submission_id: hastagaras-halu-8b-llama_4766_v5
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/HALU-8B-LLAMA3-BRSLURP
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.1, 'top_p': 1.0, 'min_p': 0.08, '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': "<|begin_of_text|><|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: 2024-06-11T06:48:25+00:00
model_name: propriety-test
model_eval_status: success
model_group: Hastagaras/HALU-8B-LLAMA
num_battles: 12670
num_wins: 7083
celo_rating: 1213.05
propriety_score: 0.6754054654521218
propriety_total_count: 4501.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: propriety-test
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/HALU-8B-LLAMA3-BRSLURP
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-10
win_ratio: 0.5590370955011839
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-halu-8b-llama-4766-v5-mkmlizer
Waiting for job on hastagaras-halu-8b-llama-4766-v5-mkmlizer to finish
hastagaras-halu-8b-llama-4766-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-8b-llama-4766-v5-mkmlizer: ║ _____ __ __ ║
hastagaras-halu-8b-llama-4766-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-halu-8b-llama-4766-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-halu-8b-llama-4766-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-halu-8b-llama-4766-v5-mkmlizer: ║ /___/ ║
hastagaras-halu-8b-llama-4766-v5-mkmlizer: ║ ║
hastagaras-halu-8b-llama-4766-v5-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-halu-8b-llama-4766-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-halu-8b-llama-4766-v5-mkmlizer: ║ https://mk1.ai ║
hastagaras-halu-8b-llama-4766-v5-mkmlizer: ║ ║
hastagaras-halu-8b-llama-4766-v5-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-halu-8b-llama-4766-v5-mkmlizer: ║ belonging to: ║
hastagaras-halu-8b-llama-4766-v5-mkmlizer: ║ ║
hastagaras-halu-8b-llama-4766-v5-mkmlizer: ║ Chai Research Corp. ║
hastagaras-halu-8b-llama-4766-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-halu-8b-llama-4766-v5-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-halu-8b-llama-4766-v5-mkmlizer: ║ ║
hastagaras-halu-8b-llama-4766-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-8b-llama-4766-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-4766-v5-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-halu-8b-llama-4766-v5-mkmlizer: Downloaded to shared memory in 30.291s
hastagaras-halu-8b-llama-4766-v5-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-8b-llama-4766-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-8b-llama-4766-v5-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<09:42, 2.02s/it] Loading 0: 8%|▊ | 23/291 [00:04<00:35, 7.64it/s] Loading 0: 16%|█▌ | 46/291 [00:04<00:13, 17.95it/s] Loading 0: 22%|██▏ | 63/291 [00:04<00:09, 23.74it/s] Loading 0: 30%|██▉ | 86/291 [00:04<00:05, 38.19it/s] Loading 0: 37%|███▋ | 109/291 [00:04<00:03, 55.71it/s] Loading 0: 45%|████▌ | 131/291 [00:04<00:02, 74.07it/s] Loading 0: 53%|█████▎ | 154/291 [00:05<00:01, 95.83it/s] Loading 0: 60%|█████▉ | 174/291 [00:05<00:01, 81.29it/s] Loading 0: 67%|██████▋ | 194/291 [00:05<00:00, 97.60it/s] Loading 0: 74%|███████▍ | 216/291 [00:05<00:00, 118.31it/s] Loading 0: 82%|████████▏ | 238/291 [00:05<00:00, 138.15it/s] Loading 0: 89%|████████▊ | 258/291 [00:05<00:00, 149.22it/s] Loading 0: 96%|█████████▌| 278/291 [00:06<00:00, 103.29it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-halu-8b-llama-4766-v5-mkmlizer: quantized model in 16.765s
hastagaras-halu-8b-llama-4766-v5-mkmlizer: Processed model Hastagaras/HALU-8B-LLAMA3-BRSLURP in 47.996s
hastagaras-halu-8b-llama-4766-v5-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-8b-llama-4766-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-8b-llama-4766-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-8b-llama-4766-v5
hastagaras-halu-8b-llama-4766-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-4766-v5/special_tokens_map.json
hastagaras-halu-8b-llama-4766-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-4766-v5/config.json
hastagaras-halu-8b-llama-4766-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-4766-v5/tokenizer_config.json
hastagaras-halu-8b-llama-4766-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-4766-v5/tokenizer.json
hastagaras-halu-8b-llama-4766-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-8b-llama-4766-v5/flywheel_model.0.safetensors
hastagaras-halu-8b-llama-4766-v5-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-8b-llama-4766-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-4766-v5-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-4766-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-4766-v5-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-4766-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-4766-v5-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-4766-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-4766-v5-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-halu-8b-llama-4766-v5-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-halu-8b-llama-4766-v5-mkmlizer: Saving duration: 0.217s
hastagaras-halu-8b-llama-4766-v5-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.991s
hastagaras-halu-8b-llama-4766-v5-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-8b-llama-4766-v5-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-8b-llama-4766-v5-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-8b-llama-4766-v5_reward
hastagaras-halu-8b-llama-4766-v5-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-4766-v5_reward/config.json
hastagaras-halu-8b-llama-4766-v5-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-4766-v5_reward/special_tokens_map.json
hastagaras-halu-8b-llama-4766-v5-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-4766-v5_reward/tokenizer_config.json
hastagaras-halu-8b-llama-4766-v5-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-halu-8b-llama-4766-v5_reward/merges.txt
hastagaras-halu-8b-llama-4766-v5-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-4766-v5_reward/vocab.json
hastagaras-halu-8b-llama-4766-v5-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-4766-v5_reward/tokenizer.json
hastagaras-halu-8b-llama-4766-v5-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-halu-8b-llama-4766-v5_reward/reward.tensors
Job hastagaras-halu-8b-llama-4766-v5-mkmlizer completed after 72.73s with status: succeeded
Stopping job with name hastagaras-halu-8b-llama-4766-v5-mkmlizer
Pipeline stage MKMLizer completed in 76.63s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-8b-llama-4766-v5
Waiting for inference service hastagaras-halu-8b-llama-4766-v5 to be ready
Inference service hastagaras-halu-8b-llama-4766-v5 ready after 90.42561769485474s
Pipeline stage ISVCDeployer completed in 97.85s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.197374105453491s
Received healthy response to inference request in 1.377171516418457s
Received healthy response to inference request in 1.3300087451934814s
Received healthy response to inference request in 1.286055088043213s
Received healthy response to inference request in 1.3554093837738037s
5 requests
0 failed requests
5th percentile: 1.2948458194732666
10th percentile: 1.3036365509033203
20th percentile: 1.3212180137634277
30th percentile: 1.3350888729095458
40th percentile: 1.3452491283416748
50th percentile: 1.3554093837738037
60th percentile: 1.364114236831665
70th percentile: 1.3728190898895263
80th percentile: 1.541212034225464
90th percentile: 1.8692930698394776
95th percentile: 2.033333587646484
99th percentile: 2.16456600189209
mean time: 1.5092037677764893
Pipeline stage StressChecker completed in 8.17s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
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_4766_v5 status is now deployed due to DeploymentManager action
hastagaras-halu-8b-llama_4766_v5 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics