submission_id: sao10k-l3-8b-stheno-v3-2_v2
developer_uid: windyheath
alignment_samples: 0
best_of: 4
celo_rating: 1192.68
display_name: sao10k-l3-8b-stheno-v3-2_v2
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}
generation_params: {'temperature': 1.15, 'top_p': 1.0, 'min_p': 0.075, 'top_k': 50, 'presence_penalty': 1.1, 'frequency_penalty': 1.1, 'stopping_words': ['\n', '<|eot_id|>', '<|end_of_text|>'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
ineligible_reason: propriety_total_count < 800
is_internal_developer: False
language_model: Sao10K/L3-8B-Stheno-v3.2
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: Sao10K/L3-8B-Stheno-v3.2
model_name: sao10k-l3-8b-stheno-v3-2_v2
model_num_parameters: 8030261248.0
model_repo: Sao10K/L3-8B-Stheno-v3.2
model_size: 8B
num_battles: 8469
num_wins: 4378
propriety_score: 0.6851574212893553
propriety_total_count: 667.0
ranking_group: single
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-06-08T16:45:06+00:00
us_pacific_date: 2024-06-08
win_ratio: 0.5169441492502066
Resubmit model
Running pipeline stage MKMLizer
Starting job with name sao10k-l3-8b-stheno-v3-2-v2-mkmlizer
Waiting for job on sao10k-l3-8b-stheno-v3-2-v2-mkmlizer to finish
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: ║ _____ __ __ ║
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: ║ /___/ ║
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: ║ ║
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: ║ Version: 0.8.14 ║
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: ║ https://mk1.ai ║
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: ║ ║
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: ║ The license key for the current software has been verified as ║
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: ║ belonging to: ║
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: ║ ║
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: ║ Chai Research Corp. ║
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: ║ ║
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-l3-8b-stheno-v3-2-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.
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: Downloaded to shared memory in 17.302s
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: quantizing model to /dev/shm/model_cache
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:49, 2.25s/it] Loading 0: 5%|▌ | 15/291 [00:04<01:02, 4.43it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:21, 11.77it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:11, 21.15it/s] Loading 0: 22%|██▏ | 65/291 [00:05<00:08, 25.19it/s] Loading 0: 27%|██▋ | 78/291 [00:05<00:06, 33.75it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:04, 48.46it/s] Loading 0: 39%|███▉ | 113/291 [00:05<00:02, 63.80it/s] Loading 0: 45%|████▌ | 131/291 [00:05<00:01, 80.48it/s] Loading 0: 51%|█████ | 149/291 [00:05<00:01, 96.23it/s] Loading 0: 57%|█████▋ | 166/291 [00:06<00:01, 73.12it/s] Loading 0: 63%|██████▎ | 184/291 [00:06<00:01, 88.76it/s] Loading 0: 69%|██████▉ | 202/291 [00:06<00:00, 103.81it/s] Loading 0: 76%|███████▌ | 220/291 [00:06<00:00, 116.82it/s] Loading 0: 82%|████████▏ | 238/291 [00:06<00:00, 128.32it/s] Loading 0: 88%|████████▊ | 256/291 [00:06<00:00, 138.14it/s] Loading 0: 93%|█████████▎| 272/291 [00:06<00:00, 88.53it/s] Loading 0: 99%|█████████▉| 288/291 [00:07<00:00, 100.82it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: quantized model in 23.058s
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: Processed model Sao10K/L3-8B-Stheno-v3.2 in 43.001s
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: creating bucket guanaco-mkml-models
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-l3-8b-stheno-v3-2-v2
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-l3-8b-stheno-v3-2-v2/special_tokens_map.json
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-l3-8b-stheno-v3-2-v2/config.json
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-l3-8b-stheno-v3-2-v2/tokenizer_config.json
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-l3-8b-stheno-v3-2-v2/tokenizer.json
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-l3-8b-stheno-v3-2-v2/flywheel_model.0.safetensors
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
sao10k-l3-8b-stheno-v3-2-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.
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: warnings.warn(
sao10k-l3-8b-stheno-v3-2-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.
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: warnings.warn(
sao10k-l3-8b-stheno-v3-2-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.
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: warnings.warn(
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: Saving duration: 0.416s
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.380s
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: creating bucket guanaco-reward-models
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/sao10k-l3-8b-stheno-v3-2-v2_reward
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/sao10k-l3-8b-stheno-v3-2-v2_reward/tokenizer_config.json
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/sao10k-l3-8b-stheno-v3-2-v2_reward/special_tokens_map.json
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/sao10k-l3-8b-stheno-v3-2-v2_reward/config.json
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-l3-8b-stheno-v3-2-v2_reward/merges.txt
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-l3-8b-stheno-v3-2-v2_reward/vocab.json
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-l3-8b-stheno-v3-2-v2_reward/tokenizer.json
sao10k-l3-8b-stheno-v3-2-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-l3-8b-stheno-v3-2-v2_reward/reward.tensors
Job sao10k-l3-8b-stheno-v3-2-v2-mkmlizer completed after 73.06s with status: succeeded
Stopping job with name sao10k-l3-8b-stheno-v3-2-v2-mkmlizer
Pipeline stage MKMLizer completed in 76.27s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-l3-8b-stheno-v3-2-v2
Waiting for inference service sao10k-l3-8b-stheno-v3-2-v2 to be ready
Inference service sao10k-l3-8b-stheno-v3-2-v2 ready after 493.60707426071167s
Pipeline stage ISVCDeployer completed in 500.67s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.102924346923828s
Received healthy response to inference request in 1.1447348594665527s
Received healthy response to inference request in 0.7853267192840576s
Received healthy response to inference request in 0.780789852142334s
Received healthy response to inference request in 16.103293895721436s
5 requests
0 failed requests
5th percentile: 0.7816972255706787
10th percentile: 0.7826045989990235
20th percentile: 0.7844193458557129
30th percentile: 0.8572083473205566
40th percentile: 1.0009716033935547
50th percentile: 1.1447348594665527
60th percentile: 1.5280106544494627
70th percentile: 1.911286449432373
80th percentile: 4.902998256683352
90th percentile: 10.503146076202395
95th percentile: 13.303219985961912
99th percentile: 15.54327911376953
mean time: 4.183413934707642
Pipeline stage StressChecker completed in 21.52s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.06s
sao10k-l3-8b-stheno-v3-2_v2 status is now deployed due to DeploymentManager action
sao10k-l3-8b-stheno-v3-2_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of sao10k-l3-8b-stheno-v3-2_v2
Running pipeline stage ISVCDeleter
Checking if service sao10k-l3-8b-stheno-v3-2-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.23s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key sao10k-l3-8b-stheno-v3-2-v2/config.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-8b-stheno-v3-2-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key sao10k-l3-8b-stheno-v3-2-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-8b-stheno-v3-2-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-8b-stheno-v3-2-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key sao10k-l3-8b-stheno-v3-2-v2_reward/config.json from bucket guanaco-reward-models
Deleting key sao10k-l3-8b-stheno-v3-2-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key sao10k-l3-8b-stheno-v3-2-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key sao10k-l3-8b-stheno-v3-2-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key sao10k-l3-8b-stheno-v3-2-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key sao10k-l3-8b-stheno-v3-2-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key sao10k-l3-8b-stheno-v3-2-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.11s
sao10k-l3-8b-stheno-v3-2_v2 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics