submission_id: hastagaras-jamet-8b-l3-m_6628_v1
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Jamet-8B-L3-MK.V-BR3
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.05, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 60, '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: 2024-06-06T21:14:29+00:00
model_name: br3
model_eval_status: success
model_group: Hastagaras/Jamet-8B-L3-M
num_battles: 17434
num_wins: 9296
celo_rating: 1210.24
safety_score: 0.97
propriety_score: 0.6721581548599671
propriety_total_count: 1214.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: br3
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Jamet-8B-L3-MK.V-BR3
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-06
win_ratio: 0.5332109670758288
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer
Waiting for job on hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer to finish
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: ║ /___/ ║
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: ║ belonging to: ║
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-jamet-8b-l3-m-6628-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-m-6628-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: Downloaded to shared memory in 40.555s
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:12, 2.12s/it] Loading 0: 8%|▊ | 23/291 [00:04<00:36, 7.28it/s] Loading 0: 15%|█▌ | 44/291 [00:04<00:15, 16.28it/s] Loading 0: 21%|██ | 60/291 [00:04<00:10, 21.68it/s] Loading 0: 29%|██▉ | 85/291 [00:04<00:05, 37.35it/s] Loading 0: 36%|███▌ | 104/291 [00:05<00:03, 50.86it/s] Loading 0: 42%|████▏ | 123/291 [00:05<00:02, 66.61it/s] Loading 0: 48%|████▊ | 141/291 [00:05<00:01, 78.39it/s] Loading 0: 56%|█████▌ | 163/291 [00:05<00:01, 100.42it/s] Loading 0: 62%|██████▏ | 181/291 [00:05<00:01, 76.59it/s] Loading 0: 69%|██████▉ | 202/291 [00:05<00:00, 96.14it/s] Loading 0: 76%|███████▌ | 221/291 [00:05<00:00, 112.23it/s] Loading 0: 82%|████████▏ | 240/291 [00:06<00:00, 127.39it/s] Loading 0: 90%|█████████ | 263/291 [00:06<00:00, 150.02it/s] Loading 0: 97%|█████████▋| 283/291 [00:06<00:00, 95.07it/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-6628-v1-mkmlizer: quantized model in 17.838s
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: Processed model Hastagaras/Jamet-8B-L3-MK.V-BR3 in 59.398s
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-6628-v1
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-6628-v1/config.json
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-6628-v1/special_tokens_map.json
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-6628-v1/tokenizer_config.json
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-6628-v1/tokenizer.json
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-6628-v1/flywheel_model.0.safetensors
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-jamet-8b-l3-m-6628-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-m-6628-v1-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-6628-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-m-6628-v1-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-6628-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-m-6628-v1-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-6628-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-m-6628-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: Saving duration: 0.236s
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 8.027s
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-6628-v1_reward
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-6628-v1_reward/config.json
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-6628-v1_reward/special_tokens_map.json
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-6628-v1_reward/tokenizer_config.json
hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-6628-v1_reward/reward.tensors
Job hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer completed after 165.44s with status: succeeded
Stopping job with name hastagaras-jamet-8b-l3-m-6628-v1-mkmlizer
Pipeline stage MKMLizer completed in 170.67s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-jamet-8b-l3-m-6628-v1
Waiting for inference service hastagaras-jamet-8b-l3-m-6628-v1 to be ready
Inference service hastagaras-jamet-8b-l3-m-6628-v1 ready after 40.36037611961365s
Pipeline stage ISVCDeployer completed in 48.21s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.143498182296753s
Received healthy response to inference request in 1.3417322635650635s
Received healthy response to inference request in 1.317784309387207s
Received healthy response to inference request in 1.2940564155578613s
Received healthy response to inference request in 1.2542622089385986s
5 requests
0 failed requests
5th percentile: 1.2622210502624511
10th percentile: 1.2701798915863036
20th percentile: 1.2860975742340088
30th percentile: 1.2988019943237306
40th percentile: 1.3082931518554688
50th percentile: 1.317784309387207
60th percentile: 1.3273634910583496
70th percentile: 1.3369426727294922
80th percentile: 1.5020854473114016
90th percentile: 1.8227918148040771
95th percentile: 1.9831449985504148
99th percentile: 2.1114275455474854
mean time: 1.4702666759490968
Pipeline stage StressChecker completed in 7.99s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.07s
hastagaras-jamet-8b-l3-m_6628_v1 status is now deployed due to DeploymentManager action
hastagaras-jamet-8b-l3-m_6628_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics