submission_id: hastagaras-l3-uneimo-8b-_2833_v1
developer_uid: Hastagaras
status: torndown
model_repo: Hastagaras/L3-Uneimo-8B-ChatML
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, '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': 512, 'best_of': 16, '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}<|im_end|>", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>', 'response_template': '<|im_start|>assistant\n{bot_name}:', 'truncate_by_message': False}
reward_formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
timestamp: 2024-04-23T06:33:37+00:00
model_name: hastagaras-l3-uneimo-8b-_2833_v1
model_eval_status: success
model_group: Hastagaras/L3-Uneimo-8B-
num_battles: 7092
num_wins: 3843
celo_rating: 1184.79
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: hastagaras-l3-uneimo-8b-_2833_v1
ineligible_reason: propriety_total_count < 800
language_model: Hastagaras/L3-Uneimo-8B-ChatML
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-22
win_ratio: 0.5418781725888325
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-l3-uneimo-8b-2833-v1-mkmlizer
Waiting for job on hastagaras-l3-uneimo-8b-2833-v1-mkmlizer to finish
Stopping job with name hastagaras-l3-uneimo-8b-2833-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name hastagaras-l3-uneimo-8b-2833-v1-mkmlizer
Waiting for job on hastagaras-l3-uneimo-8b-2833-v1-mkmlizer to finish
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: ║ /___/ ║
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: ║ ║
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: ║ Version: 0.8.10 ║
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: ║ ║
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: ║ belonging to: ║
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: ║ ║
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: ║ ║
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-l3-uneimo-8b-2833-v1-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-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: Downloaded to shared memory in 16.043s
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 45%|████▌ | 131/291 [00:01<00:01, 130.87it/s] Loading 0: 99%|█████████▊| 287/291 [00:06<00:00, 38.36it/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-v1-mkmlizer: quantized model in 17.145s
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: Processed model Hastagaras/L3-Uneimo-8B-ChatML in 34.191s
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-l3-uneimo-8b-2833-v1
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-l3-uneimo-8b-2833-v1/config.json
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-l3-uneimo-8b-2833-v1/special_tokens_map.json
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-l3-uneimo-8b-2833-v1/tokenizer.json
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-l3-uneimo-8b-2833-v1/tokenizer_config.json
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-l3-uneimo-8b-2833-v1/flywheel_model.0.safetensors
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-l3-uneimo-8b-2833-v1-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-v1-mkmlizer: warnings.warn(
hastagaras-l3-uneimo-8b-2833-v1-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-v1-mkmlizer: warnings.warn(
hastagaras-l3-uneimo-8b-2833-v1-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-v1-mkmlizer: warnings.warn(
hastagaras-l3-uneimo-8b-2833-v1-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-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: Saving duration: 0.258s
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.382s
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-l3-uneimo-8b-2833-v1_reward
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-l3-uneimo-8b-2833-v1_reward/config.json
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-l3-uneimo-8b-2833-v1_reward/special_tokens_map.json
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-l3-uneimo-8b-2833-v1_reward/merges.txt
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-l3-uneimo-8b-2833-v1_reward/tokenizer_config.json
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-l3-uneimo-8b-2833-v1_reward/vocab.json
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-l3-uneimo-8b-2833-v1_reward/tokenizer.json
hastagaras-l3-uneimo-8b-2833-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-l3-uneimo-8b-2833-v1_reward/reward.tensors
Job hastagaras-l3-uneimo-8b-2833-v1-mkmlizer completed after 63.59s with status: succeeded
Stopping job with name hastagaras-l3-uneimo-8b-2833-v1-mkmlizer
Pipeline stage MKMLizer completed in 67.77s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-l3-uneimo-8b-2833-v1
Waiting for inference service hastagaras-l3-uneimo-8b-2833-v1 to be ready
Inference service hastagaras-l3-uneimo-8b-2833-v1 ready after 40.23705434799194s
Pipeline stage ISVCDeployer completed in 47.71s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1071250438690186s
Received healthy response to inference request in 1.2625341415405273s
Received healthy response to inference request in 1.8573155403137207s
Received healthy response to inference request in 1.283494472503662s
Received healthy response to inference request in 1.270676851272583s
5 requests
0 failed requests
5th percentile: 1.2641626834869384
10th percentile: 1.2657912254333497
20th percentile: 1.269048309326172
30th percentile: 1.2732403755187989
40th percentile: 1.2783674240112304
50th percentile: 1.283494472503662
60th percentile: 1.5130228996276855
70th percentile: 1.742551326751709
80th percentile: 1.9072774410247804
90th percentile: 2.0072012424468992
95th percentile: 2.057163143157959
99th percentile: 2.0971326637268066
mean time: 1.5562292098999024
Pipeline stage StressChecker completed in 8.57s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-l3-uneimo-8b-_2833_v1 status is now deployed due to DeploymentManager action
hastagaras-l3-uneimo-8b-_2833_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-l3-uneimo-8b-_2833_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-l3-uneimo-8b-2833-v1 is running
Tearing down inference service hastagaras-l3-uneimo-8b-2833-v1
Toredown service hastagaras-l3-uneimo-8b-2833-v1
Pipeline stage ISVCDeleter completed in 4.09s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-l3-uneimo-8b-2833-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-uneimo-8b-2833-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-l3-uneimo-8b-2833-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-uneimo-8b-2833-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-uneimo-8b-2833-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-l3-uneimo-8b-2833-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-uneimo-8b-2833-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-l3-uneimo-8b-2833-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-l3-uneimo-8b-2833-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-uneimo-8b-2833-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-uneimo-8b-2833-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-uneimo-8b-2833-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.13s
hastagaras-l3-uneimo-8b-_2833_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics