submission_id: frank2030-llama3-chat-tu_7635_v3
developer_uid: frank2030
best_of: 4
celo_rating: 1126.97
display_name: frank2030-l3-tu_7635_v1
family_friendly_score: 0.0
formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
is_internal_developer: False
language_model: frank2030/llama3_chat_tune_lora_merged
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: frank2030/llama3_chat_tu
model_name: frank2030-l3-tu_7635_v1
model_num_parameters: 8030261248.0
model_repo: frank2030/llama3_chat_tune_lora_merged
model_size: 8B
num_battles: 36331
num_wins: 14821
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: 2024-07-09T19:06:48+00:00
us_pacific_date: 2024-07-09
win_ratio: 0.40794362940739315
Resubmit model
Running pipeline stage MKMLizer
Starting job with name frank2030-llama3-chat-tu-7635-v3-mkmlizer
Waiting for job on frank2030-llama3-chat-tu-7635-v3-mkmlizer to finish
frank2030-llama3-chat-tu-7635-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
frank2030-llama3-chat-tu-7635-v3-mkmlizer: ║     _____            __           __                                ║
frank2030-llama3-chat-tu-7635-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
frank2030-llama3-chat-tu-7635-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
frank2030-llama3-chat-tu-7635-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
frank2030-llama3-chat-tu-7635-v3-mkmlizer: ║       /___/                                                         ║
frank2030-llama3-chat-tu-7635-v3-mkmlizer: ║                                                                     ║
frank2030-llama3-chat-tu-7635-v3-mkmlizer: ║  Version: 0.8.14                                                    ║
frank2030-llama3-chat-tu-7635-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
frank2030-llama3-chat-tu-7635-v3-mkmlizer: ║  https://mk1.ai                                                     ║
frank2030-llama3-chat-tu-7635-v3-mkmlizer: ║                                                                     ║
frank2030-llama3-chat-tu-7635-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
frank2030-llama3-chat-tu-7635-v3-mkmlizer: ║  belonging to:                                                      ║
frank2030-llama3-chat-tu-7635-v3-mkmlizer: ║                                                                     ║
frank2030-llama3-chat-tu-7635-v3-mkmlizer: ║  Chai Research Corp.                                                ║
frank2030-llama3-chat-tu-7635-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
frank2030-llama3-chat-tu-7635-v3-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
frank2030-llama3-chat-tu-7635-v3-mkmlizer: ║                                                                     ║
frank2030-llama3-chat-tu-7635-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s
frank2030-llama3-chat-tu-7635-v3-mkmlizer: Downloaded to shared memory in 38.330s
frank2030-llama3-chat-tu-7635-v3-mkmlizer: quantizing model to /dev/shm/model_cache
frank2030-llama3-chat-tu-7635-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
frank2030-llama3-chat-tu-7635-v3-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:02, 118.17it/s]
Loading 0:   9%|▉         | 27/291 [00:00<00:02, 129.88it/s]
Loading 0:  14%|█▍        | 41/291 [00:00<00:02, 120.43it/s]
Loading 0:  19%|█▊        | 54/291 [00:00<00:04, 52.62it/s] 
Loading 0:  23%|██▎       | 67/291 [00:00<00:03, 64.43it/s]
Loading 0:  27%|██▋       | 80/291 [00:01<00:02, 77.10it/s]
Loading 0:  31%|███▏      | 91/291 [00:01<00:04, 47.35it/s]
Loading 0:  35%|███▌      | 103/291 [00:01<00:03, 57.71it/s]
Loading 0:  40%|████      | 117/291 [00:01<00:02, 71.99it/s]
Loading 0:  45%|████▍     | 130/291 [00:01<00:01, 81.60it/s]
Loading 0:  49%|████▉     | 144/291 [00:01<00:01, 94.23it/s]
Loading 0:  54%|█████▍    | 157/291 [00:02<00:01, 100.82it/s]
Loading 0:  59%|█████▉    | 171/291 [00:02<00:01, 110.05it/s]
Loading 0:  64%|██████▎   | 185/291 [00:02<00:00, 116.79it/s]
Loading 0:  68%|██████▊   | 198/291 [00:02<00:01, 61.73it/s] 
Loading 0:  73%|███████▎  | 211/291 [00:02<00:01, 72.30it/s]
Loading 0:  77%|███████▋  | 225/291 [00:02<00:00, 84.83it/s]
Loading 0:  82%|████████▏ | 238/291 [00:02<00:00, 93.14it/s]
Loading 0:  87%|████████▋ | 252/291 [00:03<00:00, 103.50it/s]
Loading 0:  91%|█████████ | 265/291 [00:03<00:00, 108.21it/s]
Loading 0:  96%|█████████▌| 280/291 [00:03<00:00, 118.58it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
frank2030-llama3-chat-tu-7635-v3-mkmlizer: quantized model in 34.655s
frank2030-llama3-chat-tu-7635-v3-mkmlizer: Processed model frank2030/llama3_chat_tune_lora_merged in 72.985s
frank2030-llama3-chat-tu-7635-v3-mkmlizer: creating bucket guanaco-mkml-models
frank2030-llama3-chat-tu-7635-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
frank2030-llama3-chat-tu-7635-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/frank2030-llama3-chat-tu-7635-v3
frank2030-llama3-chat-tu-7635-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/frank2030-llama3-chat-tu-7635-v3/config.json
frank2030-llama3-chat-tu-7635-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/frank2030-llama3-chat-tu-7635-v3/special_tokens_map.json
frank2030-llama3-chat-tu-7635-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/frank2030-llama3-chat-tu-7635-v3/tokenizer.json
frank2030-llama3-chat-tu-7635-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/frank2030-llama3-chat-tu-7635-v3/tokenizer_config.json
frank2030-llama3-chat-tu-7635-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
frank2030-llama3-chat-tu-7635-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
frank2030-llama3-chat-tu-7635-v3-mkmlizer:   warnings.warn(
frank2030-llama3-chat-tu-7635-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
frank2030-llama3-chat-tu-7635-v3-mkmlizer:   warnings.warn(
frank2030-llama3-chat-tu-7635-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
frank2030-llama3-chat-tu-7635-v3-mkmlizer:   warnings.warn(
frank2030-llama3-chat-tu-7635-v3-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.
frank2030-llama3-chat-tu-7635-v3-mkmlizer:   warnings.warn(
frank2030-llama3-chat-tu-7635-v3-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()
frank2030-llama3-chat-tu-7635-v3-mkmlizer:   return self.fget.__get__(instance, owner)()
frank2030-llama3-chat-tu-7635-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
frank2030-llama3-chat-tu-7635-v3-mkmlizer: Saving duration: 0.502s
frank2030-llama3-chat-tu-7635-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.854s
frank2030-llama3-chat-tu-7635-v3-mkmlizer: creating bucket guanaco-reward-models
frank2030-llama3-chat-tu-7635-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
frank2030-llama3-chat-tu-7635-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/frank2030-llama3-chat-tu-7635-v3_reward
frank2030-llama3-chat-tu-7635-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/frank2030-llama3-chat-tu-7635-v3_reward/config.json
frank2030-llama3-chat-tu-7635-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/frank2030-llama3-chat-tu-7635-v3_reward/tokenizer_config.json
frank2030-llama3-chat-tu-7635-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/frank2030-llama3-chat-tu-7635-v3_reward/vocab.json
frank2030-llama3-chat-tu-7635-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/frank2030-llama3-chat-tu-7635-v3_reward/merges.txt
frank2030-llama3-chat-tu-7635-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/frank2030-llama3-chat-tu-7635-v3_reward/special_tokens_map.json
frank2030-llama3-chat-tu-7635-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/frank2030-llama3-chat-tu-7635-v3_reward/tokenizer.json
frank2030-llama3-chat-tu-7635-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/frank2030-llama3-chat-tu-7635-v3_reward/reward.tensors
Job frank2030-llama3-chat-tu-7635-v3-mkmlizer completed after 105.06s with status: succeeded
Stopping job with name frank2030-llama3-chat-tu-7635-v3-mkmlizer
Pipeline stage MKMLizer completed in 106.00s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service frank2030-llama3-chat-tu-7635-v3
Waiting for inference service frank2030-llama3-chat-tu-7635-v3 to be ready
Inference service frank2030-llama3-chat-tu-7635-v3 ready after 40.28821039199829s
Pipeline stage ISVCDeployer completed in 47.31s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8168599605560303s
Received healthy response to inference request in 1.110480785369873s
Received healthy response to inference request in 1.110551118850708s
Received healthy response to inference request in 1.1275184154510498s
Received healthy response to inference request in 1.1296100616455078s
5 requests
0 failed requests
5th percentile: 1.11049485206604
10th percentile: 1.110508918762207
20th percentile: 1.110537052154541
30th percentile: 1.1139445781707764
40th percentile: 1.120731496810913
50th percentile: 1.1275184154510498
60th percentile: 1.128355073928833
70th percentile: 1.1291917324066163
80th percentile: 1.2670600414276123
90th percentile: 1.5419600009918213
95th percentile: 1.6794099807739258
99th percentile: 1.7893699645996093
mean time: 1.2590040683746337
Pipeline stage StressChecker completed in 7.13s
frank2030-llama3-chat-tu_7635_v3 status is now deployed due to DeploymentManager action
frank2030-llama3-chat-tu_7635_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of frank2030-llama3-chat-tu_7635_v3
Running pipeline stage ISVCDeleter
Checking if service frank2030-llama3-chat-tu-7635-v3 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.00s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key frank2030-llama3-chat-tu-7635-v3/config.json from bucket guanaco-mkml-models
Deleting key frank2030-llama3-chat-tu-7635-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key frank2030-llama3-chat-tu-7635-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key frank2030-llama3-chat-tu-7635-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key frank2030-llama3-chat-tu-7635-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key frank2030-llama3-chat-tu-7635-v3_reward/config.json from bucket guanaco-reward-models
Deleting key frank2030-llama3-chat-tu-7635-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key frank2030-llama3-chat-tu-7635-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key frank2030-llama3-chat-tu-7635-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key frank2030-llama3-chat-tu-7635-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key frank2030-llama3-chat-tu-7635-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key frank2030-llama3-chat-tu-7635-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.28s
frank2030-llama3-chat-tu_7635_v3 status is now torndown due to DeploymentManager action