developer_uid: chace9580
submission_id: jic062-instruct_v9
model_name: jic062-instruct_v9
model_group: jic062/instruct
status: torndown
timestamp: 2024-07-29T17:55:55+00:00
num_battles: 14451
num_wins: 7913
celo_rating: 1230.21
family_friendly_score: 0.0
submission_type: basic
model_repo: jic062/instruct
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_v9
is_internal_developer: False
language_model: jic062/instruct
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-29
win_ratio: 0.5475745623140267
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}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{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-v9-mkmlizer
Waiting for job on jic062-instruct-v9-mkmlizer to finish
jic062-instruct-v9-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-instruct-v9-mkmlizer: ║     _____            __           __                                ║
jic062-instruct-v9-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jic062-instruct-v9-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jic062-instruct-v9-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jic062-instruct-v9-mkmlizer: ║       /___/                                                         ║
jic062-instruct-v9-mkmlizer: ║                                                                     ║
jic062-instruct-v9-mkmlizer: ║  Version: 0.9.7                                                     ║
jic062-instruct-v9-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jic062-instruct-v9-mkmlizer: ║  https://mk1.ai                                                     ║
jic062-instruct-v9-mkmlizer: ║                                                                     ║
jic062-instruct-v9-mkmlizer: ║  The license key for the current software has been verified as      ║
jic062-instruct-v9-mkmlizer: ║  belonging to:                                                      ║
jic062-instruct-v9-mkmlizer: ║                                                                     ║
jic062-instruct-v9-mkmlizer: ║  Chai Research Corp.                                                ║
jic062-instruct-v9-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jic062-instruct-v9-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
jic062-instruct-v9-mkmlizer: ║                                                                     ║
jic062-instruct-v9-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jic062-instruct-v9-mkmlizer: Downloaded to shared memory in 46.154s
jic062-instruct-v9-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpzsj7bt0m, device:0
jic062-instruct-v9-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jic062-instruct-v9-mkmlizer: quantized model in 27.136s
jic062-instruct-v9-mkmlizer: Processed model jic062/instruct in 73.290s
jic062-instruct-v9-mkmlizer: creating bucket guanaco-mkml-models
jic062-instruct-v9-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-instruct-v9-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-instruct-v9
jic062-instruct-v9-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-instruct-v9/config.json
jic062-instruct-v9-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-instruct-v9/special_tokens_map.json
jic062-instruct-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-instruct-v9/tokenizer_config.json
jic062-instruct-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-instruct-v9/tokenizer.json
jic062-instruct-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-instruct-v9/flywheel_model.0.safetensors
jic062-instruct-v9-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
jic062-instruct-v9-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 49.70it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:04, 64.03it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:03, 71.76it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:03, 76.05it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:03, 77.84it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:03, 74.15it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:03, 76.33it/s]
Loading 0:  24%|██▍       | 70/291 [00:00<00:02, 76.60it/s]
Loading 0:  27%|██▋       | 79/291 [00:01<00:02, 75.29it/s]
Loading 0:  30%|██▉       | 87/291 [00:02<00:10, 19.03it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:08, 23.20it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:06, 29.69it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:04, 36.90it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 43.65it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 50.24it/s]
Loading 0:  48%|████▊     | 139/291 [00:03<00:02, 55.44it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:02, 61.01it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 63.93it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:01, 67.67it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:01, 69.86it/s]
Loading 0:  63%|██████▎   | 184/291 [00:03<00:01, 72.79it/s]
Loading 0:  66%|██████▌   | 192/291 [00:04<00:04, 20.46it/s]
Loading 0:  68%|██████▊   | 198/291 [00:04<00:03, 23.50it/s]
Loading 0:  70%|███████   | 205/291 [00:04<00:03, 28.20it/s]
Loading 0:  74%|███████▎  | 214/291 [00:05<00:02, 35.73it/s]
Loading 0:  77%|███████▋  | 223/291 [00:05<00:01, 42.22it/s]
Loading 0:  80%|███████▉  | 232/291 [00:05<00:01, 48.91it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:00, 55.13it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 58.73it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 63.80it/s]
Loading 0:  92%|█████████▏| 268/291 [00:05<00:00, 68.08it/s]
Loading 0:  95%|█████████▌| 277/291 [00:05<00:00, 70.42it/s]
Loading 0:  98%|█████████▊| 286/291 [00:06<00:00, 73.27it/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-v9-mkmlizer:   warnings.warn(
jic062-instruct-v9-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-v9-mkmlizer:   warnings.warn(
jic062-instruct-v9-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-v9-mkmlizer:   warnings.warn(
jic062-instruct-v9-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jic062-instruct-v9-mkmlizer: Saving duration: 1.367s
jic062-instruct-v9-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.217s
jic062-instruct-v9-mkmlizer: creating bucket guanaco-reward-models
jic062-instruct-v9-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jic062-instruct-v9-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jic062-instruct-v9_reward
jic062-instruct-v9-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jic062-instruct-v9_reward/special_tokens_map.json
jic062-instruct-v9-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jic062-instruct-v9_reward/config.json
jic062-instruct-v9-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jic062-instruct-v9_reward/tokenizer_config.json
jic062-instruct-v9-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jic062-instruct-v9_reward/merges.txt
jic062-instruct-v9-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jic062-instruct-v9_reward/vocab.json
jic062-instruct-v9-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jic062-instruct-v9_reward/tokenizer.json
jic062-instruct-v9-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/jic062-instruct-v9_reward/reward.tensors
Job jic062-instruct-v9-mkmlizer completed after 116.57s with status: succeeded
Stopping job with name jic062-instruct-v9-mkmlizer
Pipeline stage MKMLizer completed in 117.56s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.38s
Running pipeline stage ISVCDeployer
Creating inference service jic062-instruct-v9
Waiting for inference service jic062-instruct-v9 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service jic062-instruct-v9 ready after 110.92461585998535s
Pipeline stage ISVCDeployer completed in 112.64s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2344071865081787s
Received healthy response to inference request in 1.3950812816619873s
Received healthy response to inference request in 1.406428575515747s
Received healthy response to inference request in 1.4018890857696533s
Received healthy response to inference request in 1.4169793128967285s
5 requests
0 failed requests
5th percentile: 1.3964428424835205
10th percentile: 1.3978044033050536
20th percentile: 1.4005275249481202
30th percentile: 1.402796983718872
40th percentile: 1.4046127796173096
50th percentile: 1.406428575515747
60th percentile: 1.4106488704681397
70th percentile: 1.4148691654205323
80th percentile: 1.5804648876190188
90th percentile: 1.9074360370635988
95th percentile: 2.0709216117858884
99th percentile: 2.2017100715637206
mean time: 1.570957088470459
Pipeline stage StressChecker completed in 8.47s
jic062-instruct_v9 status is now deployed due to DeploymentManager action
jic062-instruct_v9 status is now inactive due to auto deactivation removed underperforming models
jic062-instruct_v9 status is now deployed due to admin request
jic062-instruct_v9 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of jic062-instruct_v9
Running pipeline stage ISVCDeleter
Checking if service jic062-instruct-v9 is running
Tearing down inference service jic062-instruct-v9
Service jic062-instruct-v9 has been torndown
Pipeline stage ISVCDeleter completed in 5.11s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key jic062-instruct-v9/config.json from bucket guanaco-mkml-models
Deleting key jic062-instruct-v9/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key jic062-instruct-v9/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key jic062-instruct-v9/tokenizer.json from bucket guanaco-mkml-models
Deleting key jic062-instruct-v9/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key jic062-instruct-v9_reward/config.json from bucket guanaco-reward-models
Deleting key jic062-instruct-v9_reward/merges.txt from bucket guanaco-reward-models
Deleting key jic062-instruct-v9_reward/reward.tensors from bucket guanaco-reward-models
Deleting key jic062-instruct-v9_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key jic062-instruct-v9_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key jic062-instruct-v9_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key jic062-instruct-v9_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.62s
jic062-instruct_v9 status is now torndown due to DeploymentManager action