sao10k-hydrochoerus-12b-v1-s1

developer_uid: sao10k

submission_id: sao10k-hydrochoerus-12b-v1-s1_v3

model_name: v1test2

model_group: Sao10K/Hydrochoerus-12B-

status: torndown

timestamp: 2024-07-28T15:24:37+00:00

num_battles: 1

num_wins: 0

family_friendly_score: 0.0

submission_type: basic

model_repo: Sao10K/Hydrochoerus-12B-v1-s1

model_architecture: MistralForCausalLM

reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 512

max_output_tokens: 64

display_name: v1test2

ineligible_reason: num_battles<5000

is_internal_developer: False

language_model: Sao10K/Hydrochoerus-12B-v1-s1

model_size: 13B

ranking_group: single

us_pacific_date: 2024-07-28

win_ratio: 0.0

generation_params: {'temperature': 0.45, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '\n\n', '\nYou:', '<|im_end|>', '</s>'], 'max_input_tokens': 512, 'best_of': 8, 'max_output_tokens': 64, 'reward_max_token_input': 1024}

formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\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 sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer
Waiting for job on sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer to finish
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: ║     _____            __           __                                ║
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: ║       /___/                                                         ║
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: ║                                                                     ║
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: ║  Version: 0.9.7                                                     ║
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: ║  https://mk1.ai                                                     ║
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: ║                                                                     ║
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: ║  belonging to:                                                      ║
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: ║                                                                     ║
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: ║                                                                     ║
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: Downloaded to shared memory in 31.047s
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpu92yh4t0, device:0
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: quantized model in 35.882s
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: Processed model Sao10K/Hydrochoerus-12B-v1-s1 in 66.930s
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-hydrochoerus-12b-v1-s1-v3
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-hydrochoerus-12b-v1-s1-v3/config.json
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-hydrochoerus-12b-v1-s1-v3/special_tokens_map.json
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-hydrochoerus-12b-v1-s1-v3/tokenizer_config.json
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-hydrochoerus-12b-v1-s1-v3/tokenizer.json
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-hydrochoerus-12b-v1-s1-v3/flywheel_model.0.safetensors
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:785: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer:   warnings.warn(
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:469: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer:   warnings.warn(
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:05<00:05,  6.00s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  4.02s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  4.31s/it]
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  2.36it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.89it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.55it/s]
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: Saving duration: 1.379s
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.715s
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: creating bucket guanaco-reward-models
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/sao10k-hydrochoerus-12b-v1-s1-v3_reward
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/sao10k-hydrochoerus-12b-v1-s1-v3_reward/special_tokens_map.json
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/sao10k-hydrochoerus-12b-v1-s1-v3_reward/config.json
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/sao10k-hydrochoerus-12b-v1-s1-v3_reward/tokenizer_config.json
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-hydrochoerus-12b-v1-s1-v3_reward/merges.txt
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-hydrochoerus-12b-v1-s1-v3_reward/vocab.json
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-hydrochoerus-12b-v1-s1-v3_reward/tokenizer.json
sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-hydrochoerus-12b-v1-s1-v3_reward/reward.tensors
Job sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer completed after 116.15s with status: succeeded
Stopping job with name sao10k-hydrochoerus-12b-v1-s1-v3-mkmlizer
Pipeline stage MKMLizer completed in 117.13s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-hydrochoerus-12b-v1-s1-v3
Waiting for inference service sao10k-hydrochoerus-12b-v1-s1-v3 to be ready
Inference service sao10k-hydrochoerus-12b-v1-s1-v3 ready after 91.00544667243958s
Pipeline stage ISVCDeployer completed in 92.54s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.704437017440796s
Received healthy response to inference request in 1.560438632965088s
Received healthy response to inference request in 1.5937230587005615s
Received healthy response to inference request in 1.4819927215576172s
Received healthy response to inference request in 1.6443474292755127s
5 requests
0 failed requests
5th percentile: 1.4976819038391114
10th percentile: 1.5133710861206056
20th percentile: 1.5447494506835937
30th percentile: 1.5670955181121826
40th percentile: 1.580409288406372
50th percentile: 1.5937230587005615
60th percentile: 1.613972806930542
70th percentile: 1.6342225551605225
80th percentile: 1.8563653469085695
90th percentile: 2.280401182174683
95th percentile: 2.492419099807739
99th percentile: 2.6620334339141847
mean time: 1.796987771987915
Pipeline stage StressChecker completed in 9.74s
sao10k-hydrochoerus-12b-v1-s1_v3 status is now deployed due to DeploymentManager action
sao10k-hydrochoerus-12b-v1-s1_v3 status is now inactive due to admin request
admin requested tearing down of sao10k-hydrochoerus-12b-v1-s1_v3
Running pipeline stage ISVCDeleter
Checking if service sao10k-hydrochoerus-12b-v1-s1-v3 is running
Tearing down inference service sao10k-hydrochoerus-12b-v1-s1-v3
Service sao10k-hydrochoerus-12b-v1-s1-v3 has been torndown
Pipeline stage ISVCDeleter completed in 5.16s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key sao10k-hydrochoerus-12b-v1-s1-v3/config.json from bucket guanaco-mkml-models
Deleting key sao10k-hydrochoerus-12b-v1-s1-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key sao10k-hydrochoerus-12b-v1-s1-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key sao10k-hydrochoerus-12b-v1-s1-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key sao10k-hydrochoerus-12b-v1-s1-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key sao10k-hydrochoerus-12b-v1-s1-v3_reward/config.json from bucket guanaco-reward-models
Deleting key sao10k-hydrochoerus-12b-v1-s1-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key sao10k-hydrochoerus-12b-v1-s1-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key sao10k-hydrochoerus-12b-v1-s1-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key sao10k-hydrochoerus-12b-v1-s1-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key sao10k-hydrochoerus-12b-v1-s1-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key sao10k-hydrochoerus-12b-v1-s1-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.90s
sao10k-hydrochoerus-12b-v1-s1_v3 status is now torndown due to DeploymentManager action