developer_uid: chace9580
submission_id: jic062-instruct_v11
model_name: jic062-instruct_v11
model_group: jic062/instruct
status: torndown
timestamp: 2024-07-30T21:10:05+00:00
num_battles: 10434
num_wins: 4960
celo_rating: 1185.02
family_friendly_score: 0.0
submission_type: basic
model_repo: jic062/instruct
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_v11
is_internal_developer: False
language_model: jic062/instruct
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-30
win_ratio: 0.4753689860072839
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|>'], '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-v11-mkmlizer
Waiting for job on jic062-instruct-v11-mkmlizer to finish
jic062-instruct-v11-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-instruct-v11-mkmlizer: ║     _____            __           __                                ║
jic062-instruct-v11-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jic062-instruct-v11-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jic062-instruct-v11-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jic062-instruct-v11-mkmlizer: ║       /___/                                                         ║
jic062-instruct-v11-mkmlizer: ║                                                                     ║
jic062-instruct-v11-mkmlizer: ║  Version: 0.9.7                                                     ║
jic062-instruct-v11-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jic062-instruct-v11-mkmlizer: ║  https://mk1.ai                                                     ║
jic062-instruct-v11-mkmlizer: ║                                                                     ║
jic062-instruct-v11-mkmlizer: ║  The license key for the current software has been verified as      ║
jic062-instruct-v11-mkmlizer: ║  belonging to:                                                      ║
jic062-instruct-v11-mkmlizer: ║                                                                     ║
jic062-instruct-v11-mkmlizer: ║  Chai Research Corp.                                                ║
jic062-instruct-v11-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jic062-instruct-v11-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
jic062-instruct-v11-mkmlizer: ║                                                                     ║
jic062-instruct-v11-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
jic062-instruct-v11-mkmlizer: Downloaded to shared memory in 24.107s
jic062-instruct-v11-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpngp5fful, device:0
jic062-instruct-v11-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jic062-instruct-v11-mkmlizer: quantized model in 25.789s
jic062-instruct-v11-mkmlizer: Processed model jic062/instruct in 49.896s
jic062-instruct-v11-mkmlizer: creating bucket guanaco-mkml-models
jic062-instruct-v11-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-instruct-v11-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-instruct-v11
jic062-instruct-v11-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-instruct-v11/config.json
jic062-instruct-v11-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-instruct-v11/special_tokens_map.json
jic062-instruct-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-instruct-v11/tokenizer_config.json
jic062-instruct-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-instruct-v11/tokenizer.json
jic062-instruct-v11-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-instruct-v11/flywheel_model.0.safetensors
jic062-instruct-v11-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
jic062-instruct-v11-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 50.58it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:03, 69.47it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:03, 74.55it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:03, 79.87it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:02, 83.09it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:02, 82.64it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:02, 80.94it/s]
Loading 0:  24%|██▍       | 70/291 [00:00<00:02, 81.32it/s]
Loading 0:  27%|██▋       | 80/291 [00:00<00:02, 86.33it/s]
Loading 0:  31%|███       | 89/291 [00:02<00:09, 21.58it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:05, 31.44it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:04, 38.10it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 44.13it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 51.18it/s]
Loading 0:  48%|████▊     | 141/291 [00:02<00:02, 62.11it/s]
Loading 0:  52%|█████▏    | 151/291 [00:02<00:02, 63.38it/s]
Loading 0:  55%|█████▍    | 160/291 [00:02<00:01, 66.02it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:01, 69.97it/s]
Loading 0:  61%|██████    | 178/291 [00:03<00:01, 74.47it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:04, 21.74it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:03, 27.65it/s]
Loading 0:  70%|███████   | 205/291 [00:04<00:02, 34.58it/s]
Loading 0:  74%|███████▍  | 215/291 [00:04<00:01, 43.39it/s]
Loading 0:  77%|███████▋  | 223/291 [00:04<00:01, 49.08it/s]
Loading 0:  80%|███████▉  | 232/291 [00:04<00:01, 56.09it/s]
Loading 0:  85%|████████▍ | 247/291 [00:04<00:00, 69.36it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 73.67it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 75.45it/s]
Loading 0:  94%|█████████▍| 274/291 [00:05<00:00, 78.33it/s]
Loading 0:  98%|█████████▊| 285/291 [00:05<00:00, 86.41it/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-v11-mkmlizer:   warnings.warn(
jic062-instruct-v11-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-v11-mkmlizer:   warnings.warn(
jic062-instruct-v11-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-v11-mkmlizer:   warnings.warn(
jic062-instruct-v11-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jic062-instruct-v11-mkmlizer: Saving duration: 1.417s
jic062-instruct-v11-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.066s
jic062-instruct-v11-mkmlizer: creating bucket guanaco-reward-models
jic062-instruct-v11-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jic062-instruct-v11-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jic062-instruct-v11_reward
jic062-instruct-v11-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jic062-instruct-v11_reward/config.json
jic062-instruct-v11-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jic062-instruct-v11_reward/special_tokens_map.json
jic062-instruct-v11-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jic062-instruct-v11_reward/tokenizer_config.json
jic062-instruct-v11-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jic062-instruct-v11_reward/merges.txt
jic062-instruct-v11-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jic062-instruct-v11_reward/vocab.json
jic062-instruct-v11-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jic062-instruct-v11_reward/tokenizer.json
jic062-instruct-v11-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/jic062-instruct-v11_reward/reward.tensors
Job jic062-instruct-v11-mkmlizer completed after 95.8s with status: succeeded
Stopping job with name jic062-instruct-v11-mkmlizer
Pipeline stage MKMLizer completed in 97.14s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service jic062-instruct-v11
Waiting for inference service jic062-instruct-v11 to be ready
Inference service jic062-instruct-v11 ready after 111.02253723144531s
Pipeline stage ISVCDeployer completed in 112.72s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2833683490753174s
Received healthy response to inference request in 1.3424689769744873s
Received healthy response to inference request in 1.4063310623168945s
Received healthy response to inference request in 1.4108197689056396s
Received healthy response to inference request in 1.3774809837341309s
5 requests
0 failed requests
5th percentile: 1.349471378326416
10th percentile: 1.3564737796783448
20th percentile: 1.370478582382202
30th percentile: 1.3832509994506836
40th percentile: 1.394791030883789
50th percentile: 1.4063310623168945
60th percentile: 1.4081265449523925
70th percentile: 1.4099220275878905
80th percentile: 1.5853294849395754
90th percentile: 1.9343489170074464
95th percentile: 2.1088586330413817
99th percentile: 2.2484664058685304
mean time: 1.564093828201294
Pipeline stage StressChecker completed in 8.58s
jic062-instruct_v11 status is now deployed due to DeploymentManager action
jic062-instruct_v11 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of jic062-instruct_v11
Running pipeline stage ISVCDeleter
Checking if service jic062-instruct-v11 is running
Tearing down inference service jic062-instruct-v11
Service jic062-instruct-v11 has been torndown
Pipeline stage ISVCDeleter completed in 4.63s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key jic062-instruct-v11/config.json from bucket guanaco-mkml-models
Deleting key jic062-instruct-v11/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key jic062-instruct-v11/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key jic062-instruct-v11/tokenizer.json from bucket guanaco-mkml-models
Deleting key jic062-instruct-v11/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key jic062-instruct-v11_reward/config.json from bucket guanaco-reward-models
Deleting key jic062-instruct-v11_reward/merges.txt from bucket guanaco-reward-models
Deleting key jic062-instruct-v11_reward/reward.tensors from bucket guanaco-reward-models
Deleting key jic062-instruct-v11_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key jic062-instruct-v11_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key jic062-instruct-v11_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key jic062-instruct-v11_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.45s
jic062-instruct_v11 status is now torndown due to DeploymentManager action