submission_id: saishf-sovl-mega-mash-v2_4112_v1
developer_uid: saishf
status: inactive
model_repo: saishf/SOVL-Mega-Mash-V2-L3-8B
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.15, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 65, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{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: 2024-06-02T14:46:45+00:00
model_name: saishf-sovl-mega-mash-v2_4112_v1
model_eval_status: success
model_group: saishf/SOVL-Mega-Mash-V2
num_battles: 18540
num_wins: 9967
celo_rating: 1195.52
safety_score: 0.97
propriety_score: 0.6980676328502415
propriety_total_count: 414.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: saishf-sovl-mega-mash-v2_4112_v1
ineligible_reason: propriety_total_count < 5000
language_model: saishf/SOVL-Mega-Mash-V2-L3-8B
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-02
win_ratio: 0.5375943905070119
Resubmit model
Running pipeline stage MKMLizer
Starting job with name saishf-sovl-mega-mash-v2-4112-v1-mkmlizer
Waiting for job on saishf-sovl-mega-mash-v2-4112-v1-mkmlizer to finish
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: ║ _____ __ __ ║
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: ║ /___/ ║
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: ║ ║
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: ║ Version: 0.8.14 ║
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: ║ https://mk1.ai ║
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: ║ ║
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: ║ The license key for the current software has been verified as ║
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: ║ belonging to: ║
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: ║ ║
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: ║ Chai Research Corp. ║
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: ║ ║
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
saishf-sovl-mega-mash-v2-4112-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.
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: Downloaded to shared memory in 56.451s
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: quantizing model to /dev/shm/model_cache
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:09, 2.32s/it] Loading 0: 5%|▍ | 14/291 [00:04<01:09, 4.00it/s] Loading 0: 11%|█ | 31/291 [00:04<00:24, 10.73it/s] Loading 0: 14%|█▍ | 42/291 [00:05<00:17, 14.39it/s] Loading 0: 20%|█▉ | 58/291 [00:05<00:09, 23.88it/s] Loading 0: 24%|██▎ | 69/291 [00:05<00:07, 31.08it/s] Loading 0: 29%|██▉ | 85/291 [00:05<00:04, 44.99it/s] Loading 0: 34%|███▎ | 98/291 [00:05<00:03, 55.50it/s] Loading 0: 39%|███▉ | 113/291 [00:05<00:02, 68.89it/s] Loading 0: 43%|████▎ | 126/291 [00:06<00:02, 57.49it/s] Loading 0: 48%|████▊ | 140/291 [00:06<00:02, 68.99it/s] Loading 0: 54%|█████▍ | 157/291 [00:06<00:01, 84.55it/s] Loading 0: 58%|█████▊ | 169/291 [00:06<00:01, 90.73it/s] Loading 0: 63%|██████▎ | 184/291 [00:06<00:01, 103.54it/s] Loading 0: 68%|██████▊ | 197/291 [00:06<00:00, 108.34it/s] Loading 0: 72%|███████▏ | 210/291 [00:06<00:01, 76.16it/s] Loading 0: 76%|███████▌ | 221/291 [00:06<00:00, 82.20it/s] Loading 0: 82%|████████▏ | 238/291 [00:07<00:00, 97.68it/s] Loading 0: 86%|████████▌ | 250/291 [00:07<00:00, 102.01it/s] Loading 0: 91%|█████████▏| 266/291 [00:07<00:00, 111.79it/s] Loading 0: 96%|█████████▌| 280/291 [00:07<00:00, 118.56it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: quantized model in 23.567s
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: Processed model saishf/SOVL-Mega-Mash-V2-L3-8B in 82.509s
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: creating bucket guanaco-mkml-models
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/saishf-sovl-mega-mash-v2-4112-v1
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/saishf-sovl-mega-mash-v2-4112-v1/tokenizer_config.json
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/saishf-sovl-mega-mash-v2-4112-v1/special_tokens_map.json
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/saishf-sovl-mega-mash-v2-4112-v1/config.json
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/saishf-sovl-mega-mash-v2-4112-v1/tokenizer.json
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/saishf-sovl-mega-mash-v2-4112-v1/flywheel_model.0.safetensors
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
saishf-sovl-mega-mash-v2-4112-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.
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: warnings.warn(
saishf-sovl-mega-mash-v2-4112-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.
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: warnings.warn(
saishf-sovl-mega-mash-v2-4112-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.
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: warnings.warn(
saishf-sovl-mega-mash-v2-4112-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()
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: return self.fget.__get__(instance, owner)()
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: Saving duration: 0.411s
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.439s
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: creating bucket guanaco-reward-models
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/saishf-sovl-mega-mash-v2-4112-v1_reward
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/saishf-sovl-mega-mash-v2-4112-v1_reward/config.json
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/saishf-sovl-mega-mash-v2-4112-v1_reward/special_tokens_map.json
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/saishf-sovl-mega-mash-v2-4112-v1_reward/vocab.json
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/saishf-sovl-mega-mash-v2-4112-v1_reward/merges.txt
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/saishf-sovl-mega-mash-v2-4112-v1_reward/tokenizer_config.json
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/saishf-sovl-mega-mash-v2-4112-v1_reward/tokenizer.json
saishf-sovl-mega-mash-v2-4112-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/saishf-sovl-mega-mash-v2-4112-v1_reward/reward.tensors
Job saishf-sovl-mega-mash-v2-4112-v1-mkmlizer completed after 114.08s with status: succeeded
Stopping job with name saishf-sovl-mega-mash-v2-4112-v1-mkmlizer
Pipeline stage MKMLizer completed in 117.62s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service saishf-sovl-mega-mash-v2-4112-v1
Waiting for inference service saishf-sovl-mega-mash-v2-4112-v1 to be ready
Inference service saishf-sovl-mega-mash-v2-4112-v1 ready after 30.169834852218628s
Pipeline stage ISVCDeployer completed in 37.22s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1810574531555176s
Received healthy response to inference request in 1.2362961769104004s
Received healthy response to inference request in 1.2527649402618408s
Received healthy response to inference request in 1.256270170211792s
Received healthy response to inference request in 1.2485933303833008s
5 requests
0 failed requests
5th percentile: 1.2387556076049804
10th percentile: 1.2412150382995606
20th percentile: 1.2461338996887208
30th percentile: 1.2494276523590089
40th percentile: 1.2510962963104248
50th percentile: 1.2527649402618408
60th percentile: 1.2541670322418212
70th percentile: 1.2555691242218017
80th percentile: 1.4412276268005373
90th percentile: 1.8111425399780274
95th percentile: 1.9960999965667723
99th percentile: 2.1440659618377684
mean time: 1.4349964141845704
Pipeline stage StressChecker completed in 7.83s
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
saishf-sovl-mega-mash-v2_4112_v1 status is now deployed due to DeploymentManager action
saishf-sovl-mega-mash-v2_4112_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics