jic062-instruct-v17-g24

developer_uid: chace9580

submission_id: jic062-instruct-v17-g24_v1

model_name: jic062-instruct-v17-g24_v1

model_group: jic062/instruct_v17_g24

status: torndown

timestamp: 2024-08-05T00:54:00+00:00

num_battles: 12632

num_wins: 6575

celo_rating: 1224.58

family_friendly_score: 0.0

submission_type: basic

model_repo: jic062/instruct_v17_g24

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-v17-g24_v1

is_internal_developer: False

language_model: jic062/instruct_v17_g24

model_size: 8B

ranking_group: single

us_pacific_date: 2024-08-04

win_ratio: 0.5205034832172261

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', '|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-g24-v1-mkmlizer
Waiting for job on jic062-instruct-v17-g24-v1-mkmlizer to finish
jic062-instruct-v17-g24-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-instruct-v17-g24-v1-mkmlizer: ║     _____            __           __                                ║
jic062-instruct-v17-g24-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jic062-instruct-v17-g24-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jic062-instruct-v17-g24-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jic062-instruct-v17-g24-v1-mkmlizer: ║       /___/                                                         ║
jic062-instruct-v17-g24-v1-mkmlizer: ║                                                                     ║
jic062-instruct-v17-g24-v1-mkmlizer: ║  Version: 0.9.9                                                     ║
jic062-instruct-v17-g24-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jic062-instruct-v17-g24-v1-mkmlizer: ║  https://mk1.ai                                                     ║
jic062-instruct-v17-g24-v1-mkmlizer: ║                                                                     ║
jic062-instruct-v17-g24-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
jic062-instruct-v17-g24-v1-mkmlizer: ║  belonging to:                                                      ║
jic062-instruct-v17-g24-v1-mkmlizer: ║                                                                     ║
jic062-instruct-v17-g24-v1-mkmlizer: ║  Chai Research Corp.                                                ║
jic062-instruct-v17-g24-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jic062-instruct-v17-g24-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
jic062-instruct-v17-g24-v1-mkmlizer: ║                                                                     ║
jic062-instruct-v17-g24-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jic062-instruct-v17-g24-v1-mkmlizer: Downloaded to shared memory in 33.867s
jic062-instruct-v17-g24-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8b22invi, device:0
jic062-instruct-v17-g24-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jic062-instruct-v17-g24-v1-mkmlizer: quantized model in 25.965s
jic062-instruct-v17-g24-v1-mkmlizer: Processed model jic062/instruct_v17_g24 in 59.832s
jic062-instruct-v17-g24-v1-mkmlizer: creating bucket guanaco-mkml-models
jic062-instruct-v17-g24-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-instruct-v17-g24-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-instruct-v17-g24-v1
jic062-instruct-v17-g24-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-instruct-v17-g24-v1/config.json
jic062-instruct-v17-g24-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-instruct-v17-g24-v1/special_tokens_map.json
jic062-instruct-v17-g24-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-instruct-v17-g24-v1/tokenizer_config.json
jic062-instruct-v17-g24-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-instruct-v17-g24-v1/tokenizer.json
jic062-instruct-v17-g24-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-instruct-v17-g24-v1/flywheel_model.0.safetensors
jic062-instruct-v17-g24-v1-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
jic062-instruct-v17-g24-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 53.47it/s]
Loading 0:   6%|▌         | 17/291 [00:00<00:03, 76.27it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:02, 87.71it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:02, 85.64it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:02, 85.68it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:02, 86.46it/s]
Loading 0:  24%|██▍       | 70/291 [00:00<00:02, 82.99it/s]
Loading 0:  27%|██▋       | 80/291 [00:00<00:02, 87.67it/s]
Loading 0:  31%|███       | 89/291 [00:02<00:09, 22.17it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:05, 31.85it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:04, 38.34it/s]
Loading 0:  42%|████▏     | 123/291 [00:02<00:03, 48.29it/s]
Loading 0:  45%|████▌     | 132/291 [00:02<00:02, 55.17it/s]
Loading 0:  49%|████▉     | 142/291 [00:02<00:02, 58.86it/s]
Loading 0:  52%|█████▏    | 151/291 [00:02<00:02, 64.43it/s]
Loading 0:  55%|█████▍    | 160/291 [00:02<00:01, 67.49it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:01, 69.18it/s]
Loading 0:  61%|██████    | 178/291 [00:03<00:01, 70.49it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:04, 21.74it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:02, 32.24it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:02, 38.37it/s]
Loading 0:  76%|███████▌  | 220/291 [00:04<00:01, 44.76it/s]
Loading 0:  79%|███████▊  | 229/291 [00:04<00:01, 51.73it/s]
Loading 0:  82%|████████▏ | 238/291 [00:04<00:00, 57.13it/s]
Loading 0:  85%|████████▍ | 247/291 [00:04<00:00, 62.80it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 66.91it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 71.31it/s]
Loading 0:  95%|█████████▍| 276/291 [00:05<00:00, 80.84it/s]
Loading 0:  98%|█████████▊| 285/291 [00:05<00:00, 80.95it/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-g24-v1-mkmlizer:   warnings.warn(
jic062-instruct-v17-g24-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-g24-v1-mkmlizer:   warnings.warn(
jic062-instruct-v17-g24-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-g24-v1-mkmlizer:   warnings.warn(
jic062-instruct-v17-g24-v1-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:05<00:05,  5.35s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  4.10s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  4.29s/it]
jic062-instruct-v17-g24-v1-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,  3.60it/s]
jic062-instruct-v17-g24-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jic062-instruct-v17-g24-v1-mkmlizer: Saving duration: 1.392s
jic062-instruct-v17-g24-v1-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.415s
jic062-instruct-v17-g24-v1-mkmlizer: creating bucket guanaco-reward-models
jic062-instruct-v17-g24-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jic062-instruct-v17-g24-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jic062-instruct-v17-g24-v1_reward
jic062-instruct-v17-g24-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jic062-instruct-v17-g24-v1_reward/config.json
jic062-instruct-v17-g24-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jic062-instruct-v17-g24-v1_reward/special_tokens_map.json
jic062-instruct-v17-g24-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jic062-instruct-v17-g24-v1_reward/tokenizer_config.json
jic062-instruct-v17-g24-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jic062-instruct-v17-g24-v1_reward/merges.txt
jic062-instruct-v17-g24-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jic062-instruct-v17-g24-v1_reward/vocab.json
jic062-instruct-v17-g24-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jic062-instruct-v17-g24-v1_reward/tokenizer.json
Job jic062-instruct-v17-g24-v1-mkmlizer completed after 105.13s with status: succeeded
Stopping job with name jic062-instruct-v17-g24-v1-mkmlizer
Pipeline stage MKMLizer completed in 106.28s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.37s
Running pipeline stage ISVCDeployer
Creating inference service jic062-instruct-v17-g24-v1
Waiting for inference service jic062-instruct-v17-g24-v1 to be ready
Inference service jic062-instruct-v17-g24-v1 ready after 171.14035177230835s
Pipeline stage ISVCDeployer completed in 172.81s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.198796033859253s
Received healthy response to inference request in 1.4686124324798584s
Received healthy response to inference request in 1.4307599067687988s
Received healthy response to inference request in 1.4207189083099365s
Received healthy response to inference request in 1.4804253578186035s
5 requests
0 failed requests
5th percentile: 1.422727108001709
10th percentile: 1.4247353076934814
20th percentile: 1.4287517070770264
30th percentile: 1.4383304119110107
40th percentile: 1.4534714221954346
50th percentile: 1.4686124324798584
60th percentile: 1.4733376026153564
70th percentile: 1.4780627727508544
80th percentile: 1.6240994930267336
90th percentile: 1.9114477634429932
95th percentile: 2.055121898651123
99th percentile: 2.170061206817627
mean time: 1.59986252784729
Pipeline stage StressChecker completed in 8.69s
jic062-instruct-v17-g24_v1 status is now deployed due to DeploymentManager action
jic062-instruct-v17-g24_v1 status is now inactive due to auto deactivation removed underperforming models
jic062-instruct-v17-g24_v1 status is now torndown due to DeploymentManager action