developer_uid: cloudyu
submission_id: cloudyu-chaiml-nemo-dpo-v9_v5
model_name: cloudyu-chaiml-nemo-dpo-v9_v5
model_group: cloudyu/ChaiML-Nemo-DPO-
status: inactive
timestamp: 2024-12-03T03:36:51+00:00
num_battles: 13826
num_wins: 7079
celo_rating: 1271.82
family_friendly_score: 0.5626
family_friendly_standard_error: 0.0070154292812343285
submission_type: basic
model_repo: cloudyu/ChaiML-Nemo-DPO-V9
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6157818321712009, 'latency_mean': 1.6238838529586792, 'latency_p50': 1.612646460533142, 'latency_p90': 1.8019252061843871}, {'batch_size': 3, 'throughput': 1.1484073054548323, 'latency_mean': 2.603204001188278, 'latency_p50': 2.6027402877807617, 'latency_p90': 2.8597187757492066}, {'batch_size': 5, 'throughput': 1.3919917931935266, 'latency_mean': 3.576486797332764, 'latency_p50': 3.584008574485779, 'latency_p90': 4.007773685455322}, {'batch_size': 6, 'throughput': 1.4637805391384793, 'latency_mean': 4.080601254701614, 'latency_p50': 4.093540668487549, 'latency_p90': 4.615571141242981}, {'batch_size': 8, 'throughput': 1.5393452384775386, 'latency_mean': 5.172959585189819, 'latency_p50': 5.172858238220215, 'latency_p90': 5.7932531356811525}, {'batch_size': 10, 'throughput': 1.5703118692819031, 'latency_mean': 6.320393075942993, 'latency_p50': 6.272089600563049, 'latency_p90': 7.147075533866882}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: cloudyu-chaiml-nemo-dpo-v9_v5
is_internal_developer: False
language_model: cloudyu/ChaiML-Nemo-DPO-V9
model_size: 13B
ranking_group: single
throughput_3p7s: 1.42
us_pacific_date: 2024-12-02
win_ratio: 0.5120063648199046
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-chaiml-nemo-dpo-v9-v5-mkmlizer
Waiting for job on cloudyu-chaiml-nemo-dpo-v9-v5-mkmlizer to finish
cloudyu-chaiml-nemo-dpo-v9-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-chaiml-nemo-dpo-v9-v5-mkmlizer: ║ _____ __ __ ║
cloudyu-chaiml-nemo-dpo-v9-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cloudyu-chaiml-nemo-dpo-v9-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cloudyu-chaiml-nemo-dpo-v9-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cloudyu-chaiml-nemo-dpo-v9-v5-mkmlizer: ║ /___/ ║
cloudyu-chaiml-nemo-dpo-v9-v5-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v9-v5-mkmlizer: ║ Version: 0.11.12 ║
cloudyu-chaiml-nemo-dpo-v9-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cloudyu-chaiml-nemo-dpo-v9-v5-mkmlizer: ║ https://mk1.ai ║
cloudyu-chaiml-nemo-dpo-v9-v5-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v9-v5-mkmlizer: ║ The license key for the current software has been verified as ║
cloudyu-chaiml-nemo-dpo-v9-v5-mkmlizer: ║ belonging to: ║
cloudyu-chaiml-nemo-dpo-v9-v5-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v9-v5-mkmlizer: ║ Chai Research Corp. ║
cloudyu-chaiml-nemo-dpo-v9-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cloudyu-chaiml-nemo-dpo-v9-v5-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cloudyu-chaiml-nemo-dpo-v9-v5-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v9-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-chaiml-nemo-dpo-v9-v5-mkmlizer: Downloaded to shared memory in 54.666s
cloudyu-chaiml-nemo-dpo-v9-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpbpu5nsjg, device:0
cloudyu-chaiml-nemo-dpo-v9-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-chaiml-nemo-dpo-v9-v5-mkmlizer: quantized model in 35.743s
cloudyu-chaiml-nemo-dpo-v9-v5-mkmlizer: Processed model cloudyu/ChaiML-Nemo-DPO-V9 in 90.410s
cloudyu-chaiml-nemo-dpo-v9-v5-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-chaiml-nemo-dpo-v9-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-chaiml-nemo-dpo-v9-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v9-v5
cloudyu-chaiml-nemo-dpo-v9-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v9-v5/config.json
cloudyu-chaiml-nemo-dpo-v9-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v9-v5/special_tokens_map.json
cloudyu-chaiml-nemo-dpo-v9-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v9-v5/tokenizer_config.json
cloudyu-chaiml-nemo-dpo-v9-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v9-v5/tokenizer.json
cloudyu-chaiml-nemo-dpo-v9-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v9-v5/flywheel_model.0.safetensors
cloudyu-chaiml-nemo-dpo-v9-v5-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:12, 29.05it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:07, 49.35it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 46.89it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:07, 45.75it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 51.98it/s] Loading 0: 10%|█ | 37/363 [00:00<00:06, 48.23it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 44.80it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 49.56it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 45.37it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 34.96it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:08, 33.76it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 39.91it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:07, 40.29it/s] Loading 0: 23%|██▎ | 83/363 [00:01<00:06, 40.45it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:05, 46.05it/s] Loading 0: 26%|██▋ | 96/363 [00:02<00:06, 43.58it/s] Loading 0: 28%|██▊ | 101/363 [00:02<00:06, 40.63it/s] Loading 0: 29%|██▉ | 106/363 [00:02<00:06, 42.26it/s] Loading 0: 31%|███ | 113/363 [00:02<00:05, 42.96it/s] Loading 0: 33%|███▎ | 118/363 [00:02<00:05, 42.61it/s] Loading 0: 35%|███▍ | 126/363 [00:02<00:04, 49.76it/s] Loading 0: 36%|███▋ | 132/363 [00:03<00:04, 46.27it/s] Loading 0: 38%|███▊ | 137/363 [00:03<00:05, 43.92it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 34.32it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 34.59it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 33.82it/s] Loading 0: 43%|████▎ | 157/363 [00:03<00:05, 40.83it/s] Loading 0: 45%|████▍ | 162/363 [00:03<00:04, 42.25it/s] Loading 0: 46%|████▌ | 167/363 [00:04<00:05, 36.20it/s] Loading 0: 48%|████▊ | 174/363 [00:04<00:04, 42.18it/s] Loading 0: 49%|████▉ | 179/363 [00:04<00:04, 42.85it/s] Loading 0: 51%|█████ | 184/363 [00:04<00:04, 43.21it/s] Loading 0: 52%|█████▏ | 189/363 [00:04<00:03, 44.78it/s] Loading 0: 53%|█████▎ | 194/363 [00:04<00:04, 38.98it/s] Loading 0: 56%|█████▌ | 202/363 [00:04<00:03, 47.22it/s] Loading 0: 57%|█████▋ | 208/363 [00:04<00:03, 45.55it/s] Loading 0: 59%|█████▊ | 213/363 [00:05<00:03, 44.55it/s] Loading 0: 60%|██████ | 219/363 [00:05<00:02, 48.35it/s] Loading 0: 62%|██████▏ | 224/363 [00:05<00:04, 34.54it/s] Loading 0: 63%|██████▎ | 229/363 [00:05<00:03, 35.12it/s] Loading 0: 65%|██████▍ | 235/363 [00:05<00:03, 36.90it/s] Loading 0: 66%|██████▌ | 240/363 [00:05<00:03, 38.13it/s] Loading 0: 68%|██████▊ | 246/363 [00:05<00:02, 42.11it/s] Loading 0: 69%|██████▉ | 251/363 [00:06<00:02, 42.83it/s] Loading 0: 71%|███████ | 256/363 [00:06<00:02, 43.84it/s] Loading 0: 72%|███████▏ | 261/363 [00:06<00:02, 44.34it/s] Loading 0: 73%|███████▎ | 266/363 [00:06<00:02, 36.66it/s] Loading 0: 75%|███████▌ | 273/363 [00:06<00:02, 43.91it/s] Loading 0: 77%|███████▋ | 278/363 [00:06<00:01, 44.58it/s] Loading 0: 78%|███████▊ | 283/363 [00:06<00:01, 45.22it/s] Loading 0: 79%|███████▉ | 288/363 [00:06<00:01, 45.92it/s] Loading 0: 81%|████████ | 293/363 [00:07<00:01, 39.80it/s] Loading 0: 82%|████████▏ | 299/363 [00:07<00:01, 44.44it/s] Loading 0: 84%|████████▎ | 304/363 [00:13<00:23, 2.50it/s] Loading 0: 85%|████████▍ | 308/363 [00:14<00:17, 3.23it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:12, 4.23it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:06, 7.09it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:03, 9.60it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:02, 12.24it/s] Loading 0: 93%|█████████▎| 339/363 [00:14<00:01, 17.05it/s] Loading 0: 96%|█████████▌| 347/363 [00:14<00:00, 23.31it/s] Loading 0: 97%|█████████▋| 353/363 [00:14<00:00, 26.54it/s] Loading 0: 99%|█████████▉| 359/363 [00:15<00:00, 30.03it/s]
Job cloudyu-chaiml-nemo-dpo-v9-v5-mkmlizer completed after 115.04s with status: succeeded
Stopping job with name cloudyu-chaiml-nemo-dpo-v9-v5-mkmlizer
Pipeline stage MKMLizer completed in 115.59s
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-v9-v5
Waiting for inference service cloudyu-chaiml-nemo-dpo-v9-v5 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-v9-v5 ready after 140.52826976776123s
Pipeline stage MKMLDeployer completed in 141.09s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.725205421447754s
Received healthy response to inference request in 2.2604446411132812s
Received healthy response to inference request in 1.5831403732299805s
Received healthy response to inference request in 2.3923394680023193s
Received healthy response to inference request in 2.166518449783325s
5 requests
0 failed requests
5th percentile: 1.6115533828735351
10th percentile: 1.6399663925170898
20th percentile: 1.6967924118041993
30th percentile: 1.8134680271148682
40th percentile: 1.9899932384490968
50th percentile: 2.166518449783325
60th percentile: 2.2040889263153076
70th percentile: 2.24165940284729
80th percentile: 2.286823606491089
90th percentile: 2.339581537246704
95th percentile: 2.3659605026245116
99th percentile: 2.387063674926758
mean time: 2.025529670715332
Pipeline stage StressChecker completed in 12.10s
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 2.34s
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 2.14s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v9_v5 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 2998.24s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v9_v5 status is now inactive due to auto deactivation removed underperforming models