submission_id: alkahestry-llmama3-monol_3361_v6
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': 0.73, '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': 512, 'best_of': 16, '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: 2024-06-30T01:11:09+00:00
model_name: alkacchi-monologue-8B
model_group: alkahestry/Llmama3-Monol
num_battles: 20035
num_wins: 7500
celo_rating: 1072.63
propriety_score: 0.7639791245074022
propriety_total_count: 9389.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: 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: 0.3743448964312453
Resubmit model
Running pipeline stage MKMLizer
Starting job with name alkahestry-llmama3-monol-3361-v6-mkmlizer
Waiting for job on alkahestry-llmama3-monol-3361-v6-mkmlizer to finish
alkahestry-llmama3-monol-3361-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alkahestry-llmama3-monol-3361-v6-mkmlizer: ║ _____ __ __ ║
alkahestry-llmama3-monol-3361-v6-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
alkahestry-llmama3-monol-3361-v6-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
alkahestry-llmama3-monol-3361-v6-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
alkahestry-llmama3-monol-3361-v6-mkmlizer: ║ /___/ ║
alkahestry-llmama3-monol-3361-v6-mkmlizer: ║ ║
alkahestry-llmama3-monol-3361-v6-mkmlizer: ║ Version: 0.8.14 ║
alkahestry-llmama3-monol-3361-v6-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
alkahestry-llmama3-monol-3361-v6-mkmlizer: ║ https://mk1.ai ║
alkahestry-llmama3-monol-3361-v6-mkmlizer: ║ ║
alkahestry-llmama3-monol-3361-v6-mkmlizer: ║ The license key for the current software has been verified as ║
alkahestry-llmama3-monol-3361-v6-mkmlizer: ║ belonging to: ║
alkahestry-llmama3-monol-3361-v6-mkmlizer: ║ ║
alkahestry-llmama3-monol-3361-v6-mkmlizer: ║ Chai Research Corp. ║
alkahestry-llmama3-monol-3361-v6-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
alkahestry-llmama3-monol-3361-v6-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
alkahestry-llmama3-monol-3361-v6-mkmlizer: ║ ║
alkahestry-llmama3-monol-3361-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alkahestry-llmama3-monol-3361-v6-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-v6-mkmlizer: warnings.warn(warning_message, FutureWarning)
alkahestry-llmama3-monol-3361-v6-mkmlizer: Downloaded to shared memory in 24.481s
alkahestry-llmama3-monol-3361-v6-mkmlizer: quantizing model to /dev/shm/model_cache
alkahestry-llmama3-monol-3361-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alkahestry-llmama3-monol-3361-v6-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▌ | 15/291 [00:00<00:01, 149.56it/s] Loading 0: 11%|█ | 32/291 [00:00<00:01, 156.45it/s] Loading 0: 17%|█▋ | 50/291 [00:00<00:01, 162.66it/s] Loading 0: 23%|██▎ | 68/291 [00:00<00:01, 165.71it/s] Loading 0: 29%|██▉ | 85/291 [00:00<00:02, 89.36it/s] Loading 0: 35%|███▌ | 103/291 [00:00<00:01, 106.67it/s] Loading 0: 40%|████ | 117/291 [00:00<00:01, 112.47it/s] Loading 0: 45%|████▌ | 131/291 [00:01<00:01, 112.60it/s] Loading 0: 51%|█████ | 149/291 [00:01<00:01, 126.19it/s] Loading 0: 57%|█████▋ | 167/291 [00:01<00:00, 135.60it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 94.96it/s] Loading 0: 69%|██████▉ | 201/291 [00:01<00:00, 103.45it/s] Loading 0: 75%|███████▌ | 219/291 [00:01<00:00, 117.25it/s] Loading 0: 81%|████████▏ | 237/291 [00:01<00:00, 128.72it/s] Loading 0: 88%|████████▊ | 255/291 [00:02<00:00, 137.51it/s] Loading 0: 94%|█████████▍| 273/291 [00:02<00:00, 144.19it/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-v6-mkmlizer: quantized model in 22.780s
alkahestry-llmama3-monol-3361-v6-mkmlizer: Processed model alkahestry/Llmama3-Monologue-8B in 49.733s
alkahestry-llmama3-monol-3361-v6-mkmlizer: creating bucket guanaco-mkml-models
alkahestry-llmama3-monol-3361-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alkahestry-llmama3-monol-3361-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alkahestry-llmama3-monol-3361-v6
alkahestry-llmama3-monol-3361-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alkahestry-llmama3-monol-3361-v6/tokenizer_config.json
alkahestry-llmama3-monol-3361-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alkahestry-llmama3-monol-3361-v6/special_tokens_map.json
alkahestry-llmama3-monol-3361-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alkahestry-llmama3-monol-3361-v6/config.json
alkahestry-llmama3-monol-3361-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alkahestry-llmama3-monol-3361-v6/tokenizer.json
alkahestry-llmama3-monol-3361-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alkahestry-llmama3-monol-3361-v6/flywheel_model.0.safetensors
alkahestry-llmama3-monol-3361-v6-mkmlizer: loading reward model from Jellywibble/CHAI_alignment_reward_model
alkahestry-llmama3-monol-3361-v6-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-v6-mkmlizer: warnings.warn(
alkahestry-llmama3-monol-3361-v6-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-v6-mkmlizer: warnings.warn(
alkahestry-llmama3-monol-3361-v6-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-v6-mkmlizer: warnings.warn(
alkahestry-llmama3-monol-3361-v6-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
alkahestry-llmama3-monol-3361-v6-mkmlizer: Saving duration: 0.150s
alkahestry-llmama3-monol-3361-v6-mkmlizer: Processed model Jellywibble/CHAI_alignment_reward_model in 4.270s
alkahestry-llmama3-monol-3361-v6-mkmlizer: creating bucket guanaco-reward-models
alkahestry-llmama3-monol-3361-v6-mkmlizer: Bucket 's3://guanaco-reward-models/' created
alkahestry-llmama3-monol-3361-v6-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/alkahestry-llmama3-monol-3361-v6_reward
alkahestry-llmama3-monol-3361-v6-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/alkahestry-llmama3-monol-3361-v6_reward/special_tokens_map.json
alkahestry-llmama3-monol-3361-v6-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/alkahestry-llmama3-monol-3361-v6_reward/vocab.json
alkahestry-llmama3-monol-3361-v6-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/alkahestry-llmama3-monol-3361-v6_reward/config.json
alkahestry-llmama3-monol-3361-v6-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/alkahestry-llmama3-monol-3361-v6_reward/tokenizer_config.json
alkahestry-llmama3-monol-3361-v6-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/alkahestry-llmama3-monol-3361-v6_reward/tokenizer.json
alkahestry-llmama3-monol-3361-v6-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/alkahestry-llmama3-monol-3361-v6_reward/merges.txt
alkahestry-llmama3-monol-3361-v6-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/alkahestry-llmama3-monol-3361-v6_reward/reward.tensors
Job alkahestry-llmama3-monol-3361-v6-mkmlizer completed after 73.84s with status: succeeded
Stopping job with name alkahestry-llmama3-monol-3361-v6-mkmlizer
Pipeline stage MKMLizer completed in 74.69s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service alkahestry-llmama3-monol-3361-v6
Waiting for inference service alkahestry-llmama3-monol-3361-v6 to be ready
Inference service alkahestry-llmama3-monol-3361-v6 ready after 50.306920289993286s
Pipeline stage ISVCDeployer completed in 57.26s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1192409992218018s
Received healthy response to inference request in 1.183614730834961s
Received healthy response to inference request in 1.2802815437316895s
Received healthy response to inference request in 1.2149899005889893s
Received healthy response to inference request in 1.0455007553100586s
5 requests
0 failed requests
5th percentile: 1.0731235504150392
10th percentile: 1.1007463455200195
20th percentile: 1.1559919357299804
30th percentile: 1.1898897647857667
40th percentile: 1.202439832687378
50th percentile: 1.2149899005889893
60th percentile: 1.2411065578460694
70th percentile: 1.2672232151031495
80th percentile: 1.4480734348297122
90th percentile: 1.783657217025757
95th percentile: 1.951449108123779
99th percentile: 2.085682621002197
mean time: 1.3687255859375
Pipeline stage StressChecker completed in 7.48s
alkahestry-llmama3-monol_3361_v6 status is now deployed due to DeploymentManager action
alkahestry-llmama3-monol_3361_v6 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics