submission_id: cloudyu-chaiml-nemo-dpo-v8_v2
developer_uid: cloudyu
best_of: 8
celo_rating: 1265.29
display_name: cloudyu-chaiml-nemo-dpo-v8_v2
family_friendly_score: 0.5582
family_friendly_standard_error: 0.007023001637476671
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': 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}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: cloudyu/ChaiML-Nemo-DPO-V8
latencies: [{'batch_size': 1, 'throughput': 0.6208466653291356, 'latency_mean': 1.6106380248069763, 'latency_p50': 1.6220916509628296, 'latency_p90': 1.764455008506775}, {'batch_size': 3, 'throughput': 1.1706503633814664, 'latency_mean': 2.5527929162979124, 'latency_p50': 2.567281126976013, 'latency_p90': 2.7791767358779906}, {'batch_size': 5, 'throughput': 1.4105024354835438, 'latency_mean': 3.5273810660839082, 'latency_p50': 3.5252082347869873, 'latency_p90': 3.9808411598205566}, {'batch_size': 6, 'throughput': 1.4911288114659722, 'latency_mean': 3.993527932167053, 'latency_p50': 3.9904178380966187, 'latency_p90': 4.5045661449432375}, {'batch_size': 8, 'throughput': 1.569668787122149, 'latency_mean': 5.059351369142532, 'latency_p50': 5.057339310646057, 'latency_p90': 5.70709490776062}, {'batch_size': 10, 'throughput': 1.6227547677288934, 'latency_mean': 6.116320497989655, 'latency_p50': 6.110349416732788, 'latency_p90': 6.918183040618897}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: cloudyu/ChaiML-Nemo-DPO-
model_name: cloudyu-chaiml-nemo-dpo-v8_v2
model_num_parameters: 12772070400.0
model_repo: cloudyu/ChaiML-Nemo-DPO-V8
model_size: 13B
num_battles: 29121
num_wins: 14701
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.45
timestamp: 2024-11-24T13:40:17+00:00
us_pacific_date: 2024-11-24
win_ratio: 0.5048246969540882
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-v8-v2-mkmlizer
Waiting for job on cloudyu-chaiml-nemo-dpo-v8-v2-mkmlizer to finish
Failed to get response for submission blend_lepur_2024-11-18: ('http://chaiml-llama-8b-pairwis-8189-v27-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:40292->127.0.0.1:8080: read: connection reset by peer\n')
cloudyu-chaiml-nemo-dpo-v8-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-chaiml-nemo-dpo-v8-v2-mkmlizer: ║ _____ __ __ ║
cloudyu-chaiml-nemo-dpo-v8-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cloudyu-chaiml-nemo-dpo-v8-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cloudyu-chaiml-nemo-dpo-v8-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cloudyu-chaiml-nemo-dpo-v8-v2-mkmlizer: ║ /___/ ║
cloudyu-chaiml-nemo-dpo-v8-v2-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v8-v2-mkmlizer: ║ Version: 0.11.12 ║
cloudyu-chaiml-nemo-dpo-v8-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cloudyu-chaiml-nemo-dpo-v8-v2-mkmlizer: ║ https://mk1.ai ║
cloudyu-chaiml-nemo-dpo-v8-v2-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v8-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cloudyu-chaiml-nemo-dpo-v8-v2-mkmlizer: ║ belonging to: ║
cloudyu-chaiml-nemo-dpo-v8-v2-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v8-v2-mkmlizer: ║ Chai Research Corp. ║
cloudyu-chaiml-nemo-dpo-v8-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cloudyu-chaiml-nemo-dpo-v8-v2-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cloudyu-chaiml-nemo-dpo-v8-v2-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v8-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-chaiml-nemo-dpo-v8-v2-mkmlizer: Downloaded to shared memory in 33.041s
cloudyu-chaiml-nemo-dpo-v8-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpoj84gy_q, device:0
cloudyu-chaiml-nemo-dpo-v8-v2-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-v8-v2-mkmlizer: quantized model in 35.988s
cloudyu-chaiml-nemo-dpo-v8-v2-mkmlizer: Processed model cloudyu/ChaiML-Nemo-DPO-V8 in 69.029s
cloudyu-chaiml-nemo-dpo-v8-v2-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-chaiml-nemo-dpo-v8-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-chaiml-nemo-dpo-v8-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v8-v2
cloudyu-chaiml-nemo-dpo-v8-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v8-v2/config.json
cloudyu-chaiml-nemo-dpo-v8-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v8-v2/special_tokens_map.json
cloudyu-chaiml-nemo-dpo-v8-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v8-v2/tokenizer_config.json
cloudyu-chaiml-nemo-dpo-v8-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v8-v2/tokenizer.json
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
cloudyu-chaiml-nemo-dpo-v8-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v8-v2/flywheel_model.0.safetensors
cloudyu-chaiml-nemo-dpo-v8-v2-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 2/363 [00:06<18:09, 3.02s/it] Loading 0: 2%|▏ | 6/363 [00:06<04:50, 1.23it/s] Loading 0: 4%|▎ | 13/363 [00:06<01:43, 3.37it/s] Loading 0: 5%|▍ | 17/363 [00:06<01:10, 4.90it/s] Loading 0: 6%|▋ | 23/363 [00:06<00:42, 7.99it/s] Loading 0: 8%|▊ | 28/363 [00:06<00:30, 11.12it/s] Loading 0: 9%|▉ | 33/363 [00:06<00:23, 13.89it/s] Loading 0: 11%|█ | 40/363 [00:07<00:18, 17.19it/s] Loading 0: 12%|█▏ | 44/363 [00:07<00:16, 19.57it/s] Loading 0: 14%|█▍ | 50/363 [00:07<00:12, 25.08it/s] Loading 0: 15%|█▌ | 56/363 [00:07<00:10, 28.50it/s] Loading 0: 17%|█▋ | 61/363 [00:07<00:09, 31.03it/s] Loading 0: 18%|█▊ | 67/363 [00:07<00:08, 36.76it/s] Loading 0: 20%|█▉ | 72/363 [00:07<00:07, 38.21it/s] Loading 0: 21%|██ | 77/363 [00:07<00:07, 40.64it/s] Loading 0: 23%|██▎ | 83/363 [00:08<00:06, 40.70it/s] Loading 0: 24%|██▍ | 88/363 [00:08<00:06, 39.50it/s] Loading 0: 26%|██▌ | 95/363 [00:08<00:05, 44.77it/s] Loading 0: 28%|██▊ | 101/363 [00:08<00:06, 43.53it/s] Loading 0: 29%|██▉ | 106/363 [00:08<00:06, 40.70it/s] Loading 0: 31%|███ | 112/363 [00:08<00:05, 44.98it/s] Loading 0: 32%|███▏ | 117/363 [00:08<00:05, 45.22it/s] Loading 0: 34%|███▎ | 122/363 [00:09<00:07, 32.68it/s] Loading 0: 35%|███▍ | 126/363 [00:09<00:06, 34.02it/s] Loading 0: 36%|███▌ | 131/363 [00:09<00:06, 37.22it/s] Loading 0: 38%|███▊ | 137/363 [00:09<00:05, 37.84it/s] Loading 0: 39%|███▉ | 142/363 [00:09<00:05, 37.15it/s] Loading 0: 40%|████ | 146/363 [00:09<00:05, 37.69it/s] Loading 0: 41%|████▏ | 150/363 [00:09<00:05, 35.71it/s] Loading 0: 43%|████▎ | 157/363 [00:09<00:04, 43.93it/s] Loading 0: 45%|████▍ | 162/363 [00:10<00:04, 43.85it/s] Loading 0: 46%|████▌ | 167/363 [00:10<00:04, 44.95it/s] Loading 0: 47%|████▋ | 172/363 [00:10<00:04, 46.04it/s] Loading 0: 49%|████▉ | 177/363 [00:10<00:04, 37.66it/s] Loading 0: 51%|█████ | 185/363 [00:10<00:03, 45.88it/s] Loading 0: 53%|█████▎ | 191/363 [00:10<00:03, 43.93it/s] Loading 0: 54%|█████▍ | 196/363 [00:10<00:03, 43.58it/s] Loading 0: 56%|█████▌ | 202/363 [00:11<00:04, 35.20it/s] Loading 0: 57%|█████▋ | 206/363 [00:11<00:04, 35.02it/s] Loading 0: 58%|█████▊ | 211/363 [00:11<00:03, 38.32it/s] Loading 0: 60%|█████▉ | 216/363 [00:11<00:03, 37.66it/s] Loading 0: 61%|██████ | 220/363 [00:11<00:03, 37.81it/s] Loading 0: 62%|██████▏ | 224/363 [00:11<00:03, 37.62it/s] Loading 0: 63%|██████▎ | 230/363 [00:11<00:03, 42.45it/s] Loading 0: 65%|██████▌ | 236/363 [00:11<00:03, 41.62it/s] Loading 0: 66%|██████▋ | 241/363 [00:12<00:02, 41.74it/s] Loading 0: 68%|██████▊ | 248/363 [00:12<00:02, 47.58it/s] Loading 0: 70%|██████▉ | 254/363 [00:12<00:02, 45.18it/s] Loading 0: 71%|███████▏ | 259/363 [00:12<00:02, 44.01it/s] Loading 0: 73%|███████▎ | 266/363 [00:12<00:02, 48.16it/s] Loading 0: 75%|███████▍ | 271/363 [00:12<00:01, 48.16it/s] Loading 0: 76%|███████▌ | 276/363 [00:12<00:02, 39.91it/s] Loading 0: 78%|███████▊ | 283/363 [00:13<00:02, 34.86it/s] Loading 0: 79%|███████▉ | 287/363 [00:13<00:02, 34.77it/s] Loading 0: 81%|████████ | 293/363 [00:13<00:01, 38.85it/s] Loading 0: 82%|████████▏ | 299/363 [00:13<00:01, 38.98it/s] Loading 0: 84%|████████▎ | 304/363 [00:13<00:01, 38.94it/s] Loading 0: 85%|████████▌ | 310/363 [00:13<00:01, 42.98it/s] Loading 0: 87%|████████▋ | 315/363 [00:13<00:01, 43.14it/s] Loading 0: 88%|████████▊ | 320/363 [00:13<00:00, 44.73it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:00, 42.85it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:00, 41.60it/s] Loading 0: 93%|█████████▎| 337/363 [00:14<00:00, 45.64it/s] Loading 0: 94%|█████████▍| 342/363 [00:14<00:00, 44.62it/s] Loading 0: 96%|█████████▌| 347/363 [00:14<00:00, 44.87it/s] Loading 0: 97%|█████████▋| 352/363 [00:14<00:00, 45.96it/s] Loading 0: 98%|█████████▊| 357/363 [00:14<00:00, 36.46it/s]
Job cloudyu-chaiml-nemo-dpo-v8-v2-mkmlizer completed after 93.81s with status: succeeded
Stopping job with name cloudyu-chaiml-nemo-dpo-v8-v2-mkmlizer
Pipeline stage MKMLizer completed in 94.30s
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-v8-v2
Waiting for inference service cloudyu-chaiml-nemo-dpo-v8-v2 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
Inference service cloudyu-chaiml-nemo-dpo-v8-v2 ready after 120.45595216751099s
Pipeline stage MKMLDeployer completed in 120.97s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.418166160583496s
Received healthy response to inference request in 1.860138177871704s
Received healthy response to inference request in 1.7218291759490967s
Received healthy response to inference request in 1.801572561264038s
Received healthy response to inference request in 1.8853750228881836s
5 requests
0 failed requests
5th percentile: 1.7377778530120849
10th percentile: 1.7537265300750733
20th percentile: 1.78562388420105
30th percentile: 1.8132856845855714
40th percentile: 1.8367119312286377
50th percentile: 1.860138177871704
60th percentile: 1.870232915878296
70th percentile: 1.8803276538848877
80th percentile: 1.9919332504272462
90th percentile: 2.2050497055053713
95th percentile: 2.3116079330444337
99th percentile: 2.3968545150756837
mean time: 1.9374162197113036
Pipeline stage StressChecker completed in 11.02s
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 2.50s
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 2.34s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v8_v2 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 2992.27s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v8_v2 status is now inactive due to auto deactivation removed underperforming models