submission_id: hastagaras-llama3-rebaha_6335_v2
developer_uid: Hastagaras
best_of: 16
celo_rating: 1202.22
display_name: m
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': 2.0, 'top_p': 1.0, 'min_p': 0.2, 'top_k': 1000, '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/Llama3-RebahanSthenoMaidBlackroot-8B
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: Hastagaras/Llama3-Rebaha
model_name: m
model_num_parameters: 8030261248.0
model_repo: Hastagaras/Llama3-RebahanSthenoMaidBlackroot-8B
model_size: 8B
num_battles: 15932
num_wins: 8179
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: 2024-06-21T03:18:56+00:00
us_pacific_date: 2024-06-20
win_ratio: 0.5133693196083354
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama3-rebaha-6335-v2-mkmlizer
Waiting for job on hastagaras-llama3-rebaha-6335-v2-mkmlizer to finish
hastagaras-llama3-rebaha-6335-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama3-rebaha-6335-v2-mkmlizer: ║     _____            __           __                                ║
hastagaras-llama3-rebaha-6335-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-llama3-rebaha-6335-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-llama3-rebaha-6335-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-llama3-rebaha-6335-v2-mkmlizer: ║       /___/                                                         ║
hastagaras-llama3-rebaha-6335-v2-mkmlizer: ║                                                                     ║
hastagaras-llama3-rebaha-6335-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-llama3-rebaha-6335-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-llama3-rebaha-6335-v2-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-llama3-rebaha-6335-v2-mkmlizer: ║                                                                     ║
hastagaras-llama3-rebaha-6335-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-llama3-rebaha-6335-v2-mkmlizer: ║  belonging to:                                                      ║
hastagaras-llama3-rebaha-6335-v2-mkmlizer: ║                                                                     ║
hastagaras-llama3-rebaha-6335-v2-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-llama3-rebaha-6335-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-llama3-rebaha-6335-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-llama3-rebaha-6335-v2-mkmlizer: ║                                                                     ║
hastagaras-llama3-rebaha-6335-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama3-rebaha-6335-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.
hastagaras-llama3-rebaha-6335-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
hastagaras-llama3-rebaha-6335-v2-mkmlizer: Downloaded to shared memory in 17.394s
hastagaras-llama3-rebaha-6335-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama3-rebaha-6335-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama3-rebaha-6335-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<10:53,  2.26s/it]
Loading 0:   5%|▌         | 15/291 [00:04<01:02,  4.41it/s]
Loading 0:  11%|█▏        | 33/291 [00:04<00:22, 11.71it/s]
Loading 0:  18%|█▊        | 51/291 [00:04<00:11, 21.02it/s]
Loading 0:  22%|██▏       | 65/291 [00:05<00:08, 25.38it/s]
Loading 0:  27%|██▋       | 78/291 [00:05<00:06, 33.83it/s]
Loading 0:  33%|███▎      | 96/291 [00:05<00:04, 48.42it/s]
Loading 0:  39%|███▉      | 113/291 [00:05<00:02, 64.02it/s]
Loading 0:  45%|████▍     | 130/291 [00:05<00:02, 80.29it/s]
Loading 0:  51%|█████     | 148/291 [00:05<00:01, 96.46it/s]
Loading 0:  57%|█████▋    | 166/291 [00:06<00:01, 75.34it/s]
Loading 0:  63%|██████▎   | 184/291 [00:06<00:01, 90.93it/s]
Loading 0:  69%|██████▉   | 202/291 [00:06<00:00, 105.78it/s]
Loading 0:  75%|███████▍  | 217/291 [00:06<00:00, 109.44it/s]
Loading 0:  79%|███████▉  | 231/291 [00:06<00:00, 103.16it/s]
Loading 0:  85%|████████▌ | 248/291 [00:06<00:00, 117.38it/s]
Loading 0:  91%|█████████ | 265/291 [00:06<00:00, 129.60it/s]
Loading 0:  96%|█████████▌| 280/291 [00:07<00:00, 85.33it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama3-rebaha-6335-v2-mkmlizer: quantized model in 23.119s
hastagaras-llama3-rebaha-6335-v2-mkmlizer: Processed model Hastagaras/Llama3-RebahanSthenoMaidBlackroot-8B in 43.047s
hastagaras-llama3-rebaha-6335-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama3-rebaha-6335-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama3-rebaha-6335-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama3-rebaha-6335-v2
hastagaras-llama3-rebaha-6335-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama3-rebaha-6335-v2/config.json
hastagaras-llama3-rebaha-6335-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama3-rebaha-6335-v2/special_tokens_map.json
hastagaras-llama3-rebaha-6335-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama3-rebaha-6335-v2/tokenizer_config.json
hastagaras-llama3-rebaha-6335-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama3-rebaha-6335-v2/tokenizer.json
hastagaras-llama3-rebaha-6335-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama3-rebaha-6335-v2/flywheel_model.0.safetensors
hastagaras-llama3-rebaha-6335-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama3-rebaha-6335-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.
hastagaras-llama3-rebaha-6335-v2-mkmlizer:   warnings.warn(
hastagaras-llama3-rebaha-6335-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.
hastagaras-llama3-rebaha-6335-v2-mkmlizer:   warnings.warn(
hastagaras-llama3-rebaha-6335-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.
hastagaras-llama3-rebaha-6335-v2-mkmlizer:   warnings.warn(
hastagaras-llama3-rebaha-6335-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()
hastagaras-llama3-rebaha-6335-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-llama3-rebaha-6335-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama3-rebaha-6335-v2-mkmlizer: Saving duration: 0.402s
hastagaras-llama3-rebaha-6335-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.928s
hastagaras-llama3-rebaha-6335-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama3-rebaha-6335-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama3-rebaha-6335-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama3-rebaha-6335-v2_reward
hastagaras-llama3-rebaha-6335-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama3-rebaha-6335-v2_reward/special_tokens_map.json
hastagaras-llama3-rebaha-6335-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama3-rebaha-6335-v2_reward/config.json
hastagaras-llama3-rebaha-6335-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama3-rebaha-6335-v2_reward/tokenizer_config.json
hastagaras-llama3-rebaha-6335-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama3-rebaha-6335-v2_reward/merges.txt
hastagaras-llama3-rebaha-6335-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama3-rebaha-6335-v2_reward/vocab.json
hastagaras-llama3-rebaha-6335-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama3-rebaha-6335-v2_reward/tokenizer.json
hastagaras-llama3-rebaha-6335-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama3-rebaha-6335-v2_reward/reward.tensors
Job hastagaras-llama3-rebaha-6335-v2-mkmlizer completed after 73.14s with status: succeeded
Stopping job with name hastagaras-llama3-rebaha-6335-v2-mkmlizer
Pipeline stage MKMLizer completed in 73.51s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama3-rebaha-6335-v2
Waiting for inference service hastagaras-llama3-rebaha-6335-v2 to be ready
Inference service hastagaras-llama3-rebaha-6335-v2 ready after 40.177762508392334s
Pipeline stage ISVCDeployer completed in 45.88s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.112769603729248s
Received healthy response to inference request in 1.2993826866149902s
Received healthy response to inference request in 1.2945289611816406s
Received healthy response to inference request in 1.2614672183990479s
Received healthy response to inference request in 1.6565916538238525s
5 requests
0 failed requests
5th percentile: 1.2680795669555665
10th percentile: 1.274691915512085
20th percentile: 1.287916612625122
30th percentile: 1.2954997062683105
40th percentile: 1.2974411964416503
50th percentile: 1.2993826866149902
60th percentile: 1.4422662734985352
70th percentile: 1.58514986038208
80th percentile: 1.7478272438049318
90th percentile: 1.93029842376709
95th percentile: 2.0215340137481688
99th percentile: 2.094522485733032
mean time: 1.5249480247497558
Pipeline stage StressChecker completed in 8.36s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.04s
hastagaras-llama3-rebaha_6335_v2 status is now deployed due to DeploymentManager action
hastagaras-llama3-rebaha_6335_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama3-rebaha_6335_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama3-rebaha-6335-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.11s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama3-rebaha-6335-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-rebaha-6335-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-rebaha-6335-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-rebaha-6335-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-rebaha-6335-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama3-rebaha-6335-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-rebaha-6335-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama3-rebaha-6335-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama3-rebaha-6335-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-rebaha-6335-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-rebaha-6335-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-rebaha-6335-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.59s
hastagaras-llama3-rebaha_6335_v2 status is now torndown due to DeploymentManager action