submission_id: neversleep-noromaid-v0_8068_v130
developer_uid: robert_irvine
status: inactive
model_repo: NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3
reward_repo: ChaiML/gpt2_medium_pairwise_60m_step_937500
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 50, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['</s>', '<|user|>', '###', '\n'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': '<s>[INST] This is an entertaining conversation. You are {bot_name} who has the persona: {memory}.\nPlay the role of {bot_name}. Engage in a chat with {user_name} while staying in character. You should create a fun dialogue which entertains {user_name}.\n', 'prompt_template': '{prompt}\n', 'bot_template': '{bot_name}: {message}</s>', 'user_template': '[INST] {user_name}: {message} [/INST]', 'response_template': '[INST] respond with humor [/INST]{bot_name}:', 'truncate_by_message': False}
reward_formatter: {'memory_template': '""', 'prompt_template': '""', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', 'truncate_by_message': False}
timestamp: 2024-07-11T20:11:23+00:00
model_name: neversleep-noromaid-v0_8068_v130
model_group: NeverSleep/Noromaid-v0.1
num_battles: 35715
num_wins: 14665
celo_rating: 1132.56
propriety_score: 0.7211824383417876
propriety_total_count: 5717.0
submission_type: basic
model_architecture: MixtralForCausalLM
model_num_parameters: 46702792704.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: neversleep-noromaid-v0_8068_v130
ineligible_reason: None
language_model: NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3
model_size: 47B
reward_model: ChaiML/gpt2_medium_pairwise_60m_step_937500
us_pacific_date: 2024-07-11
win_ratio: 0.41061178776424473
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v130-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v130-mkmlizer to finish
neversleep-noromaid-v0-8068-v130-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v130-mkmlizer: ║ _____ __ __ ║
neversleep-noromaid-v0-8068-v130-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-noromaid-v0-8068-v130-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-noromaid-v0-8068-v130-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-noromaid-v0-8068-v130-mkmlizer: ║ /___/ ║
neversleep-noromaid-v0-8068-v130-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v130-mkmlizer: ║ Version: 0.8.14 ║
neversleep-noromaid-v0-8068-v130-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-noromaid-v0-8068-v130-mkmlizer: ║ https://mk1.ai ║
neversleep-noromaid-v0-8068-v130-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v130-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-noromaid-v0-8068-v130-mkmlizer: ║ belonging to: ║
neversleep-noromaid-v0-8068-v130-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v130-mkmlizer: ║ Chai Research Corp. ║
neversleep-noromaid-v0-8068-v130-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-noromaid-v0-8068-v130-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
neversleep-noromaid-v0-8068-v130-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v130-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v130-mkmlizer: Downloaded to shared memory in 94.070s
neversleep-noromaid-v0-8068-v130-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v130-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-noromaid-v0-8068-v130-mkmlizer: quantized model in 233.628s
neversleep-noromaid-v0-8068-v130-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 327.698s
neversleep-noromaid-v0-8068-v130-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v130-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v130-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v130
neversleep-noromaid-v0-8068-v130-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v130/tokenizer_config.json
neversleep-noromaid-v0-8068-v130-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v130/special_tokens_map.json
neversleep-noromaid-v0-8068-v130-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v130/config.json
neversleep-noromaid-v0-8068-v130-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v130/tokenizer.model
neversleep-noromaid-v0-8068-v130-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v130/tokenizer.json
neversleep-noromaid-v0-8068-v130-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v130/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v130-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v130/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v130-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v130/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v130-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v130/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v130-mkmlizer: loading reward model from ChaiML/gpt2_medium_pairwise_60m_step_937500
neversleep-noromaid-v0-8068-v130-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 5%|▌ | 52/995 [00:11<03:20, 4.70it/s] Loading 0: 11%|█ | 107/995 [00:15<01:59, 7.43it/s] Loading 0: 16%|█▋ | 162/995 [00:16<01:06, 12.51it/s] Loading 0: 21%|██ | 210/995 [00:17<00:45, 17.32it/s] Loading 0: 27%|██▋ | 265/995 [00:18<00:30, 23.65it/s] Loading 0: 28%|██▊ | 277/995 [00:30<00:30, 23.65it/s] Loading 0: 28%|██▊ | 278/995 [00:30<01:43, 6.93it/s] Loading 0: 32%|███▏ | 320/995 [00:32<01:14, 9.10it/s] Loading 0: 37%|███▋ | 368/995 [00:33<00:49, 12.69it/s] Loading 0: 43%|████▎ | 423/995 [00:34<00:32, 17.77it/s] Loading 0: 48%|████▊ | 478/995 [00:35<00:22, 23.31it/s] Loading 0: 53%|█████▎ | 526/995 [00:36<00:17, 27.47it/s] Loading 0: 57%|█████▋ | 564/995 [00:47<00:15, 27.47it/s] Loading 0: 57%|█████▋ | 565/995 [00:47<00:42, 10.03it/s] Loading 0: 58%|█████▊ | 581/995 [00:52<00:51, 8.09it/s] Loading 0: 64%|██████▍ | 636/995 [00:55<00:36, 9.92it/s] Loading 0: 69%|██████▉ | 691/995 [01:06<00:41, 7.37it/s] Loading 0: 74%|███████▍ | 739/995 [01:15<00:39, 6.55it/s] Loading 0: 80%|███████▉ | 794/995 [01:17<00:22, 9.13it/s] Loading 0: 85%|████████▌ | 846/995 [01:27<00:20, 7.16it/s] Loading 0: 85%|████████▌ | 849/995 [01:30<00:23, 6.21it/s] Loading 0: 90%|█████████ | 897/995 [01:33<00:12, 8.12it/s] Loading 0: 96%|█████████▌| 952/995 [01:49<00:08, 5.30it/s] Loading 0: 100%|██████████| 995/995 [01:51<00:00, 7.05it/s] /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
neversleep-noromaid-v0-8068-v130-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v130-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
neversleep-noromaid-v0-8068-v130-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v130-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
neversleep-noromaid-v0-8068-v130-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v130-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:468: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
neversleep-noromaid-v0-8068-v130-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v130-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v130-mkmlizer: Saving duration: 0.332s
neversleep-noromaid-v0-8068-v130-mkmlizer: Processed model ChaiML/gpt2_medium_pairwise_60m_step_937500 in 7.388s
neversleep-noromaid-v0-8068-v130-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v130-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v130-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v130_reward
neversleep-noromaid-v0-8068-v130-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v130_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v130-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v130_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v130-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v130_reward/vocab.json
neversleep-noromaid-v0-8068-v130-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v130_reward/merges.txt
neversleep-noromaid-v0-8068-v130-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v130_reward/config.json
neversleep-noromaid-v0-8068-v130-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v130_reward/tokenizer.json
neversleep-noromaid-v0-8068-v130-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v130_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v130-mkmlizer completed after 466.04s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v130-mkmlizer
Pipeline stage MKMLizer completed in 467.06s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v130
Waiting for inference service neversleep-noromaid-v0-8068-v130 to be ready
Connection pool is full, discarding connection: %s
Inference service neversleep-noromaid-v0-8068-v130 ready after 70.61428904533386s
Pipeline stage ISVCDeployer completed in 77.85s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.385435104370117s
Received healthy response to inference request in 2.264662265777588s
Received healthy response to inference request in 2.416304588317871s
Received healthy response to inference request in 2.355363130569458s
Received healthy response to inference request in 2.2545554637908936s
5 requests
0 failed requests
5th percentile: 2.2565768241882322
10th percentile: 2.2585981845855714
20th percentile: 2.262640905380249
30th percentile: 2.282802438735962
40th percentile: 2.31908278465271
50th percentile: 2.355363130569458
60th percentile: 2.3797397136688234
70th percentile: 2.4041162967681884
80th percentile: 2.6101306915283207
90th percentile: 2.997782897949219
95th percentile: 3.1916090011596676
99th percentile: 3.346669883728027
mean time: 2.5352641105651856
Pipeline stage StressChecker completed in 13.38s
neversleep-noromaid-v0_8068_v130 status is now deployed due to DeploymentManager action
neversleep-noromaid-v0_8068_v130 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics