submission_id: hastagaras-jamet-8b-l3-mk1_v2
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Jamet-8B-L3-MK1
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.1, '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: 2024-06-04T09:27:19+00:00
model_name: jmet2
model_eval_status: success
model_group: Hastagaras/Jamet-8B-L3-M
num_battles: 21037
num_wins: 11973
celo_rating: 1216.54
propriety_score: 0.6793893129770993
propriety_total_count: 393.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: jmet2
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: 0.5691400865142369
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-jamet-8b-l3-mk1-v2-mkmlizer
Waiting for job on hastagaras-jamet-8b-l3-mk1-v2-mkmlizer to finish
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: ║ _____ __ __ ║
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: ║ /___/ ║
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: ║ https://mk1.ai ║
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: ║ belonging to: ║
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: ║ Chai Research Corp. ║
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-jamet-8b-l3-mk1-v2-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-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: Downloaded to shared memory in 18.172s
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 129.79it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 152.90it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:01, 160.87it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 163.88it/s] Loading 0: 29%|██▉ | 84/291 [00:00<00:02, 89.56it/s] Loading 0: 35%|███▌ | 102/291 [00:00<00:01, 107.70it/s] Loading 0: 41%|████ | 120/291 [00:00<00:01, 122.91it/s] Loading 0: 47%|████▋ | 138/291 [00:01<00:01, 135.19it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:00, 144.19it/s] Loading 0: 59%|█████▉ | 173/291 [00:01<00:00, 148.87it/s] Loading 0: 65%|██████▌ | 190/291 [00:01<00:01, 95.55it/s] Loading 0: 71%|███████ | 207/291 [00:01<00:00, 109.30it/s] Loading 0: 77%|███████▋ | 225/291 [00:01<00:00, 123.54it/s] Loading 0: 83%|████████▎ | 242/291 [00:01<00:00, 134.11it/s] Loading 0: 89%|████████▊ | 258/291 [00:02<00:00, 140.29it/s] Loading 0: 95%|█████████▍| 275/291 [00:02<00:00, 146.08it/s] Loading 0: 100%|██████████| 291/291 [00:07<00:00, 9.89it/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-v2-mkmlizer: quantized model in 22.501s
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: Processed model Hastagaras/Jamet-8B-L3-MK1 in 43.143s
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-mk1-v2
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-mk1-v2/config.json
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-mk1-v2/special_tokens_map.json
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-mk1-v2/tokenizer_config.json
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-mk1-v2/tokenizer.json
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-mk1-v2/flywheel_model.0.safetensors
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-jamet-8b-l3-mk1-v2-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-v2-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-mk1-v2-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-v2-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-mk1-v2-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-v2-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-mk1-v2-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-v2-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: Saving duration: 0.385s
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.134s
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk1-v2_reward
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk1-v2_reward/special_tokens_map.json
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk1-v2_reward/tokenizer_config.json
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk1-v2_reward/config.json
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk1-v2_reward/vocab.json
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk1-v2_reward/merges.txt
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk1-v2_reward/tokenizer.json
hastagaras-jamet-8b-l3-mk1-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk1-v2_reward/reward.tensors
Job hastagaras-jamet-8b-l3-mk1-v2-mkmlizer completed after 72.96s with status: succeeded
Stopping job with name hastagaras-jamet-8b-l3-mk1-v2-mkmlizer
Pipeline stage MKMLizer completed in 78.10s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-jamet-8b-l3-mk1-v2
Waiting for inference service hastagaras-jamet-8b-l3-mk1-v2 to be ready
Inference service hastagaras-jamet-8b-l3-mk1-v2 ready after 50.357550621032715s
Pipeline stage ISVCDeployer completed in 58.24s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.926377773284912s
Received healthy response to inference request in 1.3576507568359375s
Received healthy response to inference request in 1.3003566265106201s
Received healthy response to inference request in 1.2718372344970703s
Received healthy response to inference request in 1.2649519443511963s
5 requests
0 failed requests
5th percentile: 1.266329002380371
10th percentile: 1.2677060604095458
20th percentile: 1.2704601764678956
30th percentile: 1.2775411128997802
40th percentile: 1.2889488697052003
50th percentile: 1.3003566265106201
60th percentile: 1.323274278640747
70th percentile: 1.346191930770874
80th percentile: 1.871396160125733
90th percentile: 2.8988869667053225
95th percentile: 3.4126323699951167
99th percentile: 3.823628692626953
mean time: 1.8242348670959472
Pipeline stage StressChecker completed in 9.78s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
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-mk1_v2 status is now deployed due to DeploymentManager action
hastagaras-jamet-8b-l3-mk1_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics