developer_uid: chace9580
submission_id: jic062-instruct-v17-g24_v3
model_name: jic062-instruct-v17-g24_v3
model_group: jic062/instruct_v17_g24
status: torndown
timestamp: 2024-08-05T03:27:18+00:00
num_battles: 11913
num_wins: 6335
celo_rating: 1226.74
family_friendly_score: 0.0
submission_type: basic
model_repo: jic062/instruct_v17_g24
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-g24_v3
is_internal_developer: False
language_model: jic062/instruct_v17_g24
model_size: 8B
ranking_group: single
us_pacific_date: 2024-08-04
win_ratio: 0.5317720137664737
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-v3-mkmlizer
Waiting for job on jic062-instruct-v17-g24-v3-mkmlizer to finish
jic062-instruct-v17-g24-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-instruct-v17-g24-v3-mkmlizer: ║     _____            __           __                                ║
jic062-instruct-v17-g24-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jic062-instruct-v17-g24-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jic062-instruct-v17-g24-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jic062-instruct-v17-g24-v3-mkmlizer: ║       /___/                                                         ║
jic062-instruct-v17-g24-v3-mkmlizer: ║                                                                     ║
jic062-instruct-v17-g24-v3-mkmlizer: ║  Version: 0.9.9                                                     ║
jic062-instruct-v17-g24-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jic062-instruct-v17-g24-v3-mkmlizer: ║  https://mk1.ai                                                     ║
jic062-instruct-v17-g24-v3-mkmlizer: ║                                                                     ║
jic062-instruct-v17-g24-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
jic062-instruct-v17-g24-v3-mkmlizer: ║  belonging to:                                                      ║
jic062-instruct-v17-g24-v3-mkmlizer: ║                                                                     ║
jic062-instruct-v17-g24-v3-mkmlizer: ║  Chai Research Corp.                                                ║
jic062-instruct-v17-g24-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jic062-instruct-v17-g24-v3-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
jic062-instruct-v17-g24-v3-mkmlizer: ║                                                                     ║
jic062-instruct-v17-g24-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jic062-instruct-v17-g24-v3-mkmlizer: Downloaded to shared memory in 21.893s
jic062-instruct-v17-g24-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxye6kep6, device:0
jic062-instruct-v17-g24-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jic062-instruct-v17-g24-v3-mkmlizer: quantized model in 26.039s
jic062-instruct-v17-g24-v3-mkmlizer: Processed model jic062/instruct_v17_g24 in 47.932s
jic062-instruct-v17-g24-v3-mkmlizer: creating bucket guanaco-mkml-models
jic062-instruct-v17-g24-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-instruct-v17-g24-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-instruct-v17-g24-v3
jic062-instruct-v17-g24-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-instruct-v17-g24-v3/config.json
jic062-instruct-v17-g24-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-instruct-v17-g24-v3/special_tokens_map.json
jic062-instruct-v17-g24-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-instruct-v17-g24-v3/tokenizer_config.json
jic062-instruct-v17-g24-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-instruct-v17-g24-v3/tokenizer.json
jic062-instruct-v17-g24-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-instruct-v17-g24-v3/flywheel_model.0.safetensors
jic062-instruct-v17-g24-v3-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
jic062-instruct-v17-g24-v3-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:06, 46.54it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:04, 61.74it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:03, 69.06it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:03, 75.89it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:03, 78.53it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:02, 81.78it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:02, 90.30it/s]
Loading 0:  26%|██▌       | 76/291 [00:00<00:02, 89.58it/s]
Loading 0:  29%|██▉       | 85/291 [00:02<00:09, 22.54it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:06, 28.56it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:05, 35.34it/s]
Loading 0:  39%|███▉      | 114/291 [00:02<00:03, 45.80it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:03, 51.52it/s]
Loading 0:  48%|████▊     | 139/291 [00:02<00:02, 64.30it/s]
Loading 0:  51%|█████     | 148/291 [00:02<00:02, 68.75it/s]
Loading 0:  55%|█████▍    | 160/291 [00:02<00:01, 72.85it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:01, 82.62it/s]
Loading 0:  64%|██████▎   | 185/291 [00:03<00:01, 84.25it/s]
Loading 0:  67%|██████▋   | 195/291 [00:04<00:03, 25.54it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:03, 29.45it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:02, 35.82it/s]
Loading 0:  76%|███████▌  | 220/291 [00:04<00:01, 43.10it/s]
Loading 0:  79%|███████▊  | 229/291 [00:04<00:01, 49.91it/s]
Loading 0:  82%|████████▏ | 238/291 [00:04<00:00, 56.87it/s]
Loading 0:  85%|████████▍ | 247/291 [00:04<00:00, 61.74it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 66.04it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 68.34it/s]
Loading 0:  94%|█████████▍| 274/291 [00:05<00:00, 72.05it/s]
Loading 0:  97%|█████████▋| 283/291 [00:05<00:00, 74.41it/s]
Loading 0: 100%|██████████| 291/291 [00:10<00:00,  5.05it/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-v3-mkmlizer:   warnings.warn(
jic062-instruct-v17-g24-v3-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-v3-mkmlizer:   warnings.warn(
jic062-instruct-v17-g24-v3-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-v3-mkmlizer:   warnings.warn(
jic062-instruct-v17-g24-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jic062-instruct-v17-g24-v3-mkmlizer: Saving duration: 1.402s
jic062-instruct-v17-g24-v3-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.015s
jic062-instruct-v17-g24-v3-mkmlizer: creating bucket guanaco-reward-models
jic062-instruct-v17-g24-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jic062-instruct-v17-g24-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jic062-instruct-v17-g24-v3_reward
jic062-instruct-v17-g24-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jic062-instruct-v17-g24-v3_reward/config.json
jic062-instruct-v17-g24-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jic062-instruct-v17-g24-v3_reward/special_tokens_map.json
jic062-instruct-v17-g24-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jic062-instruct-v17-g24-v3_reward/tokenizer_config.json
jic062-instruct-v17-g24-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jic062-instruct-v17-g24-v3_reward/merges.txt
jic062-instruct-v17-g24-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jic062-instruct-v17-g24-v3_reward/vocab.json
jic062-instruct-v17-g24-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jic062-instruct-v17-g24-v3_reward/tokenizer.json
jic062-instruct-v17-g24-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/jic062-instruct-v17-g24-v3_reward/reward.tensors
Job jic062-instruct-v17-g24-v3-mkmlizer completed after 94.45s with status: succeeded
Stopping job with name jic062-instruct-v17-g24-v3-mkmlizer
Pipeline stage MKMLizer completed in 95.54s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service jic062-instruct-v17-g24-v3
Waiting for inference service jic062-instruct-v17-g24-v3 to be ready
Failed to get response for submission blend_mofos_2024-07-31: ('http://neversleep-noromaid-v0-8068-v142-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:50464->127.0.0.1:8080: read: connection reset by peer\n')
Failed to get response for submission deverdever-heavenly-mous_3469_v3: ('http://deverdever-heavenly-mous-3469-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"ValueError : [TypeError(\\"\'numpy.int64\' object is not iterable\\"), TypeError(\'vars() argument must have __dict__ attribute\')]"}')
Inference service jic062-instruct-v17-g24-v3 ready after 171.07956099510193s
Pipeline stage ISVCDeployer completed in 172.89s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2191081047058105s
Received healthy response to inference request in 1.49159574508667s
Received healthy response to inference request in 1.4403085708618164s
Received healthy response to inference request in 1.4343159198760986s
Received healthy response to inference request in 1.5098896026611328s
5 requests
0 failed requests
5th percentile: 1.4355144500732422
10th percentile: 1.4367129802703857
20th percentile: 1.4391100406646729
30th percentile: 1.450566005706787
40th percentile: 1.4710808753967286
50th percentile: 1.49159574508667
60th percentile: 1.498913288116455
70th percentile: 1.5062308311462402
80th percentile: 1.6517333030700685
90th percentile: 1.9354207038879396
95th percentile: 2.0772644042968746
99th percentile: 2.190739364624023
mean time: 1.6190435886383057
Pipeline stage StressChecker completed in 8.77s
jic062-instruct-v17-g24_v3 status is now deployed due to DeploymentManager action
jic062-instruct-v17-g24_v3 status is now inactive due to auto deactivation removed underperforming models
jic062-instruct-v17-g24_v3 status is now torndown due to DeploymentManager action