chaiml-mistral-nemo-dpo-_8024

developer_uid: azuruce

submission_id: chaiml-mistral-nemo-dpo-_8024_v1

model_name: chaiml-mistral-nemo-dpo-_8024_v1

model_group: ChaiML/mistral_nemo_dpo_

status: inactive

timestamp: 2024-12-20T23:19:08+00:00

num_battles: 12330

num_wins: 6080

celo_rating: 1240.05

family_friendly_score: 0.603

family_friendly_standard_error: 0.006919407489084596

submission_type: basic

model_repo: ChaiML/mistral_nemo_dpo_round2_albert_20241220_v1-checkpoint-1311

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6349557365932502, 'latency_mean': 1.5747944235801696, 'latency_p50': 1.5802732706069946, 'latency_p90': 1.7432382345199584}, {'batch_size': 3, 'throughput': 1.2813030419465539, 'latency_mean': 2.3369092559814453, 'latency_p50': 2.327973246574402, 'latency_p90': 2.594570446014404}, {'batch_size': 5, 'throughput': 1.5974384976434128, 'latency_mean': 3.1154650270938875, 'latency_p50': 3.1300512552261353, 'latency_p90': 3.4364384412765503}, {'batch_size': 6, 'throughput': 1.7249892730634893, 'latency_mean': 3.4550818145275115, 'latency_p50': 3.4332854747772217, 'latency_p90': 3.919884443283081}, {'batch_size': 8, 'throughput': 1.8870156709386852, 'latency_mean': 4.221514104604721, 'latency_p50': 4.221574902534485, 'latency_p90': 4.789563989639282}, {'batch_size': 10, 'throughput': 1.9601903263870109, 'latency_mean': 5.061388744115829, 'latency_p50': 5.046655893325806, 'latency_p90': 5.819239926338196}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-mistral-nemo-dpo-_8024_v1

is_internal_developer: True

language_model: ChaiML/mistral_nemo_dpo_round2_albert_20241220_v1-checkpoint-1311

model_size: 13B

ranking_group: single

throughput_3p7s: 1.79

us_pacific_date: 2024-12-20

win_ratio: 0.4931062449310625

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-8024-v1-mkmlizer
Waiting for job on chaiml-mistral-nemo-dpo-8024-v1-mkmlizer to finish
chaiml-mistral-nemo-dpo-8024-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-dpo-8024-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral-nemo-dpo-8024-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral-nemo-dpo-8024-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral-nemo-dpo-8024-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral-nemo-dpo-8024-v1-mkmlizer: ║       /___/                                                         ║
chaiml-mistral-nemo-dpo-8024-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-8024-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-mistral-nemo-dpo-8024-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral-nemo-dpo-8024-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-nemo-dpo-8024-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-8024-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-nemo-dpo-8024-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-nemo-dpo-8024-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-8024-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-nemo-dpo-8024-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-nemo-dpo-8024-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-mistral-nemo-dpo-8024-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-8024-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-nemo-dpo-8024-v1-mkmlizer: Downloaded to shared memory in 54.690s
chaiml-mistral-nemo-dpo-8024-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp11qp89pw, device:0
chaiml-mistral-nemo-dpo-8024-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-nemo-dpo-8024-v1-mkmlizer: quantized model in 37.540s
chaiml-mistral-nemo-dpo-8024-v1-mkmlizer: Processed model ChaiML/mistral_nemo_dpo_round2_albert_20241220_v1-checkpoint-1311 in 92.230s
chaiml-mistral-nemo-dpo-8024-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-dpo-8024-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-dpo-8024-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-8024-v1
chaiml-mistral-nemo-dpo-8024-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-8024-v1/config.json
chaiml-mistral-nemo-dpo-8024-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-8024-v1/tokenizer.json
chaiml-mistral-nemo-dpo-8024-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-8024-v1/flywheel_model.0.safetensors
chaiml-mistral-nemo-dpo-8024-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 27.24it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 45.38it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:07, 46.87it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:09, 37.62it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:07, 43.03it/s]
Loading 0:  10%|▉         | 35/363 [00:00<00:07, 42.80it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:07, 42.90it/s]
Loading 0:  12%|█▏        | 45/363 [00:01<00:07, 44.32it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:08, 35.63it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:07, 40.44it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:10, 28.23it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:10, 27.73it/s]
Loading 0:  19%|█▉        | 69/363 [00:01<00:09, 29.78it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:09, 29.17it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:07, 37.63it/s]
Loading 0:  23%|██▎       | 85/363 [00:02<00:07, 38.22it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 39.32it/s]
Loading 0:  26%|██▌       | 95/363 [00:02<00:06, 40.34it/s]
Loading 0:  28%|██▊       | 100/363 [00:02<00:07, 34.57it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:06, 39.88it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:05, 44.10it/s]
Loading 0:  32%|███▏      | 117/363 [00:03<00:05, 41.82it/s]
Loading 0:  34%|███▍      | 123/363 [00:03<00:05, 40.59it/s]
Loading 0:  35%|███▌      | 128/363 [00:03<00:05, 40.23it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:05, 44.05it/s]
Loading 0:  38%|███▊      | 139/363 [00:03<00:05, 43.73it/s]
Loading 0:  40%|███▉      | 144/363 [00:03<00:08, 26.61it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:07, 28.70it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:05, 36.38it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 38.01it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:04, 39.83it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 42.02it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 34.93it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 42.19it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 42.24it/s]
Loading 0:  53%|█████▎    | 193/363 [00:05<00:03, 42.69it/s]
Loading 0:  55%|█████▍    | 199/363 [00:05<00:03, 41.23it/s]
Loading 0:  56%|█████▌    | 204/363 [00:05<00:03, 40.51it/s]
Loading 0:  58%|█████▊    | 211/363 [00:05<00:03, 45.16it/s]
Loading 0:  60%|█████▉    | 216/363 [00:05<00:03, 46.15it/s]
Loading 0:  61%|██████    | 221/363 [00:05<00:03, 46.43it/s]
Loading 0:  62%|██████▏   | 226/363 [00:06<00:04, 28.28it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:04, 28.39it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 36.28it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 37.23it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:03, 38.32it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 39.74it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:03, 33.74it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 40.21it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 39.10it/s]
Loading 0:  75%|███████▌  | 274/363 [00:07<00:02, 39.04it/s]
Loading 0:  77%|███████▋  | 279/363 [00:07<00:02, 40.76it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:02, 34.07it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 40.61it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 40.46it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 40.83it/s]
Loading 0:  84%|████████▍ | 306/363 [00:15<00:24,  2.36it/s]
Loading 0:  85%|████████▌ | 310/363 [00:15<00:17,  3.07it/s]
Loading 0:  87%|████████▋ | 314/363 [00:15<00:12,  4.03it/s]
Loading 0:  88%|████████▊ | 320/363 [00:15<00:07,  6.00it/s]
Loading 0:  90%|████████▉ | 326/363 [00:15<00:04,  8.41it/s]
Loading 0:  91%|█████████ | 330/363 [00:15<00:03, 10.28it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:01, 15.70it/s]
Loading 0:  94%|█████████▍| 343/363 [00:15<00:01, 19.02it/s]
Loading 0:  96%|█████████▌| 348/363 [00:16<00:00, 20.64it/s]
Loading 0:  98%|█████████▊| 355/363 [00:16<00:00, 27.43it/s]
Loading 0:  99%|█████████▉| 360/363 [00:16<00:00, 30.11it/s]
                                                            
Job chaiml-mistral-nemo-dpo-8024-v1-mkmlizer completed after 114.32s with status: succeeded
Stopping job with name chaiml-mistral-nemo-dpo-8024-v1-mkmlizer
Pipeline stage MKMLizer completed in 114.77s
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 chaiml-mistral-nemo-dpo-8024-v1
Waiting for inference service chaiml-mistral-nemo-dpo-8024-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-mistral-nemo-dpo-8024-v1 ready after 381.313010931015s
Pipeline stage MKMLDeployer completed in 381.85s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.214914083480835s
Received healthy response to inference request in 1.372668981552124s
Received healthy response to inference request in 0.7643914222717285s
Received healthy response to inference request in 0.8504638671875s
Received healthy response to inference request in 1.729201316833496s
5 requests
0 failed requests
5th percentile: 0.7816059112548828
10th percentile: 0.7988204002380371
20th percentile: 0.8332493782043457
30th percentile: 0.923353910446167
40th percentile: 1.069133996963501
50th percentile: 1.214914083480835
60th percentile: 1.2780160427093505
70th percentile: 1.3411180019378661
80th percentile: 1.4439754486083984
90th percentile: 1.5865883827209473
95th percentile: 1.6578948497772217
99th percentile: 1.7149400234222412
mean time: 1.1863279342651367
Pipeline stage StressChecker completed in 7.26s
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 0.64s
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 0.64s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_8024_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 2201.56s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_8024_v1 status is now inactive due to auto deactivation removed underperforming models