submission_id: hastagaras-jamet-8b-l3-m_4081_v1
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Jamet-8B-L3-MK.V-BASE
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.0, '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: 2024-06-06T08:17:20+00:00
model_name: hastagaras-jamet-8b-l3-m_4081_v1
model_eval_status: success
model_group: Hastagaras/Jamet-8B-L3-M
num_battles: 25610
num_wins: 14462
celo_rating: 1213.22
propriety_score: 0.6634182908545727
propriety_total_count: 1334.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: hastagaras-jamet-8b-l3-m_4081_v1
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Jamet-8B-L3-MK.V-BASE
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-06
win_ratio: 0.5647012885591566
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer
Waiting for job on hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer to finish
Stopping job with name hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer
Waiting for job on hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer to finish
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: ║ /___/ ║
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: ║ belonging to: ║
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-jamet-8b-l3-m-4081-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-m-4081-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: Downloaded to shared memory in 34.395s
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 6%|▌ | 17/291 [00:00<00:01, 169.88it/s] Loading 0: 13%|█▎ | 39/291 [00:00<00:01, 197.59it/s] Loading 0: 20%|██ | 59/291 [00:00<00:01, 191.90it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 101.45it/s] Loading 0: 35%|███▌ | 103/291 [00:00<00:01, 119.70it/s] Loading 0: 42%|████▏ | 123/291 [00:00<00:01, 137.76it/s] Loading 0: 51%|█████ | 147/291 [00:01<00:00, 159.64it/s] Loading 0: 57%|█████▋ | 167/291 [00:01<00:00, 167.31it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:00, 107.68it/s] Loading 0: 69%|██████▉ | 202/291 [00:01<00:00, 115.61it/s] Loading 0: 77%|███████▋ | 224/291 [00:01<00:00, 136.77it/s] Loading 0: 85%|████████▍ | 246/291 [00:01<00:00, 155.67it/s] Loading 0: 91%|█████████ | 265/291 [00:01<00:00, 163.36it/s] Loading 0: 99%|█████████▊| 287/291 [00:06<00:00, 12.87it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: quantized model in 17.550s
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: Processed model Hastagaras/Jamet-8B-L3-MK.V-BASE in 52.957s
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-4081-v1
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-4081-v1/special_tokens_map.json
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-4081-v1/config.json
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-4081-v1/tokenizer_config.json
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-4081-v1/tokenizer.json
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-4081-v1/flywheel_model.0.safetensors
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-jamet-8b-l3-m-4081-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-m-4081-v1-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-4081-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-jamet-8b-l3-m-4081-v1-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-4081-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-m-4081-v1-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-4081-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-m-4081-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: Saving duration: 0.234s
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.317s
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-4081-v1_reward/merges.txt
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-4081-v1_reward/vocab.json
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-4081-v1_reward/tokenizer.json
hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-4081-v1_reward/reward.tensors
Job hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer completed after 86.22s with status: succeeded
Stopping job with name hastagaras-jamet-8b-l3-m-4081-v1-mkmlizer
Pipeline stage MKMLizer completed in 92.83s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-jamet-8b-l3-m-4081-v1
Waiting for inference service hastagaras-jamet-8b-l3-m-4081-v1 to be ready
Inference service hastagaras-jamet-8b-l3-m-4081-v1 ready after 40.249980211257935s
Pipeline stage ISVCDeployer completed in 48.04s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0685477256774902s
Received healthy response to inference request in 1.344944953918457s
Received healthy response to inference request in 1.3447952270507812s
Received healthy response to inference request in 1.2749392986297607s
Received healthy response to inference request in 1.2330663204193115s
5 requests
0 failed requests
5th percentile: 1.2414409160614013
10th percentile: 1.2498155117034913
20th percentile: 1.266564702987671
30th percentile: 1.288910484313965
40th percentile: 1.316852855682373
50th percentile: 1.3447952270507812
60th percentile: 1.3448551177978516
70th percentile: 1.344915008544922
80th percentile: 1.489665508270264
90th percentile: 1.779106616973877
95th percentile: 1.9238271713256834
99th percentile: 2.039603614807129
mean time: 1.4532587051391601
Pipeline stage StressChecker completed in 7.90s
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-m_4081_v1 status is now deployed due to DeploymentManager action
hastagaras-jamet-8b-l3-m_4081_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics