submission_id: arlineka-nyannyan_v4
developer_uid: arlineka
status: inactive
model_repo: arlineka/NyanNyan
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.1, 'top_p': 1.0, 'min_p': 0.08, '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|>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: 2024-05-31T23:16:42+00:00
model_name: arlineka-nyannyan_v4
model_eval_status: success
model_group: arlineka/NyanNyan
num_battles: 8728
num_wins: 4724
celo_rating: 1207.54
propriety_score: 0.6
propriety_total_count: 5.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: arlineka-nyannyan_v4
ineligible_reason: propriety_total_count < 5000
language_model: arlineka/NyanNyan
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-31
win_ratio: 0.5412465627864345
Resubmit model
Running pipeline stage MKMLizer
Starting job with name arlineka-nyannyan-v4-mkmlizer
Waiting for job on arlineka-nyannyan-v4-mkmlizer to finish
arlineka-nyannyan-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
arlineka-nyannyan-v4-mkmlizer: ║ _____ __ __ ║
arlineka-nyannyan-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
arlineka-nyannyan-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
arlineka-nyannyan-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
arlineka-nyannyan-v4-mkmlizer: ║ /___/ ║
arlineka-nyannyan-v4-mkmlizer: ║ ║
arlineka-nyannyan-v4-mkmlizer: ║ Version: 0.8.14 ║
arlineka-nyannyan-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
arlineka-nyannyan-v4-mkmlizer: ║ https://mk1.ai ║
arlineka-nyannyan-v4-mkmlizer: ║ ║
arlineka-nyannyan-v4-mkmlizer: ║ The license key for the current software has been verified as ║
arlineka-nyannyan-v4-mkmlizer: ║ belonging to: ║
arlineka-nyannyan-v4-mkmlizer: ║ ║
arlineka-nyannyan-v4-mkmlizer: ║ Chai Research Corp. ║
arlineka-nyannyan-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
arlineka-nyannyan-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
arlineka-nyannyan-v4-mkmlizer: ║ ║
arlineka-nyannyan-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
arlineka-nyannyan-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.
arlineka-nyannyan-v4-mkmlizer: warnings.warn(warning_message, FutureWarning)
arlineka-nyannyan-v4-mkmlizer: Downloaded to shared memory in 33.335s
arlineka-nyannyan-v4-mkmlizer: quantizing model to /dev/shm/model_cache
arlineka-nyannyan-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
arlineka-nyannyan-v4-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:47, 2.24s/it] Loading 0: 5%|▌ | 15/291 [00:04<01:02, 4.45it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:21, 11.82it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:11, 21.29it/s] Loading 0: 22%|██▏ | 65/291 [00:05<00:08, 25.78it/s] Loading 0: 28%|██▊ | 82/291 [00:05<00:05, 37.72it/s] Loading 0: 34%|███▍ | 100/291 [00:05<00:03, 52.70it/s] Loading 0: 40%|███▉ | 115/291 [00:05<00:02, 65.42it/s] Loading 0: 45%|████▌ | 132/291 [00:05<00:01, 81.53it/s] Loading 0: 52%|█████▏ | 150/291 [00:05<00:01, 98.71it/s] Loading 0: 57%|█████▋ | 166/291 [00:05<00:01, 77.86it/s] Loading 0: 63%|██████▎ | 184/291 [00:06<00:01, 94.66it/s] Loading 0: 69%|██████▉ | 202/291 [00:06<00:00, 110.50it/s] Loading 0: 76%|███████▌ | 220/291 [00:06<00:00, 123.56it/s] Loading 0: 82%|████████▏ | 238/291 [00:06<00:00, 135.69it/s] Loading 0: 88%|████████▊ | 256/291 [00:06<00:00, 141.97it/s] Loading 0: 94%|█████████▍| 273/291 [00:06<00:00, 94.85it/s] Loading 0: 99%|█████████▉| 288/291 [00:06<00:00, 105.18it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
arlineka-nyannyan-v4-mkmlizer: quantized model in 22.641s
arlineka-nyannyan-v4-mkmlizer: Processed model arlineka/NyanNyan in 58.425s
arlineka-nyannyan-v4-mkmlizer: creating bucket guanaco-mkml-models
arlineka-nyannyan-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
arlineka-nyannyan-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/arlineka-nyannyan-v4
arlineka-nyannyan-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/arlineka-nyannyan-v4/config.json
arlineka-nyannyan-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/arlineka-nyannyan-v4/special_tokens_map.json
arlineka-nyannyan-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/arlineka-nyannyan-v4/tokenizer_config.json
arlineka-nyannyan-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/arlineka-nyannyan-v4/tokenizer.json
arlineka-nyannyan-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/arlineka-nyannyan-v4/flywheel_model.0.safetensors
arlineka-nyannyan-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
arlineka-nyannyan-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.
arlineka-nyannyan-v4-mkmlizer: warnings.warn(
arlineka-nyannyan-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.
arlineka-nyannyan-v4-mkmlizer: warnings.warn(
arlineka-nyannyan-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.
arlineka-nyannyan-v4-mkmlizer: warnings.warn(
arlineka-nyannyan-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
arlineka-nyannyan-v4-mkmlizer: Saving duration: 0.383s
arlineka-nyannyan-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.766s
arlineka-nyannyan-v4-mkmlizer: creating bucket guanaco-reward-models
arlineka-nyannyan-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
arlineka-nyannyan-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/arlineka-nyannyan-v4_reward
arlineka-nyannyan-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/arlineka-nyannyan-v4_reward/config.json
arlineka-nyannyan-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/arlineka-nyannyan-v4_reward/special_tokens_map.json
arlineka-nyannyan-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/arlineka-nyannyan-v4_reward/tokenizer_config.json
arlineka-nyannyan-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/arlineka-nyannyan-v4_reward/vocab.json
arlineka-nyannyan-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/arlineka-nyannyan-v4_reward/merges.txt
arlineka-nyannyan-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/arlineka-nyannyan-v4_reward/tokenizer.json
arlineka-nyannyan-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/arlineka-nyannyan-v4_reward/reward.tensors
Job arlineka-nyannyan-v4-mkmlizer completed after 134.73s with status: succeeded
Stopping job with name arlineka-nyannyan-v4-mkmlizer
Pipeline stage MKMLizer completed in 138.67s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service arlineka-nyannyan-v4
Waiting for inference service arlineka-nyannyan-v4 to be ready
Inference service arlineka-nyannyan-v4 ready after 40.26912522315979s
Pipeline stage ISVCDeployer completed in 57.04s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.071775436401367s
Received healthy response to inference request in 1.346064805984497s
%s, retrying in %s seconds...
Received healthy response to inference request in 1.2715160846710205s
Received healthy response to inference request in 1.3498806953430176s
Received healthy response to inference request in 1.3022890090942383s
Received healthy response to inference request in 1.3080768585205078s
Received healthy response to inference request in 1.247255563735962s
5 requests
0 failed requests
5th percentile: 1.2521076679229737
10th percentile: 1.2569597721099854
20th percentile: 1.2666639804840087
30th percentile: 1.277670669555664
40th percentile: 1.289979839324951
50th percentile: 1.3022890090942383
60th percentile: 1.3046041488647462
70th percentile: 1.3069192886352539
80th percentile: 1.3164376258850097
90th percentile: 1.3331591606140136
95th percentile: 1.3415199279785157
99th percentile: 1.3482085418701173
mean time: 1.2958036422729493
Pipeline stage StressChecker completed in 30.57s
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
arlineka-nyannyan_v4 status is now deployed due to DeploymentManager action
arlineka-nyannyan_v4 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics