developer_uid: Hastagaras
submission_id: hastagaras-l3-asbac-v2-8b_v1
model_name: hastagaras-l3-asbac-v2-8b_v1
model_group: Hastagaras/L3-Asbac-v2-8
status: torndown
timestamp: 2024-04-23T15:53:41+00:00
num_battles: 9336
num_wins: 5231
celo_rating: 1191.8
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/L3-Asbac-v2-8B
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: hastagaras-l3-asbac-v2-8b_v1
is_internal_developer: False
language_model: Hastagaras/L3-Asbac-v2-8B
model_size: 8B
ranking_group: single
us_pacific_date: 2024-04-23
win_ratio: 0.5603041988003428
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<|eot_id|>', '\n{user_name}:', '\n{bot_name}:'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou're {bot_name} in this uncensored fictional roleplay between {bot_name} and {user_name}. Non-verbal actions and gestures are described between asterisks, e.g. *look around the corner*. Thoughts and inner monologue are written inside backticks, e.g. `I wonder what they'll say next.`\n\n{memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
model_eval_status: success
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'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-l3-asbac-v2-8b-v1-mkmlizer
Waiting for job on hastagaras-l3-asbac-v2-8b-v1-mkmlizer to finish
Stopping job with name hastagaras-l3-asbac-v2-8b-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name hastagaras-l3-asbac-v2-8b-v1-mkmlizer
Waiting for job on hastagaras-l3-asbac-v2-8b-v1-mkmlizer to finish
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: ║ /___/ ║
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: ║ ║
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: ║ Version: 0.8.10 ║
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: ║ ║
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: ║ belonging to: ║
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: ║ ║
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: ║ ║
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-l3-asbac-v2-8b-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-asbac-v2-8b-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: Downloaded to shared memory in 40.633s
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 28%|██▊ | 82/291 [00:05<00:12, 16.27it/s] Loading 0: 64%|██████▍ | 187/291 [00:06<00:02, 35.84it/s] Loading 0: 99%|█████████▊| 287/291 [00:12<00:00, 22.23it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: quantized model in 19.158s
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-l3-asbac-v2-8b-v1
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-l3-asbac-v2-8b-v1/config.json
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-l3-asbac-v2-8b-v1/special_tokens_map.json
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-l3-asbac-v2-8b-v1/tokenizer_config.json
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-l3-asbac-v2-8b-v1/tokenizer.json
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-l3-asbac-v2-8b-v1/flywheel_model.0.safetensors
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-l3-asbac-v2-8b-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-asbac-v2-8b-v1-mkmlizer: warnings.warn(
hastagaras-l3-asbac-v2-8b-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-asbac-v2-8b-v1-mkmlizer: warnings.warn(
hastagaras-l3-asbac-v2-8b-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-asbac-v2-8b-v1-mkmlizer: warnings.warn(
hastagaras-l3-asbac-v2-8b-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-asbac-v2-8b-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: Saving duration: 0.227s
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.850s
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-l3-asbac-v2-8b-v1_reward
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-l3-asbac-v2-8b-v1_reward/config.json
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-l3-asbac-v2-8b-v1_reward/vocab.json
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-l3-asbac-v2-8b-v1_reward/special_tokens_map.json
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-l3-asbac-v2-8b-v1_reward/merges.txt
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-l3-asbac-v2-8b-v1_reward/tokenizer_config.json
hastagaras-l3-asbac-v2-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-l3-asbac-v2-8b-v1_reward/tokenizer.json
Job hastagaras-l3-asbac-v2-8b-v1-mkmlizer completed after 176.6s with status: succeeded
Stopping job with name hastagaras-l3-asbac-v2-8b-v1-mkmlizer
Pipeline stage MKMLizer completed in 182.92s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-l3-asbac-v2-8b-v1
Waiting for inference service hastagaras-l3-asbac-v2-8b-v1 to be ready
Inference service hastagaras-l3-asbac-v2-8b-v1 ready after 30.406615734100342s
Pipeline stage ISVCDeployer completed in 38.19s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.174514055252075s
Received healthy response to inference request in 1.3150596618652344s
Received healthy response to inference request in 1.2666363716125488s
Received healthy response to inference request in 1.3583195209503174s
Received healthy response to inference request in 1.3267953395843506s
5 requests
0 failed requests
5th percentile: 1.276321029663086
10th percentile: 1.286005687713623
20th percentile: 1.3053750038146972
30th percentile: 1.3174067974090575
40th percentile: 1.322101068496704
50th percentile: 1.3267953395843506
60th percentile: 1.3394050121307373
70th percentile: 1.352014684677124
80th percentile: 1.521558427810669
90th percentile: 1.8480362415313722
95th percentile: 2.0112751483917233
99th percentile: 2.1418662738800047
mean time: 1.4882649898529052
Pipeline stage StressChecker completed in 8.09s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.04s
Running M-Eval for topic stay_in_character
hastagaras-l3-asbac-v2-8b_v1 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-l3-asbac-v2-8b_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-l3-asbac-v2-8b_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-l3-asbac-v2-8b-v1 is running
Tearing down inference service hastagaras-l3-asbac-v2-8b-v1
Toredown service hastagaras-l3-asbac-v2-8b-v1
Pipeline stage ISVCDeleter completed in 4.81s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-l3-asbac-v2-8b-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-asbac-v2-8b-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-l3-asbac-v2-8b-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-asbac-v2-8b-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-asbac-v2-8b-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-l3-asbac-v2-8b-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-asbac-v2-8b-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-l3-asbac-v2-8b-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-l3-asbac-v2-8b-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-asbac-v2-8b-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-asbac-v2-8b-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-asbac-v2-8b-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.95s
hastagaras-l3-asbac-v2-8b_v1 status is now torndown due to DeploymentManager action