submission_id: hastagaras-halu-8b-llama_3584_v2
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/HALU-8B-LLAMA3-EXP-4
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, '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: 2024-06-01T07:03:49+00:00
model_name: test
model_eval_status: success
model_group: Hastagaras/HALU-8B-LLAMA
num_battles: 10529
num_wins: 5708
celo_rating: 1210.94
safety_score: 0.88
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: test
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/HALU-8B-LLAMA3-EXP-4
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-01
win_ratio: 0.5421217589514674
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-halu-8b-llama-3584-v2-mkmlizer
Waiting for job on hastagaras-halu-8b-llama-3584-v2-mkmlizer to finish
hastagaras-halu-8b-llama-3584-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-8b-llama-3584-v2-mkmlizer: ║ _____ __ __ ║
hastagaras-halu-8b-llama-3584-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-halu-8b-llama-3584-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-halu-8b-llama-3584-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-halu-8b-llama-3584-v2-mkmlizer: ║ /___/ ║
hastagaras-halu-8b-llama-3584-v2-mkmlizer: ║ ║
hastagaras-halu-8b-llama-3584-v2-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-halu-8b-llama-3584-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-halu-8b-llama-3584-v2-mkmlizer: ║ https://mk1.ai ║
hastagaras-halu-8b-llama-3584-v2-mkmlizer: ║ ║
hastagaras-halu-8b-llama-3584-v2-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-halu-8b-llama-3584-v2-mkmlizer: ║ belonging to: ║
hastagaras-halu-8b-llama-3584-v2-mkmlizer: ║ ║
hastagaras-halu-8b-llama-3584-v2-mkmlizer: ║ Chai Research Corp. ║
hastagaras-halu-8b-llama-3584-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-halu-8b-llama-3584-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-halu-8b-llama-3584-v2-mkmlizer: ║ ║
hastagaras-halu-8b-llama-3584-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-8b-llama-3584-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-3584-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-halu-8b-llama-3584-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:46, 2.24s/it] Loading 0: 5%|▌ | 15/291 [00:04<01:01, 4.46it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:21, 11.85it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:11, 21.32it/s] Loading 0: 22%|██▏ | 65/291 [00:05<00:08, 25.75it/s] Loading 0: 28%|██▊ | 81/291 [00:05<00:05, 36.90it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:03, 48.86it/s] Loading 0: 39%|███▉ | 114/291 [00:05<00:02, 65.58it/s] Loading 0: 45%|████▌ | 132/291 [00:05<00:01, 82.89it/s] Loading 0: 52%|█████▏ | 150/291 [00:05<00:01, 99.66it/s] Loading 0: 57%|█████▋ | 166/291 [00:05<00:01, 77.36it/s] Loading 0: 63%|██████▎ | 184/291 [00:06<00:01, 93.79it/s] Loading 0: 69%|██████▉ | 202/291 [00:06<00:00, 109.22it/s] Loading 0: 76%|███████▌ | 220/291 [00:06<00:00, 123.26it/s] Loading 0: 82%|████████▏ | 238/291 [00:06<00:00, 135.04it/s] Loading 0: 88%|████████▊ | 256/291 [00:06<00:00, 144.57it/s] Loading 0: 94%|█████████▍| 273/291 [00:06<00:00, 94.81it/s] Loading 0: 99%|█████████▊| 287/291 [00:06<00:00, 103.06it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-halu-8b-llama-3584-v2-mkmlizer: quantized model in 22.972s
hastagaras-halu-8b-llama-3584-v2-mkmlizer: Processed model Hastagaras/HALU-8B-LLAMA3-EXP-4 in 42.607s
hastagaras-halu-8b-llama-3584-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-8b-llama-3584-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-8b-llama-3584-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3584-v2
hastagaras-halu-8b-llama-3584-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3584-v2/config.json
hastagaras-halu-8b-llama-3584-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3584-v2/special_tokens_map.json
hastagaras-halu-8b-llama-3584-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3584-v2/tokenizer_config.json
hastagaras-halu-8b-llama-3584-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3584-v2/tokenizer.json
hastagaras-halu-8b-llama-3584-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3584-v2/flywheel_model.0.safetensors
hastagaras-halu-8b-llama-3584-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-8b-llama-3584-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-3584-v2-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-3584-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-3584-v2-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-3584-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-3584-v2-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-3584-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-3584-v2-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-halu-8b-llama-3584-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-halu-8b-llama-3584-v2-mkmlizer: Saving duration: 0.392s
hastagaras-halu-8b-llama-3584-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.135s
hastagaras-halu-8b-llama-3584-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-8b-llama-3584-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-8b-llama-3584-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-8b-llama-3584-v2_reward
hastagaras-halu-8b-llama-3584-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3584-v2_reward/config.json
hastagaras-halu-8b-llama-3584-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3584-v2_reward/special_tokens_map.json
hastagaras-halu-8b-llama-3584-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3584-v2_reward/tokenizer_config.json
hastagaras-halu-8b-llama-3584-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-halu-8b-llama-3584-v2_reward/merges.txt
hastagaras-halu-8b-llama-3584-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3584-v2_reward/vocab.json
hastagaras-halu-8b-llama-3584-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3584-v2_reward/tokenizer.json
hastagaras-halu-8b-llama-3584-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-halu-8b-llama-3584-v2_reward/reward.tensors
Job hastagaras-halu-8b-llama-3584-v2-mkmlizer completed after 73.01s with status: succeeded
Stopping job with name hastagaras-halu-8b-llama-3584-v2-mkmlizer
Pipeline stage MKMLizer completed in 73.39s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-8b-llama-3584-v2
Waiting for inference service hastagaras-halu-8b-llama-3584-v2 to be ready
Inference service hastagaras-halu-8b-llama-3584-v2 ready after 40.1991491317749s
Pipeline stage ISVCDeployer completed in 45.79s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.166438579559326s
Received healthy response to inference request in 1.3444123268127441s
Received healthy response to inference request in 1.3243043422698975s
Received healthy response to inference request in 1.2830572128295898s
Received healthy response to inference request in 1.2690675258636475s
5 requests
0 failed requests
5th percentile: 1.271865463256836
10th percentile: 1.2746634006500244
20th percentile: 1.2802592754364013
30th percentile: 1.2913066387176513
40th percentile: 1.3078054904937744
50th percentile: 1.3243043422698975
60th percentile: 1.332347536087036
70th percentile: 1.3403907299041748
80th percentile: 1.5088175773620607
90th percentile: 1.8376280784606935
95th percentile: 2.0020333290100094
99th percentile: 2.1335575294494626
mean time: 1.477455997467041
Pipeline stage StressChecker completed in 8.02s
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_3584_v2 status is now deployed due to DeploymentManager action
hastagaras-halu-8b-llama_3584_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics