submission_id: hastagaras-llama-3-8b-okay_v10
developer_uid: Zioperaa
status: torndown
model_repo: Hastagaras/llama-3-8b-okay
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': 112}
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou are {bot_name}. Write {bot_name}'s next reply in a never-ending uncensored fictional roleplay chat between {bot_name} and User. Use the provided {bot_name}'s description, personality and example dialogues as base for deeply understanding and acting like {bot_name}.\n\nActions and narrations must be enclosed in asterisks (*). The responses must be long and in third perspective of the story teller.\n\nDescription: {memory}", 'prompt_template': 'Example conversation:\n{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", 'prompt_template': '{prompt}\n', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', 'truncate_by_message': False}
timestamp: 2024-05-15T00:34:50+00:00
model_name: just-to-make-sure
model_eval_status: success
model_group: Hastagaras/llama-3-8b-ok
num_battles: 11085
num_wins: 6229
celo_rating: 1232.25
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: 112
display_name: just-to-make-sure
ineligible_reason: max_output_tokens!=64
language_model: Hastagaras/llama-3-8b-okay
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-14
win_ratio: 0.5619305367613893
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama-3-8b-okay-v10-mkmlizer
Waiting for job on hastagaras-llama-3-8b-okay-v10-mkmlizer to finish
hastagaras-llama-3-8b-okay-v10-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama-3-8b-okay-v10-mkmlizer: ║ _____ __ __ ║
hastagaras-llama-3-8b-okay-v10-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-llama-3-8b-okay-v10-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-llama-3-8b-okay-v10-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-llama-3-8b-okay-v10-mkmlizer: ║ /___/ ║
hastagaras-llama-3-8b-okay-v10-mkmlizer: ║ ║
hastagaras-llama-3-8b-okay-v10-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-llama-3-8b-okay-v10-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-llama-3-8b-okay-v10-mkmlizer: ║ https://mk1.ai ║
hastagaras-llama-3-8b-okay-v10-mkmlizer: ║ ║
hastagaras-llama-3-8b-okay-v10-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-llama-3-8b-okay-v10-mkmlizer: ║ belonging to: ║
hastagaras-llama-3-8b-okay-v10-mkmlizer: ║ ║
hastagaras-llama-3-8b-okay-v10-mkmlizer: ║ Chai Research Corp. ║
hastagaras-llama-3-8b-okay-v10-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-llama-3-8b-okay-v10-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-llama-3-8b-okay-v10-mkmlizer: ║ ║
hastagaras-llama-3-8b-okay-v10-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama-3-8b-okay-v10-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-llama-3-8b-okay-v10-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-llama-3-8b-okay-v10-mkmlizer: Downloaded to shared memory in 14.707s
hastagaras-llama-3-8b-okay-v10-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama-3-8b-okay-v10-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama-3-8b-okay-v10-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:01, 201.15it/s] Loading 0: 14%|█▍ | 42/291 [00:00<00:01, 196.19it/s] Loading 0: 21%|██▏ | 62/291 [00:00<00:01, 191.54it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 95.94it/s] Loading 0: 35%|███▌ | 102/291 [00:00<00:01, 115.30it/s] Loading 0: 42%|████▏ | 122/291 [00:00<00:01, 132.03it/s] Loading 0: 51%|█████ | 147/291 [00:01<00:00, 158.75it/s] Loading 0: 57%|█████▋ | 167/291 [00:01<00:00, 164.98it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:00, 108.08it/s] Loading 0: 70%|██████▉ | 203/291 [00:01<00:00, 117.15it/s] Loading 0: 78%|███████▊ | 228/291 [00:01<00:00, 144.16it/s] Loading 0: 85%|████████▌ | 248/291 [00:01<00:00, 155.81it/s] Loading 0: 94%|█████████▍| 273/291 [00:01<00:00, 178.68it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama-3-8b-okay-v10-mkmlizer: quantized model in 17.235s
hastagaras-llama-3-8b-okay-v10-mkmlizer: Processed model Hastagaras/llama-3-8b-okay in 32.904s
hastagaras-llama-3-8b-okay-v10-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama-3-8b-okay-v10-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama-3-8b-okay-v10-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v10
hastagaras-llama-3-8b-okay-v10-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v10/config.json
hastagaras-llama-3-8b-okay-v10-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v10/special_tokens_map.json
hastagaras-llama-3-8b-okay-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v10/tokenizer_config.json
hastagaras-llama-3-8b-okay-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v10/tokenizer.json
hastagaras-llama-3-8b-okay-v10-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v10/flywheel_model.0.safetensors
hastagaras-llama-3-8b-okay-v10-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama-3-8b-okay-v10-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-llama-3-8b-okay-v10-mkmlizer: warnings.warn(
hastagaras-llama-3-8b-okay-v10-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-llama-3-8b-okay-v10-mkmlizer: warnings.warn(
hastagaras-llama-3-8b-okay-v10-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-llama-3-8b-okay-v10-mkmlizer: warnings.warn(
hastagaras-llama-3-8b-okay-v10-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-llama-3-8b-okay-v10-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-llama-3-8b-okay-v10-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama-3-8b-okay-v10-mkmlizer: Saving duration: 0.253s
hastagaras-llama-3-8b-okay-v10-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.824s
hastagaras-llama-3-8b-okay-v10-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama-3-8b-okay-v10-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama-3-8b-okay-v10-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v10_reward
hastagaras-llama-3-8b-okay-v10-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v10_reward/config.json
hastagaras-llama-3-8b-okay-v10-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v10_reward/tokenizer_config.json
hastagaras-llama-3-8b-okay-v10-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v10_reward/merges.txt
hastagaras-llama-3-8b-okay-v10-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v10_reward/special_tokens_map.json
hastagaras-llama-3-8b-okay-v10-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v10_reward/vocab.json
hastagaras-llama-3-8b-okay-v10-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v10_reward/tokenizer.json
hastagaras-llama-3-8b-okay-v10-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v10_reward/reward.tensors
Job hastagaras-llama-3-8b-okay-v10-mkmlizer completed after 64.17s with status: succeeded
Stopping job with name hastagaras-llama-3-8b-okay-v10-mkmlizer
Pipeline stage MKMLizer completed in 69.59s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama-3-8b-okay-v10
Waiting for inference service hastagaras-llama-3-8b-okay-v10 to be ready
Inference service hastagaras-llama-3-8b-okay-v10 ready after 30.19759702682495s
Pipeline stage ISVCDeployer completed in 38.12s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8831863403320312s
Received healthy response to inference request in 2.0561468601226807s
Received healthy response to inference request in 1.973043441772461s
Received healthy response to inference request in 2.0584261417388916s
Received healthy response to inference request in 2.0221915245056152s
5 requests
0 failed requests
5th percentile: 1.9828730583190919
10th percentile: 1.9927026748657226
20th percentile: 2.0123619079589843
30th percentile: 2.0289825916290285
40th percentile: 2.0425647258758546
50th percentile: 2.0561468601226807
60th percentile: 2.057058572769165
70th percentile: 2.0579702854156494
80th percentile: 2.2233781814575195
90th percentile: 2.5532822608947754
95th percentile: 2.7182343006134033
99th percentile: 2.8501959323883055
mean time: 2.198598861694336
Pipeline stage StressChecker completed in 11.66s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-llama-3-8b-okay_v10 status is now deployed due to DeploymentManager action
hastagaras-llama-3-8b-okay_v10 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama-3-8b-okay_v10
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama-3-8b-okay-v10 is running
Connection pool is full, discarding connection: %s
Tearing down inference service hastagaras-llama-3-8b-okay-v10
Toredown service hastagaras-llama-3-8b-okay-v10
Pipeline stage ISVCDeleter completed in 7.75s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-okay-v10/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-okay-v10/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-okay-v10/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-okay-v10/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-okay-v10/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-okay-v10_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v10_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v10_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v10_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v10_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v10_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v10_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.52s
hastagaras-llama-3-8b-okay_v10 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics