hastagaras-kaliurang-8b-l3-g

developer_uid: Hastagaras

submission_id: hastagaras-kaliurang-8b-l3-g_v1

model_name: test-st-only

model_group: Hastagaras/Kaliurang-8B-

status: torndown

timestamp: 2024-07-12T11:44:25+00:00

num_battles: 20156

num_wins: 9989

celo_rating: 1183.08

family_friendly_score: 0.0

submission_type: basic

model_repo: Hastagaras/Kaliurang-8B-L3-G

model_architecture: LlamaForCausalLM

reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2

model_num_parameters: 8030261248.0

best_of: 16

max_input_tokens: 512

max_output_tokens: 64

display_name: test-st-only

is_internal_developer: False

language_model: Hastagaras/Kaliurang-8B-L3-G

model_size: 8B

ranking_group: single

us_pacific_date: 2024-07-12

win_ratio: 0.4955844413574122

generation_params: {'temperature': 1.05, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 50, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}

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}

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'}

Resubmit model

Running pipeline stage MKMLizer
Starting job with name hastagaras-kaliurang-8b-l3-g-v1-mkmlizer
Waiting for job on hastagaras-kaliurang-8b-l3-g-v1-mkmlizer to finish
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
hastagaras-kaliurang-8b-l3-g-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-kaliurang-8b-l3-g-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-kaliurang-8b-l3-g-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-kaliurang-8b-l3-g-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-kaliurang-8b-l3-g-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-kaliurang-8b-l3-g-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-kaliurang-8b-l3-g-v1-mkmlizer: ║                                                                     ║
hastagaras-kaliurang-8b-l3-g-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-kaliurang-8b-l3-g-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-kaliurang-8b-l3-g-v1-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-kaliurang-8b-l3-g-v1-mkmlizer: ║                                                                     ║
hastagaras-kaliurang-8b-l3-g-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-kaliurang-8b-l3-g-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-kaliurang-8b-l3-g-v1-mkmlizer: ║                                                                     ║
hastagaras-kaliurang-8b-l3-g-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-kaliurang-8b-l3-g-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-kaliurang-8b-l3-g-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
hastagaras-kaliurang-8b-l3-g-v1-mkmlizer: ║                                                                     ║
hastagaras-kaliurang-8b-l3-g-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-kaliurang-8b-l3-g-v1-mkmlizer: Downloaded to shared memory in 32.357s
hastagaras-kaliurang-8b-l3-g-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-kaliurang-8b-l3-g-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-kaliurang-8b-l3-g-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:02, 119.42it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:01, 142.49it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:01, 152.67it/s]
Loading 0:  22%|██▏       | 65/291 [00:00<00:01, 148.65it/s]
Loading 0:  27%|██▋       | 80/291 [00:00<00:01, 144.73it/s]
Loading 0:  33%|███▎      | 95/291 [00:00<00:02, 76.83it/s] 
Loading 0:  38%|███▊      | 112/291 [00:01<00:01, 94.40it/s]
Loading 0:  45%|████▍     | 130/291 [00:01<00:01, 110.26it/s]
Loading 0:  51%|█████     | 148/291 [00:01<00:01, 122.19it/s]
Loading 0:  57%|█████▋    | 166/291 [00:01<00:00, 132.30it/s]
Loading 0:  62%|██████▏   | 181/291 [00:01<00:00, 136.66it/s]
Loading 0:  67%|██████▋   | 196/291 [00:01<00:01, 85.81it/s] 
Loading 0:  73%|███████▎  | 212/291 [00:01<00:00, 98.51it/s]
Loading 0:  79%|███████▉  | 230/291 [00:02<00:00, 114.52it/s]
Loading 0:  85%|████████▌ | 248/291 [00:02<00:00, 127.62it/s]
Loading 0:  91%|█████████▏| 266/291 [00:02<00:00, 136.29it/s]
Loading 0:  98%|█████████▊| 285/291 [00:02<00:00, 149.20it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-kaliurang-8b-l3-g-v1-mkmlizer: quantized model in 23.003s
hastagaras-kaliurang-8b-l3-g-v1-mkmlizer: Processed model Hastagaras/Kaliurang-8B-L3-G in 55.360s
hastagaras-kaliurang-8b-l3-g-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-kaliurang-8b-l3-g-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-kaliurang-8b-l3-g-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-kaliurang-8b-l3-g-v1
hastagaras-kaliurang-8b-l3-g-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-kaliurang-8b-l3-g-v1/config.json
hastagaras-kaliurang-8b-l3-g-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-kaliurang-8b-l3-g-v1/special_tokens_map.json
hastagaras-kaliurang-8b-l3-g-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-kaliurang-8b-l3-g-v1/tokenizer_config.json
hastagaras-kaliurang-8b-l3-g-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-kaliurang-8b-l3-g-v1/tokenizer.json
hastagaras-kaliurang-8b-l3-g-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-kaliurang-8b-l3-g-v1/flywheel_model.0.safetensors
hastagaras-kaliurang-8b-l3-g-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-kaliurang-8b-l3-g-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.
hastagaras-kaliurang-8b-l3-g-v1-mkmlizer:   warnings.warn(
hastagaras-kaliurang-8b-l3-g-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`.
hastagaras-kaliurang-8b-l3-g-v1-mkmlizer:   warnings.warn(
hastagaras-kaliurang-8b-l3-g-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.
hastagaras-kaliurang-8b-l3-g-v1-mkmlizer:   warnings.warn(
hastagaras-kaliurang-8b-l3-g-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-kaliurang-8b-l3-g-v1-mkmlizer:   warnings.warn(
hastagaras-kaliurang-8b-l3-g-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-kaliurang-8b-l3-g-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-kaliurang-8b-l3-g-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-kaliurang-8b-l3-g-v1-mkmlizer: Saving duration: 2.051s
hastagaras-kaliurang-8b-l3-g-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.003s
hastagaras-kaliurang-8b-l3-g-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-kaliurang-8b-l3-g-v1_reward/reward.tensors
Connection pool is full, discarding connection: %s
Job hastagaras-kaliurang-8b-l3-g-v1-mkmlizer completed after 164.17s with status: succeeded
Stopping job with name hastagaras-kaliurang-8b-l3-g-v1-mkmlizer
Pipeline stage MKMLizer completed in 165.17s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-kaliurang-8b-l3-g-v1
Waiting for inference service hastagaras-kaliurang-8b-l3-g-v1 to be ready
Inference service hastagaras-kaliurang-8b-l3-g-v1 ready after 40.20961284637451s
Pipeline stage ISVCDeployer completed in 47.45s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.054060697555542s
Received healthy response to inference request in 1.3284788131713867s
Received healthy response to inference request in 1.3264272212982178s
Received healthy response to inference request in 1.2832753658294678s
Received healthy response to inference request in 1.346947431564331s
5 requests
0 failed requests
5th percentile: 1.2919057369232179
10th percentile: 1.3005361080169677
20th percentile: 1.3177968502044677
30th percentile: 1.3268375396728516
40th percentile: 1.3276581764221191
50th percentile: 1.3284788131713867
60th percentile: 1.3358662605285645
70th percentile: 1.3432537078857423
80th percentile: 1.4883700847625734
90th percentile: 1.7712153911590578
95th percentile: 1.9126380443572997
99th percentile: 2.0257761669158936
mean time: 1.4678379058837892
Pipeline stage StressChecker completed in 7.95s
hastagaras-kaliurang-8b-l3-g_v1 status is now deployed due to DeploymentManager action
hastagaras-kaliurang-8b-l3-g_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-kaliurang-8b-l3-g_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-kaliurang-8b-l3-g-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.76s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-kaliurang-8b-l3-g-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-kaliurang-8b-l3-g-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-kaliurang-8b-l3-g-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-kaliurang-8b-l3-g-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-kaliurang-8b-l3-g-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-kaliurang-8b-l3-g-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-kaliurang-8b-l3-g-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-kaliurang-8b-l3-g-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-kaliurang-8b-l3-g-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-kaliurang-8b-l3-g-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-kaliurang-8b-l3-g-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-kaliurang-8b-l3-g-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.25s
hastagaras-kaliurang-8b-l3-g_v1 status is now torndown due to DeploymentManager action