chaiml-mistral-nemo-dpo-_1903

developer_uid: azuruce

submission_id: chaiml-mistral-nemo-dpo-_1903_v1

model_name: chaiml-mistral-nemo-dpo-_1903_v1

model_group: ChaiML/mistral_nemo_dpo_

status: torndown

timestamp: 2024-12-21T21:17:09+00:00

num_battles: 16106

num_wins: 7292

celo_rating: 1226.91

family_friendly_score: 0.5993999999999999

family_friendly_standard_error: 0.006929929869775018

submission_type: basic

model_repo: ChaiML/mistral_nemo_dpo_round2_albert_20241220_v3-checkpoint-897

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.6351802476095555, 'latency_mean': 1.5742732059955598, 'latency_p50': 1.5861479043960571, 'latency_p90': 1.7337238311767578}, {'batch_size': 4, 'throughput': 1.4854823966492936, 'latency_mean': 2.681346055269241, 'latency_p50': 2.6541770696640015, 'latency_p90': 2.973890686035156}, {'batch_size': 5, 'throughput': 1.633050010153358, 'latency_mean': 3.0522346699237826, 'latency_p50': 3.0416927337646484, 'latency_p90': 3.406778407096863}, {'batch_size': 8, 'throughput': 1.899436209033446, 'latency_mean': 4.184408888816834, 'latency_p50': 4.200663328170776, 'latency_p90': 4.6942634105682375}, {'batch_size': 10, 'throughput': 1.9855149196169835, 'latency_mean': 4.994653024673462, 'latency_p50': 5.000548362731934, 'latency_p90': 5.656272840499878}, {'batch_size': 12, 'throughput': 2.039197581597501, 'latency_mean': 5.8323399186134335, 'latency_p50': 5.886536359786987, 'latency_p90': 6.562275433540345}, {'batch_size': 15, 'throughput': 2.0994019237932244, 'latency_mean': 7.070648673772812, 'latency_p50': 7.049831509590149, 'latency_p90': 7.969938087463379}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-mistral-nemo-dpo-_1903_v1

is_internal_developer: False

language_model: ChaiML/mistral_nemo_dpo_round2_albert_20241220_v3-checkpoint-897

model_size: 13B

ranking_group: single

throughput_3p7s: 1.82

us_pacific_date: 2024-12-21

win_ratio: 0.45275052775363217

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': ['User:', '<|im_end|>', 'You:', 'Bot:', '\n', '<|eot_id|>', '</s>', '####'], '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-1903-v1-mkmlizer
Waiting for job on chaiml-mistral-nemo-dpo-1903-v1-mkmlizer to finish
chaiml-mistral-nemo-dpo-1903-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-dpo-1903-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral-nemo-dpo-1903-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral-nemo-dpo-1903-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral-nemo-dpo-1903-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral-nemo-dpo-1903-v1-mkmlizer: ║       /___/                                                         ║
chaiml-mistral-nemo-dpo-1903-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-1903-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-mistral-nemo-dpo-1903-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral-nemo-dpo-1903-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-nemo-dpo-1903-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-1903-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-nemo-dpo-1903-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-nemo-dpo-1903-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-1903-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-nemo-dpo-1903-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-nemo-dpo-1903-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-mistral-nemo-dpo-1903-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-1903-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-nemo-dpo-1903-v1-mkmlizer: Downloaded to shared memory in 53.520s
chaiml-mistral-nemo-dpo-1903-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8kedq1s_, device:0
chaiml-mistral-nemo-dpo-1903-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-nemo-dpo-1903-v1-mkmlizer: quantized model in 35.966s
chaiml-mistral-nemo-dpo-1903-v1-mkmlizer: Processed model ChaiML/mistral_nemo_dpo_round2_albert_20241220_v3-checkpoint-897 in 89.486s
chaiml-mistral-nemo-dpo-1903-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-dpo-1903-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-dpo-1903-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-1903-v1
chaiml-mistral-nemo-dpo-1903-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-1903-v1/config.json
chaiml-mistral-nemo-dpo-1903-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-1903-v1/special_tokens_map.json
chaiml-mistral-nemo-dpo-1903-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-1903-v1/tokenizer_config.json
chaiml-mistral-nemo-dpo-1903-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-1903-v1/tokenizer.json
chaiml-mistral-nemo-dpo-1903-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-1903-v1/flywheel_model.0.safetensors
chaiml-mistral-nemo-dpo-1903-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 27.75it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 49.20it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:08, 42.26it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 40.41it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:07, 46.92it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 45.64it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 45.37it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 51.28it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 48.40it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 36.82it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 35.55it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:07, 38.61it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:07, 39.84it/s]
Loading 0:  22%|██▏       | 81/363 [00:01<00:06, 42.27it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:06, 42.89it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 34.47it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 40.25it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 40.56it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:05, 44.72it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:06, 37.73it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:06, 37.68it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 42.83it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 42.48it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 43.92it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:04, 45.52it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:07, 28.91it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 29.05it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:05, 38.02it/s]
Loading 0:  45%|████▍     | 162/363 [00:04<00:04, 40.44it/s]
Loading 0:  46%|████▌     | 167/363 [00:04<00:05, 36.31it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 44.57it/s]
Loading 0:  50%|████▉     | 180/363 [00:04<00:04, 45.71it/s]
Loading 0:  51%|█████     | 185/363 [00:04<00:04, 39.24it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 47.37it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 44.65it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:03, 43.30it/s]
Loading 0:  58%|█████▊    | 211/363 [00:05<00:03, 47.29it/s]
Loading 0:  60%|█████▉    | 217/363 [00:05<00:03, 44.88it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:03, 35.52it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:03, 34.48it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:03, 33.38it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 40.10it/s]
Loading 0:  67%|██████▋   | 243/363 [00:05<00:02, 42.39it/s]
Loading 0:  68%|██████▊   | 248/363 [00:06<00:03, 36.53it/s]
Loading 0:  70%|███████   | 255/363 [00:06<00:02, 43.67it/s]
Loading 0:  72%|███████▏  | 260/363 [00:06<00:02, 43.06it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 41.74it/s]
Loading 0:  74%|███████▍  | 270/363 [00:06<00:02, 43.00it/s]
Loading 0:  76%|███████▌  | 275/363 [00:06<00:02, 36.92it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 45.50it/s]
Loading 0:  80%|███████▉  | 289/363 [00:07<00:01, 44.01it/s]
Loading 0:  81%|████████  | 294/363 [00:07<00:01, 42.49it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 48.57it/s]
Loading 0:  85%|████████▍ | 307/363 [00:14<00:19,  2.81it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:13,  3.71it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:07,  5.76it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:04,  7.67it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:03,  9.69it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 13.61it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:01, 16.99it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 20.18it/s]
Loading 0:  98%|█████████▊| 355/363 [00:15<00:00, 25.12it/s]
Loading 0:  99%|█████████▉| 361/363 [00:15<00:00, 29.30it/s]
                                                            
Job chaiml-mistral-nemo-dpo-1903-v1-mkmlizer completed after 114.81s with status: succeeded
Stopping job with name chaiml-mistral-nemo-dpo-1903-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.31s
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 chaiml-mistral-nemo-dpo-1903-v1
Waiting for inference service chaiml-mistral-nemo-dpo-1903-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-mistral-nemo-dpo-1903-v1 ready after 271.6074306964874s
Pipeline stage MKMLDeployer completed in 272.16s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.5795059204101562s
Received healthy response to inference request in 1.4566004276275635s
Received healthy response to inference request in 1.3974542617797852s
Received healthy response to inference request in 0.9206557273864746s
Received healthy response to inference request in 0.9570648670196533s
5 requests
0 failed requests
5th percentile: 0.9279375553131104
10th percentile: 0.9352193832397461
20th percentile: 0.9497830390930175
30th percentile: 1.0451427459716798
40th percentile: 1.2212985038757325
50th percentile: 1.3974542617797852
60th percentile: 1.4211127281188964
70th percentile: 1.4447711944580077
80th percentile: 1.481181526184082
90th percentile: 1.530343723297119
95th percentile: 1.5549248218536378
99th percentile: 1.5745897006988525
mean time: 1.2622562408447267
Pipeline stage StressChecker completed in 7.68s
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 1.06s
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 0.68s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_1903_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 2521.88s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_1903_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral-nemo-dpo-_1903_v1 status is now torndown due to DeploymentManager action
chaiml-mistral-nemo-dpo-_1903_v1 status is now torndown due to DeploymentManager action
chaiml-mistral-nemo-dpo-_1903_v1 status is now torndown due to DeploymentManager action