developer_uid: Hastagaras
submission_id: hastagaras-yirp-9b-test_v3
model_name: yipyipREALLYBAD
model_group: Hastagaras/YIRP-9B-TEST
status: torndown
timestamp: 2024-05-23T05:51:18+00:00
num_battles: 12535
num_wins: 5516
celo_rating: 1126.17
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/YIRP-9B-TEST
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 8829407232.0
best_of: 8
max_input_tokens: 512
max_output_tokens: 64
display_name: yipyipREALLYBAD
is_internal_developer: False
language_model: Hastagaras/YIRP-9B-TEST
model_size: 9B
ranking_group: single
us_pacific_date: 2024-05-22
win_ratio: 0.44004786597526924
generation_params: {'temperature': 1.05, 'top_p': 0.95, 'min_p': 0.1, 'top_k': 200, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|im_end|>'], 'max_input_tokens': 512, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "<|im_start|>system\nYou're {bot_name} in this roleplay scenario. Your actions should be wrapped in asterisks (*).\n\nPersona of {bot_name}: {memory}\n\n", 'prompt_template': 'Dialogue Example: {prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', 'truncate_by_message': False}
model_eval_status: success
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'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-yirp-9b-test-v3-mkmlizer
Waiting for job on hastagaras-yirp-9b-test-v3-mkmlizer to finish
Stopping job with name hastagaras-yirp-9b-test-v3-mkmlizer
%s, retrying in %s seconds...
Starting job with name hastagaras-yirp-9b-test-v3-mkmlizer
Waiting for job on hastagaras-yirp-9b-test-v3-mkmlizer to finish
Retrying (%r) after connection broken by '%r': %s
hastagaras-yirp-9b-test-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-yirp-9b-test-v3-mkmlizer: ║ _____ __ __ ║
hastagaras-yirp-9b-test-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-yirp-9b-test-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-yirp-9b-test-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-yirp-9b-test-v3-mkmlizer: ║ /___/ ║
hastagaras-yirp-9b-test-v3-mkmlizer: ║ ║
hastagaras-yirp-9b-test-v3-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-yirp-9b-test-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-yirp-9b-test-v3-mkmlizer: ║ https://mk1.ai ║
hastagaras-yirp-9b-test-v3-mkmlizer: ║ ║
hastagaras-yirp-9b-test-v3-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-yirp-9b-test-v3-mkmlizer: ║ belonging to: ║
hastagaras-yirp-9b-test-v3-mkmlizer: ║ ║
hastagaras-yirp-9b-test-v3-mkmlizer: ║ Chai Research Corp. ║
hastagaras-yirp-9b-test-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-yirp-9b-test-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-yirp-9b-test-v3-mkmlizer: ║ ║
hastagaras-yirp-9b-test-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-yirp-9b-test-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-yirp-9b-test-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-yirp-9b-test-v3-mkmlizer: Downloaded to shared memory in 175.681s
hastagaras-yirp-9b-test-v3-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-yirp-9b-test-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-yirp-9b-test-v3-mkmlizer: quantized model in 19.078s
hastagaras-yirp-9b-test-v3-mkmlizer: Processed model Hastagaras/YIRP-9B-TEST in 197.638s
hastagaras-yirp-9b-test-v3-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-yirp-9b-test-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-yirp-9b-test-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-yirp-9b-test-v3
hastagaras-yirp-9b-test-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-yirp-9b-test-v3/config.json
hastagaras-yirp-9b-test-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-yirp-9b-test-v3/tokenizer_config.json
hastagaras-yirp-9b-test-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-yirp-9b-test-v3/special_tokens_map.json
hastagaras-yirp-9b-test-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-yirp-9b-test-v3/tokenizer.json
hastagaras-yirp-9b-test-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-yirp-9b-test-v3/flywheel_model.0.safetensors
hastagaras-yirp-9b-test-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-yirp-9b-test-v3-mkmlizer: Loading 0: 0%| | 0/435 [00:00<?, ?it/s] Loading 0: 3%|▎ | 13/435 [00:00<00:03, 113.56it/s] Loading 0: 6%|▌ | 27/435 [00:00<00:03, 125.72it/s] Loading 0: 9%|▉ | 40/435 [00:00<00:03, 115.96it/s] Loading 0: 13%|█▎ | 56/435 [00:00<00:02, 128.63it/s] Loading 0: 18%|█▊ | 77/435 [00:00<00:02, 155.37it/s] Loading 0: 22%|██▏ | 96/435 [00:00<00:02, 166.08it/s] Loading 0: 27%|██▋ | 116/435 [00:01<00:03, 94.56it/s] Loading 0: 31%|███ | 135/435 [00:01<00:02, 112.96it/s] Loading 0: 36%|███▌ | 157/435 [00:01<00:02, 132.97it/s] Loading 0: 40%|████ | 176/435 [00:01<00:01, 146.07it/s] Loading 0: 46%|████▌ | 201/435 [00:01<00:01, 168.05it/s] Loading 0: 51%|█████ | 221/435 [00:01<00:01, 171.43it/s] Loading 0: 56%|█████▌ | 243/435 [00:01<00:01, 182.95it/s] Loading 0: 60%|██████ | 263/435 [00:02<00:01, 109.21it/s] Loading 0: 65%|██████▌ | 283/435 [00:02<00:01, 123.87it/s] Loading 0: 70%|██████▉ | 303/435 [00:02<00:00, 139.49it/s] Loading 0: 75%|███████▌ | 327/435 [00:02<00:00, 159.82it/s] Loading 0: 80%|███████▉ | 347/435 [00:02<00:00, 164.98it/s] Loading 0: 85%|████████▌ | 371/435 [00:02<00:00, 180.54it/s] Loading 0: 90%|████████▉ | 391/435 [00:05<00:01, 22.11it/s] Loading 0: 94%|█████████▍| 411/435 [00:05<00:00, 29.58it/s] /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-yirp-9b-test-v3-mkmlizer: warnings.warn(
hastagaras-yirp-9b-test-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-yirp-9b-test-v3-mkmlizer: warnings.warn(
hastagaras-yirp-9b-test-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-yirp-9b-test-v3-mkmlizer: warnings.warn(
Retrying (%r) after connection broken by '%r': %s
Job hastagaras-yirp-9b-test-v3-mkmlizer completed after 367.39s with status: succeeded
Stopping job with name hastagaras-yirp-9b-test-v3-mkmlizer
Pipeline stage MKMLizer completed in 369.55s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-yirp-9b-test-v3
Waiting for inference service hastagaras-yirp-9b-test-v3 to be ready
Inference service hastagaras-yirp-9b-test-v3 ready after 40.219831228256226s
Pipeline stage ISVCDeployer completed in 46.25s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.263446092605591s
Received healthy response to inference request in 1.341921091079712s
Received healthy response to inference request in 1.3534538745880127s
Received healthy response to inference request in 1.351719617843628s
Received healthy response to inference request in 1.370739459991455s
5 requests
0 failed requests
5th percentile: 1.343880796432495
10th percentile: 1.3458405017852784
20th percentile: 1.3497599124908448
30th percentile: 1.3520664691925048
40th percentile: 1.3527601718902589
50th percentile: 1.3534538745880127
60th percentile: 1.3603681087493897
70th percentile: 1.3672823429107666
80th percentile: 1.5492807865142824
90th percentile: 1.9063634395599367
95th percentile: 2.0849047660827633
99th percentile: 2.2277378273010253
mean time: 1.5362560272216796
Pipeline stage StressChecker completed in 8.30s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.06s
hastagaras-yirp-9b-test_v3 status is now deployed due to DeploymentManager action
hastagaras-yirp-9b-test_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-yirp-9b-test_v3
Running pipeline stage ISVCDeleter
Checking if service hastagaras-yirp-9b-test-v3 is running
Tearing down inference service hastagaras-yirp-9b-test-v3
Toredown service hastagaras-yirp-9b-test-v3
Pipeline stage ISVCDeleter completed in 3.67s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-yirp-9b-test-v3/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-yirp-9b-test-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-yirp-9b-test-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-yirp-9b-test-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-yirp-9b-test-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-yirp-9b-test-v3_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-yirp-9b-test-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-yirp-9b-test-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-yirp-9b-test-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-yirp-9b-test-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-yirp-9b-test-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-yirp-9b-test-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.91s
hastagaras-yirp-9b-test_v3 status is now torndown due to DeploymentManager action