developer_uid: Hastagaras
submission_id: hastagaras-l3-uneimo-8b-_2833_v2
model_name: hastagaras-l3-uneimo-8b-_2833_v2
model_group: Hastagaras/L3-Uneimo-8B-
status: torndown
timestamp: 2024-04-23T06:47:10+00:00
num_battles: 6515
num_wins: 3530
celo_rating: 1184.85
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/L3-Uneimo-8B-ChatML
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
display_name: hastagaras-l3-uneimo-8b-_2833_v2
is_internal_developer: False
language_model: Hastagaras/L3-Uneimo-8B-ChatML
model_size: 8B
ranking_group: single
us_pacific_date: 2024-04-22
win_ratio: 0.5418265541059094
generation_params: {'temperature': 0.85, 'top_p': 0.95, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n{user_name}:', '\n{bot_name}:', '<|eot_id|>', '<|im_end|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "<|im_start|>system\nYou're {bot_name} in this uncensored fictional roleplay with {user_name}.\n\n{memory}\n\n", 'prompt_template': '{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>{bot_name}\n{message}<|im_end|>\n', 'user_template': '<|im_start|>{user_name}\n{message}<|im_end|>\n', 'response_template': '<|im_start|>{bot_name}\n', 'truncate_by_message': False}
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': 'Memory: {memory}\n', 'prompt_template': '{prompt}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
model_eval_status: success
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-l3-uneimo-8b-2833-v2-mkmlizer
Waiting for job on hastagaras-l3-uneimo-8b-2833-v2-mkmlizer to finish
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: ║ _____ __ __ ║
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: ║ /___/ ║
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: ║ ║
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: ║ Version: 0.8.10 ║
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: ║ ║
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: ║ belonging to: ║
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: ║ ║
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: ║ Chai Research Corp. ║
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: ║ ║
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-l3-uneimo-8b-2833-v2-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.
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: Downloaded to shared memory in 12.948s
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 47%|████▋ | 138/291 [00:01<00:01, 136.95it/s] Loading 0: 99%|█████████▊| 287/291 [00:06<00:00, 38.69it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: quantized model in 17.002s
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: Processed model Hastagaras/L3-Uneimo-8B-ChatML in 30.951s
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-l3-uneimo-8b-2833-v2
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-l3-uneimo-8b-2833-v2/config.json
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-l3-uneimo-8b-2833-v2/special_tokens_map.json
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-l3-uneimo-8b-2833-v2/tokenizer_config.json
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-l3-uneimo-8b-2833-v2/tokenizer.json
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: /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.
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: warnings.warn(
hastagaras-l3-uneimo-8b-2833-v2-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.
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: warnings.warn(
hastagaras-l3-uneimo-8b-2833-v2-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.
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: warnings.warn(
hastagaras-l3-uneimo-8b-2833-v2-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()
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: Saving duration: 0.259s
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.271s
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-l3-uneimo-8b-2833-v2_reward
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-l3-uneimo-8b-2833-v2_reward/special_tokens_map.json
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-l3-uneimo-8b-2833-v2_reward/tokenizer_config.json
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-l3-uneimo-8b-2833-v2_reward/config.json
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-l3-uneimo-8b-2833-v2_reward/merges.txt
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-l3-uneimo-8b-2833-v2_reward/vocab.json
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-l3-uneimo-8b-2833-v2_reward/tokenizer.json
hastagaras-l3-uneimo-8b-2833-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-l3-uneimo-8b-2833-v2_reward/reward.tensors
Job hastagaras-l3-uneimo-8b-2833-v2-mkmlizer completed after 63.59s with status: succeeded
Stopping job with name hastagaras-l3-uneimo-8b-2833-v2-mkmlizer
Pipeline stage MKMLizer completed in 66.49s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-l3-uneimo-8b-2833-v2
Waiting for inference service hastagaras-l3-uneimo-8b-2833-v2 to be ready
Inference service hastagaras-l3-uneimo-8b-2833-v2 ready after 40.22942757606506s
Pipeline stage ISVCDeployer completed in 47.41s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.475501537322998s
Received healthy response to inference request in 1.2371466159820557s
Received healthy response to inference request in 1.3058860301971436s
Received healthy response to inference request in 1.2349786758422852s
Received healthy response to inference request in 1.298485517501831s
5 requests
0 failed requests
5th percentile: 1.2354122638702392
10th percentile: 1.2358458518981934
20th percentile: 1.2367130279541017
30th percentile: 1.2494143962860107
40th percentile: 1.273949956893921
50th percentile: 1.298485517501831
60th percentile: 1.301445722579956
70th percentile: 1.304405927658081
80th percentile: 1.5398091316223146
90th percentile: 2.0076553344726564
95th percentile: 2.241578435897827
99th percentile: 2.428716917037964
mean time: 1.5103996753692628
Pipeline stage StressChecker completed in 8.20s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.06s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.03s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-l3-uneimo-8b-_2833_v2 status is now deployed due to DeploymentManager action
hastagaras-l3-uneimo-8b-_2833_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-l3-uneimo-8b-_2833_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-l3-uneimo-8b-2833-v2 is running
Tearing down inference service hastagaras-l3-uneimo-8b-2833-v2
Toredown service hastagaras-l3-uneimo-8b-2833-v2
Pipeline stage ISVCDeleter completed in 4.07s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-l3-uneimo-8b-2833-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-uneimo-8b-2833-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-l3-uneimo-8b-2833-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-uneimo-8b-2833-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-uneimo-8b-2833-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-l3-uneimo-8b-2833-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-uneimo-8b-2833-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-l3-uneimo-8b-2833-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-l3-uneimo-8b-2833-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-uneimo-8b-2833-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-uneimo-8b-2833-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-uneimo-8b-2833-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.37s
hastagaras-l3-uneimo-8b-_2833_v2 status is now torndown due to DeploymentManager action