submission_id: hastagaras-hexp0br8bl3_v3
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/hexp0br8bl3
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.35, 'top_p': 1.0, 'min_p': 0.15, 'top_k': 35, '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: 2024-06-13T03:13:40+00:00
model_name: br-kw
model_eval_status: success
model_group: Hastagaras/hexp0br8bl3
num_battles: 27997
num_wins: 15245
celo_rating: 1211.28
propriety_score: 0.6684153551503039
propriety_total_count: 12009.0
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: 0.5445226274243669
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-hexp0br8bl3-v3-mkmlizer
Waiting for job on hastagaras-hexp0br8bl3-v3-mkmlizer to finish
hastagaras-hexp0br8bl3-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-hexp0br8bl3-v3-mkmlizer: ║ _____ __ __ ║
hastagaras-hexp0br8bl3-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-hexp0br8bl3-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-hexp0br8bl3-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-hexp0br8bl3-v3-mkmlizer: ║ /___/ ║
hastagaras-hexp0br8bl3-v3-mkmlizer: ║ ║
hastagaras-hexp0br8bl3-v3-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-hexp0br8bl3-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-hexp0br8bl3-v3-mkmlizer: ║ https://mk1.ai ║
hastagaras-hexp0br8bl3-v3-mkmlizer: ║ ║
hastagaras-hexp0br8bl3-v3-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-hexp0br8bl3-v3-mkmlizer: ║ belonging to: ║
hastagaras-hexp0br8bl3-v3-mkmlizer: ║ ║
hastagaras-hexp0br8bl3-v3-mkmlizer: ║ Chai Research Corp. ║
hastagaras-hexp0br8bl3-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-hexp0br8bl3-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-hexp0br8bl3-v3-mkmlizer: ║ ║
hastagaras-hexp0br8bl3-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-hexp0br8bl3-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-hexp0br8bl3-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-hexp0br8bl3-v3-mkmlizer: Downloaded to shared memory in 19.548s
hastagaras-hexp0br8bl3-v3-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-hexp0br8bl3-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-hexp0br8bl3-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:46, 2.24s/it] Loading 0: 5%|▌ | 15/291 [00:04<01:01, 4.45it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:21, 11.85it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:11, 21.32it/s] Loading 0: 22%|██▏ | 65/291 [00:05<00:08, 25.63it/s] Loading 0: 27%|██▋ | 78/291 [00:05<00:06, 34.23it/s] Loading 0: 32%|███▏ | 94/291 [00:05<00:04, 47.32it/s] Loading 0: 37%|███▋ | 107/291 [00:05<00:03, 57.91it/s] Loading 0: 42%|████▏ | 123/291 [00:05<00:02, 72.39it/s] Loading 0: 48%|████▊ | 139/291 [00:05<00:01, 87.43it/s] Loading 0: 53%|█████▎ | 153/291 [00:05<00:01, 97.21it/s] Loading 0: 57%|█████▋ | 167/291 [00:06<00:01, 68.73it/s] Loading 0: 64%|██████▎ | 185/291 [00:06<00:01, 85.90it/s] Loading 0: 70%|██████▉ | 203/291 [00:06<00:00, 101.67it/s] Loading 0: 76%|███████▌ | 221/291 [00:06<00:00, 114.72it/s] Loading 0: 82%|████████▏ | 239/291 [00:06<00:00, 126.25it/s] Loading 0: 88%|████████▊ | 257/291 [00:06<00:00, 135.89it/s] Loading 0: 94%|█████████▍| 273/291 [00:07<00:00, 87.72it/s] Loading 0: 99%|█████████▉| 288/291 [00:07<00:00, 98.64it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-hexp0br8bl3-v3-mkmlizer: quantized model in 23.396s
hastagaras-hexp0br8bl3-v3-mkmlizer: Processed model Hastagaras/hexp0br8bl3 in 45.634s
hastagaras-hexp0br8bl3-v3-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-hexp0br8bl3-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-hexp0br8bl3-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-hexp0br8bl3-v3
hastagaras-hexp0br8bl3-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-hexp0br8bl3-v3/tokenizer_config.json
hastagaras-hexp0br8bl3-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-hexp0br8bl3-v3/special_tokens_map.json
hastagaras-hexp0br8bl3-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-hexp0br8bl3-v3/config.json
hastagaras-hexp0br8bl3-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-hexp0br8bl3-v3/tokenizer.json
hastagaras-hexp0br8bl3-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-hexp0br8bl3-v3/flywheel_model.0.safetensors
hastagaras-hexp0br8bl3-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-hexp0br8bl3-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-hexp0br8bl3-v3-mkmlizer: warnings.warn(
hastagaras-hexp0br8bl3-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-hexp0br8bl3-v3-mkmlizer: warnings.warn(
hastagaras-hexp0br8bl3-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-hexp0br8bl3-v3-mkmlizer: warnings.warn(
hastagaras-hexp0br8bl3-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-hexp0br8bl3-v3-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-hexp0br8bl3-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-hexp0br8bl3-v3-mkmlizer: Saving duration: 0.405s
hastagaras-hexp0br8bl3-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.934s
hastagaras-hexp0br8bl3-v3-mkmlizer: creating bucket guanaco-reward-models
hastagaras-hexp0br8bl3-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-hexp0br8bl3-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-hexp0br8bl3-v3_reward
hastagaras-hexp0br8bl3-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-hexp0br8bl3-v3_reward/special_tokens_map.json
hastagaras-hexp0br8bl3-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-hexp0br8bl3-v3_reward/config.json
hastagaras-hexp0br8bl3-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-hexp0br8bl3-v3_reward/tokenizer_config.json
hastagaras-hexp0br8bl3-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-hexp0br8bl3-v3_reward/vocab.json
hastagaras-hexp0br8bl3-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-hexp0br8bl3-v3_reward/merges.txt
hastagaras-hexp0br8bl3-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-hexp0br8bl3-v3_reward/tokenizer.json
hastagaras-hexp0br8bl3-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-hexp0br8bl3-v3_reward/reward.tensors
Job hastagaras-hexp0br8bl3-v3-mkmlizer completed after 72.84s with status: succeeded
Stopping job with name hastagaras-hexp0br8bl3-v3-mkmlizer
Pipeline stage MKMLizer completed in 76.15s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-hexp0br8bl3-v3
Waiting for inference service hastagaras-hexp0br8bl3-v3 to be ready
Inference service hastagaras-hexp0br8bl3-v3 ready after 221.22340369224548s
Pipeline stage ISVCDeployer completed in 228.61s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.289067268371582s
Received healthy response to inference request in 1.371025562286377s
Received healthy response to inference request in 1.350215196609497s
Received healthy response to inference request in 1.2982468605041504s
Received healthy response to inference request in 1.3987393379211426s
5 requests
0 failed requests
5th percentile: 1.3086405277252198
10th percentile: 1.3190341949462892
20th percentile: 1.3398215293884277
30th percentile: 1.354377269744873
40th percentile: 1.362701416015625
50th percentile: 1.371025562286377
60th percentile: 1.3821110725402832
70th percentile: 1.3931965827941895
80th percentile: 1.5768049240112307
90th percentile: 1.9329360961914064
95th percentile: 2.111001682281494
99th percentile: 2.2534541511535644
mean time: 1.5414588451385498
Pipeline stage StressChecker completed in 8.42s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-hexp0br8bl3_v3 status is now deployed due to DeploymentManager action
hastagaras-hexp0br8bl3_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics