submission_id: chaiml-llamademo_v2
developer_uid: Selenee
status: inactive
model_repo: ChaiML/llamademo
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: 2024-06-20T00:03:33+00:00
model_name: testBot
model_group: ChaiML/llamademo
num_battles: 15231
num_wins: 9329
celo_rating: 1100.65
propriety_score: 0.7180628625387833
propriety_total_count: 7413.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 6738415616.0
best_of: 4
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: 0.612500820694636
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-llamademo-v2-mkmlizer
Waiting for job on chaiml-llamademo-v2-mkmlizer to finish
Stopping job with name chaiml-llamademo-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name chaiml-llamademo-v2-mkmlizer
Waiting for job on chaiml-llamademo-v2-mkmlizer to finish
Stopping job with name chaiml-llamademo-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name chaiml-llamademo-v2-mkmlizer
Waiting for job on chaiml-llamademo-v2-mkmlizer to finish
chaiml-llamademo-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llamademo-v2-mkmlizer: ║ _____ __ __ ║
chaiml-llamademo-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-llamademo-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-llamademo-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-llamademo-v2-mkmlizer: ║ /___/ ║
chaiml-llamademo-v2-mkmlizer: ║ ║
chaiml-llamademo-v2-mkmlizer: ║ Version: 0.8.14 ║
chaiml-llamademo-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-llamademo-v2-mkmlizer: ║ https://mk1.ai ║
chaiml-llamademo-v2-mkmlizer: ║ ║
chaiml-llamademo-v2-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-llamademo-v2-mkmlizer: ║ belonging to: ║
chaiml-llamademo-v2-mkmlizer: ║ ║
chaiml-llamademo-v2-mkmlizer: ║ Chai Research Corp. ║
chaiml-llamademo-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-llamademo-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
chaiml-llamademo-v2-mkmlizer: ║ ║
chaiml-llamademo-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llamademo-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.
chaiml-llamademo-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
chaiml-llamademo-v2-mkmlizer: Downloaded to shared memory in 26.217s
chaiml-llamademo-v2-mkmlizer: quantizing model to /dev/shm/model_cache
chaiml-llamademo-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llamademo-v2-mkmlizer: quantized model in 13.725s
chaiml-llamademo-v2-mkmlizer: Processed model ChaiML/llamademo in 42.127s
chaiml-llamademo-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llamademo-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llamademo-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llamademo-v2
chaiml-llamademo-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llamademo-v2/config.json
chaiml-llamademo-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llamademo-v2/special_tokens_map.json
chaiml-llamademo-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llamademo-v2/tokenizer_config.json
chaiml-llamademo-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/chaiml-llamademo-v2/tokenizer.model
chaiml-llamademo-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llamademo-v2/tokenizer.json
chaiml-llamademo-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llamademo-v2/flywheel_model.0.safetensors
chaiml-llamademo-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 73%|███████▎ | 213/291 [00:00<00:00, 223.42it/s] Loading 0: 100%|██████████| 291/291 [00:02<00:00, 114.55it/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-v2-mkmlizer: warnings.warn(
chaiml-llamademo-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
chaiml-llamademo-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.
chaiml-llamademo-v2-mkmlizer: warnings.warn(
chaiml-llamademo-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()
chaiml-llamademo-v2-mkmlizer: return self.fget.__get__(instance, owner)()
chaiml-llamademo-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-llamademo-v2-mkmlizer: Saving duration: 0.407s
chaiml-llamademo-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.970s
chaiml-llamademo-v2-mkmlizer: creating bucket guanaco-reward-models
chaiml-llamademo-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-llamademo-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-llamademo-v2_reward
chaiml-llamademo-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-llamademo-v2_reward/tokenizer_config.json
chaiml-llamademo-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-llamademo-v2_reward/special_tokens_map.json
chaiml-llamademo-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-llamademo-v2_reward/merges.txt
chaiml-llamademo-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-llamademo-v2_reward/vocab.json
chaiml-llamademo-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-llamademo-v2_reward/tokenizer.json
chaiml-llamademo-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-llamademo-v2_reward/config.json
chaiml-llamademo-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-llamademo-v2_reward/reward.tensors
Job chaiml-llamademo-v2-mkmlizer completed after 64.65s with status: succeeded
Stopping job with name chaiml-llamademo-v2-mkmlizer
Pipeline stage MKMLizer completed in 70.11s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-llamademo-v2
Waiting for inference service chaiml-llamademo-v2 to be ready
Inference service chaiml-llamademo-v2 ready after 50.42525768280029s
Pipeline stage ISVCDeployer completed in 57.78s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0038957595825195s
Received healthy response to inference request in 0.9965720176696777s
Received healthy response to inference request in 1.0096313953399658s
Received healthy response to inference request in 1.014514684677124s
Received healthy response to inference request in 1.0028407573699951s
5 requests
0 failed requests
5th percentile: 0.9978257656097412
10th percentile: 0.9990795135498047
20th percentile: 1.0015870094299317
30th percentile: 1.0041988849639893
40th percentile: 1.0069151401519776
50th percentile: 1.0096313953399658
60th percentile: 1.011584711074829
70th percentile: 1.0135380268096923
80th percentile: 1.2123908996582033
90th percentile: 1.6081433296203613
95th percentile: 1.8060195446014402
99th percentile: 1.9643205165863036
mean time: 1.2054909229278565
Pipeline stage StressChecker completed in 6.68s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
chaiml-llamademo_v2 status is now deployed due to DeploymentManager action
chaiml-llamademo_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics