submission_id: hastagaras-jamet-8b-l3-mk-i_v3
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': 0.085, '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': "<|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: 2024-06-10T19:50:10+00:00
model_name: p
model_eval_status: success
model_group: Hastagaras/Jamet-8B-L3-M
num_battles: 10150
num_wins: 5500
celo_rating: 1210.56
propriety_score: 0.7249539028887523
propriety_total_count: 3254.0
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: 0.541871921182266
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer
Waiting for job on hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer to finish
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: ║ _____ __ __ ║
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: ║ /___/ ║
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: ║ https://mk1.ai ║
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: ║ belonging to: ║
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: ║ Chai Research Corp. ║
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-jamet-8b-l3-mk-i-v3-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-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: Downloaded to shared memory in 16.402s
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:01, 194.57it/s] Loading 0: 14%|█▍ | 41/291 [00:00<00:01, 188.16it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 209.99it/s] Loading 0: 30%|███ | 88/291 [00:00<00:01, 105.87it/s] Loading 0: 38%|███▊ | 111/291 [00:00<00:01, 131.83it/s] Loading 0: 45%|████▌ | 131/291 [00:00<00:01, 145.42it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:00, 169.03it/s] Loading 0: 62%|██████▏ | 179/291 [00:01<00:00, 182.97it/s] Loading 0: 69%|██████▊ | 200/291 [00:01<00:00, 114.99it/s] Loading 0: 76%|███████▌ | 220/291 [00:01<00:00, 129.65it/s] Loading 0: 83%|████████▎ | 242/291 [00:01<00:00, 148.45it/s] Loading 0: 91%|█████████ | 265/291 [00:01<00:00, 163.74it/s] Loading 0: 99%|█████████▊| 287/291 [00:06<00:00, 14.25it/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-v3-mkmlizer: quantized model in 16.700s
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: Processed model Hastagaras/Jamet-8B-L3-MK.I in 34.002s
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-mk-i-v3
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-mk-i-v3/config.json
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-mk-i-v3/tokenizer_config.json
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-mk-i-v3/special_tokens_map.json
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-mk-i-v3/tokenizer.json
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-mk-i-v3/flywheel_model.0.safetensors
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-jamet-8b-l3-mk-i-v3-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-v3-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-mk-i-v3-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-v3-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-mk-i-v3-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-v3-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-mk-i-v3-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-v3-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: Saving duration: 0.224s
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.366s
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: creating bucket guanaco-reward-models
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk-i-v3_reward
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk-i-v3_reward/tokenizer_config.json
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk-i-v3_reward/special_tokens_map.json
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk-i-v3_reward/vocab.json
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk-i-v3_reward/config.json
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk-i-v3_reward/merges.txt
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk-i-v3_reward/tokenizer.json
hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk-i-v3_reward/reward.tensors
Job hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer completed after 56.68s with status: succeeded
Stopping job with name hastagaras-jamet-8b-l3-mk-i-v3-mkmlizer
Pipeline stage MKMLizer completed in 59.72s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-jamet-8b-l3-mk-i-v3
Waiting for inference service hastagaras-jamet-8b-l3-mk-i-v3 to be ready
Inference service hastagaras-jamet-8b-l3-mk-i-v3 ready after 51.130518198013306s
Pipeline stage ISVCDeployer completed in 61.96s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1472344398498535s
Received healthy response to inference request in 1.35135817527771s
Received healthy response to inference request in 1.3285102844238281s
Received healthy response to inference request in 1.3132503032684326s
Received healthy response to inference request in 9.942714929580688s
5 requests
0 failed requests
5th percentile: 1.3163022994995117
10th percentile: 1.3193542957305908
20th percentile: 1.325458288192749
30th percentile: 1.3330798625946045
40th percentile: 1.3422190189361571
50th percentile: 1.35135817527771
60th percentile: 1.6697086811065673
70th percentile: 1.9880591869354247
80th percentile: 3.706330537796022
90th percentile: 6.824522733688355
95th percentile: 8.38361883163452
99th percentile: 9.630895709991455
mean time: 3.2166136264801026
Pipeline stage StressChecker completed in 16.70s
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_v3 status is now deployed due to DeploymentManager action
hastagaras-jamet-8b-l3-mk-i_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics