submission_id: zonemercy-cogent-nemo-v1_4327_v4
developer_uid: zonemercy
alignment_samples: 11538
alignment_score: 6.239401452912152
best_of: 8
celo_rating: 1256.9
display_name: zonemercy-cogent-nemo-v1_4327_v4
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': 0.05, '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_v4
model_num_parameters: 12772070400.0
model_repo: zonemercy/Cogent-Nemo-v1-1k1e5-ep1
model_size: 13B
num_battles: 11538
num_wins: 6275
propriety_score: 0.6968541468064824
propriety_total_count: 1049.0
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: 2024-08-10T22:51:46+00:00
us_pacific_date: 2024-08-10
win_ratio: 0.5438550875368348
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name zonemercy-cogent-nemo-v1-4327-v4-mkmlizer
Waiting for job on zonemercy-cogent-nemo-v1-4327-v4-mkmlizer to finish
Stopping job with name zonemercy-cogent-nemo-v1-4327-v4-mkmlizer
%s, retrying in %s seconds...
Starting job with name zonemercy-cogent-nemo-v1-4327-v4-mkmlizer
Waiting for job on zonemercy-cogent-nemo-v1-4327-v4-mkmlizer to finish
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: ║ _____ __ __ ║
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: ║ /___/ ║
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: ║ ║
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: ║ Version: 0.9.9 ║
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: ║ https://mk1.ai ║
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: ║ ║
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: ║ The license key for the current software has been verified as ║
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: ║ belonging to: ║
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: ║ ║
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: ║ Chai Research Corp. ║
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: ║ ║
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: Downloaded to shared memory in 69.737s
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp0mpfzojv, device:0
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: quantized model in 40.186s
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: Processed model zonemercy/Cogent-Nemo-v1-1k1e5-ep1 in 109.924s
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: creating bucket guanaco-mkml-models
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zonemercy-cogent-nemo-v1-4327-v4
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zonemercy-cogent-nemo-v1-4327-v4/special_tokens_map.json
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zonemercy-cogent-nemo-v1-4327-v4/config.json
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zonemercy-cogent-nemo-v1-4327-v4/tokenizer_config.json
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zonemercy-cogent-nemo-v1-4327-v4/tokenizer.json
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zonemercy-cogent-nemo-v1-4327-v4/flywheel_model.0.safetensors
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:14, 24.04it/s] Loading 0: 3%|▎ | 10/363 [00:00<00:11, 30.80it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:13, 26.72it/s] Loading 0: 6%|▌ | 21/363 [00:00<00:08, 38.04it/s] Loading 0: 7%|▋ | 26/363 [00:01<00:14, 22.72it/s] Loading 0: 9%|▊ | 31/363 [00:01<00:12, 27.36it/s] Loading 0: 10%|▉ | 35/363 [00:01<00:11, 28.65it/s] Loading 0: 11%|█ | 39/363 [00:01<00:10, 29.93it/s] Loading 0: 12%|█▏ | 43/363 [00:01<00:11, 28.83it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:10, 31.42it/s] Loading 0: 14%|█▍ | 52/363 [00:01<00:10, 28.72it/s] Loading 0: 15%|█▌ | 56/363 [00:01<00:10, 28.91it/s] Loading 0: 17%|█▋ | 61/363 [00:02<00:11, 25.33it/s] Loading 0: 18%|█▊ | 64/363 [00:02<00:13, 22.37it/s] Loading 0: 20%|█▉ | 71/363 [00:02<00:09, 29.59it/s] Loading 0: 21%|██ | 75/363 [00:02<00:09, 29.48it/s] Loading 0: 22%|██▏ | 79/363 [00:02<00:09, 28.46it/s] Loading 0: 23%|██▎ | 84/363 [00:02<00:09, 30.44it/s] Loading 0: 24%|██▍ | 88/363 [00:03<00:09, 29.35it/s] Loading 0: 26%|██▌ | 93/363 [00:03<00:08, 31.79it/s] Loading 0: 27%|██▋ | 97/363 [00:03<00:08, 30.39it/s] Loading 0: 28%|██▊ | 101/363 [00:03<00:10, 24.84it/s] Loading 0: 29%|██▊ | 104/363 [00:03<00:11, 22.06it/s] Loading 0: 31%|███ | 111/363 [00:03<00:08, 29.38it/s] Loading 0: 32%|███▏ | 115/363 [00:04<00:08, 28.65it/s] Loading 0: 33%|███▎ | 120/363 [00:04<00:08, 30.12it/s] Loading 0: 34%|███▍ | 124/363 [00:04<00:08, 29.02it/s] Loading 0: 36%|███▌ | 129/363 [00:04<00:07, 31.77it/s] Loading 0: 37%|███▋ | 133/363 [00:04<00:07, 30.26it/s] Loading 0: 38%|███▊ | 137/363 [00:04<00:07, 30.50it/s] Loading 0: 39%|███▉ | 142/363 [00:05<00:08, 26.36it/s] Loading 0: 40%|███▉ | 145/363 [00:05<00:08, 24.38it/s] Loading 0: 41%|████ | 149/363 [00:05<00:09, 23.12it/s] Loading 0: 43%|████▎ | 156/363 [00:05<00:07, 29.49it/s] Loading 0: 44%|████▍ | 160/363 [00:05<00:07, 28.38it/s] Loading 0: 45%|████▌ | 165/363 [00:05<00:06, 30.91it/s] Loading 0: 47%|████▋ | 169/363 [00:05<00:06, 30.02it/s] Loading 0: 48%|████▊ | 174/363 [00:06<00:05, 32.25it/s] Loading 0: 49%|████▉ | 178/363 [00:06<00:06, 30.37it/s] Loading 0: 50%|█████ | 182/363 [00:06<00:07, 25.07it/s] Loading 0: 51%|█████ | 185/363 [00:06<00:08, 21.94it/s] Loading 0: 52%|█████▏ | 190/363 [00:06<00:06, 27.22it/s] Loading 0: 53%|█████▎ | 194/363 [00:06<00:06, 24.49it/s] Loading 0: 55%|█████▍ | 199/363 [00:07<00:05, 28.70it/s] Loading 0: 56%|█████▌ | 203/363 [00:07<00:06, 25.84it/s] Loading 0: 58%|█████▊ | 210/363 [00:07<00:04, 32.36it/s] Loading 0: 59%|█████▉ | 214/363 [00:07<00:04, 30.57it/s] Loading 0: 60%|██████ | 218/363 [00:07<00:04, 31.07it/s] Loading 0: 61%|██████▏ | 223/363 [00:07<00:05, 26.80it/s] Loading 0: 62%|██████▏ | 226/363 [00:08<00:05, 25.08it/s] Loading 0: 63%|██████▎ | 230/363 [00:08<00:05, 24.03it/s] Loading 0: 65%|██████▌ | 237/363 [00:08<00:04, 30.57it/s] Loading 0: 66%|██████▋ | 241/363 [00:08<00:04, 29.58it/s] Loading 0: 68%|██████▊ | 246/363 [00:08<00:03, 32.26it/s] Loading 0: 69%|██████▉ | 250/363 [00:08<00:03, 30.62it/s] Loading 0: 70%|███████ | 255/363 [00:08<00:03, 32.94it/s] Loading 0: 71%|███████▏ | 259/363 [00:09<00:03, 31.22it/s] Loading 0: 72%|███████▏ | 263/363 [00:09<00:03, 25.32it/s] Loading 0: 73%|███████▎ | 266/363 [00:09<00:04, 22.08it/s] Loading 0: 75%|███████▌ | 273/363 [00:09<00:03, 29.24it/s] Loading 0: 76%|███████▋ | 277/363 [00:09<00:03, 28.35it/s] Loading 0: 78%|███████▊ | 282/363 [00:09<00:02, 30.80it/s] Loading 0: 79%|███████▉ | 286/363 [00:10<00:02, 29.50it/s] Loading 0: 80%|████████ | 291/363 [00:10<00:02, 31.80it/s] Loading 0: 81%|████████▏ | 295/363 [00:10<00:02, 30.05it/s] Loading 0: 82%|████████▏ | 299/363 [00:10<00:02, 28.52it/s] Loading 0: 84%|████████▎ | 304/363 [00:10<00:02, 24.46it/s] Loading 0: 85%|████████▍ | 307/363 [00:10<00:02, 23.57it/s] Loading 0: 86%|████████▌ | 311/363 [00:11<00:02, 22.54it/s] Loading 0: 88%|████████▊ | 318/363 [00:11<00:01, 29.39it/s] Loading 0: 89%|████████▊ | 322/363 [00:11<00:01, 28.68it/s] Loading 0: 90%|█████████ | 327/363 [00:11<00:01, 30.85it/s] Loading 0: 91%|█████████ | 331/363 [00:11<00:01, 29.38it/s] Loading 0: 93%|█████████▎| 336/363 [00:11<00:00, 31.18it/s] Loading 0: 94%|█████████▎| 340/363 [00:12<00:00, 30.08it/s] Loading 0: 95%|█████████▍| 344/363 [00:18<00:09, 1.98it/s] Loading 0: 96%|█████████▌| 348/363 [00:19<00:05, 2.67it/s] Loading 0: 97%|█████████▋| 353/363 [00:19<00:02, 3.87it/s] Loading 0: 98%|█████████▊| 357/363 [00:19<00:01, 5.03it/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-v4-mkmlizer: warnings.warn(
zonemercy-cogent-nemo-v1-4327-v4-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-v4-mkmlizer: warnings.warn(
zonemercy-cogent-nemo-v1-4327-v4-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-v4-mkmlizer: warnings.warn(
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:05<00:05, 5.35s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 3.88s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.10s/it]
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 2.27it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.81it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.46it/s]
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: Saving duration: 1.374s
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 12.989s
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: creating bucket guanaco-reward-models
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/zonemercy-cogent-nemo-v1-4327-v4_reward
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/zonemercy-cogent-nemo-v1-4327-v4_reward/special_tokens_map.json
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/zonemercy-cogent-nemo-v1-4327-v4_reward/tokenizer_config.json
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/zonemercy-cogent-nemo-v1-4327-v4_reward/config.json
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/zonemercy-cogent-nemo-v1-4327-v4_reward/merges.txt
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/zonemercy-cogent-nemo-v1-4327-v4_reward/vocab.json
zonemercy-cogent-nemo-v1-4327-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/zonemercy-cogent-nemo-v1-4327-v4_reward/tokenizer.json
Job zonemercy-cogent-nemo-v1-4327-v4-mkmlizer completed after 156.95s with status: succeeded
Stopping job with name zonemercy-cogent-nemo-v1-4327-v4-mkmlizer
Pipeline stage MKMLizer completed in 158.66s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service zonemercy-cogent-nemo-v1-4327-v4
Waiting for inference service zonemercy-cogent-nemo-v1-4327-v4 to be ready
Inference service zonemercy-cogent-nemo-v1-4327-v4 ready after 201.28758192062378s
Pipeline stage ISVCDeployer completed in 203.14s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.448512554168701s
Received healthy response to inference request in 1.655479907989502s
Received healthy response to inference request in 1.6706464290618896s
Received healthy response to inference request in 1.6840627193450928s
Received healthy response to inference request in 1.6886553764343262s
5 requests
0 failed requests
5th percentile: 1.6585132122039794
10th percentile: 1.661546516418457
20th percentile: 1.6676131248474122
30th percentile: 1.6733296871185304
40th percentile: 1.6786962032318116
50th percentile: 1.6840627193450928
60th percentile: 1.6858997821807862
70th percentile: 1.6877368450164796
80th percentile: 1.8406268119812013
90th percentile: 2.144569683074951
95th percentile: 2.296541118621826
99th percentile: 2.418118267059326
mean time: 1.8294713973999024
Pipeline stage StressChecker completed in 10.21s
zonemercy-cogent-nemo-v1_4327_v4 status is now deployed due to DeploymentManager action
zonemercy-cogent-nemo-v1_4327_v4 status is now inactive due to auto deactivation removed underperforming models
zonemercy-cogent-nemo-v1_4327_v4 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics