submission_id: alkahestry-llmama3-monol_3361_v2
developer_uid: alkacchi
status: inactive
model_repo: alkahestry/Llmama3-Monologue-8B
reward_repo: Jellywibble/CHAI_alignment_reward_model
generation_params: {'temperature': 0.72, 'top_p': 1.0, 'min_p': 0.075, 'top_k': 1000, 'presence_penalty': 0.82, 'frequency_penalty': 0.2, 'stopping_words': ['\n', '</s>', '<|im_end|>', '\n{{User}}', '<|eot_id|>', '<|end_of_text|>', '\n<'], 'max_input_tokens': 1900, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system\nYou are now in roleplay chat mode. Engage in an endless chat with {user_name}. Always wait {user_name} turn, next actions and responses. You will fully embody the given character, creating immersive, captivating narratives. Stay true to the character's personality and background, generating responses that not only reflect their core traits but are also accurate to their character. Your responses should evoke emotion, suspense, and anticipation in the user. The more detailed and descriptive your response, the more vivid the narrative becomes. Aim to create a fertile environment for ongoing interaction – introduce new elements, offer choices, or ask questions to invite the user to participate more fully in the conversation. This conversation is a dance, always continuing, always evolving.\nYour character: {bot_name}.\nContext: {memory}<|end_header_id|>", 'prompt_template': '{prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>', 'bot_template': '{bot_name}: {message}<|end_header_id|>', 'user_template': '{user_name}: {message}<|end_header_id|>', '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: 2024-06-22T02:49:57+00:00
model_name: alkacchi-monologue-8B
model_group: alkahestry/Llmama3-Monol
num_battles: 22512
num_wins: 8089
celo_rating: 1090.89
propriety_score: 0.7359112984513883
propriety_total_count: 10913.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 4
max_input_tokens: 1900
max_output_tokens: 64
display_name: alkacchi-monologue-8B
ineligible_reason: None
language_model: alkahestry/Llmama3-Monologue-8B
model_size: 8B
reward_model: Jellywibble/CHAI_alignment_reward_model
us_pacific_date: 2024-06-21
win_ratio: 0.35931947405828
Resubmit model
Running pipeline stage MKMLizer
Starting job with name alkahestry-llmama3-monol-3361-v2-mkmlizer
Waiting for job on alkahestry-llmama3-monol-3361-v2-mkmlizer to finish
alkahestry-llmama3-monol-3361-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alkahestry-llmama3-monol-3361-v2-mkmlizer: ║ _____ __ __ ║
alkahestry-llmama3-monol-3361-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
alkahestry-llmama3-monol-3361-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
alkahestry-llmama3-monol-3361-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
alkahestry-llmama3-monol-3361-v2-mkmlizer: ║ /___/ ║
alkahestry-llmama3-monol-3361-v2-mkmlizer: ║ ║
alkahestry-llmama3-monol-3361-v2-mkmlizer: ║ Version: 0.8.14 ║
alkahestry-llmama3-monol-3361-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
alkahestry-llmama3-monol-3361-v2-mkmlizer: ║ https://mk1.ai ║
alkahestry-llmama3-monol-3361-v2-mkmlizer: ║ ║
alkahestry-llmama3-monol-3361-v2-mkmlizer: ║ The license key for the current software has been verified as ║
alkahestry-llmama3-monol-3361-v2-mkmlizer: ║ belonging to: ║
alkahestry-llmama3-monol-3361-v2-mkmlizer: ║ ║
alkahestry-llmama3-monol-3361-v2-mkmlizer: ║ Chai Research Corp. ║
alkahestry-llmama3-monol-3361-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
alkahestry-llmama3-monol-3361-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
alkahestry-llmama3-monol-3361-v2-mkmlizer: ║ ║
alkahestry-llmama3-monol-3361-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alkahestry-llmama3-monol-3361-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.
alkahestry-llmama3-monol-3361-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
alkahestry-llmama3-monol-3361-v2-mkmlizer: Downloaded to shared memory in 18.628s
alkahestry-llmama3-monol-3361-v2-mkmlizer: quantizing model to /dev/shm/model_cache
alkahestry-llmama3-monol-3361-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alkahestry-llmama3-monol-3361-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 135.20it/s] Loading 0: 11%|█ | 32/291 [00:00<00:01, 152.27it/s] Loading 0: 17%|█▋ | 50/291 [00:00<00:01, 156.53it/s] Loading 0: 23%|██▎ | 68/291 [00:00<00:01, 157.89it/s] Loading 0: 29%|██▉ | 84/291 [00:00<00:02, 75.72it/s] Loading 0: 33%|███▎ | 96/291 [00:00<00:02, 83.38it/s] Loading 0: 39%|███▉ | 113/291 [00:01<00:01, 99.49it/s] Loading 0: 45%|████▌ | 131/291 [00:01<00:01, 114.69it/s] Loading 0: 51%|█████ | 149/291 [00:01<00:01, 127.12it/s] Loading 0: 57%|█████▋ | 166/291 [00:01<00:00, 137.75it/s] Loading 0: 63%|██████▎ | 184/291 [00:01<00:00, 148.15it/s] Loading 0: 69%|██████▉ | 201/291 [00:01<00:01, 88.08it/s] Loading 0: 75%|███████▌ | 219/291 [00:01<00:00, 102.27it/s] Loading 0: 81%|████████▏ | 237/291 [00:02<00:00, 115.34it/s] Loading 0: 88%|████████▊ | 255/291 [00:02<00:00, 126.26it/s] Loading 0: 94%|█████████▍| 273/291 [00:02<00:00, 135.30it/s] Loading 0: 99%|█████████▉| 289/291 [00:07<00:00, 9.91it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
alkahestry-llmama3-monol-3361-v2-mkmlizer: quantized model in 23.101s
alkahestry-llmama3-monol-3361-v2-mkmlizer: Processed model alkahestry/Llmama3-Monologue-8B in 44.336s
alkahestry-llmama3-monol-3361-v2-mkmlizer: creating bucket guanaco-mkml-models
alkahestry-llmama3-monol-3361-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alkahestry-llmama3-monol-3361-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alkahestry-llmama3-monol-3361-v2
alkahestry-llmama3-monol-3361-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alkahestry-llmama3-monol-3361-v2/config.json
alkahestry-llmama3-monol-3361-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alkahestry-llmama3-monol-3361-v2/tokenizer_config.json
alkahestry-llmama3-monol-3361-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alkahestry-llmama3-monol-3361-v2/special_tokens_map.json
alkahestry-llmama3-monol-3361-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alkahestry-llmama3-monol-3361-v2/tokenizer.json
alkahestry-llmama3-monol-3361-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alkahestry-llmama3-monol-3361-v2/flywheel_model.0.safetensors
alkahestry-llmama3-monol-3361-v2-mkmlizer: loading reward model from Jellywibble/CHAI_alignment_reward_model
alkahestry-llmama3-monol-3361-v2-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.
alkahestry-llmama3-monol-3361-v2-mkmlizer: warnings.warn(
alkahestry-llmama3-monol-3361-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.
alkahestry-llmama3-monol-3361-v2-mkmlizer: warnings.warn(
alkahestry-llmama3-monol-3361-v2-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.
alkahestry-llmama3-monol-3361-v2-mkmlizer: warnings.warn(
alkahestry-llmama3-monol-3361-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
alkahestry-llmama3-monol-3361-v2-mkmlizer: Saving duration: 0.149s
alkahestry-llmama3-monol-3361-v2-mkmlizer: Processed model Jellywibble/CHAI_alignment_reward_model in 2.406s
alkahestry-llmama3-monol-3361-v2-mkmlizer: creating bucket guanaco-reward-models
alkahestry-llmama3-monol-3361-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
alkahestry-llmama3-monol-3361-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/alkahestry-llmama3-monol-3361-v2_reward
alkahestry-llmama3-monol-3361-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/alkahestry-llmama3-monol-3361-v2_reward/tokenizer_config.json
alkahestry-llmama3-monol-3361-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/alkahestry-llmama3-monol-3361-v2_reward/special_tokens_map.json
alkahestry-llmama3-monol-3361-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/alkahestry-llmama3-monol-3361-v2_reward/merges.txt
alkahestry-llmama3-monol-3361-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/alkahestry-llmama3-monol-3361-v2_reward/config.json
alkahestry-llmama3-monol-3361-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/alkahestry-llmama3-monol-3361-v2_reward/vocab.json
alkahestry-llmama3-monol-3361-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/alkahestry-llmama3-monol-3361-v2_reward/tokenizer.json
alkahestry-llmama3-monol-3361-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/alkahestry-llmama3-monol-3361-v2_reward/reward.tensors
Job alkahestry-llmama3-monol-3361-v2-mkmlizer completed after 62.74s with status: succeeded
Stopping job with name alkahestry-llmama3-monol-3361-v2-mkmlizer
Pipeline stage MKMLizer completed in 63.09s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service alkahestry-llmama3-monol-3361-v2
Waiting for inference service alkahestry-llmama3-monol-3361-v2 to be ready
Inference service alkahestry-llmama3-monol-3361-v2 ready after 40.19354724884033s
Pipeline stage ISVCDeployer completed in 46.12s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1181726455688477s
Received healthy response to inference request in 1.1687040328979492s
Received healthy response to inference request in 1.1794755458831787s
Received healthy response to inference request in 1.1960315704345703s
Received healthy response to inference request in 1.183532953262329s
5 requests
0 failed requests
5th percentile: 1.170858335494995
10th percentile: 1.173012638092041
20th percentile: 1.1773212432861329
30th percentile: 1.1802870273590087
40th percentile: 1.181909990310669
50th percentile: 1.183532953262329
60th percentile: 1.1885324001312256
70th percentile: 1.1935318470001222
80th percentile: 1.380459785461426
90th percentile: 1.7493162155151367
95th percentile: 1.933744430541992
99th percentile: 2.0812870025634767
mean time: 1.369183349609375
Pipeline stage StressChecker completed in 7.46s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
alkahestry-llmama3-monol_3361_v2 status is now deployed due to DeploymentManager action
alkahestry-llmama3-monol_3361_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics