submission_id: neversleep-noromaid-v0_8068_v119
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': '{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: 2024-07-10T17:50:41+00:00
model_name: neversleep-noromaid-v0_8068_v119
model_group: NeverSleep/Noromaid-v0.1
num_battles: 31559
num_wins: 16356
celo_rating: 1186.84
propriety_score: 0.7284585706411906
propriety_total_count: 5443.0
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_v119
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: 0.5182673722234545
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v119-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v119-mkmlizer to finish
neversleep-noromaid-v0-8068-v119-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v119-mkmlizer: ║ _____ __ __ ║
neversleep-noromaid-v0-8068-v119-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-noromaid-v0-8068-v119-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-noromaid-v0-8068-v119-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-noromaid-v0-8068-v119-mkmlizer: ║ /___/ ║
neversleep-noromaid-v0-8068-v119-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v119-mkmlizer: ║ Version: 0.8.14 ║
neversleep-noromaid-v0-8068-v119-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-noromaid-v0-8068-v119-mkmlizer: ║ https://mk1.ai ║
neversleep-noromaid-v0-8068-v119-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v119-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-noromaid-v0-8068-v119-mkmlizer: ║ belonging to: ║
neversleep-noromaid-v0-8068-v119-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v119-mkmlizer: ║ Chai Research Corp. ║
neversleep-noromaid-v0-8068-v119-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-noromaid-v0-8068-v119-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
neversleep-noromaid-v0-8068-v119-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v119-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission blend_pefis_2024-07-04: ('http://mistralai-mixtral-8x7b-3473-v33-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"TypeError : SamplingParameters.__init__() got an unexpected keyword argument \'min_p\'"}')
Failed to get response for submission blend_pefis_2024-07-04: ('http://mistralai-mixtral-8x7b-3473-v33-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"TypeError : SamplingParameters.__init__() got an unexpected keyword argument \'min_p\'"}')
neversleep-noromaid-v0-8068-v119-mkmlizer: Downloaded to shared memory in 208.879s
neversleep-noromaid-v0-8068-v119-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v119-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-noromaid-v0-8068-v119-mkmlizer: quantized model in 101.835s
neversleep-noromaid-v0-8068-v119-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 310.714s
neversleep-noromaid-v0-8068-v119-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v119-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v119-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v119
neversleep-noromaid-v0-8068-v119-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v119/config.json
neversleep-noromaid-v0-8068-v119-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v119/tokenizer.json
neversleep-noromaid-v0-8068-v119-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v119/tokenizer_config.json
neversleep-noromaid-v0-8068-v119-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v119/special_tokens_map.json
neversleep-noromaid-v0-8068-v119-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v119/tokenizer.model
neversleep-noromaid-v0-8068-v119-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v119/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v119-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v119/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v119-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v119/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v119-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v119/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v119-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
neversleep-noromaid-v0-8068-v119-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 5%|▌ | 52/995 [00:01<00:27, 34.79it/s] Loading 0: 11%|█ | 107/995 [00:02<00:23, 38.09it/s] Loading 0: 16%|█▋ | 162/995 [00:04<00:21, 39.08it/s] Loading 0: 21%|██ | 210/995 [00:05<00:20, 37.83it/s] Loading 0: 27%|██▋ | 265/995 [00:06<00:19, 37.90it/s] Loading 0: 28%|██▊ | 277/995 [00:20<00:18, 37.90it/s] Loading 0: 28%|██▊ | 278/995 [00:27<02:21, 5.06it/s] Loading 0: 32%|███▏ | 320/995 [00:28<01:36, 6.97it/s] Loading 0: 37%|███▋ | 368/995 [00:30<01:03, 9.84it/s] Loading 0: 43%|████▎ | 423/995 [00:31<00:41, 13.69it/s] Loading 0: 48%|████▊ | 478/995 [00:32<00:29, 17.82it/s] Loading 0: 53%|█████▎ | 526/995 [00:33<00:22, 21.22it/s] Loading 0: 57%|█████▋ | 564/995 [00:54<00:20, 21.22it/s] Loading 0: 57%|█████▋ | 565/995 [00:54<01:13, 5.84it/s] Loading 0: 58%|█████▊ | 581/995 [00:56<01:06, 6.21it/s] Loading 0: 64%|██████▍ | 636/995 [00:57<00:38, 9.33it/s] Loading 0: 69%|██████▉ | 691/995 [00:58<00:23, 13.01it/s] Loading 0: 74%|███████▍ | 739/995 [00:59<00:15, 16.34it/s] Loading 0: 80%|███████▉ | 794/995 [01:01<00:09, 20.60it/s] Loading 0: 85%|████████▍ | 845/995 [01:21<00:07, 20.60it/s] Loading 0: 85%|████████▌ | 846/995 [01:21<00:23, 6.41it/s] Loading 0: 85%|████████▌ | 849/995 [01:23<00:24, 6.08it/s] Loading 0: 90%|█████████ | 897/995 [01:24<00:11, 8.75it/s] Loading 0: 96%|█████████▌| 952/995 [01:25<00:03, 12.65it/s] Loading 0: 100%|██████████| 995/995 [01:27<00:00, 14.96it/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-v119-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v119-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-v119-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v119-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-v119-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v119-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-v119-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v119-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:07<00:07, 7.05s/it] Downloading shards: 100%|██████████| 2/2 [00:09<00:00, 4.26s/it] Downloading shards: 100%|██████████| 2/2 [00:09<00:00, 4.68s/it]
neversleep-noromaid-v0-8068-v119-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 1.63it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.66it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.43it/s]
neversleep-noromaid-v0-8068-v119-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v119-mkmlizer: Saving duration: 2.205s
neversleep-noromaid-v0-8068-v119-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 14.187s
neversleep-noromaid-v0-8068-v119-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v119-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v119-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v119_reward
neversleep-noromaid-v0-8068-v119-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v119_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v119-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v119_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v119-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v119_reward/config.json
neversleep-noromaid-v0-8068-v119-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v119_reward/vocab.json
neversleep-noromaid-v0-8068-v119-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v119_reward/merges.txt
neversleep-noromaid-v0-8068-v119-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v119_reward/tokenizer.json
neversleep-noromaid-v0-8068-v119-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v119_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v119-mkmlizer completed after 382.0s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v119-mkmlizer
Pipeline stage MKMLizer completed in 382.94s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v119
Waiting for inference service neversleep-noromaid-v0-8068-v119 to be ready
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
Failed to get response for submission blend_pefis_2024-07-04: ('http://mistralai-mixtral-8x7b-3473-v33-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"TypeError : SamplingParameters.__init__() got an unexpected keyword argument \'min_p\'"}')
Inference service neversleep-noromaid-v0-8068-v119 ready after 80.56019186973572s
Pipeline stage ISVCDeployer completed in 87.74s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.112272262573242s
Received healthy response to inference request in 2.3418989181518555s
Received healthy response to inference request in 2.280355453491211s
Received healthy response to inference request in 2.2452549934387207s
Received healthy response to inference request in 2.386662721633911s
5 requests
0 failed requests
5th percentile: 2.252275085449219
10th percentile: 2.259295177459717
20th percentile: 2.273335361480713
30th percentile: 2.29266414642334
40th percentile: 2.3172815322875975
50th percentile: 2.3418989181518555
60th percentile: 2.3598044395446776
70th percentile: 2.3777099609375
80th percentile: 2.5317846298217774
90th percentile: 2.8220284461975096
95th percentile: 2.967150354385376
99th percentile: 3.083247880935669
mean time: 2.473288869857788
Pipeline stage StressChecker completed in 13.20s
neversleep-noromaid-v0_8068_v119 status is now deployed due to DeploymentManager action
neversleep-noromaid-v0_8068_v119 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics