submission_id: hastagaras-halu-8b-llama3-oas_v2
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Halu-8B-Llama3-OAS
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 70, '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: 2024-05-27T02:51:02+00:00
model_name: Test-Baukit2
model_eval_status: success
model_group: Hastagaras/Halu-8B-Llama
num_battles: 10678
num_wins: 5833
celo_rating: 1205.74
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-Baukit2
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: 0.5462633451957295
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-halu-8b-llama3-oas-v2-mkmlizer
Waiting for job on hastagaras-halu-8b-llama3-oas-v2-mkmlizer to finish
hastagaras-halu-8b-llama3-oas-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-8b-llama3-oas-v2-mkmlizer: ║ _____ __ __ ║
hastagaras-halu-8b-llama3-oas-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-halu-8b-llama3-oas-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-halu-8b-llama3-oas-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-halu-8b-llama3-oas-v2-mkmlizer: ║ /___/ ║
hastagaras-halu-8b-llama3-oas-v2-mkmlizer: ║ ║
hastagaras-halu-8b-llama3-oas-v2-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-halu-8b-llama3-oas-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-halu-8b-llama3-oas-v2-mkmlizer: ║ https://mk1.ai ║
hastagaras-halu-8b-llama3-oas-v2-mkmlizer: ║ ║
hastagaras-halu-8b-llama3-oas-v2-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-halu-8b-llama3-oas-v2-mkmlizer: ║ belonging to: ║
hastagaras-halu-8b-llama3-oas-v2-mkmlizer: ║ ║
hastagaras-halu-8b-llama3-oas-v2-mkmlizer: ║ Chai Research Corp. ║
hastagaras-halu-8b-llama3-oas-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-halu-8b-llama3-oas-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-halu-8b-llama3-oas-v2-mkmlizer: ║ ║
hastagaras-halu-8b-llama3-oas-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-8b-llama3-oas-v2-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-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-halu-8b-llama3-oas-v2-mkmlizer: Downloaded to shared memory in 17.274s
hastagaras-halu-8b-llama3-oas-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-8b-llama3-oas-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-8b-llama3-oas-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 123.38it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 148.67it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:01, 158.19it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 149.52it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 81.33it/s] Loading 0: 33%|███▎ | 95/291 [00:00<00:02, 85.21it/s] Loading 0: 39%|███▉ | 113/291 [00:01<00:01, 102.97it/s] Loading 0: 45%|████▌ | 131/291 [00:01<00:01, 118.82it/s] Loading 0: 51%|█████ | 149/291 [00:01<00:01, 131.22it/s] Loading 0: 57%|█████▋ | 167/291 [00:01<00:00, 141.22it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 96.55it/s] Loading 0: 69%|██████▉ | 202/291 [00:01<00:00, 103.82it/s] Loading 0: 76%|███████▌ | 220/291 [00:01<00:00, 118.05it/s] Loading 0: 82%|████████▏ | 238/291 [00:02<00:00, 130.22it/s] Loading 0: 88%|████████▊ | 256/291 [00:02<00:00, 139.88it/s] Loading 0: 94%|█████████▍| 274/291 [00:02<00:00, 146.73it/s] Loading 0: 100%|█████████▉| 290/291 [00:07<00:00, 10.13it/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-v2-mkmlizer: quantized model in 22.873s
hastagaras-halu-8b-llama3-oas-v2-mkmlizer: Processed model Hastagaras/Halu-8B-Llama3-OAS in 42.727s
hastagaras-halu-8b-llama3-oas-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-8b-llama3-oas-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-8b-llama3-oas-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-8b-llama3-oas-v2
hastagaras-halu-8b-llama3-oas-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama3-oas-v2/special_tokens_map.json
hastagaras-halu-8b-llama3-oas-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama3-oas-v2/tokenizer_config.json
hastagaras-halu-8b-llama3-oas-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama3-oas-v2/config.json
hastagaras-halu-8b-llama3-oas-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama3-oas-v2/tokenizer.json
hastagaras-halu-8b-llama3-oas-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-8b-llama3-oas-v2/flywheel_model.0.safetensors
hastagaras-halu-8b-llama3-oas-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-8b-llama3-oas-v2-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-v2-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama3-oas-v2-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-v2-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama3-oas-v2-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-v2-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama3-oas-v2-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-v2-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-halu-8b-llama3-oas-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-halu-8b-llama3-oas-v2-mkmlizer: Saving duration: 0.389s
hastagaras-halu-8b-llama3-oas-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.111s
hastagaras-halu-8b-llama3-oas-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-8b-llama3-oas-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-8b-llama3-oas-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-8b-llama3-oas-v2_reward
hastagaras-halu-8b-llama3-oas-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-halu-8b-llama3-oas-v2_reward/reward.tensors
Job hastagaras-halu-8b-llama3-oas-v2-mkmlizer completed after 72.67s with status: succeeded
Stopping job with name hastagaras-halu-8b-llama3-oas-v2-mkmlizer
Pipeline stage MKMLizer completed in 76.43s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-8b-llama3-oas-v2
Waiting for inference service hastagaras-halu-8b-llama3-oas-v2 to be ready
Inference service hastagaras-halu-8b-llama3-oas-v2 ready after 60.34573841094971s
Pipeline stage ISVCDeployer completed in 67.70s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.24798583984375s
Received healthy response to inference request in 1.4023096561431885s
Received healthy response to inference request in 1.3795645236968994s
Received healthy response to inference request in 1.3379778861999512s
Received healthy response to inference request in 1.2968847751617432s
5 requests
0 failed requests
5th percentile: 1.3051033973693849
10th percentile: 1.3133220195770263
20th percentile: 1.3297592639923095
30th percentile: 1.346295213699341
40th percentile: 1.3629298686981202
50th percentile: 1.3795645236968994
60th percentile: 1.388662576675415
70th percentile: 1.3977606296539307
80th percentile: 1.571444892883301
90th percentile: 1.9097153663635256
95th percentile: 2.0788506031036373
99th percentile: 2.2141587924957276
mean time: 1.5329445362091065
Pipeline stage StressChecker completed in 8.25s
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-llama3-oas_v2 status is now deployed due to DeploymentManager action
hastagaras-halu-8b-llama3-oas_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics