submission_id: hastagaras-halu-8b-llam_2564_v12
developer_uid: Jellywibble
status: inactive
model_repo: Hastagaras/Halu-8B-Llama3-v0.3
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.05, 'top_p': 0.95, '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: 2024-06-03T14:41:59+00:00
model_name: HWEHWHEHW
model_eval_status: success
model_group: Hastagaras/Halu-8B-Llama
num_battles: 27611
num_wins: 14689
celo_rating: 1209.56
safety_score: 0.95
propriety_score: 0.6447761194029851
propriety_total_count: 670.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: HWEHWHEHW
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: 2024-06-03
win_ratio: 0.5319981166926225
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-halu-8b-llam-2564-v12-mkmlizer
Waiting for job on hastagaras-halu-8b-llam-2564-v12-mkmlizer to finish
hastagaras-halu-8b-llam-2564-v12-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-8b-llam-2564-v12-mkmlizer: ║ _____ __ __ ║
hastagaras-halu-8b-llam-2564-v12-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-halu-8b-llam-2564-v12-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-halu-8b-llam-2564-v12-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-halu-8b-llam-2564-v12-mkmlizer: ║ /___/ ║
hastagaras-halu-8b-llam-2564-v12-mkmlizer: ║ ║
hastagaras-halu-8b-llam-2564-v12-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-halu-8b-llam-2564-v12-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-halu-8b-llam-2564-v12-mkmlizer: ║ https://mk1.ai ║
hastagaras-halu-8b-llam-2564-v12-mkmlizer: ║ ║
hastagaras-halu-8b-llam-2564-v12-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-halu-8b-llam-2564-v12-mkmlizer: ║ belonging to: ║
hastagaras-halu-8b-llam-2564-v12-mkmlizer: ║ ║
hastagaras-halu-8b-llam-2564-v12-mkmlizer: ║ Chai Research Corp. ║
hastagaras-halu-8b-llam-2564-v12-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-halu-8b-llam-2564-v12-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-halu-8b-llam-2564-v12-mkmlizer: ║ ║
hastagaras-halu-8b-llam-2564-v12-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-8b-llam-2564-v12-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-v12-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-halu-8b-llam-2564-v12-mkmlizer: Downloaded to shared memory in 62.720s
hastagaras-halu-8b-llam-2564-v12-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-8b-llam-2564-v12-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-8b-llam-2564-v12-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:02, 108.82it/s] Loading 0: 8%|▊ | 23/291 [00:00<00:02, 103.07it/s] Loading 0: 13%|█▎ | 39/291 [00:00<00:02, 123.02it/s] Loading 0: 18%|█▊ | 52/291 [00:00<00:02, 118.51it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 123.43it/s] Loading 0: 27%|██▋ | 79/291 [00:00<00:01, 119.67it/s] Loading 0: 32%|███▏ | 92/291 [00:01<00:03, 65.97it/s] Loading 0: 35%|███▌ | 103/291 [00:01<00:02, 72.56it/s] Loading 0: 40%|███▉ | 116/291 [00:01<00:02, 83.98it/s] Loading 0: 45%|████▍ | 130/291 [00:01<00:01, 93.06it/s] Loading 0: 49%|████▉ | 144/291 [00:01<00:01, 103.00it/s] Loading 0: 54%|█████▍ | 157/291 [00:01<00:01, 106.40it/s] Loading 0: 58%|█████▊ | 170/291 [00:01<00:01, 112.13it/s] Loading 0: 63%|██████▎ | 182/291 [00:01<00:00, 113.21it/s] Loading 0: 67%|██████▋ | 194/291 [00:02<00:01, 65.81it/s] Loading 0: 72%|███████▏ | 210/291 [00:02<00:00, 81.64it/s] Loading 0: 76%|███████▌ | 221/291 [00:02<00:00, 84.87it/s] Loading 0: 81%|████████▏ | 237/291 [00:02<00:00, 99.48it/s] Loading 0: 86%|████████▌ | 249/291 [00:02<00:00, 101.39it/s] Loading 0: 91%|█████████ | 264/291 [00:02<00:00, 112.42it/s] Loading 0: 95%|█████████▌| 277/291 [00:02<00:00, 112.67it/s] Loading 0: 100%|█████████▉| 290/291 [00:08<00:00, 7.59it/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-v12-mkmlizer: quantized model in 23.781s
hastagaras-halu-8b-llam-2564-v12-mkmlizer: Processed model Hastagaras/Halu-8B-Llama3-v0.3 in 89.055s
hastagaras-halu-8b-llam-2564-v12-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-8b-llam-2564-v12-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-8b-llam-2564-v12-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-8b-llam-2564-v12
hastagaras-halu-8b-llam-2564-v12-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llam-2564-v12/config.json
hastagaras-halu-8b-llam-2564-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llam-2564-v12/tokenizer_config.json
hastagaras-halu-8b-llam-2564-v12-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-8b-llam-2564-v12/special_tokens_map.json
hastagaras-halu-8b-llam-2564-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-8b-llam-2564-v12/tokenizer.json
hastagaras-halu-8b-llam-2564-v12-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-8b-llam-2564-v12/flywheel_model.0.safetensors
hastagaras-halu-8b-llam-2564-v12-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-8b-llam-2564-v12-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-v12-mkmlizer: warnings.warn(
hastagaras-halu-8b-llam-2564-v12-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-v12-mkmlizer: warnings.warn(
hastagaras-halu-8b-llam-2564-v12-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-v12-mkmlizer: warnings.warn(
hastagaras-halu-8b-llam-2564-v12-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-v12-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-halu-8b-llam-2564-v12-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-halu-8b-llam-2564-v12-mkmlizer: Saving duration: 0.393s
hastagaras-halu-8b-llam-2564-v12-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 146.291s
hastagaras-halu-8b-llam-2564-v12-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-halu-8b-llam-2564-v12_reward/reward.tensors
Job hastagaras-halu-8b-llam-2564-v12-mkmlizer completed after 276.97s with status: succeeded
Stopping job with name hastagaras-halu-8b-llam-2564-v12-mkmlizer
Pipeline stage MKMLizer completed in 280.49s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-8b-llam-2564-v12
Waiting for inference service hastagaras-halu-8b-llam-2564-v12 to be ready
Inference service hastagaras-halu-8b-llam-2564-v12 ready after 40.23308849334717s
Pipeline stage ISVCDeployer completed in 47.15s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1385374069213867s
Received healthy response to inference request in 1.4153900146484375s
Received healthy response to inference request in 1.340559959411621s
Received healthy response to inference request in 1.328709602355957s
Received healthy response to inference request in 1.2878899574279785s
5 requests
0 failed requests
5th percentile: 1.2960538864135742
10th percentile: 1.30421781539917
20th percentile: 1.3205456733703613
30th percentile: 1.3310796737670898
40th percentile: 1.3358198165893556
50th percentile: 1.340559959411621
60th percentile: 1.3704919815063477
70th percentile: 1.4004240036010742
80th percentile: 1.5600194931030276
90th percentile: 1.849278450012207
95th percentile: 1.9939079284667967
99th percentile: 2.1096115112304688
mean time: 1.5022173881530763
Pipeline stage StressChecker completed in 8.13s
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-8b-llam_2564_v12 status is now deployed due to DeploymentManager action
hastagaras-halu-8b-llam_2564_v12 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics