submission_id: hastagaras-halu-8b-llama_2564_v5
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': 1.0, 'top_p': 0.95, 'min_p': 0.1, 'top_k': 120, '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: 2024-05-24T10:55:05+00:00
model_name: HWEHWHEHW
model_eval_status: success
model_group: Hastagaras/Halu-8B-Llama
num_battles: 18558
num_wins: 10193
celo_rating: 1206.54
safety_score: 0.96
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: HWEHWHEHW
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: 2024-05-24
win_ratio: 0.5492509968746632
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-halu-8b-llama-2564-v5-mkmlizer
Waiting for job on hastagaras-halu-8b-llama-2564-v5-mkmlizer to finish
hastagaras-halu-8b-llama-2564-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-8b-llama-2564-v5-mkmlizer: ║ _____ __ __ ║
hastagaras-halu-8b-llama-2564-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-halu-8b-llama-2564-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-halu-8b-llama-2564-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-halu-8b-llama-2564-v5-mkmlizer: ║ /___/ ║
hastagaras-halu-8b-llama-2564-v5-mkmlizer: ║ ║
hastagaras-halu-8b-llama-2564-v5-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-halu-8b-llama-2564-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-halu-8b-llama-2564-v5-mkmlizer: ║ https://mk1.ai ║
hastagaras-halu-8b-llama-2564-v5-mkmlizer: ║ ║
hastagaras-halu-8b-llama-2564-v5-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-halu-8b-llama-2564-v5-mkmlizer: ║ belonging to: ║
hastagaras-halu-8b-llama-2564-v5-mkmlizer: ║ ║
hastagaras-halu-8b-llama-2564-v5-mkmlizer: ║ Chai Research Corp. ║
hastagaras-halu-8b-llama-2564-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-halu-8b-llama-2564-v5-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-halu-8b-llama-2564-v5-mkmlizer: ║ ║
hastagaras-halu-8b-llama-2564-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-8b-llama-2564-v5-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-v5-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-halu-8b-llama-2564-v5-mkmlizer: Downloaded to shared memory in 16.380s
hastagaras-halu-8b-llama-2564-v5-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-8b-llama-2564-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-8b-llama-2564-v5-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 125.10it/s] Loading 0: 11%|█ | 32/291 [00:00<00:01, 151.52it/s] Loading 0: 17%|█▋ | 50/291 [00:00<00:01, 159.09it/s] Loading 0: 23%|██▎ | 68/291 [00:00<00:01, 164.66it/s] Loading 0: 29%|██▉ | 85/291 [00:00<00:02, 92.09it/s] Loading 0: 35%|███▌ | 103/291 [00:00<00:01, 109.11it/s] Loading 0: 42%|████▏ | 121/291 [00:00<00:01, 124.27it/s] Loading 0: 48%|████▊ | 139/291 [00:01<00:01, 136.67it/s] Loading 0: 54%|█████▍ | 157/291 [00:01<00:00, 146.62it/s] Loading 0: 60%|██████ | 176/291 [00:01<00:00, 158.09it/s] Loading 0: 67%|██████▋ | 194/291 [00:01<00:01, 93.28it/s] Loading 0: 71%|███████▏ | 208/291 [00:01<00:00, 101.74it/s] Loading 0: 76%|███████▋ | 222/291 [00:01<00:00, 109.16it/s] Loading 0: 82%|████████▏ | 239/291 [00:01<00:00, 120.91it/s] Loading 0: 88%|████████▊ | 257/291 [00:02<00:00, 134.07it/s] Loading 0: 95%|█████████▍| 275/291 [00:02<00:00, 145.27it/s] Loading 0: 100%|██████████| 291/291 [00:07<00:00, 9.90it/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-v5-mkmlizer: quantized model in 22.708s
hastagaras-halu-8b-llama-2564-v5-mkmlizer: Processed model Hastagaras/Halu-8B-Llama3-v0.3 in 41.515s
hastagaras-halu-8b-llama-2564-v5-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-8b-llama-2564-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-8b-llama-2564-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v5
hastagaras-halu-8b-llama-2564-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v5/special_tokens_map.json
hastagaras-halu-8b-llama-2564-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v5/tokenizer_config.json
hastagaras-halu-8b-llama-2564-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v5/config.json
hastagaras-halu-8b-llama-2564-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v5/tokenizer.json
hastagaras-halu-8b-llama-2564-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v5/flywheel_model.0.safetensors
hastagaras-halu-8b-llama-2564-v5-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-8b-llama-2564-v5-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-v5-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-2564-v5-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-v5-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-2564-v5-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-v5-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-2564-v5-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-v5-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-halu-8b-llama-2564-v5-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-halu-8b-llama-2564-v5-mkmlizer: Saving duration: 0.417s
hastagaras-halu-8b-llama-2564-v5-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.630s
hastagaras-halu-8b-llama-2564-v5-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-8b-llama-2564-v5-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-8b-llama-2564-v5-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v5_reward
hastagaras-halu-8b-llama-2564-v5-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v5_reward/config.json
hastagaras-halu-8b-llama-2564-v5-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v5_reward/tokenizer_config.json
hastagaras-halu-8b-llama-2564-v5-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v5_reward/special_tokens_map.json
hastagaras-halu-8b-llama-2564-v5-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v5_reward/vocab.json
hastagaras-halu-8b-llama-2564-v5-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v5_reward/merges.txt
hastagaras-halu-8b-llama-2564-v5-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v5_reward/tokenizer.json
hastagaras-halu-8b-llama-2564-v5-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v5_reward/reward.tensors
Job hastagaras-halu-8b-llama-2564-v5-mkmlizer completed after 62.88s with status: succeeded
Stopping job with name hastagaras-halu-8b-llama-2564-v5-mkmlizer
Pipeline stage MKMLizer completed in 67.42s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-8b-llama-2564-v5
Waiting for inference service hastagaras-halu-8b-llama-2564-v5 to be ready
Inference service hastagaras-halu-8b-llama-2564-v5 ready after 60.28955841064453s
Pipeline stage ISVCDeployer completed in 68.07s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1691904067993164s
Received healthy response to inference request in 1.3457286357879639s
Received healthy response to inference request in 1.3353495597839355s
Received healthy response to inference request in 1.2971351146697998s
Received healthy response to inference request in 1.238548994064331s
5 requests
0 failed requests
5th percentile: 1.2502662181854247
10th percentile: 1.2619834423065186
20th percentile: 1.2854178905487061
30th percentile: 1.3047780036926269
40th percentile: 1.3200637817382812
50th percentile: 1.3353495597839355
60th percentile: 1.339501190185547
70th percentile: 1.3436528205871583
80th percentile: 1.5104209899902346
90th percentile: 1.8398056983947755
95th percentile: 2.0044980525970457
99th percentile: 2.136251935958862
mean time: 1.4771905422210694
Pipeline stage StressChecker completed in 8.00s
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_v5 status is now deployed due to DeploymentManager action
hastagaras-halu-8b-llama_2564_v5 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics