submission_id: hastagaras-hexp0br8bl3_v2
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/hexp0br8bl3
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.05, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 60, '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", '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: 2024-06-13T03:01:15+00:00
model_name: br-kw
model_eval_status: success
model_group: Hastagaras/hexp0br8bl3
num_battles: 28408
num_wins: 15548
celo_rating: 1213.37
propriety_score: 0.6637760158572844
propriety_total_count: 12108.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: br-kw
ineligible_reason: None
language_model: Hastagaras/hexp0br8bl3
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-12
win_ratio: 0.5473106167276823
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-hexp0br8bl3-v2-mkmlizer
Waiting for job on hastagaras-hexp0br8bl3-v2-mkmlizer to finish
hastagaras-hexp0br8bl3-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-hexp0br8bl3-v2-mkmlizer: ║ _____ __ __ ║
hastagaras-hexp0br8bl3-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-hexp0br8bl3-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-hexp0br8bl3-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-hexp0br8bl3-v2-mkmlizer: ║ /___/ ║
hastagaras-hexp0br8bl3-v2-mkmlizer: ║ ║
hastagaras-hexp0br8bl3-v2-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-hexp0br8bl3-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-hexp0br8bl3-v2-mkmlizer: ║ https://mk1.ai ║
hastagaras-hexp0br8bl3-v2-mkmlizer: ║ ║
hastagaras-hexp0br8bl3-v2-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-hexp0br8bl3-v2-mkmlizer: ║ belonging to: ║
hastagaras-hexp0br8bl3-v2-mkmlizer: ║ ║
hastagaras-hexp0br8bl3-v2-mkmlizer: ║ Chai Research Corp. ║
hastagaras-hexp0br8bl3-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-hexp0br8bl3-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-hexp0br8bl3-v2-mkmlizer: ║ ║
hastagaras-hexp0br8bl3-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-hexp0br8bl3-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-hexp0br8bl3-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-hexp0br8bl3-v2-mkmlizer: Downloaded to shared memory in 21.253s
hastagaras-hexp0br8bl3-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-hexp0br8bl3-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-hexp0br8bl3-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:30, 2.39s/it] Loading 0: 5%|▌ | 15/291 [00:04<01:06, 4.16it/s] Loading 0: 11%|█ | 32/291 [00:04<00:24, 10.73it/s] Loading 0: 17%|█▋ | 49/291 [00:05<00:12, 19.25it/s] Loading 0: 22%|██▏ | 63/291 [00:05<00:09, 23.14it/s] Loading 0: 27%|██▋ | 78/291 [00:05<00:06, 32.78it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:04, 46.73it/s] Loading 0: 39%|███▉ | 113/291 [00:05<00:02, 61.60it/s] Loading 0: 45%|████▍ | 130/291 [00:05<00:02, 77.64it/s] Loading 0: 50%|████▉ | 145/291 [00:06<00:01, 90.26it/s] Loading 0: 55%|█████▍ | 160/291 [00:06<00:01, 100.87it/s] Loading 0: 60%|██████ | 175/291 [00:06<00:01, 69.33it/s] Loading 0: 65%|██████▌ | 190/291 [00:06<00:01, 82.48it/s] Loading 0: 70%|███████ | 204/291 [00:06<00:00, 92.94it/s] Loading 0: 76%|███████▋ | 222/291 [00:06<00:00, 108.68it/s] Loading 0: 82%|████████▏ | 240/291 [00:06<00:00, 121.14it/s] Loading 0: 89%|████████▊ | 258/291 [00:07<00:00, 131.39it/s] Loading 0: 94%|█████████▍| 273/291 [00:07<00:00, 87.26it/s] Loading 0: 98%|█████████▊| 285/291 [00:07<00:00, 92.98it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-hexp0br8bl3-v2-mkmlizer: quantized model in 24.208s
hastagaras-hexp0br8bl3-v2-mkmlizer: Processed model Hastagaras/hexp0br8bl3 in 48.105s
hastagaras-hexp0br8bl3-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-hexp0br8bl3-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-hexp0br8bl3-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-hexp0br8bl3-v2
hastagaras-hexp0br8bl3-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-hexp0br8bl3-v2/special_tokens_map.json
hastagaras-hexp0br8bl3-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-hexp0br8bl3-v2/config.json
hastagaras-hexp0br8bl3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-hexp0br8bl3-v2/tokenizer_config.json
hastagaras-hexp0br8bl3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-hexp0br8bl3-v2/tokenizer.json
hastagaras-hexp0br8bl3-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-hexp0br8bl3-v2/flywheel_model.0.safetensors
hastagaras-hexp0br8bl3-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-hexp0br8bl3-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-hexp0br8bl3-v2-mkmlizer: warnings.warn(
hastagaras-hexp0br8bl3-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-hexp0br8bl3-v2-mkmlizer: warnings.warn(
hastagaras-hexp0br8bl3-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-hexp0br8bl3-v2-mkmlizer: warnings.warn(
hastagaras-hexp0br8bl3-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-hexp0br8bl3-v2-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-hexp0br8bl3-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-hexp0br8bl3-v2-mkmlizer: Saving duration: 0.410s
hastagaras-hexp0br8bl3-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.741s
hastagaras-hexp0br8bl3-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-hexp0br8bl3-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-hexp0br8bl3-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-hexp0br8bl3-v2_reward
hastagaras-hexp0br8bl3-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-hexp0br8bl3-v2_reward/config.json
hastagaras-hexp0br8bl3-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-hexp0br8bl3-v2_reward/special_tokens_map.json
hastagaras-hexp0br8bl3-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-hexp0br8bl3-v2_reward/merges.txt
hastagaras-hexp0br8bl3-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-hexp0br8bl3-v2_reward/vocab.json
hastagaras-hexp0br8bl3-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-hexp0br8bl3-v2_reward/tokenizer_config.json
hastagaras-hexp0br8bl3-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-hexp0br8bl3-v2_reward/tokenizer.json
hastagaras-hexp0br8bl3-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-hexp0br8bl3-v2_reward/reward.tensors
Job hastagaras-hexp0br8bl3-v2-mkmlizer completed after 73.02s with status: succeeded
Stopping job with name hastagaras-hexp0br8bl3-v2-mkmlizer
Pipeline stage MKMLizer completed in 74.05s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-hexp0br8bl3-v2
Waiting for inference service hastagaras-hexp0br8bl3-v2 to be ready
Inference service hastagaras-hexp0br8bl3-v2 ready after 50.26874375343323s
Pipeline stage ISVCDeployer completed in 56.36s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.16048264503479s
Received healthy response to inference request in 1.3545384407043457s
Received healthy response to inference request in 1.313441514968872s
Received healthy response to inference request in 1.283982515335083s
Received healthy response to inference request in 1.3626415729522705s
5 requests
0 failed requests
5th percentile: 1.2898743152618408
10th percentile: 1.2957661151885986
20th percentile: 1.3075497150421143
30th percentile: 1.3216609001159667
40th percentile: 1.3380996704101562
50th percentile: 1.3545384407043457
60th percentile: 1.3577796936035156
70th percentile: 1.3610209465026855
80th percentile: 1.5222097873687745
90th percentile: 1.8413462162017824
95th percentile: 2.0009144306182858
99th percentile: 2.1285690021514894
mean time: 1.4950173377990723
Pipeline stage StressChecker completed in 8.11s
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-hexp0br8bl3_v2 status is now deployed due to DeploymentManager action
hastagaras-hexp0br8bl3_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics