submission_id: arlineka-pharaoh-8b_v2
developer_uid: arlineka
status: inactive
model_repo: arlineka/pharaoh-8b
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '\\User'], '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: 2024-06-01T16:46:28+00:00
model_name: arlineka-pharaoh-8b_v1
model_eval_status: success
model_group: arlineka/pharaoh-8b
num_battles: 66109
num_wins: 35621
celo_rating: 1196.5
safety_score: 0.91
propriety_score: 0.6615589606928715
propriety_total_count: 1501.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030277632.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: arlineka-pharaoh-8b_v1
ineligible_reason: propriety_total_count < 5000
language_model: arlineka/pharaoh-8b
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-01
win_ratio: 0.5388222481054017
Resubmit model
Running pipeline stage MKMLizer
Starting job with name arlineka-pharaoh-8b-v2-mkmlizer
Waiting for job on arlineka-pharaoh-8b-v2-mkmlizer to finish
arlineka-pharaoh-8b-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
arlineka-pharaoh-8b-v2-mkmlizer: ║ _____ __ __ ║
arlineka-pharaoh-8b-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
arlineka-pharaoh-8b-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
arlineka-pharaoh-8b-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
arlineka-pharaoh-8b-v2-mkmlizer: ║ /___/ ║
arlineka-pharaoh-8b-v2-mkmlizer: ║ ║
arlineka-pharaoh-8b-v2-mkmlizer: ║ Version: 0.8.14 ║
arlineka-pharaoh-8b-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
arlineka-pharaoh-8b-v2-mkmlizer: ║ https://mk1.ai ║
arlineka-pharaoh-8b-v2-mkmlizer: ║ ║
arlineka-pharaoh-8b-v2-mkmlizer: ║ The license key for the current software has been verified as ║
arlineka-pharaoh-8b-v2-mkmlizer: ║ belonging to: ║
arlineka-pharaoh-8b-v2-mkmlizer: ║ ║
arlineka-pharaoh-8b-v2-mkmlizer: ║ Chai Research Corp. ║
arlineka-pharaoh-8b-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
arlineka-pharaoh-8b-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
arlineka-pharaoh-8b-v2-mkmlizer: ║ ║
arlineka-pharaoh-8b-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
arlineka-pharaoh-8b-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.
arlineka-pharaoh-8b-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
arlineka-pharaoh-8b-v2-mkmlizer: Downloaded to shared memory in 53.591s
arlineka-pharaoh-8b-v2-mkmlizer: quantizing model to /dev/shm/model_cache
arlineka-pharaoh-8b-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
arlineka-pharaoh-8b-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:02, 99.45it/s] Loading 0: 8%|▊ | 22/291 [00:00<00:02, 94.52it/s] Loading 0: 11%|█ | 32/291 [00:00<00:02, 92.81it/s] Loading 0: 15%|█▌ | 45/291 [00:00<00:02, 104.68it/s] Loading 0: 20%|█▉ | 58/291 [00:00<00:02, 106.50it/s] Loading 0: 24%|██▎ | 69/291 [00:00<00:02, 104.58it/s] Loading 0: 28%|██▊ | 81/291 [00:00<00:01, 108.35it/s] Loading 0: 32%|███▏ | 92/291 [00:01<00:03, 60.01it/s] Loading 0: 35%|███▌ | 102/291 [00:01<00:02, 66.79it/s] Loading 0: 38%|███▊ | 112/291 [00:01<00:02, 72.91it/s] Loading 0: 42%|████▏ | 122/291 [00:01<00:02, 78.87it/s] Loading 0: 47%|████▋ | 138/291 [00:01<00:01, 96.86it/s] Loading 0: 51%|█████ | 149/291 [00:01<00:01, 97.07it/s] Loading 0: 57%|█████▋ | 165/291 [00:01<00:01, 111.54it/s] Loading 0: 62%|██████▏ | 179/291 [00:01<00:00, 116.94it/s] Loading 0: 66%|██████▌ | 192/291 [00:02<00:01, 65.38it/s] Loading 0: 69%|██████▉ | 202/291 [00:02<00:01, 70.80it/s] Loading 0: 73%|███████▎ | 212/291 [00:02<00:01, 75.84it/s] Loading 0: 78%|███████▊ | 228/291 [00:02<00:00, 90.44it/s] Loading 0: 82%|████████▏ | 239/291 [00:02<00:00, 90.84it/s] Loading 0: 86%|████████▋ | 251/291 [00:02<00:00, 96.57it/s] Loading 0: 91%|█████████ | 264/291 [00:02<00:00, 104.86it/s] Loading 0: 95%|█████████▍| 276/291 [00:03<00:00, 104.64it/s] Loading 0: 99%|█████████▉| 288/291 [00:08<00:00, 6.97it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
arlineka-pharaoh-8b-v2-mkmlizer: quantized model in 23.927s
arlineka-pharaoh-8b-v2-mkmlizer: Processed model arlineka/pharaoh-8b in 80.107s
arlineka-pharaoh-8b-v2-mkmlizer: creating bucket guanaco-mkml-models
arlineka-pharaoh-8b-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
arlineka-pharaoh-8b-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/arlineka-pharaoh-8b-v2
arlineka-pharaoh-8b-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/arlineka-pharaoh-8b-v2/config.json
arlineka-pharaoh-8b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/arlineka-pharaoh-8b-v2/tokenizer_config.json
arlineka-pharaoh-8b-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/arlineka-pharaoh-8b-v2/special_tokens_map.json
arlineka-pharaoh-8b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/arlineka-pharaoh-8b-v2/tokenizer.json
arlineka-pharaoh-8b-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/arlineka-pharaoh-8b-v2/flywheel_model.0.safetensors
arlineka-pharaoh-8b-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
arlineka-pharaoh-8b-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.
arlineka-pharaoh-8b-v2-mkmlizer: warnings.warn(
arlineka-pharaoh-8b-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.
arlineka-pharaoh-8b-v2-mkmlizer: warnings.warn(
arlineka-pharaoh-8b-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.
arlineka-pharaoh-8b-v2-mkmlizer: warnings.warn(
arlineka-pharaoh-8b-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()
arlineka-pharaoh-8b-v2-mkmlizer: return self.fget.__get__(instance, owner)()
arlineka-pharaoh-8b-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
arlineka-pharaoh-8b-v2-mkmlizer: Saving duration: 0.432s
arlineka-pharaoh-8b-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 32.394s
arlineka-pharaoh-8b-v2-mkmlizer: creating bucket guanaco-reward-models
arlineka-pharaoh-8b-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
arlineka-pharaoh-8b-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/arlineka-pharaoh-8b-v2_reward
arlineka-pharaoh-8b-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/arlineka-pharaoh-8b-v2_reward/config.json
arlineka-pharaoh-8b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/arlineka-pharaoh-8b-v2_reward/tokenizer_config.json
arlineka-pharaoh-8b-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/arlineka-pharaoh-8b-v2_reward/merges.txt
arlineka-pharaoh-8b-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/arlineka-pharaoh-8b-v2_reward/special_tokens_map.json
arlineka-pharaoh-8b-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/arlineka-pharaoh-8b-v2_reward/vocab.json
arlineka-pharaoh-8b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/arlineka-pharaoh-8b-v2_reward/tokenizer.json
arlineka-pharaoh-8b-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/arlineka-pharaoh-8b-v2_reward/reward.tensors
Job arlineka-pharaoh-8b-v2-mkmlizer completed after 135.18s with status: succeeded
Stopping job with name arlineka-pharaoh-8b-v2-mkmlizer
Pipeline stage MKMLizer completed in 139.49s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service arlineka-pharaoh-8b-v2
Waiting for inference service arlineka-pharaoh-8b-v2 to be ready
Inference service arlineka-pharaoh-8b-v2 ready after 30.16343092918396s
Pipeline stage ISVCDeployer completed in 37.83s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.226290702819824s
Received healthy response to inference request in 1.3278822898864746s
Received healthy response to inference request in 1.3041200637817383s
Received healthy response to inference request in 1.2975785732269287s
Received healthy response to inference request in 1.3551816940307617s
5 requests
0 failed requests
5th percentile: 1.2988868713378907
10th percentile: 1.3001951694488525
20th percentile: 1.3028117656707763
30th percentile: 1.3088725090026856
40th percentile: 1.31837739944458
50th percentile: 1.3278822898864746
60th percentile: 1.3388020515441894
70th percentile: 1.3497218132019042
80th percentile: 1.5294034957885745
90th percentile: 1.8778470993041994
95th percentile: 2.0520689010620115
99th percentile: 2.1914463424682618
mean time: 1.5022106647491456
Pipeline stage StressChecker completed in 8.17s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
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
arlineka-pharaoh-8b_v2 status is now deployed due to DeploymentManager action
arlineka-pharaoh-8b_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics