cloudyu-chaiml-nemo-dpo-v6

developer_uid: cloudyu

submission_id: cloudyu-chaiml-nemo-dpo-v6_v2

model_name: cloudyu-chaiml-nemo-dpo-v6_v2

model_group: cloudyu/ChaiML-Nemo-DPO-

status: inactive

timestamp: 2024-11-24T10:48:45+00:00

num_battles: 16622

num_wins: 8310

celo_rating: 1261.24

family_friendly_score: 0.5569999999999999

family_friendly_standard_error: 0.007024969750824553

submission_type: basic

model_repo: cloudyu/ChaiML-Nemo-DPO-V6

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6240376773483821, 'latency_mean': 1.602345484495163, 'latency_p50': 1.5888696908950806, 'latency_p90': 1.7785791873931884}, {'batch_size': 3, 'throughput': 1.146721960212846, 'latency_mean': 2.6099152076244354, 'latency_p50': 2.613559126853943, 'latency_p90': 2.8605924606323243}, {'batch_size': 5, 'throughput': 1.39531380332333, 'latency_mean': 3.564376585483551, 'latency_p50': 3.5752928256988525, 'latency_p90': 3.955123853683472}, {'batch_size': 6, 'throughput': 1.4653152920515087, 'latency_mean': 4.06453380227089, 'latency_p50': 4.0893319845199585, 'latency_p90': 4.605045247077942}, {'batch_size': 8, 'throughput': 1.5419341879308757, 'latency_mean': 5.157524785995483, 'latency_p50': 5.164792537689209, 'latency_p90': 5.836569881439209}, {'batch_size': 10, 'throughput': 1.5800673423433729, 'latency_mean': 6.292365947961807, 'latency_p50': 6.271769165992737, 'latency_p90': 7.119686150550842}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: cloudyu-chaiml-nemo-dpo-v6_v2

is_internal_developer: False

language_model: cloudyu/ChaiML-Nemo-DPO-V6

model_size: 13B

ranking_group: single

throughput_3p7s: 1.42

us_pacific_date: 2024-11-24

win_ratio: 0.499939838767898

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-v6-v2-mkmlizer
Waiting for job on cloudyu-chaiml-nemo-dpo-v6-v2-mkmlizer to finish
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
cloudyu-chaiml-nemo-dpo-v6-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-chaiml-nemo-dpo-v6-v2-mkmlizer: ║     _____            __           __                                ║
cloudyu-chaiml-nemo-dpo-v6-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-chaiml-nemo-dpo-v6-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-chaiml-nemo-dpo-v6-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-chaiml-nemo-dpo-v6-v2-mkmlizer: ║       /___/                                                         ║
cloudyu-chaiml-nemo-dpo-v6-v2-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v6-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-chaiml-nemo-dpo-v6-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-chaiml-nemo-dpo-v6-v2-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-chaiml-nemo-dpo-v6-v2-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v6-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-chaiml-nemo-dpo-v6-v2-mkmlizer: ║  belonging to:                                                      ║
cloudyu-chaiml-nemo-dpo-v6-v2-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v6-v2-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-chaiml-nemo-dpo-v6-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-chaiml-nemo-dpo-v6-v2-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-chaiml-nemo-dpo-v6-v2-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v6-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-chaiml-nemo-dpo-v6-v2-mkmlizer: Downloaded to shared memory in 31.287s
cloudyu-chaiml-nemo-dpo-v6-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp4r04nxe2, device:0
cloudyu-chaiml-nemo-dpo-v6-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-chaiml-nemo-dpo-v6-v2-mkmlizer: quantized model in 36.306s
cloudyu-chaiml-nemo-dpo-v6-v2-mkmlizer: Processed model cloudyu/ChaiML-Nemo-DPO-V6 in 67.593s
cloudyu-chaiml-nemo-dpo-v6-v2-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-chaiml-nemo-dpo-v6-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-chaiml-nemo-dpo-v6-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v2
cloudyu-chaiml-nemo-dpo-v6-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v2/config.json
cloudyu-chaiml-nemo-dpo-v6-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v2/special_tokens_map.json
cloudyu-chaiml-nemo-dpo-v6-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v2/tokenizer_config.json
cloudyu-chaiml-nemo-dpo-v6-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v2/tokenizer.json
Retrying (%r) after connection broken by '%r': %s
cloudyu-chaiml-nemo-dpo-v6-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 27.91it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 46.21it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:07, 46.41it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:09, 36.46it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:07, 46.63it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 43.90it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:07, 41.88it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:06, 46.10it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:07, 44.18it/s]
Loading 0:  16%|█▌        | 58/363 [00:01<00:06, 45.56it/s]
Loading 0:  17%|█▋        | 63/363 [00:01<00:09, 31.18it/s]
Loading 0:  18%|█▊        | 67/363 [00:01<00:08, 32.92it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:08, 36.10it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:07, 39.36it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:08, 33.56it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:06, 41.51it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:06, 40.52it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:06, 41.24it/s]
Loading 0:  29%|██▊       | 104/363 [00:02<00:06, 42.20it/s]
Loading 0:  30%|███       | 110/363 [00:02<00:06, 41.25it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:05, 41.95it/s]
Loading 0:  33%|███▎      | 120/363 [00:02<00:06, 40.26it/s]
Loading 0:  35%|███▍      | 126/363 [00:03<00:05, 42.94it/s]
Loading 0:  36%|███▌      | 131/363 [00:03<00:05, 44.60it/s]
Loading 0:  37%|███▋      | 136/363 [00:03<00:05, 38.18it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 32.62it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 33.61it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 32.80it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:05, 39.71it/s]
Loading 0:  45%|████▍     | 163/363 [00:04<00:05, 39.34it/s]
Loading 0:  46%|████▋     | 168/363 [00:04<00:04, 40.05it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 45.96it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:04, 44.57it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:04, 43.39it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 48.22it/s]
Loading 0:  55%|█████▍    | 198/363 [00:04<00:03, 48.47it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:03, 40.10it/s]
Loading 0:  58%|█████▊    | 211/363 [00:05<00:03, 47.15it/s]
Loading 0:  60%|█████▉    | 216/363 [00:05<00:03, 47.41it/s]
Loading 0:  61%|██████    | 222/363 [00:05<00:03, 44.47it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 32.46it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:04, 31.85it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 38.37it/s]
Loading 0:  67%|██████▋   | 244/363 [00:06<00:03, 38.41it/s]
Loading 0:  69%|██████▊   | 249/363 [00:06<00:02, 38.80it/s]
Loading 0:  71%|███████   | 256/363 [00:06<00:02, 44.04it/s]
Loading 0:  72%|███████▏  | 262/363 [00:06<00:02, 42.72it/s]
Loading 0:  74%|███████▎  | 267/363 [00:06<00:02, 42.54it/s]
Loading 0:  75%|███████▌  | 273/363 [00:06<00:01, 46.52it/s]
Loading 0:  77%|███████▋  | 278/363 [00:06<00:01, 45.47it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 45.78it/s]
Loading 0:  80%|███████▉  | 289/363 [00:07<00:01, 43.26it/s]
Loading 0:  81%|████████  | 294/363 [00:07<00:01, 42.53it/s]
Loading 0:  82%|████████▏ | 299/363 [00:07<00:01, 44.35it/s]
Loading 0:  84%|████████▎ | 304/363 [00:14<00:24,  2.46it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:17,  3.19it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:12,  4.18it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:06,  7.00it/s]
Loading 0:  90%|████████▉ | 325/363 [00:14<00:04,  9.11it/s]
Loading 0:  91%|█████████ | 330/363 [00:14<00:03, 10.96it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 16.27it/s]
Loading 0:  95%|█████████▍| 344/363 [00:15<00:00, 19.85it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 22.80it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 28.87it/s]
Loading 0:  99%|█████████▉| 361/363 [00:15<00:00, 32.30it/s]
                                                            
Job cloudyu-chaiml-nemo-dpo-v6-v2-mkmlizer completed after 93.82s with status: succeeded
Stopping job with name cloudyu-chaiml-nemo-dpo-v6-v2-mkmlizer
Pipeline stage MKMLizer completed in 94.33s
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-v6-v2
Waiting for inference service cloudyu-chaiml-nemo-dpo-v6-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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service cloudyu-chaiml-nemo-dpo-v6-v2 ready after 120.46771931648254s
Pipeline stage MKMLDeployer completed in 120.90s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.2758948802948s
Received healthy response to inference request in 1.732591152191162s
Received healthy response to inference request in 1.9978010654449463s
Received healthy response to inference request in 1.6743872165679932s
5 requests
1 failed requests
5th percentile: 1.686028003692627
10th percentile: 1.6976687908172607
20th percentile: 1.7209503650665283
30th percentile: 1.785633134841919
40th percentile: 1.8917171001434325
50th percentile: 1.9978010654449463
60th percentile: 2.1090385913848877
70th percentile: 2.220276117324829
80th percentile: 5.852041435241702
90th percentile: 13.0043345451355
95th percentile: 16.580481100082395
99th percentile: 19.441398344039918
mean time: 5.567460393905639
%s, retrying in %s seconds...
Received healthy response to inference request in 1.909320592880249s
Received healthy response to inference request in 2.021153211593628s
Received healthy response to inference request in 1.926603078842163s
Received healthy response to inference request in 1.6508731842041016s
Received healthy response to inference request in 2.052016258239746s
5 requests
0 failed requests
5th percentile: 1.7025626659393311
10th percentile: 1.7542521476745605
20th percentile: 1.8576311111450194
30th percentile: 1.9127770900726317
40th percentile: 1.9196900844573974
50th percentile: 1.926603078842163
60th percentile: 1.964423131942749
70th percentile: 2.002243185043335
80th percentile: 2.0273258209228517
90th percentile: 2.039671039581299
95th percentile: 2.0458436489105223
99th percentile: 2.050781736373901
mean time: 1.9119932651519775
Pipeline stage StressChecker completed in 40.27s
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 2.01s
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 1.95s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v6_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 2867.31s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v6_v2 status is now inactive due to auto deactivation removed underperforming models