thetsar1209-llama3-carpm_1580

submission_id: thetsar1209-llama3-carpm_1580_v1

developer_uid: TheTsar1209

best_of: 16

celo_rating: 1171.29

display_name: thetsar1209-llama3-carpm_1580_v1

family_friendly_score: 0.0

formatter: {'memory_template': '<|im_start|>system\nYou are {bot_name}\nDescription : {memory}\n', 'prompt_template': 'Example conversation:\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', 'truncate_by_message': True}

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<|im_end|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}

is_internal_developer: False

language_model: TheTsar1209/llama3-carpmuscle-v0.1.1

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: TheTsar1209/llama3-carpm

model_name: thetsar1209-llama3-carpm_1580_v1

model_num_parameters: 8030261248.0

model_repo: TheTsar1209/llama3-carpmuscle-v0.1.1

model_size: 8B

num_battles: 30839

num_wins: 14904

ranking_group: single

reward_formatter: {'bot_template': 'Bot: {message}\n', 'memory_template': 'Memory: {memory}\n', 'prompt_template': 'Prompt: {prompt}\n', 'response_template': 'Bot:', 'truncate_by_message': True, 'user_template': 'User: {message}\n'}

reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2

status: torndown

submission_type: basic

timestamp: 2024-07-06T03:03:05+00:00

us_pacific_date: 2024-07-05

win_ratio: 0.4832841531826583

Resubmit model

Running pipeline stage MKMLizer
Starting job with name thetsar1209-llama3-carpm-1580-v1-mkmlizer
Waiting for job on thetsar1209-llama3-carpm-1580-v1-mkmlizer to finish
thetsar1209-llama3-carpm-1580-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
thetsar1209-llama3-carpm-1580-v1-mkmlizer: ║     _____            __           __                                ║
thetsar1209-llama3-carpm-1580-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
thetsar1209-llama3-carpm-1580-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
thetsar1209-llama3-carpm-1580-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
thetsar1209-llama3-carpm-1580-v1-mkmlizer: ║       /___/                                                         ║
thetsar1209-llama3-carpm-1580-v1-mkmlizer: ║                                                                     ║
thetsar1209-llama3-carpm-1580-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
thetsar1209-llama3-carpm-1580-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
thetsar1209-llama3-carpm-1580-v1-mkmlizer: ║  https://mk1.ai                                                     ║
thetsar1209-llama3-carpm-1580-v1-mkmlizer: ║                                                                     ║
thetsar1209-llama3-carpm-1580-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
thetsar1209-llama3-carpm-1580-v1-mkmlizer: ║  belonging to:                                                      ║
thetsar1209-llama3-carpm-1580-v1-mkmlizer: ║                                                                     ║
thetsar1209-llama3-carpm-1580-v1-mkmlizer: ║  Chai Research Corp.                                                ║
thetsar1209-llama3-carpm-1580-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
thetsar1209-llama3-carpm-1580-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
thetsar1209-llama3-carpm-1580-v1-mkmlizer: ║                                                                     ║
thetsar1209-llama3-carpm-1580-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
thetsar1209-llama3-carpm-1580-v1-mkmlizer: Downloaded to shared memory in 60.698s
thetsar1209-llama3-carpm-1580-v1-mkmlizer: quantizing model to /dev/shm/model_cache
thetsar1209-llama3-carpm-1580-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
thetsar1209-llama3-carpm-1580-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:02, 112.95it/s]
Loading 0:  10%|█         | 30/291 [00:00<00:01, 131.47it/s]
Loading 0:  15%|█▌        | 44/291 [00:00<00:01, 127.42it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:01, 125.52it/s]
Loading 0:  25%|██▍       | 72/291 [00:00<00:01, 128.37it/s]
Loading 0:  29%|██▉       | 85/291 [00:00<00:03, 68.33it/s] 
Loading 0:  34%|███▍      | 99/291 [00:01<00:02, 82.06it/s]
Loading 0:  38%|███▊      | 112/291 [00:01<00:01, 90.36it/s]
Loading 0:  43%|████▎     | 126/291 [00:01<00:01, 101.59it/s]
Loading 0:  48%|████▊     | 139/291 [00:01<00:01, 106.25it/s]
Loading 0:  53%|█████▎    | 154/291 [00:01<00:01, 117.32it/s]
Loading 0:  57%|█████▋    | 167/291 [00:01<00:01, 113.60it/s]
Loading 0:  62%|██████▏   | 181/291 [00:01<00:00, 119.95it/s]
Loading 0:  67%|██████▋   | 194/291 [00:02<00:01, 73.47it/s] 
Loading 0:  72%|███████▏  | 210/291 [00:02<00:00, 89.16it/s]
Loading 0:  76%|███████▋  | 222/291 [00:02<00:00, 94.60it/s]
Loading 0:  81%|████████▏ | 237/291 [00:02<00:00, 107.31it/s]
Loading 0:  86%|████████▌ | 250/291 [00:02<00:00, 110.68it/s]
Loading 0:  91%|█████████ | 265/291 [00:02<00:00, 115.56it/s]
Loading 0:  96%|█████████▌| 279/291 [00:02<00:00, 121.32it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
thetsar1209-llama3-carpm-1580-v1-mkmlizer: quantized model in 24.685s
thetsar1209-llama3-carpm-1580-v1-mkmlizer: Processed model TheTsar1209/llama3-carpmuscle-v0.1.1 in 85.384s
thetsar1209-llama3-carpm-1580-v1-mkmlizer: creating bucket guanaco-mkml-models
thetsar1209-llama3-carpm-1580-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
thetsar1209-llama3-carpm-1580-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/thetsar1209-llama3-carpm-1580-v1
thetsar1209-llama3-carpm-1580-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/thetsar1209-llama3-carpm-1580-v1/special_tokens_map.json
thetsar1209-llama3-carpm-1580-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/thetsar1209-llama3-carpm-1580-v1/config.json
thetsar1209-llama3-carpm-1580-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/thetsar1209-llama3-carpm-1580-v1/tokenizer_config.json
thetsar1209-llama3-carpm-1580-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/thetsar1209-llama3-carpm-1580-v1/tokenizer.json
thetsar1209-llama3-carpm-1580-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
thetsar1209-llama3-carpm-1580-v1-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.
thetsar1209-llama3-carpm-1580-v1-mkmlizer:   warnings.warn(
thetsar1209-llama3-carpm-1580-v1-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`.
thetsar1209-llama3-carpm-1580-v1-mkmlizer:   warnings.warn(
thetsar1209-llama3-carpm-1580-v1-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.
thetsar1209-llama3-carpm-1580-v1-mkmlizer:   warnings.warn(
thetsar1209-llama3-carpm-1580-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.
thetsar1209-llama3-carpm-1580-v1-mkmlizer:   warnings.warn(
thetsar1209-llama3-carpm-1580-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()
thetsar1209-llama3-carpm-1580-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
thetsar1209-llama3-carpm-1580-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
thetsar1209-llama3-carpm-1580-v1-mkmlizer: Saving duration: 0.391s
thetsar1209-llama3-carpm-1580-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.469s
thetsar1209-llama3-carpm-1580-v1-mkmlizer: creating bucket guanaco-reward-models
thetsar1209-llama3-carpm-1580-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
thetsar1209-llama3-carpm-1580-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/thetsar1209-llama3-carpm-1580-v1_reward
thetsar1209-llama3-carpm-1580-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/thetsar1209-llama3-carpm-1580-v1_reward/special_tokens_map.json
thetsar1209-llama3-carpm-1580-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/thetsar1209-llama3-carpm-1580-v1_reward/config.json
thetsar1209-llama3-carpm-1580-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/thetsar1209-llama3-carpm-1580-v1_reward/merges.txt
thetsar1209-llama3-carpm-1580-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/thetsar1209-llama3-carpm-1580-v1_reward/tokenizer_config.json
thetsar1209-llama3-carpm-1580-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/thetsar1209-llama3-carpm-1580-v1_reward/vocab.json
thetsar1209-llama3-carpm-1580-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/thetsar1209-llama3-carpm-1580-v1_reward/tokenizer.json
thetsar1209-llama3-carpm-1580-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/thetsar1209-llama3-carpm-1580-v1_reward/reward.tensors
Job thetsar1209-llama3-carpm-1580-v1-mkmlizer completed after 114.85s with status: succeeded
Stopping job with name thetsar1209-llama3-carpm-1580-v1-mkmlizer
Pipeline stage MKMLizer completed in 116.01s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.14s
Running pipeline stage ISVCDeployer
Creating inference service thetsar1209-llama3-carpm-1580-v1
Waiting for inference service thetsar1209-llama3-carpm-1580-v1 to be ready
Inference service thetsar1209-llama3-carpm-1580-v1 ready after 50.2974066734314s
Pipeline stage ISVCDeployer completed in 57.44s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.079972267150879s
Received healthy response to inference request in 1.2925782203674316s
Received healthy response to inference request in 1.2788565158843994s
Received healthy response to inference request in 1.274493932723999s
Received healthy response to inference request in 1.2721259593963623s
5 requests
0 failed requests
5th percentile: 1.2725995540618897
10th percentile: 1.273073148727417
20th percentile: 1.2740203380584716
30th percentile: 1.275366449356079
40th percentile: 1.2771114826202392
50th percentile: 1.2788565158843994
60th percentile: 1.2843451976776123
70th percentile: 1.2898338794708253
80th percentile: 1.4500570297241213
90th percentile: 1.7650146484375
95th percentile: 1.9224934577941892
99th percentile: 2.048476505279541
mean time: 1.4396053791046142
Pipeline stage StressChecker completed in 7.96s
thetsar1209-llama3-carpm_1580_v1 status is now deployed due to DeploymentManager action
thetsar1209-llama3-carpm_1580_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of thetsar1209-llama3-carpm_1580_v1
Running pipeline stage ISVCDeleter
Checking if service thetsar1209-llama3-carpm-1580-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.68s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key thetsar1209-llama3-carpm-1580-v1/config.json from bucket guanaco-mkml-models
Deleting key thetsar1209-llama3-carpm-1580-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key thetsar1209-llama3-carpm-1580-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key thetsar1209-llama3-carpm-1580-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key thetsar1209-llama3-carpm-1580-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key thetsar1209-llama3-carpm-1580-v1_reward/config.json from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carpm-1580-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carpm-1580-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carpm-1580-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carpm-1580-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carpm-1580-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carpm-1580-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.48s
thetsar1209-llama3-carpm_1580_v1 status is now torndown due to DeploymentManager action