submission_id: hastagaras-halu-8b-llam_2564_v11
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Halu-8B-Llama3-v0.3
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: 2024-06-02T02:23:14+00:00
model_name: propriety-test
model_eval_status: success
model_group: Hastagaras/Halu-8B-Llama
num_battles: 7617
num_wins: 4125
celo_rating: 1212.3
safety_score: 0.96
propriety_score: 0.7239583333333334
propriety_total_count: 192.0
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-v0.3
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-01
win_ratio: 0.5415517920441119
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-halu-8b-llam-2564-v11-mkmlizer
Waiting for job on hastagaras-halu-8b-llam-2564-v11-mkmlizer to finish
Stopping job with name hastagaras-halu-8b-llam-2564-v11-mkmlizer
%s, retrying in %s seconds...
Starting job with name hastagaras-halu-8b-llam-2564-v11-mkmlizer
Waiting for job on hastagaras-halu-8b-llam-2564-v11-mkmlizer to finish
hastagaras-halu-8b-llam-2564-v11-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-8b-llam-2564-v11-mkmlizer: ║ _____ __ __ ║
hastagaras-halu-8b-llam-2564-v11-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-halu-8b-llam-2564-v11-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-halu-8b-llam-2564-v11-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-halu-8b-llam-2564-v11-mkmlizer: ║ /___/ ║
hastagaras-halu-8b-llam-2564-v11-mkmlizer: ║ ║
hastagaras-halu-8b-llam-2564-v11-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-halu-8b-llam-2564-v11-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-halu-8b-llam-2564-v11-mkmlizer: ║ https://mk1.ai ║
hastagaras-halu-8b-llam-2564-v11-mkmlizer: ║ ║
hastagaras-halu-8b-llam-2564-v11-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-halu-8b-llam-2564-v11-mkmlizer: ║ belonging to: ║
hastagaras-halu-8b-llam-2564-v11-mkmlizer: ║ ║
hastagaras-halu-8b-llam-2564-v11-mkmlizer: ║ Chai Research Corp. ║
hastagaras-halu-8b-llam-2564-v11-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-halu-8b-llam-2564-v11-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-halu-8b-llam-2564-v11-mkmlizer: ║ ║
hastagaras-halu-8b-llam-2564-v11-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-8b-llam-2564-v11-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-llam-2564-v11-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-halu-8b-llam-2564-v11-mkmlizer: Downloaded to shared memory in 35.538s
hastagaras-halu-8b-llam-2564-v11-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-8b-llam-2564-v11-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-8b-llam-2564-v11-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 120.11it/s] Loading 0: 10%|█ | 30/291 [00:00<00:01, 147.02it/s] Loading 0: 15%|█▌ | 45/291 [00:00<00:01, 147.60it/s] Loading 0: 21%|██ | 60/291 [00:00<00:01, 147.59it/s] Loading 0: 26%|██▋ | 77/291 [00:00<00:01, 147.98it/s] Loading 0: 32%|███▏ | 92/291 [00:00<00:02, 79.22it/s] Loading 0: 36%|███▌ | 104/291 [00:00<00:02, 87.30it/s] Loading 0: 42%|████▏ | 122/291 [00:01<00:01, 104.38it/s] Loading 0: 48%|████▊ | 140/291 [00:01<00:01, 118.28it/s] Loading 0: 54%|█████▍ | 158/291 [00:01<00:01, 129.20it/s] Loading 0: 62%|██████▏ | 179/291 [00:01<00:00, 145.63it/s] Loading 0: 67%|██████▋ | 195/291 [00:01<00:01, 85.39it/s] Loading 0: 73%|███████▎ | 212/291 [00:01<00:00, 98.65it/s] Loading 0: 79%|███████▉ | 230/291 [00:02<00:00, 112.54it/s] Loading 0: 85%|████████▌ | 248/291 [00:02<00:00, 124.70it/s] Loading 0: 91%|█████████▏| 266/291 [00:02<00:00, 134.14it/s] Loading 0: 98%|█████████▊| 284/291 [00:02<00:00, 144.32it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-halu-8b-llam-2564-v11-mkmlizer: quantized model in 23.043s
hastagaras-halu-8b-llam-2564-v11-mkmlizer: Processed model Hastagaras/Halu-8B-Llama3-v0.3 in 61.225s
hastagaras-halu-8b-llam-2564-v11-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-8b-llam-2564-v11-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-8b-llam-2564-v11-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-8b-llam-2564-v11
hastagaras-halu-8b-llam-2564-v11-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llam-2564-v11/config.json
hastagaras-halu-8b-llam-2564-v11-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-8b-llam-2564-v11/special_tokens_map.json
hastagaras-halu-8b-llam-2564-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llam-2564-v11/tokenizer_config.json
hastagaras-halu-8b-llam-2564-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-8b-llam-2564-v11/tokenizer.json
hastagaras-halu-8b-llam-2564-v11-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-8b-llam-2564-v11/flywheel_model.0.safetensors
hastagaras-halu-8b-llam-2564-v11-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-8b-llam-2564-v11-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-llam-2564-v11-mkmlizer: warnings.warn(
hastagaras-halu-8b-llam-2564-v11-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-llam-2564-v11-mkmlizer: warnings.warn(
hastagaras-halu-8b-llam-2564-v11-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-llam-2564-v11-mkmlizer: warnings.warn(
hastagaras-halu-8b-llam-2564-v11-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-llam-2564-v11-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-halu-8b-llam-2564-v11-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-halu-8b-llam-2564-v11-mkmlizer: Saving duration: 0.460s
hastagaras-halu-8b-llam-2564-v11-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.433s
hastagaras-halu-8b-llam-2564-v11-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-8b-llam-2564-v11-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-8b-llam-2564-v11-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-8b-llam-2564-v11_reward
hastagaras-halu-8b-llam-2564-v11-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-halu-8b-llam-2564-v11_reward/special_tokens_map.json
hastagaras-halu-8b-llam-2564-v11-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-halu-8b-llam-2564-v11_reward/tokenizer_config.json
hastagaras-halu-8b-llam-2564-v11-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-halu-8b-llam-2564-v11_reward/merges.txt
hastagaras-halu-8b-llam-2564-v11-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-halu-8b-llam-2564-v11_reward/vocab.json
hastagaras-halu-8b-llam-2564-v11-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-halu-8b-llam-2564-v11_reward/config.json
hastagaras-halu-8b-llam-2564-v11-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-halu-8b-llam-2564-v11_reward/tokenizer.json
Job hastagaras-halu-8b-llam-2564-v11-mkmlizer completed after 95.06s with status: succeeded
Stopping job with name hastagaras-halu-8b-llam-2564-v11-mkmlizer
Pipeline stage MKMLizer completed in 98.81s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-8b-llam-2564-v11
Waiting for inference service hastagaras-halu-8b-llam-2564-v11 to be ready
Inference service hastagaras-halu-8b-llam-2564-v11 ready after 40.251832008361816s
Pipeline stage ISVCDeployer completed in 47.46s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1650946140289307s
Received healthy response to inference request in 1.3382189273834229s
Received healthy response to inference request in 1.3258686065673828s
Received healthy response to inference request in 1.2948088645935059s
Received healthy response to inference request in 4.005577564239502s
5 requests
0 failed requests
5th percentile: 1.3010208129882812
10th percentile: 1.3072327613830566
20th percentile: 1.3196566581726075
30th percentile: 1.3283386707305909
40th percentile: 1.3332787990570067
50th percentile: 1.3382189273834229
60th percentile: 1.6689692020416258
70th percentile: 1.999719476699829
80th percentile: 2.5331912040710454
90th percentile: 3.2693843841552734
95th percentile: 3.6374809741973873
99th percentile: 3.931958246231079
mean time: 2.025913715362549
Pipeline stage StressChecker completed in 11.47s
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-llam_2564_v11 status is now deployed due to DeploymentManager action
hastagaras-halu-8b-llam_2564_v11 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics