submission_id: hastagaras-jamet-8b-l3-m_8630_v7
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Jamet-8B-L3-MK.V-Blackroot
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.05, 'top_p': 1.0, 'min_p': 0.0, '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: 2024-06-11T07:21:24+00:00
model_name: p
model_eval_status: success
model_group: Hastagaras/Jamet-8B-L3-M
num_battles: 12049
num_wins: 6533
celo_rating: 1210.74
safety_score: 0.93
propriety_score: 0.676737160120846
propriety_total_count: 4303.0
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.V-Blackroot
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-11
win_ratio: 0.5422026724209478
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer
Waiting for job on hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer to finish
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: ║ _____ __ __ ║
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: ║ /___/ ║
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: ║ https://mk1.ai ║
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: ║ belonging to: ║
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: ║ Chai Research Corp. ║
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-jamet-8b-l3-m-8630-v7-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-8630-v7-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: Downloaded to shared memory in 17.615s
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 120.08it/s] Loading 0: 10%|█ | 30/291 [00:00<00:01, 148.32it/s] Loading 0: 15%|█▌ | 45/291 [00:00<00:01, 145.24it/s] Loading 0: 21%|██ | 60/291 [00:00<00:01, 128.88it/s] Loading 0: 26%|██▌ | 75/291 [00:00<00:01, 129.89it/s] Loading 0: 31%|███ | 89/291 [00:00<00:02, 69.65it/s] Loading 0: 35%|███▌ | 103/291 [00:01<00:02, 81.32it/s] Loading 0: 41%|████ | 120/291 [00:01<00:01, 96.85it/s] Loading 0: 46%|████▌ | 133/291 [00:01<00:01, 103.09it/s] Loading 0: 51%|█████ | 148/291 [00:01<00:01, 110.85it/s] Loading 0: 57%|█████▋ | 165/291 [00:01<00:01, 121.40it/s] Loading 0: 62%|██████▏ | 179/291 [00:01<00:00, 120.59it/s] Loading 0: 66%|██████▌ | 192/291 [00:02<00:01, 70.45it/s] Loading 0: 70%|██████▉ | 203/291 [00:02<00:01, 76.49it/s] Loading 0: 76%|███████▌ | 220/291 [00:02<00:00, 93.19it/s] Loading 0: 81%|████████▏ | 237/291 [00:02<00:00, 107.14it/s] Loading 0: 86%|████████▌ | 250/291 [00:02<00:00, 112.03it/s] Loading 0: 91%|█████████ | 265/291 [00:02<00:00, 118.25it/s] Loading 0: 97%|█████████▋| 281/291 [00:02<00:00, 125.23it/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-8630-v7-mkmlizer: quantized model in 28.749s
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: Processed model Hastagaras/Jamet-8B-L3-MK.V-Blackroot in 49.247s
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-8630-v7
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-8630-v7/config.json
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-8630-v7/tokenizer_config.json
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-8630-v7/special_tokens_map.json
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-8630-v7/tokenizer.json
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-8630-v7/flywheel_model.0.safetensors
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-jamet-8b-l3-m-8630-v7-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-8630-v7-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-8630-v7-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-8630-v7-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-8630-v7-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-8630-v7-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-8630-v7-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-8630-v7-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: Saving duration: 0.383s
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.046s
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: creating bucket guanaco-reward-models
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8630-v7_reward
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8630-v7_reward/config.json
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8630-v7_reward/special_tokens_map.json
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8630-v7_reward/tokenizer_config.json
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8630-v7_reward/vocab.json
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8630-v7_reward/merges.txt
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8630-v7_reward/tokenizer.json
hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8630-v7_reward/reward.tensors
Job hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer completed after 83.09s with status: succeeded
Stopping job with name hastagaras-jamet-8b-l3-m-8630-v7-mkmlizer
Pipeline stage MKMLizer completed in 86.75s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-jamet-8b-l3-m-8630-v7
Waiting for inference service hastagaras-jamet-8b-l3-m-8630-v7 to be ready
Inference service hastagaras-jamet-8b-l3-m-8630-v7 ready after 30.298015356063843s
Pipeline stage ISVCDeployer completed in 37.43s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1520278453826904s
Received healthy response to inference request in 1.3241755962371826s
Received healthy response to inference request in 1.3083391189575195s
Received healthy response to inference request in 1.2436020374298096s
Received healthy response to inference request in 1.327577829360962s
5 requests
0 failed requests
5th percentile: 1.2565494537353517
10th percentile: 1.2694968700408935
20th percentile: 1.2953917026519775
30th percentile: 1.311506414413452
40th percentile: 1.3178410053253173
50th percentile: 1.3241755962371826
60th percentile: 1.3255364894866943
70th percentile: 1.326897382736206
80th percentile: 1.4924678325653078
90th percentile: 1.8222478389739991
95th percentile: 1.9871378421783445
99th percentile: 2.1190498447418213
mean time: 1.4711444854736329
Pipeline stage StressChecker completed in 7.97s
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 0.12s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-jamet-8b-l3-m_8630_v7 status is now deployed due to DeploymentManager action
hastagaras-jamet-8b-l3-m_8630_v7 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics