developer_uid: chace9580
submission_id: jic062-instruct_v10
model_name: jic062-instruct_v10
model_group: jic062/instruct
status: torndown
timestamp: 2024-07-30T20:55:36+00:00
num_battles: 13202
num_wins: 6122
celo_rating: 1178.09
family_friendly_score: 0.0
submission_type: basic
model_repo: jic062/instruct
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: jic062-instruct_v10
is_internal_developer: False
language_model: jic062/instruct
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-30
win_ratio: 0.46371761854264504
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', '<|end_of_text|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64, 'reward_max_token_input': 256}
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 jic062-instruct-v10-mkmlizer
Waiting for job on jic062-instruct-v10-mkmlizer to finish
jic062-instruct-v10-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-instruct-v10-mkmlizer: ║     _____            __           __                                ║
jic062-instruct-v10-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jic062-instruct-v10-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jic062-instruct-v10-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jic062-instruct-v10-mkmlizer: ║       /___/                                                         ║
jic062-instruct-v10-mkmlizer: ║                                                                     ║
jic062-instruct-v10-mkmlizer: ║  Version: 0.9.7                                                     ║
jic062-instruct-v10-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jic062-instruct-v10-mkmlizer: ║  https://mk1.ai                                                     ║
jic062-instruct-v10-mkmlizer: ║                                                                     ║
jic062-instruct-v10-mkmlizer: ║  The license key for the current software has been verified as      ║
jic062-instruct-v10-mkmlizer: ║  belonging to:                                                      ║
jic062-instruct-v10-mkmlizer: ║                                                                     ║
jic062-instruct-v10-mkmlizer: ║  Chai Research Corp.                                                ║
jic062-instruct-v10-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jic062-instruct-v10-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
jic062-instruct-v10-mkmlizer: ║                                                                     ║
jic062-instruct-v10-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jic062-instruct-v10-mkmlizer: Downloaded to shared memory in 33.892s
jic062-instruct-v10-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpwvn1r3q5, device:0
jic062-instruct-v10-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jic062-instruct-v10-mkmlizer: quantized model in 26.130s
jic062-instruct-v10-mkmlizer: Processed model jic062/instruct in 60.022s
jic062-instruct-v10-mkmlizer: creating bucket guanaco-mkml-models
jic062-instruct-v10-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-instruct-v10-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-instruct-v10
jic062-instruct-v10-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-instruct-v10/config.json
jic062-instruct-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-instruct-v10/tokenizer_config.json
jic062-instruct-v10-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-instruct-v10/special_tokens_map.json
jic062-instruct-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-instruct-v10/tokenizer.json
jic062-instruct-v10-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-instruct-v10/flywheel_model.0.safetensors
jic062-instruct-v10-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
jic062-instruct-v10-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 54.21it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:03, 70.13it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:03, 76.79it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:03, 80.05it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:02, 82.90it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:03, 79.34it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:02, 81.53it/s]
Loading 0:  24%|██▍       | 70/291 [00:00<00:02, 82.80it/s]
Loading 0:  27%|██▋       | 79/291 [00:01<00:02, 80.17it/s]
Loading 0:  30%|███       | 88/291 [00:02<00:10, 18.58it/s]
Loading 0:  33%|███▎      | 97/291 [00:02<00:07, 24.38it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:04, 35.97it/s]
Loading 0:  42%|████▏     | 123/291 [00:02<00:03, 45.30it/s]
Loading 0:  45%|████▌     | 132/291 [00:02<00:03, 50.23it/s]
Loading 0:  48%|████▊     | 141/291 [00:02<00:02, 56.46it/s]
Loading 0:  52%|█████▏    | 150/291 [00:03<00:02, 62.66it/s]
Loading 0:  55%|█████▍    | 160/291 [00:03<00:02, 65.05it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:01, 70.29it/s]
Loading 0:  63%|██████▎   | 184/291 [00:03<00:01, 80.51it/s]
Loading 0:  66%|██████▋   | 193/291 [00:04<00:03, 24.58it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:02, 30.37it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:02, 36.96it/s]
Loading 0:  77%|███████▋  | 223/291 [00:04<00:01, 45.68it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:00, 57.78it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:00, 62.28it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 67.64it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 72.51it/s]
Loading 0:  94%|█████████▍| 274/291 [00:05<00:00, 73.79it/s]
Loading 0:  97%|█████████▋| 283/291 [00:05<00:00, 73.43it/s]
                                                            
/opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:957: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
jic062-instruct-v10-mkmlizer:   warnings.warn(
jic062-instruct-v10-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.
jic062-instruct-v10-mkmlizer:   warnings.warn(
jic062-instruct-v10-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.
jic062-instruct-v10-mkmlizer:   warnings.warn(
jic062-instruct-v10-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:05<00:05,  5.52s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  4.15s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  4.36s/it]
jic062-instruct-v10-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  2.45it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  4.05it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.69it/s]
jic062-instruct-v10-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jic062-instruct-v10-mkmlizer: Saving duration: 1.343s
jic062-instruct-v10-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.656s
jic062-instruct-v10-mkmlizer: creating bucket guanaco-reward-models
jic062-instruct-v10-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jic062-instruct-v10-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jic062-instruct-v10_reward
jic062-instruct-v10-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jic062-instruct-v10_reward/config.json
jic062-instruct-v10-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jic062-instruct-v10_reward/special_tokens_map.json
jic062-instruct-v10-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jic062-instruct-v10_reward/tokenizer_config.json
jic062-instruct-v10-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jic062-instruct-v10_reward/merges.txt
jic062-instruct-v10-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jic062-instruct-v10_reward/vocab.json
jic062-instruct-v10-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jic062-instruct-v10_reward/tokenizer.json
Job jic062-instruct-v10-mkmlizer completed after 105.51s with status: succeeded
Stopping job with name jic062-instruct-v10-mkmlizer
Pipeline stage MKMLizer completed in 106.54s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service jic062-instruct-v10
Waiting for inference service jic062-instruct-v10 to be ready
Inference service jic062-instruct-v10 ready after 121.26066493988037s
Pipeline stage ISVCDeployer completed in 123.36s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.152294158935547s
Received healthy response to inference request in 1.3524055480957031s
Received healthy response to inference request in 1.428758144378662s
Received healthy response to inference request in 1.3308846950531006s
Received healthy response to inference request in 1.4500935077667236s
5 requests
0 failed requests
5th percentile: 1.335188865661621
10th percentile: 1.3394930362701416
20th percentile: 1.3481013774871826
30th percentile: 1.367676067352295
40th percentile: 1.3982171058654784
50th percentile: 1.428758144378662
60th percentile: 1.4372922897338867
70th percentile: 1.4458264350891112
80th percentile: 1.5905336380004884
90th percentile: 1.8714138984680178
95th percentile: 2.011854028701782
99th percentile: 2.124206132888794
mean time: 1.5428872108459473
Pipeline stage StressChecker completed in 8.38s
jic062-instruct_v10 status is now deployed due to DeploymentManager action
jic062-instruct_v10 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of jic062-instruct_v10
Running pipeline stage ISVCDeleter
Checking if service jic062-instruct-v10 is running
Tearing down inference service jic062-instruct-v10
Service jic062-instruct-v10 has been torndown
Pipeline stage ISVCDeleter completed in 4.74s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key jic062-instruct-v10/config.json from bucket guanaco-mkml-models
Deleting key jic062-instruct-v10/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key jic062-instruct-v10/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key jic062-instruct-v10/tokenizer.json from bucket guanaco-mkml-models
Deleting key jic062-instruct-v10/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key jic062-instruct-v10_reward/config.json from bucket guanaco-reward-models
Deleting key jic062-instruct-v10_reward/merges.txt from bucket guanaco-reward-models
Deleting key jic062-instruct-v10_reward/reward.tensors from bucket guanaco-reward-models
Deleting key jic062-instruct-v10_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key jic062-instruct-v10_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key jic062-instruct-v10_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key jic062-instruct-v10_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.37s
jic062-instruct_v10 status is now torndown due to DeploymentManager action