submission_id: hastagaras-halu-8b-llama_2564_v4
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': 0.1, '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: 2024-05-24T08:50:42+00:00
model_name: HWEHWHEHW
model_eval_status: success
model_group: Hastagaras/Halu-8B-Llama
num_battles: 101006
num_wins: 53563
celo_rating: 1208.24
safety_score: 0.97
propriety_score: 0.698971537909591
propriety_total_count: 41810.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: HWEHWHEHW
ineligible_reason: None
language_model: Hastagaras/Halu-8B-Llama3-v0.3
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-24
win_ratio: 0.5302952299863375
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-halu-8b-llama-2564-v4-mkmlizer
Waiting for job on hastagaras-halu-8b-llama-2564-v4-mkmlizer to finish
hastagaras-halu-8b-llama-2564-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-8b-llama-2564-v4-mkmlizer: ║ _____ __ __ ║
hastagaras-halu-8b-llama-2564-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-halu-8b-llama-2564-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-halu-8b-llama-2564-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-halu-8b-llama-2564-v4-mkmlizer: ║ /___/ ║
hastagaras-halu-8b-llama-2564-v4-mkmlizer: ║ ║
hastagaras-halu-8b-llama-2564-v4-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-halu-8b-llama-2564-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-halu-8b-llama-2564-v4-mkmlizer: ║ https://mk1.ai ║
hastagaras-halu-8b-llama-2564-v4-mkmlizer: ║ ║
hastagaras-halu-8b-llama-2564-v4-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-halu-8b-llama-2564-v4-mkmlizer: ║ belonging to: ║
hastagaras-halu-8b-llama-2564-v4-mkmlizer: ║ ║
hastagaras-halu-8b-llama-2564-v4-mkmlizer: ║ Chai Research Corp. ║
hastagaras-halu-8b-llama-2564-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-halu-8b-llama-2564-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-halu-8b-llama-2564-v4-mkmlizer: ║ ║
hastagaras-halu-8b-llama-2564-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-8b-llama-2564-v4-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-v4-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-halu-8b-llama-2564-v4-mkmlizer: Downloaded to shared memory in 23.233s
hastagaras-halu-8b-llama-2564-v4-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-8b-llama-2564-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-8b-llama-2564-v4-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 120.53it/s] Loading 0: 10%|█ | 30/291 [00:00<00:01, 140.03it/s] Loading 0: 15%|█▌ | 44/291 [00:00<00:01, 136.89it/s] Loading 0: 20%|█▉ | 58/291 [00:00<00:01, 136.48it/s] Loading 0: 26%|██▌ | 75/291 [00:00<00:01, 144.68it/s] Loading 0: 31%|███ | 90/291 [00:00<00:02, 68.88it/s] Loading 0: 36%|███▌ | 104/291 [00:01<00:02, 80.53it/s] Loading 0: 42%|████▏ | 121/291 [00:01<00:01, 97.98it/s] Loading 0: 47%|████▋ | 138/291 [00:01<00:01, 113.47it/s] Loading 0: 53%|█████▎ | 153/291 [00:01<00:01, 121.86it/s] Loading 0: 58%|█████▊ | 168/291 [00:01<00:00, 126.73it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 77.18it/s] Loading 0: 69%|██████▉ | 201/291 [00:02<00:01, 87.01it/s] Loading 0: 74%|███████▍ | 216/291 [00:02<00:00, 99.05it/s] Loading 0: 79%|███████▉ | 230/291 [00:02<00:00, 106.85it/s] Loading 0: 85%|████████▍ | 247/291 [00:02<00:00, 121.42it/s] Loading 0: 91%|█████████ | 264/291 [00:02<00:00, 133.54it/s] Loading 0: 96%|█████████▌| 280/291 [00:02<00:00, 140.05it/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-v4-mkmlizer: quantized model in 18.930s
hastagaras-halu-8b-llama-2564-v4-mkmlizer: Processed model Hastagaras/Halu-8B-Llama3-v0.3 in 43.249s
hastagaras-halu-8b-llama-2564-v4-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-8b-llama-2564-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-8b-llama-2564-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v4
hastagaras-halu-8b-llama-2564-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v4/config.json
hastagaras-halu-8b-llama-2564-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v4/special_tokens_map.json
hastagaras-halu-8b-llama-2564-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v4/tokenizer_config.json
hastagaras-halu-8b-llama-2564-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v4/tokenizer.json
hastagaras-halu-8b-llama-2564-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v4/flywheel_model.0.safetensors
hastagaras-halu-8b-llama-2564-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-8b-llama-2564-v4-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-v4-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-2564-v4-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-v4-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-2564-v4-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-v4-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-2564-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-halu-8b-llama-2564-v4-mkmlizer: Saving duration: 0.303s
hastagaras-halu-8b-llama-2564-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.193s
hastagaras-halu-8b-llama-2564-v4-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-8b-llama-2564-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-8b-llama-2564-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v4_reward
hastagaras-halu-8b-llama-2564-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v4_reward/config.json
hastagaras-halu-8b-llama-2564-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v4_reward/special_tokens_map.json
hastagaras-halu-8b-llama-2564-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v4_reward/tokenizer_config.json
hastagaras-halu-8b-llama-2564-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v4_reward/merges.txt
hastagaras-halu-8b-llama-2564-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v4_reward/vocab.json
hastagaras-halu-8b-llama-2564-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v4_reward/tokenizer.json
hastagaras-halu-8b-llama-2564-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v4_reward/reward.tensors
Job hastagaras-halu-8b-llama-2564-v4-mkmlizer completed after 73.17s with status: succeeded
Stopping job with name hastagaras-halu-8b-llama-2564-v4-mkmlizer
Pipeline stage MKMLizer completed in 77.20s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-8b-llama-2564-v4
Waiting for inference service hastagaras-halu-8b-llama-2564-v4 to be ready
Inference service hastagaras-halu-8b-llama-2564-v4 ready after 40.221781969070435s
Pipeline stage ISVCDeployer completed in 47.91s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0686233043670654s
Received healthy response to inference request in 1.354543685913086s
Received healthy response to inference request in 1.318098545074463s
Received healthy response to inference request in 1.2873601913452148s
Received healthy response to inference request in 1.2237789630889893s
5 requests
0 failed requests
5th percentile: 1.2364952087402343
10th percentile: 1.2492114543914794
20th percentile: 1.2746439456939698
30th percentile: 1.2935078620910645
40th percentile: 1.3058032035827636
50th percentile: 1.318098545074463
60th percentile: 1.332676601409912
70th percentile: 1.3472546577453612
80th percentile: 1.497359609603882
90th percentile: 1.7829914569854737
95th percentile: 1.9258073806762694
99th percentile: 2.0400601196289063
mean time: 1.4504809379577637
Pipeline stage StressChecker completed in 7.93s
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 0.06s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-halu-8b-llama_2564_v4 status is now deployed due to DeploymentManager action
hastagaras-halu-8b-llama_2564_v4 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics