submission_id: hastagaras-bu8bl3-x-x_v3
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/bu8bl3-x_x
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.07, 'top_p': 0.95, 'min_p': 0.06, 'top_k': 65, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], '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: 2024-06-14T06:24:31+00:00
model_name: x_x3
model_eval_status: success
model_group: Hastagaras/bu8bl3-x_x
num_battles: 19351
num_wins: 10644
celo_rating: 1211.14
propriety_score: 0.6655640874187833
propriety_total_count: 8465.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: x_x3
ineligible_reason: None
language_model: Hastagaras/bu8bl3-x_x
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-13
win_ratio: 0.5500490930701256
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-bu8bl3-x-x-v3-mkmlizer
Waiting for job on hastagaras-bu8bl3-x-x-v3-mkmlizer to finish
hastagaras-bu8bl3-x-x-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-bu8bl3-x-x-v3-mkmlizer: ║ _____ __ __ ║
hastagaras-bu8bl3-x-x-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-bu8bl3-x-x-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-bu8bl3-x-x-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-bu8bl3-x-x-v3-mkmlizer: ║ /___/ ║
hastagaras-bu8bl3-x-x-v3-mkmlizer: ║ ║
hastagaras-bu8bl3-x-x-v3-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-bu8bl3-x-x-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-bu8bl3-x-x-v3-mkmlizer: ║ https://mk1.ai ║
hastagaras-bu8bl3-x-x-v3-mkmlizer: ║ ║
hastagaras-bu8bl3-x-x-v3-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-bu8bl3-x-x-v3-mkmlizer: ║ belonging to: ║
hastagaras-bu8bl3-x-x-v3-mkmlizer: ║ ║
hastagaras-bu8bl3-x-x-v3-mkmlizer: ║ Chai Research Corp. ║
hastagaras-bu8bl3-x-x-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-bu8bl3-x-x-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-bu8bl3-x-x-v3-mkmlizer: ║ ║
hastagaras-bu8bl3-x-x-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-bu8bl3-x-x-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-bu8bl3-x-x-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-bu8bl3-x-x-v3-mkmlizer: Downloaded to shared memory in 75.765s
hastagaras-bu8bl3-x-x-v3-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-bu8bl3-x-x-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-bu8bl3-x-x-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:02, 118.27it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:02, 124.16it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:01, 128.82it/s] Loading 0: 20%|█▉ | 57/291 [00:00<00:01, 137.64it/s] Loading 0: 24%|██▍ | 71/291 [00:00<00:01, 133.48it/s] Loading 0: 29%|██▉ | 85/291 [00:00<00:03, 65.87it/s] Loading 0: 35%|███▌ | 102/291 [00:01<00:02, 82.97it/s] Loading 0: 39%|███▉ | 114/291 [00:01<00:01, 89.96it/s] Loading 0: 45%|████▍ | 130/291 [00:01<00:01, 102.99it/s] Loading 0: 51%|█████ | 147/291 [00:01<00:01, 115.31it/s] Loading 0: 55%|█████▌ | 161/291 [00:01<00:01, 117.80it/s] Loading 0: 60%|██████ | 176/291 [00:01<00:00, 125.05it/s] Loading 0: 65%|██████▌ | 190/291 [00:01<00:01, 78.88it/s] Loading 0: 70%|██████▉ | 203/291 [00:02<00:01, 85.82it/s] Loading 0: 76%|███████▌ | 220/291 [00:02<00:00, 100.54it/s] Loading 0: 81%|████████▏ | 237/291 [00:02<00:00, 112.85it/s] Loading 0: 86%|████████▌ | 250/291 [00:02<00:00, 116.24it/s] Loading 0: 91%|█████████ | 265/291 [00:02<00:00, 121.50it/s] Loading 0: 97%|█████████▋| 281/291 [00:02<00:00, 127.77it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-bu8bl3-x-x-v3-mkmlizer: quantized model in 23.263s
hastagaras-bu8bl3-x-x-v3-mkmlizer: Processed model Hastagaras/bu8bl3-x_x in 101.560s
hastagaras-bu8bl3-x-x-v3-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-bu8bl3-x-x-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-bu8bl3-x-x-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-bu8bl3-x-x-v3
hastagaras-bu8bl3-x-x-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-bu8bl3-x-x-v3/config.json
hastagaras-bu8bl3-x-x-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-bu8bl3-x-x-v3/tokenizer_config.json
hastagaras-bu8bl3-x-x-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-bu8bl3-x-x-v3/special_tokens_map.json
hastagaras-bu8bl3-x-x-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-bu8bl3-x-x-v3/tokenizer.json
hastagaras-bu8bl3-x-x-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-bu8bl3-x-x-v3/flywheel_model.0.safetensors
hastagaras-bu8bl3-x-x-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-bu8bl3-x-x-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-bu8bl3-x-x-v3-mkmlizer: warnings.warn(
hastagaras-bu8bl3-x-x-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-bu8bl3-x-x-v3-mkmlizer: warnings.warn(
hastagaras-bu8bl3-x-x-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-bu8bl3-x-x-v3-mkmlizer: warnings.warn(
hastagaras-bu8bl3-x-x-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-bu8bl3-x-x-v3-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-bu8bl3-x-x-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-bu8bl3-x-x-v3-mkmlizer: Saving duration: 0.385s
hastagaras-bu8bl3-x-x-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.372s
hastagaras-bu8bl3-x-x-v3-mkmlizer: creating bucket guanaco-reward-models
hastagaras-bu8bl3-x-x-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-bu8bl3-x-x-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-bu8bl3-x-x-v3_reward
hastagaras-bu8bl3-x-x-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-bu8bl3-x-x-v3_reward/config.json
hastagaras-bu8bl3-x-x-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-bu8bl3-x-x-v3_reward/vocab.json
hastagaras-bu8bl3-x-x-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-bu8bl3-x-x-v3_reward/special_tokens_map.json
hastagaras-bu8bl3-x-x-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-bu8bl3-x-x-v3_reward/merges.txt
hastagaras-bu8bl3-x-x-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-bu8bl3-x-x-v3_reward/tokenizer_config.json
hastagaras-bu8bl3-x-x-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-bu8bl3-x-x-v3_reward/tokenizer.json
hastagaras-bu8bl3-x-x-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-bu8bl3-x-x-v3_reward/reward.tensors
Job hastagaras-bu8bl3-x-x-v3-mkmlizer completed after 133.82s with status: succeeded
Stopping job with name hastagaras-bu8bl3-x-x-v3-mkmlizer
Pipeline stage MKMLizer completed in 137.80s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-bu8bl3-x-x-v3
Waiting for inference service hastagaras-bu8bl3-x-x-v3 to be ready
Inference service hastagaras-bu8bl3-x-x-v3 ready after 60.29649519920349s
Pipeline stage ISVCDeployer completed in 67.52s
Running pipeline stage StressChecker
Received healthy response to inference request in 6.759638547897339s
Received healthy response to inference request in 1.3406405448913574s
Received healthy response to inference request in 1.3045556545257568s
Received healthy response to inference request in 1.266819953918457s
Received healthy response to inference request in 1.4650382995605469s
5 requests
0 failed requests
5th percentile: 1.274367094039917
10th percentile: 1.281914234161377
20th percentile: 1.2970085144042969
30th percentile: 1.311772632598877
40th percentile: 1.326206588745117
50th percentile: 1.3406405448913574
60th percentile: 1.3903996467590332
70th percentile: 1.440158748626709
80th percentile: 2.5239583492279065
90th percentile: 4.641798448562623
95th percentile: 5.700718498229979
99th percentile: 6.547854537963867
mean time: 2.4273386001586914
Pipeline stage StressChecker completed in 12.73s
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-bu8bl3-x-x_v3 status is now deployed due to DeploymentManager action
hastagaras-bu8bl3-x-x_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics