submission_id: hastagaras-jamet-8b-l3-mk-iv_v1
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Jamet-8B-L3-MK.IV
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 80, '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: 2024-06-06T00:03:58+00:00
model_name: mark-iv
model_eval_status: success
model_group: Hastagaras/Jamet-8B-L3-M
num_battles: 20802
num_wins: 11356
celo_rating: 1210.87
safety_score: 0.97
propriety_score: 0.6709233791748527
propriety_total_count: 1018.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: mark-iv
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Jamet-8B-L3-MK.IV
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-05
win_ratio: 0.5459090472069993
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer
Waiting for job on hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer to finish
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: ║ /___/ ║
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: ║ belonging to: ║
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-jamet-8b-l3-mk-iv-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-jamet-8b-l3-mk-iv-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: Downloaded to shared memory in 40.717s
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 130.78it/s] Loading 0: 11%|█ | 32/291 [00:00<00:01, 152.73it/s] Loading 0: 17%|█▋ | 50/291 [00:00<00:01, 158.85it/s] Loading 0: 23%|██▎ | 68/291 [00:00<00:01, 161.46it/s] Loading 0: 29%|██▉ | 85/291 [00:00<00:02, 88.31it/s] Loading 0: 35%|███▌ | 103/291 [00:00<00:01, 105.77it/s] Loading 0: 42%|████▏ | 121/291 [00:00<00:01, 120.42it/s] Loading 0: 48%|████▊ | 139/291 [00:01<00:01, 132.36it/s] Loading 0: 54%|█████▍ | 157/291 [00:01<00:00, 141.75it/s] Loading 0: 60%|██████ | 175/291 [00:01<00:00, 151.57it/s] Loading 0: 66%|██████▌ | 192/291 [00:01<00:01, 89.90it/s] Loading 0: 71%|███████ | 207/291 [00:01<00:00, 100.64it/s] Loading 0: 76%|███████▌ | 221/291 [00:01<00:00, 107.64it/s] Loading 0: 82%|████████▏ | 238/291 [00:01<00:00, 121.36it/s] Loading 0: 88%|████████▊ | 256/291 [00:02<00:00, 131.21it/s] Loading 0: 94%|█████████▍| 273/291 [00:02<00:00, 140.91it/s] Loading 0: 99%|█████████▉| 289/291 [00:07<00:00, 10.15it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: quantized model in 19.087s
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: Processed model Hastagaras/Jamet-8B-L3-MK.IV in 60.855s
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-mk-iv-v1
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-mk-iv-v1/config.json
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-mk-iv-v1/special_tokens_map.json
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-mk-iv-v1/tokenizer_config.json
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-mk-iv-v1/tokenizer.json
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-mk-iv-v1/flywheel_model.0.safetensors
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-jamet-8b-l3-mk-iv-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-jamet-8b-l3-mk-iv-v1-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-mk-iv-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-jamet-8b-l3-mk-iv-v1-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-mk-iv-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-jamet-8b-l3-mk-iv-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: Saving duration: 0.276s
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.725s
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk-iv-v1_reward
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk-iv-v1_reward/config.json
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk-iv-v1_reward/special_tokens_map.json
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk-iv-v1_reward/tokenizer_config.json
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk-iv-v1_reward/merges.txt
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk-iv-v1_reward/vocab.json
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk-iv-v1_reward/tokenizer.json
hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk-iv-v1_reward/reward.tensors
Job hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer completed after 135.69s with status: succeeded
Stopping job with name hastagaras-jamet-8b-l3-mk-iv-v1-mkmlizer
Pipeline stage MKMLizer completed in 136.60s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-jamet-8b-l3-mk-iv-v1
Waiting for inference service hastagaras-jamet-8b-l3-mk-iv-v1 to be ready
Inference service hastagaras-jamet-8b-l3-mk-iv-v1 ready after 40.35434651374817s
Pipeline stage ISVCDeployer completed in 46.16s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0681986808776855s
Received healthy response to inference request in 1.380028247833252s
Received healthy response to inference request in 1.3579607009887695s
Received healthy response to inference request in 1.3327844142913818s
Received healthy response to inference request in 1.2614140510559082s
5 requests
0 failed requests
5th percentile: 1.2756881237030029
10th percentile: 1.2899621963500976
20th percentile: 1.3185103416442872
30th percentile: 1.3378196716308595
40th percentile: 1.3478901863098145
50th percentile: 1.3579607009887695
60th percentile: 1.3667877197265625
70th percentile: 1.3756147384643556
80th percentile: 1.5176623344421387
90th percentile: 1.7929305076599122
95th percentile: 1.9305645942687988
99th percentile: 2.0406718635559082
mean time: 1.4800772190093994
Pipeline stage StressChecker completed in 8.03s
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-jamet-8b-l3-mk-iv_v1 status is now deployed due to DeploymentManager action
hastagaras-jamet-8b-l3-mk-iv_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics