developer_uid: cloudyu
submission_id: cloudyu-chaiml-nemo-dpo-v9_v6
model_name: cloudyu-chaiml-nemo-dpo-v9_v5
model_group: cloudyu/ChaiML-Nemo-DPO-
status: inactive
timestamp: 2024-12-03T04:25:55+00:00
num_battles: 17739
num_wins: 8944
celo_rating: 1267.36
family_friendly_score: 0.5558000000000001
family_friendly_standard_error: 0.0070268963276826565
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': 0.6164411996512489, 'latency_mean': 1.6221538507938384, 'latency_p50': 1.6209373474121094, 'latency_p90': 1.8044147729873656}, {'batch_size': 3, 'throughput': 1.1311475940809195, 'latency_mean': 2.6496074545383452, 'latency_p50': 2.649500012397766, 'latency_p90': 2.910090184211731}, {'batch_size': 5, 'throughput': 1.3644307459613065, 'latency_mean': 3.646808183193207, 'latency_p50': 3.6594232320785522, 'latency_p90': 4.044194579124451}, {'batch_size': 6, 'throughput': 1.4365428267213576, 'latency_mean': 4.148849003314972, 'latency_p50': 4.142954587936401, 'latency_p90': 4.717420768737793}, {'batch_size': 8, 'throughput': 1.5064595718390827, 'latency_mean': 5.280929515361786, 'latency_p50': 5.244809508323669, 'latency_p90': 6.071161365509033}, {'batch_size': 10, 'throughput': 1.531253203855313, 'latency_mean': 6.488854709863663, 'latency_p50': 6.490522742271423, 'latency_p90': 7.365863895416259}]
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: 1.38
us_pacific_date: 2024-12-02
win_ratio: 0.5041997857827386
generation_params: {'temperature': 0.98, 'top_p': 0.98, 'min_p': 0.02, '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-v6-mkmlizer
Waiting for job on cloudyu-chaiml-nemo-dpo-v9-v6-mkmlizer to finish
cloudyu-chaiml-nemo-dpo-v9-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-chaiml-nemo-dpo-v9-v6-mkmlizer: ║ _____ __ __ ║
cloudyu-chaiml-nemo-dpo-v9-v6-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cloudyu-chaiml-nemo-dpo-v9-v6-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cloudyu-chaiml-nemo-dpo-v9-v6-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cloudyu-chaiml-nemo-dpo-v9-v6-mkmlizer: ║ /___/ ║
cloudyu-chaiml-nemo-dpo-v9-v6-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v9-v6-mkmlizer: ║ Version: 0.11.12 ║
cloudyu-chaiml-nemo-dpo-v9-v6-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cloudyu-chaiml-nemo-dpo-v9-v6-mkmlizer: ║ https://mk1.ai ║
cloudyu-chaiml-nemo-dpo-v9-v6-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v9-v6-mkmlizer: ║ The license key for the current software has been verified as ║
cloudyu-chaiml-nemo-dpo-v9-v6-mkmlizer: ║ belonging to: ║
cloudyu-chaiml-nemo-dpo-v9-v6-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v9-v6-mkmlizer: ║ Chai Research Corp. ║
cloudyu-chaiml-nemo-dpo-v9-v6-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cloudyu-chaiml-nemo-dpo-v9-v6-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cloudyu-chaiml-nemo-dpo-v9-v6-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v9-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-chaiml-nemo-dpo-v9-v6-mkmlizer: Downloaded to shared memory in 33.100s
cloudyu-chaiml-nemo-dpo-v9-v6-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjysb2_yi, device:0
cloudyu-chaiml-nemo-dpo-v9-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-chaiml-nemo-dpo-v9-v6-mkmlizer: quantized model in 36.236s
cloudyu-chaiml-nemo-dpo-v9-v6-mkmlizer: Processed model cloudyu/ChaiML-Nemo-DPO-V9 in 69.336s
cloudyu-chaiml-nemo-dpo-v9-v6-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-chaiml-nemo-dpo-v9-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-chaiml-nemo-dpo-v9-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v9-v6
cloudyu-chaiml-nemo-dpo-v9-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v9-v6/config.json
cloudyu-chaiml-nemo-dpo-v9-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v9-v6/special_tokens_map.json
cloudyu-chaiml-nemo-dpo-v9-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v9-v6/tokenizer_config.json
cloudyu-chaiml-nemo-dpo-v9-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v9-v6/tokenizer.json
cloudyu-chaiml-nemo-dpo-v9-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v9-v6/flywheel_model.0.safetensors
cloudyu-chaiml-nemo-dpo-v9-v6-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:12, 28.61it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:06, 50.01it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 47.81it/s] Loading 0: 7%|▋ | 25/363 [00:00<00:06, 49.06it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 52.03it/s] Loading 0: 10%|█ | 37/363 [00:00<00:06, 49.65it/s] Loading 0: 12%|█▏ | 43/363 [00:00<00:06, 49.96it/s] Loading 0: 13%|█▎ | 49/363 [00:00<00:06, 51.28it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 46.92it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 35.54it/s] Loading 0: 18%|█▊ | 66/363 [00:01<00:08, 35.55it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 40.05it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:06, 41.45it/s] Loading 0: 23%|██▎ | 83/363 [00:01<00:06, 41.66it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:05, 46.19it/s] Loading 0: 26%|██▌ | 95/363 [00:02<00:05, 46.68it/s] Loading 0: 28%|██▊ | 100/363 [00:02<00:06, 38.51it/s] Loading 0: 30%|██▉ | 108/363 [00:02<00:05, 48.04it/s] Loading 0: 31%|███▏ | 114/363 [00:02<00:05, 44.24it/s] Loading 0: 33%|███▎ | 119/363 [00:02<00:05, 43.44it/s] Loading 0: 35%|███▍ | 126/363 [00:02<00:04, 48.43it/s] Loading 0: 36%|███▋ | 132/363 [00:02<00:05, 45.37it/s] Loading 0: 38%|███▊ | 137/363 [00:03<00:05, 44.62it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 34.38it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 35.14it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 34.44it/s] Loading 0: 43%|████▎ | 157/363 [00:03<00:05, 40.72it/s] Loading 0: 45%|████▍ | 162/363 [00:03<00:04, 42.41it/s] Loading 0: 46%|████▌ | 167/363 [00:03<00:05, 38.60it/s] Loading 0: 48%|████▊ | 175/363 [00:04<00:04, 46.93it/s] Loading 0: 50%|████▉ | 181/363 [00:04<00:03, 45.98it/s] Loading 0: 51%|█████ | 186/363 [00:04<00:04, 44.17it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 49.32it/s] Loading 0: 55%|█████▍ | 199/363 [00:04<00:03, 44.74it/s] Loading 0: 56%|█████▌ | 204/363 [00:04<00:03, 43.12it/s] Loading 0: 58%|█████▊ | 210/363 [00:04<00:03, 46.10it/s] Loading 0: 59%|█████▉ | 215/363 [00:04<00:03, 44.66it/s] Loading 0: 61%|██████ | 220/363 [00:05<00:03, 44.57it/s] Loading 0: 62%|██████▏ | 225/363 [00:05<00:04, 28.78it/s] Loading 0: 63%|██████▎ | 230/363 [00:05<00:04, 29.42it/s] Loading 0: 66%|██████▌ | 238/363 [00:05<00:03, 37.57it/s] Loading 0: 67%|██████▋ | 243/363 [00:05<00:02, 40.02it/s] Loading 0: 68%|██████▊ | 248/363 [00:05<00:03, 36.95it/s] Loading 0: 71%|███████ | 256/363 [00:06<00:02, 44.87it/s] Loading 0: 72%|███████▏ | 262/363 [00:06<00:02, 44.36it/s] Loading 0: 74%|███████▎ | 267/363 [00:06<00:02, 43.88it/s] Loading 0: 75%|███████▌ | 274/363 [00:06<00:01, 48.65it/s] Loading 0: 77%|███████▋ | 280/363 [00:06<00:01, 45.85it/s] Loading 0: 79%|███████▊ | 285/363 [00:06<00:01, 43.71it/s] Loading 0: 80%|████████ | 291/363 [00:06<00:01, 46.70it/s] Loading 0: 82%|████████▏ | 296/363 [00:06<00:01, 44.76it/s] Loading 0: 83%|████████▎ | 302/363 [00:07<00:01, 48.10it/s] Loading 0: 85%|████████▍ | 307/363 [00:14<00:22, 2.52it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:14, 3.41it/s] Loading 0: 88%|████████▊ | 319/363 [00:14<00:08, 5.18it/s] Loading 0: 89%|████████▉ | 324/363 [00:14<00:05, 6.77it/s] Loading 0: 91%|█████████ | 330/363 [00:14<00:03, 9.07it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 13.43it/s] Loading 0: 94%|█████████▍| 343/363 [00:14<00:01, 16.38it/s] Loading 0: 96%|█████████▌| 348/363 [00:14<00:00, 18.19it/s] Loading 0: 98%|█████████▊| 355/363 [00:15<00:00, 24.00it/s] Loading 0: 99%|█████████▉| 360/363 [00:15<00:00, 26.89it/s]
Job cloudyu-chaiml-nemo-dpo-v9-v6-mkmlizer completed after 94.14s with status: succeeded
Stopping job with name cloudyu-chaiml-nemo-dpo-v9-v6-mkmlizer
Pipeline stage MKMLizer completed in 94.66s
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-chaiml-nemo-dpo-v9-v6
Waiting for inference service cloudyu-chaiml-nemo-dpo-v9-v6 to be ready
Failed to get response for submission rirv938-llama-8b-multihe_5456_v8: 7 validation errors for ParsingModel[Union[RewardSubmission, GuardSubmission, FunctionSubmission, BlendedSubmission, ProductionBlendSubmission, RoutedBlendSubmission, LLMSubmission]] __root__ -> platform unexpected value; permitted: 'reward' (type=value_error.const; given=multihead_reward; permitted=('reward',)) __root__ -> platform unexpected value; permitted: 'guard' (type=value_error.const; given=multihead_reward; permitted=('guard',)) __root__ -> platform unexpected value; permitted: 'function' (type=value_error.const; given=multihead_reward; permitted=('function',)) __root__ -> platform unexpected value; permitted: 'blended' (type=value_error.const; given=multihead_reward; permitted=('blended',)) __root__ -> platform unexpected value; permitted: 'production_blend' (type=value_error.const; given=multihead_reward; permitted=('production_blend',)) __root__ -> platform unexpected value; permitted: 'routed_blend' (type=value_error.const; given=multihead_reward; permitted=('routed_blend',)) __root__ -> platform unexpected value; permitted: 'coreweave/mkml', 'coreweave' (type=value_error.const; given=multihead_reward; permitted=('coreweave/mkml', 'coreweave'))
Inference service cloudyu-chaiml-nemo-dpo-v9-v6 ready after 150.522141456604s
Pipeline stage MKMLDeployer completed in 151.08s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5761001110076904s
Received healthy response to inference request in 1.6839213371276855s
Received healthy response to inference request in 1.7421050071716309s
Received healthy response to inference request in 2.0737881660461426s
Received healthy response to inference request in 1.2875804901123047s
5 requests
0 failed requests
5th percentile: 1.3668486595153808
10th percentile: 1.446116828918457
20th percentile: 1.6046531677246094
30th percentile: 1.6955580711364746
40th percentile: 1.7188315391540527
50th percentile: 1.7421050071716309
60th percentile: 1.8747782707214355
70th percentile: 2.0074515342712402
80th percentile: 2.1742505550384523
90th percentile: 2.3751753330230714
95th percentile: 2.4756377220153807
99th percentile: 2.5560076332092283
mean time: 1.8726990222930908
Pipeline stage StressChecker completed in 10.64s
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 2.49s
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-chaiml-nemo-dpo-v9_v6 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
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cloudyu-chaiml-nemo-dpo-v9-v6-profiler
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 3186.46s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v9_v6 status is now inactive due to auto deactivation removed underperforming models