developer_uid: chace9580
submission_id: jic062-instruct-v17-base-mix_v1
model_name: jic062-instruct-v17-base-mix_v1
model_group: jic062/instruct_v17_base
status: torndown
timestamp: 2024-08-11T07:32:00+00:00
num_battles: 10937
num_wins: 5606
celo_rating: 1234.03
family_friendly_score: 0.0
submission_type: basic
model_repo: jic062/instruct_v17_base_mix
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-base-mix_v1
is_internal_developer: False
language_model: jic062/instruct_v17_base_mix
model_size: 8B
ranking_group: single
us_pacific_date: 2024-08-11
win_ratio: 0.512572003291579
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|', '<|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}<|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-base-mix-v1-mkmlizer
Waiting for job on jic062-instruct-v17-base-mix-v1-mkmlizer to finish
Stopping job with name jic062-instruct-v17-base-mix-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name jic062-instruct-v17-base-mix-v1-mkmlizer
Waiting for job on jic062-instruct-v17-base-mix-v1-mkmlizer to finish
jic062-instruct-v17-base-mix-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-instruct-v17-base-mix-v1-mkmlizer: ║     _____            __           __                                ║
jic062-instruct-v17-base-mix-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jic062-instruct-v17-base-mix-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jic062-instruct-v17-base-mix-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jic062-instruct-v17-base-mix-v1-mkmlizer: ║       /___/                                                         ║
jic062-instruct-v17-base-mix-v1-mkmlizer: ║                                                                     ║
jic062-instruct-v17-base-mix-v1-mkmlizer: ║  Version: 0.9.9                                                     ║
jic062-instruct-v17-base-mix-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jic062-instruct-v17-base-mix-v1-mkmlizer: ║  https://mk1.ai                                                     ║
jic062-instruct-v17-base-mix-v1-mkmlizer: ║                                                                     ║
jic062-instruct-v17-base-mix-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
jic062-instruct-v17-base-mix-v1-mkmlizer: ║  belonging to:                                                      ║
jic062-instruct-v17-base-mix-v1-mkmlizer: ║                                                                     ║
jic062-instruct-v17-base-mix-v1-mkmlizer: ║  Chai Research Corp.                                                ║
jic062-instruct-v17-base-mix-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jic062-instruct-v17-base-mix-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
jic062-instruct-v17-base-mix-v1-mkmlizer: ║                                                                     ║
jic062-instruct-v17-base-mix-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jic062-instruct-v17-base-mix-v1-mkmlizer: Downloaded to shared memory in 31.990s
jic062-instruct-v17-base-mix-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpd54j8i8l, device:0
jic062-instruct-v17-base-mix-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jic062-instruct-v17-base-mix-v1-mkmlizer: quantized model in 27.780s
jic062-instruct-v17-base-mix-v1-mkmlizer: Processed model jic062/instruct_v17_base_mix in 59.770s
jic062-instruct-v17-base-mix-v1-mkmlizer: creating bucket guanaco-mkml-models
jic062-instruct-v17-base-mix-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-instruct-v17-base-mix-v1/config.json
jic062-instruct-v17-base-mix-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-instruct-v17-base-mix-v1/special_tokens_map.json
jic062-instruct-v17-base-mix-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-instruct-v17-base-mix-v1/tokenizer_config.json
jic062-instruct-v17-base-mix-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-instruct-v17-base-mix-v1/tokenizer.json
jic062-instruct-v17-base-mix-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-instruct-v17-base-mix-v1/flywheel_model.0.safetensors
jic062-instruct-v17-base-mix-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
jic062-instruct-v17-base-mix-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 4/291 [00:00<00:07, 38.45it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:05, 50.98it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:04, 55.63it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:04, 56.08it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:04, 55.00it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:04, 58.06it/s]
Loading 0:  20%|█▉        | 58/291 [00:01<00:03, 61.17it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:03, 66.48it/s]
Loading 0:  27%|██▋       | 79/291 [00:01<00:02, 72.51it/s]
Loading 0:  30%|██▉       | 87/291 [00:02<00:10, 20.25it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:08, 23.90it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:06, 29.61it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:05, 34.74it/s]
Loading 0:  42%|████▏     | 121/291 [00:03<00:04, 39.02it/s]
Loading 0:  45%|████▍     | 130/291 [00:03<00:03, 43.26it/s]
Loading 0:  48%|████▊     | 139/291 [00:03<00:03, 47.20it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:02, 50.89it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 53.43it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:02, 55.07it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:02, 55.19it/s]
Loading 0:  63%|██████▎   | 184/291 [00:04<00:01, 55.66it/s]
Loading 0:  65%|██████▌   | 190/291 [00:05<00:05, 17.33it/s]
Loading 0:  67%|██████▋   | 196/291 [00:05<00:04, 20.02it/s]
Loading 0:  70%|███████   | 205/291 [00:05<00:03, 26.03it/s]
Loading 0:  74%|███████▎  | 214/291 [00:05<00:02, 31.70it/s]
Loading 0:  77%|███████▋  | 223/291 [00:05<00:01, 36.55it/s]
Loading 0:  80%|███████▉  | 232/291 [00:06<00:01, 41.84it/s]
Loading 0:  83%|████████▎ | 241/291 [00:06<00:01, 47.49it/s]
Loading 0:  86%|████████▌ | 250/291 [00:06<00:00, 52.23it/s]
Loading 0:  89%|████████▉ | 259/291 [00:06<00:00, 55.77it/s]
Loading 0:  92%|█████████▏| 268/291 [00:06<00:00, 60.07it/s]
Loading 0:  97%|█████████▋| 283/291 [00:06<00:00, 72.86it/s]
Loading 0: 100%|██████████| 291/291 [00:12<00:00,  5.70it/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-base-mix-v1-mkmlizer:   warnings.warn(
jic062-instruct-v17-base-mix-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-base-mix-v1-mkmlizer:   warnings.warn(
jic062-instruct-v17-base-mix-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jic062-instruct-v17-base-mix-v1-mkmlizer: Saving duration: 1.462s
jic062-instruct-v17-base-mix-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 12.152s
jic062-instruct-v17-base-mix-v1-mkmlizer: creating bucket guanaco-reward-models
jic062-instruct-v17-base-mix-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jic062-instruct-v17-base-mix-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jic062-instruct-v17-base-mix-v1_reward
jic062-instruct-v17-base-mix-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jic062-instruct-v17-base-mix-v1_reward/special_tokens_map.json
jic062-instruct-v17-base-mix-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jic062-instruct-v17-base-mix-v1_reward/tokenizer_config.json
jic062-instruct-v17-base-mix-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jic062-instruct-v17-base-mix-v1_reward/config.json
jic062-instruct-v17-base-mix-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jic062-instruct-v17-base-mix-v1_reward/merges.txt
jic062-instruct-v17-base-mix-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jic062-instruct-v17-base-mix-v1_reward/vocab.json
jic062-instruct-v17-base-mix-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jic062-instruct-v17-base-mix-v1_reward/tokenizer.json
jic062-instruct-v17-base-mix-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/jic062-instruct-v17-base-mix-v1_reward/reward.tensors
Job jic062-instruct-v17-base-mix-v1-mkmlizer completed after 105.1s with status: succeeded
Stopping job with name jic062-instruct-v17-base-mix-v1-mkmlizer
Pipeline stage MKMLizer completed in 106.95s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service jic062-instruct-v17-base-mix-v1
Waiting for inference service jic062-instruct-v17-base-mix-v1 to be ready
Inference service jic062-instruct-v17-base-mix-v1 ready after 211.35441994667053s
Pipeline stage ISVCDeployer completed in 213.60s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.401746988296509s
Received healthy response to inference request in 1.488619089126587s
Received healthy response to inference request in 1.4527397155761719s
Received healthy response to inference request in 1.4229381084442139s
Received healthy response to inference request in 1.4806568622589111s
5 requests
0 failed requests
5th percentile: 1.4288984298706056
10th percentile: 1.434858751296997
20th percentile: 1.4467793941497802
30th percentile: 1.4583231449127196
40th percentile: 1.4694900035858154
50th percentile: 1.4806568622589111
60th percentile: 1.4838417530059815
70th percentile: 1.4870266437530517
80th percentile: 1.6712446689605716
90th percentile: 2.03649582862854
95th percentile: 2.219121408462524
99th percentile: 2.365221872329712
mean time: 1.6493401527404785
Pipeline stage StressChecker completed in 9.07s
jic062-instruct-v17-base-mix_v1 status is now deployed due to DeploymentManager action
jic062-instruct-v17-base-mix_v1 status is now inactive due to auto deactivation removed underperforming models
jic062-instruct-v17-base-mix_v1 status is now torndown due to DeploymentManager action