submission_id: hastagaras-jamet-8b-l3-m_2070_v3
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': 1.0, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 55, '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: 2024-06-06T01:47:41+00:00
model_name: test
model_eval_status: success
model_group: Hastagaras/Jamet-8B-L3-M
num_battles: 15528
num_wins: 8770
celo_rating: 1215.06
safety_score: 0.97
propriety_score: 0.6235294117647059
propriety_total_count: 765.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: 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: 0.5647861926841834
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer
Waiting for job on hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer to finish
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: ║ _____ __ __ ║
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: ║ /___/ ║
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: ║ https://mk1.ai ║
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: ║ belonging to: ║
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: ║ Chai Research Corp. ║
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-jamet-8b-l3-m-2070-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-m-2070-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: Downloaded to shared memory in 22.947s
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 122.73it/s] Loading 0: 10%|█ | 30/291 [00:00<00:01, 144.70it/s] Loading 0: 15%|█▌ | 45/291 [00:00<00:01, 143.83it/s] Loading 0: 21%|██ | 60/291 [00:00<00:01, 139.37it/s] Loading 0: 26%|██▌ | 76/291 [00:00<00:01, 140.75it/s] Loading 0: 31%|███▏ | 91/291 [00:00<00:02, 68.71it/s] Loading 0: 36%|███▌ | 104/291 [00:01<00:02, 78.20it/s] Loading 0: 42%|████▏ | 121/291 [00:01<00:01, 95.86it/s] Loading 0: 47%|████▋ | 138/291 [00:01<00:01, 111.54it/s] Loading 0: 53%|█████▎ | 153/291 [00:01<00:01, 120.08it/s] Loading 0: 58%|█████▊ | 168/291 [00:01<00:01, 122.28it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 74.68it/s] Loading 0: 69%|██████▉ | 201/291 [00:02<00:01, 84.52it/s] Loading 0: 74%|███████▍ | 216/291 [00:02<00:00, 96.76it/s] Loading 0: 79%|███████▉ | 230/291 [00:02<00:00, 104.55it/s] Loading 0: 85%|████████▍ | 247/291 [00:02<00:00, 119.28it/s] Loading 0: 91%|█████████ | 264/291 [00:02<00:00, 128.91it/s] Loading 0: 96%|█████████▌| 279/291 [00:02<00:00, 134.28it/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-v3-mkmlizer: quantized model in 19.355s
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: Processed model Hastagaras/Jamet-8B-L3-MK.II-LV in 43.398s
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-2070-v3
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-2070-v3/config.json
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-2070-v3/special_tokens_map.json
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-2070-v3/tokenizer_config.json
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-2070-v3/tokenizer.json
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-2070-v3/flywheel_model.0.safetensors
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-jamet-8b-l3-m-2070-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-m-2070-v3-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-2070-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-m-2070-v3-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-2070-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-m-2070-v3-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-2070-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-m-2070-v3-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: Saving duration: 0.304s
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.670s
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: creating bucket guanaco-reward-models
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-2070-v3_reward
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-2070-v3_reward/config.json
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-2070-v3_reward/special_tokens_map.json
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-2070-v3_reward/tokenizer_config.json
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-2070-v3_reward/merges.txt
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-2070-v3_reward/vocab.json
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-2070-v3_reward/tokenizer.json
hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-2070-v3_reward/reward.tensors
Job hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer completed after 73.71s with status: succeeded
Stopping job with name hastagaras-jamet-8b-l3-m-2070-v3-mkmlizer
Pipeline stage MKMLizer completed in 77.61s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-jamet-8b-l3-m-2070-v3
Waiting for inference service hastagaras-jamet-8b-l3-m-2070-v3 to be ready
Inference service hastagaras-jamet-8b-l3-m-2070-v3 ready after 40.28625297546387s
Pipeline stage ISVCDeployer completed in 47.78s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1494076251983643s
Received healthy response to inference request in 1.344066858291626s
Received healthy response to inference request in 1.3244965076446533s
Received healthy response to inference request in 1.292593002319336s
Received healthy response to inference request in 1.250746250152588s
5 requests
0 failed requests
5th percentile: 1.2591156005859374
10th percentile: 1.2674849510192872
20th percentile: 1.2842236518859864
30th percentile: 1.2989737033843993
40th percentile: 1.3117351055145263
50th percentile: 1.3244965076446533
60th percentile: 1.3323246479034423
70th percentile: 1.3401527881622315
80th percentile: 1.5051350116729738
90th percentile: 1.827271318435669
95th percentile: 1.9883394718170164
99th percentile: 2.117193994522095
mean time: 1.4722620487213134
Pipeline stage StressChecker completed in 7.98s
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 0.05s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-jamet-8b-l3-m_2070_v3 status is now deployed due to DeploymentManager action
hastagaras-jamet-8b-l3-m_2070_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics