submission_id: hastagaras-halu-8b-llama_3584_v1
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': 1.0, 'top_p': 0.95, 'min_p': 0.06, '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: 2024-06-01T06:58:07+00:00
model_name: forgot-the-4
model_eval_status: success
model_group: Hastagaras/HALU-8B-LLAMA
num_battles: 10926
num_wins: 5832
celo_rating: 1206.22
safety_score: 0.87
propriety_score: 1.0
propriety_total_count: 1.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: forgot-the-4
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: 2024-05-31
win_ratio: 0.5337726523887973
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-halu-8b-llama-3584-v1-mkmlizer
Waiting for job on hastagaras-halu-8b-llama-3584-v1-mkmlizer to finish
hastagaras-halu-8b-llama-3584-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-8b-llama-3584-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-halu-8b-llama-3584-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-halu-8b-llama-3584-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-halu-8b-llama-3584-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-halu-8b-llama-3584-v1-mkmlizer: ║ /___/ ║
hastagaras-halu-8b-llama-3584-v1-mkmlizer: ║ ║
hastagaras-halu-8b-llama-3584-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-halu-8b-llama-3584-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-halu-8b-llama-3584-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-halu-8b-llama-3584-v1-mkmlizer: ║ ║
hastagaras-halu-8b-llama-3584-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-halu-8b-llama-3584-v1-mkmlizer: ║ belonging to: ║
hastagaras-halu-8b-llama-3584-v1-mkmlizer: ║ ║
hastagaras-halu-8b-llama-3584-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-halu-8b-llama-3584-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-halu-8b-llama-3584-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-halu-8b-llama-3584-v1-mkmlizer: ║ ║
hastagaras-halu-8b-llama-3584-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-8b-llama-3584-v1-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-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-halu-8b-llama-3584-v1-mkmlizer: Downloaded to shared memory in 29.834s
hastagaras-halu-8b-llama-3584-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-8b-llama-3584-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-8b-llama-3584-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:57, 2.27s/it] Loading 0: 5%|▌ | 15/291 [00:04<01:02, 4.38it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:22, 11.64it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:11, 20.94it/s] Loading 0: 22%|██▏ | 65/291 [00:05<00:08, 25.24it/s] Loading 0: 28%|██▊ | 81/291 [00:05<00:05, 36.20it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:04, 48.06it/s] Loading 0: 39%|███▉ | 114/291 [00:05<00:02, 64.13it/s] Loading 0: 45%|████▌ | 132/291 [00:05<00:01, 81.33it/s] Loading 0: 52%|█████▏ | 150/291 [00:05<00:01, 97.59it/s] Loading 0: 57%|█████▋ | 166/291 [00:06<00:01, 76.05it/s] Loading 0: 63%|██████▎ | 184/291 [00:06<00:01, 92.11it/s] Loading 0: 69%|██████▉ | 202/291 [00:06<00:00, 107.28it/s] Loading 0: 76%|███████▌ | 220/291 [00:06<00:00, 120.25it/s] Loading 0: 82%|████████▏ | 238/291 [00:06<00:00, 130.92it/s] Loading 0: 88%|████████▊ | 256/291 [00:06<00:00, 140.22it/s] Loading 0: 93%|█████████▎| 272/291 [00:06<00:00, 89.64it/s] Loading 0: 99%|█████████▉| 288/291 [00:07<00:00, 102.03it/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-v1-mkmlizer: quantized model in 23.486s
hastagaras-halu-8b-llama-3584-v1-mkmlizer: Processed model Hastagaras/HALU-8B-LLAMA3-EXP-4 in 55.836s
hastagaras-halu-8b-llama-3584-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-8b-llama-3584-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-8b-llama-3584-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3584-v1
hastagaras-halu-8b-llama-3584-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3584-v1/config.json
hastagaras-halu-8b-llama-3584-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3584-v1/tokenizer_config.json
hastagaras-halu-8b-llama-3584-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3584-v1/special_tokens_map.json
hastagaras-halu-8b-llama-3584-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3584-v1/tokenizer.json
hastagaras-halu-8b-llama-3584-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3584-v1/flywheel_model.0.safetensors
hastagaras-halu-8b-llama-3584-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-8b-llama-3584-v1-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-v1-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-3584-v1-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-v1-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-3584-v1-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-v1-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-3584-v1-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-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-halu-8b-llama-3584-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-halu-8b-llama-3584-v1-mkmlizer: Saving duration: 0.396s
hastagaras-halu-8b-llama-3584-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.382s
hastagaras-halu-8b-llama-3584-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-8b-llama-3584-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-8b-llama-3584-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-8b-llama-3584-v1_reward
hastagaras-halu-8b-llama-3584-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3584-v1_reward/special_tokens_map.json
hastagaras-halu-8b-llama-3584-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3584-v1_reward/config.json
hastagaras-halu-8b-llama-3584-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3584-v1_reward/vocab.json
hastagaras-halu-8b-llama-3584-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-halu-8b-llama-3584-v1_reward/merges.txt
hastagaras-halu-8b-llama-3584-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3584-v1_reward/tokenizer_config.json
hastagaras-halu-8b-llama-3584-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3584-v1_reward/tokenizer.json
hastagaras-halu-8b-llama-3584-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-halu-8b-llama-3584-v1_reward/reward.tensors
Job hastagaras-halu-8b-llama-3584-v1-mkmlizer completed after 82.93s with status: succeeded
Stopping job with name hastagaras-halu-8b-llama-3584-v1-mkmlizer
Pipeline stage MKMLizer completed in 86.64s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-8b-llama-3584-v1
Waiting for inference service hastagaras-halu-8b-llama-3584-v1 to be ready
Inference service hastagaras-halu-8b-llama-3584-v1 ready after 60.502034187316895s
Pipeline stage ISVCDeployer completed in 67.63s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.245955228805542s
Received healthy response to inference request in 1.3664674758911133s
Received healthy response to inference request in 1.333484411239624s
Received healthy response to inference request in 1.332892656326294s
Received healthy response to inference request in 1.2490808963775635s
5 requests
0 failed requests
5th percentile: 1.2658432483673097
10th percentile: 1.2826056003570556
20th percentile: 1.3161303043365478
30th percentile: 1.33301100730896
40th percentile: 1.333247709274292
50th percentile: 1.333484411239624
60th percentile: 1.3466776371002198
70th percentile: 1.3598708629608154
80th percentile: 1.5423650264739992
90th percentile: 1.8941601276397706
95th percentile: 2.070057678222656
99th percentile: 2.2107757186889647
mean time: 1.5055761337280273
Pipeline stage StressChecker completed in 8.06s
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_v1 status is now deployed due to DeploymentManager action
hastagaras-halu-8b-llama_3584_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics