developer_uid: Hastagaras
submission_id: hastagaras-yirp-9b-test_v1
model_name: yipyip
model_group: Hastagaras/YIRP-9B-TEST
status: torndown
timestamp: 2024-05-23T03:42:21+00:00
num_battles: 10519
num_wins: 4313
celo_rating: 1112.18
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: yipyip
is_internal_developer: False
language_model: Hastagaras/YIRP-9B-TEST
model_size: 9B
ranking_group: single
us_pacific_date: 2024-05-22
win_ratio: 0.41001996387489303
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, '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\nName:{bot_name}\nPersona: {memory}\n', 'prompt_template': '{prompt}\n<START>\n<|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-v1-mkmlizer
Waiting for job on hastagaras-yirp-9b-test-v1-mkmlizer to finish
hastagaras-yirp-9b-test-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-yirp-9b-test-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-yirp-9b-test-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-yirp-9b-test-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-yirp-9b-test-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-yirp-9b-test-v1-mkmlizer: ║ /___/ ║
hastagaras-yirp-9b-test-v1-mkmlizer: ║ ║
hastagaras-yirp-9b-test-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-yirp-9b-test-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-yirp-9b-test-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-yirp-9b-test-v1-mkmlizer: ║ ║
hastagaras-yirp-9b-test-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-yirp-9b-test-v1-mkmlizer: ║ belonging to: ║
hastagaras-yirp-9b-test-v1-mkmlizer: ║ ║
hastagaras-yirp-9b-test-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-yirp-9b-test-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-yirp-9b-test-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-yirp-9b-test-v1-mkmlizer: ║ ║
hastagaras-yirp-9b-test-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-yirp-9b-test-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.
hastagaras-yirp-9b-test-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-yirp-9b-test-v1-mkmlizer: Downloaded to shared memory in 42.283s
hastagaras-yirp-9b-test-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-yirp-9b-test-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-yirp-9b-test-v1-mkmlizer: quantized model in 14.737s
hastagaras-yirp-9b-test-v1-mkmlizer: Processed model Hastagaras/YIRP-9B-TEST in 58.141s
hastagaras-yirp-9b-test-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-yirp-9b-test-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-yirp-9b-test-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-yirp-9b-test-v1
hastagaras-yirp-9b-test-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-yirp-9b-test-v1/config.json
hastagaras-yirp-9b-test-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-yirp-9b-test-v1/special_tokens_map.json
hastagaras-yirp-9b-test-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-yirp-9b-test-v1/tokenizer_config.json
hastagaras-yirp-9b-test-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-yirp-9b-test-v1/tokenizer.json
hastagaras-yirp-9b-test-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-yirp-9b-test-v1/flywheel_model.0.safetensors
hastagaras-yirp-9b-test-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-yirp-9b-test-v1-mkmlizer: Loading 0: 0%| | 0/435 [00:00<?, ?it/s] Loading 0: 4%|▍ | 17/435 [00:00<00:02, 167.91it/s] Loading 0: 8%|▊ | 35/435 [00:00<00:02, 172.87it/s] Loading 0: 12%|█▏ | 54/435 [00:00<00:02, 180.07it/s] Loading 0: 17%|█▋ | 73/435 [00:00<00:02, 180.43it/s] Loading 0: 21%|██ | 92/435 [00:00<00:01, 180.73it/s] Loading 0: 26%|██▌ | 113/435 [00:00<00:01, 189.64it/s] Loading 0: 30%|███ | 132/435 [00:01<00:03, 90.24it/s] Loading 0: 35%|███▌ | 153/435 [00:01<00:02, 111.26it/s] Loading 0: 40%|████ | 174/435 [00:01<00:02, 130.07it/s] Loading 0: 44%|████▍ | 193/435 [00:01<00:01, 141.86it/s] Loading 0: 49%|████▊ | 212/435 [00:01<00:01, 151.50it/s] Loading 0: 54%|█████▎ | 233/435 [00:01<00:01, 164.61it/s] Loading 0: 58%|█████▊ | 252/435 [00:01<00:01, 95.63it/s] Loading 0: 63%|██████▎ | 273/435 [00:02<00:01, 114.73it/s] Loading 0: 67%|██████▋ | 293/435 [00:02<00:01, 129.26it/s] Loading 0: 73%|███████▎ | 318/435 [00:02<00:00, 152.73it/s] Loading 0: 78%|███████▊ | 338/435 [00:02<00:00, 160.21it/s] Loading 0: 83%|████████▎ | 363/435 [00:02<00:00, 178.55it/s] Loading 0: 88%|████████▊ | 383/435 [00:05<00:02, 24.47it/s] Loading 0: 93%|█████████▎| 405/435 [00:05<00:00, 33.50it/s] Loading 0: 98%|█████████▊| 427/435 [00:05<00:00, 45.00it/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-v1-mkmlizer: warnings.warn(
hastagaras-yirp-9b-test-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.
hastagaras-yirp-9b-test-v1-mkmlizer: warnings.warn(
hastagaras-yirp-9b-test-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.
hastagaras-yirp-9b-test-v1-mkmlizer: warnings.warn(
hastagaras-yirp-9b-test-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()
hastagaras-yirp-9b-test-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-yirp-9b-test-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-yirp-9b-test-v1-mkmlizer: Saving duration: 0.302s
hastagaras-yirp-9b-test-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 9.696s
hastagaras-yirp-9b-test-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-yirp-9b-test-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-yirp-9b-test-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-yirp-9b-test-v1_reward
hastagaras-yirp-9b-test-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-yirp-9b-test-v1_reward/config.json
hastagaras-yirp-9b-test-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-yirp-9b-test-v1_reward/special_tokens_map.json
hastagaras-yirp-9b-test-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-yirp-9b-test-v1_reward/reward.tensors
Job hastagaras-yirp-9b-test-v1-mkmlizer completed after 94.16s with status: succeeded
Stopping job with name hastagaras-yirp-9b-test-v1-mkmlizer
Pipeline stage MKMLizer completed in 95.31s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-yirp-9b-test-v1
Waiting for inference service hastagaras-yirp-9b-test-v1 to be ready
Inference service hastagaras-yirp-9b-test-v1 ready after 40.27870225906372s
Pipeline stage ISVCDeployer completed in 46.29s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2985212802886963s
Received healthy response to inference request in 1.3677878379821777s
Received healthy response to inference request in 1.2423269748687744s
Received healthy response to inference request in 1.386662244796753s
Received healthy response to inference request in 1.3720204830169678s
5 requests
0 failed requests
5th percentile: 1.2674191474914551
10th percentile: 1.2925113201141358
20th percentile: 1.342695665359497
30th percentile: 1.3686343669891357
40th percentile: 1.3703274250030517
50th percentile: 1.3720204830169678
60th percentile: 1.3778771877288818
70th percentile: 1.3837338924407958
80th percentile: 1.5690340518951418
90th percentile: 1.933777666091919
95th percentile: 2.1161494731903074
99th percentile: 2.2620469188690184
mean time: 1.5334637641906739
Pipeline stage StressChecker completed in 8.28s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-yirp-9b-test_v1 status is now deployed due to DeploymentManager action
hastagaras-yirp-9b-test_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-yirp-9b-test_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-yirp-9b-test-v1 is running
Tearing down inference service hastagaras-yirp-9b-test-v1
Toredown service hastagaras-yirp-9b-test-v1
Pipeline stage ISVCDeleter completed in 4.57s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-yirp-9b-test-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-yirp-9b-test-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-yirp-9b-test-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-yirp-9b-test-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-yirp-9b-test-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-yirp-9b-test-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-yirp-9b-test-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-yirp-9b-test-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-yirp-9b-test-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-yirp-9b-test-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-yirp-9b-test-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-yirp-9b-test-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.95s
hastagaras-yirp-9b-test_v1 status is now torndown due to DeploymentManager action