading 0: 58%|█████▊ | 212/363 [00:11<00:04, 37.73it/s] Loading 0: 60%|██████ | 218/363 [00:11<00:03, 37.93it/s] Loading 0: 61%|██████ | 222/363 [00:11<00:03, 35.94it/s] Loading 0: 63%|██████▎ | 230/363 [00:11<00:03, 44.25it/s] Loading 0: 65%|██████▌ | 236/363 [00:11<00:02, 42.78it/s] Loading 0: 66%|██████▋ | 241/363 [00:12<00:02, 41.69it/s] Loading 0: 68%|██████▊ | 248/363 [00:12<00:02, 46.37it/s] Loading 0: 70%|██████▉ | 254/363 [00:12<00:02, 44.68it/s] Loading 0: 71%|███████▏ | 259/363 [00:12<00:02, 43.30it/s] Loading 0: 73%|███████▎ | 265/363 [00:12<00:02, 46.88it/s] Loading 0: 74%|███████▍ | 270/363 [00:12<00:02, 46.08it/s] Loading 0: 76%|███████▌ | 275/363 [00:12<00:01, 46.21it/s] Loading 0: 77%|███████▋ | 281/363 [00:12<00:01, 42.84it/s] Loading 0: 79%|███████▉ | 286/363 [00:13<00:02, 30.84it/s] Loading 0: 80%|████████ | 292/363 [00:13<00:01, 36.35it/s] Loading 0: 82%|████████▏ | 297/363 [00:13<00:01, 38.33it/s] Loading 0: 83%|████████▎ | 302/363 [00:13<00:01, 39.59it/s] Loading 0: 85%|████████▍ | 308/363 [00:13<00:01, 40.31it/s] Loading 0: 86%|████████▌ | 313/363 [00:13<00:01, 40.00it/s] Loading 0: 88%|████████▊ | 319/363 [00:13<00:00, 44.73it/s] Loading 0: 89%|████████▉ | 324/363 [00:14<00:00, 42.77it/s] Loading 0: 91%|█████████ | 329/363 [00:14<00:00, 44.12it/s] Loading 0: 92%|█████████▏| 335/363 [00:14<00:00, 42.87it/s] Loading 0: 94%|█████████▎| 340/363 [00:14<00:00, 41.62it/s] Loading 0: 95%|█████████▌| 346/363 [00:14<00:00, 45.50it/s] Loading 0: 97%|█████████▋| 351/363 [00:14<00:00, 45.40it/s] Loading 0: 98%|█████████▊| 356/363 [00:14<00:00, 46.27it/s] Loading 0: 100%|█████████▉| 362/363 [00:14<00:00, 44.24it/s]
Job cloudyu-nemo-dpo-v23-v1-mkmlizer completed after 115.27s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v23-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.83s
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-v23-v1
Waiting for inference service cloudyu-nemo-dpo-v23-v1 to be ready
Inference service cloudyu-nemo-dpo-v23-v1 ready after 362.2947015762329s
Pipeline stage MKMLDeployer completed in 362.88s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.590301275253296s
Received healthy response to inference request in 1.9968211650848389s
Received healthy response to inference request in 2.3227174282073975s
Received healthy response to inference request in 1.6906378269195557s
Received healthy response to inference request in 1.740581750869751s
5 requests
0 failed requests
5th percentile: 1.7006266117095947
10th percentile: 1.7106153964996338
20th percentile: 1.730592966079712
30th percentile: 1.7918296337127686
40th percentile: 1.8943253993988036
50th percentile: 1.9968211650848389
60th percentile: 2.127179670333862
70th percentile: 2.257538175582886
80th percentile: 2.376234197616577
90th percentile: 2.4832677364349367
95th percentile: 2.5367845058441163
99th percentile: 2.57959792137146
mean time: 2.068211889266968
Pipeline stage StressChecker completed in 11.87s
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 0.71s
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 0.67s
Shutdown handler de-registered
cloudyu-nemo-dpo-v23_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 2654.86s
Shutdown handler de-registered
cloudyu-nemo-dpo-v23_v1 status is now inactive due to auto deactivation removed underperforming models
cloudyu-nemo-dpo-v23_v1 status is now torndown due to DeploymentManager action