submission_id: hastagaras-llama-3-8b-okay_v13
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: 2024-05-15T00:36:38+00:00
model_name: just-to-make-sure
model_eval_status: success
model_group: Hastagaras/llama-3-8b-ok
num_battles: 10959
num_wins: 6091
celo_rating: 1228.27
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: 0.5557988867597409
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama-3-8b-okay-v13-mkmlizer
Waiting for job on hastagaras-llama-3-8b-okay-v13-mkmlizer to finish
hastagaras-llama-3-8b-okay-v13-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama-3-8b-okay-v13-mkmlizer: ║ _____ __ __ ║
hastagaras-llama-3-8b-okay-v13-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-llama-3-8b-okay-v13-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-llama-3-8b-okay-v13-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-llama-3-8b-okay-v13-mkmlizer: ║ /___/ ║
hastagaras-llama-3-8b-okay-v13-mkmlizer: ║ ║
hastagaras-llama-3-8b-okay-v13-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-llama-3-8b-okay-v13-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-llama-3-8b-okay-v13-mkmlizer: ║ https://mk1.ai ║
hastagaras-llama-3-8b-okay-v13-mkmlizer: ║ ║
hastagaras-llama-3-8b-okay-v13-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-llama-3-8b-okay-v13-mkmlizer: ║ belonging to: ║
hastagaras-llama-3-8b-okay-v13-mkmlizer: ║ ║
hastagaras-llama-3-8b-okay-v13-mkmlizer: ║ Chai Research Corp. ║
hastagaras-llama-3-8b-okay-v13-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-llama-3-8b-okay-v13-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-llama-3-8b-okay-v13-mkmlizer: ║ ║
hastagaras-llama-3-8b-okay-v13-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama-3-8b-okay-v13-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-v13-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-llama-3-8b-okay-v13-mkmlizer: Downloaded to shared memory in 27.247s
hastagaras-llama-3-8b-okay-v13-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama-3-8b-okay-v13-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama-3-8b-okay-v13-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 120.15it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 138.19it/s] Loading 0: 16%|█▋ | 48/291 [00:00<00:01, 146.63it/s] Loading 0: 22%|██▏ | 63/291 [00:00<00:01, 145.34it/s] Loading 0: 27%|██▋ | 78/291 [00:00<00:01, 139.45it/s] Loading 0: 32%|███▏ | 92/291 [00:00<00:02, 75.33it/s] Loading 0: 36%|███▌ | 104/291 [00:01<00:02, 82.44it/s] Loading 0: 42%|████▏ | 121/291 [00:01<00:01, 100.12it/s] Loading 0: 47%|████▋ | 138/291 [00:01<00:01, 115.18it/s] Loading 0: 52%|█████▏ | 152/291 [00:01<00:01, 120.62it/s] Loading 0: 57%|█████▋ | 166/291 [00:01<00:01, 124.84it/s] Loading 0: 62%|██████▏ | 181/291 [00:01<00:00, 129.38it/s] Loading 0: 67%|██████▋ | 195/291 [00:01<00:01, 75.55it/s] Loading 0: 72%|███████▏ | 210/291 [00:02<00:00, 89.14it/s] Loading 0: 77%|███████▋ | 223/291 [00:02<00:00, 97.50it/s] Loading 0: 82%|████████▏ | 238/291 [00:02<00:00, 106.77it/s] Loading 0: 88%|████████▊ | 255/291 [00:02<00:00, 117.93it/s] Loading 0: 92%|█████████▏| 269/291 [00:02<00:00, 122.14it/s] Loading 0: 97%|█████████▋| 283/291 [00:02<00:00, 123.24it/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-v13-mkmlizer: quantized model in 18.885s
hastagaras-llama-3-8b-okay-v13-mkmlizer: Processed model Hastagaras/llama-3-8b-okay in 47.090s
hastagaras-llama-3-8b-okay-v13-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama-3-8b-okay-v13-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama-3-8b-okay-v13-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v13
hastagaras-llama-3-8b-okay-v13-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v13/tokenizer_config.json
hastagaras-llama-3-8b-okay-v13-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v13/config.json
hastagaras-llama-3-8b-okay-v13-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v13/special_tokens_map.json
hastagaras-llama-3-8b-okay-v13-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v13/tokenizer.json
hastagaras-llama-3-8b-okay-v13-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v13/flywheel_model.0.safetensors
hastagaras-llama-3-8b-okay-v13-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama-3-8b-okay-v13-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-v13-mkmlizer: warnings.warn(
hastagaras-llama-3-8b-okay-v13-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-v13-mkmlizer: warnings.warn(
hastagaras-llama-3-8b-okay-v13-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-v13-mkmlizer: warnings.warn(
hastagaras-llama-3-8b-okay-v13-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-v13-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-llama-3-8b-okay-v13-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama-3-8b-okay-v13-mkmlizer: Saving duration: 0.233s
hastagaras-llama-3-8b-okay-v13-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.033s
hastagaras-llama-3-8b-okay-v13-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama-3-8b-okay-v13-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama-3-8b-okay-v13-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v13_reward
hastagaras-llama-3-8b-okay-v13-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v13_reward/config.json
hastagaras-llama-3-8b-okay-v13-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v13_reward/special_tokens_map.json
hastagaras-llama-3-8b-okay-v13-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v13_reward/tokenizer_config.json
hastagaras-llama-3-8b-okay-v13-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v13_reward/merges.txt
hastagaras-llama-3-8b-okay-v13-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v13_reward/vocab.json
hastagaras-llama-3-8b-okay-v13-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v13_reward/tokenizer.json
hastagaras-llama-3-8b-okay-v13-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v13_reward/reward.tensors
Job hastagaras-llama-3-8b-okay-v13-mkmlizer completed after 73.43s with status: succeeded
Stopping job with name hastagaras-llama-3-8b-okay-v13-mkmlizer
Pipeline stage MKMLizer completed in 76.38s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama-3-8b-okay-v13
Waiting for inference service hastagaras-llama-3-8b-okay-v13 to be ready
Inference service hastagaras-llama-3-8b-okay-v13 ready after 30.201669692993164s
Pipeline stage ISVCDeployer completed in 37.28s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8662166595458984s
Received healthy response to inference request in 2.0234487056732178s
Received healthy response to inference request in 2.089007616043091s
Received healthy response to inference request in 2.0457887649536133s
Received healthy response to inference request in 1.9956064224243164s
5 requests
0 failed requests
5th percentile: 2.001174879074097
10th percentile: 2.006743335723877
20th percentile: 2.0178802490234373
30th percentile: 2.0279167175292967
40th percentile: 2.036852741241455
50th percentile: 2.0457887649536133
60th percentile: 2.063076305389404
70th percentile: 2.0803638458251954
80th percentile: 2.2444494247436526
90th percentile: 2.5553330421447753
95th percentile: 2.7107748508453366
99th percentile: 2.835128297805786
mean time: 2.204013633728027
Pipeline stage StressChecker completed in 11.92s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-llama-3-8b-okay_v13 status is now deployed due to DeploymentManager action
hastagaras-llama-3-8b-okay_v13 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama-3-8b-okay_v13
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama-3-8b-okay-v13 is running
Connection pool is full, discarding connection: %s
Tearing down inference service hastagaras-llama-3-8b-okay-v13
Toredown service hastagaras-llama-3-8b-okay-v13
Pipeline stage ISVCDeleter completed in 5.48s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-okay-v13/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-okay-v13/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-okay-v13/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-okay-v13/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-okay-v13/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-okay-v13_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v13_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v13_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v13_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v13_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v13_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v13_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.98s
hastagaras-llama-3-8b-okay_v13 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics