submission_id: hastagaras-jamet-8b-l3-mk1_v1
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Jamet-8B-L3-MK1
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.05, 'top_p': 1.0, 'min_p': 0.08, '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': "<|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: 2024-06-04T08:54:45+00:00
model_name: jmet
model_eval_status: success
model_group: Hastagaras/Jamet-8B-L3-M
num_battles: 12104
num_wins: 6880
celo_rating: 1216.14
safety_score: 0.97
propriety_score: 0.7228915662650602
propriety_total_count: 249.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: jmet
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Jamet-8B-L3-MK1
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-04
win_ratio: 0.5684071381361533
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-jamet-8b-l3-mk1-v1-mkmlizer
Waiting for job on hastagaras-jamet-8b-l3-mk1-v1-mkmlizer to finish
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: ║ /___/ ║
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: ║ belonging to: ║
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-jamet-8b-l3-mk1-v1-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-mk1-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: Downloaded to shared memory in 27.158s
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:02, 99.09it/s] Loading 0: 8%|▊ | 23/291 [00:00<00:02, 98.74it/s] Loading 0: 13%|█▎ | 39/291 [00:00<00:02, 122.52it/s] Loading 0: 18%|█▊ | 52/291 [00:00<00:02, 119.20it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 125.11it/s] Loading 0: 27%|██▋ | 79/291 [00:00<00:01, 121.98it/s] Loading 0: 32%|███▏ | 92/291 [00:01<00:03, 54.79it/s] Loading 0: 35%|███▌ | 103/291 [00:01<00:02, 62.69it/s] Loading 0: 41%|████ | 120/291 [00:01<00:02, 80.57it/s] Loading 0: 45%|████▌ | 132/291 [00:01<00:01, 87.93it/s] Loading 0: 51%|█████ | 148/291 [00:01<00:01, 101.32it/s] Loading 0: 57%|█████▋ | 165/291 [00:01<00:01, 113.70it/s] Loading 0: 62%|██████▏ | 180/291 [00:01<00:00, 118.38it/s] Loading 0: 67%|██████▋ | 194/291 [00:02<00:01, 63.23it/s] Loading 0: 73%|███████▎ | 211/291 [00:02<00:01, 78.13it/s] Loading 0: 78%|███████▊ | 228/291 [00:02<00:00, 92.06it/s] Loading 0: 83%|████████▎ | 241/291 [00:02<00:00, 98.79it/s] Loading 0: 88%|████████▊ | 256/291 [00:02<00:00, 107.43it/s] Loading 0: 94%|█████████▍| 273/291 [00:02<00:00, 118.33it/s] Loading 0: 99%|█████████▊| 287/291 [00:10<00:00, 6.67it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: quantized model in 24.310s
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: Processed model Hastagaras/Jamet-8B-L3-MK1 in 52.702s
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-mk1-v1
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-mk1-v1/special_tokens_map.json
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-mk1-v1/tokenizer_config.json
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-mk1-v1/config.json
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-mk1-v1/tokenizer.json
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-mk1-v1/flywheel_model.0.safetensors
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-jamet-8b-l3-mk1-v1-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-mk1-v1-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-mk1-v1-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-mk1-v1-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-mk1-v1-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-mk1-v1-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-mk1-v1-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-mk1-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: Saving duration: 0.246s
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.483s
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk1-v1_reward
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk1-v1_reward/tokenizer_config.json
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk1-v1_reward/config.json
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk1-v1_reward/special_tokens_map.json
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk1-v1_reward/merges.txt
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk1-v1_reward/vocab.json
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk1-v1_reward/tokenizer.json
hastagaras-jamet-8b-l3-mk1-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk1-v1_reward/reward.tensors
Job hastagaras-jamet-8b-l3-mk1-v1-mkmlizer completed after 83.07s with status: succeeded
Stopping job with name hastagaras-jamet-8b-l3-mk1-v1-mkmlizer
Pipeline stage MKMLizer completed in 83.82s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-jamet-8b-l3-mk1-v1
Waiting for inference service hastagaras-jamet-8b-l3-mk1-v1 to be ready
Inference service hastagaras-jamet-8b-l3-mk1-v1 ready after 30.2782986164093s
Pipeline stage ISVCDeployer completed in 36.07s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0650789737701416s
Received healthy response to inference request in 1.3497116565704346s
Received healthy response to inference request in 1.2686498165130615s
Received healthy response to inference request in 1.2859482765197754s
Received healthy response to inference request in 1.2660291194915771s
5 requests
0 failed requests
5th percentile: 1.2665532588958741
10th percentile: 1.2670773983001709
20th percentile: 1.2681256771087646
30th percentile: 1.2721095085144043
40th percentile: 1.2790288925170898
50th percentile: 1.2859482765197754
60th percentile: 1.311453628540039
70th percentile: 1.3369589805603028
80th percentile: 1.492785120010376
90th percentile: 1.778932046890259
95th percentile: 1.9220055103302
99th percentile: 2.036464281082153
mean time: 1.4470835685729981
Pipeline stage StressChecker completed in 7.84s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-jamet-8b-l3-mk1_v1 status is now deployed due to DeploymentManager action
hastagaras-jamet-8b-l3-mk1_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics