submission_id: hastagaras-jamet-8b-l3-mk-i_v4
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': 0.09, '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: 2024-06-10T20:52:35+00:00
model_name: p
model_eval_status: success
model_group: Hastagaras/Jamet-8B-L3-M
num_battles: 13991
num_wins: 7781
celo_rating: 1206.73
safety_score: 0.97
propriety_score: 0.7067368421052631
propriety_total_count: 4750.0
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: 0.556143234936745
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer
Waiting for job on hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer to finish
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: ║ _____ __ __ ║
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: ║ /___/ ║
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: ║ https://mk1.ai ║
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: ║ belonging to: ║
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: ║ Chai Research Corp. ║
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-jamet-8b-l3-mk-i-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-mk-i-v4-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: Downloaded to shared memory in 15.520s
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 11/291 [00:00<00:02, 109.88it/s] Loading 0: 8%|▊ | 22/291 [00:00<00:02, 96.23it/s] Loading 0: 12%|█▏ | 36/291 [00:00<00:02, 113.50it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:02, 115.49it/s] Loading 0: 21%|██ | 61/291 [00:00<00:02, 110.21it/s] Loading 0: 25%|██▌ | 73/291 [00:00<00:01, 111.35it/s] Loading 0: 29%|██▉ | 85/291 [00:01<00:04, 50.59it/s] Loading 0: 33%|███▎ | 96/291 [00:01<00:03, 60.16it/s] Loading 0: 36%|███▋ | 106/291 [00:01<00:02, 66.21it/s] Loading 0: 40%|████ | 117/291 [00:01<00:02, 74.44it/s] Loading 0: 44%|████▍ | 129/291 [00:01<00:01, 82.55it/s] Loading 0: 48%|████▊ | 139/291 [00:01<00:01, 86.20it/s] Loading 0: 51%|█████ | 149/291 [00:01<00:01, 88.94it/s] Loading 0: 57%|█████▋ | 165/291 [00:01<00:01, 104.38it/s] Loading 0: 62%|██████▏ | 180/291 [00:02<00:00, 112.23it/s] Loading 0: 66%|██████▌ | 192/291 [00:02<00:01, 58.38it/s] Loading 0: 69%|██████▉ | 202/291 [00:02<00:01, 63.61it/s] Loading 0: 74%|███████▍ | 215/291 [00:02<00:01, 75.32it/s] Loading 0: 79%|███████▊ | 229/291 [00:02<00:00, 86.81it/s] Loading 0: 85%|████████▍ | 246/291 [00:02<00:00, 101.91it/s] Loading 0: 89%|████████▊ | 258/291 [00:03<00:00, 99.37it/s] Loading 0: 94%|█████████▍| 273/291 [00:03<00:00, 106.24it/s] Loading 0: 98%|█████████▊| 285/291 [00:03<00:00, 106.56it/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-v4-mkmlizer: quantized model in 20.491s
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: Processed model Hastagaras/Jamet-8B-L3-MK.I in 37.190s
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-mk-i-v4
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-mk-i-v4/special_tokens_map.json
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-mk-i-v4/config.json
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-mk-i-v4/tokenizer_config.json
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-mk-i-v4/flywheel_model.0.safetensors
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-jamet-8b-l3-mk-i-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-mk-i-v4-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-mk-i-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-mk-i-v4-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-mk-i-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-mk-i-v4-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-mk-i-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-mk-i-v4-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: Saving duration: 0.305s
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.087s
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: creating bucket guanaco-reward-models
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk-i-v4_reward
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk-i-v4_reward/config.json
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk-i-v4_reward/special_tokens_map.json
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk-i-v4_reward/tokenizer_config.json
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk-i-v4_reward/vocab.json
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk-i-v4_reward/merges.txt
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk-i-v4_reward/tokenizer.json
hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk-i-v4_reward/reward.tensors
Job hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer completed after 63.12s with status: succeeded
Stopping job with name hastagaras-jamet-8b-l3-mk-i-v4-mkmlizer
Pipeline stage MKMLizer completed in 66.53s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-jamet-8b-l3-mk-i-v4
Waiting for inference service hastagaras-jamet-8b-l3-mk-i-v4 to be ready
Inference service hastagaras-jamet-8b-l3-mk-i-v4 ready after 90.52774477005005s
Pipeline stage ISVCDeployer completed in 97.95s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.158975839614868s
Received healthy response to inference request in 1.3367996215820312s
Received healthy response to inference request in 2.151214838027954s
Received healthy response to inference request in 1.2672483921051025s
Received healthy response to inference request in 1.3297719955444336s
5 requests
0 failed requests
5th percentile: 1.2797531127929687
10th percentile: 1.292257833480835
20th percentile: 1.3172672748565675
30th percentile: 1.3311775207519532
40th percentile: 1.333988571166992
50th percentile: 1.3367996215820312
60th percentile: 1.6625657081604004
70th percentile: 1.9883317947387693
80th percentile: 2.152767038345337
90th percentile: 2.1558714389801024
95th percentile: 2.1574236392974853
99th percentile: 2.1586653995513916
mean time: 1.648802137374878
Pipeline stage StressChecker completed in 8.88s
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_v4 status is now deployed due to DeploymentManager action
hastagaras-jamet-8b-l3-mk-i_v4 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics