submission_id: neversleep-noromaid-v0-_8068_v35
developer_uid: chaiverse_console_tests
best_of: 8
celo_rating: 1197.22
display_name: neversleep_v3
family_friendly_score: 0.0
formatter: {'memory_template': '<s>[INST] This is an entertaining conversation. You are {bot_name} who has the persona: {memory}.\nEngage in a chat with {user_name} while staying in character. Try to flirt with {user_name}. Engage in *roleplay* actions. Describe the scene dramatically. \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}
generation_params: {'temperature': 0.8, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 70, 'presence_penalty': 0.9, 'frequency_penalty': 0.9, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 8, 'max_output_tokens': 64}
is_internal_developer: True
language_model: NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3
max_input_tokens: 512
max_output_tokens: 64
model_architecture: MixtralForCausalLM
model_eval_status: success
model_group: NeverSleep/Noromaid-v0.1
model_name: neversleep_v3
model_num_parameters: 46702792704.0
model_repo: NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3
model_size: 47B
num_battles: 328479
num_wins: 183825
ranking_group: single
reward_formatter: {'bot_template': 'Bot: {message}\n', 'memory_template': 'Memory: {memory}\n', 'prompt_template': '{prompt}\n', 'response_template': 'Bot:', 'truncate_by_message': False, 'user_template': 'User: {message}\n'}
reward_repo: rirv938/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-04-27T02:51:36+00:00
us_pacific_date: 2024-04-26
win_ratio: 0.5596248161982957
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v35-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v35-mkmlizer to finish
Stopping job with name neversleep-noromaid-v0-8068-v35-mkmlizer
%s, retrying in %s seconds...
Starting job with name neversleep-noromaid-v0-8068-v35-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v35-mkmlizer to finish
neversleep-noromaid-v0-8068-v35-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v35-mkmlizer: ║ _____ __ __ ║
neversleep-noromaid-v0-8068-v35-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-noromaid-v0-8068-v35-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-noromaid-v0-8068-v35-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-noromaid-v0-8068-v35-mkmlizer: ║ /___/ ║
neversleep-noromaid-v0-8068-v35-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v35-mkmlizer: ║ Version: 0.8.10 ║
neversleep-noromaid-v0-8068-v35-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-noromaid-v0-8068-v35-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v35-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-noromaid-v0-8068-v35-mkmlizer: ║ belonging to: ║
neversleep-noromaid-v0-8068-v35-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v35-mkmlizer: ║ Chai Research Corp. ║
neversleep-noromaid-v0-8068-v35-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-noromaid-v0-8068-v35-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
neversleep-noromaid-v0-8068-v35-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v35-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v35-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-noromaid-v0-8068-v35-mkmlizer: warnings.warn(warning_message, FutureWarning)
neversleep-noromaid-v0-8068-v35-mkmlizer: Downloaded to shared memory in 79.685s
neversleep-noromaid-v0-8068-v35-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v35-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-noromaid-v0-8068-v35-mkmlizer: quantized model in 64.601s
neversleep-noromaid-v0-8068-v35-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 151.921s
neversleep-noromaid-v0-8068-v35-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v35-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v35-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v35
neversleep-noromaid-v0-8068-v35-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v35/config.json
neversleep-noromaid-v0-8068-v35-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v35/tokenizer_config.json
neversleep-noromaid-v0-8068-v35-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v35/special_tokens_map.json
neversleep-noromaid-v0-8068-v35-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v35/tokenizer.model
neversleep-noromaid-v0-8068-v35-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v35/tokenizer.json
neversleep-noromaid-v0-8068-v35-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v35/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v35-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v35/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v35-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v35/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v35-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v35/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v35-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
neversleep-noromaid-v0-8068-v35-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 5%|▌ | 52/995 [00:01<00:20, 46.40it/s] Loading 0: 11%|█ | 107/995 [00:02<00:18, 49.16it/s] Loading 0: 16%|█▋ | 162/995 [00:03<00:16, 49.49it/s] Loading 0: 21%|██ | 210/995 [00:04<00:16, 47.04it/s] Loading 0: 27%|██▋ | 265/995 [00:05<00:15, 48.10it/s] Loading 0: 28%|██▊ | 278/995 [00:16<01:20, 8.86it/s] Loading 0: 32%|███▏ | 320/995 [00:18<00:59, 11.34it/s] Loading 0: 37%|███▋ | 368/995 [00:19<00:41, 15.26it/s] Loading 0: 43%|████▎ | 423/995 [00:20<00:27, 20.56it/s] Loading 0: 48%|████▊ | 478/995 [00:21<00:20, 25.83it/s] Loading 0: 53%|█████▎ | 526/995 [00:22<00:15, 29.34it/s] Loading 0: 57%|█████▋ | 565/995 [00:33<00:42, 10.20it/s] Loading 0: 58%|█████▊ | 581/995 [00:34<00:39, 10.41it/s] Loading 0: 64%|██████▍ | 636/995 [00:36<00:24, 14.93it/s] Loading 0: 69%|██████▉ | 691/995 [00:37<00:15, 19.74it/s] Loading 0: 74%|███████▍ | 739/995 [00:38<00:11, 23.15it/s] Loading 0: 80%|███████▉ | 794/995 [00:39<00:07, 27.58it/s] Loading 0: 80%|███████▉ | 794/995 [00:51<00:07, 27.58it/s] Loading 0: 85%|████████▌ | 846/995 [00:51<00:13, 10.86it/s] Loading 0: 85%|████████▌ | 849/995 [00:52<00:14, 9.80it/s] Loading 0: 90%|█████████ | 897/995 [00:53<00:07, 13.54it/s] Loading 0: 96%|█████████▌| 952/995 [00:54<00:02, 18.58it/s] Loading 0: 100%|██████████| 995/995 [00:56<00:00, 21.05it/s] /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:913: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
neversleep-noromaid-v0-8068-v35-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v35-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:757: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
neversleep-noromaid-v0-8068-v35-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v35-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-v35-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v35-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-noromaid-v0-8068-v35-mkmlizer: return self.fget.__get__(instance, owner)()
neversleep-noromaid-v0-8068-v35-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v35-mkmlizer: Saving duration: 0.287s
neversleep-noromaid-v0-8068-v35-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 7.693s
neversleep-noromaid-v0-8068-v35-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v35-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v35-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v35_reward
neversleep-noromaid-v0-8068-v35-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v35_reward/config.json
neversleep-noromaid-v0-8068-v35-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v35_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v35-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v35_reward/vocab.json
neversleep-noromaid-v0-8068-v35-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v35_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v35-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v35_reward/merges.txt
neversleep-noromaid-v0-8068-v35-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v35_reward/tokenizer.json
neversleep-noromaid-v0-8068-v35-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v35_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v35-mkmlizer completed after 287.69s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v35-mkmlizer
Pipeline stage MKMLizer completed in 291.04s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v35
Waiting for inference service neversleep-noromaid-v0-8068-v35 to be ready
Inference service neversleep-noromaid-v0-8068-v35 ready after 60.334574699401855s
Pipeline stage ISVCDeployer completed in 67.02s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.1779065132141113s
Received healthy response to inference request in 2.4383814334869385s
Received healthy response to inference request in 2.2789759635925293s
Received healthy response to inference request in 2.212137222290039s
Received healthy response to inference request in 2.241105318069458s
5 requests
0 failed requests
5th percentile: 2.2179308414459227
10th percentile: 2.2237244606018067
20th percentile: 2.2353116989135744
30th percentile: 2.248679447174072
40th percentile: 2.2638277053833007
50th percentile: 2.2789759635925293
60th percentile: 2.342738151550293
70th percentile: 2.4065003395080566
80th percentile: 2.5862864494323734
90th percentile: 2.8820964813232424
95th percentile: 3.0300014972686764
99th percentile: 3.1483255100250243
mean time: 2.4697012901306152
Pipeline stage StressChecker completed in 13.01s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.04s
%s, retrying in %s seconds...
M-Eval Dataset for topic stay_in_character is loaded
neversleep-noromaid-v0-_8068_v35 status is now deployed due to DeploymentManager action
%s, retrying in %s seconds...
neversleep-noromaid-v0-_8068_v35 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of neversleep-noromaid-v0-_8068_v35
Running pipeline stage ISVCDeleter
Checking if service neversleep-noromaid-v0-8068-v35 is running
Tearing down inference service neversleep-noromaid-v0-8068-v35
Toredown service neversleep-noromaid-v0-8068-v35
Pipeline stage ISVCDeleter completed in 6.74s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key neversleep-noromaid-v0-8068-v35/config.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v35/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v35/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v35/flywheel_model.2.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v35/flywheel_model.3.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v35/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v35/tokenizer.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v35/tokenizer.model from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v35/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key neversleep-noromaid-v0-8068-v35_reward/config.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v35_reward/merges.txt from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v35_reward/reward.tensors from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v35_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v35_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v35_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v35_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.44s
neversleep-noromaid-v0-_8068_v35 status is now torndown due to DeploymentManager action