chaiml-mistral-nemo-dpo-_2986

developer_uid: azuruce

submission_id: chaiml-mistral-nemo-dpo-_2986_v1

model_name: chaiml-mistral-nemo-dpo-_2986_v1

model_group: ChaiML/mistral_nemo_dpo_

status: inactive

timestamp: 2024-12-18T07:05:34+00:00

num_battles: 15401

num_wins: 7651

celo_rating: 1260.66

family_friendly_score: 0.5736

family_friendly_standard_error: 0.006994040892073766

submission_type: basic

model_repo: ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-2496

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6358027457870978, 'latency_mean': 1.572734099626541, 'latency_p50': 1.5733240842819214, 'latency_p90': 1.7162335395812989}, {'batch_size': 3, 'throughput': 1.2649604376332493, 'latency_mean': 2.357684026956558, 'latency_p50': 2.3621994256973267, 'latency_p90': 2.5848411321640015}, {'batch_size': 5, 'throughput': 1.595562111586865, 'latency_mean': 3.1126467978954313, 'latency_p50': 3.1168971061706543, 'latency_p90': 3.5323874950408936}, {'batch_size': 6, 'throughput': 1.704323897461547, 'latency_mean': 3.5064398419857024, 'latency_p50': 3.524265170097351, 'latency_p90': 3.8714315414428713}, {'batch_size': 8, 'throughput': 1.8779779452894678, 'latency_mean': 4.222695705890655, 'latency_p50': 4.191606163978577, 'latency_p90': 4.780915570259094}, {'batch_size': 10, 'throughput': 1.957406199431286, 'latency_mean': 5.076772382259369, 'latency_p50': 5.052236318588257, 'latency_p90': 5.685748505592346}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-mistral-nemo-dpo-_2986_v1

is_internal_developer: True

language_model: ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-2496

model_size: 13B

ranking_group: single

throughput_3p7s: 1.77

us_pacific_date: 2024-12-17

win_ratio: 0.4967859229920135

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-2986-v1-mkmlizer
Waiting for job on chaiml-mistral-nemo-dpo-2986-v1-mkmlizer to finish
chaiml-mistral-nemo-dpo-2986-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-dpo-2986-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral-nemo-dpo-2986-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral-nemo-dpo-2986-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral-nemo-dpo-2986-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral-nemo-dpo-2986-v1-mkmlizer: ║       /___/                                                         ║
chaiml-mistral-nemo-dpo-2986-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-2986-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-mistral-nemo-dpo-2986-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral-nemo-dpo-2986-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-nemo-dpo-2986-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-2986-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-nemo-dpo-2986-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-nemo-dpo-2986-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-2986-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-nemo-dpo-2986-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-nemo-dpo-2986-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-mistral-nemo-dpo-2986-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-2986-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-nemo-dpo-2986-v1-mkmlizer: Downloaded to shared memory in 43.875s
chaiml-mistral-nemo-dpo-2986-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpqbqvm2gq, device:0
chaiml-mistral-nemo-dpo-2986-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-nemo-dpo-2986-v1-mkmlizer: quantized model in 37.228s
chaiml-mistral-nemo-dpo-2986-v1-mkmlizer: Processed model ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-2496 in 81.104s
chaiml-mistral-nemo-dpo-2986-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-dpo-2986-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-dpo-2986-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-2986-v1
chaiml-mistral-nemo-dpo-2986-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-2986-v1/config.json
chaiml-mistral-nemo-dpo-2986-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-2986-v1/special_tokens_map.json
chaiml-mistral-nemo-dpo-2986-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-2986-v1/tokenizer_config.json
chaiml-mistral-nemo-dpo-2986-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-2986-v1/tokenizer.json
chaiml-mistral-nemo-dpo-2986-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-2986-v1/flywheel_model.0.safetensors
chaiml-mistral-nemo-dpo-2986-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 26.66it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 46.01it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:08, 41.76it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 40.90it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:07, 46.72it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 45.96it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 44.59it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 50.13it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 46.46it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 34.62it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 33.20it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:07, 38.51it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:07, 39.42it/s]
Loading 0:  22%|██▏       | 81/363 [00:01<00:06, 40.78it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:06, 42.26it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 36.69it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:05, 44.23it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:05, 43.95it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:05, 48.02it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:05, 44.19it/s]
Loading 0:  33%|███▎      | 120/363 [00:02<00:05, 42.31it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:05, 45.24it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:05, 43.83it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:05, 43.09it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:07, 31.42it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 32.58it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 32.55it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 38.64it/s]
Loading 0:  44%|████▍     | 161/363 [00:03<00:05, 38.65it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:04, 40.32it/s]
Loading 0:  47%|████▋     | 172/363 [00:04<00:04, 40.16it/s]
Loading 0:  49%|████▉     | 177/363 [00:04<00:04, 38.89it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 43.24it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 42.55it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 42.95it/s]
Loading 0:  55%|█████▍    | 198/363 [00:04<00:03, 44.04it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:04, 36.53it/s]
Loading 0:  58%|█████▊    | 211/363 [00:05<00:03, 44.67it/s]
Loading 0:  60%|█████▉    | 217/363 [00:05<00:03, 43.69it/s]
Loading 0:  61%|██████    | 222/363 [00:05<00:03, 44.73it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:05, 26.90it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:04, 27.07it/s]
Loading 0:  66%|██████▌   | 238/363 [00:06<00:03, 33.95it/s]
Loading 0:  67%|██████▋   | 243/363 [00:06<00:03, 37.01it/s]
Loading 0:  68%|██████▊   | 248/363 [00:06<00:03, 32.75it/s]
Loading 0:  70%|███████   | 255/363 [00:06<00:02, 40.47it/s]
Loading 0:  72%|███████▏  | 260/363 [00:06<00:02, 41.97it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 43.61it/s]
Loading 0:  75%|███████▍  | 271/363 [00:06<00:02, 42.40it/s]
Loading 0:  76%|███████▌  | 276/363 [00:06<00:02, 41.45it/s]
Loading 0:  78%|███████▊  | 283/363 [00:07<00:01, 46.80it/s]
Loading 0:  80%|███████▉  | 289/363 [00:07<00:01, 45.55it/s]
Loading 0:  81%|████████  | 294/363 [00:07<00:01, 41.97it/s]
Loading 0:  82%|████████▏ | 299/363 [00:07<00:01, 43.30it/s]
Loading 0:  84%|████████▎ | 304/363 [00:14<00:24,  2.44it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:17,  3.15it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:12,  4.12it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:06,  6.87it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:03,  9.30it/s]
Loading 0:  91%|█████████ | 331/363 [00:15<00:02, 11.83it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:01, 16.60it/s]
Loading 0:  95%|█████████▍| 344/363 [00:15<00:00, 20.39it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 23.65it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 30.02it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 32.79it/s]
                                                            
Job chaiml-mistral-nemo-dpo-2986-v1-mkmlizer completed after 104.55s with status: succeeded
Stopping job with name chaiml-mistral-nemo-dpo-2986-v1-mkmlizer
Pipeline stage MKMLizer completed in 105.05s
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 chaiml-mistral-nemo-dpo-2986-v1
Waiting for inference service chaiml-mistral-nemo-dpo-2986-v1 to be ready
Inference service chaiml-mistral-nemo-dpo-2986-v1 ready after 241.9464647769928s
Pipeline stage MKMLDeployer completed in 242.52s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.2738289833068848s
Received healthy response to inference request in 0.96722412109375s
Received healthy response to inference request in 0.7007777690887451s
Received healthy response to inference request in 0.5887038707733154s
Received healthy response to inference request in 0.796654224395752s
5 requests
0 failed requests
5th percentile: 0.6111186504364013
10th percentile: 0.6335334300994873
20th percentile: 0.6783629894256592
30th percentile: 0.7199530601501465
40th percentile: 0.7583036422729492
50th percentile: 0.796654224395752
60th percentile: 0.8648821830749511
70th percentile: 0.9331101417541503
80th percentile: 1.028545093536377
90th percentile: 1.151187038421631
95th percentile: 1.2125080108642579
99th percentile: 1.2615647888183594
mean time: 0.8654377937316895
Pipeline stage StressChecker completed in 5.64s
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 2.14s
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 2.01s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_2986_v1 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 2913.23s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_2986_v1 status is now inactive due to auto deactivation removed underperforming models