submission_id: hastagaras-halu-oas-8b-l_4311_v1
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Halu-OAS-8B-Llama3-TUNED
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.1, '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: 2024-05-28T04:42:49+00:00
model_name: test22
model_eval_status: success
model_group: Hastagaras/Halu-OAS-8B-L
num_battles: 15643
num_wins: 8460
celo_rating: 1196.52
safety_score: 0.83
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: test22
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Halu-OAS-8B-Llama3-TUNED
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-27
win_ratio: 0.5408169788403759
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-halu-oas-8b-l-4311-v1-mkmlizer
Waiting for job on hastagaras-halu-oas-8b-l-4311-v1-mkmlizer to finish
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: ║ /___/ ║
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: ║ ║
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: ║ ║
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: ║ belonging to: ║
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: ║ ║
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: ║ ║
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-oas-8b-l-4311-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-oas-8b-l-4311-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: Downloaded to shared memory in 32.633s
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 124.54it/s] Loading 0: 11%|█ | 32/291 [00:00<00:01, 148.46it/s] Loading 0: 17%|█▋ | 50/291 [00:00<00:01, 144.98it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 144.86it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 82.43it/s] Loading 0: 34%|███▎ | 98/291 [00:00<00:02, 95.95it/s] Loading 0: 39%|███▉ | 113/291 [00:01<00:01, 108.03it/s] Loading 0: 45%|████▌ | 131/291 [00:01<00:01, 123.79it/s] Loading 0: 51%|█████ | 149/291 [00:01<00:01, 135.34it/s] Loading 0: 57%|█████▋ | 167/291 [00:01<00:00, 143.71it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 96.55it/s] Loading 0: 69%|██████▊ | 200/291 [00:01<00:00, 97.40it/s] Loading 0: 74%|███████▍ | 215/291 [00:01<00:00, 107.67it/s] Loading 0: 80%|███████▉ | 232/291 [00:02<00:00, 121.53it/s] Loading 0: 85%|████████▌ | 248/291 [00:02<00:00, 128.17it/s] Loading 0: 91%|█████████▏| 266/291 [00:02<00:00, 139.60it/s] Loading 0: 98%|█████████▊| 284/291 [00:02<00:00, 149.81it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: quantized model in 22.908s
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-oas-8b-l-4311-v1
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-oas-8b-l-4311-v1/config.json
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-oas-8b-l-4311-v1/special_tokens_map.json
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-oas-8b-l-4311-v1/tokenizer_config.json
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-oas-8b-l-4311-v1/tokenizer.json
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-oas-8b-l-4311-v1/flywheel_model.0.safetensors
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-oas-8b-l-4311-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-oas-8b-l-4311-v1-mkmlizer: warnings.warn(
hastagaras-halu-oas-8b-l-4311-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-oas-8b-l-4311-v1-mkmlizer: warnings.warn(
hastagaras-halu-oas-8b-l-4311-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-oas-8b-l-4311-v1-mkmlizer: warnings.warn(
hastagaras-halu-oas-8b-l-4311-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-oas-8b-l-4311-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: Saving duration: 0.383s
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.449s
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-oas-8b-l-4311-v1_reward
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-halu-oas-8b-l-4311-v1_reward/special_tokens_map.json
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-halu-oas-8b-l-4311-v1_reward/config.json
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-halu-oas-8b-l-4311-v1_reward/tokenizer_config.json
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-halu-oas-8b-l-4311-v1_reward/tokenizer.json
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-halu-oas-8b-l-4311-v1_reward/merges.txt
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-halu-oas-8b-l-4311-v1_reward/vocab.json
hastagaras-halu-oas-8b-l-4311-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-halu-oas-8b-l-4311-v1_reward/reward.tensors
Job hastagaras-halu-oas-8b-l-4311-v1-mkmlizer completed after 83.2s with status: succeeded
Stopping job with name hastagaras-halu-oas-8b-l-4311-v1-mkmlizer
Pipeline stage MKMLizer completed in 86.88s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-oas-8b-l-4311-v1
Waiting for inference service hastagaras-halu-oas-8b-l-4311-v1 to be ready
Inference service hastagaras-halu-oas-8b-l-4311-v1 ready after 30.17270278930664s
Pipeline stage ISVCDeployer completed in 37.65s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.213672399520874s
Received healthy response to inference request in 1.3407764434814453s
Received healthy response to inference request in 1.3029475212097168s
Received healthy response to inference request in 1.2775425910949707s
Received healthy response to inference request in 1.2403724193572998s
5 requests
0 failed requests
5th percentile: 1.247806453704834
10th percentile: 1.2552404880523682
20th percentile: 1.2701085567474366
30th percentile: 1.28262357711792
40th percentile: 1.2927855491638183
50th percentile: 1.3029475212097168
60th percentile: 1.3180790901184083
70th percentile: 1.3332106590270996
80th percentile: 1.5153556346893313
90th percentile: 1.8645140171051027
95th percentile: 2.039093208312988
99th percentile: 2.1787565612792967
mean time: 1.4750622749328612
Pipeline stage StressChecker completed in 8.20s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-halu-oas-8b-l_4311_v1 status is now deployed due to DeploymentManager action
hastagaras-halu-oas-8b-l_4311_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics