submission_id: mistralai-mistral-nemo-_9330_v41
developer_uid: chai_backend_admin
alignment_samples: 0
best_of: 2
celo_rating: 1164.23
display_name: mistralai-mistral-nemo-_9330_v41
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}</s>\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': True}
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['</s>', '###'], 'max_input_tokens': 1500, 'best_of': 2, 'max_output_tokens': 64, 'reward_max_token_input': 256}
is_internal_developer: True
language_model: mistralai/Mistral-Nemo-Instruct-2407
max_input_tokens: 1500
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: mistralai/Mistral-Nemo-I
model_name: mistralai-mistral-nemo-_9330_v41
model_num_parameters: 12772070400.0
model_repo: mistralai/Mistral-Nemo-Instruct-2407
model_size: 13B
num_battles: 12649
num_wins: 5539
propriety_score: 0.7209705372616985
propriety_total_count: 1154.0
ranking_group: single
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
status: torndown
submission_type: basic
timestamp: 2024-08-09T02:50:24+00:00
us_pacific_date: 2024-08-08
win_ratio: 0.43790022926713573
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name mistralai-mistral-nemo-9330-v41-mkmlizer
Waiting for job on mistralai-mistral-nemo-9330-v41-mkmlizer to finish
Stopping job with name mistralai-mistral-nemo-9330-v41-mkmlizer
%s, retrying in %s seconds...
Starting job with name mistralai-mistral-nemo-9330-v41-mkmlizer
Waiting for job on mistralai-mistral-nemo-9330-v41-mkmlizer to finish
mistralai-mistral-nemo-9330-v41-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mistralai-mistral-nemo-9330-v41-mkmlizer: ║     _____            __           __                                ║
mistralai-mistral-nemo-9330-v41-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
mistralai-mistral-nemo-9330-v41-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
mistralai-mistral-nemo-9330-v41-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
mistralai-mistral-nemo-9330-v41-mkmlizer: ║       /___/                                                         ║
mistralai-mistral-nemo-9330-v41-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v41-mkmlizer: ║  Version: 0.9.9                                                     ║
mistralai-mistral-nemo-9330-v41-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
mistralai-mistral-nemo-9330-v41-mkmlizer: ║  https://mk1.ai                                                     ║
mistralai-mistral-nemo-9330-v41-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v41-mkmlizer: ║  The license key for the current software has been verified as      ║
mistralai-mistral-nemo-9330-v41-mkmlizer: ║  belonging to:                                                      ║
mistralai-mistral-nemo-9330-v41-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v41-mkmlizer: ║  Chai Research Corp.                                                ║
mistralai-mistral-nemo-9330-v41-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
mistralai-mistral-nemo-9330-v41-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
mistralai-mistral-nemo-9330-v41-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v41-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
mistralai-mistral-nemo-9330-v41-mkmlizer: Downloaded to shared memory in 53.811s
mistralai-mistral-nemo-9330-v41-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5yvazcn7, device:0
mistralai-mistral-nemo-9330-v41-mkmlizer: Saving flywheel model at /dev/shm/model_cache
mistralai-mistral-nemo-9330-v41-mkmlizer: quantized model in 36.802s
mistralai-mistral-nemo-9330-v41-mkmlizer: Processed model mistralai/Mistral-Nemo-Instruct-2407 in 90.613s
mistralai-mistral-nemo-9330-v41-mkmlizer: creating bucket guanaco-mkml-models
mistralai-mistral-nemo-9330-v41-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
mistralai-mistral-nemo-9330-v41-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v41
mistralai-mistral-nemo-9330-v41-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v41/config.json
mistralai-mistral-nemo-9330-v41-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v41/special_tokens_map.json
mistralai-mistral-nemo-9330-v41-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v41/tokenizer_config.json
mistralai-mistral-nemo-9330-v41-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v41/tokenizer.json
mistralai-mistral-nemo-9330-v41-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v41/flywheel_model.0.safetensors
mistralai-mistral-nemo-9330-v41-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
mistralai-mistral-nemo-9330-v41-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 32.28it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 50.72it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 45.26it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 43.13it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 48.67it/s]
Loading 0:  10%|▉         | 36/363 [00:00<00:06, 49.04it/s]
Loading 0:  11%|█▏        | 41/363 [00:00<00:08, 39.07it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:06, 46.54it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:06, 48.16it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:06, 45.19it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 30.66it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 36.87it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:07, 39.29it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:08, 33.91it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 41.72it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:06, 40.62it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 40.08it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:06, 42.30it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:05, 44.86it/s]
Loading 0:  32%|███▏      | 117/363 [00:02<00:05, 42.95it/s]
Loading 0:  34%|███▎      | 122/363 [00:02<00:05, 44.31it/s]
Loading 0:  35%|███▍      | 127/363 [00:03<00:06, 36.66it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:05, 42.97it/s]
Loading 0:  38%|███▊      | 139/363 [00:03<00:05, 42.06it/s]
Loading 0:  40%|███▉      | 144/363 [00:03<00:08, 26.82it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 29.05it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 36.00it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 36.89it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 38.69it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 40.14it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 34.26it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 41.74it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 42.22it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:04, 41.87it/s]
Loading 0:  55%|█████▍    | 198/363 [00:04<00:03, 43.86it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:04, 36.46it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 43.07it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 43.49it/s]
Loading 0:  61%|██████    | 221/363 [00:05<00:03, 47.28it/s]
Loading 0:  62%|██████▏   | 226/363 [00:05<00:04, 29.39it/s]
Loading 0:  63%|██████▎   | 230/363 [00:05<00:04, 29.76it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 37.29it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 38.07it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 38.68it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 41.03it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:03, 34.47it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 41.12it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 41.51it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:02, 41.83it/s]
Loading 0:  77%|███████▋  | 279/363 [00:07<00:01, 42.94it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:02, 35.22it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 42.00it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 41.72it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 42.58it/s]
Loading 0:  84%|████████▍ | 306/363 [00:14<00:23,  2.47it/s]
Loading 0:  85%|████████▌ | 310/363 [00:14<00:16,  3.20it/s]
Loading 0:  87%|████████▋ | 314/363 [00:14<00:11,  4.19it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:06,  6.24it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:04,  8.71it/s]
Loading 0:  91%|█████████ | 330/363 [00:15<00:03, 10.59it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:01, 16.20it/s]
Loading 0:  95%|█████████▍| 344/363 [00:15<00:00, 19.61it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 22.29it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 28.48it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 30.70it/s]
                                                            
/opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:957: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
mistralai-mistral-nemo-9330-v41-mkmlizer:   warnings.warn(
mistralai-mistral-nemo-9330-v41-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:785: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
mistralai-mistral-nemo-9330-v41-mkmlizer:   warnings.warn(
mistralai-mistral-nemo-9330-v41-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:469: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
mistralai-mistral-nemo-9330-v41-mkmlizer:   warnings.warn(
mistralai-mistral-nemo-9330-v41-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:05<00:05,  5.79s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  4.19s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  4.43s/it]
mistralai-mistral-nemo-9330-v41-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  2.29it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.87it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.50it/s]
mistralai-mistral-nemo-9330-v41-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
mistralai-mistral-nemo-9330-v41-mkmlizer: Saving duration: 1.354s
mistralai-mistral-nemo-9330-v41-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.863s
mistralai-mistral-nemo-9330-v41-mkmlizer: creating bucket guanaco-reward-models
mistralai-mistral-nemo-9330-v41-mkmlizer: Bucket 's3://guanaco-reward-models/' created
mistralai-mistral-nemo-9330-v41-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/mistralai-mistral-nemo-9330-v41_reward
mistralai-mistral-nemo-9330-v41-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/mistralai-mistral-nemo-9330-v41_reward/config.json
mistralai-mistral-nemo-9330-v41-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/mistralai-mistral-nemo-9330-v41_reward/tokenizer_config.json
mistralai-mistral-nemo-9330-v41-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/mistralai-mistral-nemo-9330-v41_reward/special_tokens_map.json
mistralai-mistral-nemo-9330-v41-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/mistralai-mistral-nemo-9330-v41_reward/merges.txt
mistralai-mistral-nemo-9330-v41-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/mistralai-mistral-nemo-9330-v41_reward/vocab.json
mistralai-mistral-nemo-9330-v41-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/mistralai-mistral-nemo-9330-v41_reward/tokenizer.json
mistralai-mistral-nemo-9330-v41-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/mistralai-mistral-nemo-9330-v41_reward/reward.tensors
Job mistralai-mistral-nemo-9330-v41-mkmlizer completed after 145.95s with status: succeeded
Stopping job with name mistralai-mistral-nemo-9330-v41-mkmlizer
Pipeline stage MKMLizer completed in 147.62s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service mistralai-mistral-nemo-9330-v41
Waiting for inference service mistralai-mistral-nemo-9330-v41 to be ready
Inference service mistralai-mistral-nemo-9330-v41 ready after 201.29883337020874s
Pipeline stage ISVCDeployer completed in 202.93s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.844569444656372s
Received healthy response to inference request in 1.829956293106079s
Received healthy response to inference request in 1.3349661827087402s
Received healthy response to inference request in 1.3546700477600098s
Received healthy response to inference request in 1.3020954132080078s
5 requests
0 failed requests
5th percentile: 1.3086695671081543
10th percentile: 1.3152437210083008
20th percentile: 1.3283920288085938
30th percentile: 1.338906955718994
40th percentile: 1.346788501739502
50th percentile: 1.3546700477600098
60th percentile: 1.5447845458984375
70th percentile: 1.7348990440368652
80th percentile: 1.8328789234161378
90th percentile: 1.838724184036255
95th percentile: 1.8416468143463134
99th percentile: 1.8439849185943604
mean time: 1.5332514762878418
Pipeline stage StressChecker completed in 8.43s
mistralai-mistral-nemo-_9330_v41 status is now deployed due to DeploymentManager action
mistralai-mistral-nemo-_9330_v41 status is now inactive due to auto deactivation removed underperforming models
mistralai-mistral-nemo-_9330_v41 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics