submission_id: setiaku-run1-rescaled_v2
developer_uid: sao10k
best_of: 16
celo_rating: 1199.38
display_name: L3-Run-2-Formatted-Test
family_friendly_score: 0.0
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': 'Example Conversation:\n{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>[{bot_name}]<|end_header_id|>\n\n{message}<|eot_id|>', 'user_template': '<|start_header_id|>[{user_name}]<|end_header_id|>\n\n{message}<|eot_id|>', 'response_template': '<|start_header_id|>[{bot_name}]<|end_header_id|>\n\n', 'truncate_by_message': True}
generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 60, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n,', '<|end_header_id|>,', '<|eot_id|>,', '\n\n{user_name}'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
is_internal_developer: False
language_model: Setiaku/Run1-Rescaled
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: Setiaku/Run1-Rescaled
model_name: L3-Run-2-Formatted-Test
model_num_parameters: 8030261248.0
model_repo: Setiaku/Run1-Rescaled
model_size: 8B
num_battles: 7064
num_wins: 3756
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: 2024-05-28T15:33:02+00:00
us_pacific_date: 2024-05-28
win_ratio: 0.5317100792751982
Resubmit model
Running pipeline stage MKMLizer
Starting job with name setiaku-run1-rescaled-v2-mkmlizer
Waiting for job on setiaku-run1-rescaled-v2-mkmlizer to finish
setiaku-run1-rescaled-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
setiaku-run1-rescaled-v2-mkmlizer: ║ _____ __ __ ║
setiaku-run1-rescaled-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
setiaku-run1-rescaled-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
setiaku-run1-rescaled-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
setiaku-run1-rescaled-v2-mkmlizer: ║ /___/ ║
setiaku-run1-rescaled-v2-mkmlizer: ║ ║
setiaku-run1-rescaled-v2-mkmlizer: ║ Version: 0.8.14 ║
setiaku-run1-rescaled-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
setiaku-run1-rescaled-v2-mkmlizer: ║ https://mk1.ai ║
setiaku-run1-rescaled-v2-mkmlizer: ║ ║
setiaku-run1-rescaled-v2-mkmlizer: ║ The license key for the current software has been verified as ║
setiaku-run1-rescaled-v2-mkmlizer: ║ belonging to: ║
setiaku-run1-rescaled-v2-mkmlizer: ║ ║
setiaku-run1-rescaled-v2-mkmlizer: ║ Chai Research Corp. ║
setiaku-run1-rescaled-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
setiaku-run1-rescaled-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
setiaku-run1-rescaled-v2-mkmlizer: ║ ║
setiaku-run1-rescaled-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
setiaku-run1-rescaled-v2-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.
setiaku-run1-rescaled-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
setiaku-run1-rescaled-v2-mkmlizer: Downloaded to shared memory in 30.051s
setiaku-run1-rescaled-v2-mkmlizer: quantizing model to /dev/shm/model_cache
setiaku-run1-rescaled-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
setiaku-run1-rescaled-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:38, 2.21s/it] Loading 0: 6%|▌ | 18/291 [00:04<00:50, 5.45it/s] Loading 0: 12%|█▏ | 36/291 [00:04<00:19, 12.90it/s] Loading 0: 18%|█▊ | 53/291 [00:04<00:10, 21.95it/s] Loading 0: 23%|██▎ | 68/291 [00:05<00:08, 26.77it/s] Loading 0: 30%|██▉ | 86/291 [00:05<00:05, 39.49it/s] Loading 0: 36%|███▌ | 104/291 [00:05<00:03, 54.25it/s] Loading 0: 42%|████▏ | 122/291 [00:05<00:02, 70.46it/s] Loading 0: 48%|████▊ | 140/291 [00:05<00:01, 86.61it/s] Loading 0: 54%|█████▍ | 158/291 [00:05<00:01, 101.87it/s] Loading 0: 60%|█████▉ | 174/291 [00:05<00:01, 78.75it/s] Loading 0: 65%|██████▍ | 189/291 [00:06<00:01, 90.39it/s] Loading 0: 70%|███████ | 205/291 [00:06<00:00, 103.81it/s] Loading 0: 76%|███████▋ | 222/291 [00:06<00:00, 116.14it/s] Loading 0: 82%|████████▏ | 240/291 [00:06<00:00, 130.00it/s] Loading 0: 89%|████████▊ | 258/291 [00:06<00:00, 139.32it/s] Loading 0: 94%|█████████▍| 274/291 [00:06<00:00, 92.99it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
setiaku-run1-rescaled-v2-mkmlizer: quantized model in 22.702s
setiaku-run1-rescaled-v2-mkmlizer: Processed model Setiaku/Run1-Rescaled in 55.242s
setiaku-run1-rescaled-v2-mkmlizer: creating bucket guanaco-mkml-models
setiaku-run1-rescaled-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
setiaku-run1-rescaled-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/setiaku-run1-rescaled-v2
setiaku-run1-rescaled-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/setiaku-run1-rescaled-v2/config.json
setiaku-run1-rescaled-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/setiaku-run1-rescaled-v2/special_tokens_map.json
setiaku-run1-rescaled-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/setiaku-run1-rescaled-v2/tokenizer_config.json
setiaku-run1-rescaled-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/setiaku-run1-rescaled-v2/tokenizer.json
setiaku-run1-rescaled-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/setiaku-run1-rescaled-v2/flywheel_model.0.safetensors
setiaku-run1-rescaled-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
setiaku-run1-rescaled-v2-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.
setiaku-run1-rescaled-v2-mkmlizer: warnings.warn(
setiaku-run1-rescaled-v2-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.
setiaku-run1-rescaled-v2-mkmlizer: warnings.warn(
setiaku-run1-rescaled-v2-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.
setiaku-run1-rescaled-v2-mkmlizer: warnings.warn(
setiaku-run1-rescaled-v2-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()
setiaku-run1-rescaled-v2-mkmlizer: return self.fget.__get__(instance, owner)()
setiaku-run1-rescaled-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
setiaku-run1-rescaled-v2-mkmlizer: Saving duration: 0.402s
setiaku-run1-rescaled-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.300s
setiaku-run1-rescaled-v2-mkmlizer: creating bucket guanaco-reward-models
setiaku-run1-rescaled-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
setiaku-run1-rescaled-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/setiaku-run1-rescaled-v2_reward
setiaku-run1-rescaled-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/setiaku-run1-rescaled-v2_reward/tokenizer_config.json
setiaku-run1-rescaled-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/setiaku-run1-rescaled-v2_reward/config.json
setiaku-run1-rescaled-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/setiaku-run1-rescaled-v2_reward/special_tokens_map.json
setiaku-run1-rescaled-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/setiaku-run1-rescaled-v2_reward/merges.txt
setiaku-run1-rescaled-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/setiaku-run1-rescaled-v2_reward/vocab.json
setiaku-run1-rescaled-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/setiaku-run1-rescaled-v2_reward/tokenizer.json
setiaku-run1-rescaled-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/setiaku-run1-rescaled-v2_reward/reward.tensors
Job setiaku-run1-rescaled-v2-mkmlizer completed after 83.18s with status: succeeded
Stopping job with name setiaku-run1-rescaled-v2-mkmlizer
Pipeline stage MKMLizer completed in 86.90s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service setiaku-run1-rescaled-v2
Waiting for inference service setiaku-run1-rescaled-v2 to be ready
Inference service setiaku-run1-rescaled-v2 ready after 40.23020935058594s
Pipeline stage ISVCDeployer completed in 47.30s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.35384464263916s
Received healthy response to inference request in 1.3035252094268799s
Received healthy response to inference request in 1.4879729747772217s
Received healthy response to inference request in 1.2777512073516846s
Received healthy response to inference request in 1.3490352630615234s
5 requests
0 failed requests
5th percentile: 1.2829060077667236
10th percentile: 1.2880608081817626
20th percentile: 1.2983704090118409
30th percentile: 1.3126272201538085
40th percentile: 1.330831241607666
50th percentile: 1.3490352630615234
60th percentile: 1.4046103477478027
70th percentile: 1.460185432434082
80th percentile: 1.6611473083496096
90th percentile: 2.007495975494385
95th percentile: 2.1806703090667723
99th percentile: 2.3192097759246826
mean time: 1.5544258594512939
Pipeline stage StressChecker completed in 8.50s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.05s
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
setiaku-run1-rescaled_v2 status is now deployed due to DeploymentManager action
setiaku-run1-rescaled_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of setiaku-run1-rescaled_v2
Running pipeline stage ISVCDeleter
Checking if service setiaku-run1-rescaled-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.08s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key setiaku-run1-rescaled-v2/config.json from bucket guanaco-mkml-models
Deleting key setiaku-run1-rescaled-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key setiaku-run1-rescaled-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key setiaku-run1-rescaled-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key setiaku-run1-rescaled-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key setiaku-run1-rescaled-v2_reward/config.json from bucket guanaco-reward-models
Deleting key setiaku-run1-rescaled-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key setiaku-run1-rescaled-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key setiaku-run1-rescaled-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key setiaku-run1-rescaled-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key setiaku-run1-rescaled-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key setiaku-run1-rescaled-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.04s
setiaku-run1-rescaled_v2 status is now torndown due to DeploymentManager action