cloudyu-chaiml-nemo-dpo-v3

developer_uid: cloudyu

submission_id: cloudyu-chaiml-nemo-dpo-v3_v3

model_name: cloudyu-chaiml-nemo-dpo-v3_v3

model_group: cloudyu/ChaiML-Nemo-DPO-

status: inactive

timestamp: 2024-11-24T09:45:03+00:00

num_battles: 16133

num_wins: 7797

celo_rating: 1245.11

family_friendly_score: 0.5780000000000001

family_friendly_standard_error: 0.006984497118619207

submission_type: basic

model_repo: cloudyu/ChaiML-Nemo-DPO-V3

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6178122263996499, 'latency_mean': 1.618520928621292, 'latency_p50': 1.6200023889541626, 'latency_p90': 1.7795633316040038}, {'batch_size': 3, 'throughput': 1.160020590449558, 'latency_mean': 2.5811833572387695, 'latency_p50': 2.5801124572753906, 'latency_p90': 2.8405237674713133}, {'batch_size': 5, 'throughput': 1.3990218850703033, 'latency_mean': 3.55464955329895, 'latency_p50': 3.5408931970596313, 'latency_p90': 3.9625752449035643}, {'batch_size': 6, 'throughput': 1.476864792310378, 'latency_mean': 4.038721213340759, 'latency_p50': 4.024596929550171, 'latency_p90': 4.563282561302185}, {'batch_size': 8, 'throughput': 1.5545983093482452, 'latency_mean': 5.110719692707062, 'latency_p50': 5.110886931419373, 'latency_p90': 5.758121395111084}, {'batch_size': 10, 'throughput': 1.590020553317034, 'latency_mean': 6.249328736066818, 'latency_p50': 6.285682439804077, 'latency_p90': 6.928256154060364}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: cloudyu-chaiml-nemo-dpo-v3_v3

is_internal_developer: False

language_model: cloudyu/ChaiML-Nemo-DPO-V3

model_size: 13B

ranking_group: single

throughput_3p7s: 1.43

us_pacific_date: 2024-11-24

win_ratio: 0.48329510940308684

generation_params: {'temperature': 0.95, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 40, '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-v3-v3-mkmlizer
Waiting for job on cloudyu-chaiml-nemo-dpo-v3-v3-mkmlizer to finish
cloudyu-chaiml-nemo-dpo-v3-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-chaiml-nemo-dpo-v3-v3-mkmlizer: ║     _____            __           __                                ║
cloudyu-chaiml-nemo-dpo-v3-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-chaiml-nemo-dpo-v3-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-chaiml-nemo-dpo-v3-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-chaiml-nemo-dpo-v3-v3-mkmlizer: ║       /___/                                                         ║
cloudyu-chaiml-nemo-dpo-v3-v3-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v3-v3-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-chaiml-nemo-dpo-v3-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-chaiml-nemo-dpo-v3-v3-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-chaiml-nemo-dpo-v3-v3-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v3-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-chaiml-nemo-dpo-v3-v3-mkmlizer: ║  belonging to:                                                      ║
cloudyu-chaiml-nemo-dpo-v3-v3-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v3-v3-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-chaiml-nemo-dpo-v3-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-chaiml-nemo-dpo-v3-v3-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-chaiml-nemo-dpo-v3-v3-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v3-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-chaiml-nemo-dpo-v3-v3-mkmlizer: Downloaded to shared memory in 46.618s
cloudyu-chaiml-nemo-dpo-v3-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpe4s1mokv, device:0
cloudyu-chaiml-nemo-dpo-v3-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-chaiml-nemo-dpo-v3-v3-mkmlizer: quantized model in 36.625s
cloudyu-chaiml-nemo-dpo-v3-v3-mkmlizer: Processed model cloudyu/ChaiML-Nemo-DPO-V3 in 83.243s
cloudyu-chaiml-nemo-dpo-v3-v3-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-chaiml-nemo-dpo-v3-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-chaiml-nemo-dpo-v3-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v3-v3
cloudyu-chaiml-nemo-dpo-v3-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v3-v3/config.json
cloudyu-chaiml-nemo-dpo-v3-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v3-v3/special_tokens_map.json
cloudyu-chaiml-nemo-dpo-v3-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v3-v3/tokenizer_config.json
cloudyu-chaiml-nemo-dpo-v3-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v3-v3/flywheel_model.0.safetensors
cloudyu-chaiml-nemo-dpo-v3-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 28.34it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 48.95it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 46.02it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 44.71it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 51.12it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 48.09it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:06, 45.95it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 51.15it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 47.37it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 35.03it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 35.41it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 40.04it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:06, 40.80it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:07, 39.76it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:06, 44.12it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:06, 42.58it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:06, 43.41it/s]
Loading 0:  29%|██▉       | 105/363 [00:02<00:06, 42.34it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:05, 46.10it/s]
Loading 0:  32%|███▏      | 117/363 [00:02<00:05, 44.44it/s]
Loading 0:  34%|███▍      | 123/363 [00:02<00:05, 43.49it/s]
Loading 0:  35%|███▌      | 128/363 [00:02<00:05, 41.83it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:04, 47.27it/s]
Loading 0:  39%|███▉      | 141/363 [00:03<00:04, 46.60it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 31.44it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 31.80it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:05, 38.43it/s]
Loading 0:  45%|████▍     | 163/363 [00:03<00:05, 39.90it/s]
Loading 0:  46%|████▋     | 168/363 [00:04<00:04, 39.31it/s]
Loading 0:  48%|████▊     | 174/363 [00:04<00:04, 43.94it/s]
Loading 0:  49%|████▉     | 179/363 [00:04<00:04, 43.12it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:04, 43.07it/s]
Loading 0:  52%|█████▏    | 190/363 [00:04<00:04, 42.66it/s]
Loading 0:  54%|█████▎    | 195/363 [00:04<00:04, 41.85it/s]
Loading 0:  56%|█████▌    | 202/363 [00:04<00:03, 46.57it/s]
Loading 0:  57%|█████▋    | 208/363 [00:04<00:03, 45.70it/s]
Loading 0:  59%|█████▊    | 213/363 [00:05<00:03, 45.11it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:02, 50.80it/s]
Loading 0:  62%|██████▏   | 226/363 [00:05<00:04, 31.98it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:04, 32.74it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 39.22it/s]
Loading 0:  67%|██████▋   | 244/363 [00:05<00:02, 40.33it/s]
Loading 0:  69%|██████▊   | 249/363 [00:05<00:02, 40.94it/s]
Loading 0:  71%|███████   | 256/363 [00:06<00:02, 46.30it/s]
Loading 0:  72%|███████▏  | 261/363 [00:06<00:02, 46.05it/s]
Loading 0:  73%|███████▎  | 266/363 [00:06<00:02, 39.09it/s]
Loading 0:  75%|███████▌  | 273/363 [00:06<00:01, 45.89it/s]
Loading 0:  77%|███████▋  | 278/363 [00:06<00:01, 45.50it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 46.30it/s]
Loading 0:  80%|███████▉  | 289/363 [00:06<00:01, 44.27it/s]
Loading 0:  81%|████████  | 294/363 [00:06<00:01, 42.88it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 49.17it/s]
Loading 0:  85%|████████▍ | 307/363 [00:14<00:20,  2.68it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:14,  3.56it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:07,  5.55it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:05,  7.36it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:03,  9.30it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 13.06it/s]
Loading 0:  94%|█████████▍| 343/363 [00:14<00:01, 16.07it/s]
Loading 0:  96%|█████████▌| 348/363 [00:15<00:00, 18.07it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 25.03it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 27.61it/s]
                                                            
Job cloudyu-chaiml-nemo-dpo-v3-v3-mkmlizer completed after 104.13s with status: succeeded
Stopping job with name cloudyu-chaiml-nemo-dpo-v3-v3-mkmlizer
Pipeline stage MKMLizer completed in 104.62s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cloudyu-chaiml-nemo-dpo-v3-v3
Waiting for inference service cloudyu-chaiml-nemo-dpo-v3-v3 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
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-v3-v3 ready after 110.41128969192505s
Pipeline stage MKMLDeployer completed in 110.99s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1390395164489746s
Received healthy response to inference request in 1.8126115798950195s
Received healthy response to inference request in 1.7137718200683594s
Received healthy response to inference request in 2.121591091156006s
Received healthy response to inference request in 1.7414767742156982s
5 requests
0 failed requests
5th percentile: 1.719312810897827
10th percentile: 1.724853801727295
20th percentile: 1.7359357833862306
30th percentile: 1.7557037353515625
40th percentile: 1.784157657623291
50th percentile: 1.8126115798950195
60th percentile: 1.936203384399414
70th percentile: 2.0597951889038084
80th percentile: 2.1250807762146
90th percentile: 2.132060146331787
95th percentile: 2.1355498313903807
99th percentile: 2.138341579437256
mean time: 1.9056981563568116
Pipeline stage StressChecker completed in 10.86s
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 2.37s
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 2.29s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v3_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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cloudyu-chaiml-nemo-dpo-v3-v3-profiler
Waiting for inference service cloudyu-chaiml-nemo-dpo-v3-v3-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 2712.10s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v3_v3 status is now inactive due to auto deactivation removed underperforming models