submission_id: hastagaras-halu-8b-llam_2564_v17
developer_uid: Hastagaras
best_of: 16
celo_rating: 1213.92
display_name: prop-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': '{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': 1.1, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
is_internal_developer: False
language_model: Hastagaras/Halu-8B-Llama3-v0.3
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: Hastagaras/Halu-8B-Llama
model_name: prop-test
model_num_parameters: 8030261248.0
model_repo: Hastagaras/Halu-8B-Llama3-v0.3
model_size: 8B
num_battles: 7977
num_wins: 4360
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: 2024-06-10T12:35:57+00:00
us_pacific_date: 2024-06-10
win_ratio: 0.5465713927541682
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-halu-8b-llam-2564-v17-mkmlizer
Waiting for job on hastagaras-halu-8b-llam-2564-v17-mkmlizer to finish
hastagaras-halu-8b-llam-2564-v17-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-8b-llam-2564-v17-mkmlizer: ║ _____ __ __ ║
hastagaras-halu-8b-llam-2564-v17-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-halu-8b-llam-2564-v17-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-halu-8b-llam-2564-v17-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-halu-8b-llam-2564-v17-mkmlizer: ║ /___/ ║
hastagaras-halu-8b-llam-2564-v17-mkmlizer: ║ ║
hastagaras-halu-8b-llam-2564-v17-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-halu-8b-llam-2564-v17-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-halu-8b-llam-2564-v17-mkmlizer: ║ https://mk1.ai ║
hastagaras-halu-8b-llam-2564-v17-mkmlizer: ║ ║
hastagaras-halu-8b-llam-2564-v17-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-halu-8b-llam-2564-v17-mkmlizer: ║ belonging to: ║
hastagaras-halu-8b-llam-2564-v17-mkmlizer: ║ ║
hastagaras-halu-8b-llam-2564-v17-mkmlizer: ║ Chai Research Corp. ║
hastagaras-halu-8b-llam-2564-v17-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-halu-8b-llam-2564-v17-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-halu-8b-llam-2564-v17-mkmlizer: ║ ║
hastagaras-halu-8b-llam-2564-v17-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-8b-llam-2564-v17-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-halu-8b-llam-2564-v17-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-halu-8b-llam-2564-v17-mkmlizer: Downloaded to shared memory in 33.472s
hastagaras-halu-8b-llam-2564-v17-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-8b-llam-2564-v17-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-8b-llam-2564-v17-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 116.54it/s] Loading 0: 10%|█ | 30/291 [00:00<00:01, 144.46it/s] Loading 0: 15%|█▌ | 45/291 [00:00<00:01, 144.43it/s] Loading 0: 21%|██ | 60/291 [00:00<00:01, 142.08it/s] Loading 0: 26%|██▌ | 76/291 [00:00<00:01, 147.74it/s] Loading 0: 31%|███▏ | 91/291 [00:00<00:02, 74.82it/s] Loading 0: 36%|███▌ | 104/291 [00:01<00:02, 84.26it/s] Loading 0: 42%|████▏ | 121/291 [00:01<00:01, 102.46it/s] Loading 0: 47%|████▋ | 138/291 [00:01<00:01, 117.96it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:01, 128.83it/s] Loading 0: 59%|█████▉ | 171/291 [00:01<00:00, 133.91it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 82.96it/s] Loading 0: 69%|██████▉ | 201/291 [00:01<00:00, 92.74it/s] Loading 0: 75%|███████▌ | 219/291 [00:02<00:00, 108.03it/s] Loading 0: 81%|████████▏ | 237/291 [00:02<00:00, 120.51it/s] Loading 0: 88%|████████▊ | 255/291 [00:02<00:00, 130.21it/s] Loading 0: 94%|█████████▍| 273/291 [00:02<00:00, 138.20it/s] Loading 0: 99%|█████████▉| 289/291 [00:07<00:00, 9.67it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-halu-8b-llam-2564-v17-mkmlizer: quantized model in 23.254s
hastagaras-halu-8b-llam-2564-v17-mkmlizer: Processed model Hastagaras/Halu-8B-Llama3-v0.3 in 59.398s
hastagaras-halu-8b-llam-2564-v17-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-8b-llam-2564-v17-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-8b-llam-2564-v17-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-8b-llam-2564-v17
hastagaras-halu-8b-llam-2564-v17-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-8b-llam-2564-v17/special_tokens_map.json
hastagaras-halu-8b-llam-2564-v17-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llam-2564-v17/config.json
hastagaras-halu-8b-llam-2564-v17-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llam-2564-v17/tokenizer_config.json
hastagaras-halu-8b-llam-2564-v17-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-8b-llam-2564-v17/tokenizer.json
hastagaras-halu-8b-llam-2564-v17-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-8b-llam-2564-v17/flywheel_model.0.safetensors
hastagaras-halu-8b-llam-2564-v17-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-8b-llam-2564-v17-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-halu-8b-llam-2564-v17-mkmlizer: warnings.warn(
hastagaras-halu-8b-llam-2564-v17-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-halu-8b-llam-2564-v17-mkmlizer: warnings.warn(
hastagaras-halu-8b-llam-2564-v17-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-halu-8b-llam-2564-v17-mkmlizer: warnings.warn(
hastagaras-halu-8b-llam-2564-v17-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-halu-8b-llam-2564-v17-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-halu-8b-llam-2564-v17-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-halu-8b-llam-2564-v17-mkmlizer: Saving duration: 0.420s
hastagaras-halu-8b-llam-2564-v17-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.220s
hastagaras-halu-8b-llam-2564-v17-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-8b-llam-2564-v17-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-8b-llam-2564-v17-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-8b-llam-2564-v17_reward
hastagaras-halu-8b-llam-2564-v17-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-halu-8b-llam-2564-v17_reward/special_tokens_map.json
hastagaras-halu-8b-llam-2564-v17-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-halu-8b-llam-2564-v17_reward/tokenizer_config.json
hastagaras-halu-8b-llam-2564-v17-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-halu-8b-llam-2564-v17_reward/merges.txt
hastagaras-halu-8b-llam-2564-v17-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-halu-8b-llam-2564-v17_reward/vocab.json
hastagaras-halu-8b-llam-2564-v17-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-halu-8b-llam-2564-v17_reward/config.json
hastagaras-halu-8b-llam-2564-v17-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-halu-8b-llam-2564-v17_reward/tokenizer.json
hastagaras-halu-8b-llam-2564-v17-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-halu-8b-llam-2564-v17_reward/reward.tensors
Job hastagaras-halu-8b-llam-2564-v17-mkmlizer completed after 83.48s with status: succeeded
Stopping job with name hastagaras-halu-8b-llam-2564-v17-mkmlizer
Pipeline stage MKMLizer completed in 87.24s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-8b-llam-2564-v17
Waiting for inference service hastagaras-halu-8b-llam-2564-v17 to be ready
Inference service hastagaras-halu-8b-llam-2564-v17 ready after 291.6703152656555s
Pipeline stage ISVCDeployer completed in 298.77s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.225808620452881s
Received healthy response to inference request in 1.380772590637207s
Received healthy response to inference request in 1.3676743507385254s
Received healthy response to inference request in 1.340329885482788s
Received healthy response to inference request in 1.3896875381469727s
5 requests
0 failed requests
5th percentile: 1.3457987785339356
10th percentile: 1.351267671585083
20th percentile: 1.3622054576873779
30th percentile: 1.3702939987182616
40th percentile: 1.3755332946777343
50th percentile: 1.380772590637207
60th percentile: 1.3843385696411132
70th percentile: 1.3879045486450194
80th percentile: 1.5569117546081546
90th percentile: 1.8913601875305177
95th percentile: 2.058584403991699
99th percentile: 2.1923637771606446
mean time: 1.5408545970916747
Pipeline stage StressChecker completed in 8.29s
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
hastagaras-halu-8b-llam_2564_v17 status is now deployed due to DeploymentManager action
hastagaras-halu-8b-llam_2564_v17 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-halu-8b-llam_2564_v17
Running pipeline stage ISVCDeleter
Checking if service hastagaras-halu-8b-llam-2564-v17 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.55s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-halu-8b-llam-2564-v17/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llam-2564-v17/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llam-2564-v17/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llam-2564-v17/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llam-2564-v17/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-halu-8b-llam-2564-v17_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llam-2564-v17_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llam-2564-v17_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llam-2564-v17_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llam-2564-v17_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llam-2564-v17_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llam-2564-v17_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.21s
hastagaras-halu-8b-llam_2564_v17 status is now torndown due to DeploymentManager action