submission_id: hastagaras-halu-8b-llama_3029_v2
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Halu-8B-Llama3-v0.4
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.05, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, '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: 2024-05-25T01:59:44+00:00
model_name: wlewelwel
model_eval_status: success
model_group: Hastagaras/Halu-8B-Llama
num_battles: 13266
num_wins: 7262
celo_rating: 1203.56
safety_score: 0.97
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: wlewelwel
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Halu-8B-Llama3-v0.4
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-24
win_ratio: 0.547414442936831
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-halu-8b-llama-3029-v2-mkmlizer
Waiting for job on hastagaras-halu-8b-llama-3029-v2-mkmlizer to finish
hastagaras-halu-8b-llama-3029-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-8b-llama-3029-v2-mkmlizer: ║ _____ __ __ ║
hastagaras-halu-8b-llama-3029-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-halu-8b-llama-3029-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-halu-8b-llama-3029-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-halu-8b-llama-3029-v2-mkmlizer: ║ /___/ ║
hastagaras-halu-8b-llama-3029-v2-mkmlizer: ║ ║
hastagaras-halu-8b-llama-3029-v2-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-halu-8b-llama-3029-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-halu-8b-llama-3029-v2-mkmlizer: ║ https://mk1.ai ║
hastagaras-halu-8b-llama-3029-v2-mkmlizer: ║ ║
hastagaras-halu-8b-llama-3029-v2-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-halu-8b-llama-3029-v2-mkmlizer: ║ belonging to: ║
hastagaras-halu-8b-llama-3029-v2-mkmlizer: ║ ║
hastagaras-halu-8b-llama-3029-v2-mkmlizer: ║ Chai Research Corp. ║
hastagaras-halu-8b-llama-3029-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-halu-8b-llama-3029-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-halu-8b-llama-3029-v2-mkmlizer: ║ ║
hastagaras-halu-8b-llama-3029-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-8b-llama-3029-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-llama-3029-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-halu-8b-llama-3029-v2-mkmlizer: Downloaded to shared memory in 16.846s
hastagaras-halu-8b-llama-3029-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-8b-llama-3029-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-8b-llama-3029-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 128.70it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 152.44it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:01, 161.29it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 165.36it/s] Loading 0: 29%|██▉ | 84/291 [00:00<00:02, 87.12it/s] Loading 0: 35%|███▌ | 102/291 [00:00<00:01, 105.56it/s] Loading 0: 41%|████ | 120/291 [00:00<00:01, 121.37it/s] Loading 0: 47%|████▋ | 138/291 [00:01<00:01, 134.48it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:00, 143.97it/s] Loading 0: 59%|█████▉ | 173/291 [00:01<00:00, 148.03it/s] Loading 0: 65%|██████▌ | 190/291 [00:01<00:01, 95.85it/s] Loading 0: 71%|███████ | 207/291 [00:01<00:00, 109.42it/s] Loading 0: 77%|███████▋ | 225/291 [00:01<00:00, 124.05it/s] Loading 0: 84%|████████▎ | 243/291 [00:01<00:00, 136.83it/s] Loading 0: 90%|████████▉ | 261/291 [00:02<00:00, 147.01it/s] Loading 0: 96%|█████████▌| 279/291 [00:02<00:00, 154.38it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-halu-8b-llama-3029-v2-mkmlizer: quantized model in 22.882s
hastagaras-halu-8b-llama-3029-v2-mkmlizer: Processed model Hastagaras/Halu-8B-Llama3-v0.4 in 42.203s
hastagaras-halu-8b-llama-3029-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-8b-llama-3029-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-8b-llama-3029-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3029-v2
hastagaras-halu-8b-llama-3029-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3029-v2/special_tokens_map.json
hastagaras-halu-8b-llama-3029-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3029-v2/config.json
hastagaras-halu-8b-llama-3029-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3029-v2/tokenizer_config.json
hastagaras-halu-8b-llama-3029-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3029-v2/tokenizer.json
hastagaras-halu-8b-llama-3029-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3029-v2/flywheel_model.0.safetensors
hastagaras-halu-8b-llama-3029-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-8b-llama-3029-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-llama-3029-v2-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-3029-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-llama-3029-v2-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-3029-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-llama-3029-v2-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-3029-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-llama-3029-v2-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-halu-8b-llama-3029-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-halu-8b-llama-3029-v2-mkmlizer: Saving duration: 0.398s
hastagaras-halu-8b-llama-3029-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.949s
hastagaras-halu-8b-llama-3029-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-8b-llama-3029-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-8b-llama-3029-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-8b-llama-3029-v2_reward
hastagaras-halu-8b-llama-3029-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3029-v2_reward/config.json
hastagaras-halu-8b-llama-3029-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3029-v2_reward/special_tokens_map.json
hastagaras-halu-8b-llama-3029-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3029-v2_reward/tokenizer_config.json
hastagaras-halu-8b-llama-3029-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-halu-8b-llama-3029-v2_reward/merges.txt
hastagaras-halu-8b-llama-3029-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3029-v2_reward/vocab.json
hastagaras-halu-8b-llama-3029-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3029-v2_reward/tokenizer.json
hastagaras-halu-8b-llama-3029-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-halu-8b-llama-3029-v2_reward/reward.tensors
Job hastagaras-halu-8b-llama-3029-v2-mkmlizer completed after 62.67s with status: succeeded
Stopping job with name hastagaras-halu-8b-llama-3029-v2-mkmlizer
Pipeline stage MKMLizer completed in 67.06s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-8b-llama-3029-v2
Waiting for inference service hastagaras-halu-8b-llama-3029-v2 to be ready
Inference service hastagaras-halu-8b-llama-3029-v2 ready after 30.195447206497192s
Pipeline stage ISVCDeployer completed in 39.04s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0740604400634766s
Received healthy response to inference request in 1.3352441787719727s
Received healthy response to inference request in 1.331923007965088s
Received healthy response to inference request in 1.3083302974700928s
Received healthy response to inference request in 1.2491800785064697s
5 requests
0 failed requests
5th percentile: 1.2610101222991943
10th percentile: 1.2728401660919189
20th percentile: 1.2965002536773682
30th percentile: 1.3130488395690918
40th percentile: 1.3224859237670898
50th percentile: 1.331923007965088
60th percentile: 1.3332514762878418
70th percentile: 1.3345799446105957
80th percentile: 1.4830074310302737
90th percentile: 1.778533935546875
95th percentile: 1.9262971878051756
99th percentile: 2.0445077896118162
mean time: 1.45974760055542
Pipeline stage StressChecker completed in 7.95s
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-llama_3029_v2 status is now deployed due to DeploymentManager action
hastagaras-halu-8b-llama_3029_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics