developer_uid: azuruce
submission_id: chaiml-mistral-nemo-dpo-_3312_v1
model_name: chaiml-mistral-nemo-dpo-_3312_v1
model_group: ChaiML/mistral_nemo_dpo_
status: torndown
timestamp: 2024-12-22T06:07:58+00:00
num_battles: 23798
num_wins: 11558
celo_rating: 1260.87
family_friendly_score: 0.5831999999999999
family_friendly_standard_error: 0.006972485353157796
submission_type: basic
model_repo: ChaiML/mistral_nemo_dpo_round2_albert_20241220_v4
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6376879554588243, 'latency_mean': 1.5680799186229706, 'latency_p50': 1.5670114755630493, 'latency_p90': 1.7454610824584962}, {'batch_size': 3, 'throughput': 1.2640744766185361, 'latency_mean': 2.368764544725418, 'latency_p50': 2.361072063446045, 'latency_p90': 2.6415951013565064}, {'batch_size': 5, 'throughput': 1.6007902277412465, 'latency_mean': 3.1065977668762206, 'latency_p50': 3.109057068824768, 'latency_p90': 3.497534728050232}, {'batch_size': 6, 'throughput': 1.6940059230901203, 'latency_mean': 3.5247366535663605, 'latency_p50': 3.5328866243362427, 'latency_p90': 3.973041820526123}, {'batch_size': 8, 'throughput': 1.8429240221276864, 'latency_mean': 4.312391151189804, 'latency_p50': 4.355143427848816, 'latency_p90': 4.830340385437012}, {'batch_size': 10, 'throughput': 1.9488836867801806, 'latency_mean': 5.086735497713089, 'latency_p50': 5.1149662733078, 'latency_p90': 5.70660297870636}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-mistral-nemo-dpo-_3312_v1
is_internal_developer: True
language_model: ChaiML/mistral_nemo_dpo_round2_albert_20241220_v4
model_size: 13B
ranking_group: single
throughput_3p7s: 1.74
us_pacific_date: 2024-12-21
win_ratio: 0.48567106479536093
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '####', 'Bot:', 'User:', 'You:', '<|im_end|>', '<|eot_id|>'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': '', 'prompt_template': '', '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 chaiml-mistral-nemo-dpo-3312-v1-mkmlizer
Waiting for job on chaiml-mistral-nemo-dpo-3312-v1-mkmlizer to finish
chaiml-mistral-nemo-dpo-3312-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-dpo-3312-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral-nemo-dpo-3312-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral-nemo-dpo-3312-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral-nemo-dpo-3312-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral-nemo-dpo-3312-v1-mkmlizer: ║       /___/                                                         ║
chaiml-mistral-nemo-dpo-3312-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-3312-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-mistral-nemo-dpo-3312-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral-nemo-dpo-3312-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-nemo-dpo-3312-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-3312-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-nemo-dpo-3312-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-nemo-dpo-3312-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-3312-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-nemo-dpo-3312-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-nemo-dpo-3312-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-mistral-nemo-dpo-3312-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-3312-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-nemo-dpo-3312-v1-mkmlizer: Downloaded to shared memory in 49.709s
chaiml-mistral-nemo-dpo-3312-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpbyykeg6e, device:0
chaiml-mistral-nemo-dpo-3312-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-nemo-dpo-3312-v1-mkmlizer: quantized model in 35.752s
chaiml-mistral-nemo-dpo-3312-v1-mkmlizer: Processed model ChaiML/mistral_nemo_dpo_round2_albert_20241220_v4 in 85.461s
chaiml-mistral-nemo-dpo-3312-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-dpo-3312-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-3312-v1/config.json
chaiml-mistral-nemo-dpo-3312-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-3312-v1/special_tokens_map.json
chaiml-mistral-nemo-dpo-3312-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-3312-v1/tokenizer_config.json
chaiml-mistral-nemo-dpo-3312-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-3312-v1/tokenizer.json
chaiml-mistral-nemo-dpo-3312-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-3312-v1/flywheel_model.0.safetensors
chaiml-mistral-nemo-dpo-3312-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 28.97it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 48.24it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:08, 42.40it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 41.14it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:07, 46.85it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 43.71it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 42.19it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:06, 46.52it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:07, 43.86it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:06, 47.75it/s]
Loading 0:  18%|█▊        | 64/363 [00:01<00:11, 27.14it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:08, 34.74it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:07, 36.38it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:07, 38.72it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:07, 38.55it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:06, 39.02it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 43.51it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:05, 43.61it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:05, 47.16it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:06, 40.81it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:06, 40.60it/s]
Loading 0:  35%|███▍      | 126/363 [00:03<00:05, 45.88it/s]
Loading 0:  36%|███▌      | 131/363 [00:03<00:04, 46.51it/s]
Loading 0:  37%|███▋      | 136/363 [00:03<00:05, 39.03it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 32.71it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 33.95it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 33.21it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 38.97it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:04, 40.42it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:04, 42.11it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 43.86it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:04, 37.43it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 44.62it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:03, 44.01it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 42.56it/s]
Loading 0:  55%|█████▍    | 198/363 [00:04<00:03, 43.88it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:04, 35.67it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 43.20it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 43.25it/s]
Loading 0:  61%|██████    | 221/363 [00:05<00:03, 46.90it/s]
Loading 0:  62%|██████▏   | 226/363 [00:05<00:04, 29.29it/s]
Loading 0:  63%|██████▎   | 230/363 [00:05<00:04, 29.64it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 38.26it/s]
Loading 0:  67%|██████▋   | 243/363 [00:06<00:02, 40.43it/s]
Loading 0:  68%|██████▊   | 248/363 [00:06<00:03, 35.13it/s]
Loading 0:  70%|███████   | 255/363 [00:06<00:02, 42.58it/s]
Loading 0:  72%|███████▏  | 260/363 [00:06<00:02, 41.84it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 42.24it/s]
Loading 0:  74%|███████▍  | 270/363 [00:06<00:02, 43.93it/s]
Loading 0:  76%|███████▌  | 275/363 [00:06<00:02, 36.41it/s]
Loading 0:  78%|███████▊  | 283/363 [00:07<00:01, 44.27it/s]
Loading 0:  80%|███████▉  | 289/363 [00:07<00:01, 42.70it/s]
Loading 0:  81%|████████  | 294/363 [00:07<00:01, 42.20it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 48.33it/s]
Loading 0:  85%|████████▍ | 307/363 [00:14<00:19,  2.86it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:13,  3.77it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:07,  5.84it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:04,  7.74it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:03,  9.75it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 13.55it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:01, 16.70it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 19.84it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 25.79it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 28.58it/s]
                                                            

Job chaiml-mistral-nemo-dpo-3312-v1-mkmlizer completed after 114.88s with status: succeeded
Stopping job with name chaiml-mistral-nemo-dpo-3312-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.52s
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 chaiml-mistral-nemo-dpo-3312-v1
Waiting for inference service chaiml-mistral-nemo-dpo-3312-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-mistral-nemo-dpo-3312-v1 ready after 261.2822868824005s
Pipeline stage MKMLDeployer completed in 261.84s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.3671281337738037s
Received healthy response to inference request in 1.3364372253417969s
Received healthy response to inference request in 1.16633939743042s
Received healthy response to inference request in 1.3752295970916748s
Received healthy response to inference request in 1.8221571445465088s
5 requests
0 failed requests
5th percentile: 1.2003589630126954
10th percentile: 1.2343785285949707
20th percentile: 1.3024176597595214
30th percentile: 1.3425754070281983
40th percentile: 1.354851770401001
50th percentile: 1.3671281337738037
60th percentile: 1.3703687191009521
70th percentile: 1.3736093044281006
80th percentile: 1.4646151065826416
90th percentile: 1.6433861255645752
95th percentile: 1.732771635055542
99th percentile: 1.8042800426483154
mean time: 1.4134582996368408
Pipeline stage StressChecker completed in 8.44s
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 0.73s
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 0.74s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_3312_v1 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 0.09s
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 chaiml-mistral-nemo-dpo-3312-v1-profiler
Waiting for inference service chaiml-mistral-nemo-dpo-3312-v1-profiler to be ready
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 2418.40s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_3312_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral-nemo-dpo-_3312_v1 status is now torndown due to DeploymentManager action
chaiml-mistral-nemo-dpo-_3312_v1 status is now torndown due to DeploymentManager action
chaiml-mistral-nemo-dpo-_3312_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1