developer_uid: cloudyu
submission_id: cloudyu-nemo-dpo-v20_v3
model_name: cloudyu-nemo-dpo-v20_v1
model_group: cloudyu/Nemo-DPO-V20
status: inactive
timestamp: 2024-12-16T14:41:37+00:00
num_battles: 12485
num_wins: 6448
celo_rating: 1275.59
family_friendly_score: 0.562
family_friendly_standard_error: 0.00701649485141976
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': 0.6173517225696569, 'latency_mean': 1.6197644197940826, 'latency_p50': 1.6070386171340942, 'latency_p90': 1.7894963502883912}, {'batch_size': 3, 'throughput': 1.1425326011933585, 'latency_mean': 2.620935473442078, 'latency_p50': 2.627113699913025, 'latency_p90': 2.9248717784881593}, {'batch_size': 5, 'throughput': 1.3820490364751992, 'latency_mean': 3.599604340791702, 'latency_p50': 3.579520106315613, 'latency_p90': 4.063385057449341}, {'batch_size': 6, 'throughput': 1.4546708371121528, 'latency_mean': 4.111487194299698, 'latency_p50': 4.100148439407349, 'latency_p90': 4.520485281944275}, {'batch_size': 8, 'throughput': 1.530665161054812, 'latency_mean': 5.1900948822498325, 'latency_p50': 5.15337347984314, 'latency_p90': 5.8708209037780765}, {'batch_size': 10, 'throughput': 1.5463595158089478, 'latency_mean': 6.410782704353332, 'latency_p50': 6.450120687484741, 'latency_p90': 7.3420597314834595}]
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: 1.4
us_pacific_date: 2024-12-16
win_ratio: 0.5164597517020425
generation_params: {'temperature': 0.95, 'top_p': 0.95, 'min_p': 0.05, '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-v3-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v20-v3-mkmlizer to finish
cloudyu-nemo-dpo-v20-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v20-v3-mkmlizer: ║ _____ __ __ ║
cloudyu-nemo-dpo-v20-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cloudyu-nemo-dpo-v20-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cloudyu-nemo-dpo-v20-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cloudyu-nemo-dpo-v20-v3-mkmlizer: ║ /___/ ║
cloudyu-nemo-dpo-v20-v3-mkmlizer: ║ ║
cloudyu-nemo-dpo-v20-v3-mkmlizer: ║ Version: 0.11.12 ║
cloudyu-nemo-dpo-v20-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cloudyu-nemo-dpo-v20-v3-mkmlizer: ║ https://mk1.ai ║
cloudyu-nemo-dpo-v20-v3-mkmlizer: ║ ║
cloudyu-nemo-dpo-v20-v3-mkmlizer: ║ The license key for the current software has been verified as ║
cloudyu-nemo-dpo-v20-v3-mkmlizer: ║ belonging to: ║
cloudyu-nemo-dpo-v20-v3-mkmlizer: ║ ║
cloudyu-nemo-dpo-v20-v3-mkmlizer: ║ Chai Research Corp. ║
cloudyu-nemo-dpo-v20-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cloudyu-nemo-dpo-v20-v3-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cloudyu-nemo-dpo-v20-v3-mkmlizer: ║ ║
cloudyu-nemo-dpo-v20-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v20-v3-mkmlizer: Downloaded to shared memory in 50.139s
cloudyu-nemo-dpo-v20-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpqf8b0k6g, device:0
cloudyu-nemo-dpo-v20-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v20-v3-mkmlizer: quantized model in 36.523s
cloudyu-nemo-dpo-v20-v3-mkmlizer: Processed model cloudyu/Nemo-DPO-V20 in 86.663s
cloudyu-nemo-dpo-v20-v3-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v20-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v20-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v3
cloudyu-nemo-dpo-v20-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v3/config.json
cloudyu-nemo-dpo-v20-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v3/special_tokens_map.json
cloudyu-nemo-dpo-v20-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v3/tokenizer_config.json
cloudyu-nemo-dpo-v20-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v3/tokenizer.json
cloudyu-nemo-dpo-v20-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v3/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v20-v3-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:12, 28.93it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:07, 48.24it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:08, 42.64it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:08, 41.96it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 47.61it/s] Loading 0: 10%|█ | 37/363 [00:00<00:07, 43.75it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 42.35it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:06, 46.14it/s] Loading 0: 15%|█▍ | 53/363 [00:01<00:06, 44.40it/s] Loading 0: 16%|█▌ | 58/363 [00:01<00:06, 45.29it/s] Loading 0: 17%|█▋ | 63/363 [00:01<00:09, 30.21it/s] Loading 0: 18%|█▊ | 67/363 [00:01<00:09, 30.90it/s] Loading 0: 20%|█▉ | 71/363 [00:01<00:08, 32.65it/s] Loading 0: 21%|██ | 75/363 [00:01<00:08, 33.47it/s] Loading 0: 22%|██▏ | 80/363 [00:02<00:07, 36.58it/s] Loading 0: 23%|██▎ | 84/363 [00:02<00:07, 35.87it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:06, 40.06it/s] Loading 0: 26%|██▌ | 95/363 [00:02<00:06, 42.60it/s] Loading 0: 28%|██▊ | 100/363 [00:02<00:07, 35.35it/s] Loading 0: 29%|██▉ | 106/363 [00:02<00:06, 40.64it/s] Loading 0: 31%|███ | 112/363 [00:02<00:05, 44.27it/s] Loading 0: 32%|███▏ | 117/363 [00:02<00:05, 41.56it/s] Loading 0: 34%|███▎ | 122/363 [00:03<00:05, 41.63it/s] Loading 0: 35%|███▍ | 127/363 [00:03<00:06, 34.10it/s] Loading 0: 37%|███▋ | 134/363 [00:03<00:05, 41.80it/s] Loading 0: 38%|███▊ | 139/363 [00:03<00:05, 42.60it/s] Loading 0: 40%|███▉ | 144/363 [00:03<00:07, 27.96it/s] Loading 0: 41%|████ | 149/363 [00:03<00:07, 30.11it/s] Loading 0: 43%|████▎ | 156/363 [00:04<00:05, 37.97it/s] Loading 0: 44%|████▍ | 161/363 [00:04<00:05, 39.13it/s] Loading 0: 46%|████▌ | 166/363 [00:04<00:04, 40.71it/s] Loading 0: 47%|████▋ | 172/363 [00:04<00:04, 39.70it/s] Loading 0: 49%|████▉ | 177/363 [00:04<00:04, 38.75it/s] Loading 0: 50%|█████ | 183/363 [00:04<00:04, 41.93it/s] Loading 0: 52%|█████▏ | 188/363 [00:04<00:04, 41.86it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 42.62it/s] Loading 0: 55%|█████▍ | 198/363 [00:05<00:03, 44.11it/s] Loading 0: 56%|█████▌ | 203/363 [00:05<00:04, 36.56it/s] Loading 0: 58%|█████▊ | 210/363 [00:05<00:03, 44.23it/s] Loading 0: 59%|█████▉ | 215/363 [00:05<00:03, 43.81it/s] Loading 0: 61%|██████ | 220/363 [00:05<00:03, 45.19it/s] Loading 0: 62%|██████▏ | 225/363 [00:05<00:05, 27.47it/s] Loading 0: 63%|██████▎ | 230/363 [00:06<00:04, 29.31it/s] Loading 0: 65%|██████▌ | 237/363 [00:06<00:03, 37.13it/s] Loading 0: 67%|██████▋ | 242/363 [00:06<00:03, 38.78it/s] Loading 0: 68%|██████▊ | 247/363 [00:06<00:02, 40.02it/s] Loading 0: 69%|██████▉ | 252/363 [00:06<00:02, 42.17it/s] Loading 0: 71%|███████ | 257/363 [00:06<00:02, 35.93it/s] Loading 0: 73%|███████▎ | 264/363 [00:06<00:02, 43.32it/s] Loading 0: 74%|███████▍ | 269/363 [00:06<00:02, 42.47it/s] Loading 0: 75%|███████▌ | 274/363 [00:07<00:02, 42.24it/s] Loading 0: 77%|███████▋ | 279/363 [00:07<00:01, 43.74it/s] Loading 0: 78%|███████▊ | 284/363 [00:07<00:02, 37.12it/s] Loading 0: 80%|████████ | 291/363 [00:07<00:01, 44.13it/s] Loading 0: 82%|████████▏ | 296/363 [00:07<00:01, 43.77it/s] Loading 0: 83%|████████▎ | 302/363 [00:07<00:01, 47.22it/s] Loading 0: 85%|████████▍ | 307/363 [00:14<00:22, 2.53it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:14, 3.45it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:07, 5.50it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:05, 7.38it/s] Loading 0: 91%|█████████ | 331/363 [00:15<00:03, 9.38it/s] Loading 0: 93%|█████████▎| 337/363 [00:15<00:02, 12.67it/s] Loading 0: 94%|█████████▍| 342/363 [00:15<00:01, 15.64it/s] Loading 0: 96%|█████████▌| 347/363 [00:15<00:00, 19.06it/s] Loading 0: 97%|█████████▋| 353/363 [00:15<00:00, 22.73it/s] Loading 0: 99%|█████████▊| 358/363 [00:15<00:00, 25.82it/s]
Job cloudyu-nemo-dpo-v20-v3-mkmlizer completed after 115.23s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v20-v3-mkmlizer
Pipeline stage MKMLizer completed in 115.79s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cloudyu-nemo-dpo-v20-v3
Waiting for inference service cloudyu-nemo-dpo-v20-v3 to be ready
Retrying (%r) after connection broken by '%r': %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
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
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-v3 ready after 220.83029127120972s
Pipeline stage MKMLDeployer completed in 221.39s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3023838996887207s
Received healthy response to inference request in 2.081510305404663s
Received healthy response to inference request in 1.7761266231536865s
Received healthy response to inference request in 1.7296688556671143s
Received healthy response to inference request in 2.6545250415802s
5 requests
0 failed requests
5th percentile: 1.7389604091644286
10th percentile: 1.7482519626617432
20th percentile: 1.7668350696563722
30th percentile: 1.837203359603882
40th percentile: 1.9593568325042725
50th percentile: 2.081510305404663
60th percentile: 2.169859743118286
70th percentile: 2.2582091808319094
80th percentile: 2.3728121280670167
90th percentile: 2.513668584823608
95th percentile: 2.584096813201904
99th percentile: 2.640439395904541
mean time: 2.108842945098877
Pipeline stage StressChecker completed in 11.88s
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 2.43s
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 2.31s
Shutdown handler de-registered
cloudyu-nemo-dpo-v20_v3 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 0.10s
run pipeline stage %s
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 3129.79s
Shutdown handler de-registered
cloudyu-nemo-dpo-v20_v3 status is now inactive due to auto deactivation removed underperforming models