submission_id: hastagaras-anjrit_v5
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/anjrit
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.0, '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|>{bot_name}<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>{user_name}<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>{bot_name}<|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: 2024-05-29T06:57:41+00:00
model_name: ins-name
model_eval_status: success
model_group: Hastagaras/anjrit
num_battles: 11051
num_wins: 5951
celo_rating: 1202.1
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: ins-name
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/anjrit
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-28
win_ratio: 0.5385033028685187
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-anjrit-v5-mkmlizer
Waiting for job on hastagaras-anjrit-v5-mkmlizer to finish
hastagaras-anjrit-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-anjrit-v5-mkmlizer: ║ _____ __ __ ║
hastagaras-anjrit-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-anjrit-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-anjrit-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-anjrit-v5-mkmlizer: ║ /___/ ║
hastagaras-anjrit-v5-mkmlizer: ║ ║
hastagaras-anjrit-v5-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-anjrit-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-anjrit-v5-mkmlizer: ║ https://mk1.ai ║
hastagaras-anjrit-v5-mkmlizer: ║ ║
hastagaras-anjrit-v5-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-anjrit-v5-mkmlizer: ║ belonging to: ║
hastagaras-anjrit-v5-mkmlizer: ║ ║
hastagaras-anjrit-v5-mkmlizer: ║ Chai Research Corp. ║
hastagaras-anjrit-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-anjrit-v5-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-anjrit-v5-mkmlizer: ║ ║
hastagaras-anjrit-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-anjrit-v5-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-anjrit-v5-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-anjrit-v5-mkmlizer: Downloaded to shared memory in 18.123s
hastagaras-anjrit-v5-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-anjrit-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-anjrit-v5-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:03, 2.29s/it] Loading 0: 5%|▌ | 15/291 [00:04<01:03, 4.34it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:22, 11.54it/s] Loading 0: 17%|█▋ | 50/291 [00:04<00:11, 20.32it/s] Loading 0: 22%|██▏ | 64/291 [00:05<00:09, 24.45it/s] Loading 0: 27%|██▋ | 78/291 [00:05<00:06, 33.81it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:04, 48.47it/s] Loading 0: 39%|███▉ | 114/291 [00:05<00:02, 64.38it/s] Loading 0: 45%|████▌ | 132/291 [00:05<00:01, 80.77it/s] Loading 0: 51%|█████ | 149/291 [00:05<00:01, 96.14it/s] Loading 0: 57%|█████▋ | 166/291 [00:06<00:01, 74.32it/s] Loading 0: 63%|██████▎ | 184/291 [00:06<00:01, 89.79it/s] Loading 0: 69%|██████▉ | 202/291 [00:06<00:00, 103.69it/s] Loading 0: 76%|███████▌ | 220/291 [00:06<00:00, 117.56it/s] Loading 0: 82%|████████▏ | 238/291 [00:06<00:00, 128.83it/s] Loading 0: 88%|████████▊ | 256/291 [00:06<00:00, 138.51it/s] Loading 0: 93%|█████████▎| 272/291 [00:07<00:00, 90.29it/s] Loading 0: 98%|█████████▊| 285/291 [00:07<00:00, 97.50it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-anjrit-v5-mkmlizer: quantized model in 23.305s
hastagaras-anjrit-v5-mkmlizer: Processed model Hastagaras/anjrit in 43.975s
hastagaras-anjrit-v5-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-anjrit-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-anjrit-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-anjrit-v5
hastagaras-anjrit-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-anjrit-v5/config.json
hastagaras-anjrit-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-anjrit-v5/special_tokens_map.json
hastagaras-anjrit-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-anjrit-v5/tokenizer_config.json
hastagaras-anjrit-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-anjrit-v5/tokenizer.json
hastagaras-anjrit-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-anjrit-v5/flywheel_model.0.safetensors
hastagaras-anjrit-v5-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-anjrit-v5-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-anjrit-v5-mkmlizer: warnings.warn(
hastagaras-anjrit-v5-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-anjrit-v5-mkmlizer: warnings.warn(
hastagaras-anjrit-v5-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-anjrit-v5-mkmlizer: warnings.warn(
hastagaras-anjrit-v5-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-anjrit-v5-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-anjrit-v5-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-anjrit-v5-mkmlizer: Saving duration: 0.388s
hastagaras-anjrit-v5-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.172s
hastagaras-anjrit-v5-mkmlizer: creating bucket guanaco-reward-models
hastagaras-anjrit-v5-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-anjrit-v5-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-anjrit-v5_reward
hastagaras-anjrit-v5-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-anjrit-v5_reward/config.json
hastagaras-anjrit-v5-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-anjrit-v5_reward/tokenizer_config.json
hastagaras-anjrit-v5-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-anjrit-v5_reward/merges.txt
hastagaras-anjrit-v5-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-anjrit-v5_reward/special_tokens_map.json
hastagaras-anjrit-v5-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-anjrit-v5_reward/vocab.json
hastagaras-anjrit-v5-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-anjrit-v5_reward/tokenizer.json
hastagaras-anjrit-v5-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-anjrit-v5_reward/reward.tensors
Job hastagaras-anjrit-v5-mkmlizer completed after 72.67s with status: succeeded
Stopping job with name hastagaras-anjrit-v5-mkmlizer
Pipeline stage MKMLizer completed in 76.91s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-anjrit-v5
Waiting for inference service hastagaras-anjrit-v5 to be ready
Inference service hastagaras-anjrit-v5 ready after 40.199554204940796s
Pipeline stage ISVCDeployer completed in 47.47s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.114224910736084s
Received healthy response to inference request in 1.3560841083526611s
Received healthy response to inference request in 1.299471378326416s
Received healthy response to inference request in 1.2943594455718994s
Received healthy response to inference request in 1.26310396194458s
5 requests
0 failed requests
5th percentile: 1.269355058670044
10th percentile: 1.2756061553955078
20th percentile: 1.2881083488464355
30th percentile: 1.2953818321228028
40th percentile: 1.2974266052246093
50th percentile: 1.299471378326416
60th percentile: 1.3221164703369142
70th percentile: 1.344761562347412
80th percentile: 1.5077122688293458
90th percentile: 1.810968589782715
95th percentile: 1.9625967502593993
99th percentile: 2.083899278640747
mean time: 1.465448760986328
Pipeline stage StressChecker completed in 7.88s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.02s
Running M-Eval for topic stay_in_character
hastagaras-anjrit_v5 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-anjrit_v5 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics