developer_uid: chace9580
submission_id: jic062-instruct-v16_v2
model_name: instruct_v17
model_group: jic062/instruct_v16
status: torndown
timestamp: 2024-08-01T22:49:19+00:00
num_battles: 10250
num_wins: 5557
celo_rating: 1227.84
family_friendly_score: 0.0
submission_type: basic
model_repo: jic062/instruct_v16
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: instruct_v17
is_internal_developer: False
language_model: jic062/instruct_v16
model_size: 8B
ranking_group: single
us_pacific_date: 2024-08-01
win_ratio: 0.5421463414634147
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-v16-v2-mkmlizer
Waiting for job on jic062-instruct-v16-v2-mkmlizer to finish
jic062-instruct-v16-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-instruct-v16-v2-mkmlizer: ║     _____            __           __                                ║
jic062-instruct-v16-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jic062-instruct-v16-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jic062-instruct-v16-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jic062-instruct-v16-v2-mkmlizer: ║       /___/                                                         ║
jic062-instruct-v16-v2-mkmlizer: ║                                                                     ║
jic062-instruct-v16-v2-mkmlizer: ║  Version: 0.9.7                                                     ║
jic062-instruct-v16-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jic062-instruct-v16-v2-mkmlizer: ║  https://mk1.ai                                                     ║
jic062-instruct-v16-v2-mkmlizer: ║                                                                     ║
jic062-instruct-v16-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
jic062-instruct-v16-v2-mkmlizer: ║  belonging to:                                                      ║
jic062-instruct-v16-v2-mkmlizer: ║                                                                     ║
jic062-instruct-v16-v2-mkmlizer: ║  Chai Research Corp.                                                ║
jic062-instruct-v16-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jic062-instruct-v16-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
jic062-instruct-v16-v2-mkmlizer: ║                                                                     ║
jic062-instruct-v16-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jic062-instruct-v16-v2-mkmlizer: Downloaded to shared memory in 24.063s
jic062-instruct-v16-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_86gcbnp, device:0
jic062-instruct-v16-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jic062-instruct-v16-v2-mkmlizer: quantized model in 25.983s
jic062-instruct-v16-v2-mkmlizer: Processed model jic062/instruct_v16 in 50.046s
jic062-instruct-v16-v2-mkmlizer: creating bucket guanaco-mkml-models
jic062-instruct-v16-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-instruct-v16-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-instruct-v16-v2
jic062-instruct-v16-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-instruct-v16-v2/config.json
jic062-instruct-v16-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-instruct-v16-v2/special_tokens_map.json
jic062-instruct-v16-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-instruct-v16-v2/tokenizer_config.json
jic062-instruct-v16-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-instruct-v16-v2/tokenizer.json
jic062-instruct-v16-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-instruct-v16-v2/flywheel_model.0.safetensors
jic062-instruct-v16-v2-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
jic062-instruct-v16-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 54.72it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:03, 72.53it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:02, 88.53it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:02, 88.19it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:02, 86.15it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:02, 92.79it/s]
Loading 0:  26%|██▋       | 77/291 [00:00<00:02, 93.88it/s]
Loading 0:  30%|██▉       | 87/291 [00:02<00:08, 24.03it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:07, 27.85it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:05, 34.53it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:04, 43.52it/s]
Loading 0:  43%|████▎     | 125/291 [00:02<00:03, 52.30it/s]
Loading 0:  46%|████▌     | 134/291 [00:02<00:02, 58.12it/s]
Loading 0:  49%|████▉     | 143/291 [00:02<00:02, 63.69it/s]
Loading 0:  52%|█████▏    | 152/291 [00:02<00:02, 68.88it/s]
Loading 0:  55%|█████▌    | 161/291 [00:02<00:01, 73.53it/s]
Loading 0:  58%|█████▊    | 170/291 [00:03<00:01, 77.43it/s]
Loading 0:  62%|██████▏   | 179/291 [00:03<00:01, 79.52it/s]
Loading 0:  65%|██████▍   | 188/291 [00:04<00:04, 21.42it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:03, 26.74it/s]
Loading 0:  70%|███████   | 205/291 [00:04<00:02, 33.67it/s]
Loading 0:  74%|███████▍  | 215/291 [00:04<00:01, 42.80it/s]
Loading 0:  77%|███████▋  | 223/291 [00:04<00:01, 48.96it/s]
Loading 0:  80%|████████  | 233/291 [00:04<00:00, 58.35it/s]
Loading 0:  83%|████████▎ | 242/291 [00:04<00:00, 64.43it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 74.64it/s]
Loading 0:  92%|█████████▏| 268/291 [00:05<00:00, 77.19it/s]
Loading 0:  95%|█████████▌| 277/291 [00:05<00:00, 78.84it/s]
Loading 0:  98%|█████████▊| 286/291 [00:05<00:00, 80.68it/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-v16-v2-mkmlizer:   warnings.warn(
jic062-instruct-v16-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-v16-v2-mkmlizer:   warnings.warn(
jic062-instruct-v16-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-v16-v2-mkmlizer:   warnings.warn(
jic062-instruct-v16-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jic062-instruct-v16-v2-mkmlizer: Saving duration: 1.393s
jic062-instruct-v16-v2-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.555s
jic062-instruct-v16-v2-mkmlizer: creating bucket guanaco-reward-models
jic062-instruct-v16-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jic062-instruct-v16-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jic062-instruct-v16-v2_reward
jic062-instruct-v16-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jic062-instruct-v16-v2_reward/config.json
jic062-instruct-v16-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jic062-instruct-v16-v2_reward/special_tokens_map.json
jic062-instruct-v16-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jic062-instruct-v16-v2_reward/tokenizer_config.json
jic062-instruct-v16-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jic062-instruct-v16-v2_reward/merges.txt
jic062-instruct-v16-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jic062-instruct-v16-v2_reward/vocab.json
jic062-instruct-v16-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jic062-instruct-v16-v2_reward/tokenizer.json
jic062-instruct-v16-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/jic062-instruct-v16-v2_reward/reward.tensors
Job jic062-instruct-v16-v2-mkmlizer completed after 94.49s with status: succeeded
Stopping job with name jic062-instruct-v16-v2-mkmlizer
Pipeline stage MKMLizer completed in 95.32s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service jic062-instruct-v16-v2
Waiting for inference service jic062-instruct-v16-v2 to be ready
Failed to get response for submission mistralai-mixtral-8x7b-_3473_v86: ('http://mistralai-mixtral-8x7b-3473-v86-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:44026->127.0.0.1:8080: read: connection reset by peer\n')
Inference service jic062-instruct-v16-v2 ready after 151.4355833530426s
Pipeline stage ISVCDeployer completed in 152.94s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.308156728744507s
Received healthy response to inference request in 1.4878733158111572s
Received healthy response to inference request in 1.456204891204834s
Received healthy response to inference request in 1.4265086650848389s
Received healthy response to inference request in 1.5145330429077148s
5 requests
0 failed requests
5th percentile: 1.432447910308838
10th percentile: 1.438387155532837
20th percentile: 1.450265645980835
30th percentile: 1.4625385761260987
40th percentile: 1.475205945968628
50th percentile: 1.4878733158111572
60th percentile: 1.4985372066497802
70th percentile: 1.5092010974884034
80th percentile: 1.6732577800750734
90th percentile: 1.9907072544097901
95th percentile: 2.1494319915771483
99th percentile: 2.276411781311035
mean time: 1.6386553287506103
Pipeline stage StressChecker completed in 8.89s
jic062-instruct-v16_v2 status is now deployed due to DeploymentManager action
jic062-instruct-v16_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of jic062-instruct-v16_v2
Running pipeline stage ISVCDeleter
Checking if service jic062-instruct-v16-v2 is running
Tearing down inference service jic062-instruct-v16-v2
Service jic062-instruct-v16-v2 has been torndown
Pipeline stage ISVCDeleter completed in 4.47s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key jic062-instruct-v16-v2/config.json from bucket guanaco-mkml-models
Deleting key jic062-instruct-v16-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key jic062-instruct-v16-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key jic062-instruct-v16-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key jic062-instruct-v16-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key jic062-instruct-v16-v2_reward/config.json from bucket guanaco-reward-models
Deleting key jic062-instruct-v16-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key jic062-instruct-v16-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key jic062-instruct-v16-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key jic062-instruct-v16-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key jic062-instruct-v16-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key jic062-instruct-v16-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.37s
jic062-instruct-v16_v2 status is now torndown due to DeploymentManager action