developer_uid: chace9580
submission_id: jic062-instruct-v17-g4_v1
model_name: jic062-instruct-v17-g4_v1
model_group: jic062/instruct_v17_g4
status: torndown
timestamp: 2024-08-04T03:49:24+00:00
num_battles: 12571
num_wins: 6519
celo_rating: 1226.12
family_friendly_score: 0.0
submission_type: basic
model_repo: jic062/instruct_v17_g4
model_architecture: LlamaForCausalLM
reward_repo: Jellywibble/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-v17-g4_v1
is_internal_developer: False
language_model: jic062/instruct_v17_g4
model_size: 8B
ranking_group: single
us_pacific_date: 2024-08-03
win_ratio: 0.5185744968578474
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|>', '|eot_id|'], '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-v17-g4-v1-mkmlizer
Waiting for job on jic062-instruct-v17-g4-v1-mkmlizer to finish
Stopping job with name jic062-instruct-v17-g4-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name jic062-instruct-v17-g4-v1-mkmlizer
Waiting for job on jic062-instruct-v17-g4-v1-mkmlizer to finish
jic062-instruct-v17-g4-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-instruct-v17-g4-v1-mkmlizer: ║     _____            __           __                                ║
jic062-instruct-v17-g4-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jic062-instruct-v17-g4-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jic062-instruct-v17-g4-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jic062-instruct-v17-g4-v1-mkmlizer: ║       /___/                                                         ║
jic062-instruct-v17-g4-v1-mkmlizer: ║                                                                     ║
jic062-instruct-v17-g4-v1-mkmlizer: ║  Version: 0.9.9                                                     ║
jic062-instruct-v17-g4-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jic062-instruct-v17-g4-v1-mkmlizer: ║  https://mk1.ai                                                     ║
jic062-instruct-v17-g4-v1-mkmlizer: ║                                                                     ║
jic062-instruct-v17-g4-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
jic062-instruct-v17-g4-v1-mkmlizer: ║  belonging to:                                                      ║
jic062-instruct-v17-g4-v1-mkmlizer: ║                                                                     ║
jic062-instruct-v17-g4-v1-mkmlizer: ║  Chai Research Corp.                                                ║
jic062-instruct-v17-g4-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jic062-instruct-v17-g4-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
jic062-instruct-v17-g4-v1-mkmlizer: ║                                                                     ║
jic062-instruct-v17-g4-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jic062-instruct-v17-g4-v1-mkmlizer: Downloaded to shared memory in 30.942s
jic062-instruct-v17-g4-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp09zqm_yy, device:0
jic062-instruct-v17-g4-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jic062-instruct-v17-g4-v1-mkmlizer: quantized model in 26.026s
jic062-instruct-v17-g4-v1-mkmlizer: Processed model jic062/instruct_v17_g4 in 56.968s
jic062-instruct-v17-g4-v1-mkmlizer: creating bucket guanaco-mkml-models
jic062-instruct-v17-g4-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-instruct-v17-g4-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-instruct-v17-g4-v1
jic062-instruct-v17-g4-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-instruct-v17-g4-v1/config.json
jic062-instruct-v17-g4-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-instruct-v17-g4-v1/special_tokens_map.json
jic062-instruct-v17-g4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-instruct-v17-g4-v1/tokenizer_config.json
jic062-instruct-v17-g4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-instruct-v17-g4-v1/tokenizer.json
jic062-instruct-v17-g4-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-instruct-v17-g4-v1/flywheel_model.0.safetensors
jic062-instruct-v17-g4-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
jic062-instruct-v17-g4-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 50.71it/s]
Loading 0:   6%|▌         | 17/291 [00:00<00:03, 74.96it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:03, 76.94it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:03, 78.48it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:03, 79.24it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:02, 80.17it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:02, 81.51it/s]
Loading 0:  24%|██▍       | 70/291 [00:00<00:02, 80.32it/s]
Loading 0:  27%|██▋       | 79/291 [00:01<00:02, 78.71it/s]
Loading 0:  30%|██▉       | 87/291 [00:02<00:09, 20.74it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:07, 25.25it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:05, 32.13it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:04, 39.83it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 47.91it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:02, 55.05it/s]
Loading 0:  48%|████▊     | 139/291 [00:02<00:02, 59.73it/s]
Loading 0:  51%|█████     | 148/291 [00:02<00:02, 61.95it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:01, 67.42it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:01, 71.99it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:01, 73.11it/s]
Loading 0:  63%|██████▎   | 184/291 [00:03<00:01, 75.61it/s]
Loading 0:  66%|██████▌   | 192/291 [00:04<00:04, 21.93it/s]
Loading 0:  68%|██████▊   | 198/291 [00:04<00:03, 25.54it/s]
Loading 0:  70%|███████   | 205/291 [00:04<00:02, 30.60it/s]
Loading 0:  74%|███████▎  | 214/291 [00:04<00:01, 39.06it/s]
Loading 0:  77%|███████▋  | 223/291 [00:04<00:01, 46.50it/s]
Loading 0:  80%|███████▉  | 232/291 [00:04<00:01, 54.11it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:00, 60.25it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 66.36it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 71.04it/s]
Loading 0:  92%|█████████▏| 268/291 [00:05<00:00, 73.79it/s]
Loading 0:  95%|█████████▌| 277/291 [00:05<00:00, 73.74it/s]
Loading 0:  98%|█████████▊| 286/291 [00:05<00:00, 74.41it/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-v17-g4-v1-mkmlizer:   warnings.warn(
jic062-instruct-v17-g4-v1-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-v17-g4-v1-mkmlizer:   warnings.warn(
jic062-instruct-v17-g4-v1-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-v17-g4-v1-mkmlizer:   warnings.warn(
jic062-instruct-v17-g4-v1-mkmlizer: Saving duration: 1.440s
jic062-instruct-v17-g4-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.706s
jic062-instruct-v17-g4-v1-mkmlizer: creating bucket guanaco-reward-models
jic062-instruct-v17-g4-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jic062-instruct-v17-g4-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jic062-instruct-v17-g4-v1_reward
jic062-instruct-v17-g4-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jic062-instruct-v17-g4-v1_reward/config.json
jic062-instruct-v17-g4-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jic062-instruct-v17-g4-v1_reward/special_tokens_map.json
jic062-instruct-v17-g4-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jic062-instruct-v17-g4-v1_reward/tokenizer_config.json
jic062-instruct-v17-g4-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jic062-instruct-v17-g4-v1_reward/merges.txt
jic062-instruct-v17-g4-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jic062-instruct-v17-g4-v1_reward/vocab.json
jic062-instruct-v17-g4-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jic062-instruct-v17-g4-v1_reward/tokenizer.json
jic062-instruct-v17-g4-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/jic062-instruct-v17-g4-v1_reward/reward.tensors
Job jic062-instruct-v17-g4-v1-mkmlizer completed after 105.12s with status: succeeded
Stopping job with name jic062-instruct-v17-g4-v1-mkmlizer
Pipeline stage MKMLizer completed in 106.71s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service jic062-instruct-v17-g4-v1
Waiting for inference service jic062-instruct-v17-g4-v1 to be ready
Inference service jic062-instruct-v17-g4-v1 ready after 161.01621437072754s
Pipeline stage ISVCDeployer completed in 162.93s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.265840768814087s
Received healthy response to inference request in 1.4394869804382324s
Received healthy response to inference request in 1.4101881980895996s
Received healthy response to inference request in 1.3942220211029053s
Received healthy response to inference request in 1.4834036827087402s
5 requests
0 failed requests
5th percentile: 1.3974152565002442
10th percentile: 1.400608491897583
20th percentile: 1.4069949626922607
30th percentile: 1.416047954559326
40th percentile: 1.4277674674987793
50th percentile: 1.4394869804382324
60th percentile: 1.4570536613464355
70th percentile: 1.4746203422546387
80th percentile: 1.6398910999298097
90th percentile: 1.9528659343719483
95th percentile: 2.1093533515930174
99th percentile: 2.234543285369873
mean time: 1.598628330230713
Pipeline stage StressChecker completed in 8.79s
jic062-instruct-v17-g4_v1 status is now deployed due to DeploymentManager action
jic062-instruct-v17-g4_v1 status is now inactive due to auto deactivation removed underperforming models
jic062-instruct-v17-g4_v1 status is now torndown due to DeploymentManager action