submission_id: hastagaras-jamet-8b-l3-m_2070_v4
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Jamet-8B-L3-MK.II-LV
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.1, 'top_p': 1.0, 'min_p': 0.08, '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: 2024-06-06T04:25:14+00:00
model_name: ht-prop-test
model_eval_status: success
model_group: Hastagaras/Jamet-8B-L3-M
num_battles: 26176
num_wins: 14721
celo_rating: 1211.95
safety_score: 0.97
propriety_score: 0.6679049034175334
propriety_total_count: 1346.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: ht-prop-test
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Jamet-8B-L3-MK.II-LV
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-05
win_ratio: 0.562385391198044
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer
Waiting for job on hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer to finish
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: ║ _____ __ __ ║
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: ║ /___/ ║
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: ║ https://mk1.ai ║
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: ║ belonging to: ║
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: ║ Chai Research Corp. ║
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-jamet-8b-l3-m-2070-v4-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-2070-v4-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: Downloaded to shared memory in 30.765s
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 124.32it/s] Loading 0: 10%|█ | 30/291 [00:00<00:01, 147.29it/s] Loading 0: 15%|█▌ | 45/291 [00:00<00:01, 145.81it/s] Loading 0: 21%|██ | 60/291 [00:00<00:01, 143.64it/s] Loading 0: 26%|██▌ | 76/291 [00:00<00:01, 148.75it/s] Loading 0: 31%|███▏ | 91/291 [00:00<00:02, 70.66it/s] Loading 0: 36%|███▌ | 104/291 [00:01<00:02, 80.88it/s] Loading 0: 42%|████▏ | 121/291 [00:01<00:01, 98.35it/s] Loading 0: 47%|████▋ | 138/291 [00:01<00:01, 114.27it/s] Loading 0: 53%|█████▎ | 154/291 [00:01<00:01, 125.19it/s] Loading 0: 58%|█████▊ | 169/291 [00:01<00:00, 128.48it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 74.92it/s] Loading 0: 69%|██████▉ | 201/291 [00:02<00:01, 84.05it/s] Loading 0: 74%|███████▍ | 215/291 [00:02<00:00, 94.24it/s] Loading 0: 79%|███████▊ | 229/291 [00:02<00:00, 103.70it/s] Loading 0: 85%|████████▍ | 246/291 [00:02<00:00, 117.11it/s] Loading 0: 89%|████████▉ | 260/291 [00:02<00:00, 121.95it/s] Loading 0: 94%|█████████▍| 274/291 [00:02<00:00, 124.23it/s] Loading 0: 99%|█████████▉| 288/291 [00:07<00:00, 8.64it/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-2070-v4-mkmlizer: quantized model in 20.070s
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: Processed model Hastagaras/Jamet-8B-L3-MK.II-LV in 52.002s
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-2070-v4
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-2070-v4/config.json
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-2070-v4/special_tokens_map.json
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-2070-v4/tokenizer_config.json
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-2070-v4/tokenizer.json
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-2070-v4/flywheel_model.0.safetensors
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-jamet-8b-l3-m-2070-v4-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-2070-v4-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-2070-v4-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-2070-v4-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-2070-v4-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-2070-v4-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-2070-v4-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-2070-v4-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: Saving duration: 0.292s
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 8.668s
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: creating bucket guanaco-reward-models
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-2070-v4_reward
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-2070-v4_reward/config.json
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-2070-v4_reward/special_tokens_map.json
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-2070-v4_reward/tokenizer_config.json
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-2070-v4_reward/merges.txt
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-2070-v4_reward/vocab.json
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-2070-v4_reward/tokenizer.json
hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-2070-v4_reward/reward.tensors
Job hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer completed after 83.82s with status: succeeded
Stopping job with name hastagaras-jamet-8b-l3-m-2070-v4-mkmlizer
Pipeline stage MKMLizer completed in 84.69s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-jamet-8b-l3-m-2070-v4
Waiting for inference service hastagaras-jamet-8b-l3-m-2070-v4 to be ready
Inference service hastagaras-jamet-8b-l3-m-2070-v4 ready after 40.23914909362793s
Pipeline stage ISVCDeployer completed in 46.07s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1654140949249268s
Received healthy response to inference request in 1.3898050785064697s
Received healthy response to inference request in 1.3305039405822754s
Received healthy response to inference request in 1.298633337020874s
Received healthy response to inference request in 1.2468409538269043s
5 requests
0 failed requests
5th percentile: 1.2571994304656982
10th percentile: 1.2675579071044922
20th percentile: 1.2882748603820802
30th percentile: 1.3050074577331543
40th percentile: 1.3177556991577148
50th percentile: 1.3305039405822754
60th percentile: 1.354224395751953
70th percentile: 1.3779448509216308
80th percentile: 1.5449268817901614
90th percentile: 1.855170488357544
95th percentile: 2.0102922916412354
99th percentile: 2.1343897342681886
mean time: 1.48623948097229
Pipeline stage StressChecker completed in 9.06s
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-m_2070_v4 status is now deployed due to DeploymentManager action
hastagaras-jamet-8b-l3-m_2070_v4 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics