submission_id: chaiml-llamademo_v4
developer_uid: Selenee
status: inactive
model_repo: ChaiML/llamademo
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 100.0, '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': 6, '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: 2024-06-20T00:05:02+00:00
model_name: testBot
model_group: ChaiML/llamademo
num_battles: 13822
num_wins: 3715
celo_rating: 817.1
propriety_score: 0.6573949454164797
propriety_total_count: 6687.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 6738415616.0
best_of: 6
max_input_tokens: 512
max_output_tokens: 64
display_name: testBot
ineligible_reason: None
language_model: ChaiML/llamademo
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-19
win_ratio: 0.2687744175951382
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-llamademo-v4-mkmlizer
Waiting for job on chaiml-llamademo-v4-mkmlizer to finish
chaiml-llamademo-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llamademo-v4-mkmlizer: ║ _____ __ __ ║
chaiml-llamademo-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-llamademo-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-llamademo-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-llamademo-v4-mkmlizer: ║ /___/ ║
chaiml-llamademo-v4-mkmlizer: ║ ║
chaiml-llamademo-v4-mkmlizer: ║ Version: 0.8.14 ║
chaiml-llamademo-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-llamademo-v4-mkmlizer: ║ https://mk1.ai ║
chaiml-llamademo-v4-mkmlizer: ║ ║
chaiml-llamademo-v4-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-llamademo-v4-mkmlizer: ║ belonging to: ║
chaiml-llamademo-v4-mkmlizer: ║ ║
chaiml-llamademo-v4-mkmlizer: ║ Chai Research Corp. ║
chaiml-llamademo-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-llamademo-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
chaiml-llamademo-v4-mkmlizer: ║ ║
chaiml-llamademo-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llamademo-v4-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.
chaiml-llamademo-v4-mkmlizer: warnings.warn(warning_message, FutureWarning)
chaiml-llamademo-v4-mkmlizer: Downloaded to shared memory in 12.958s
chaiml-llamademo-v4-mkmlizer: quantizing model to /dev/shm/model_cache
chaiml-llamademo-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llamademo-v4-mkmlizer: Processed model ChaiML/llamademo in 29.089s
chaiml-llamademo-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llamademo-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llamademo-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llamademo-v4
chaiml-llamademo-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/chaiml-llamademo-v4/tokenizer.model
chaiml-llamademo-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llamademo-v4/config.json
chaiml-llamademo-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llamademo-v4/tokenizer_config.json
chaiml-llamademo-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llamademo-v4/special_tokens_map.json
chaiml-llamademo-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llamademo-v4/tokenizer.json
chaiml-llamademo-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llamademo-v4/flywheel_model.0.safetensors
chaiml-llamademo-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
chaiml-llamademo-v4-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 73%|███████▎ | 213/291 [00:01<00:00, 182.44it/s] Loading 0: 100%|██████████| 291/291 [00:02<00:00, 108.48it/s] /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.
chaiml-llamademo-v4-mkmlizer: warnings.warn(
chaiml-llamademo-v4-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.
chaiml-llamademo-v4-mkmlizer: warnings.warn(
chaiml-llamademo-v4-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.
chaiml-llamademo-v4-mkmlizer: warnings.warn(
chaiml-llamademo-v4-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()
chaiml-llamademo-v4-mkmlizer: return self.fget.__get__(instance, owner)()
chaiml-llamademo-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-llamademo-v4-mkmlizer: Saving duration: 0.408s
chaiml-llamademo-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.035s
chaiml-llamademo-v4-mkmlizer: creating bucket guanaco-reward-models
chaiml-llamademo-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-llamademo-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-llamademo-v4_reward
chaiml-llamademo-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-llamademo-v4_reward/special_tokens_map.json
chaiml-llamademo-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-llamademo-v4_reward/tokenizer_config.json
chaiml-llamademo-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-llamademo-v4_reward/vocab.json
chaiml-llamademo-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-llamademo-v4_reward/merges.txt
chaiml-llamademo-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-llamademo-v4_reward/config.json
chaiml-llamademo-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-llamademo-v4_reward/tokenizer.json
chaiml-llamademo-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-llamademo-v4_reward/reward.tensors
Job chaiml-llamademo-v4-mkmlizer completed after 52.61s with status: succeeded
Stopping job with name chaiml-llamademo-v4-mkmlizer
Pipeline stage MKMLizer completed in 55.70s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-llamademo-v4
Waiting for inference service chaiml-llamademo-v4 to be ready
Inference service chaiml-llamademo-v4 ready after 51.450751066207886s
Pipeline stage ISVCDeployer completed in 58.20s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8936913013458252s
Received healthy response to inference request in 1.0059661865234375s
Received healthy response to inference request in 1.0143165588378906s
Received healthy response to inference request in 1.0334653854370117s
Received healthy response to inference request in 1.0271549224853516s
5 requests
0 failed requests
5th percentile: 1.007636260986328
10th percentile: 1.0093063354492187
20th percentile: 1.012646484375
30th percentile: 1.0168842315673827
40th percentile: 1.0220195770263671
50th percentile: 1.0271549224853516
60th percentile: 1.0296791076660157
70th percentile: 1.0322032928466798
80th percentile: 1.2055105686187746
90th percentile: 1.5496009349823
95th percentile: 1.7216461181640623
99th percentile: 1.8592822647094727
mean time: 1.1949188709259033
Pipeline stage StressChecker completed in 6.64s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
chaiml-llamademo_v4 status is now deployed due to DeploymentManager action
chaiml-llamademo_v4 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics