submission_id: alkahestry-stheno-l3-8b_v1
developer_uid: alkacchi
status: inactive
model_repo: alkahestry/Stheno-L3-8B
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.8, 'top_p': 0.73, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.8, 'stopping_words': ['\n', '</s>', '<|im_end|>'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
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}
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: 2024-06-15T12:11:10+00:00
model_name: alkahestry-stheno-l3-8b_v1
model_eval_status: success
model_group: alkahestry/Stheno-L3-8B
num_battles: 26118
num_wins: 13000
celo_rating: 1177.38
propriety_score: 0.6961302778477294
propriety_total_count: 11913.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: alkahestry-stheno-l3-8b_v1
ineligible_reason: None
language_model: alkahestry/Stheno-L3-8B
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-15
win_ratio: 0.49774102151772726
Resubmit model
Running pipeline stage MKMLizer
Starting job with name alkahestry-stheno-l3-8b-v1-mkmlizer
Waiting for job on alkahestry-stheno-l3-8b-v1-mkmlizer to finish
alkahestry-stheno-l3-8b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alkahestry-stheno-l3-8b-v1-mkmlizer: ║ _____ __ __ ║
alkahestry-stheno-l3-8b-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
alkahestry-stheno-l3-8b-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
alkahestry-stheno-l3-8b-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
alkahestry-stheno-l3-8b-v1-mkmlizer: ║ /___/ ║
alkahestry-stheno-l3-8b-v1-mkmlizer: ║ ║
alkahestry-stheno-l3-8b-v1-mkmlizer: ║ Version: 0.8.14 ║
alkahestry-stheno-l3-8b-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
alkahestry-stheno-l3-8b-v1-mkmlizer: ║ https://mk1.ai ║
alkahestry-stheno-l3-8b-v1-mkmlizer: ║ ║
alkahestry-stheno-l3-8b-v1-mkmlizer: ║ The license key for the current software has been verified as ║
alkahestry-stheno-l3-8b-v1-mkmlizer: ║ belonging to: ║
alkahestry-stheno-l3-8b-v1-mkmlizer: ║ ║
alkahestry-stheno-l3-8b-v1-mkmlizer: ║ Chai Research Corp. ║
alkahestry-stheno-l3-8b-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
alkahestry-stheno-l3-8b-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
alkahestry-stheno-l3-8b-v1-mkmlizer: ║ ║
alkahestry-stheno-l3-8b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alkahestry-stheno-l3-8b-v1-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-stheno-l3-8b-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
alkahestry-stheno-l3-8b-v1-mkmlizer: Downloaded to shared memory in 47.830s
alkahestry-stheno-l3-8b-v1-mkmlizer: quantizing model to /dev/shm/model_cache
alkahestry-stheno-l3-8b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alkahestry-stheno-l3-8b-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:05<12:22, 2.57s/it] Loading 0: 4%|▍ | 13/291 [00:05<01:23, 3.34it/s] Loading 0: 8%|▊ | 23/291 [00:05<00:38, 6.90it/s] Loading 0: 11%|█▏ | 33/291 [00:05<00:22, 11.50it/s] Loading 0: 16%|█▌ | 47/291 [00:05<00:12, 20.03it/s] Loading 0: 20%|█▉ | 58/291 [00:05<00:08, 27.63it/s] Loading 0: 24%|██▎ | 69/291 [00:06<00:08, 25.59it/s] Loading 0: 28%|██▊ | 82/291 [00:06<00:05, 35.65it/s] Loading 0: 32%|███▏ | 94/291 [00:06<00:04, 45.50it/s] Loading 0: 36%|███▌ | 104/291 [00:06<00:03, 52.72it/s] Loading 0: 39%|███▉ | 114/291 [00:06<00:02, 60.26it/s] Loading 0: 44%|████▎ | 127/291 [00:06<00:02, 73.68it/s] Loading 0: 48%|████▊ | 139/291 [00:06<00:01, 82.27it/s] Loading 0: 52%|█████▏ | 150/291 [00:06<00:01, 83.46it/s] Loading 0: 56%|█████▌ | 163/291 [00:07<00:01, 94.27it/s] Loading 0: 60%|█████▉ | 174/291 [00:07<00:01, 59.71it/s] Loading 0: 63%|██████▎ | 184/291 [00:07<00:01, 65.78it/s] Loading 0: 66%|██████▋ | 193/291 [00:07<00:01, 69.67it/s] Loading 0: 69%|██████▉ | 202/291 [00:07<00:01, 69.60it/s] Loading 0: 73%|███████▎ | 211/291 [00:07<00:01, 69.04it/s] Loading 0: 76%|███████▌ | 221/291 [00:07<00:00, 73.16it/s] Loading 0: 79%|███████▉ | 231/291 [00:08<00:00, 77.35it/s] Loading 0: 84%|████████▍ | 244/291 [00:08<00:00, 90.04it/s] Loading 0: 87%|████████▋ | 254/291 [00:08<00:00, 88.32it/s] Loading 0: 91%|█████████ | 264/291 [00:08<00:00, 86.35it/s] Loading 0: 94%|█████████▍| 273/291 [00:08<00:00, 49.39it/s] Loading 0: 96%|█████████▌| 280/291 [00:08<00:00, 52.00it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
alkahestry-stheno-l3-8b-v1-mkmlizer: quantized model in 25.864s
alkahestry-stheno-l3-8b-v1-mkmlizer: Processed model alkahestry/Stheno-L3-8B in 76.598s
alkahestry-stheno-l3-8b-v1-mkmlizer: creating bucket guanaco-mkml-models
alkahestry-stheno-l3-8b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alkahestry-stheno-l3-8b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alkahestry-stheno-l3-8b-v1
alkahestry-stheno-l3-8b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alkahestry-stheno-l3-8b-v1/special_tokens_map.json
alkahestry-stheno-l3-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alkahestry-stheno-l3-8b-v1/tokenizer_config.json
alkahestry-stheno-l3-8b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alkahestry-stheno-l3-8b-v1/config.json
alkahestry-stheno-l3-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alkahestry-stheno-l3-8b-v1/tokenizer.json
alkahestry-stheno-l3-8b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alkahestry-stheno-l3-8b-v1/flywheel_model.0.safetensors
alkahestry-stheno-l3-8b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
alkahestry-stheno-l3-8b-v1-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-stheno-l3-8b-v1-mkmlizer: warnings.warn(
alkahestry-stheno-l3-8b-v1-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-stheno-l3-8b-v1-mkmlizer: warnings.warn(
alkahestry-stheno-l3-8b-v1-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-stheno-l3-8b-v1-mkmlizer: warnings.warn(
alkahestry-stheno-l3-8b-v1-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()
alkahestry-stheno-l3-8b-v1-mkmlizer: return self.fget.__get__(instance, owner)()
alkahestry-stheno-l3-8b-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
alkahestry-stheno-l3-8b-v1-mkmlizer: Saving duration: 0.469s
alkahestry-stheno-l3-8b-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.720s
alkahestry-stheno-l3-8b-v1-mkmlizer: creating bucket guanaco-reward-models
alkahestry-stheno-l3-8b-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
alkahestry-stheno-l3-8b-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/alkahestry-stheno-l3-8b-v1_reward
alkahestry-stheno-l3-8b-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/alkahestry-stheno-l3-8b-v1_reward/special_tokens_map.json
alkahestry-stheno-l3-8b-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/alkahestry-stheno-l3-8b-v1_reward/merges.txt
alkahestry-stheno-l3-8b-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/alkahestry-stheno-l3-8b-v1_reward/config.json
alkahestry-stheno-l3-8b-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/alkahestry-stheno-l3-8b-v1_reward/vocab.json
alkahestry-stheno-l3-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/alkahestry-stheno-l3-8b-v1_reward/tokenizer.json
alkahestry-stheno-l3-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/alkahestry-stheno-l3-8b-v1_reward/tokenizer_config.json
alkahestry-stheno-l3-8b-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/alkahestry-stheno-l3-8b-v1_reward/reward.tensors
Job alkahestry-stheno-l3-8b-v1-mkmlizer completed after 134.7s with status: succeeded
Stopping job with name alkahestry-stheno-l3-8b-v1-mkmlizer
Pipeline stage MKMLizer completed in 138.67s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.14s
Running pipeline stage ISVCDeployer
Creating inference service alkahestry-stheno-l3-8b-v1
Waiting for inference service alkahestry-stheno-l3-8b-v1 to be ready
Inference service alkahestry-stheno-l3-8b-v1 ready after 40.23603963851929s
Pipeline stage ISVCDeployer completed in 48.15s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.02752685546875s
Received healthy response to inference request in 1.1303064823150635s
Received healthy response to inference request in 0.7939178943634033s
Received healthy response to inference request in 0.9925646781921387s
Received healthy response to inference request in 1.1323530673980713s
5 requests
0 failed requests
5th percentile: 0.8336472511291504
10th percentile: 0.8733766078948975
20th percentile: 0.9528353214263916
30th percentile: 1.0201130390167237
40th percentile: 1.0752097606658935
50th percentile: 1.1303064823150635
60th percentile: 1.1311251163482665
70th percentile: 1.1319437503814698
80th percentile: 1.3113878250122073
90th percentile: 1.6694573402404786
95th percentile: 1.848492097854614
99th percentile: 1.9917199039459228
mean time: 1.2153337955474854
Pipeline stage StressChecker completed in 6.68s
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 0.04s
M-Eval Dataset for topic stay_in_character is loaded
alkahestry-stheno-l3-8b_v1 status is now deployed due to DeploymentManager action
alkahestry-stheno-l3-8b_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics