submission_id: hastagaras-anjrit_v4
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/anjrit
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.8, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 40, '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': "{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}
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: 2024-05-29T02:52:04+00:00
model_name: no-format
model_eval_status: success
model_group: Hastagaras/anjrit
num_battles: 9656
num_wins: 5317
celo_rating: 1212.57
safety_score: 0.79
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: no-format
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: 0.550642087821044
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-anjrit-v4-mkmlizer
Waiting for job on hastagaras-anjrit-v4-mkmlizer to finish
hastagaras-anjrit-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-anjrit-v4-mkmlizer: ║ _____ __ __ ║
hastagaras-anjrit-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-anjrit-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-anjrit-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-anjrit-v4-mkmlizer: ║ /___/ ║
hastagaras-anjrit-v4-mkmlizer: ║ ║
hastagaras-anjrit-v4-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-anjrit-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-anjrit-v4-mkmlizer: ║ https://mk1.ai ║
hastagaras-anjrit-v4-mkmlizer: ║ ║
hastagaras-anjrit-v4-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-anjrit-v4-mkmlizer: ║ belonging to: ║
hastagaras-anjrit-v4-mkmlizer: ║ ║
hastagaras-anjrit-v4-mkmlizer: ║ Chai Research Corp. ║
hastagaras-anjrit-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-anjrit-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-anjrit-v4-mkmlizer: ║ ║
hastagaras-anjrit-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-anjrit-v4-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-v4-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-anjrit-v4-mkmlizer: Downloaded to shared memory in 16.790s
hastagaras-anjrit-v4-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-anjrit-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-anjrit-v4-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:41, 2.22s/it] Loading 0: 5%|▌ | 16/291 [00:04<00:57, 4.80it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:21, 11.79it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:11, 21.32it/s] Loading 0: 22%|██▏ | 65/291 [00:05<00:08, 25.81it/s] Loading 0: 27%|██▋ | 79/291 [00:05<00:05, 35.38it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:03, 49.40it/s] Loading 0: 39%|███▉ | 113/291 [00:05<00:02, 64.89it/s] Loading 0: 45%|████▌ | 131/291 [00:05<00:01, 81.43it/s] Loading 0: 51%|█████ | 149/291 [00:05<00:01, 96.73it/s] Loading 0: 57%|█████▋ | 166/291 [00:05<00:01, 74.45it/s] Loading 0: 63%|██████▎ | 184/291 [00:06<00:01, 89.48it/s] Loading 0: 69%|██████▉ | 202/291 [00:06<00:00, 104.59it/s] Loading 0: 76%|███████▌ | 220/291 [00:06<00:00, 118.23it/s] Loading 0: 82%|████████▏ | 238/291 [00:06<00:00, 129.15it/s] Loading 0: 88%|████████▊ | 256/291 [00:06<00:00, 138.18it/s] Loading 0: 93%|█████████▎| 272/291 [00:06<00:00, 86.44it/s] Loading 0: 98%|█████████▊| 286/291 [00:06<00:00, 95.91it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-anjrit-v4-mkmlizer: quantized model in 22.748s
hastagaras-anjrit-v4-mkmlizer: Processed model Hastagaras/anjrit in 42.110s
hastagaras-anjrit-v4-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-anjrit-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-anjrit-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-anjrit-v4
hastagaras-anjrit-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-anjrit-v4/config.json
hastagaras-anjrit-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-anjrit-v4/special_tokens_map.json
hastagaras-anjrit-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-anjrit-v4/tokenizer_config.json
hastagaras-anjrit-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-anjrit-v4/tokenizer.json
hastagaras-anjrit-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-anjrit-v4/flywheel_model.0.safetensors
hastagaras-anjrit-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-anjrit-v4-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-v4-mkmlizer: warnings.warn(
hastagaras-anjrit-v4-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-v4-mkmlizer: warnings.warn(
hastagaras-anjrit-v4-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-v4-mkmlizer: warnings.warn(
hastagaras-anjrit-v4-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-v4-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-anjrit-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-anjrit-v4-mkmlizer: Saving duration: 0.388s
hastagaras-anjrit-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.131s
hastagaras-anjrit-v4-mkmlizer: creating bucket guanaco-reward-models
hastagaras-anjrit-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-anjrit-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-anjrit-v4_reward
hastagaras-anjrit-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-anjrit-v4_reward/config.json
hastagaras-anjrit-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-anjrit-v4_reward/special_tokens_map.json
hastagaras-anjrit-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-anjrit-v4_reward/merges.txt
hastagaras-anjrit-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-anjrit-v4_reward/tokenizer_config.json
hastagaras-anjrit-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-anjrit-v4_reward/vocab.json
hastagaras-anjrit-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-anjrit-v4_reward/tokenizer.json
hastagaras-anjrit-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-anjrit-v4_reward/reward.tensors
Job hastagaras-anjrit-v4-mkmlizer completed after 73.01s with status: succeeded
Stopping job with name hastagaras-anjrit-v4-mkmlizer
Pipeline stage MKMLizer completed in 77.40s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-anjrit-v4
Waiting for inference service hastagaras-anjrit-v4 to be ready
Inference service hastagaras-anjrit-v4 ready after 40.211419343948364s
Pipeline stage ISVCDeployer completed in 47.73s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2020468711853027s
Received healthy response to inference request in 1.3668882846832275s
Received healthy response to inference request in 1.263023853302002s
Received healthy response to inference request in 1.2642147541046143s
Received healthy response to inference request in 1.2539472579956055s
5 requests
0 failed requests
5th percentile: 1.2557625770568848
10th percentile: 1.257577896118164
20th percentile: 1.2612085342407227
30th percentile: 1.2632620334625244
40th percentile: 1.2637383937835693
50th percentile: 1.2642147541046143
60th percentile: 1.3052841663360595
70th percentile: 1.346353578567505
80th percentile: 1.5339200019836428
90th percentile: 1.8679834365844727
95th percentile: 2.0350151538848875
99th percentile: 2.16864052772522
mean time: 1.4700242042541505
Pipeline stage StressChecker completed in 7.94s
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-anjrit_v4 status is now deployed due to DeploymentManager action
hastagaras-anjrit_v4 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics