submission_id: hastagaras-halu-8b-llama_2564_v1
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Halu-8B-Llama3-v0.3
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.05, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, '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: 2024-05-24T06:30:00+00:00
model_name: hashslingingslasher
model_eval_status: success
model_group: Hastagaras/Halu-8B-Llama
num_battles: 13390
num_wins: 7346
celo_rating: 1207.95
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: hashslingingslasher
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: 2024-05-23
win_ratio: 0.5486183719193428
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-halu-8b-llama-2564-v1-mkmlizer
Waiting for job on hastagaras-halu-8b-llama-2564-v1-mkmlizer to finish
hastagaras-halu-8b-llama-2564-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-8b-llama-2564-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-halu-8b-llama-2564-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-halu-8b-llama-2564-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-halu-8b-llama-2564-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-halu-8b-llama-2564-v1-mkmlizer: ║ /___/ ║
hastagaras-halu-8b-llama-2564-v1-mkmlizer: ║ ║
hastagaras-halu-8b-llama-2564-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-halu-8b-llama-2564-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-halu-8b-llama-2564-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-halu-8b-llama-2564-v1-mkmlizer: ║ ║
hastagaras-halu-8b-llama-2564-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-halu-8b-llama-2564-v1-mkmlizer: ║ belonging to: ║
hastagaras-halu-8b-llama-2564-v1-mkmlizer: ║ ║
hastagaras-halu-8b-llama-2564-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-halu-8b-llama-2564-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-halu-8b-llama-2564-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-halu-8b-llama-2564-v1-mkmlizer: ║ ║
hastagaras-halu-8b-llama-2564-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-8b-llama-2564-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.
hastagaras-halu-8b-llama-2564-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-halu-8b-llama-2564-v1-mkmlizer: Downloaded to shared memory in 34.717s
hastagaras-halu-8b-llama-2564-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-8b-llama-2564-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-8b-llama-2564-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 125.78it/s] Loading 0: 11%|█ | 32/291 [00:00<00:01, 150.47it/s] Loading 0: 17%|█▋ | 50/291 [00:00<00:01, 159.28it/s] Loading 0: 23%|██▎ | 68/291 [00:00<00:01, 166.04it/s] Loading 0: 29%|██▉ | 85/291 [00:00<00:02, 88.41it/s] Loading 0: 35%|███▌ | 103/291 [00:00<00:01, 106.96it/s] Loading 0: 42%|████▏ | 121/291 [00:00<00:01, 122.99it/s] Loading 0: 48%|████▊ | 139/291 [00:01<00:01, 136.01it/s] Loading 0: 54%|█████▍ | 157/291 [00:01<00:00, 146.07it/s] Loading 0: 60%|██████ | 176/291 [00:01<00:00, 157.04it/s] Loading 0: 67%|██████▋ | 194/291 [00:01<00:01, 95.87it/s] Loading 0: 73%|███████▎ | 212/291 [00:01<00:00, 110.12it/s] Loading 0: 79%|███████▉ | 230/291 [00:01<00:00, 124.33it/s] Loading 0: 85%|████████▌ | 248/291 [00:01<00:00, 136.20it/s] Loading 0: 91%|█████████▏| 266/291 [00:02<00:00, 146.14it/s] Loading 0: 98%|█████████▊| 286/291 [00:02<00:00, 159.69it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-halu-8b-llama-2564-v1-mkmlizer: quantized model in 22.587s
hastagaras-halu-8b-llama-2564-v1-mkmlizer: Processed model Hastagaras/Halu-8B-Llama3-v0.3 in 59.734s
hastagaras-halu-8b-llama-2564-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-8b-llama-2564-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-8b-llama-2564-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v1
hastagaras-halu-8b-llama-2564-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v1/config.json
hastagaras-halu-8b-llama-2564-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v1/special_tokens_map.json
hastagaras-halu-8b-llama-2564-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v1/tokenizer_config.json
hastagaras-halu-8b-llama-2564-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v1/tokenizer.json
hastagaras-halu-8b-llama-2564-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v1/flywheel_model.0.safetensors
hastagaras-halu-8b-llama-2564-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-8b-llama-2564-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.
hastagaras-halu-8b-llama-2564-v1-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-2564-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.
hastagaras-halu-8b-llama-2564-v1-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-2564-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.
hastagaras-halu-8b-llama-2564-v1-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-2564-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()
hastagaras-halu-8b-llama-2564-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-halu-8b-llama-2564-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-halu-8b-llama-2564-v1-mkmlizer: Saving duration: 0.402s
hastagaras-halu-8b-llama-2564-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.282s
hastagaras-halu-8b-llama-2564-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-8b-llama-2564-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-8b-llama-2564-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v1_reward
hastagaras-halu-8b-llama-2564-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v1_reward/config.json
hastagaras-halu-8b-llama-2564-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v1_reward/special_tokens_map.json
hastagaras-halu-8b-llama-2564-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v1_reward/tokenizer_config.json
hastagaras-halu-8b-llama-2564-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v1_reward/vocab.json
hastagaras-halu-8b-llama-2564-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v1_reward/merges.txt
hastagaras-halu-8b-llama-2564-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v1_reward/tokenizer.json
hastagaras-halu-8b-llama-2564-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v1_reward/reward.tensors
Job hastagaras-halu-8b-llama-2564-v1-mkmlizer completed after 83.1s with status: succeeded
Stopping job with name hastagaras-halu-8b-llama-2564-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.02s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-8b-llama-2564-v1
Waiting for inference service hastagaras-halu-8b-llama-2564-v1 to be ready
Inference service hastagaras-halu-8b-llama-2564-v1 ready after 30.161564111709595s
Pipeline stage ISVCDeployer completed in 36.00s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.102938652038574s
Received healthy response to inference request in 1.3700051307678223s
Received healthy response to inference request in 1.3266146183013916s
Received healthy response to inference request in 1.3003957271575928s
Received healthy response to inference request in 1.254899263381958s
5 requests
0 failed requests
5th percentile: 1.263998556137085
10th percentile: 1.273097848892212
20th percentile: 1.2912964344024658
30th percentile: 1.3056395053863525
40th percentile: 1.316127061843872
50th percentile: 1.3266146183013916
60th percentile: 1.343970823287964
70th percentile: 1.3613270282745362
80th percentile: 1.5165918350219727
90th percentile: 1.8097652435302736
95th percentile: 1.9563519477844238
99th percentile: 2.073621311187744
mean time: 1.4709706783294678
Pipeline stage StressChecker completed in 7.99s
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
hastagaras-halu-8b-llama_2564_v1 status is now deployed due to DeploymentManager action
hastagaras-halu-8b-llama_2564_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics