submission_id: hastagaras-dirtybu8bl3-r_6770_v1
developer_uid: Hastagaras
best_of: 16
celo_rating: 1211.64
display_name: 5
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': '{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}
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 45, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
is_internal_developer: False
language_model: Hastagaras/DirtyBu8bl3-RP-TEST-5
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: Hastagaras/DirtyBu8bl3-R
model_name: 5
model_num_parameters: 8030261248.0
model_repo: Hastagaras/DirtyBu8bl3-RP-TEST-5
model_size: 8B
num_battles: 17571
num_wins: 9304
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: 2024-06-16T17:35:54+00:00
us_pacific_date: 2024-06-16
win_ratio: 0.529508849809345
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer
Waiting for job on hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer to finish
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: ║ /___/ ║
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: ║ ║
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: ║ ║
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: ║ belonging to: ║
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: ║ ║
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: ║ ║
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-dirtybu8bl3-r-6770-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-dirtybu8bl3-r-6770-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: Downloaded to shared memory in 34.341s
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:56, 2.27s/it] Loading 0: 6%|▌ | 18/291 [00:04<00:51, 5.30it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:22, 11.32it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:11, 20.73it/s] Loading 0: 22%|██▏ | 65/291 [00:05<00:09, 25.06it/s] Loading 0: 27%|██▋ | 78/291 [00:05<00:06, 33.66it/s] Loading 0: 31%|███▏ | 91/291 [00:05<00:04, 43.75it/s] Loading 0: 36%|███▌ | 105/291 [00:05<00:03, 55.47it/s] Loading 0: 42%|████▏ | 123/291 [00:05<00:02, 74.11it/s] Loading 0: 48%|████▊ | 141/291 [00:05<00:01, 91.41it/s] Loading 0: 55%|█████▍ | 159/291 [00:05<00:01, 108.22it/s] Loading 0: 60%|██████ | 175/291 [00:06<00:01, 78.72it/s] Loading 0: 66%|██████▋ | 193/291 [00:06<00:01, 95.43it/s] Loading 0: 73%|███████▎ | 211/291 [00:06<00:00, 110.86it/s] Loading 0: 79%|███████▊ | 229/291 [00:06<00:00, 124.49it/s] Loading 0: 85%|████████▍ | 247/291 [00:06<00:00, 133.75it/s] Loading 0: 91%|█████████ | 265/291 [00:06<00:00, 143.13it/s] Loading 0: 97%|█████████▋| 282/291 [00:07<00:00, 91.93it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: quantized model in 23.060s
Failed to get response for submission mistralai-mixtral-8x7b-_3473_v33: ('http://mistralai-mixtral-8x7b-3473-v33-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'upstream connect error or disconnect/reset before headers. reset reason: overflow')
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: Processed model Hastagaras/DirtyBu8bl3-RP-TEST-5 in 59.954s
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-dirtybu8bl3-r-6770-v1
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-dirtybu8bl3-r-6770-v1/tokenizer_config.json
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-dirtybu8bl3-r-6770-v1/config.json
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-dirtybu8bl3-r-6770-v1/special_tokens_map.json
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-dirtybu8bl3-r-6770-v1/tokenizer.json
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-dirtybu8bl3-r-6770-v1/flywheel_model.0.safetensors
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-dirtybu8bl3-r-6770-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.
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: warnings.warn(
hastagaras-dirtybu8bl3-r-6770-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-dirtybu8bl3-r-6770-v1-mkmlizer: warnings.warn(
hastagaras-dirtybu8bl3-r-6770-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-dirtybu8bl3-r-6770-v1-mkmlizer: warnings.warn(
hastagaras-dirtybu8bl3-r-6770-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-dirtybu8bl3-r-6770-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: Saving duration: 0.410s
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 8.331s
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-dirtybu8bl3-r-6770-v1_reward
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-dirtybu8bl3-r-6770-v1_reward/config.json
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-dirtybu8bl3-r-6770-v1_reward/special_tokens_map.json
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-dirtybu8bl3-r-6770-v1_reward/vocab.json
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-dirtybu8bl3-r-6770-v1_reward/merges.txt
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-dirtybu8bl3-r-6770-v1_reward/tokenizer.json
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-dirtybu8bl3-r-6770-v1_reward/tokenizer_config.json
hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-dirtybu8bl3-r-6770-v1_reward/reward.tensors
Job hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer completed after 93.53s with status: succeeded
Stopping job with name hastagaras-dirtybu8bl3-r-6770-v1-mkmlizer
Pipeline stage MKMLizer completed in 96.44s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-dirtybu8bl3-r-6770-v1
Waiting for inference service hastagaras-dirtybu8bl3-r-6770-v1 to be ready
Inference service hastagaras-dirtybu8bl3-r-6770-v1 ready after 100.49311995506287s
Pipeline stage ISVCDeployer completed in 107.52s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2313232421875s
Received healthy response to inference request in 1.3678216934204102s
Received healthy response to inference request in 1.337907075881958s
Received healthy response to inference request in 1.3092472553253174s
Received healthy response to inference request in 1.4062004089355469s
5 requests
0 failed requests
5th percentile: 1.3149792194366454
10th percentile: 1.3207111835479737
20th percentile: 1.33217511177063
30th percentile: 1.3438899993896485
40th percentile: 1.3558558464050292
50th percentile: 1.3678216934204102
60th percentile: 1.3831731796264648
70th percentile: 1.3985246658325194
80th percentile: 1.5712249755859378
90th percentile: 1.9012741088867189
95th percentile: 2.066298675537109
99th percentile: 2.1983183288574217
mean time: 1.5304999351501465
Pipeline stage StressChecker completed in 8.30s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
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
hastagaras-dirtybu8bl3-r_6770_v1 status is now deployed due to DeploymentManager action
hastagaras-dirtybu8bl3-r_6770_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-dirtybu8bl3-r_6770_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-dirtybu8bl3-r-6770-v1 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 hastagaras-dirtybu8bl3-r-6770-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-dirtybu8bl3-r-6770-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-dirtybu8bl3-r-6770-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-dirtybu8bl3-r-6770-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-dirtybu8bl3-r-6770-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-dirtybu8bl3-r-6770-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-dirtybu8bl3-r-6770-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-dirtybu8bl3-r-6770-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-dirtybu8bl3-r-6770-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-dirtybu8bl3-r-6770-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-dirtybu8bl3-r-6770-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-dirtybu8bl3-r-6770-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.21s
hastagaras-dirtybu8bl3-r_6770_v1 status is now torndown due to DeploymentManager action