submission_id: hastagaras-jamet-8b-l3-mk-i_v5
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Jamet-8B-L3-MK.I
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.05, 'top_p': 1.0, 'min_p': 0.087, 'top_k': 65, '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': "<|begin_of_text|><|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: 2024-06-11T03:15:44+00:00
model_name: p
model_eval_status: success
model_group: Hastagaras/Jamet-8B-L3-M
num_battles: 7759
num_wins: 4195
celo_rating: 1207.19
safety_score: 0.97
propriety_score: 0.670969993021633
propriety_total_count: 2866.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: p
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Jamet-8B-L3-MK.I
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-10
win_ratio: 0.5406624565021265
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer
Waiting for job on hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer to finish
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: ║ _____ __ __ ║
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: ║ /___/ ║
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: ║ https://mk1.ai ║
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: ║ belonging to: ║
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: ║ Chai Research Corp. ║
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-jamet-8b-l3-mk-i-v5-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-i-v5-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: Downloaded to shared memory in 16.165s
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 123.63it/s] Loading 0: 11%|█ | 32/291 [00:00<00:01, 147.94it/s] Loading 0: 17%|█▋ | 50/291 [00:00<00:01, 154.67it/s] Loading 0: 23%|██▎ | 68/291 [00:00<00:01, 156.67it/s] Loading 0: 29%|██▉ | 84/291 [00:00<00:02, 85.52it/s] Loading 0: 35%|███▌ | 102/291 [00:00<00:01, 103.66it/s] Loading 0: 41%|████ | 120/291 [00:01<00:01, 119.78it/s] Loading 0: 47%|████▋ | 138/291 [00:01<00:01, 131.98it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:00, 139.91it/s] Loading 0: 59%|█████▉ | 172/291 [00:01<00:00, 143.94it/s] Loading 0: 65%|██████▍ | 188/291 [00:01<00:01, 91.16it/s] Loading 0: 70%|██████▉ | 203/291 [00:01<00:00, 100.57it/s] Loading 0: 76%|███████▌ | 221/291 [00:01<00:00, 115.96it/s] Loading 0: 82%|████████▏ | 239/291 [00:01<00:00, 128.24it/s] Loading 0: 88%|████████▊ | 257/291 [00:02<00:00, 139.08it/s] Loading 0: 95%|█████████▍| 275/291 [00:02<00:00, 148.25it/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-i-v5-mkmlizer: quantized model in 26.692s
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: Processed model Hastagaras/Jamet-8B-L3-MK.I in 45.355s
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-mk-i-v5
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-mk-i-v5/config.json
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-mk-i-v5/special_tokens_map.json
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-mk-i-v5/tokenizer.json
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-mk-i-v5/tokenizer_config.json
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-mk-i-v5/flywheel_model.0.safetensors
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-jamet-8b-l3-mk-i-v5-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-i-v5-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-mk-i-v5-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-jamet-8b-l3-mk-i-v5-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-mk-i-v5-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-i-v5-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-mk-i-v5-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-i-v5-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: Saving duration: 0.408s
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.562s
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: creating bucket guanaco-reward-models
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk-i-v5_reward
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk-i-v5_reward/special_tokens_map.json
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk-i-v5_reward/config.json
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk-i-v5_reward/tokenizer_config.json
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk-i-v5_reward/merges.txt
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk-i-v5_reward/vocab.json
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk-i-v5_reward/tokenizer.json
hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk-i-v5_reward/reward.tensors
Job hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer completed after 72.99s with status: succeeded
Stopping job with name hastagaras-jamet-8b-l3-mk-i-v5-mkmlizer
Pipeline stage MKMLizer completed in 73.64s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-jamet-8b-l3-mk-i-v5
Waiting for inference service hastagaras-jamet-8b-l3-mk-i-v5 to be ready
Inference service hastagaras-jamet-8b-l3-mk-i-v5 ready after 40.250601053237915s
Pipeline stage ISVCDeployer completed in 46.06s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1789700984954834s
Received healthy response to inference request in 1.3292210102081299s
Received healthy response to inference request in 1.3231699466705322s
Received healthy response to inference request in 1.2968525886535645s
Received healthy response to inference request in 1.3354754447937012s
5 requests
0 failed requests
5th percentile: 1.302116060256958
10th percentile: 1.3073795318603516
20th percentile: 1.3179064750671388
30th percentile: 1.3243801593780518
40th percentile: 1.3268005847930908
50th percentile: 1.3292210102081299
60th percentile: 1.3317227840423584
70th percentile: 1.334224557876587
80th percentile: 1.5041743755340578
90th percentile: 1.8415722370147707
95th percentile: 2.0102711677551266
99th percentile: 2.145230312347412
mean time: 1.4927378177642823
Pipeline stage StressChecker completed in 8.08s
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-jamet-8b-l3-mk-i_v5 status is now deployed due to DeploymentManager action
hastagaras-jamet-8b-l3-mk-i_v5 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics