submission_id: hastagaras-markites-llama3-8b_v1
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Markites-llama3-8b
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': 16, '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': True}
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': True}
timestamp: 2024-05-16T14:47:08+00:00
model_name: for-the-meme
model_eval_status: success
model_group: Hastagaras/Markites-llam
num_battles: 12363
num_wins: 6417
celo_rating: 1186.32
safety_score: 0.95
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: for-the-meme
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Markites-llama3-8b
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-16
win_ratio: 0.5190487745692793
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-markites-llama3-8b-v1-mkmlizer
Waiting for job on hastagaras-markites-llama3-8b-v1-mkmlizer to finish
hastagaras-markites-llama3-8b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-markites-llama3-8b-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-markites-llama3-8b-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-markites-llama3-8b-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-markites-llama3-8b-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-markites-llama3-8b-v1-mkmlizer: ║ /___/ ║
hastagaras-markites-llama3-8b-v1-mkmlizer: ║ ║
hastagaras-markites-llama3-8b-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-markites-llama3-8b-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-markites-llama3-8b-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-markites-llama3-8b-v1-mkmlizer: ║ ║
hastagaras-markites-llama3-8b-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-markites-llama3-8b-v1-mkmlizer: ║ belonging to: ║
hastagaras-markites-llama3-8b-v1-mkmlizer: ║ ║
hastagaras-markites-llama3-8b-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-markites-llama3-8b-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-markites-llama3-8b-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-markites-llama3-8b-v1-mkmlizer: ║ ║
hastagaras-markites-llama3-8b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-markites-llama3-8b-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-markites-llama3-8b-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-markites-llama3-8b-v1-mkmlizer: Downloaded to shared memory in 30.811s
hastagaras-markites-llama3-8b-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-markites-llama3-8b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-markites-llama3-8b-v1-mkmlizer: Processed model Hastagaras/Markites-llama3-8b in 49.661s
hastagaras-markites-llama3-8b-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-markites-llama3-8b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-markites-llama3-8b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-markites-llama3-8b-v1
hastagaras-markites-llama3-8b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-markites-llama3-8b-v1/config.json
hastagaras-markites-llama3-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-markites-llama3-8b-v1/tokenizer_config.json
hastagaras-markites-llama3-8b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-markites-llama3-8b-v1/special_tokens_map.json
hastagaras-markites-llama3-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-markites-llama3-8b-v1/tokenizer.json
hastagaras-markites-llama3-8b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-markites-llama3-8b-v1/flywheel_model.0.safetensors
hastagaras-markites-llama3-8b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-markites-llama3-8b-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-markites-llama3-8b-v1-mkmlizer: warnings.warn(
hastagaras-markites-llama3-8b-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-markites-llama3-8b-v1-mkmlizer: warnings.warn(
hastagaras-markites-llama3-8b-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-markites-llama3-8b-v1-mkmlizer: warnings.warn(
hastagaras-markites-llama3-8b-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-markites-llama3-8b-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-markites-llama3-8b-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-markites-llama3-8b-v1-mkmlizer: Saving duration: 0.248s
hastagaras-markites-llama3-8b-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.027s
hastagaras-markites-llama3-8b-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-markites-llama3-8b-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-markites-llama3-8b-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-markites-llama3-8b-v1_reward
hastagaras-markites-llama3-8b-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-markites-llama3-8b-v1_reward/special_tokens_map.json
hastagaras-markites-llama3-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-markites-llama3-8b-v1_reward/tokenizer_config.json
hastagaras-markites-llama3-8b-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-markites-llama3-8b-v1_reward/merges.txt
hastagaras-markites-llama3-8b-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-markites-llama3-8b-v1_reward/vocab.json
hastagaras-markites-llama3-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-markites-llama3-8b-v1_reward/tokenizer.json
hastagaras-markites-llama3-8b-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-markites-llama3-8b-v1_reward/config.json
hastagaras-markites-llama3-8b-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-markites-llama3-8b-v1_reward/reward.tensors
Job hastagaras-markites-llama3-8b-v1-mkmlizer completed after 73.59s with status: succeeded
Stopping job with name hastagaras-markites-llama3-8b-v1-mkmlizer
Pipeline stage MKMLizer completed in 78.87s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-markites-llama3-8b-v1
Waiting for inference service hastagaras-markites-llama3-8b-v1 to be ready
Inference service hastagaras-markites-llama3-8b-v1 ready after 80.47526693344116s
Pipeline stage ISVCDeployer completed in 88.17s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0920591354370117s
Received healthy response to inference request in 1.0698890686035156s
Received healthy response to inference request in 1.2179081439971924s
Received healthy response to inference request in 1.2305891513824463s
Received healthy response to inference request in 1.2599925994873047s
5 requests
0 failed requests
5th percentile: 1.099492883682251
10th percentile: 1.1290966987609863
20th percentile: 1.188304328918457
30th percentile: 1.220444345474243
40th percentile: 1.2255167484283447
50th percentile: 1.2305891513824463
60th percentile: 1.2423505306243896
70th percentile: 1.254111909866333
80th percentile: 1.4264059066772463
90th percentile: 1.759232521057129
95th percentile: 1.92564582824707
99th percentile: 2.0587764739990235
mean time: 1.3740876197814942
Pipeline stage StressChecker completed in 7.72s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.04s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-markites-llama3-8b_v1 status is now deployed due to DeploymentManager action
hastagaras-markites-llama3-8b_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics