submission_id: hastagaras-halu-8b-llama3-oas_v1
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Halu-8B-Llama3-OAS
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, '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: 2024-05-27T02:36:50+00:00
model_name: Test-Baukit
model_eval_status: success
model_group: Hastagaras/Halu-8B-Llama
num_battles: 11492
num_wins: 6174
celo_rating: 1200.08
safety_score: 0.92
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: Test-Baukit
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Halu-8B-Llama3-OAS
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-26
win_ratio: 0.5372432996867386
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-halu-8b-llama3-oas-v1-mkmlizer
Waiting for job on hastagaras-halu-8b-llama3-oas-v1-mkmlizer to finish
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: ║ /___/ ║
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: ║ ║
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: ║ ║
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: ║ belonging to: ║
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: ║ ║
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: ║ ║
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-8b-llama3-oas-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-llama3-oas-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: Downloaded to shared memory in 25.225s
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 124.08it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 144.50it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:01, 152.60it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 156.74it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 84.01it/s] Loading 0: 33%|███▎ | 95/291 [00:00<00:02, 90.34it/s] Loading 0: 39%|███▉ | 113/291 [00:01<00:01, 108.75it/s] Loading 0: 45%|████▌ | 131/291 [00:01<00:01, 123.70it/s] Loading 0: 51%|█████ | 149/291 [00:01<00:01, 135.08it/s] Loading 0: 57%|█████▋ | 167/291 [00:01<00:00, 143.73it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 98.17it/s] Loading 0: 69%|██████▉ | 202/291 [00:01<00:00, 106.29it/s] Loading 0: 76%|███████▌ | 220/291 [00:01<00:00, 121.20it/s] Loading 0: 82%|████████▏ | 238/291 [00:01<00:00, 133.48it/s] Loading 0: 88%|████████▊ | 256/291 [00:02<00:00, 143.04it/s] Loading 0: 94%|█████████▍| 274/291 [00:02<00:00, 151.40it/s] Loading 0: 100%|██████████| 291/291 [00:07<00:00, 10.12it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: quantized model in 22.813s
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: Processed model Hastagaras/Halu-8B-Llama3-OAS in 50.590s
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-8b-llama3-oas-v1
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama3-oas-v1/config.json
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama3-oas-v1/special_tokens_map.json
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama3-oas-v1/tokenizer.json
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama3-oas-v1/tokenizer_config.json
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-8b-llama3-oas-v1/flywheel_model.0.safetensors
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-8b-llama3-oas-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-llama3-oas-v1-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama3-oas-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-llama3-oas-v1-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama3-oas-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-llama3-oas-v1-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama3-oas-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-llama3-oas-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: Saving duration: 0.390s
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.565s
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-8b-llama3-oas-v1_reward
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama3-oas-v1_reward/config.json
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama3-oas-v1_reward/tokenizer_config.json
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-halu-8b-llama3-oas-v1_reward/merges.txt
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-halu-8b-llama3-oas-v1_reward/vocab.json
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-halu-8b-llama3-oas-v1_reward/special_tokens_map.json
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-halu-8b-llama3-oas-v1_reward/tokenizer.json
hastagaras-halu-8b-llama3-oas-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-halu-8b-llama3-oas-v1_reward/reward.tensors
Job hastagaras-halu-8b-llama3-oas-v1-mkmlizer completed after 83.06s with status: succeeded
Stopping job with name hastagaras-halu-8b-llama3-oas-v1-mkmlizer
Pipeline stage MKMLizer completed in 85.88s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-8b-llama3-oas-v1
Waiting for inference service hastagaras-halu-8b-llama3-oas-v1 to be ready
Inference service hastagaras-halu-8b-llama3-oas-v1 ready after 40.21401381492615s
Pipeline stage ISVCDeployer completed in 47.14s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1227071285247803s
Received healthy response to inference request in 1.9213218688964844s
Received healthy response to inference request in 1.3249695301055908s
Received healthy response to inference request in 1.3293216228485107s
Received healthy response to inference request in 1.2555279731750488s
5 requests
0 failed requests
5th percentile: 1.2694162845611572
10th percentile: 1.2833045959472655
20th percentile: 1.3110812187194825
30th percentile: 1.3258399486541748
40th percentile: 1.3275807857513429
50th percentile: 1.3293216228485107
60th percentile: 1.5661217212677
70th percentile: 1.8029218196868895
80th percentile: 1.9615989208221436
90th percentile: 2.042153024673462
95th percentile: 2.0824300765991213
99th percentile: 2.1146517181396485
mean time: 1.590769624710083
Pipeline stage StressChecker completed in 8.52s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.05s
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-llama3-oas_v1 status is now deployed due to DeploymentManager action
hastagaras-halu-8b-llama3-oas_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics