developer_uid: zonemercy
submission_id: mistralai-mistral-nemo-_9330_v28
model_name: mistralai-mistral-nemo-_9330_v28
model_group: mistralai/Mistral-Nemo-I
status: torndown
timestamp: 2024-07-31T01:08:06+00:00
num_battles: 372387
num_wins: 160676
celo_rating: 1148.43
family_friendly_score: 0.0
submission_type: basic
model_repo: mistralai/Mistral-Nemo-Instruct-2407
model_architecture: MistralForCausalLM
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
model_num_parameters: 12772070400.0
best_of: 1
max_input_tokens: 1024
max_output_tokens: 64
display_name: mistralai-mistral-nemo-_9330_v28
is_internal_developer: True
language_model: mistralai/Mistral-Nemo-Instruct-2407
model_size: 13B
ranking_group: single
us_pacific_date: 2024-07-30
win_ratio: 0.43147585710564546
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['</s>', '###', 'Bot:', 'User:', 'You:', '<|im_end|>'], 'max_input_tokens': 1024, 'best_of': 1, 'max_output_tokens': 64, 'reward_max_token_input': 256}
formatter: {'memory_template': "Bot's Name: {bot_name}\nBot's Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', 'truncate_by_message': False}
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name mistralai-mistral-nemo-9330-v28-mkmlizer
Waiting for job on mistralai-mistral-nemo-9330-v28-mkmlizer to finish
mistralai-mistral-nemo-9330-v28-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mistralai-mistral-nemo-9330-v28-mkmlizer: ║     _____            __           __                                ║
mistralai-mistral-nemo-9330-v28-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
mistralai-mistral-nemo-9330-v28-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
mistralai-mistral-nemo-9330-v28-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
mistralai-mistral-nemo-9330-v28-mkmlizer: ║       /___/                                                         ║
mistralai-mistral-nemo-9330-v28-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v28-mkmlizer: ║  Version: 0.9.7                                                     ║
mistralai-mistral-nemo-9330-v28-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
mistralai-mistral-nemo-9330-v28-mkmlizer: ║  https://mk1.ai                                                     ║
mistralai-mistral-nemo-9330-v28-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v28-mkmlizer: ║  The license key for the current software has been verified as      ║
mistralai-mistral-nemo-9330-v28-mkmlizer: ║  belonging to:                                                      ║
mistralai-mistral-nemo-9330-v28-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v28-mkmlizer: ║  Chai Research Corp.                                                ║
mistralai-mistral-nemo-9330-v28-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
mistralai-mistral-nemo-9330-v28-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
mistralai-mistral-nemo-9330-v28-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v28-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
mistralai-mistral-nemo-9330-v28-mkmlizer: Downloaded to shared memory in 50.552s
mistralai-mistral-nemo-9330-v28-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpbpdnii01, device:0
mistralai-mistral-nemo-9330-v28-mkmlizer: Saving flywheel model at /dev/shm/model_cache
mistralai-mistral-nemo-9330-v28-mkmlizer: quantized model in 36.262s
mistralai-mistral-nemo-9330-v28-mkmlizer: Processed model mistralai/Mistral-Nemo-Instruct-2407 in 86.814s
mistralai-mistral-nemo-9330-v28-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
mistralai-mistral-nemo-9330-v28-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v28
mistralai-mistral-nemo-9330-v28-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v28/config.json
mistralai-mistral-nemo-9330-v28-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v28/special_tokens_map.json
mistralai-mistral-nemo-9330-v28-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v28/tokenizer_config.json
mistralai-mistral-nemo-9330-v28-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v28/tokenizer.json
mistralai-mistral-nemo-9330-v28-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v28/flywheel_model.0.safetensors
mistralai-mistral-nemo-9330-v28-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-v28-mkmlizer:   warnings.warn(
mistralai-mistral-nemo-9330-v28-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:06<00:06,  6.64s/it]
Downloading shards: 100%|██████████| 2/2 [00:11<00:00,  5.42s/it]
Downloading shards: 100%|██████████| 2/2 [00:11<00:00,  5.61s/it]
mistralai-mistral-nemo-9330-v28-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  1.99it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.39it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.07it/s]
mistralai-mistral-nemo-9330-v28-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
mistralai-mistral-nemo-9330-v28-mkmlizer: Saving duration: 1.333s
mistralai-mistral-nemo-9330-v28-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 16.681s
mistralai-mistral-nemo-9330-v28-mkmlizer: creating bucket guanaco-reward-models
mistralai-mistral-nemo-9330-v28-mkmlizer: Bucket 's3://guanaco-reward-models/' created
mistralai-mistral-nemo-9330-v28-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/mistralai-mistral-nemo-9330-v28_reward
mistralai-mistral-nemo-9330-v28-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/mistralai-mistral-nemo-9330-v28_reward/config.json
mistralai-mistral-nemo-9330-v28-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/mistralai-mistral-nemo-9330-v28_reward/special_tokens_map.json
mistralai-mistral-nemo-9330-v28-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/mistralai-mistral-nemo-9330-v28_reward/tokenizer_config.json
mistralai-mistral-nemo-9330-v28-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/mistralai-mistral-nemo-9330-v28_reward/merges.txt
mistralai-mistral-nemo-9330-v28-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/mistralai-mistral-nemo-9330-v28_reward/vocab.json
mistralai-mistral-nemo-9330-v28-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/mistralai-mistral-nemo-9330-v28_reward/tokenizer.json
Job mistralai-mistral-nemo-9330-v28-mkmlizer completed after 136.58s with status: succeeded
Stopping job with name mistralai-mistral-nemo-9330-v28-mkmlizer
Pipeline stage MKMLizer completed in 137.93s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service mistralai-mistral-nemo-9330-v28
Waiting for inference service mistralai-mistral-nemo-9330-v28 to be ready
Inference service mistralai-mistral-nemo-9330-v28 ready after 130.99566531181335s
Pipeline stage ISVCDeployer completed in 133.03s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7784862518310547s
Received healthy response to inference request in 0.8267679214477539s
Received healthy response to inference request in 1.4891412258148193s
Received healthy response to inference request in 1.0158517360687256s
Received healthy response to inference request in 0.5467689037322998s
5 requests
0 failed requests
5th percentile: 0.6027687072753907
10th percentile: 0.6587685108184814
20th percentile: 0.770768117904663
30th percentile: 0.8645846843719482
40th percentile: 0.9402182102203369
50th percentile: 1.0158517360687256
60th percentile: 1.205167531967163
70th percentile: 1.3944833278656006
80th percentile: 1.5470102310180665
90th percentile: 1.6627482414245605
95th percentile: 1.7206172466278076
99th percentile: 1.7669124507904053
mean time: 1.1314032077789307
Pipeline stage StressChecker completed in 6.29s
mistralai-mistral-nemo-_9330_v28 status is now deployed due to DeploymentManager action
mistralai-mistral-nemo-_9330_v28 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of mistralai-mistral-nemo-_9330_v28
Running pipeline stage ISVCDeleter
Checking if service mistralai-mistral-nemo-9330-v28 is running
Tearing down inference service mistralai-mistral-nemo-9330-v28
Service mistralai-mistral-nemo-9330-v28 has been torndown
Pipeline stage ISVCDeleter completed in 4.74s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key mistralai-mistral-nemo-9330-v28/config.json from bucket guanaco-mkml-models
Deleting key mistralai-mistral-nemo-9330-v28/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key mistralai-mistral-nemo-9330-v28/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key mistralai-mistral-nemo-9330-v28/tokenizer.json from bucket guanaco-mkml-models
Deleting key mistralai-mistral-nemo-9330-v28/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key mistralai-mistral-nemo-9330-v28_reward/config.json from bucket guanaco-reward-models
Deleting key mistralai-mistral-nemo-9330-v28_reward/merges.txt from bucket guanaco-reward-models
Deleting key mistralai-mistral-nemo-9330-v28_reward/reward.tensors from bucket guanaco-reward-models
Deleting key mistralai-mistral-nemo-9330-v28_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key mistralai-mistral-nemo-9330-v28_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key mistralai-mistral-nemo-9330-v28_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key mistralai-mistral-nemo-9330-v28_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.72s
mistralai-mistral-nemo-_9330_v28 status is now torndown due to DeploymentManager action