developer_uid: nguyenzzz
submission_id: meseca-sophon-2_v2
model_name: meseca-sophon-2_v1
model_group: meseca/sophon-2
status: torndown
timestamp: 2024-05-18T11:35:19+00:00
num_battles: 17041
num_wins: 9053
celo_rating: 1199.73
family_friendly_score: 0.0
submission_type: basic
model_repo: meseca/sophon-2
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: meseca-sophon-2_v1
is_internal_developer: False
language_model: meseca/sophon-2
model_size: 8B
ranking_group: single
us_pacific_date: 2024-05-18
win_ratio: 0.5312481661874303
generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 200, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|im_start|>system\n{bot_name}'s personality: {memory}\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': True}
model_eval_status: success
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\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 meseca-sophon-2-v2-mkmlizer
Waiting for job on meseca-sophon-2-v2-mkmlizer to finish
meseca-sophon-2-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
meseca-sophon-2-v2-mkmlizer: ║ _____ __ __ ║
meseca-sophon-2-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
meseca-sophon-2-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
meseca-sophon-2-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
meseca-sophon-2-v2-mkmlizer: ║ /___/ ║
meseca-sophon-2-v2-mkmlizer: ║ ║
meseca-sophon-2-v2-mkmlizer: ║ Version: 0.8.14 ║
meseca-sophon-2-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
meseca-sophon-2-v2-mkmlizer: ║ https://mk1.ai ║
meseca-sophon-2-v2-mkmlizer: ║ ║
meseca-sophon-2-v2-mkmlizer: ║ The license key for the current software has been verified as ║
meseca-sophon-2-v2-mkmlizer: ║ belonging to: ║
meseca-sophon-2-v2-mkmlizer: ║ ║
meseca-sophon-2-v2-mkmlizer: ║ Chai Research Corp. ║
meseca-sophon-2-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
meseca-sophon-2-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
meseca-sophon-2-v2-mkmlizer: ║ ║
meseca-sophon-2-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
meseca-sophon-2-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.
meseca-sophon-2-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
meseca-sophon-2-v2-mkmlizer: Downloaded to shared memory in 27.328s
meseca-sophon-2-v2-mkmlizer: quantizing model to /dev/shm/model_cache
meseca-sophon-2-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
meseca-sophon-2-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:01, 191.67it/s] Loading 0: 14%|█▍ | 41/291 [00:00<00:01, 190.96it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 211.27it/s] Loading 0: 30%|███ | 88/291 [00:00<00:02, 97.16it/s] Loading 0: 38%|███▊ | 111/291 [00:00<00:01, 122.35it/s] Loading 0: 45%|████▌ | 131/291 [00:00<00:01, 137.23it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:00, 163.45it/s] Loading 0: 62%|██████▏ | 179/291 [00:01<00:00, 178.08it/s] Loading 0: 69%|██████▊ | 200/291 [00:01<00:00, 112.52it/s] Loading 0: 76%|███████▌ | 220/291 [00:01<00:00, 127.75it/s] Loading 0: 84%|████████▍ | 244/291 [00:01<00:00, 150.77it/s] Loading 0: 91%|█████████ | 265/291 [00:01<00:00, 162.07it/s] Loading 0: 99%|█████████▊| 287/291 [00:06<00:00, 14.20it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
meseca-sophon-2-v2-mkmlizer: quantized model in 16.942s
meseca-sophon-2-v2-mkmlizer: Processed model meseca/sophon-2 in 45.250s
meseca-sophon-2-v2-mkmlizer: creating bucket guanaco-mkml-models
meseca-sophon-2-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
meseca-sophon-2-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/meseca-sophon-2-v2
meseca-sophon-2-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/meseca-sophon-2-v2/config.json
meseca-sophon-2-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/meseca-sophon-2-v2/special_tokens_map.json
meseca-sophon-2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/meseca-sophon-2-v2/tokenizer_config.json
meseca-sophon-2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/meseca-sophon-2-v2/tokenizer.json
meseca-sophon-2-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/meseca-sophon-2-v2/flywheel_model.0.safetensors
meseca-sophon-2-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
meseca-sophon-2-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.
meseca-sophon-2-v2-mkmlizer: warnings.warn(
meseca-sophon-2-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.
meseca-sophon-2-v2-mkmlizer: warnings.warn(
meseca-sophon-2-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.
meseca-sophon-2-v2-mkmlizer: warnings.warn(
meseca-sophon-2-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()
meseca-sophon-2-v2-mkmlizer: return self.fget.__get__(instance, owner)()
meseca-sophon-2-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
meseca-sophon-2-v2-mkmlizer: Saving duration: 0.227s
meseca-sophon-2-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.510s
meseca-sophon-2-v2-mkmlizer: creating bucket guanaco-reward-models
meseca-sophon-2-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
meseca-sophon-2-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/meseca-sophon-2-v2_reward
meseca-sophon-2-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/meseca-sophon-2-v2_reward/config.json
meseca-sophon-2-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/meseca-sophon-2-v2_reward/special_tokens_map.json
meseca-sophon-2-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/meseca-sophon-2-v2_reward/vocab.json
meseca-sophon-2-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/meseca-sophon-2-v2_reward/merges.txt
meseca-sophon-2-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/meseca-sophon-2-v2_reward/tokenizer_config.json
meseca-sophon-2-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/meseca-sophon-2-v2_reward/tokenizer.json
meseca-sophon-2-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/meseca-sophon-2-v2_reward/reward.tensors
Job meseca-sophon-2-v2-mkmlizer completed after 73.41s with status: succeeded
Stopping job with name meseca-sophon-2-v2-mkmlizer
Pipeline stage MKMLizer completed in 76.17s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service meseca-sophon-2-v2
Waiting for inference service meseca-sophon-2-v2 to be ready
Inference service meseca-sophon-2-v2 ready after 30.1957426071167s
Pipeline stage ISVCDeployer completed in 37.28s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9405746459960938s
Received healthy response to inference request in 1.2037982940673828s
Received healthy response to inference request in 1.2299187183380127s
Received healthy response to inference request in 1.259140968322754s
Received healthy response to inference request in 0.9674019813537598s
5 requests
0 failed requests
5th percentile: 1.0146812438964843
10th percentile: 1.061960506439209
20th percentile: 1.1565190315246583
30th percentile: 1.2090223789215089
40th percentile: 1.2194705486297608
50th percentile: 1.2299187183380127
60th percentile: 1.2416076183319091
70th percentile: 1.2532965183258056
80th percentile: 1.3954277038574219
90th percentile: 1.6680011749267578
95th percentile: 1.8042879104614258
99th percentile: 1.91331729888916
mean time: 1.3201669216156007
Pipeline stage StressChecker completed in 7.26s
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 0.05s
M-Eval Dataset for topic stay_in_character is loaded
meseca-sophon-2_v2 status is now deployed due to DeploymentManager action
meseca-sophon-2_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of meseca-sophon-2_v2
Running pipeline stage ISVCDeleter
Checking if service meseca-sophon-2-v2 is running
Tearing down inference service meseca-sophon-2-v2
Toredown service meseca-sophon-2-v2
Pipeline stage ISVCDeleter completed in 3.62s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key meseca-sophon-2-v2/config.json from bucket guanaco-mkml-models
Deleting key meseca-sophon-2-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key meseca-sophon-2-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key meseca-sophon-2-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key meseca-sophon-2-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key meseca-sophon-2-v2_reward/config.json from bucket guanaco-reward-models
Deleting key meseca-sophon-2-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key meseca-sophon-2-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key meseca-sophon-2-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key meseca-sophon-2-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key meseca-sophon-2-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key meseca-sophon-2-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.88s
meseca-sophon-2_v2 status is now torndown due to DeploymentManager action