developer_uid: Hastagaras
submission_id: hastagaras-kaliurang-8b-l3-mt_v2
model_name: kaliurang
model_group: Hastagaras/Kaliurang-8B-
status: torndown
timestamp: 2024-07-08T02:11:27+00:00
num_battles: 30666
num_wins: 14867
celo_rating: 1181.5
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/Kaliurang-8B-L3-MT
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: kaliurang
is_internal_developer: False
language_model: Hastagaras/Kaliurang-8B-L3-MT
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-07
win_ratio: 0.4848040174786408
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.075, '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}
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-mt-v2-mkmlizer
Waiting for job on hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer to finish
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: ║     _____            __           __                                ║
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: ║       /___/                                                         ║
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: ║                                                                     ║
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: ║                                                                     ║
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: ║  belonging to:                                                      ║
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: ║                                                                     ║
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: ║                                                                     ║
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: Downloaded to shared memory in 53.275s
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:02, 119.55it/s]
Loading 0:   8%|▊         | 24/291 [00:00<00:02, 119.53it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:01, 130.44it/s]
Loading 0:  20%|█▉        | 57/291 [00:00<00:01, 139.31it/s]
Loading 0:  24%|██▍       | 71/291 [00:00<00:01, 136.64it/s]
Loading 0:  29%|██▉       | 85/291 [00:01<00:03, 61.34it/s] 
Loading 0:  35%|███▌      | 102/291 [00:01<00:02, 78.25it/s]
Loading 0:  39%|███▉      | 114/291 [00:01<00:02, 85.23it/s]
Loading 0:  45%|████▍     | 130/291 [00:01<00:01, 100.01it/s]
Loading 0:  51%|█████     | 147/291 [00:01<00:01, 113.13it/s]
Loading 0:  55%|█████▌    | 161/291 [00:01<00:01, 118.29it/s]
Loading 0:  62%|██████▏   | 179/291 [00:01<00:00, 129.21it/s]
Loading 0:  67%|██████▋   | 194/291 [00:02<00:01, 74.13it/s] 
Loading 0:  73%|███████▎  | 211/291 [00:02<00:00, 88.44it/s]
Loading 0:  77%|███████▋  | 224/291 [00:02<00:00, 95.48it/s]
Loading 0:  82%|████████▏ | 238/291 [00:02<00:00, 104.04it/s]
Loading 0:  88%|████████▊ | 255/291 [00:02<00:00, 115.95it/s]
Loading 0:  92%|█████████▏| 269/291 [00:02<00:00, 117.94it/s]
Loading 0:  97%|█████████▋| 283/291 [00:02<00:00, 120.96it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: quantized model in 24.217s
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: Processed model Hastagaras/Kaliurang-8B-L3-MT in 77.493s
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-kaliurang-8b-l3-mt-v2
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-kaliurang-8b-l3-mt-v2/config.json
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-kaliurang-8b-l3-mt-v2/tokenizer_config.json
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-kaliurang-8b-l3-mt-v2/special_tokens_map.json
Retrying (%r) after connection broken by '%r': %s
hastagaras-kaliurang-8b-l3-mt-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-kaliurang-8b-l3-mt-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: Saving duration: 0.432s
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.766s
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-kaliurang-8b-l3-mt-v2_reward
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-kaliurang-8b-l3-mt-v2_reward/special_tokens_map.json
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-kaliurang-8b-l3-mt-v2_reward/merges.txt
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-kaliurang-8b-l3-mt-v2_reward/tokenizer_config.json
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-kaliurang-8b-l3-mt-v2_reward/config.json
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-kaliurang-8b-l3-mt-v2_reward/vocab.json
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-kaliurang-8b-l3-mt-v2_reward/tokenizer.json
hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-kaliurang-8b-l3-mt-v2_reward/reward.tensors
Job hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer completed after 124.07s with status: succeeded
Stopping job with name hastagaras-kaliurang-8b-l3-mt-v2-mkmlizer
Pipeline stage MKMLizer completed in 124.91s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-kaliurang-8b-l3-mt-v2
Waiting for inference service hastagaras-kaliurang-8b-l3-mt-v2 to be ready
Failed to get response for submission mistralai-mixtral-8x7b-_3473_v61: ('http://mistralai-mixtral-8x7b-3473-v61-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'upstream connect error or disconnect/reset before headers. reset reason: connection timeout')
Inference service hastagaras-kaliurang-8b-l3-mt-v2 ready after 40.18975210189819s
Pipeline stage ISVCDeployer completed in 47.04s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.031346082687378s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Received healthy response to inference request in 1.3334264755249023s
Received healthy response to inference request in 1.2889275550842285s
Received healthy response to inference request in 1.3246314525604248s
Received healthy response to inference request in 1.3494746685028076s
5 requests
0 failed requests
5th percentile: 1.2960683345794677
10th percentile: 1.303209114074707
20th percentile: 1.3174906730651856
30th percentile: 1.3263904571533203
40th percentile: 1.3299084663391114
50th percentile: 1.3334264755249023
60th percentile: 1.3398457527160645
70th percentile: 1.3462650299072265
80th percentile: 1.4858489513397217
90th percentile: 1.75859751701355
95th percentile: 1.8949717998504638
99th percentile: 2.004071226119995
mean time: 1.4655612468719483
Pipeline stage StressChecker completed in 8.32s
hastagaras-kaliurang-8b-l3-mt_v2 status is now deployed due to DeploymentManager action
hastagaras-kaliurang-8b-l3-mt_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-kaliurang-8b-l3-mt_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-kaliurang-8b-l3-mt-v2 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-mt-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-kaliurang-8b-l3-mt-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-kaliurang-8b-l3-mt-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-kaliurang-8b-l3-mt-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-kaliurang-8b-l3-mt-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-kaliurang-8b-l3-mt-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-kaliurang-8b-l3-mt-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-kaliurang-8b-l3-mt-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-kaliurang-8b-l3-mt-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-kaliurang-8b-l3-mt-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-kaliurang-8b-l3-mt-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-kaliurang-8b-l3-mt-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.37s
hastagaras-kaliurang-8b-l3-mt_v2 status is now torndown due to DeploymentManager action