submission_id: v000000-l3-8b-poppy-moon_1166_v1
developer_uid: v000000
best_of: 16
celo_rating: 1220.29
display_name: v000000-l3-8b-poppy-moon_1166_v1
family_friendly_score: 0.0
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}
generation_params: {'temperature': 1.22, 'top_p': 0.95, 'min_p': 0.08, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_of_text|>', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
is_internal_developer: False
language_model: v000000/L3-8B-Poppy-Moonfall-C
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: v000000/L3-8B-Poppy-Moon
model_name: v000000-l3-8b-poppy-moon_1166_v1
model_num_parameters: 8030261248.0
model_repo: v000000/L3-8B-Poppy-Moonfall-C
model_size: 8B
num_battles: 7992
num_wins: 4326
ranking_group: single
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-06-12T18:53:12+00:00
us_pacific_date: 2024-06-12
win_ratio: 0.5412912912912913
Resubmit model
Running pipeline stage MKMLizer
Starting job with name v000000-l3-8b-poppy-moon-1166-v1-mkmlizer
Waiting for job on v000000-l3-8b-poppy-moon-1166-v1-mkmlizer to finish
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: ║ _____ __ __ ║
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: ║ /___/ ║
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: ║ ║
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: ║ Version: 0.8.14 ║
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: ║ https://mk1.ai ║
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: ║ ║
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: ║ The license key for the current software has been verified as ║
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: ║ belonging to: ║
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: ║ ║
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: ║ Chai Research Corp. ║
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: ║ ║
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
v000000-l3-8b-poppy-moon-1166-v1-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.
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: Downloaded to shared memory in 35.283s
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: quantizing model to /dev/shm/model_cache
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:06, 2.31s/it] Loading 0: 5%|▌ | 15/291 [00:04<01:03, 4.32it/s] Loading 0: 11%|█ | 32/291 [00:04<00:23, 11.11it/s] Loading 0: 17%|█▋ | 50/291 [00:04<00:11, 20.34it/s] Loading 0: 22%|██▏ | 64/291 [00:05<00:09, 24.59it/s] Loading 0: 27%|██▋ | 78/291 [00:05<00:06, 33.89it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:04, 48.58it/s] Loading 0: 39%|███▉ | 114/291 [00:05<00:02, 64.43it/s] Loading 0: 45%|████▌ | 131/291 [00:05<00:02, 79.67it/s] Loading 0: 51%|█████ | 149/291 [00:05<00:01, 96.37it/s] Loading 0: 57%|█████▋ | 166/291 [00:06<00:01, 74.07it/s] Loading 0: 63%|██████▎ | 184/291 [00:06<00:01, 90.22it/s] Loading 0: 69%|██████▉ | 202/291 [00:06<00:00, 104.72it/s] Loading 0: 76%|███████▌ | 220/291 [00:06<00:00, 113.14it/s] Loading 0: 81%|████████ | 235/291 [00:06<00:00, 120.06it/s] Loading 0: 86%|████████▌ | 250/291 [00:06<00:00, 123.26it/s] Loading 0: 91%|█████████▏| 266/291 [00:07<00:00, 80.11it/s] Loading 0: 97%|█████████▋| 283/291 [00:07<00:00, 95.61it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: quantized model in 23.595s
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: Processed model v000000/L3-8B-Poppy-Moonfall-C in 61.479s
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: creating bucket guanaco-mkml-models
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/v000000-l3-8b-poppy-moon-1166-v1
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/v000000-l3-8b-poppy-moon-1166-v1/special_tokens_map.json
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/v000000-l3-8b-poppy-moon-1166-v1/config.json
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/v000000-l3-8b-poppy-moon-1166-v1/tokenizer_config.json
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/v000000-l3-8b-poppy-moon-1166-v1/tokenizer.json
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/v000000-l3-8b-poppy-moon-1166-v1/flywheel_model.0.safetensors
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
v000000-l3-8b-poppy-moon-1166-v1-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.
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: warnings.warn(
v000000-l3-8b-poppy-moon-1166-v1-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.
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: warnings.warn(
v000000-l3-8b-poppy-moon-1166-v1-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.
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: warnings.warn(
v000000-l3-8b-poppy-moon-1166-v1-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()
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: return self.fget.__get__(instance, owner)()
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: Saving duration: 0.403s
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.916s
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: creating bucket guanaco-reward-models
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/v000000-l3-8b-poppy-moon-1166-v1_reward
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/v000000-l3-8b-poppy-moon-1166-v1_reward/special_tokens_map.json
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/v000000-l3-8b-poppy-moon-1166-v1_reward/vocab.json
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/v000000-l3-8b-poppy-moon-1166-v1_reward/config.json
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/v000000-l3-8b-poppy-moon-1166-v1_reward/tokenizer_config.json
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/v000000-l3-8b-poppy-moon-1166-v1_reward/merges.txt
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/v000000-l3-8b-poppy-moon-1166-v1_reward/tokenizer.json
v000000-l3-8b-poppy-moon-1166-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/v000000-l3-8b-poppy-moon-1166-v1_reward/reward.tensors
Job v000000-l3-8b-poppy-moon-1166-v1-mkmlizer completed after 93.72s with status: succeeded
Stopping job with name v000000-l3-8b-poppy-moon-1166-v1-mkmlizer
Pipeline stage MKMLizer completed in 98.14s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service v000000-l3-8b-poppy-moon-1166-v1
Waiting for inference service v000000-l3-8b-poppy-moon-1166-v1 to be ready
Inference service v000000-l3-8b-poppy-moon-1166-v1 ready after 30.20154595375061s
Pipeline stage ISVCDeployer completed in 37.80s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.239795446395874s
Received healthy response to inference request in 1.2751505374908447s
Received healthy response to inference request in 1.2851009368896484s
Received healthy response to inference request in 1.277116060256958s
Received healthy response to inference request in 1.2792909145355225s
5 requests
0 failed requests
5th percentile: 1.2755436420440673
10th percentile: 1.27593674659729
20th percentile: 1.2767229557037354
30th percentile: 1.277551031112671
40th percentile: 1.2784209728240967
50th percentile: 1.2792909145355225
60th percentile: 1.2816149234771728
70th percentile: 1.2839389324188233
80th percentile: 1.4760398387908937
90th percentile: 1.8579176425933839
95th percentile: 2.0488565444946287
99th percentile: 2.201607666015625
mean time: 1.4712907791137695
Pipeline stage StressChecker completed in 8.07s
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
v000000-l3-8b-poppy-moon_1166_v1 status is now deployed due to DeploymentManager action
v000000-l3-8b-poppy-moon_1166_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of v000000-l3-8b-poppy-moon_1166_v1
Running pipeline stage ISVCDeleter
Checking if service v000000-l3-8b-poppy-moon-1166-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.27s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key v000000-l3-8b-poppy-moon-1166-v1/config.json from bucket guanaco-mkml-models
Deleting key v000000-l3-8b-poppy-moon-1166-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key v000000-l3-8b-poppy-moon-1166-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key v000000-l3-8b-poppy-moon-1166-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key v000000-l3-8b-poppy-moon-1166-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key v000000-l3-8b-poppy-moon-1166-v1_reward/config.json from bucket guanaco-reward-models
Deleting key v000000-l3-8b-poppy-moon-1166-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key v000000-l3-8b-poppy-moon-1166-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key v000000-l3-8b-poppy-moon-1166-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key v000000-l3-8b-poppy-moon-1166-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key v000000-l3-8b-poppy-moon-1166-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key v000000-l3-8b-poppy-moon-1166-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.05s
v000000-l3-8b-poppy-moon_1166_v1 status is now torndown due to DeploymentManager action