submission_id: intervitens-mini-magnum-_5180_v2
developer_uid: alpin
best_of: 4
celo_rating: 1208.52
display_name: magnum-12b-v1
family_friendly_score: 0.0
formatter: {'memory_template': "<s>{bot_name}'s Persona: {memory}\\\n\\\n", 'prompt_template': '{prompt} [/INST]', 'bot_template': '{bot_name}: {message}</s>', 'user_template': '[INST] {user_name}: {message} [/INST]', 'response_template': '{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 1.15, 'top_p': 1.0, 'min_p': 0.07, 'top_k': 1024, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '\n\n', 'You:'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64, 'reward_max_token_input': 1024}
is_internal_developer: False
language_model: intervitens/mini-magnum-12b-v1.1
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: intervitens/mini-magnum-
model_name: magnum-12b-v1
model_num_parameters: 12772080640.0
model_repo: intervitens/mini-magnum-12b-v1.1
model_size: 13B
num_battles: 43958
num_wins: 24730
ranking_group: single
reward_formatter: {'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n'}
reward_repo: Jellywibble/gpt2_xl_pairwise_89m_step_347634
status: torndown
submission_type: basic
timestamp: 2024-07-27T00:24:38+00:00
us_pacific_date: 2024-07-26
win_ratio: 0.562582465080304
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name intervitens-mini-magnum-5180-v2-mkmlizer
Waiting for job on intervitens-mini-magnum-5180-v2-mkmlizer to finish
intervitens-mini-magnum-5180-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
intervitens-mini-magnum-5180-v2-mkmlizer: ║ _____ __ __ ║
intervitens-mini-magnum-5180-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
intervitens-mini-magnum-5180-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
intervitens-mini-magnum-5180-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
intervitens-mini-magnum-5180-v2-mkmlizer: ║ /___/ ║
intervitens-mini-magnum-5180-v2-mkmlizer: ║ ║
intervitens-mini-magnum-5180-v2-mkmlizer: ║ Version: 0.9.7 ║
intervitens-mini-magnum-5180-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
intervitens-mini-magnum-5180-v2-mkmlizer: ║ https://mk1.ai ║
intervitens-mini-magnum-5180-v2-mkmlizer: ║ ║
intervitens-mini-magnum-5180-v2-mkmlizer: ║ The license key for the current software has been verified as ║
intervitens-mini-magnum-5180-v2-mkmlizer: ║ belonging to: ║
intervitens-mini-magnum-5180-v2-mkmlizer: ║ ║
intervitens-mini-magnum-5180-v2-mkmlizer: ║ Chai Research Corp. ║
intervitens-mini-magnum-5180-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
intervitens-mini-magnum-5180-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
intervitens-mini-magnum-5180-v2-mkmlizer: ║ ║
intervitens-mini-magnum-5180-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
intervitens-mini-magnum-5180-v2-mkmlizer: Downloaded to shared memory in 28.818s
intervitens-mini-magnum-5180-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpngjlvql6, device:0
intervitens-mini-magnum-5180-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
intervitens-mini-magnum-5180-v2-mkmlizer: quantized model in 35.557s
intervitens-mini-magnum-5180-v2-mkmlizer: Processed model intervitens/mini-magnum-12b-v1.1 in 64.376s
intervitens-mini-magnum-5180-v2-mkmlizer: creating bucket guanaco-mkml-models
intervitens-mini-magnum-5180-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
intervitens-mini-magnum-5180-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/intervitens-mini-magnum-5180-v2
intervitens-mini-magnum-5180-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/intervitens-mini-magnum-5180-v2/special_tokens_map.json
intervitens-mini-magnum-5180-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/intervitens-mini-magnum-5180-v2/config.json
intervitens-mini-magnum-5180-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/intervitens-mini-magnum-5180-v2/tokenizer_config.json
intervitens-mini-magnum-5180-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/intervitens-mini-magnum-5180-v2/flywheel_model.0.safetensors
intervitens-mini-magnum-5180-v2-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
intervitens-mini-magnum-5180-v2-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:10, 33.75it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:06, 53.41it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 48.14it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:07, 46.27it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 51.66it/s] Loading 0: 10%|█ | 37/363 [00:00<00:06, 48.28it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:06, 46.16it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 51.17it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 48.16it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 36.02it/s] Loading 0: 18%|█▊ | 66/363 [00:01<00:07, 37.24it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 41.32it/s] Loading 0: 21%|██ | 77/363 [00:01<00:06, 42.75it/s] Loading 0: 23%|██▎ | 82/363 [00:01<00:07, 36.26it/s] Loading 0: 25%|██▍ | 89/363 [00:02<00:06, 43.30it/s] Loading 0: 26%|██▌ | 94/363 [00:02<00:06, 43.00it/s] Loading 0: 27%|██▋ | 99/363 [00:02<00:05, 44.11it/s] Loading 0: 29%|██▊ | 104/363 [00:02<00:05, 45.53it/s] Loading 0: 30%|███ | 110/363 [00:02<00:05, 42.64it/s] Loading 0: 32%|███▏ | 115/363 [00:02<00:05, 43.20it/s] Loading 0: 33%|███▎ | 120/363 [00:02<00:05, 41.02it/s] Loading 0: 34%|███▍ | 125/363 [00:02<00:05, 43.15it/s] Loading 0: 36%|███▌ | 130/363 [00:02<00:05, 43.87it/s] Loading 0: 37%|███▋ | 135/363 [00:03<00:05, 44.51it/s] Loading 0: 39%|███▉ | 141/363 [00:03<00:05, 43.19it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 31.20it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 31.58it/s] Loading 0: 43%|████▎ | 156/363 [00:03<00:05, 37.65it/s] Loading 0: 44%|████▍ | 161/363 [00:03<00:05, 39.93it/s] Loading 0: 46%|████▌ | 166/363 [00:03<00:04, 39.86it/s] Loading 0: 47%|████▋ | 171/363 [00:04<00:04, 42.24it/s] Loading 0: 48%|████▊ | 176/363 [00:04<00:05, 35.54it/s] Loading 0: 50%|█████ | 183/363 [00:04<00:04, 43.43it/s] Loading 0: 52%|█████▏ | 188/363 [00:04<00:04, 43.70it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 45.07it/s] Loading 0: 55%|█████▍ | 199/363 [00:04<00:03, 43.65it/s] Loading 0: 56%|█████▌ | 204/363 [00:04<00:03, 43.01it/s] Loading 0: 58%|█████▊ | 211/363 [00:04<00:03, 47.85it/s] Loading 0: 60%|█████▉ | 217/363 [00:05<00:03, 45.23it/s] Loading 0: 61%|██████ | 222/363 [00:05<00:03, 46.25it/s] Loading 0: 63%|██████▎ | 227/363 [00:05<00:04, 32.32it/s] Loading 0: 64%|██████▎ | 231/363 [00:05<00:04, 32.37it/s] Loading 0: 65%|██████▌ | 237/363 [00:05<00:03, 38.11it/s] Loading 0: 67%|██████▋ | 242/363 [00:05<00:03, 39.99it/s] Loading 0: 68%|██████▊ | 247/363 [00:05<00:02, 41.82it/s] Loading 0: 70%|██████▉ | 253/363 [00:06<00:02, 41.42it/s] Loading 0: 71%|███████ | 258/363 [00:06<00:02, 40.06it/s] Loading 0: 73%|███████▎ | 265/363 [00:06<00:02, 45.53it/s] Loading 0: 75%|███████▍ | 271/363 [00:06<00:02, 42.53it/s] Loading 0: 76%|███████▌ | 276/363 [00:06<00:02, 41.67it/s] Loading 0: 78%|███████▊ | 283/363 [00:06<00:01, 46.40it/s] Loading 0: 80%|███████▉ | 289/363 [00:06<00:01, 44.29it/s] Loading 0: 81%|████████ | 294/363 [00:07<00:01, 43.42it/s] Loading 0: 83%|████████▎ | 300/363 [00:07<00:01, 47.37it/s] Loading 0: 84%|████████▍ | 305/363 [00:13<00:22, 2.63it/s] Loading 0: 85%|████████▌ | 309/363 [00:13<00:16, 3.36it/s] Loading 0: 86%|████████▌ | 313/363 [00:14<00:11, 4.27it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:06, 6.66it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:04, 9.09it/s] Loading 0: 91%|█████████ | 330/363 [00:14<00:03, 10.96it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 16.51it/s] Loading 0: 95%|█████████▍| 344/363 [00:14<00:00, 20.08it/s] Loading 0: 96%|█████████▌| 349/363 [00:14<00:00, 23.36it/s] Loading 0: 98%|█████████▊| 356/363 [00:15<00:00, 29.46it/s] Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 32.18it/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.
intervitens-mini-magnum-5180-v2-mkmlizer: warnings.warn(
intervitens-mini-magnum-5180-v2-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.
intervitens-mini-magnum-5180-v2-mkmlizer: warnings.warn(
intervitens-mini-magnum-5180-v2-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.
intervitens-mini-magnum-5180-v2-mkmlizer: warnings.warn(
intervitens-mini-magnum-5180-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
intervitens-mini-magnum-5180-v2-mkmlizer: Saving duration: 1.373s
intervitens-mini-magnum-5180-v2-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.253s
intervitens-mini-magnum-5180-v2-mkmlizer: creating bucket guanaco-reward-models
intervitens-mini-magnum-5180-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
intervitens-mini-magnum-5180-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/intervitens-mini-magnum-5180-v2_reward
intervitens-mini-magnum-5180-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/intervitens-mini-magnum-5180-v2_reward/config.json
intervitens-mini-magnum-5180-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/intervitens-mini-magnum-5180-v2_reward/special_tokens_map.json
intervitens-mini-magnum-5180-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/intervitens-mini-magnum-5180-v2_reward/tokenizer_config.json
intervitens-mini-magnum-5180-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/intervitens-mini-magnum-5180-v2_reward/merges.txt
intervitens-mini-magnum-5180-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/intervitens-mini-magnum-5180-v2_reward/vocab.json
intervitens-mini-magnum-5180-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/intervitens-mini-magnum-5180-v2_reward/tokenizer.json
intervitens-mini-magnum-5180-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/intervitens-mini-magnum-5180-v2_reward/reward.tensors
Job intervitens-mini-magnum-5180-v2-mkmlizer completed after 114.81s with status: succeeded
Stopping job with name intervitens-mini-magnum-5180-v2-mkmlizer
Pipeline stage MKMLizer completed in 115.70s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service intervitens-mini-magnum-5180-v2
Waiting for inference service intervitens-mini-magnum-5180-v2 to be ready
Inference service intervitens-mini-magnum-5180-v2 ready after 80.88397336006165s
Pipeline stage ISVCDeployer completed in 82.54s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.198913335800171s
Received healthy response to inference request in 1.7997725009918213s
Received healthy response to inference request in 1.8011293411254883s
Received healthy response to inference request in 1.8200287818908691s
Received healthy response to inference request in 1.2857961654663086s
5 requests
0 failed requests
5th percentile: 1.388591432571411
10th percentile: 1.4913866996765137
20th percentile: 1.6969772338867188
30th percentile: 1.8000438690185547
40th percentile: 1.8005866050720214
50th percentile: 1.8011293411254883
60th percentile: 1.8086891174316406
70th percentile: 1.816248893737793
80th percentile: 1.8958056926727296
90th percentile: 2.04735951423645
95th percentile: 2.1231364250183105
99th percentile: 2.183757953643799
mean time: 1.7811280250549317
Pipeline stage StressChecker completed in 9.67s
intervitens-mini-magnum-_5180_v2 status is now deployed due to DeploymentManager action
intervitens-mini-magnum-_5180_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of intervitens-mini-magnum-_5180_v2
Running pipeline stage ISVCDeleter
Checking if service intervitens-mini-magnum-5180-v2 is running
Tearing down inference service intervitens-mini-magnum-5180-v2
Service intervitens-mini-magnum-5180-v2 has been torndown
Pipeline stage ISVCDeleter completed in 4.06s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key intervitens-mini-magnum-5180-v2/config.json from bucket guanaco-mkml-models
Deleting key intervitens-mini-magnum-5180-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key intervitens-mini-magnum-5180-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key intervitens-mini-magnum-5180-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key intervitens-mini-magnum-5180-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key intervitens-mini-magnum-5180-v2_reward/config.json from bucket guanaco-reward-models
Deleting key intervitens-mini-magnum-5180-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key intervitens-mini-magnum-5180-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key intervitens-mini-magnum-5180-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key intervitens-mini-magnum-5180-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key intervitens-mini-magnum-5180-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key intervitens-mini-magnum-5180-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.87s
intervitens-mini-magnum-_5180_v2 status is now torndown due to DeploymentManager action