submission_id: mistralai-mistral-nemo-_9330_v25
developer_uid: chai_backend_admin
alignment_samples: 0
best_of: 1
celo_rating: 1130.7
display_name: mistralai-mistral-nemo-_9330_v25
formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', 'truncate_by_message': False}
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': ['\n', '<eot_id>', '<|im_end|>', 'You:'], 'max_input_tokens': 512, 'best_of': 1, 'max_output_tokens': 64, 'reward_max_token_input': 256}
is_internal_developer: True
language_model: mistralai/Mistral-Nemo-Instruct-2407
max_input_tokens: 512
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: mistralai/Mistral-Nemo-I
model_name: mistralai-mistral-nemo-_9330_v25
model_num_parameters: 12772070400.0
model_repo: mistralai/Mistral-Nemo-Instruct-2407
model_size: 13B
num_battles: 11860
num_wins: 4801
propriety_score: 0.7316356513222331
propriety_total_count: 1021.0
ranking_group: single
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'}
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
status: torndown
submission_type: basic
timestamp: 2024-07-30T10:46:44+00:00
us_pacific_date: 2024-07-30
win_ratio: 0.40480607082630693
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name mistralai-mistral-nemo-9330-v25-mkmlizer
Waiting for job on mistralai-mistral-nemo-9330-v25-mkmlizer to finish
mistralai-mistral-nemo-9330-v25-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mistralai-mistral-nemo-9330-v25-mkmlizer: ║ _____ __ __ ║
mistralai-mistral-nemo-9330-v25-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
mistralai-mistral-nemo-9330-v25-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
mistralai-mistral-nemo-9330-v25-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
mistralai-mistral-nemo-9330-v25-mkmlizer: ║ /___/ ║
mistralai-mistral-nemo-9330-v25-mkmlizer: ║ ║
mistralai-mistral-nemo-9330-v25-mkmlizer: ║ Version: 0.9.7 ║
mistralai-mistral-nemo-9330-v25-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
mistralai-mistral-nemo-9330-v25-mkmlizer: ║ https://mk1.ai ║
mistralai-mistral-nemo-9330-v25-mkmlizer: ║ ║
mistralai-mistral-nemo-9330-v25-mkmlizer: ║ The license key for the current software has been verified as ║
mistralai-mistral-nemo-9330-v25-mkmlizer: ║ belonging to: ║
mistralai-mistral-nemo-9330-v25-mkmlizer: ║ ║
mistralai-mistral-nemo-9330-v25-mkmlizer: ║ Chai Research Corp. ║
mistralai-mistral-nemo-9330-v25-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
mistralai-mistral-nemo-9330-v25-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
mistralai-mistral-nemo-9330-v25-mkmlizer: ║ ║
mistralai-mistral-nemo-9330-v25-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
mistralai-mistral-nemo-9330-v25-mkmlizer: Downloaded to shared memory in 51.358s
mistralai-mistral-nemo-9330-v25-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpd7govj5h, device:0
mistralai-mistral-nemo-9330-v25-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
mistralai-mistral-nemo-9330-v25-mkmlizer: quantized model in 42.348s
mistralai-mistral-nemo-9330-v25-mkmlizer: Processed model mistralai/Mistral-Nemo-Instruct-2407 in 93.706s
mistralai-mistral-nemo-9330-v25-mkmlizer: creating bucket guanaco-mkml-models
mistralai-mistral-nemo-9330-v25-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
mistralai-mistral-nemo-9330-v25-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v25
mistralai-mistral-nemo-9330-v25-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v25/config.json
mistralai-mistral-nemo-9330-v25-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v25/special_tokens_map.json
mistralai-mistral-nemo-9330-v25-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v25/tokenizer_config.json
mistralai-mistral-nemo-9330-v25-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v25/tokenizer.json
mistralai-mistral-nemo-9330-v25-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v25/flywheel_model.0.safetensors
mistralai-mistral-nemo-9330-v25-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
mistralai-mistral-nemo-9330-v25-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:11, 32.45it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:06, 52.92it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 49.09it/s] Loading 0: 7%|▋ | 25/363 [00:00<00:06, 50.43it/s] Loading 0: 9%|▉ | 32/363 [00:00<00:07, 46.79it/s] Loading 0: 11%|█▏ | 41/363 [00:00<00:06, 49.45it/s] Loading 0: 13%|█▎ | 49/363 [00:00<00:05, 56.89it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:05, 54.16it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:07, 40.72it/s] Loading 0: 18%|█▊ | 66/363 [00:01<00:07, 40.85it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:06, 44.98it/s] Loading 0: 21%|██ | 77/363 [00:01<00:06, 46.02it/s] Loading 0: 23%|██▎ | 82/363 [00:01<00:07, 38.26it/s] Loading 0: 25%|██▍ | 90/363 [00:01<00:06, 45.35it/s] Loading 0: 26%|██▋ | 96/363 [00:02<00:06, 43.66it/s] Loading 0: 28%|██▊ | 101/363 [00:02<00:06, 41.77it/s] Loading 0: 29%|██▉ | 107/363 [00:02<00:05, 45.93it/s] Loading 0: 31%|███ | 112/363 [00:02<00:05, 45.90it/s] Loading 0: 32%|███▏ | 117/363 [00:02<00:05, 41.49it/s] Loading 0: 34%|███▎ | 122/363 [00:02<00:05, 42.74it/s] Loading 0: 35%|███▍ | 127/363 [00:02<00:06, 36.13it/s] Loading 0: 37%|███▋ | 134/363 [00:03<00:05, 43.07it/s] Loading 0: 38%|███▊ | 139/363 [00:03<00:05, 42.82it/s] Loading 0: 40%|███▉ | 144/363 [00:03<00:08, 26.50it/s] Loading 0: 41%|████ | 149/363 [00:03<00:07, 29.01it/s] Loading 0: 43%|████▎ | 156/363 [00:03<00:05, 36.41it/s] Loading 0: 44%|████▍ | 161/363 [00:03<00:05, 37.33it/s] Loading 0: 46%|████▌ | 166/363 [00:03<00:05, 39.02it/s] Loading 0: 47%|████▋ | 171/363 [00:04<00:04, 41.55it/s] Loading 0: 48%|████▊ | 176/363 [00:04<00:05, 34.88it/s] Loading 0: 50%|█████ | 183/363 [00:04<00:04, 42.33it/s] Loading 0: 52%|█████▏ | 188/363 [00:04<00:04, 42.27it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 42.52it/s] Loading 0: 55%|█████▍ | 198/363 [00:04<00:03, 44.26it/s] Loading 0: 56%|█████▌ | 203/363 [00:04<00:04, 36.45it/s] Loading 0: 58%|█████▊ | 210/363 [00:05<00:03, 43.17it/s] Loading 0: 59%|█████▉ | 215/363 [00:05<00:03, 41.76it/s] Loading 0: 61%|██████ | 221/363 [00:05<00:03, 45.48it/s] Loading 0: 62%|██████▏ | 226/363 [00:05<00:04, 27.93it/s] Loading 0: 63%|██████▎ | 230/363 [00:05<00:04, 27.87it/s] Loading 0: 65%|██████▌ | 237/363 [00:05<00:03, 35.57it/s] Loading 0: 67%|██████▋ | 242/363 [00:05<00:03, 37.21it/s] Loading 0: 68%|██████▊ | 247/363 [00:06<00:03, 38.53it/s] Loading 0: 69%|██████▉ | 252/363 [00:06<00:02, 40.48it/s] Loading 0: 71%|███████ | 257/363 [00:06<00:03, 34.00it/s] Loading 0: 73%|███████▎ | 264/363 [00:06<00:02, 41.03it/s] Loading 0: 74%|███████▍ | 269/363 [00:06<00:02, 40.60it/s] Loading 0: 75%|███████▌ | 274/363 [00:06<00:02, 41.21it/s] Loading 0: 77%|███████▋ | 279/363 [00:06<00:01, 42.19it/s] Loading 0: 78%|███████▊ | 284/363 [00:07<00:02, 34.11it/s] Loading 0: 80%|████████ | 291/363 [00:07<00:01, 39.87it/s] Loading 0: 82%|████████▏ | 296/363 [00:07<00:01, 38.98it/s] Loading 0: 83%|████████▎ | 301/363 [00:07<00:01, 40.41it/s] Loading 0: 84%|████████▍ | 306/363 [00:14<00:25, 2.27it/s] Loading 0: 85%|████████▌ | 310/363 [00:14<00:18, 2.94it/s] Loading 0: 87%|████████▋ | 314/363 [00:15<00:12, 3.86it/s] Loading 0: 88%|████████▊ | 319/363 [00:15<00:08, 5.46it/s] Loading 0: 89%|████████▉ | 323/363 [00:15<00:05, 7.06it/s] Loading 0: 91%|█████████ | 329/363 [00:15<00:03, 10.28it/s] Loading 0: 92%|█████████▏| 335/363 [00:15<00:02, 13.78it/s] Loading 0: 94%|█████████▎| 340/363 [00:15<00:01, 16.87it/s] Loading 0: 96%|█████████▌| 347/363 [00:15<00:00, 22.87it/s] Loading 0: 97%|█████████▋| 353/363 [00:15<00:00, 26.59it/s] Loading 0: 99%|█████████▊| 358/363 [00:16<00:00, 28.82it/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-v25-mkmlizer: warnings.warn(
mistralai-mistral-nemo-9330-v25-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-v25-mkmlizer: warnings.warn(
mistralai-mistral-nemo-9330-v25-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-v25-mkmlizer: warnings.warn(
mistralai-mistral-nemo-9330-v25-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:06<00:06, 6.59s/it] Downloading shards: 100%|██████████| 2/2 [00:09<00:00, 4.59s/it] Downloading shards: 100%|██████████| 2/2 [00:09<00:00, 4.89s/it]
mistralai-mistral-nemo-9330-v25-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 2.14it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.52it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.20it/s]
mistralai-mistral-nemo-9330-v25-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
mistralai-mistral-nemo-9330-v25-mkmlizer: Saving duration: 1.638s
mistralai-mistral-nemo-9330-v25-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 15.087s
mistralai-mistral-nemo-9330-v25-mkmlizer: creating bucket guanaco-reward-models
mistralai-mistral-nemo-9330-v25-mkmlizer: Bucket 's3://guanaco-reward-models/' created
mistralai-mistral-nemo-9330-v25-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/mistralai-mistral-nemo-9330-v25_reward
mistralai-mistral-nemo-9330-v25-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/mistralai-mistral-nemo-9330-v25_reward/config.json
mistralai-mistral-nemo-9330-v25-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/mistralai-mistral-nemo-9330-v25_reward/special_tokens_map.json
mistralai-mistral-nemo-9330-v25-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/mistralai-mistral-nemo-9330-v25_reward/tokenizer_config.json
mistralai-mistral-nemo-9330-v25-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/mistralai-mistral-nemo-9330-v25_reward/merges.txt
mistralai-mistral-nemo-9330-v25-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/mistralai-mistral-nemo-9330-v25_reward/vocab.json
mistralai-mistral-nemo-9330-v25-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/mistralai-mistral-nemo-9330-v25_reward/tokenizer.json
mistralai-mistral-nemo-9330-v25-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/mistralai-mistral-nemo-9330-v25_reward/reward.tensors
Job mistralai-mistral-nemo-9330-v25-mkmlizer completed after 146.56s with status: succeeded
Stopping job with name mistralai-mistral-nemo-9330-v25-mkmlizer
Pipeline stage MKMLizer completed in 147.72s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service mistralai-mistral-nemo-9330-v25
Waiting for inference service mistralai-mistral-nemo-9330-v25 to be ready
Inference service mistralai-mistral-nemo-9330-v25 ready after 120.96187329292297s
Pipeline stage ISVCDeployer completed in 122.83s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2779014110565186s
Received healthy response to inference request in 1.1826400756835938s
Received healthy response to inference request in 1.243537187576294s
Received healthy response to inference request in 1.4494502544403076s
Received healthy response to inference request in 1.5442469120025635s
5 requests
0 failed requests
5th percentile: 1.1948194980621338
10th percentile: 1.206998920440674
20th percentile: 1.2313577651977539
30th percentile: 1.2847198009490968
40th percentile: 1.3670850276947022
50th percentile: 1.4494502544403076
60th percentile: 1.48736891746521
70th percentile: 1.5252875804901123
80th percentile: 1.6909778118133547
90th percentile: 1.9844396114349365
95th percentile: 2.1311705112457275
99th percentile: 2.24855523109436
mean time: 1.5395551681518556
Pipeline stage StressChecker completed in 8.38s
mistralai-mistral-nemo-_9330_v25 status is now deployed due to DeploymentManager action
mistralai-mistral-nemo-_9330_v25 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of mistralai-mistral-nemo-_9330_v25
Running pipeline stage ISVCDeleter
Checking if service mistralai-mistral-nemo-9330-v25 is running
Tearing down inference service mistralai-mistral-nemo-9330-v25
Service mistralai-mistral-nemo-9330-v25 has been torndown
Pipeline stage ISVCDeleter completed in 4.61s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key mistralai-mistral-nemo-9330-v25/config.json from bucket guanaco-mkml-models
Deleting key mistralai-mistral-nemo-9330-v25/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key mistralai-mistral-nemo-9330-v25/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key mistralai-mistral-nemo-9330-v25/tokenizer.json from bucket guanaco-mkml-models
Deleting key mistralai-mistral-nemo-9330-v25/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key mistralai-mistral-nemo-9330-v25_reward/config.json from bucket guanaco-reward-models
Deleting key mistralai-mistral-nemo-9330-v25_reward/merges.txt from bucket guanaco-reward-models
Deleting key mistralai-mistral-nemo-9330-v25_reward/reward.tensors from bucket guanaco-reward-models
Deleting key mistralai-mistral-nemo-9330-v25_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key mistralai-mistral-nemo-9330-v25_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key mistralai-mistral-nemo-9330-v25_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key mistralai-mistral-nemo-9330-v25_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.20s
mistralai-mistral-nemo-_9330_v25 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics