zonemercy-cogent-nemo-v1_3266

developer_uid: zonemercy
submission_id: zonemercy-cogent-nemo-v1_3266_v7
model_name: 0814v1-7
model_group: zonemercy/Cogent-Nemo-v1
status: torndown
timestamp: 2024-08-15T00:26:57+00:00
num_battles: 9360
num_wins: 5039
celo_rating: 1256.28
family_friendly_score: 0.0
submission_type: basic
model_repo: zonemercy/Cogent-Nemo-v1-1k1e5
model_architecture: MistralForCausalLM
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
model_num_parameters: 12772070400.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: 0814v1-7
is_internal_developer: True
language_model: zonemercy/Cogent-Nemo-v1-1k1e5
model_size: 13B
ranking_group: single
us_pacific_date: 2024-08-14
win_ratio: 0.5383547008547008
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '###', 'Bot:', 'User:', 'You:', '<|im_end|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64, 'reward_max_token_input': 256}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
reward_formatter: {'bot_template': 'Bot: {message}\n', 'memory_template': '', 'prompt_template': '', 'response_template': 'Bot:', 'truncate_by_message': False, 'user_template': 'User: {message}\n'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name zonemercy-cogent-nemo-v1-3266-v7-mkmlizer
Waiting for job on zonemercy-cogent-nemo-v1-3266-v7-mkmlizer to finish
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: ║     _____            __           __                                ║
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: ║       /___/                                                         ║
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: ║                                                                     ║
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: ║  Version: 0.9.9                                                     ║
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: ║  https://mk1.ai                                                     ║
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: ║                                                                     ║
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: ║  The license key for the current software has been verified as      ║
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: ║  belonging to:                                                      ║
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: ║                                                                     ║
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: ║  Chai Research Corp.                                                ║
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: ║                                                                     ║
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: Downloaded to shared memory in 76.104s
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5fvttryb, device:0
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: quantized model in 40.859s
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: Processed model zonemercy/Cogent-Nemo-v1-1k1e5 in 116.964s
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: creating bucket guanaco-mkml-models
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zonemercy-cogent-nemo-v1-3266-v7
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zonemercy-cogent-nemo-v1-3266-v7/config.json
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zonemercy-cogent-nemo-v1-3266-v7/special_tokens_map.json
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zonemercy-cogent-nemo-v1-3266-v7/tokenizer_config.json
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zonemercy-cogent-nemo-v1-3266-v7/tokenizer.json
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zonemercy-cogent-nemo-v1-3266-v7/flywheel_model.0.safetensors
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 22.75it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 27.97it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:14, 24.30it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:11, 30.73it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:15, 22.16it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:17, 19.69it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:13, 25.48it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:12, 26.56it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:12, 26.88it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:13, 24.59it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:11, 27.72it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:12, 24.80it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:10, 29.47it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 25.41it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:13, 21.92it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:10, 26.80it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:11, 26.08it/s]
Loading 0:  21%|██        | 77/363 [00:03<00:12, 23.64it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:09, 28.55it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 25.53it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:08, 30.23it/s]
Loading 0:  26%|██▌       | 95/363 [00:03<00:10, 26.16it/s]
Loading 0:  28%|██▊       | 100/363 [00:03<00:08, 30.72it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:12, 20.13it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:10, 25.01it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:10, 23.60it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 30.02it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 28.88it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 30.65it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:07, 29.25it/s]
Loading 0:  38%|███▊      | 137/363 [00:05<00:07, 29.61it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 25.89it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:08, 24.23it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 22.75it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:07, 27.60it/s]
Loading 0:  44%|████▎     | 158/363 [00:06<00:08, 24.86it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:06, 30.93it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 29.23it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 31.24it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 29.79it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:08, 22.09it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:08, 20.33it/s]
Loading 0:  53%|█████▎    | 192/363 [00:07<00:06, 27.04it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 26.79it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 29.70it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 28.68it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 31.05it/s]
Loading 0:  59%|█████▉    | 214/363 [00:08<00:05, 29.66it/s]
Loading 0:  60%|██████    | 218/363 [00:08<00:04, 29.73it/s]
Loading 0:  61%|██████▏   | 223/363 [00:08<00:05, 25.98it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 24.45it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 23.03it/s]
Loading 0:  65%|██████▍   | 235/363 [00:08<00:04, 28.31it/s]
Loading 0:  66%|██████▌   | 239/363 [00:09<00:04, 26.05it/s]
Loading 0:  68%|██████▊   | 246/363 [00:09<00:03, 32.22it/s]
Loading 0:  69%|██████▉   | 250/363 [00:09<00:03, 30.13it/s]
Loading 0:  70%|███████   | 255/363 [00:09<00:03, 31.90it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 29.98it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:04, 24.68it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:04, 21.85it/s]
Loading 0:  75%|███████▌  | 273/363 [00:10<00:03, 28.52it/s]
Loading 0:  76%|███████▋  | 277/363 [00:10<00:03, 27.77it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 30.37it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 28.99it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 31.18it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 29.41it/s]
Loading 0:  82%|████████▏ | 299/363 [00:11<00:02, 29.02it/s]
Loading 0:  84%|████████▎ | 304/363 [00:11<00:02, 24.88it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 23.28it/s]
Loading 0:  85%|████████▌ | 310/363 [00:11<00:02, 24.48it/s]
Loading 0:  86%|████████▌ | 313/363 [00:11<00:02, 24.54it/s]
Loading 0:  88%|████████▊ | 318/363 [00:11<00:01, 27.86it/s]
Loading 0:  88%|████████▊ | 321/363 [00:12<00:01, 25.34it/s]
Loading 0:  90%|████████▉ | 325/363 [00:12<00:01, 28.44it/s]
Loading 0:  91%|█████████ | 329/363 [00:12<00:01, 25.24it/s]
Loading 0:  93%|█████████▎| 336/363 [00:12<00:00, 31.54it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 29.35it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:09,  2.00it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.67it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.86it/s]
Loading 0:  98%|█████████▊| 357/363 [00:20<00:01,  4.98it/s]
Loading 0: 100%|█████████▉| 362/363 [00:20<00:00,  7.07it/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.
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer:   warnings.warn(
zonemercy-cogent-nemo-v1-3266-v7-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.
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer:   warnings.warn(
zonemercy-cogent-nemo-v1-3266-v7-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.
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer:   warnings.warn(
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:05<00:05,  5.01s/it]
Downloading shards: 100%|██████████| 2/2 [00:07<00:00,  3.55s/it]
Downloading shards: 100%|██████████| 2/2 [00:07<00:00,  3.77s/it]
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  2.44it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  4.00it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.65it/s]
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: Saving duration: 1.427s
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 12.346s
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: creating bucket guanaco-reward-models
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: Bucket 's3://guanaco-reward-models/' created
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/zonemercy-cogent-nemo-v1-3266-v7_reward
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/zonemercy-cogent-nemo-v1-3266-v7_reward/config.json
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/zonemercy-cogent-nemo-v1-3266-v7_reward/special_tokens_map.json
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/zonemercy-cogent-nemo-v1-3266-v7_reward/tokenizer_config.json
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/zonemercy-cogent-nemo-v1-3266-v7_reward/merges.txt
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/zonemercy-cogent-nemo-v1-3266-v7_reward/vocab.json
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/zonemercy-cogent-nemo-v1-3266-v7_reward/tokenizer.json
zonemercy-cogent-nemo-v1-3266-v7-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/zonemercy-cogent-nemo-v1-3266-v7_reward/reward.tensors
Job zonemercy-cogent-nemo-v1-3266-v7-mkmlizer completed after 168.48s with status: succeeded
Stopping job with name zonemercy-cogent-nemo-v1-3266-v7-mkmlizer
Pipeline stage MKMLizer completed in 168.99s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service zonemercy-cogent-nemo-v1-3266-v7
Waiting for inference service zonemercy-cogent-nemo-v1-3266-v7 to be ready
Inference service zonemercy-cogent-nemo-v1-3266-v7 ready after 231.73820281028748s
Pipeline stage ISVCDeployer completed in 232.51s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6019959449768066s
Received healthy response to inference request in 1.7550380229949951s
Received healthy response to inference request in 1.7640330791473389s
Received healthy response to inference request in 1.7914454936981201s
Received healthy response to inference request in 1.7501232624053955s
5 requests
0 failed requests
5th percentile: 1.7511062145233154
10th percentile: 1.7520891666412353
20th percentile: 1.7540550708770752
30th percentile: 1.7568370342254638
40th percentile: 1.7604350566864013
50th percentile: 1.7640330791473389
60th percentile: 1.7749980449676515
70th percentile: 1.7859630107879638
80th percentile: 1.9535555839538576
90th percentile: 2.277775764465332
95th percentile: 2.4398858547210693
99th percentile: 2.569573926925659
mean time: 1.9325271606445313
Pipeline stage StressChecker completed in 10.44s
zonemercy-cogent-nemo-v1_3266_v7 status is now deployed due to DeploymentManager action
zonemercy-cogent-nemo-v1_3266_v7 status is now inactive due to auto deactivation removed underperforming models
zonemercy-cogent-nemo-v1_3266_v7 status is now torndown due to DeploymentManager action