chaiml-mistral-nemo-dpo-_2338

developer_uid: azuruce

submission_id: chaiml-mistral-nemo-dpo-_2338_v1

model_name: chaiml-mistral-nemo-dpo-_2338_v1

model_group: ChaiML/mistral_nemo_dpo_

status: torndown

timestamp: 2024-12-17T18:55:47+00:00

num_battles: 7834

num_wins: 3762

celo_rating: 1239.6

family_friendly_score: 0.5864

family_friendly_standard_error: 0.006964697265495466

submission_type: basic

model_repo: ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-312

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.637225509378209, 'latency_mean': 1.5692390477657319, 'latency_p50': 1.5650620460510254, 'latency_p90': 1.7335551977157593}, {'batch_size': 3, 'throughput': 1.2624257491096713, 'latency_mean': 2.36580278635025, 'latency_p50': 2.3534996509552, 'latency_p90': 2.6513685703277585}, {'batch_size': 5, 'throughput': 1.5971349399738504, 'latency_mean': 3.1165924894809724, 'latency_p50': 3.12543261051178, 'latency_p90': 3.520186519622803}, {'batch_size': 6, 'throughput': 1.6993274679831358, 'latency_mean': 3.5100901305675505, 'latency_p50': 3.511743664741516, 'latency_p90': 3.9806044578552244}, {'batch_size': 8, 'throughput': 1.8620188604710708, 'latency_mean': 4.261728454828262, 'latency_p50': 4.29003643989563, 'latency_p90': 4.803493309020996}, {'batch_size': 10, 'throughput': 1.9424256877987318, 'latency_mean': 5.1079890608787535, 'latency_p50': 5.10680079460144, 'latency_p90': 5.739106631278991}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-mistral-nemo-dpo-_2338_v1

is_internal_developer: True

language_model: ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-312

model_size: 13B

ranking_group: single

throughput_3p7s: 1.76

us_pacific_date: 2024-12-17

win_ratio: 0.4802144498340567

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-2338-v1-mkmlizer
Waiting for job on chaiml-mistral-nemo-dpo-2338-v1-mkmlizer to finish
chaiml-mistral-nemo-dpo-2338-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-dpo-2338-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral-nemo-dpo-2338-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral-nemo-dpo-2338-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral-nemo-dpo-2338-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral-nemo-dpo-2338-v1-mkmlizer: ║       /___/                                                         ║
chaiml-mistral-nemo-dpo-2338-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-2338-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-mistral-nemo-dpo-2338-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral-nemo-dpo-2338-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-nemo-dpo-2338-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-2338-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-nemo-dpo-2338-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-nemo-dpo-2338-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-2338-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-nemo-dpo-2338-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-nemo-dpo-2338-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-mistral-nemo-dpo-2338-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-2338-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-nemo-dpo-2338-v1-mkmlizer: Downloaded to shared memory in 49.172s
chaiml-mistral-nemo-dpo-2338-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpvbu37cjx, device:0
chaiml-mistral-nemo-dpo-2338-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-nemo-dpo-2338-v1-mkmlizer: quantized model in 36.129s
chaiml-mistral-nemo-dpo-2338-v1-mkmlizer: Processed model ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-312 in 85.301s
chaiml-mistral-nemo-dpo-2338-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-dpo-2338-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-dpo-2338-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-2338-v1
chaiml-mistral-nemo-dpo-2338-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-2338-v1/config.json
chaiml-mistral-nemo-dpo-2338-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-2338-v1/special_tokens_map.json
chaiml-mistral-nemo-dpo-2338-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-2338-v1/tokenizer_config.json
chaiml-mistral-nemo-dpo-2338-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-2338-v1/tokenizer.json
chaiml-mistral-nemo-dpo-2338-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-2338-v1/flywheel_model.0.safetensors
chaiml-mistral-nemo-dpo-2338-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 28.25it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 49.38it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 44.57it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 42.03it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 48.00it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 45.64it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 44.77it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 50.20it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 45.26it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:06, 46.19it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 29.98it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 36.48it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:07, 37.35it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:07, 37.97it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 43.69it/s]
Loading 0:  26%|██▌       | 95/363 [00:02<00:06, 44.11it/s]
Loading 0:  28%|██▊       | 100/363 [00:02<00:06, 38.20it/s]
Loading 0:  29%|██▉       | 107/363 [00:02<00:05, 45.47it/s]
Loading 0:  31%|███       | 113/363 [00:02<00:05, 42.30it/s]
Loading 0:  33%|███▎      | 118/363 [00:02<00:05, 41.69it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:04, 49.22it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:04, 46.92it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:04, 45.80it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 34.92it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 35.34it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 33.18it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 38.88it/s]
Loading 0:  44%|████▍     | 161/363 [00:03<00:05, 39.49it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:04, 41.45it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 43.22it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 35.23it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 42.46it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 42.21it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 43.48it/s]
Loading 0:  55%|█████▍    | 198/363 [00:04<00:03, 45.15it/s]
Loading 0:  56%|█████▌    | 203/363 [00:04<00:04, 37.56it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 45.02it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 44.39it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:03, 45.67it/s]
Loading 0:  62%|██████▏   | 225/363 [00:05<00:05, 27.50it/s]
Loading 0:  63%|██████▎   | 230/363 [00:05<00:04, 29.72it/s]
Loading 0:  65%|██████▌   | 237/363 [00:05<00:03, 37.67it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 37.84it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 39.96it/s]
Loading 0:  70%|██████▉   | 253/363 [00:06<00:02, 39.87it/s]
Loading 0:  71%|███████   | 258/363 [00:06<00:02, 39.99it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 44.69it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 44.21it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:02, 43.88it/s]
Loading 0:  77%|███████▋  | 279/363 [00:06<00:01, 45.40it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:02, 37.56it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 45.12it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 44.90it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 46.14it/s]
Loading 0:  84%|████████▍ | 306/363 [00:14<00:23,  2.46it/s]
Loading 0:  85%|████████▌ | 310/363 [00:14<00:16,  3.19it/s]
Loading 0:  87%|████████▋ | 316/363 [00:14<00:09,  4.74it/s]
Loading 0:  88%|████████▊ | 321/363 [00:14<00:06,  6.30it/s]
Loading 0:  91%|█████████ | 329/363 [00:14<00:03,  9.93it/s]
Loading 0:  92%|█████████▏| 335/363 [00:14<00:02, 12.82it/s]
Loading 0:  94%|█████████▎| 340/363 [00:14<00:01, 15.69it/s]
Loading 0:  96%|█████████▌| 347/363 [00:15<00:00, 21.08it/s]
Loading 0:  97%|█████████▋| 353/363 [00:15<00:00, 24.79it/s]
Loading 0:  99%|█████████▊| 358/363 [00:15<00:00, 27.14it/s]
                                                            
Job chaiml-mistral-nemo-dpo-2338-v1-mkmlizer completed after 115.54s with status: succeeded
Stopping job with name chaiml-mistral-nemo-dpo-2338-v1-mkmlizer
Pipeline stage MKMLizer completed in 116.07s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mistral-nemo-dpo-2338-v1
Waiting for inference service chaiml-mistral-nemo-dpo-2338-v1 to be ready
Inference service chaiml-mistral-nemo-dpo-2338-v1 ready after 221.86749601364136s
Pipeline stage MKMLDeployer completed in 222.45s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.813966989517212s
Received healthy response to inference request in 1.097074031829834s
Received healthy response to inference request in 1.3078539371490479s
Received healthy response to inference request in 1.3912088871002197s
Received healthy response to inference request in 0.859001874923706s
5 requests
0 failed requests
5th percentile: 0.9066163063049316
10th percentile: 0.9542307376861572
20th percentile: 1.0494596004486083
30th percentile: 1.1392300128936768
40th percentile: 1.2235419750213623
50th percentile: 1.3078539371490479
60th percentile: 1.3411959171295167
70th percentile: 1.3745378971099853
80th percentile: 1.4757605075836182
90th percentile: 1.6448637485504152
95th percentile: 1.7294153690338134
99th percentile: 1.7970566654205322
mean time: 1.293821144104004
Pipeline stage StressChecker completed in 7.83s
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 2.33s
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 2.08s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_2338_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 2940.25s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_2338_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral-nemo-dpo-_2338_v1 status is now torndown due to DeploymentManager action
chaiml-mistral-nemo-dpo-_2338_v1 status is now torndown due to DeploymentManager action
chaiml-mistral-nemo-dpo-_2338_v1 status is now torndown due to DeploymentManager action