submission_id: alkahestry-llmama3-monol_3361_v5
developer_uid: alkacchi
status: inactive
model_repo: alkahestry/Llmama3-Monologue-8B
reward_repo: Jellywibble/CHAI_alignment_reward_model
generation_params: {'temperature': 1.0, 'top_p': 0.8, 'min_p': 0.1, '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: 2024-06-29T12:17:00+00:00
model_name: alkacchi-monologue-8B
model_group: alkahestry/Llmama3-Monol
num_battles: 26477
num_wins: 9645
celo_rating: 1085.33
propriety_score: 0.7538876547127896
propriety_total_count: 12604.0
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: 2024-06-29
win_ratio: 0.3642784303357631
Resubmit model
Running pipeline stage MKMLizer
Starting job with name alkahestry-llmama3-monol-3361-v5-mkmlizer
Waiting for job on alkahestry-llmama3-monol-3361-v5-mkmlizer to finish
alkahestry-llmama3-monol-3361-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alkahestry-llmama3-monol-3361-v5-mkmlizer: ║ _____ __ __ ║
alkahestry-llmama3-monol-3361-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
alkahestry-llmama3-monol-3361-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
alkahestry-llmama3-monol-3361-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
alkahestry-llmama3-monol-3361-v5-mkmlizer: ║ /___/ ║
alkahestry-llmama3-monol-3361-v5-mkmlizer: ║ ║
alkahestry-llmama3-monol-3361-v5-mkmlizer: ║ Version: 0.8.14 ║
alkahestry-llmama3-monol-3361-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
alkahestry-llmama3-monol-3361-v5-mkmlizer: ║ https://mk1.ai ║
alkahestry-llmama3-monol-3361-v5-mkmlizer: ║ ║
alkahestry-llmama3-monol-3361-v5-mkmlizer: ║ The license key for the current software has been verified as ║
alkahestry-llmama3-monol-3361-v5-mkmlizer: ║ belonging to: ║
alkahestry-llmama3-monol-3361-v5-mkmlizer: ║ ║
alkahestry-llmama3-monol-3361-v5-mkmlizer: ║ Chai Research Corp. ║
alkahestry-llmama3-monol-3361-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
alkahestry-llmama3-monol-3361-v5-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
alkahestry-llmama3-monol-3361-v5-mkmlizer: ║ ║
alkahestry-llmama3-monol-3361-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alkahestry-llmama3-monol-3361-v5-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-v5-mkmlizer: warnings.warn(warning_message, FutureWarning)
alkahestry-llmama3-monol-3361-v5-mkmlizer: Downloaded to shared memory in 17.774s
alkahestry-llmama3-monol-3361-v5-mkmlizer: quantizing model to /dev/shm/model_cache
alkahestry-llmama3-monol-3361-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alkahestry-llmama3-monol-3361-v5-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 137.24it/s] Loading 0: 11%|█ | 32/291 [00:00<00:01, 154.34it/s] Loading 0: 17%|█▋ | 50/291 [00:00<00:01, 158.83it/s] Loading 0: 23%|██▎ | 68/291 [00:00<00:01, 160.95it/s] Loading 0: 29%|██▉ | 85/291 [00:00<00:02, 86.29it/s] Loading 0: 35%|███▌ | 103/291 [00:00<00:01, 102.71it/s] Loading 0: 42%|████▏ | 121/291 [00:01<00:01, 117.50it/s] Loading 0: 48%|████▊ | 139/291 [00:01<00:01, 129.16it/s] Loading 0: 54%|█████▍ | 157/291 [00:01<00:00, 137.66it/s] Loading 0: 60%|██████ | 176/291 [00:01<00:00, 150.02it/s] Loading 0: 66%|██████▋ | 193/291 [00:01<00:01, 91.61it/s] Loading 0: 73%|███████▎ | 211/291 [00:01<00:00, 106.65it/s] Loading 0: 79%|███████▊ | 229/291 [00:01<00:00, 120.18it/s] Loading 0: 85%|████████▍ | 247/291 [00:02<00:00, 131.56it/s] Loading 0: 91%|█████████ | 265/291 [00:02<00:00, 141.21it/s] Loading 0: 97%|█████████▋| 282/291 [00:02<00:00, 144.87it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
alkahestry-llmama3-monol-3361-v5-mkmlizer: quantized model in 22.846s
alkahestry-llmama3-monol-3361-v5-mkmlizer: Processed model alkahestry/Llmama3-Monologue-8B in 43.167s
alkahestry-llmama3-monol-3361-v5-mkmlizer: creating bucket guanaco-mkml-models
alkahestry-llmama3-monol-3361-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alkahestry-llmama3-monol-3361-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alkahestry-llmama3-monol-3361-v5
alkahestry-llmama3-monol-3361-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alkahestry-llmama3-monol-3361-v5/special_tokens_map.json
alkahestry-llmama3-monol-3361-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alkahestry-llmama3-monol-3361-v5/config.json
alkahestry-llmama3-monol-3361-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alkahestry-llmama3-monol-3361-v5/tokenizer_config.json
alkahestry-llmama3-monol-3361-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alkahestry-llmama3-monol-3361-v5/tokenizer.json
Failed to get response for submission blend_lakem_2024-06-25: ('http://mistralai-mixtral-8x7b-3473-v33-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:51848->127.0.0.1:8080: read: connection reset by peer\n')
alkahestry-llmama3-monol-3361-v5-mkmlizer: loading reward model from Jellywibble/CHAI_alignment_reward_model
alkahestry-llmama3-monol-3361-v5-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-v5-mkmlizer: warnings.warn(
alkahestry-llmama3-monol-3361-v5-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-v5-mkmlizer: warnings.warn(
alkahestry-llmama3-monol-3361-v5-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-v5-mkmlizer: warnings.warn(
alkahestry-llmama3-monol-3361-v5-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
alkahestry-llmama3-monol-3361-v5-mkmlizer: Saving duration: 0.158s
alkahestry-llmama3-monol-3361-v5-mkmlizer: Processed model Jellywibble/CHAI_alignment_reward_model in 2.432s
alkahestry-llmama3-monol-3361-v5-mkmlizer: creating bucket guanaco-reward-models
alkahestry-llmama3-monol-3361-v5-mkmlizer: Bucket 's3://guanaco-reward-models/' created
alkahestry-llmama3-monol-3361-v5-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/alkahestry-llmama3-monol-3361-v5_reward
alkahestry-llmama3-monol-3361-v5-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/alkahestry-llmama3-monol-3361-v5_reward/special_tokens_map.json
alkahestry-llmama3-monol-3361-v5-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/alkahestry-llmama3-monol-3361-v5_reward/tokenizer_config.json
alkahestry-llmama3-monol-3361-v5-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/alkahestry-llmama3-monol-3361-v5_reward/config.json
alkahestry-llmama3-monol-3361-v5-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/alkahestry-llmama3-monol-3361-v5_reward/merges.txt
alkahestry-llmama3-monol-3361-v5-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/alkahestry-llmama3-monol-3361-v5_reward/vocab.json
alkahestry-llmama3-monol-3361-v5-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/alkahestry-llmama3-monol-3361-v5_reward/tokenizer.json
alkahestry-llmama3-monol-3361-v5-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/alkahestry-llmama3-monol-3361-v5_reward/reward.tensors
Job alkahestry-llmama3-monol-3361-v5-mkmlizer completed after 63.33s with status: succeeded
Stopping job with name alkahestry-llmama3-monol-3361-v5-mkmlizer
Pipeline stage MKMLizer completed in 64.36s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service alkahestry-llmama3-monol-3361-v5
Waiting for inference service alkahestry-llmama3-monol-3361-v5 to be ready
Inference service alkahestry-llmama3-monol-3361-v5 ready after 120.52810645103455s
Pipeline stage ISVCDeployer completed in 127.47s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.252920150756836s
Received healthy response to inference request in 1.1703212261199951s
Received healthy response to inference request in 1.1825850009918213s
Received healthy response to inference request in 1.1924092769622803s
Received healthy response to inference request in 0.9109029769897461s
5 requests
0 failed requests
5th percentile: 0.9627866268157959
10th percentile: 1.0146702766418456
20th percentile: 1.1184375762939454
30th percentile: 1.1727739810943603
40th percentile: 1.1776794910430908
50th percentile: 1.1825850009918213
60th percentile: 1.186514711380005
70th percentile: 1.1904444217681884
80th percentile: 1.4045114517211916
90th percentile: 1.8287158012390137
95th percentile: 2.040817975997925
99th percentile: 2.210499715805054
mean time: 1.3418277263641358
Pipeline stage StressChecker completed in 7.52s
alkahestry-llmama3-monol_3361_v5 status is now deployed due to DeploymentManager action
alkahestry-llmama3-monol_3361_v5 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics