submission_id: hastagaras-halu-8b-llam_2564_v15
developer_uid: Jellywibble
status: inactive
model_repo: Hastagaras/Halu-8B-Llama3-v0.3
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 100, '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': "<|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\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: 2024-06-04T00:47:59+00:00
model_name: propriety-test-tl
model_eval_status: success
model_group: Hastagaras/Halu-8B-Llama
num_battles: 9555
num_wins: 5104
celo_rating: 1206.0
safety_score: 0.97
propriety_score: 0.6759581881533101
propriety_total_count: 287.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: propriety-test-tl
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Halu-8B-Llama3-v0.3
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-03
win_ratio: 0.5341705913134485
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-halu-8b-llam-2564-v15-mkmlizer
Waiting for job on hastagaras-halu-8b-llam-2564-v15-mkmlizer to finish
hastagaras-halu-8b-llam-2564-v15-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-8b-llam-2564-v15-mkmlizer: ║ _____ __ __ ║
hastagaras-halu-8b-llam-2564-v15-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-halu-8b-llam-2564-v15-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-halu-8b-llam-2564-v15-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-halu-8b-llam-2564-v15-mkmlizer: ║ /___/ ║
hastagaras-halu-8b-llam-2564-v15-mkmlizer: ║ ║
hastagaras-halu-8b-llam-2564-v15-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-halu-8b-llam-2564-v15-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-halu-8b-llam-2564-v15-mkmlizer: ║ https://mk1.ai ║
hastagaras-halu-8b-llam-2564-v15-mkmlizer: ║ ║
hastagaras-halu-8b-llam-2564-v15-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-halu-8b-llam-2564-v15-mkmlizer: ║ belonging to: ║
hastagaras-halu-8b-llam-2564-v15-mkmlizer: ║ ║
hastagaras-halu-8b-llam-2564-v15-mkmlizer: ║ Chai Research Corp. ║
hastagaras-halu-8b-llam-2564-v15-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-halu-8b-llam-2564-v15-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-halu-8b-llam-2564-v15-mkmlizer: ║ ║
hastagaras-halu-8b-llam-2564-v15-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-8b-llam-2564-v15-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.
hastagaras-halu-8b-llam-2564-v15-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-halu-8b-llam-2564-v15-mkmlizer: Downloaded to shared memory in 17.899s
hastagaras-halu-8b-llam-2564-v15-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-8b-llam-2564-v15-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-8b-llam-2564-v15-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 126.64it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 147.12it/s] Loading 0: 16%|█▋ | 48/291 [00:00<00:01, 155.92it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 158.86it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 85.20it/s] Loading 0: 33%|███▎ | 97/291 [00:00<00:02, 96.37it/s] Loading 0: 39%|███▉ | 113/291 [00:00<00:01, 109.30it/s] Loading 0: 45%|████▌ | 131/291 [00:01<00:01, 123.83it/s] Loading 0: 51%|█████ | 149/291 [00:01<00:01, 135.80it/s] Loading 0: 57%|█████▋ | 167/291 [00:01<00:00, 144.24it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 99.31it/s] Loading 0: 69%|██████▉ | 202/291 [00:01<00:00, 107.14it/s] Loading 0: 76%|███████▌ | 220/291 [00:01<00:00, 121.71it/s] Loading 0: 82%|████████▏ | 238/291 [00:01<00:00, 134.05it/s] Loading 0: 88%|████████▊ | 256/291 [00:02<00:00, 143.20it/s] Loading 0: 94%|█████████▍| 274/291 [00:02<00:00, 150.95it/s] Loading 0: 100%|██████████| 291/291 [00:07<00:00, 10.32it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-halu-8b-llam-2564-v15-mkmlizer: quantized model in 22.938s
hastagaras-halu-8b-llam-2564-v15-mkmlizer: Processed model Hastagaras/Halu-8B-Llama3-v0.3 in 43.365s
hastagaras-halu-8b-llam-2564-v15-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-8b-llam-2564-v15-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-8b-llam-2564-v15-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-8b-llam-2564-v15
hastagaras-halu-8b-llam-2564-v15-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llam-2564-v15/config.json
hastagaras-halu-8b-llam-2564-v15-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-8b-llam-2564-v15/special_tokens_map.json
hastagaras-halu-8b-llam-2564-v15-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llam-2564-v15/tokenizer_config.json
hastagaras-halu-8b-llam-2564-v15-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-8b-llam-2564-v15/tokenizer.json
hastagaras-halu-8b-llam-2564-v15-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-8b-llam-2564-v15/flywheel_model.0.safetensors
hastagaras-halu-8b-llam-2564-v15-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-8b-llam-2564-v15-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.
hastagaras-halu-8b-llam-2564-v15-mkmlizer: warnings.warn(
hastagaras-halu-8b-llam-2564-v15-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.
hastagaras-halu-8b-llam-2564-v15-mkmlizer: warnings.warn(
hastagaras-halu-8b-llam-2564-v15-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.
hastagaras-halu-8b-llam-2564-v15-mkmlizer: warnings.warn(
hastagaras-halu-8b-llam-2564-v15-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()
hastagaras-halu-8b-llam-2564-v15-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-halu-8b-llam-2564-v15-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-halu-8b-llam-2564-v15-mkmlizer: Saving duration: 0.397s
hastagaras-halu-8b-llam-2564-v15-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.054s
hastagaras-halu-8b-llam-2564-v15-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-8b-llam-2564-v15-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-8b-llam-2564-v15-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-8b-llam-2564-v15_reward
Job hastagaras-halu-8b-llam-2564-v15-mkmlizer completed after 72.97s with status: succeeded
Stopping job with name hastagaras-halu-8b-llam-2564-v15-mkmlizer
Pipeline stage MKMLizer completed in 77.39s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-8b-llam-2564-v15
Waiting for inference service hastagaras-halu-8b-llam-2564-v15 to be ready
Inference service hastagaras-halu-8b-llam-2564-v15 ready after 60.47865581512451s
Pipeline stage ISVCDeployer completed in 67.77s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1139862537384033s
Received healthy response to inference request in 1.3408000469207764s
Received healthy response to inference request in 1.3708786964416504s
Received healthy response to inference request in 1.295853853225708s
Received healthy response to inference request in 1.2477304935455322s
5 requests
0 failed requests
5th percentile: 1.2573551654815673
10th percentile: 1.2669798374176025
20th percentile: 1.286229181289673
30th percentile: 1.3048430919647216
40th percentile: 1.322821569442749
50th percentile: 1.3408000469207764
60th percentile: 1.3528315067291259
70th percentile: 1.3648629665374756
80th percentile: 1.5195002079010012
90th percentile: 1.8167432308197022
95th percentile: 1.9653647422790526
99th percentile: 2.0842619514465333
mean time: 1.4738498687744142
Pipeline stage StressChecker completed in 8.06s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.02s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.03s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-halu-8b-llam_2564_v15 status is now deployed due to DeploymentManager action
hastagaras-halu-8b-llam_2564_v15 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics