submission_id: zonemercy-cogent-nemo-v1_4327_v3
developer_uid: zonemercy
alignment_samples: 0
best_of: 8
celo_rating: 1259.27
display_name: zonemercy-cogent-nemo-v1_4327_v3
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}
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '###', 'Bot:', 'User:', 'You:', '<|im_end|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64, 'reward_max_token_input': 256}
is_internal_developer: True
language_model: zonemercy/Cogent-Nemo-v1-1k1e5-ep1
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: zonemercy/Cogent-Nemo-v1
model_name: zonemercy-cogent-nemo-v1_4327_v3
model_num_parameters: 12772070400.0
model_repo: zonemercy/Cogent-Nemo-v1-1k1e5-ep1
model_size: 13B
num_battles: 11120
num_wins: 6340
propriety_score: 0.7209302325581395
propriety_total_count: 989.0
ranking_group: single
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': '', 'prompt_template': '', '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: 2024-08-08T01:55:37+00:00
us_pacific_date: 2024-08-07
win_ratio: 0.5701438848920863
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name zonemercy-cogent-nemo-v1-4327-v3-mkmlizer
Waiting for job on zonemercy-cogent-nemo-v1-4327-v3-mkmlizer to finish
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: ║ _____ __ __ ║
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: ║ /___/ ║
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: ║ ║
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: ║ Version: 0.9.9 ║
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: ║ https://mk1.ai ║
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: ║ ║
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: ║ The license key for the current software has been verified as ║
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: ║ belonging to: ║
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: ║ ║
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: ║ Chai Research Corp. ║
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: ║ ║
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: Downloaded to shared memory in 65.530s
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp7kx_3e8u, device:0
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: quantized model in 41.608s
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: Processed model zonemercy/Cogent-Nemo-v1-1k1e5-ep1 in 107.139s
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: creating bucket guanaco-mkml-models
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zonemercy-cogent-nemo-v1-4327-v3
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zonemercy-cogent-nemo-v1-4327-v3/config.json
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zonemercy-cogent-nemo-v1-4327-v3/special_tokens_map.json
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zonemercy-cogent-nemo-v1-4327-v3/tokenizer_config.json
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zonemercy-cogent-nemo-v1-4327-v3/tokenizer.json
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zonemercy-cogent-nemo-v1-4327-v3/flywheel_model.0.safetensors
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:15, 22.87it/s] Loading 0: 3%|▎ | 10/363 [00:00<00:12, 28.40it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:13, 25.20it/s] Loading 0: 6%|▌ | 20/363 [00:00<00:10, 34.07it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:15, 22.53it/s] Loading 0: 7%|▋ | 27/363 [00:01<00:15, 21.95it/s] Loading 0: 9%|▊ | 31/363 [00:01<00:12, 25.56it/s] Loading 0: 10%|▉ | 35/363 [00:01<00:11, 27.37it/s] Loading 0: 11%|█ | 39/363 [00:01<00:11, 28.66it/s] Loading 0: 12%|█▏ | 43/363 [00:01<00:11, 27.81it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:10, 30.41it/s] Loading 0: 14%|█▍ | 52/363 [00:01<00:10, 29.19it/s] Loading 0: 15%|█▌ | 56/363 [00:02<00:10, 28.53it/s] Loading 0: 17%|█▋ | 61/363 [00:02<00:12, 23.72it/s] Loading 0: 18%|█▊ | 64/363 [00:02<00:13, 21.59it/s] Loading 0: 20%|█▉ | 71/363 [00:02<00:10, 28.24it/s] Loading 0: 21%|██ | 75/363 [00:02<00:10, 28.13it/s] Loading 0: 21%|██▏ | 78/363 [00:02<00:11, 25.58it/s] Loading 0: 23%|██▎ | 84/363 [00:03<00:09, 29.79it/s] Loading 0: 24%|██▍ | 88/363 [00:03<00:09, 28.65it/s] Loading 0: 26%|██▌ | 93/363 [00:03<00:08, 30.67it/s] Loading 0: 27%|██▋ | 97/363 [00:03<00:09, 29.15it/s] Loading 0: 28%|██▊ | 101/363 [00:03<00:11, 22.49it/s] Loading 0: 29%|██▊ | 104/363 [00:04<00:12, 20.38it/s] Loading 0: 31%|███ | 111/363 [00:04<00:09, 27.16it/s] Loading 0: 31%|███▏ | 114/363 [00:04<00:09, 25.45it/s] Loading 0: 33%|███▎ | 120/363 [00:04<00:08, 29.83it/s] Loading 0: 34%|███▍ | 124/363 [00:04<00:08, 29.12it/s] Loading 0: 36%|███▌ | 129/363 [00:04<00:07, 31.34it/s] Loading 0: 37%|███▋ | 133/363 [00:04<00:07, 29.83it/s] Loading 0: 38%|███▊ | 137/363 [00:05<00:07, 29.85it/s] Loading 0: 39%|███▉ | 142/363 [00:05<00:08, 25.17it/s] Loading 0: 40%|███▉ | 145/363 [00:05<00:09, 23.93it/s] Loading 0: 41%|████ | 149/363 [00:05<00:09, 23.10it/s] Loading 0: 43%|████▎ | 156/363 [00:05<00:07, 29.45it/s] Loading 0: 44%|████▍ | 160/363 [00:05<00:07, 28.74it/s] Loading 0: 45%|████▌ | 165/363 [00:06<00:06, 31.03it/s] Loading 0: 47%|████▋ | 169/363 [00:06<00:06, 29.51it/s] Loading 0: 48%|████▊ | 174/363 [00:06<00:05, 31.66it/s] Loading 0: 49%|████▉ | 178/363 [00:06<00:06, 29.48it/s] Loading 0: 50%|█████ | 182/363 [00:06<00:07, 23.60it/s] Loading 0: 51%|█████ | 185/363 [00:06<00:08, 21.37it/s] Loading 0: 53%|█████▎ | 191/363 [00:07<00:06, 28.67it/s] Loading 0: 54%|█████▎ | 195/363 [00:07<00:06, 26.16it/s] Loading 0: 55%|█████▌ | 201/363 [00:07<00:05, 30.58it/s] Loading 0: 56%|█████▋ | 205/363 [00:07<00:05, 29.32it/s] Loading 0: 58%|█████▊ | 210/363 [00:07<00:04, 31.44it/s] Loading 0: 59%|█████▉ | 214/363 [00:07<00:04, 30.00it/s] Loading 0: 60%|██████ | 218/363 [00:07<00:04, 29.37it/s] Loading 0: 61%|██████▏ | 223/363 [00:08<00:05, 25.09it/s] Loading 0: 62%|██████▏ | 226/363 [00:08<00:05, 24.20it/s] Loading 0: 63%|██████▎ | 230/363 [00:08<00:05, 23.12it/s] Loading 0: 65%|██████▍ | 235/363 [00:08<00:04, 28.12it/s] Loading 0: 66%|██████▌ | 239/363 [00:08<00:04, 25.54it/s] Loading 0: 68%|██████▊ | 246/363 [00:08<00:03, 31.78it/s] Loading 0: 69%|██████▉ | 250/363 [00:09<00:03, 30.36it/s] Loading 0: 70%|███████ | 255/363 [00:09<00:03, 32.38it/s] Loading 0: 71%|███████▏ | 259/363 [00:09<00:03, 30.76it/s] Loading 0: 72%|███████▏ | 263/363 [00:09<00:04, 23.80it/s] Loading 0: 73%|███████▎ | 266/363 [00:09<00:04, 21.58it/s] Loading 0: 75%|███████▌ | 273/363 [00:10<00:03, 28.31it/s] Loading 0: 76%|███████▋ | 277/363 [00:10<00:03, 27.27it/s] Loading 0: 78%|███████▊ | 282/363 [00:10<00:02, 28.87it/s] Loading 0: 79%|███████▉ | 286/363 [00:10<00:02, 27.82it/s] Loading 0: 80%|████████ | 291/363 [00:10<00:02, 29.93it/s] Loading 0: 81%|████████▏ | 295/363 [00:10<00:02, 27.77it/s] Loading 0: 82%|████████▏ | 299/363 [00:10<00:02, 28.18it/s] Loading 0: 84%|████████▎ | 304/363 [00:11<00:02, 24.41it/s] Loading 0: 85%|████████▍ | 307/363 [00:11<00:02, 23.69it/s] Loading 0: 86%|████████▌ | 311/363 [00:11<00:02, 22.78it/s] Loading 0: 88%|████████▊ | 318/363 [00:11<00:01, 29.22it/s] Loading 0: 89%|████████▊ | 322/363 [00:11<00:01, 28.21it/s] Loading 0: 90%|█████████ | 327/363 [00:11<00:01, 30.80it/s] Loading 0: 91%|█████████ | 331/363 [00:12<00:01, 29.95it/s] Loading 0: 93%|█████████▎| 336/363 [00:12<00:00, 32.13it/s] Loading 0: 94%|█████████▎| 340/363 [00:12<00:00, 30.80it/s] Loading 0: 95%|█████████▍| 344/363 [00:19<00:09, 1.95it/s] Loading 0: 96%|█████████▌| 348/363 [00:19<00:05, 2.63it/s] Loading 0: 97%|█████████▋| 353/363 [00:19<00:02, 3.81it/s] Loading 0: 98%|█████████▊| 357/363 [00:19<00:01, 4.95it/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-v1-4327-v3-mkmlizer: warnings.warn(
zonemercy-cogent-nemo-v1-4327-v3-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-v1-4327-v3-mkmlizer: warnings.warn(
zonemercy-cogent-nemo-v1-4327-v3-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-v1-4327-v3-mkmlizer: warnings.warn(
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:05<00:05, 5.67s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.04s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.29s/it]
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 2.30it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.85it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.50it/s]
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: Saving duration: 1.389s
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.587s
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: creating bucket guanaco-reward-models
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/zonemercy-cogent-nemo-v1-4327-v3_reward
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/zonemercy-cogent-nemo-v1-4327-v3_reward/config.json
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/zonemercy-cogent-nemo-v1-4327-v3_reward/special_tokens_map.json
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/zonemercy-cogent-nemo-v1-4327-v3_reward/tokenizer_config.json
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/zonemercy-cogent-nemo-v1-4327-v3_reward/merges.txt
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/zonemercy-cogent-nemo-v1-4327-v3_reward/vocab.json
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/zonemercy-cogent-nemo-v1-4327-v3_reward/tokenizer.json
zonemercy-cogent-nemo-v1-4327-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/zonemercy-cogent-nemo-v1-4327-v3_reward/reward.tensors
Job zonemercy-cogent-nemo-v1-4327-v3-mkmlizer completed after 156.28s with status: succeeded
Stopping job with name zonemercy-cogent-nemo-v1-4327-v3-mkmlizer
Pipeline stage MKMLizer completed in 157.46s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service zonemercy-cogent-nemo-v1-4327-v3
Waiting for inference service zonemercy-cogent-nemo-v1-4327-v3 to be ready
Inference service zonemercy-cogent-nemo-v1-4327-v3 ready after 191.19477152824402s
Pipeline stage ISVCDeployer completed in 192.87s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.476269245147705s
Received healthy response to inference request in 1.6206598281860352s
Received healthy response to inference request in 1.6790292263031006s
Received healthy response to inference request in 1.6754827499389648s
Received healthy response to inference request in 1.6404783725738525s
5 requests
0 failed requests
5th percentile: 1.6246235370635986
10th percentile: 1.628587245941162
20th percentile: 1.636514663696289
30th percentile: 1.647479248046875
40th percentile: 1.66148099899292
50th percentile: 1.6754827499389648
60th percentile: 1.6769013404846191
70th percentile: 1.6783199310302734
80th percentile: 1.8384772300720216
90th percentile: 2.157373237609863
95th percentile: 2.316821241378784
99th percentile: 2.444379644393921
mean time: 1.8183838844299316
Pipeline stage StressChecker completed in 9.76s
zonemercy-cogent-nemo-v1_4327_v3 status is now deployed due to DeploymentManager action
zonemercy-cogent-nemo-v1_4327_v3 status is now inactive due to auto deactivation removed underperforming models
zonemercy-cogent-nemo-v1_4327_v3 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics