jic062-instruct-v17

developer_uid: chace9580

submission_id: jic062-instruct-v17_v2

model_name: jic062-instruct-v17_v2

model_group: jic062/instruct_v17

status: torndown

timestamp: 2024-08-02T20:50:03+00:00

num_battles: 25510

num_wins: 12772

celo_rating: 1225.29

family_friendly_score: 0.0

submission_type: basic

model_repo: jic062/instruct_v17

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_v2

is_internal_developer: False

language_model: jic062/instruct_v17

model_size: 8B

ranking_group: single

us_pacific_date: 2024-08-02

win_ratio: 0.5006664053312426

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-v17-v2-mkmlizer
Waiting for job on jic062-instruct-v17-v2-mkmlizer to finish
jic062-instruct-v17-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-instruct-v17-v2-mkmlizer: ║     _____            __           __                                ║
jic062-instruct-v17-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jic062-instruct-v17-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jic062-instruct-v17-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jic062-instruct-v17-v2-mkmlizer: ║       /___/                                                         ║
jic062-instruct-v17-v2-mkmlizer: ║                                                                     ║
jic062-instruct-v17-v2-mkmlizer: ║  Version: 0.9.9                                                     ║
jic062-instruct-v17-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jic062-instruct-v17-v2-mkmlizer: ║  https://mk1.ai                                                     ║
jic062-instruct-v17-v2-mkmlizer: ║                                                                     ║
jic062-instruct-v17-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
jic062-instruct-v17-v2-mkmlizer: ║  belonging to:                                                      ║
jic062-instruct-v17-v2-mkmlizer: ║                                                                     ║
jic062-instruct-v17-v2-mkmlizer: ║  Chai Research Corp.                                                ║
jic062-instruct-v17-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jic062-instruct-v17-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
jic062-instruct-v17-v2-mkmlizer: ║                                                                     ║
jic062-instruct-v17-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jic062-instruct-v17-v2-mkmlizer: Downloaded to shared memory in 25.424s
jic062-instruct-v17-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpp2yh5vr1, device:0
jic062-instruct-v17-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jic062-instruct-v17-v2-mkmlizer: quantized model in 25.959s
jic062-instruct-v17-v2-mkmlizer: Processed model jic062/instruct_v17 in 51.383s
jic062-instruct-v17-v2-mkmlizer: creating bucket guanaco-mkml-models
jic062-instruct-v17-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-instruct-v17-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-instruct-v17-v2
jic062-instruct-v17-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-instruct-v17-v2/special_tokens_map.json
jic062-instruct-v17-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-instruct-v17-v2/config.json
jic062-instruct-v17-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-instruct-v17-v2/tokenizer_config.json
jic062-instruct-v17-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-instruct-v17-v2/tokenizer.json
jic062-instruct-v17-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-instruct-v17-v2/flywheel_model.0.safetensors
jic062-instruct-v17-v2-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
jic062-instruct-v17-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 52.28it/s]
Loading 0:   6%|▌         | 17/291 [00:00<00:03, 76.72it/s]
Loading 0:   9%|▉         | 26/291 [00:00<00:03, 82.01it/s]
Loading 0:  12%|█▏        | 35/291 [00:00<00:03, 84.53it/s]
Loading 0:  15%|█▌        | 44/291 [00:00<00:02, 83.77it/s]
Loading 0:  18%|█▊        | 53/291 [00:00<00:02, 81.41it/s]
Loading 0:  22%|██▏       | 65/291 [00:00<00:02, 93.22it/s]
Loading 0:  26%|██▌       | 75/291 [00:00<00:02, 95.11it/s]
Loading 0:  29%|██▉       | 85/291 [00:02<00:09, 21.99it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:07, 27.44it/s]
Loading 0:  36%|███▌      | 104/291 [00:02<00:05, 35.49it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:04, 41.14it/s]
Loading 0:  42%|████▏     | 122/291 [00:02<00:03, 50.52it/s]
Loading 0:  45%|████▌     | 131/291 [00:02<00:02, 56.87it/s]
Loading 0:  48%|████▊     | 140/291 [00:02<00:02, 63.00it/s]
Loading 0:  52%|█████▏    | 150/291 [00:02<00:01, 71.37it/s]
Loading 0:  55%|█████▍    | 159/291 [00:02<00:01, 75.04it/s]
Loading 0:  58%|█████▊    | 168/291 [00:03<00:01, 77.08it/s]
Loading 0:  61%|██████    | 178/291 [00:03<00:01, 74.10it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:04, 21.80it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:03, 27.98it/s]
Loading 0:  70%|███████   | 205/291 [00:04<00:02, 34.95it/s]
Loading 0:  74%|███████▎  | 214/291 [00:04<00:01, 42.69it/s]
Loading 0:  77%|███████▋  | 223/291 [00:04<00:01, 48.76it/s]
Loading 0:  80%|███████▉  | 232/291 [00:04<00:01, 55.33it/s]
Loading 0:  83%|████████▎ | 241/291 [00:04<00:00, 61.53it/s]
Loading 0:  86%|████████▋ | 251/291 [00:05<00:00, 70.04it/s]
Loading 0:  89%|████████▉ | 260/291 [00:05<00:00, 74.76it/s]
Loading 0:  92%|█████████▏| 269/291 [00:05<00:00, 77.38it/s]
Loading 0:  96%|█████████▌| 278/291 [00:05<00:00, 79.05it/s]
Loading 0:  99%|█████████▊| 287/291 [00:05<00:00, 43.25it/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-v2-mkmlizer:   warnings.warn(
jic062-instruct-v17-v2-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-v2-mkmlizer:   warnings.warn(
jic062-instruct-v17-v2-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-v2-mkmlizer:   warnings.warn(
jic062-instruct-v17-v2-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:05<00:05,  5.30s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  4.07s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  4.25s/it]
jic062-instruct-v17-v2-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  2.40it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.96it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.61it/s]
jic062-instruct-v17-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jic062-instruct-v17-v2-mkmlizer: Saving duration: 1.339s
jic062-instruct-v17-v2-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.431s
jic062-instruct-v17-v2-mkmlizer: creating bucket guanaco-reward-models
jic062-instruct-v17-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jic062-instruct-v17-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jic062-instruct-v17-v2_reward
jic062-instruct-v17-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jic062-instruct-v17-v2_reward/config.json
jic062-instruct-v17-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jic062-instruct-v17-v2_reward/tokenizer_config.json
jic062-instruct-v17-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jic062-instruct-v17-v2_reward/special_tokens_map.json
jic062-instruct-v17-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jic062-instruct-v17-v2_reward/merges.txt
jic062-instruct-v17-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jic062-instruct-v17-v2_reward/vocab.json
jic062-instruct-v17-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jic062-instruct-v17-v2_reward/tokenizer.json
jic062-instruct-v17-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/jic062-instruct-v17-v2_reward/reward.tensors
Job jic062-instruct-v17-v2-mkmlizer completed after 94.81s with status: succeeded
Stopping job with name jic062-instruct-v17-v2-mkmlizer
Pipeline stage MKMLizer completed in 96.19s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service jic062-instruct-v17-v2
Waiting for inference service jic062-instruct-v17-v2 to be ready
Inference service jic062-instruct-v17-v2 ready after 151.78288960456848s
Pipeline stage ISVCDeployer completed in 153.56s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3434672355651855s
Received healthy response to inference request in 1.3837404251098633s
Received healthy response to inference request in 1.3875923156738281s
Received healthy response to inference request in 1.4040310382843018s
Received healthy response to inference request in 1.3924808502197266s
5 requests
0 failed requests
5th percentile: 1.3845108032226563
10th percentile: 1.3852811813354493
20th percentile: 1.3868219375610351
30th percentile: 1.3885700225830078
40th percentile: 1.3905254364013673
50th percentile: 1.3924808502197266
60th percentile: 1.3971009254455566
70th percentile: 1.4017210006713867
80th percentile: 1.5919182777404788
90th percentile: 1.9676927566528322
95th percentile: 2.1555799961090085
99th percentile: 2.30588978767395
mean time: 1.5822623729705811
Pipeline stage StressChecker completed in 8.74s
jic062-instruct-v17_v2 status is now deployed due to DeploymentManager action
jic062-instruct-v17_v2 status is now inactive due to auto deactivation removed underperforming models
jic062-instruct-v17_v2 status is now torndown due to DeploymentManager action