developer_uid: chace9580
submission_id: jic062-instruct_v13
model_name: jic062-instruct_v13
model_group: jic062/instruct
status: torndown
timestamp: 2024-07-31T05:57:46+00:00
num_battles: 12760
num_wins: 6484
celo_rating: 1213.56
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_v13
is_internal_developer: False
language_model: jic062/instruct
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-30
win_ratio: 0.5081504702194357
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': "{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-v13-mkmlizer
Waiting for job on jic062-instruct-v13-mkmlizer to finish
jic062-instruct-v13-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-instruct-v13-mkmlizer: ║     _____            __           __                                ║
jic062-instruct-v13-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jic062-instruct-v13-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jic062-instruct-v13-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jic062-instruct-v13-mkmlizer: ║       /___/                                                         ║
jic062-instruct-v13-mkmlizer: ║                                                                     ║
jic062-instruct-v13-mkmlizer: ║  Version: 0.9.7                                                     ║
jic062-instruct-v13-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jic062-instruct-v13-mkmlizer: ║  https://mk1.ai                                                     ║
jic062-instruct-v13-mkmlizer: ║                                                                     ║
jic062-instruct-v13-mkmlizer: ║  The license key for the current software has been verified as      ║
jic062-instruct-v13-mkmlizer: ║  belonging to:                                                      ║
jic062-instruct-v13-mkmlizer: ║                                                                     ║
jic062-instruct-v13-mkmlizer: ║  Chai Research Corp.                                                ║
jic062-instruct-v13-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jic062-instruct-v13-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
jic062-instruct-v13-mkmlizer: ║                                                                     ║
jic062-instruct-v13-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jic062-instruct-v13-mkmlizer: Downloaded to shared memory in 22.203s
jic062-instruct-v13-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp21pmfpgs, device:0
jic062-instruct-v13-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jic062-instruct-v13-mkmlizer: quantized model in 26.320s
jic062-instruct-v13-mkmlizer: Processed model jic062/instruct in 48.524s
jic062-instruct-v13-mkmlizer: creating bucket guanaco-mkml-models
jic062-instruct-v13-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-instruct-v13-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-instruct-v13
jic062-instruct-v13-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-instruct-v13/config.json
jic062-instruct-v13-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-instruct-v13/special_tokens_map.json
jic062-instruct-v13-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-instruct-v13/tokenizer_config.json
jic062-instruct-v13-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-instruct-v13/tokenizer.json
jic062-instruct-v13-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-instruct-v13/flywheel_model.0.safetensors
jic062-instruct-v13-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
jic062-instruct-v13-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:06, 46.55it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:04, 64.35it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:03, 72.98it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:03, 76.86it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:03, 80.33it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:03, 75.83it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:03, 73.49it/s]
Loading 0:  24%|██▍       | 70/291 [00:00<00:03, 73.47it/s]
Loading 0:  27%|██▋       | 79/291 [00:01<00:02, 75.15it/s]
Loading 0:  30%|██▉       | 87/291 [00:02<00:10, 20.34it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:07, 24.81it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:05, 31.56it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:04, 39.02it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 46.67it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 52.29it/s]
Loading 0:  48%|████▊     | 139/291 [00:02<00:02, 57.48it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:02, 61.24it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 66.83it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:01, 70.28it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:01, 73.63it/s]
Loading 0:  63%|██████▎   | 184/291 [00:03<00:01, 74.95it/s]
Loading 0:  66%|██████▌   | 192/291 [00:04<00:04, 21.10it/s]
Loading 0:  68%|██████▊   | 198/291 [00:04<00:03, 24.51it/s]
Loading 0:  70%|███████   | 205/291 [00:04<00:02, 29.26it/s]
Loading 0:  74%|███████▎  | 214/291 [00:04<00:02, 37.19it/s]
Loading 0:  77%|███████▋  | 223/291 [00:05<00:01, 44.96it/s]
Loading 0:  80%|███████▉  | 232/291 [00:05<00:01, 52.72it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:00, 56.42it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 61.58it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 66.79it/s]
Loading 0:  92%|█████████▏| 268/291 [00:05<00:00, 69.00it/s]
Loading 0:  95%|█████████▌| 277/291 [00:05<00:00, 68.53it/s]
Loading 0:  98%|█████████▊| 286/291 [00:05<00:00, 72.20it/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-v13-mkmlizer:   warnings.warn(
jic062-instruct-v13-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-v13-mkmlizer:   warnings.warn(
jic062-instruct-v13-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-v13-mkmlizer:   warnings.warn(
jic062-instruct-v13-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:05<00:05,  5.53s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  3.97s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  4.20s/it]
jic062-instruct-v13-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  2.39it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.95it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.59it/s]
jic062-instruct-v13-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jic062-instruct-v13-mkmlizer: Saving duration: 1.361s
jic062-instruct-v13-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.351s
jic062-instruct-v13-mkmlizer: creating bucket guanaco-reward-models
jic062-instruct-v13-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jic062-instruct-v13-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jic062-instruct-v13_reward
jic062-instruct-v13-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jic062-instruct-v13_reward/special_tokens_map.json
jic062-instruct-v13-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jic062-instruct-v13_reward/config.json
jic062-instruct-v13-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jic062-instruct-v13_reward/tokenizer_config.json
jic062-instruct-v13-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jic062-instruct-v13_reward/merges.txt
jic062-instruct-v13-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jic062-instruct-v13_reward/vocab.json
jic062-instruct-v13-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jic062-instruct-v13_reward/tokenizer.json
jic062-instruct-v13-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/jic062-instruct-v13_reward/reward.tensors
Job jic062-instruct-v13-mkmlizer completed after 95.71s with status: succeeded
Stopping job with name jic062-instruct-v13-mkmlizer
Pipeline stage MKMLizer completed in 96.65s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.36s
Running pipeline stage ISVCDeployer
Creating inference service jic062-instruct-v13
Waiting for inference service jic062-instruct-v13 to be ready
Inference service jic062-instruct-v13 ready after 121.04390239715576s
Pipeline stage ISVCDeployer completed in 122.50s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.193889617919922s
Received healthy response to inference request in 1.3879246711730957s
Received healthy response to inference request in 1.4057564735412598s
Received healthy response to inference request in 1.4017045497894287s
Received healthy response to inference request in 1.4054884910583496s
5 requests
0 failed requests
5th percentile: 1.3906806468963624
10th percentile: 1.3934366226196289
20th percentile: 1.398948574066162
30th percentile: 1.402461338043213
40th percentile: 1.4039749145507812
50th percentile: 1.4054884910583496
60th percentile: 1.4055956840515136
70th percentile: 1.4057028770446778
80th percentile: 1.5633831024169924
90th percentile: 1.878636360168457
95th percentile: 2.0362629890441895
99th percentile: 2.162364292144775
mean time: 1.558952760696411
Pipeline stage StressChecker completed in 8.52s
jic062-instruct_v13 status is now deployed due to DeploymentManager action
jic062-instruct_v13 status is now inactive due to auto deactivation removed underperforming models
jic062-instruct_v13 status is now deployed due to admin request
jic062-instruct_v13 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of jic062-instruct_v13
Running pipeline stage ISVCDeleter
Checking if service jic062-instruct-v13 is running
Tearing down inference service jic062-instruct-v13
Service jic062-instruct-v13 has been torndown
Pipeline stage ISVCDeleter completed in 4.54s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key jic062-instruct-v13/config.json from bucket guanaco-mkml-models
Deleting key jic062-instruct-v13/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key jic062-instruct-v13/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key jic062-instruct-v13/tokenizer.json from bucket guanaco-mkml-models
Deleting key jic062-instruct-v13/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key jic062-instruct-v13_reward/config.json from bucket guanaco-reward-models
Deleting key jic062-instruct-v13_reward/merges.txt from bucket guanaco-reward-models
Deleting key jic062-instruct-v13_reward/reward.tensors from bucket guanaco-reward-models
Deleting key jic062-instruct-v13_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key jic062-instruct-v13_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key jic062-instruct-v13_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key jic062-instruct-v13_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.57s
jic062-instruct_v13 status is now torndown due to DeploymentManager action