submission_id: invisietch-atlantis-v0-1-12b_v1
developer_uid: invisietch
best_of: 4
celo_rating: 1168.71
display_name: Atlantis-v0_1-12B
family_friendly_score: 0.0
formatter: {'memory_template': '[INST]### Instruction:\n{memory}\n', 'prompt_template': '### Input:\n{prompt}\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '### Response:\n{bot_name}:[/INST]', 'truncate_by_message': False}
generation_params: {'temperature': 0.45, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64, 'reward_max_token_input': 1024}
is_internal_developer: False
language_model: invisietch/Atlantis-v0.1-12B
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: invisietch/Atlantis-v0.1
model_name: Atlantis-v0_1-12B
model_num_parameters: 12772070400.0
model_repo: invisietch/Atlantis-v0.1-12B
model_size: 13B
num_battles: 11887
num_wins: 5433
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/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-07-26T22:56:38+00:00
us_pacific_date: 2024-07-26
win_ratio: 0.4570539244552873
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name invisietch-atlantis-v0-1-12b-v1-mkmlizer
Waiting for job on invisietch-atlantis-v0-1-12b-v1-mkmlizer to finish
invisietch-atlantis-v0-1-12b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
invisietch-atlantis-v0-1-12b-v1-mkmlizer: ║ _____ __ __ ║
invisietch-atlantis-v0-1-12b-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
invisietch-atlantis-v0-1-12b-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
invisietch-atlantis-v0-1-12b-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
invisietch-atlantis-v0-1-12b-v1-mkmlizer: ║ /___/ ║
invisietch-atlantis-v0-1-12b-v1-mkmlizer: ║ ║
invisietch-atlantis-v0-1-12b-v1-mkmlizer: ║ Version: 0.9.7 ║
invisietch-atlantis-v0-1-12b-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
invisietch-atlantis-v0-1-12b-v1-mkmlizer: ║ https://mk1.ai ║
invisietch-atlantis-v0-1-12b-v1-mkmlizer: ║ ║
invisietch-atlantis-v0-1-12b-v1-mkmlizer: ║ The license key for the current software has been verified as ║
invisietch-atlantis-v0-1-12b-v1-mkmlizer: ║ belonging to: ║
invisietch-atlantis-v0-1-12b-v1-mkmlizer: ║ ║
invisietch-atlantis-v0-1-12b-v1-mkmlizer: ║ Chai Research Corp. ║
invisietch-atlantis-v0-1-12b-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
invisietch-atlantis-v0-1-12b-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
invisietch-atlantis-v0-1-12b-v1-mkmlizer: ║ ║
invisietch-atlantis-v0-1-12b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
invisietch-atlantis-v0-1-12b-v1-mkmlizer: Downloaded to shared memory in 32.900s
invisietch-atlantis-v0-1-12b-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpvk01xg2e, device:0
invisietch-atlantis-v0-1-12b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
invisietch-atlantis-v0-1-12b-v1-mkmlizer: creating bucket guanaco-mkml-models
invisietch-atlantis-v0-1-12b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
invisietch-atlantis-v0-1-12b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/invisietch-atlantis-v0-1-12b-v1
invisietch-atlantis-v0-1-12b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/invisietch-atlantis-v0-1-12b-v1/config.json
invisietch-atlantis-v0-1-12b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/invisietch-atlantis-v0-1-12b-v1/special_tokens_map.json
invisietch-atlantis-v0-1-12b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/invisietch-atlantis-v0-1-12b-v1/tokenizer_config.json
invisietch-atlantis-v0-1-12b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/invisietch-atlantis-v0-1-12b-v1/tokenizer.json
invisietch-atlantis-v0-1-12b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/invisietch-atlantis-v0-1-12b-v1/flywheel_model.0.safetensors
invisietch-atlantis-v0-1-12b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
invisietch-atlantis-v0-1-12b-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:10, 34.62it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:06, 54.41it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 48.33it/s] Loading 0: 7%|▋ | 25/363 [00:00<00:06, 48.75it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 50.49it/s] Loading 0: 10%|█ | 37/363 [00:00<00:07, 46.03it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 44.74it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 50.07it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 48.03it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 36.39it/s] Loading 0: 18%|█▊ | 66/363 [00:01<00:07, 37.27it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 41.38it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:06, 41.38it/s] Loading 0: 23%|██▎ | 83/363 [00:01<00:06, 40.73it/s] Loading 0: 25%|██▍ | 89/363 [00:02<00:06, 45.05it/s] Loading 0: 26%|██▌ | 94/363 [00:02<00:06, 44.35it/s] Loading 0: 27%|██▋ | 99/363 [00:02<00:05, 44.17it/s] Loading 0: 29%|██▉ | 105/363 [00:02<00:06, 42.42it/s] Loading 0: 31%|███ | 112/363 [00:02<00:05, 46.12it/s] Loading 0: 32%|███▏ | 117/363 [00:02<00:05, 44.05it/s] Loading 0: 34%|███▍ | 123/363 [00:02<00:05, 42.44it/s] Loading 0: 35%|███▌ | 128/363 [00:02<00:05, 41.27it/s] Loading 0: 37%|███▋ | 134/363 [00:03<00:05, 45.60it/s] Loading 0: 38%|███▊ | 139/363 [00:03<00:04, 45.37it/s] Loading 0: 40%|███▉ | 144/363 [00:03<00:07, 28.20it/s] Loading 0: 41%|████ | 149/363 [00:03<00:06, 31.15it/s] Loading 0: 43%|████▎ | 156/363 [00:03<00:05, 39.00it/s] Loading 0: 44%|████▍ | 161/363 [00:03<00:05, 40.33it/s] Loading 0: 46%|████▌ | 166/363 [00:03<00:04, 41.53it/s] Loading 0: 47%|████▋ | 172/363 [00:04<00:04, 41.18it/s] Loading 0: 49%|████▉ | 177/363 [00:04<00:04, 40.84it/s] Loading 0: 51%|█████ | 184/363 [00:04<00:03, 45.72it/s] Loading 0: 52%|█████▏ | 190/363 [00:04<00:04, 42.84it/s] Loading 0: 54%|█████▎ | 195/363 [00:04<00:04, 41.75it/s] Loading 0: 55%|█████▌ | 201/363 [00:04<00:03, 45.96it/s] Loading 0: 57%|█████▋ | 206/363 [00:04<00:03, 46.08it/s] Loading 0: 58%|█████▊ | 211/363 [00:04<00:03, 46.03it/s] Loading 0: 60%|█████▉ | 217/363 [00:05<00:03, 43.54it/s] Loading 0: 61%|██████▏ | 223/363 [00:05<00:04, 33.60it/s] Loading 0: 63%|██████▎ | 228/363 [00:05<00:03, 34.89it/s] Loading 0: 64%|██████▍ | 232/363 [00:05<00:03, 35.26it/s] Loading 0: 66%|██████▌ | 238/363 [00:05<00:03, 39.28it/s] Loading 0: 67%|██████▋ | 244/363 [00:05<00:03, 38.28it/s] Loading 0: 69%|██████▊ | 249/363 [00:06<00:02, 38.01it/s] Loading 0: 70%|███████ | 255/363 [00:06<00:02, 41.97it/s] Loading 0: 72%|███████▏ | 260/363 [00:06<00:02, 42.52it/s] Loading 0: 73%|███████▎ | 265/363 [00:06<00:02, 43.61it/s] Loading 0: 75%|███████▍ | 271/363 [00:06<00:02, 41.96it/s] Loading 0: 76%|███████▌ | 276/363 [00:06<00:02, 41.65it/s] Loading 0: 78%|███████▊ | 282/363 [00:06<00:01, 45.10it/s] Loading 0: 79%|███████▉ | 287/363 [00:06<00:01, 44.28it/s] Loading 0: 80%|████████ | 292/363 [00:06<00:01, 43.81it/s] Loading 0: 82%|████████▏ | 297/363 [00:07<00:01, 44.39it/s] Loading 0: 83%|████████▎ | 303/363 [00:07<00:01, 42.48it/s] Loading 0: 85%|████████▍ | 308/363 [00:14<00:21, 2.50it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:15, 3.23it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:08, 5.32it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:05, 7.27it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:03, 9.34it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 13.30it/s] Loading 0: 95%|█████████▍| 344/363 [00:14<00:01, 16.73it/s] Loading 0: 96%|█████████▌| 349/363 [00:14<00:00, 19.93it/s] Loading 0: 98%|█████████▊| 356/363 [00:14<00:00, 26.06it/s] Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 29.36it/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.
invisietch-atlantis-v0-1-12b-v1-mkmlizer: warnings.warn(
invisietch-atlantis-v0-1-12b-v1-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.
invisietch-atlantis-v0-1-12b-v1-mkmlizer: warnings.warn(
invisietch-atlantis-v0-1-12b-v1-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.
invisietch-atlantis-v0-1-12b-v1-mkmlizer: warnings.warn(
invisietch-atlantis-v0-1-12b-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
invisietch-atlantis-v0-1-12b-v1-mkmlizer: Saving duration: 0.315s
invisietch-atlantis-v0-1-12b-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.838s
invisietch-atlantis-v0-1-12b-v1-mkmlizer: creating bucket guanaco-reward-models
invisietch-atlantis-v0-1-12b-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/invisietch-atlantis-v0-1-12b-v1_reward/config.json
invisietch-atlantis-v0-1-12b-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/invisietch-atlantis-v0-1-12b-v1_reward/special_tokens_map.json
invisietch-atlantis-v0-1-12b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/invisietch-atlantis-v0-1-12b-v1_reward/tokenizer_config.json
invisietch-atlantis-v0-1-12b-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/invisietch-atlantis-v0-1-12b-v1_reward/merges.txt
invisietch-atlantis-v0-1-12b-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/invisietch-atlantis-v0-1-12b-v1_reward/vocab.json
invisietch-atlantis-v0-1-12b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/invisietch-atlantis-v0-1-12b-v1_reward/tokenizer.json
invisietch-atlantis-v0-1-12b-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/invisietch-atlantis-v0-1-12b-v1_reward/reward.tensors
Job invisietch-atlantis-v0-1-12b-v1-mkmlizer completed after 106.09s with status: succeeded
Stopping job with name invisietch-atlantis-v0-1-12b-v1-mkmlizer
Pipeline stage MKMLizer completed in 107.01s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service invisietch-atlantis-v0-1-12b-v1
Waiting for inference service invisietch-atlantis-v0-1-12b-v1 to be ready
Inference service invisietch-atlantis-v0-1-12b-v1 ready after 80.9370002746582s
Pipeline stage ISVCDeployer completed in 82.67s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4349052906036377s
Received healthy response to inference request in 1.8280253410339355s
Received healthy response to inference request in 1.0783145427703857s
Received healthy response to inference request in 1.0596787929534912s
Received healthy response to inference request in 1.5887908935546875s
5 requests
0 failed requests
5th percentile: 1.06340594291687
10th percentile: 1.067133092880249
20th percentile: 1.0745873928070069
30th percentile: 1.180409812927246
40th percentile: 1.3846003532409668
50th percentile: 1.5887908935546875
60th percentile: 1.6844846725463867
70th percentile: 1.7801784515380858
80th percentile: 1.9494013309478762
90th percentile: 2.192153310775757
95th percentile: 2.313529300689697
99th percentile: 2.4106300926208495
mean time: 1.5979429721832275
Pipeline stage StressChecker completed in 8.67s
invisietch-atlantis-v0-1-12b_v1 status is now deployed due to DeploymentManager action
invisietch-atlantis-v0-1-12b_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of invisietch-atlantis-v0-1-12b_v1
Running pipeline stage ISVCDeleter
Checking if service invisietch-atlantis-v0-1-12b-v1 is running
Tearing down inference service invisietch-atlantis-v0-1-12b-v1
Service invisietch-atlantis-v0-1-12b-v1 has been torndown
Pipeline stage ISVCDeleter completed in 4.08s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key invisietch-atlantis-v0-1-12b-v1/config.json from bucket guanaco-mkml-models
Deleting key invisietch-atlantis-v0-1-12b-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key invisietch-atlantis-v0-1-12b-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key invisietch-atlantis-v0-1-12b-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key invisietch-atlantis-v0-1-12b-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key invisietch-atlantis-v0-1-12b-v1_reward/config.json from bucket guanaco-reward-models
Deleting key invisietch-atlantis-v0-1-12b-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key invisietch-atlantis-v0-1-12b-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key invisietch-atlantis-v0-1-12b-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key invisietch-atlantis-v0-1-12b-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key invisietch-atlantis-v0-1-12b-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key invisietch-atlantis-v0-1-12b-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.90s
invisietch-atlantis-v0-1-12b_v1 status is now torndown due to DeploymentManager action