cloudyu-chaiml-nemo-dpo-v6

developer_uid: cloudyu

submission_id: cloudyu-chaiml-nemo-dpo-v6_v13

model_name: cloudyu-chaiml-nemo-dpo-v6_v11

model_group: cloudyu/ChaiML-Nemo-DPO-

status: inactive

timestamp: 2024-12-03T03:52:41+00:00

num_battles: 13734

num_wins: 6874

celo_rating: 1264.57

family_friendly_score: 0.5656

family_friendly_standard_error: 0.007009944935589723

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': 0.612010033581434, 'latency_mean': 1.633898664712906, 'latency_p50': 1.6445022821426392, 'latency_p90': 1.806356143951416}, {'batch_size': 3, 'throughput': 1.1335012259201467, 'latency_mean': 2.63762672662735, 'latency_p50': 2.6099308729171753, 'latency_p90': 2.8755412101745605}, {'batch_size': 5, 'throughput': 1.3740620175713743, 'latency_mean': 3.6248438477516176, 'latency_p50': 3.6414971351623535, 'latency_p90': 4.021663069725037}, {'batch_size': 6, 'throughput': 1.4367291961893003, 'latency_mean': 4.15177610039711, 'latency_p50': 4.13879656791687, 'latency_p90': 4.66409969329834}, {'batch_size': 8, 'throughput': 1.5029557609068378, 'latency_mean': 5.291572699546814, 'latency_p50': 5.338207364082336, 'latency_p90': 5.921755051612854}, {'batch_size': 10, 'throughput': 1.5344349391106062, 'latency_mean': 6.468019903898239, 'latency_p50': 6.433431506156921, 'latency_p90': 7.284650230407715}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: cloudyu-chaiml-nemo-dpo-v6_v11

is_internal_developer: False

language_model: cloudyu/ChaiML-Nemo-DPO-V6

model_size: 13B

ranking_group: single

throughput_3p7s: 1.39

us_pacific_date: 2024-12-02

win_ratio: 0.5005096839959225

generation_params: {'temperature': 0.96, 'top_p': 0.96, 'min_p': 0.04, '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-v6-v13-mkmlizer
Waiting for job on cloudyu-chaiml-nemo-dpo-v6-v13-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
cloudyu-chaiml-nemo-dpo-v6-v13-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-chaiml-nemo-dpo-v6-v13-mkmlizer: ║     _____            __           __                                ║
cloudyu-chaiml-nemo-dpo-v6-v13-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-chaiml-nemo-dpo-v6-v13-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-chaiml-nemo-dpo-v6-v13-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-chaiml-nemo-dpo-v6-v13-mkmlizer: ║       /___/                                                         ║
cloudyu-chaiml-nemo-dpo-v6-v13-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v6-v13-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-chaiml-nemo-dpo-v6-v13-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-chaiml-nemo-dpo-v6-v13-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-chaiml-nemo-dpo-v6-v13-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v6-v13-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-chaiml-nemo-dpo-v6-v13-mkmlizer: ║  belonging to:                                                      ║
cloudyu-chaiml-nemo-dpo-v6-v13-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v6-v13-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-chaiml-nemo-dpo-v6-v13-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-chaiml-nemo-dpo-v6-v13-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-chaiml-nemo-dpo-v6-v13-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v6-v13-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-chaiml-nemo-dpo-v6-v13-mkmlizer: Downloaded to shared memory in 31.443s
cloudyu-chaiml-nemo-dpo-v6-v13-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpwh6abax1, device:0
cloudyu-chaiml-nemo-dpo-v6-v13-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-chaiml-nemo-dpo-v6-v13-mkmlizer: quantized model in 35.770s
cloudyu-chaiml-nemo-dpo-v6-v13-mkmlizer: Processed model cloudyu/ChaiML-Nemo-DPO-V6 in 67.213s
cloudyu-chaiml-nemo-dpo-v6-v13-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-chaiml-nemo-dpo-v6-v13-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-chaiml-nemo-dpo-v6-v13-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v13
cloudyu-chaiml-nemo-dpo-v6-v13-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v13/config.json
cloudyu-chaiml-nemo-dpo-v6-v13-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v13/special_tokens_map.json
cloudyu-chaiml-nemo-dpo-v6-v13-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v13/tokenizer_config.json
cloudyu-chaiml-nemo-dpo-v6-v13-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v13/tokenizer.json
cloudyu-chaiml-nemo-dpo-v6-v13-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v13/flywheel_model.0.safetensors
cloudyu-chaiml-nemo-dpo-v6-v13-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 28.04it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 49.14it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 46.61it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 43.92it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 49.96it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 44.98it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 42.54it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 47.48it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 45.76it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 33.86it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 32.98it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 39.49it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:06, 40.90it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:06, 41.17it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:05, 46.37it/s]
Loading 0:  26%|██▌       | 95/363 [00:02<00:05, 46.94it/s]
Loading 0:  28%|██▊       | 100/363 [00:02<00:06, 38.72it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:05, 43.39it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:05, 46.32it/s]
Loading 0:  32%|███▏      | 117/363 [00:02<00:05, 44.01it/s]
Loading 0:  34%|███▎      | 122/363 [00:02<00:05, 45.32it/s]
Loading 0:  35%|███▍      | 127/363 [00:03<00:05, 39.54it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:04, 47.55it/s]
Loading 0:  39%|███▉      | 141/363 [00:03<00:04, 45.57it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 31.51it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 30.52it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:05, 36.81it/s]
Loading 0:  45%|████▍     | 162/363 [00:03<00:05, 39.14it/s]
Loading 0:  46%|████▌     | 167/363 [00:04<00:05, 35.66it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 44.38it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:04, 43.74it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:04, 43.04it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 47.95it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 46.69it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:03, 45.67it/s]
Loading 0:  58%|█████▊    | 210/363 [00:04<00:03, 47.89it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 45.83it/s]
Loading 0:  61%|██████    | 221/363 [00:05<00:02, 48.85it/s]
Loading 0:  62%|██████▏   | 226/363 [00:05<00:04, 29.69it/s]
Loading 0:  63%|██████▎   | 230/363 [00:05<00:04, 30.05it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 38.98it/s]
Loading 0:  67%|██████▋   | 243/363 [00:05<00:02, 40.36it/s]
Loading 0:  68%|██████▊   | 248/363 [00:06<00:03, 33.45it/s]
Loading 0:  70%|███████   | 255/363 [00:06<00:02, 39.06it/s]
Loading 0:  72%|███████▏  | 260/363 [00:06<00:02, 39.38it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 41.81it/s]
Loading 0:  75%|███████▍  | 271/363 [00:06<00:02, 42.10it/s]
Loading 0:  76%|███████▌  | 276/363 [00:06<00:02, 41.68it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 46.50it/s]
Loading 0:  80%|███████▉  | 289/363 [00:06<00:01, 45.23it/s]
Loading 0:  81%|████████  | 294/363 [00:07<00:01, 44.13it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 49.95it/s]
Loading 0:  85%|████████▍ | 307/363 [00:14<00:19,  2.82it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:13,  3.73it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:07,  5.79it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:04,  7.68it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:03,  9.65it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 13.51it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:01, 16.99it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 20.24it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 26.36it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 28.84it/s]
                                                            
Job cloudyu-chaiml-nemo-dpo-v6-v13-mkmlizer completed after 93.71s with status: succeeded
Stopping job with name cloudyu-chaiml-nemo-dpo-v6-v13-mkmlizer
Pipeline stage MKMLizer completed in 94.38s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cloudyu-chaiml-nemo-dpo-v6-v13
Waiting for inference service cloudyu-chaiml-nemo-dpo-v6-v13 to be ready
Inference service cloudyu-chaiml-nemo-dpo-v6-v13 ready after 140.96043920516968s
Pipeline stage MKMLDeployer completed in 141.51s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0440070629119873s
Received healthy response to inference request in 1.9940767288208008s
Received healthy response to inference request in 1.6023046970367432s
Received healthy response to inference request in 1.6103191375732422s
Received healthy response to inference request in 1.7626664638519287s
5 requests
0 failed requests
5th percentile: 1.603907585144043
10th percentile: 1.6055104732513428
20th percentile: 1.6087162494659424
30th percentile: 1.6407886028289795
40th percentile: 1.701727533340454
50th percentile: 1.7626664638519287
60th percentile: 1.8552305698394775
70th percentile: 1.9477946758270264
80th percentile: 2.004062795639038
90th percentile: 2.024034929275513
95th percentile: 2.03402099609375
99th percentile: 2.04200984954834
mean time: 1.8026748180389405
Pipeline stage StressChecker completed in 10.26s
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 2.13s
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 2.00s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v6_v13 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 3081.30s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v6_v13 status is now inactive due to auto deactivation removed underperforming models