submission_id: neversleep-noromaidxopen_6111_v4
developer_uid: Undi95
status: inactive
model_repo: NeverSleep/NoromaidxOpenGPT4-1
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
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}:'}
reward_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}:'}
timestamp: 2024-03-25T17:12:00+00:00
model_name: neversleep-noromaidxopen_6111_v4
model_eval_status: success
safety_score: 0.96
entertaining: 6.98
stay_in_character: 8.67
user_preference: 7.3
double_thumbs_up: 481
thumbs_up: 625
thumbs_down: 294
num_battles: 71887
num_wins: 37167
win_ratio: 0.5170197671345306
celo_rating: 1169.57
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-noromaidxopen-6111-v4-mkmlizer
Waiting for job on neversleep-noromaidxopen-6111-v4-mkmlizer to finish
neversleep-noromaidxopen-6111-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaidxopen-6111-v4-mkmlizer: ║ _____ __ __ ║
neversleep-noromaidxopen-6111-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-noromaidxopen-6111-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-noromaidxopen-6111-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-noromaidxopen-6111-v4-mkmlizer: ║ /___/ ║
neversleep-noromaidxopen-6111-v4-mkmlizer: ║ ║
neversleep-noromaidxopen-6111-v4-mkmlizer: ║ Version: 0.8.6 ║
neversleep-noromaidxopen-6111-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-noromaidxopen-6111-v4-mkmlizer: ║ ║
neversleep-noromaidxopen-6111-v4-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-noromaidxopen-6111-v4-mkmlizer: ║ belonging to: ║
neversleep-noromaidxopen-6111-v4-mkmlizer: ║ ║
neversleep-noromaidxopen-6111-v4-mkmlizer: ║ Chai Research Corp. ║
neversleep-noromaidxopen-6111-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-noromaidxopen-6111-v4-mkmlizer: ║ Expiration: 2024-04-15 23:59:59 ║
neversleep-noromaidxopen-6111-v4-mkmlizer: ║ ║
neversleep-noromaidxopen-6111-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaidxopen-6111-v4-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
neversleep-noromaidxopen-6111-v4-mkmlizer: warnings.warn(warning_message, FutureWarning)
neversleep-noromaidxopen-6111-v4-mkmlizer: Downloaded to shared memory in 123.220s
neversleep-noromaidxopen-6111-v4-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaidxopen-6111-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-noromaidxopen-6111-v4-mkmlizer: quantized model in 62.449s
neversleep-noromaidxopen-6111-v4-mkmlizer: Processed model NeverSleep/NoromaidxOpenGPT4-1 in 191.622s
neversleep-noromaidxopen-6111-v4-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaidxopen-6111-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaidxopen-6111-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaidxopen-6111-v4
neversleep-noromaidxopen-6111-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaidxopen-6111-v4/config.json
neversleep-noromaidxopen-6111-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaidxopen-6111-v4/special_tokens_map.json
neversleep-noromaidxopen-6111-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaidxopen-6111-v4/tokenizer_config.json
neversleep-noromaidxopen-6111-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaidxopen-6111-v4/tokenizer.json
neversleep-noromaidxopen-6111-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaidxopen-6111-v4/tokenizer.model
neversleep-noromaidxopen-6111-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaidxopen-6111-v4/flywheel_model.3.safetensors
neversleep-noromaidxopen-6111-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaidxopen-6111-v4/flywheel_model.0.safetensors
neversleep-noromaidxopen-6111-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaidxopen-6111-v4/flywheel_model.2.safetensors
neversleep-noromaidxopen-6111-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaidxopen-6111-v4/flywheel_model.1.safetensors
neversleep-noromaidxopen-6111-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
neversleep-noromaidxopen-6111-v4-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 1%| | 7/995 [00:00<00:14, 66.74it/s] Loading 0: 1%|▏ | 14/995 [00:00<00:14, 65.71it/s] Loading 0: 2%|▏ | 21/995 [00:00<00:14, 65.15it/s] Loading 0: 3%|▎ | 34/995 [00:00<00:10, 87.66it/s] Loading 0: 4%|▍ | 43/995 [00:00<00:12, 77.91it/s] Loading 0: 5%|▌ | 51/995 [00:00<00:12, 73.06it/s] Loading 0: 6%|▋ | 64/995 [00:00<00:10, 88.46it/s] Loading 0: 7%|▋ | 74/995 [00:00<00:11, 79.40it/s] Loading 0: 8%|▊ | 83/995 [00:01<00:12, 73.95it/s] Loading 0: 10%|▉ | 96/995 [00:01<00:10, 86.87it/s] Loading 0: 11%|█▏ | 112/995 [00:01<00:08, 105.77it/s] Loading 0: 12%|█▏ | 124/995 [00:02<00:23, 37.30it/s] Loading 0: 13%|█▎ | 133/995 [00:02<00:20, 43.09it/s] Loading 0: 14%|█▍ | 142/995 [00:02<00:18, 46.86it/s] Loading 0: 15%|█▌ | 150/995 [00:02<00:16, 50.09it/s] Loading 0: 16%|█▋ | 162/995 [00:02<00:13, 62.26it/s] Loading 0: 17%|█▋ | 171/995 [00:02<00:13, 63.07it/s] Loading 0: 18%|█▊ | 179/995 [00:02<00:12, 62.87it/s] Loading 0: 19%|█▉ | 188/995 [00:02<00:11, 67.86it/s] Loading 0: 20%|█▉ | 196/995 [00:03<00:12, 66.19it/s] Loading 0: 21%|██ | 204/995 [00:03<00:11, 66.02it/s] Loading 0: 21%|██▏ | 212/995 [00:03<00:23, 33.84it/s] Loading 0: 23%|██▎ | 224/995 [00:03<00:16, 46.17it/s] Loading 0: 23%|██▎ | 233/995 [00:03<00:14, 53.06it/s] Loading 0: 24%|██▍ | 241/995 [00:04<00:13, 55.83it/s] Loading 0: 25%|██▌ | 249/995 [00:04<00:12, 57.99it/s] Loading 0: 26%|██▋ | 262/995 [00:04<00:09, 73.45it/s] Loading 0: 27%|██▋ | 271/995 [00:04<00:10, 69.97it/s] Loading 0: 28%|██▊ | 279/995 [00:04<00:10, 68.61it/s] Loading 0: 29%|██▉ | 287/995 [00:16<05:04, 2.32it/s] Loading 0: 30%|██▉ | 296/995 [00:17<03:31, 3.30it/s] Loading 0: 31%|███ | 304/995 [00:17<02:34, 4.49it/s] Loading 0: 31%|███▏ | 312/995 [00:17<01:51, 6.10it/s] Loading 0: 32%|███▏ | 322/995 [00:18<01:31, 7.39it/s] Loading 0: 33%|███▎ | 329/995 [00:18<01:09, 9.52it/s] Loading 0: 34%|███▍ | 336/995 [00:18<00:53, 12.30it/s] Loading 0: 35%|███▍ | 345/995 [00:18<00:38, 17.07it/s] Loading 0: 35%|███▌ | 352/995 [00:18<00:30, 21.27it/s] Loading 0: 36%|███▌ | 359/995 [00:18<00:24, 26.15it/s] Loading 0: 37%|███▋ | 366/995 [00:18<00:19, 31.51it/s] Loading 0: 38%|███▊ | 378/995 [00:18<00:13, 44.98it/s] Loading 0: 39%|███▉ | 387/995 [00:18<00:12, 49.70it/s] Loading 0: 40%|███▉ | 395/995 [00:19<00:11, 52.72it/s] Loading 0: 41%|████ | 408/995 [00:19<00:08, 68.47it/s] Loading 0: 42%|████▏ | 417/995 [00:19<00:08, 67.70it/s] Loading 0: 43%|████▎ | 426/995 [00:19<00:15, 36.61it/s] Loading 0: 44%|████▎ | 433/995 [00:19<00:13, 40.92it/s] Loading 0: 44%|████▍ | 442/995 [00:20<00:11, 48.62it/s] Loading 0: 45%|████▌ | 449/995 [00:20<00:10, 52.20it/s] Loading 0: 46%|████▌ | 456/995 [00:20<00:09, 55.30it/s] Loading 0: 47%|████▋ | 468/995 [00:20<00:07, 69.99it/s] Loading 0: 48%|████▊ | 477/995 [00:20<00:07, 71.22it/s] Loading 0: 49%|████▉ | 486/995 [00:20<00:07, 69.53it/s] Loading 0: 50%|█████ | 498/995 [00:20<00:06, 81.42it/s] Loading 0: 51%|█████ | 507/995 [00:20<00:06, 75.46it/s] Loading 0: 52%|█████▏ | 516/995 [00:21<00:06, 72.54it/s] Loading 0: 53%|█████▎ | 527/995 [00:21<00:05, 81.13it/s] Loading 0: 54%|█████▍ | 536/995 [00:21<00:12, 37.43it/s] Loading 0: 55%|█████▍ | 543/995 [00:21<00:10, 41.58it/s] Loading 0: 55%|█████▌ | 550/995 [00:21<00:09, 45.71it/s] Loading 0: 56%|█████▌ | 555/995 [00:33<00:09, 45.71it/s] Loading 0: 56%|█████▌ | 556/995 [00:33<03:34, 2.04it/s] Loading 0: 57%|█████▋ | 569/995 [00:33<02:01, 3.50it/s] Loading 0: 58%|█████▊ | 578/995 [00:34<01:26, 4.85it/s] Loading 0: 59%|█████▉ | 589/995 [00:34<00:56, 7.17it/s] Loading 0: 60%|██████ | 598/995 [00:34<00:41, 9.65it/s] Loading 0: 61%|██████ | 607/995 [00:34<00:30, 12.75it/s] Loading 0: 62%|██████▏ | 615/995 [00:34<00:23, 16.38it/s] Loading 0: 63%|██████▎ | 627/995 [00:34<00:15, 23.88it/s] Loading 0: 65%|██████▍ | 642/995 [00:34<00:09, 35.73it/s] Loading 0: 66%|██████▌ | 653/995 [00:35<00:13, 25.93it/s] Loading 0: 67%|██████▋ | 662/995 [00:35<00:10, 31.34it/s] Loading 0: 67%|██████▋ | 670/995 [00:35<00:09, 35.75it/s] Loading 0: 68%|██████▊ | 678/995 [00:35<00:07, 39.94it/s] Loading 0: 69%|██████▉ | 689/995 [00:35<00:06, 50.54it/s] Loading 0: 70%|███████ | 698/995 [00:36<00:05, 55.10it/s] Loading 0: 71%|███████ | 706/995 [00:36<00:05, 57.12it/s] Loading 0: 72%|███████▏ | 715/995 [00:36<00:04, 62.81it/s] Loading 0: 73%|███████▎ | 723/995 [00:36<00:04, 62.38it/s] Loading 0: 73%|███████▎ | 731/995 [00:36<00:04, 62.83it/s] Loading 0: 75%|███████▍ | 743/995 [00:37<00:07, 35.42it/s] Loading 0: 76%|███████▌ | 753/995 [00:37<00:05, 43.47it/s] Loading 0: 76%|███████▋ | 761/995 [00:37<00:04, 48.44it/s] Loading 0: 77%|███████▋ | 768/995 [00:37<00:04, 51.69it/s] Loading 0: 79%|███████▊ | 782/995 [00:37<00:03, 68.40it/s] Loading 0: 79%|███████▉ | 791/995 [00:37<00:02, 68.97it/s] Loading 0: 80%|████████ | 800/995 [00:37<00:02, 69.52it/s] Loading 0: 82%|████████▏ | 813/995 [00:38<00:02, 81.85it/s] Loading 0: 83%|████████▎ | 822/995 [00:38<00:02, 78.42it/s] Loading 0: 84%|████████▎ | 831/995 [00:38<00:02, 76.18it/s] Loading 0: 85%|████████▍ | 841/995 [00:50<00:02, 76.18it/s] Loading 0: 85%|████████▍ | 842/995 [00:50<00:54, 2.79it/s] Loading 0: 86%|████████▌ | 853/995 [00:51<00:42, 3.34it/s] Loading 0: 86%|████████▋ | 860/995 [00:52<00:31, 4.24it/s] Loading 0: 87%|████████▋ | 867/995 [00:52<00:23, 5.49it/s] Loading 0: 88%|████████▊ | 877/995 [00:52<00:14, 7.96it/s] Loading 0: 89%|████████▉ | 885/995 [00:52<00:10, 10.50it/s] Loading 0: 90%|████████▉ | 893/995 [00:52<00:07, 13.81it/s] Loading 0: 91%|█████████ | 906/995 [00:52<00:04, 21.23it/s] Loading 0: 92%|█████████▏| 915/995 [00:52<00:03, 26.42it/s] Loading 0: 93%|█████████▎| 924/995 [00:52<00:02, 31.97it/s] Loading 0: 94%|█████████▍| 937/995 [00:53<00:01, 44.37it/s] Loading 0: 95%|█████████▌| 947/995 [00:53<00:00, 49.01it/s] Loading 0: 96%|█████████▌| 956/995 [00:53<00:01, 31.78it/s] Loading 0: 97%|█████████▋| 963/995 [00:53<00:00, 35.73it/s] Loading 0: 98%|█████████▊| 972/995 [00:53<00:00, 42.77it/s] Loading 0: 98%|█████████▊| 979/995 [00:54<00:00, 46.61it/s] Loading 0: 99%|█████████▉| 986/995 [00:54<00:00, 50.09it/s] /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:1096: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
neversleep-noromaidxopen-6111-v4-mkmlizer: warnings.warn(
Retrying (%r) after connection broken by '%r': %s
neversleep-noromaidxopen-6111-v4-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:466: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
neversleep-noromaidxopen-6111-v4-mkmlizer: warnings.warn(
neversleep-noromaidxopen-6111-v4-mkmlizer: /opt/conda/lib/python3.10/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
neversleep-noromaidxopen-6111-v4-mkmlizer: return self.fget.__get__(instance, owner)()
neversleep-noromaidxopen-6111-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaidxopen-6111-v4-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaidxopen-6111-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaidxopen-6111-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaidxopen-6111-v4_reward
neversleep-noromaidxopen-6111-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaidxopen-6111-v4_reward/config.json
neversleep-noromaidxopen-6111-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaidxopen-6111-v4_reward/special_tokens_map.json
neversleep-noromaidxopen-6111-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaidxopen-6111-v4_reward/tokenizer_config.json
neversleep-noromaidxopen-6111-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaidxopen-6111-v4_reward/merges.txt
neversleep-noromaidxopen-6111-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaidxopen-6111-v4_reward/vocab.json
neversleep-noromaidxopen-6111-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaidxopen-6111-v4_reward/tokenizer.json
neversleep-noromaidxopen-6111-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaidxopen-6111-v4_reward/reward.tensors
Job neversleep-noromaidxopen-6111-v4-mkmlizer completed after 242.28s with status: succeeded
Stopping job with name neversleep-noromaidxopen-6111-v4-mkmlizer
Pipeline stage MKMLizer completed in 247.61s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.14s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaidxopen-6111-v4
Waiting for inference service neversleep-noromaidxopen-6111-v4 to be ready
Inference service neversleep-noromaidxopen-6111-v4 ready after 50.320409059524536s
Pipeline stage ISVCDeployer completed in 58.08s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5807087421417236s
Received healthy response to inference request in 2.1845862865448s
Received healthy response to inference request in 2.585209608078003s
Received healthy response to inference request in 2.5058364868164062s
Received healthy response to inference request in 2.7238829135894775s
5 requests
0 failed requests
5th percentile: 2.248836326599121
10th percentile: 2.3130863666534425
20th percentile: 2.441586446762085
30th percentile: 2.52081093788147
40th percentile: 2.5507598400115965
50th percentile: 2.5807087421417236
60th percentile: 2.582509088516235
70th percentile: 2.584309434890747
80th percentile: 2.6129442691802978
90th percentile: 2.668413591384888
95th percentile: 2.6961482524871827
99th percentile: 2.7183359813690187
mean time: 2.516044807434082
Pipeline stage StressChecker completed in 13.32s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.06s
M-Eval Dataset for topic stay_in_character is loaded
neversleep-noromaidxopen_6111_v4 status is now deployed due to DeploymentManager action
neversleep-noromaidxopen_6111_v4 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics