submission_id: neversleep-noromaid-v0_8068_v121
developer_uid: robert_irvine
status: inactive
model_repo: NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
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: 2024-07-10T18:13:46+00:00
model_name: neversleep-noromaid-v0_8068_v121
model_group: NeverSleep/Noromaid-v0.1
num_battles: 31728
num_wins: 14267
celo_rating: 1138.47
alignment_score: None
alignment_samples: 0
propriety_score: 0.7308049823387247
propriety_total_count: 5379.0
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_v121
ineligible_reason: None
language_model: NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3
model_size: 47B
reward_model: ChaiML/gpt2_xl_pairwise_89m_step_347634
us_pacific_date: 2024-07-10
win_ratio: 0.44966591023701463
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v121-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v121-mkmlizer to finish
neversleep-noromaid-v0-8068-v121-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v121-mkmlizer: ║ _____ __ __ ║
neversleep-noromaid-v0-8068-v121-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-noromaid-v0-8068-v121-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-noromaid-v0-8068-v121-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-noromaid-v0-8068-v121-mkmlizer: ║ /___/ ║
neversleep-noromaid-v0-8068-v121-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v121-mkmlizer: ║ Version: 0.8.14 ║
neversleep-noromaid-v0-8068-v121-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-noromaid-v0-8068-v121-mkmlizer: ║ https://mk1.ai ║
neversleep-noromaid-v0-8068-v121-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v121-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-noromaid-v0-8068-v121-mkmlizer: ║ belonging to: ║
neversleep-noromaid-v0-8068-v121-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v121-mkmlizer: ║ Chai Research Corp. ║
neversleep-noromaid-v0-8068-v121-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-noromaid-v0-8068-v121-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
neversleep-noromaid-v0-8068-v121-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v121-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v121-mkmlizer: Downloaded to shared memory in 114.406s
neversleep-noromaid-v0-8068-v121-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v121-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-noromaid-v0-8068-v121-mkmlizer: quantized model in 80.543s
neversleep-noromaid-v0-8068-v121-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 194.949s
neversleep-noromaid-v0-8068-v121-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v121-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v121-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v121
neversleep-noromaid-v0-8068-v121-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v121/config.json
neversleep-noromaid-v0-8068-v121-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v121/tokenizer_config.json
neversleep-noromaid-v0-8068-v121-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v121/special_tokens_map.json
neversleep-noromaid-v0-8068-v121-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v121/tokenizer.model
neversleep-noromaid-v0-8068-v121-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v121/tokenizer.json
neversleep-noromaid-v0-8068-v121-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v121/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v121-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v121/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v121-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v121/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v121-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v121/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v121-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
neversleep-noromaid-v0-8068-v121-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 5%|▌ | 52/995 [00:01<00:20, 44.94it/s] Loading 0: 11%|█ | 107/995 [00:02<00:18, 48.62it/s] Loading 0: 16%|█▋ | 162/995 [00:03<00:16, 51.12it/s] Loading 0: 21%|██ | 210/995 [00:04<00:15, 49.61it/s] Loading 0: 27%|██▋ | 265/995 [00:05<00:14, 51.20it/s] Loading 0: 28%|██▊ | 277/995 [00:21<00:14, 51.20it/s] Loading 0: 28%|██▊ | 278/995 [00:21<01:51, 6.43it/s] Loading 0: 32%|███▏ | 320/995 [00:22<01:16, 8.87it/s] Loading 0: 37%|███▋ | 368/995 [00:23<00:50, 12.46it/s] Loading 0: 43%|████▎ | 423/995 [00:24<00:32, 17.42it/s] Loading 0: 48%|████▊ | 478/995 [00:25<00:22, 22.76it/s] Loading 0: 53%|█████▎ | 526/995 [00:26<00:17, 27.07it/s] Loading 0: 57%|█████▋ | 564/995 [00:42<00:15, 27.07it/s] Loading 0: 57%|█████▋ | 565/995 [00:42<00:57, 7.41it/s] Loading 0: 58%|█████▊ | 581/995 [00:44<00:53, 7.78it/s] Loading 0: 64%|██████▍ | 636/995 [00:45<00:30, 11.74it/s] Loading 0: 69%|██████▉ | 691/995 [00:46<00:18, 16.27it/s] Loading 0: 74%|███████▍ | 739/995 [00:47<00:12, 20.43it/s] Loading 0: 80%|███████▉ | 794/995 [00:48<00:07, 25.59it/s] Loading 0: 84%|████████▍ | 836/995 [00:48<00:04, 34.21it/s] Loading 0: 85%|████████▍ | 845/995 [01:04<00:04, 34.21it/s] Loading 0: 85%|████████▌ | 846/995 [01:04<00:23, 6.24it/s] Loading 0: 85%|████████▌ | 849/995 [01:05<00:24, 5.90it/s] Loading 0: 90%|█████████ | 897/995 [01:06<00:10, 9.64it/s] Loading 0: 96%|█████████▌| 952/995 [01:07<00:02, 14.97it/s] Loading 0: 100%|██████████| 995/995 [01:08<00:00, 18.00it/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-v121-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v121-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-v121-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v121-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-v121-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v121-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-v121-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v121-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:05<00:05, 5.94s/it] Downloading shards: 100%|██████████| 2/2 [00:11<00:00, 5.50s/it] Downloading shards: 100%|██████████| 2/2 [00:11<00:00, 5.56s/it]
neversleep-noromaid-v0-8068-v121-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 1.98it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.30it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.00it/s]
neversleep-noromaid-v0-8068-v121-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v121-mkmlizer: Saving duration: 1.785s
neversleep-noromaid-v0-8068-v121-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 15.003s
neversleep-noromaid-v0-8068-v121-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v121-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v121-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v121_reward
neversleep-noromaid-v0-8068-v121-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v121_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v121-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v121_reward/config.json
neversleep-noromaid-v0-8068-v121-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v121_reward/merges.txt
neversleep-noromaid-v0-8068-v121-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v121_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v121-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v121_reward/tokenizer.json
neversleep-noromaid-v0-8068-v121-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v121_reward/vocab.json
neversleep-noromaid-v0-8068-v121-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v121_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v121-mkmlizer completed after 258.73s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v121-mkmlizer
Pipeline stage MKMLizer completed in 260.35s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v121
Waiting for inference service neversleep-noromaid-v0-8068-v121 to be ready
Retrying (%r) after connection broken by '%r': %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Inference service neversleep-noromaid-v0-8068-v121 ready after 80.41447067260742s
Pipeline stage ISVCDeployer completed in 87.11s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.2842938899993896s
Received healthy response to inference request in 2.4545178413391113s
Received healthy response to inference request in 2.374485492706299s
Received healthy response to inference request in 2.462224006652832s
Received healthy response to inference request in 2.4349348545074463s
5 requests
0 failed requests
5th percentile: 2.3865753650665282
10th percentile: 2.3986652374267576
20th percentile: 2.422844982147217
30th percentile: 2.4388514518737794
40th percentile: 2.446684646606445
50th percentile: 2.4545178413391113
60th percentile: 2.4576003074646
70th percentile: 2.460682773590088
80th percentile: 2.626637983322144
90th percentile: 2.9554659366607665
95th percentile: 3.119879913330078
99th percentile: 3.2514110946655275
mean time: 2.6020912170410155
Pipeline stage StressChecker completed in 13.70s
neversleep-noromaid-v0_8068_v121 status is now deployed due to DeploymentManager action
neversleep-noromaid-v0_8068_v121 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics