submission_id: wespro-f1-chimera-hybrid_2693_v2
developer_uid: WesPro
status: torndown
model_repo: WesPro/F1-Chimera-Hybrid-LimaRP-8B
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'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
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}
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: 2024-04-22T20:13:59+00:00
model_name: wespro-f1-chimera-hybrid_2693_v2
model_eval_status: success
model_group: WesPro/F1-Chimera-Hybrid
num_battles: 7248
num_wins: 3791
celo_rating: 1166.04
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: wespro-f1-chimera-hybrid_2693_v2
ineligible_reason: propriety_total_count < 800
language_model: WesPro/F1-Chimera-Hybrid-LimaRP-8B
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-22
win_ratio: 0.5230408388520972
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name wespro-f1-chimera-hybrid-2693-v2-mkmlizer
Waiting for job on wespro-f1-chimera-hybrid-2693-v2-mkmlizer to finish
wespro-f1-chimera-hybrid-2693-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
wespro-f1-chimera-hybrid-2693-v2-mkmlizer: ║ _____ __ __ ║
wespro-f1-chimera-hybrid-2693-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
wespro-f1-chimera-hybrid-2693-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
wespro-f1-chimera-hybrid-2693-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
wespro-f1-chimera-hybrid-2693-v2-mkmlizer: ║ /___/ ║
wespro-f1-chimera-hybrid-2693-v2-mkmlizer: ║ ║
wespro-f1-chimera-hybrid-2693-v2-mkmlizer: ║ Version: 0.8.10 ║
wespro-f1-chimera-hybrid-2693-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
wespro-f1-chimera-hybrid-2693-v2-mkmlizer: ║ ║
wespro-f1-chimera-hybrid-2693-v2-mkmlizer: ║ The license key for the current software has been verified as ║
wespro-f1-chimera-hybrid-2693-v2-mkmlizer: ║ belonging to: ║
wespro-f1-chimera-hybrid-2693-v2-mkmlizer: ║ ║
wespro-f1-chimera-hybrid-2693-v2-mkmlizer: ║ Chai Research Corp. ║
wespro-f1-chimera-hybrid-2693-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
wespro-f1-chimera-hybrid-2693-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
wespro-f1-chimera-hybrid-2693-v2-mkmlizer: ║ ║
wespro-f1-chimera-hybrid-2693-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
wespro-f1-chimera-hybrid-2693-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.
wespro-f1-chimera-hybrid-2693-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
wespro-f1-chimera-hybrid-2693-v2-mkmlizer: Downloaded to shared memory in 27.517s
wespro-f1-chimera-hybrid-2693-v2-mkmlizer: quantizing model to /dev/shm/model_cache
wespro-f1-chimera-hybrid-2693-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
wespro-f1-chimera-hybrid-2693-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 41%|████ | 119/291 [00:01<00:01, 118.30it/s] Loading 0: 64%|██████▍ | 187/291 [00:07<00:04, 22.40it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
wespro-f1-chimera-hybrid-2693-v2-mkmlizer: quantized model in 19.029s
wespro-f1-chimera-hybrid-2693-v2-mkmlizer: Processed model WesPro/F1-Chimera-Hybrid-LimaRP-8B in 47.685s
wespro-f1-chimera-hybrid-2693-v2-mkmlizer: creating bucket guanaco-mkml-models
wespro-f1-chimera-hybrid-2693-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
wespro-f1-chimera-hybrid-2693-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/wespro-f1-chimera-hybrid-2693-v2
wespro-f1-chimera-hybrid-2693-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/wespro-f1-chimera-hybrid-2693-v2/config.json
wespro-f1-chimera-hybrid-2693-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/wespro-f1-chimera-hybrid-2693-v2/tokenizer_config.json
wespro-f1-chimera-hybrid-2693-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/wespro-f1-chimera-hybrid-2693-v2/special_tokens_map.json
wespro-f1-chimera-hybrid-2693-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/wespro-f1-chimera-hybrid-2693-v2/tokenizer.json
wespro-f1-chimera-hybrid-2693-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/wespro-f1-chimera-hybrid-2693-v2/flywheel_model.0.safetensors
wespro-f1-chimera-hybrid-2693-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
wespro-f1-chimera-hybrid-2693-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.
wespro-f1-chimera-hybrid-2693-v2-mkmlizer: warnings.warn(
wespro-f1-chimera-hybrid-2693-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.
wespro-f1-chimera-hybrid-2693-v2-mkmlizer: warnings.warn(
wespro-f1-chimera-hybrid-2693-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.
wespro-f1-chimera-hybrid-2693-v2-mkmlizer: warnings.warn(
wespro-f1-chimera-hybrid-2693-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()
wespro-f1-chimera-hybrid-2693-v2-mkmlizer: return self.fget.__get__(instance, owner)()
wespro-f1-chimera-hybrid-2693-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/wespro-f1-chimera-hybrid-2693-v2_reward/reward.tensors
Job wespro-f1-chimera-hybrid-2693-v2-mkmlizer completed after 73.9s with status: succeeded
Stopping job with name wespro-f1-chimera-hybrid-2693-v2-mkmlizer
Pipeline stage MKMLizer completed in 78.55s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service wespro-f1-chimera-hybrid-2693-v2
Waiting for inference service wespro-f1-chimera-hybrid-2693-v2 to be ready
Inference service wespro-f1-chimera-hybrid-2693-v2 ready after 40.248661041259766s
Pipeline stage ISVCDeployer completed in 47.87s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.989072561264038s
Received healthy response to inference request in 1.1219279766082764s
Received healthy response to inference request in 0.919586181640625s
Received healthy response to inference request in 1.1273674964904785s
Received healthy response to inference request in 1.1677982807159424s
5 requests
0 failed requests
5th percentile: 0.9600545406341553
10th percentile: 1.0005228996276856
20th percentile: 1.0814596176147462
30th percentile: 1.1230158805847168
40th percentile: 1.1251916885375977
50th percentile: 1.1273674964904785
60th percentile: 1.143539810180664
70th percentile: 1.1597121238708497
80th percentile: 1.3320531368255617
90th percentile: 1.6605628490448
95th percentile: 1.8248177051544188
99th percentile: 1.9562215900421143
mean time: 1.265150499343872
Pipeline stage StressChecker completed in 6.98s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.07s
M-Eval Dataset for topic stay_in_character is loaded
wespro-f1-chimera-hybrid_2693_v2 status is now deployed due to DeploymentManager action
wespro-f1-chimera-hybrid_2693_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of wespro-f1-chimera-hybrid_2693_v2
Running pipeline stage ISVCDeleter
Checking if service wespro-f1-chimera-hybrid-2693-v2 is running
Tearing down inference service wespro-f1-chimera-hybrid-2693-v2
Toredown service wespro-f1-chimera-hybrid-2693-v2
Pipeline stage ISVCDeleter completed in 4.48s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key wespro-f1-chimera-hybrid-2693-v2/config.json from bucket guanaco-mkml-models
Deleting key wespro-f1-chimera-hybrid-2693-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key wespro-f1-chimera-hybrid-2693-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key wespro-f1-chimera-hybrid-2693-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key wespro-f1-chimera-hybrid-2693-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key wespro-f1-chimera-hybrid-2693-v2_reward/config.json from bucket guanaco-reward-models
Deleting key wespro-f1-chimera-hybrid-2693-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key wespro-f1-chimera-hybrid-2693-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key wespro-f1-chimera-hybrid-2693-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key wespro-f1-chimera-hybrid-2693-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key wespro-f1-chimera-hybrid-2693-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key wespro-f1-chimera-hybrid-2693-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.65s
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
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
wespro-f1-chimera-hybrid_2693_v2 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics