submission_id: hastagaras-sciemet-8b-l3-mk-i_v1
developer_uid: Hastagaras
best_of: 16
celo_rating: 1212.46
display_name: 1
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': 1.15, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 60, '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/Sciemet-8B-L3-MK.I
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: Hastagaras/Sciemet-8B-L3
model_name: 1
model_num_parameters: 8030261248.0
model_repo: Hastagaras/Sciemet-8B-L3-MK.I
model_size: 8B
num_battles: 18240
num_wins: 9951
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: 2024-06-15T04:45:18+00:00
us_pacific_date: 2024-06-14
win_ratio: 0.5455592105263158
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer
Waiting for job on hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer to finish
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: ║ /___/ ║
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: ║ ║
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: ║ ║
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: ║ belonging to: ║
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: ║ ║
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: ║ ║
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-sciemet-8b-l3-mk-i-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-sciemet-8b-l3-mk-i-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: Downloaded to shared memory in 32.977s
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 130.00it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 151.14it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:01, 157.12it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 158.07it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 82.55it/s] Loading 0: 33%|███▎ | 95/291 [00:00<00:02, 89.60it/s] Loading 0: 39%|███▉ | 113/291 [00:01<00:01, 107.43it/s] Loading 0: 45%|████▌ | 131/291 [00:01<00:01, 121.56it/s] Loading 0: 51%|█████ | 149/291 [00:01<00:01, 132.82it/s] Loading 0: 57%|█████▋ | 167/291 [00:01<00:00, 140.14it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 94.15it/s] Loading 0: 69%|██████▉ | 202/291 [00:01<00:00, 101.69it/s] Loading 0: 76%|███████▌ | 220/291 [00:01<00:00, 115.58it/s] Loading 0: 82%|████████▏ | 238/291 [00:02<00:00, 127.97it/s] Loading 0: 88%|████████▊ | 256/291 [00:02<00:00, 137.18it/s] Loading 0: 94%|█████████▍| 274/291 [00:02<00:00, 144.76it/s] Loading 0: 100%|█████████▉| 290/291 [00:07<00:00, 10.05it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: quantized model in 22.924s
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: Processed model Hastagaras/Sciemet-8B-L3-MK.I in 58.478s
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-sciemet-8b-l3-mk-i-v1
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-sciemet-8b-l3-mk-i-v1/config.json
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-sciemet-8b-l3-mk-i-v1/tokenizer_config.json
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-sciemet-8b-l3-mk-i-v1/special_tokens_map.json
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-sciemet-8b-l3-mk-i-v1/tokenizer.json
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-sciemet-8b-l3-mk-i-v1/flywheel_model.0.safetensors
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-sciemet-8b-l3-mk-i-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-sciemet-8b-l3-mk-i-v1-mkmlizer: warnings.warn(
hastagaras-sciemet-8b-l3-mk-i-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-sciemet-8b-l3-mk-i-v1-mkmlizer: warnings.warn(
hastagaras-sciemet-8b-l3-mk-i-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-sciemet-8b-l3-mk-i-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: Saving duration: 0.406s
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.597s
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-sciemet-8b-l3-mk-i-v1_reward
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-sciemet-8b-l3-mk-i-v1_reward/special_tokens_map.json
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-sciemet-8b-l3-mk-i-v1_reward/merges.txt
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-sciemet-8b-l3-mk-i-v1_reward/vocab.json
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-sciemet-8b-l3-mk-i-v1_reward/config.json
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-sciemet-8b-l3-mk-i-v1_reward/tokenizer.json
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-sciemet-8b-l3-mk-i-v1_reward/tokenizer_config.json
hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-sciemet-8b-l3-mk-i-v1_reward/reward.tensors
Job hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer completed after 103.52s with status: succeeded
Stopping job with name hastagaras-sciemet-8b-l3-mk-i-v1-mkmlizer
Pipeline stage MKMLizer completed in 106.89s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-sciemet-8b-l3-mk-i-v1
Waiting for inference service hastagaras-sciemet-8b-l3-mk-i-v1 to be ready
Inference service hastagaras-sciemet-8b-l3-mk-i-v1 ready after 60.29045486450195s
Pipeline stage ISVCDeployer completed in 67.27s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1068153381347656s
Received healthy response to inference request in 1.3774755001068115s
Received healthy response to inference request in 1.3518095016479492s
Received healthy response to inference request in 1.3309922218322754s
Received healthy response to inference request in 1.3917236328125s
5 requests
0 failed requests
5th percentile: 1.3351556777954101
10th percentile: 1.3393191337585448
20th percentile: 1.3476460456848145
30th percentile: 1.3569427013397217
40th percentile: 1.3672091007232665
50th percentile: 1.3774755001068115
60th percentile: 1.383174753189087
70th percentile: 1.3888740062713623
80th percentile: 1.5347419738769532
90th percentile: 1.8207786560058594
95th percentile: 1.9637969970703124
99th percentile: 2.078211669921875
mean time: 1.5117632389068603
Pipeline stage StressChecker completed in 8.16s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
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-sciemet-8b-l3-mk-i_v1 status is now deployed due to DeploymentManager action
hastagaras-sciemet-8b-l3-mk-i_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-sciemet-8b-l3-mk-i_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-sciemet-8b-l3-mk-i-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.34s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-sciemet-8b-l3-mk-i-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-sciemet-8b-l3-mk-i-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-sciemet-8b-l3-mk-i-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-sciemet-8b-l3-mk-i-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-sciemet-8b-l3-mk-i-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-sciemet-8b-l3-mk-i-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-sciemet-8b-l3-mk-i-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-sciemet-8b-l3-mk-i-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-sciemet-8b-l3-mk-i-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-sciemet-8b-l3-mk-i-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-sciemet-8b-l3-mk-i-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-sciemet-8b-l3-mk-i-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.10s
hastagaras-sciemet-8b-l3-mk-i_v1 status is now torndown due to DeploymentManager action