submission_id: hastagaras-anying-8b-lla_9870_v1
developer_uid: Hastagaras
status: torndown
model_repo: Hastagaras/Anying-8B-Llama3-CrestRoot
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 100, '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': "<|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{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: 2024-06-03T03:15:15+00:00
model_name: new
model_eval_status: success
model_group: Hastagaras/Anying-8B-Lla
num_battles: 8551
num_wins: 4652
celo_rating: 1211.41
propriety_score: 0.6330645161290323
propriety_total_count: 248.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: new
ineligible_reason: propriety_total_count < 800
language_model: Hastagaras/Anying-8B-Llama3-CrestRoot
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-02
win_ratio: 0.5440299380189452
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-anying-8b-lla-9870-v1-mkmlizer
Waiting for job on hastagaras-anying-8b-lla-9870-v1-mkmlizer to finish
hastagaras-anying-8b-lla-9870-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-anying-8b-lla-9870-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-anying-8b-lla-9870-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-anying-8b-lla-9870-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-anying-8b-lla-9870-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-anying-8b-lla-9870-v1-mkmlizer: ║ /___/ ║
hastagaras-anying-8b-lla-9870-v1-mkmlizer: ║ ║
hastagaras-anying-8b-lla-9870-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-anying-8b-lla-9870-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-anying-8b-lla-9870-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-anying-8b-lla-9870-v1-mkmlizer: ║ ║
hastagaras-anying-8b-lla-9870-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-anying-8b-lla-9870-v1-mkmlizer: ║ belonging to: ║
hastagaras-anying-8b-lla-9870-v1-mkmlizer: ║ ║
hastagaras-anying-8b-lla-9870-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-anying-8b-lla-9870-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-anying-8b-lla-9870-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-anying-8b-lla-9870-v1-mkmlizer: ║ ║
hastagaras-anying-8b-lla-9870-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-anying-8b-lla-9870-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-anying-8b-lla-9870-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-anying-8b-lla-9870-v1-mkmlizer: Downloaded to shared memory in 34.899s
hastagaras-anying-8b-lla-9870-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-anying-8b-lla-9870-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-anying-8b-lla-9870-v1-mkmlizer: quantized model in 23.191s
hastagaras-anying-8b-lla-9870-v1-mkmlizer: Processed model Hastagaras/Anying-8B-Llama3-CrestRoot in 60.615s
hastagaras-anying-8b-lla-9870-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-anying-8b-lla-9870-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-anying-8b-lla-9870-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-anying-8b-lla-9870-v1
hastagaras-anying-8b-lla-9870-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-anying-8b-lla-9870-v1/tokenizer_config.json
hastagaras-anying-8b-lla-9870-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-anying-8b-lla-9870-v1/special_tokens_map.json
hastagaras-anying-8b-lla-9870-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-anying-8b-lla-9870-v1/tokenizer.json
hastagaras-anying-8b-lla-9870-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-anying-8b-lla-9870-v1/config.json
hastagaras-anying-8b-lla-9870-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-anying-8b-lla-9870-v1/flywheel_model.0.safetensors
hastagaras-anying-8b-lla-9870-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-anying-8b-lla-9870-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-anying-8b-lla-9870-v1-mkmlizer: warnings.warn(
hastagaras-anying-8b-lla-9870-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-anying-8b-lla-9870-v1-mkmlizer: warnings.warn(
hastagaras-anying-8b-lla-9870-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-anying-8b-lla-9870-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-anying-8b-lla-9870-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-anying-8b-lla-9870-v1-mkmlizer: Saving duration: 0.387s
hastagaras-anying-8b-lla-9870-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.328s
hastagaras-anying-8b-lla-9870-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-anying-8b-lla-9870-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-anying-8b-lla-9870-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-anying-8b-lla-9870-v1_reward
hastagaras-anying-8b-lla-9870-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-anying-8b-lla-9870-v1_reward/special_tokens_map.json
hastagaras-anying-8b-lla-9870-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-anying-8b-lla-9870-v1_reward/tokenizer_config.json
hastagaras-anying-8b-lla-9870-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-anying-8b-lla-9870-v1_reward/vocab.json
hastagaras-anying-8b-lla-9870-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-anying-8b-lla-9870-v1_reward/config.json
hastagaras-anying-8b-lla-9870-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-anying-8b-lla-9870-v1_reward/merges.txt
hastagaras-anying-8b-lla-9870-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-anying-8b-lla-9870-v1_reward/tokenizer.json
hastagaras-anying-8b-lla-9870-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-anying-8b-lla-9870-v1_reward/reward.tensors
Job hastagaras-anying-8b-lla-9870-v1-mkmlizer completed after 82.97s with status: succeeded
Stopping job with name hastagaras-anying-8b-lla-9870-v1-mkmlizer
Pipeline stage MKMLizer completed in 85.73s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-anying-8b-lla-9870-v1
Waiting for inference service hastagaras-anying-8b-lla-9870-v1 to be ready
Inference service hastagaras-anying-8b-lla-9870-v1 ready after 40.253626108169556s
Pipeline stage ISVCDeployer completed in 47.15s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1197597980499268s
Received healthy response to inference request in 1.3967936038970947s
Received healthy response to inference request in 1.4336071014404297s
Received healthy response to inference request in 1.3487095832824707s
Received healthy response to inference request in 1.3213894367218018s
5 requests
0 failed requests
5th percentile: 1.3268534660339355
10th percentile: 1.3323174953460692
20th percentile: 1.343245553970337
30th percentile: 1.3583263874053955
40th percentile: 1.3775599956512452
50th percentile: 1.3967936038970947
60th percentile: 1.4115190029144287
70th percentile: 1.4262444019317626
80th percentile: 1.5708376407623292
90th percentile: 1.845298719406128
95th percentile: 1.9825292587280272
99th percentile: 2.092313690185547
mean time: 1.5240519046783447
Pipeline stage StressChecker completed in 8.21s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.22s
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-anying-8b-lla_9870_v1 status is now deployed due to DeploymentManager action
hastagaras-anying-8b-lla_9870_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-anying-8b-lla_9870_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-anying-8b-lla-9870-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.58s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-anying-8b-lla-9870-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-anying-8b-lla-9870-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-anying-8b-lla-9870-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-anying-8b-lla-9870-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-anying-8b-lla-9870-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-anying-8b-lla-9870-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-anying-8b-lla-9870-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-anying-8b-lla-9870-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-anying-8b-lla-9870-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-anying-8b-lla-9870-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-anying-8b-lla-9870-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-anying-8b-lla-9870-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.52s
hastagaras-anying-8b-lla_9870_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics