submission_id: hastagaras-halu-8b-llama_7060_v1
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/HALU-8B-LLAMA3-EXP-5
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.05, '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: 2024-06-01T04:19:08+00:00
model_name: whehehe
model_eval_status: success
model_group: Hastagaras/HALU-8B-LLAMA
num_battles: 11426
num_wins: 6468
celo_rating: 1215.89
safety_score: 0.94
propriety_score: 0.2
propriety_total_count: 5.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: whehehe
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/HALU-8B-LLAMA3-EXP-5
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-31
win_ratio: 0.5660773674076667
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-halu-8b-llama-7060-v1-mkmlizer
Waiting for job on hastagaras-halu-8b-llama-7060-v1-mkmlizer to finish
hastagaras-halu-8b-llama-7060-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-8b-llama-7060-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-halu-8b-llama-7060-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-halu-8b-llama-7060-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-halu-8b-llama-7060-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-halu-8b-llama-7060-v1-mkmlizer: ║ /___/ ║
hastagaras-halu-8b-llama-7060-v1-mkmlizer: ║ ║
hastagaras-halu-8b-llama-7060-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-halu-8b-llama-7060-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-halu-8b-llama-7060-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-halu-8b-llama-7060-v1-mkmlizer: ║ ║
hastagaras-halu-8b-llama-7060-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-halu-8b-llama-7060-v1-mkmlizer: ║ belonging to: ║
hastagaras-halu-8b-llama-7060-v1-mkmlizer: ║ ║
hastagaras-halu-8b-llama-7060-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-halu-8b-llama-7060-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-halu-8b-llama-7060-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-halu-8b-llama-7060-v1-mkmlizer: ║ ║
hastagaras-halu-8b-llama-7060-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-8b-llama-7060-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-7060-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-halu-8b-llama-7060-v1-mkmlizer: Downloaded to shared memory in 31.615s
hastagaras-halu-8b-llama-7060-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-8b-llama-7060-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-8b-llama-7060-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 123.79it/s] Loading 0: 11%|█ | 32/291 [00:00<00:01, 150.63it/s] Loading 0: 17%|█▋ | 50/291 [00:00<00:01, 159.61it/s] Loading 0: 23%|██▎ | 68/291 [00:00<00:01, 164.07it/s] Loading 0: 29%|██▉ | 85/291 [00:00<00:02, 86.40it/s] Loading 0: 35%|███▌ | 103/291 [00:00<00:01, 103.89it/s] Loading 0: 42%|████▏ | 121/291 [00:01<00:01, 118.64it/s] Loading 0: 48%|████▊ | 139/291 [00:01<00:01, 130.73it/s] Loading 0: 54%|█████▍ | 157/291 [00:01<00:00, 139.86it/s] Loading 0: 60%|██████ | 176/291 [00:01<00:00, 151.40it/s] Loading 0: 66%|██████▋ | 193/291 [00:01<00:01, 91.26it/s] Loading 0: 73%|███████▎ | 211/291 [00:01<00:00, 105.94it/s] Loading 0: 79%|███████▊ | 229/291 [00:01<00:00, 119.29it/s] Loading 0: 85%|████████▍ | 247/291 [00:02<00:00, 130.46it/s] Loading 0: 91%|█████████ | 265/291 [00:02<00:00, 138.86it/s] Loading 0: 97%|█████████▋| 282/291 [00:02<00:00, 144.34it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-halu-8b-llama-7060-v1-mkmlizer: quantized model in 22.995s
hastagaras-halu-8b-llama-7060-v1-mkmlizer: Processed model Hastagaras/HALU-8B-LLAMA3-EXP-5 in 57.163s
hastagaras-halu-8b-llama-7060-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-8b-llama-7060-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-8b-llama-7060-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-8b-llama-7060-v1
hastagaras-halu-8b-llama-7060-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-7060-v1/special_tokens_map.json
hastagaras-halu-8b-llama-7060-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-7060-v1/config.json
hastagaras-halu-8b-llama-7060-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-7060-v1/tokenizer_config.json
hastagaras-halu-8b-llama-7060-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-7060-v1/tokenizer.json
hastagaras-halu-8b-llama-7060-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-8b-llama-7060-v1/flywheel_model.0.safetensors
hastagaras-halu-8b-llama-7060-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-8b-llama-7060-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-7060-v1-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-7060-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-7060-v1-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-7060-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-7060-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-halu-8b-llama-7060-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-halu-8b-llama-7060-v1-mkmlizer: Saving duration: 0.390s
hastagaras-halu-8b-llama-7060-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.554s
hastagaras-halu-8b-llama-7060-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-8b-llama-7060-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-8b-llama-7060-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-8b-llama-7060-v1_reward
hastagaras-halu-8b-llama-7060-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-7060-v1_reward/config.json
hastagaras-halu-8b-llama-7060-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-7060-v1_reward/tokenizer_config.json
hastagaras-halu-8b-llama-7060-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-halu-8b-llama-7060-v1_reward/merges.txt
hastagaras-halu-8b-llama-7060-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-7060-v1_reward/vocab.json
hastagaras-halu-8b-llama-7060-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-7060-v1_reward/special_tokens_map.json
hastagaras-halu-8b-llama-7060-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-7060-v1_reward/tokenizer.json
hastagaras-halu-8b-llama-7060-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-halu-8b-llama-7060-v1_reward/reward.tensors
Job hastagaras-halu-8b-llama-7060-v1-mkmlizer completed after 82.96s with status: succeeded
Stopping job with name hastagaras-halu-8b-llama-7060-v1-mkmlizer
Pipeline stage MKMLizer completed in 86.74s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-8b-llama-7060-v1
Waiting for inference service hastagaras-halu-8b-llama-7060-v1 to be ready
Inference service hastagaras-halu-8b-llama-7060-v1 ready after 40.21433186531067s
Pipeline stage ISVCDeployer completed in 47.42s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1336045265197754s
Received healthy response to inference request in 1.3157744407653809s
Received healthy response to inference request in 1.3167662620544434s
Retrying (%r) after connection broken by '%r': %s
Received healthy response to inference request in 1.27262282371521s
Received healthy response to inference request in 1.2100083827972412s
5 requests
0 failed requests
5th percentile: 1.222531270980835
10th percentile: 1.2350541591644286
20th percentile: 1.2600999355316163
30th percentile: 1.2812531471252442
40th percentile: 1.2985137939453124
50th percentile: 1.3157744407653809
60th percentile: 1.3161711692810059
70th percentile: 1.3165678977966309
80th percentile: 1.48013391494751
90th percentile: 1.8068692207336428
95th percentile: 1.9702368736267089
99th percentile: 2.100930995941162
mean time: 1.4497552871704102
Pipeline stage StressChecker completed in 7.91s
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_7060_v1 status is now deployed due to DeploymentManager action
hastagaras-halu-8b-llama_7060_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics