submission_id: hastagaras-halu-8b-llama_2564_v9
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: 2024-05-26T05:23:57+00:00
model_name: morebattleplease
model_eval_status: success
model_group: Hastagaras/Halu-8B-Llama
num_battles: 9693
num_wins: 5474
celo_rating: 1215.35
safety_score: 0.98
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: morebattleplease
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: 2024-05-25
win_ratio: 0.56473743938925
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-halu-8b-llama-2564-v9-mkmlizer
Waiting for job on hastagaras-halu-8b-llama-2564-v9-mkmlizer to finish
hastagaras-halu-8b-llama-2564-v9-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-8b-llama-2564-v9-mkmlizer: ║ _____ __ __ ║
hastagaras-halu-8b-llama-2564-v9-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-halu-8b-llama-2564-v9-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-halu-8b-llama-2564-v9-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-halu-8b-llama-2564-v9-mkmlizer: ║ /___/ ║
hastagaras-halu-8b-llama-2564-v9-mkmlizer: ║ ║
hastagaras-halu-8b-llama-2564-v9-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-halu-8b-llama-2564-v9-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-halu-8b-llama-2564-v9-mkmlizer: ║ https://mk1.ai ║
hastagaras-halu-8b-llama-2564-v9-mkmlizer: ║ ║
hastagaras-halu-8b-llama-2564-v9-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-halu-8b-llama-2564-v9-mkmlizer: ║ belonging to: ║
hastagaras-halu-8b-llama-2564-v9-mkmlizer: ║ ║
hastagaras-halu-8b-llama-2564-v9-mkmlizer: ║ Chai Research Corp. ║
hastagaras-halu-8b-llama-2564-v9-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-halu-8b-llama-2564-v9-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-halu-8b-llama-2564-v9-mkmlizer: ║ ║
hastagaras-halu-8b-llama-2564-v9-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-8b-llama-2564-v9-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-2564-v9-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-halu-8b-llama-2564-v9-mkmlizer: Downloaded to shared memory in 16.297s
hastagaras-halu-8b-llama-2564-v9-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-8b-llama-2564-v9-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-8b-llama-2564-v9-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 127.19it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 143.49it/s] Loading 0: 16%|█▋ | 48/291 [00:00<00:01, 153.38it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 157.21it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 83.93it/s] Loading 0: 33%|███▎ | 95/291 [00:00<00:02, 90.74it/s] Loading 0: 38%|███▊ | 112/291 [00:01<00:01, 108.31it/s] Loading 0: 45%|████▍ | 130/291 [00:01<00:01, 122.61it/s] Loading 0: 51%|█████ | 148/291 [00:01<00:01, 133.37it/s] Loading 0: 57%|█████▋ | 166/291 [00:01<00:00, 141.24it/s] Loading 0: 63%|██████▎ | 184/291 [00:01<00:00, 150.13it/s] Loading 0: 69%|██████▊ | 200/291 [00:01<00:01, 90.06it/s] Loading 0: 74%|███████▍ | 215/291 [00:01<00:00, 100.31it/s] Loading 0: 79%|███████▉ | 230/291 [00:02<00:00, 110.10it/s] Loading 0: 85%|████████▌ | 248/291 [00:02<00:00, 123.24it/s] Loading 0: 91%|█████████▏| 266/291 [00:02<00:00, 133.67it/s] Loading 0: 98%|█████████▊| 284/291 [00:02<00:00, 145.02it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-halu-8b-llama-2564-v9-mkmlizer: quantized model in 22.766s
hastagaras-halu-8b-llama-2564-v9-mkmlizer: Processed model Hastagaras/Halu-8B-Llama3-v0.3 in 41.672s
hastagaras-halu-8b-llama-2564-v9-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-8b-llama-2564-v9-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-8b-llama-2564-v9-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v9
hastagaras-halu-8b-llama-2564-v9-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v9/config.json
hastagaras-halu-8b-llama-2564-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v9/tokenizer.json
hastagaras-halu-8b-llama-2564-v9-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v9/special_tokens_map.json
hastagaras-halu-8b-llama-2564-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v9/tokenizer_config.json
hastagaras-halu-8b-llama-2564-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v9/flywheel_model.0.safetensors
hastagaras-halu-8b-llama-2564-v9-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-8b-llama-2564-v9-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-2564-v9-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-2564-v9-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-2564-v9-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-2564-v9-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-2564-v9-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-2564-v9-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-2564-v9-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-halu-8b-llama-2564-v9-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-halu-8b-llama-2564-v9-mkmlizer: Saving duration: 0.409s
hastagaras-halu-8b-llama-2564-v9-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.707s
hastagaras-halu-8b-llama-2564-v9-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-8b-llama-2564-v9-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-8b-llama-2564-v9-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v9_reward
hastagaras-halu-8b-llama-2564-v9-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v9_reward/tokenizer_config.json
hastagaras-halu-8b-llama-2564-v9-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v9_reward/special_tokens_map.json
hastagaras-halu-8b-llama-2564-v9-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v9_reward/config.json
hastagaras-halu-8b-llama-2564-v9-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v9_reward/vocab.json
hastagaras-halu-8b-llama-2564-v9-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v9_reward/merges.txt
hastagaras-halu-8b-llama-2564-v9-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v9_reward/tokenizer.json
hastagaras-halu-8b-llama-2564-v9-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v9_reward/reward.tensors
Job hastagaras-halu-8b-llama-2564-v9-mkmlizer completed after 62.87s with status: succeeded
Stopping job with name hastagaras-halu-8b-llama-2564-v9-mkmlizer
Pipeline stage MKMLizer completed in 68.55s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-8b-llama-2564-v9
Waiting for inference service hastagaras-halu-8b-llama-2564-v9 to be ready
Inference service hastagaras-halu-8b-llama-2564-v9 ready after 50.240256786346436s
Pipeline stage ISVCDeployer completed in 58.12s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2290492057800293s
Received healthy response to inference request in 1.3912122249603271s
Received healthy response to inference request in 1.3776288032531738s
Received healthy response to inference request in 1.3257389068603516s
Received healthy response to inference request in 1.2846004962921143s
5 requests
0 failed requests
5th percentile: 1.2928281784057618
10th percentile: 1.3010558605194091
20th percentile: 1.317511224746704
30th percentile: 1.336116886138916
40th percentile: 1.356872844696045
50th percentile: 1.3776288032531738
60th percentile: 1.3830621719360352
70th percentile: 1.3884955406188966
80th percentile: 1.5587796211242677
90th percentile: 1.8939144134521486
95th percentile: 2.0614818096160885
99th percentile: 2.195535726547241
mean time: 1.5216459274291991
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 0.04s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-halu-8b-llama_2564_v9 status is now deployed due to DeploymentManager action
hastagaras-halu-8b-llama_2564_v9 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics