invisietch-atlantis-v0-1-12b

developer_uid: Azazelle
submission_id: invisietch-atlantis-v0-1-12b_v2
model_name: Atlantis-v0_1-12B
model_group: invisietch/Atlantis-v0.1
status: torndown
timestamp: 2024-07-29T20:36:01+00:00
num_battles: 11804
num_wins: 5896
celo_rating: 1191.19
family_friendly_score: 0.0
submission_type: basic
model_repo: invisietch/Atlantis-v0.1-12B
model_architecture: MistralForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
display_name: Atlantis-v0_1-12B
is_internal_developer: False
language_model: invisietch/Atlantis-v0.1-12B
model_size: 13B
ranking_group: single
us_pacific_date: 2024-07-29
win_ratio: 0.4994916977295832
generation_params: {'temperature': 0.7, 'top_p': 1.0, 'min_p': 0.07, 'top_k': 1024, 'presence_penalty': 0.03, 'frequency_penalty': 0.01, 'stopping_words': ['\n', '\n\n', 'You:', '[INST]', '<\\s>'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64, 'reward_max_token_input': 1024}
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}
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'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name invisietch-atlantis-v0-1-12b-v2-mkmlizer
Waiting for job on invisietch-atlantis-v0-1-12b-v2-mkmlizer to finish
invisietch-atlantis-v0-1-12b-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
invisietch-atlantis-v0-1-12b-v2-mkmlizer: ║     _____            __           __                                ║
invisietch-atlantis-v0-1-12b-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
invisietch-atlantis-v0-1-12b-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
invisietch-atlantis-v0-1-12b-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
invisietch-atlantis-v0-1-12b-v2-mkmlizer: ║       /___/                                                         ║
invisietch-atlantis-v0-1-12b-v2-mkmlizer: ║                                                                     ║
invisietch-atlantis-v0-1-12b-v2-mkmlizer: ║  Version: 0.9.7                                                     ║
invisietch-atlantis-v0-1-12b-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
invisietch-atlantis-v0-1-12b-v2-mkmlizer: ║  https://mk1.ai                                                     ║
invisietch-atlantis-v0-1-12b-v2-mkmlizer: ║                                                                     ║
invisietch-atlantis-v0-1-12b-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
invisietch-atlantis-v0-1-12b-v2-mkmlizer: ║  belonging to:                                                      ║
invisietch-atlantis-v0-1-12b-v2-mkmlizer: ║                                                                     ║
invisietch-atlantis-v0-1-12b-v2-mkmlizer: ║  Chai Research Corp.                                                ║
invisietch-atlantis-v0-1-12b-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
invisietch-atlantis-v0-1-12b-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
invisietch-atlantis-v0-1-12b-v2-mkmlizer: ║                                                                     ║
invisietch-atlantis-v0-1-12b-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission zonemercy-random-user-l3-ep2_v2: ('http://zonemercy-random-user-l3-ep2-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:41264->127.0.0.1:8080: read: connection reset by peer\n')
invisietch-atlantis-v0-1-12b-v2-mkmlizer: Downloaded to shared memory in 35.064s
invisietch-atlantis-v0-1-12b-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpw9_cai7r, device:0
invisietch-atlantis-v0-1-12b-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
invisietch-atlantis-v0-1-12b-v2-mkmlizer: quantized model in 35.513s
invisietch-atlantis-v0-1-12b-v2-mkmlizer: Processed model invisietch/Atlantis-v0.1-12B in 70.577s
invisietch-atlantis-v0-1-12b-v2-mkmlizer: creating bucket guanaco-mkml-models
invisietch-atlantis-v0-1-12b-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
invisietch-atlantis-v0-1-12b-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/invisietch-atlantis-v0-1-12b-v2
invisietch-atlantis-v0-1-12b-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/invisietch-atlantis-v0-1-12b-v2/config.json
invisietch-atlantis-v0-1-12b-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/invisietch-atlantis-v0-1-12b-v2/special_tokens_map.json
invisietch-atlantis-v0-1-12b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/invisietch-atlantis-v0-1-12b-v2/tokenizer_config.json
invisietch-atlantis-v0-1-12b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/invisietch-atlantis-v0-1-12b-v2/tokenizer.json
invisietch-atlantis-v0-1-12b-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/invisietch-atlantis-v0-1-12b-v2/flywheel_model.0.safetensors
invisietch-atlantis-v0-1-12b-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
invisietch-atlantis-v0-1-12b-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:10, 34.46it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 55.27it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 48.20it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:06, 49.40it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 51.50it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 47.69it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:06, 46.15it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:06, 50.54it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 44.50it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:06, 45.56it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 31.55it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 38.63it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:07, 39.12it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 40.23it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 44.30it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:06, 43.15it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 41.24it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:05, 43.22it/s]
Loading 0:  31%|███       | 113/363 [00:02<00:05, 42.43it/s]
Loading 0:  33%|███▎      | 118/363 [00:02<00:05, 42.21it/s]
Loading 0:  34%|███▍      | 125/363 [00:02<00:04, 48.88it/s]
Loading 0:  36%|███▌      | 131/363 [00:02<00:04, 49.32it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:05, 42.52it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 33.66it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 34.67it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 33.86it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 38.29it/s]
Loading 0:  44%|████▍     | 161/363 [00:03<00:05, 39.11it/s]
Loading 0:  46%|████▌     | 166/363 [00:03<00:04, 40.74it/s]
Loading 0:  47%|████▋     | 172/363 [00:04<00:04, 40.45it/s]
Loading 0:  49%|████▉     | 177/363 [00:04<00:04, 40.26it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 44.92it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:03, 45.14it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 45.24it/s]
Loading 0:  55%|█████▍    | 198/363 [00:04<00:03, 46.49it/s]
Loading 0:  56%|█████▌    | 203/363 [00:04<00:04, 37.56it/s]
Loading 0:  58%|█████▊    | 210/363 [00:04<00:03, 44.61it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 41.08it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:03, 42.70it/s]
Loading 0:  62%|██████▏   | 225/363 [00:05<00:04, 27.65it/s]
Loading 0:  63%|██████▎   | 230/363 [00:05<00:04, 30.17it/s]
Loading 0:  65%|██████▌   | 237/363 [00:05<00:03, 36.71it/s]
Loading 0:  67%|██████▋   | 242/363 [00:05<00:03, 38.81it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 39.28it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 41.39it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:02, 35.98it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 43.44it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 43.76it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:02, 44.15it/s]
Loading 0:  77%|███████▋  | 280/363 [00:06<00:01, 42.50it/s]
Loading 0:  79%|███████▊  | 285/363 [00:06<00:01, 41.94it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 45.79it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 45.10it/s]
Loading 0:  83%|████████▎ | 302/363 [00:07<00:01, 48.82it/s]
Loading 0:  85%|████████▍ | 307/363 [00:14<00:22,  2.54it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:14,  3.47it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:07,  5.54it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:04,  7.43it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:03,  9.43it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 13.31it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:01, 16.58it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 19.75it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 25.82it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 28.90it/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-v2-mkmlizer:   warnings.warn(
invisietch-atlantis-v0-1-12b-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.
invisietch-atlantis-v0-1-12b-v2-mkmlizer:   warnings.warn(
invisietch-atlantis-v0-1-12b-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.
invisietch-atlantis-v0-1-12b-v2-mkmlizer:   warnings.warn(
invisietch-atlantis-v0-1-12b-v2-mkmlizer: Saving duration: 0.318s
invisietch-atlantis-v0-1-12b-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.466s
invisietch-atlantis-v0-1-12b-v2-mkmlizer: creating bucket guanaco-reward-models
invisietch-atlantis-v0-1-12b-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
invisietch-atlantis-v0-1-12b-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/invisietch-atlantis-v0-1-12b-v2_reward
invisietch-atlantis-v0-1-12b-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/invisietch-atlantis-v0-1-12b-v2_reward/special_tokens_map.json
invisietch-atlantis-v0-1-12b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/invisietch-atlantis-v0-1-12b-v2_reward/tokenizer_config.json
invisietch-atlantis-v0-1-12b-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/invisietch-atlantis-v0-1-12b-v2_reward/config.json
invisietch-atlantis-v0-1-12b-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/invisietch-atlantis-v0-1-12b-v2_reward/merges.txt
invisietch-atlantis-v0-1-12b-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/invisietch-atlantis-v0-1-12b-v2_reward/vocab.json
invisietch-atlantis-v0-1-12b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/invisietch-atlantis-v0-1-12b-v2_reward/tokenizer.json
invisietch-atlantis-v0-1-12b-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/invisietch-atlantis-v0-1-12b-v2_reward/reward.tensors
Job invisietch-atlantis-v0-1-12b-v2-mkmlizer completed after 107.9s with status: succeeded
Stopping job with name invisietch-atlantis-v0-1-12b-v2-mkmlizer
Pipeline stage MKMLizer completed in 109.31s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service invisietch-atlantis-v0-1-12b-v2
Waiting for inference service invisietch-atlantis-v0-1-12b-v2 to be ready
Inference service invisietch-atlantis-v0-1-12b-v2 ready after 111.00380873680115s
Pipeline stage ISVCDeployer completed in 112.68s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4118852615356445s
Received healthy response to inference request in 1.4003002643585205s
Received healthy response to inference request in 1.5954136848449707s
Received healthy response to inference request in 1.603849172592163s
Received healthy response to inference request in 1.6234712600708008s
5 requests
0 failed requests
5th percentile: 1.4393229484558105
10th percentile: 1.4783456325531006
20th percentile: 1.5563910007476807
30th percentile: 1.5971007823944092
40th percentile: 1.600474977493286
50th percentile: 1.603849172592163
60th percentile: 1.6116980075836183
70th percentile: 1.6195468425750732
80th percentile: 1.7811540603637697
90th percentile: 2.096519660949707
95th percentile: 2.2542024612426754
99th percentile: 2.380348701477051
mean time: 1.7269839286804198
Pipeline stage StressChecker completed in 9.35s
invisietch-atlantis-v0-1-12b_v2 status is now deployed due to DeploymentManager action
invisietch-atlantis-v0-1-12b_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of invisietch-atlantis-v0-1-12b_v2
Running pipeline stage ISVCDeleter
Checking if service invisietch-atlantis-v0-1-12b-v2 is running
Tearing down inference service invisietch-atlantis-v0-1-12b-v2
Service invisietch-atlantis-v0-1-12b-v2 has been torndown
Pipeline stage ISVCDeleter completed in 4.69s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key invisietch-atlantis-v0-1-12b-v2/config.json from bucket guanaco-mkml-models
Deleting key invisietch-atlantis-v0-1-12b-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key invisietch-atlantis-v0-1-12b-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key invisietch-atlantis-v0-1-12b-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key invisietch-atlantis-v0-1-12b-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key invisietch-atlantis-v0-1-12b-v2_reward/config.json from bucket guanaco-reward-models
Deleting key invisietch-atlantis-v0-1-12b-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key invisietch-atlantis-v0-1-12b-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key invisietch-atlantis-v0-1-12b-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key invisietch-atlantis-v0-1-12b-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key invisietch-atlantis-v0-1-12b-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key invisietch-atlantis-v0-1-12b-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.95s
invisietch-atlantis-v0-1-12b_v2 status is now torndown due to DeploymentManager action