hastagaras-l3-dt-prep-test

developer_uid: Hastagaras
submission_id: hastagaras-l3-dt-prep-test_v3
model_name: hastagaras-l3-dt-prep-test_v3
model_group: Hastagaras/l3-dt-prep-te
status: torndown
timestamp: 2024-07-25T06:34:08+00:00
num_battles: 8101
num_wins: 4058
celo_rating: 1202.47
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/l3-dt-prep-test
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: hastagaras-l3-dt-prep-test_v3
is_internal_developer: False
language_model: Hastagaras/l3-dt-prep-test
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-24
win_ratio: 0.500925811628194
generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64, 'reward_max_token_input': 512}
formatter: {'memory_template': '<|im_start|>system\n{memory}\n\n', 'prompt_template': '{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\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 hastagaras-l3-dt-prep-test-v3-mkmlizer
Waiting for job on hastagaras-l3-dt-prep-test-v3-mkmlizer to finish
Failed to get response for submission neversleep-lumimaid-mist_1884_v1: ('http://neversleep-lumimaid-mist-1884-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
hastagaras-l3-dt-prep-test-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-l3-dt-prep-test-v3-mkmlizer: ║     _____            __           __                                ║
hastagaras-l3-dt-prep-test-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-l3-dt-prep-test-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-l3-dt-prep-test-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-l3-dt-prep-test-v3-mkmlizer: ║       /___/                                                         ║
hastagaras-l3-dt-prep-test-v3-mkmlizer: ║                                                                     ║
hastagaras-l3-dt-prep-test-v3-mkmlizer: ║  Version: 0.9.6                                                     ║
hastagaras-l3-dt-prep-test-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-l3-dt-prep-test-v3-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-l3-dt-prep-test-v3-mkmlizer: ║                                                                     ║
hastagaras-l3-dt-prep-test-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-l3-dt-prep-test-v3-mkmlizer: ║  belonging to:                                                      ║
hastagaras-l3-dt-prep-test-v3-mkmlizer: ║                                                                     ║
hastagaras-l3-dt-prep-test-v3-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-l3-dt-prep-test-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-l3-dt-prep-test-v3-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
hastagaras-l3-dt-prep-test-v3-mkmlizer: ║                                                                     ║
hastagaras-l3-dt-prep-test-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission neversleep-lumimaid-mist_1893_v1: ('http://neversleep-lumimaid-mist-1893-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission neversleep-lumimaid-mist_1884_v1: ('http://neversleep-lumimaid-mist-1884-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission neversleep-lumimaid-mist_1884_v1: ('http://neversleep-lumimaid-mist-1884-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
hastagaras-l3-dt-prep-test-v3-mkmlizer: Downloaded to shared memory in 22.539s
hastagaras-l3-dt-prep-test-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpe1cok_ws, device:0
hastagaras-l3-dt-prep-test-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-l3-dt-prep-test-v3-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:09, 30.84it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:05, 51.20it/s]
Loading 0:   7%|▋         | 19/291 [00:00<00:05, 45.77it/s]
Loading 0:   8%|▊         | 24/291 [00:00<00:05, 44.75it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:04, 52.02it/s]
Loading 0:  13%|█▎        | 37/291 [00:00<00:05, 49.69it/s]
Loading 0:  15%|█▌        | 44/291 [00:00<00:04, 54.94it/s]
Loading 0:  17%|█▋        | 50/291 [00:01<00:04, 49.87it/s]
Loading 0:  20%|██        | 59/291 [00:01<00:04, 52.96it/s]
Loading 0:  23%|██▎       | 68/291 [00:01<00:04, 55.11it/s]
Loading 0:  26%|██▋       | 77/291 [00:01<00:03, 54.67it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:04, 43.86it/s]
Loading 0:  30%|███       | 88/291 [00:01<00:04, 43.44it/s]
Loading 0:  33%|███▎      | 95/291 [00:01<00:04, 43.73it/s]
Loading 0:  36%|███▌      | 104/291 [00:02<00:03, 47.29it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:03, 54.09it/s]
Loading 0:  41%|████      | 118/291 [00:02<00:03, 50.81it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:03, 52.55it/s]
Loading 0:  45%|████▌     | 131/291 [00:02<00:03, 49.98it/s]
Loading 0:  48%|████▊     | 139/291 [00:02<00:02, 56.93it/s]
Loading 0:  50%|████▉     | 145/291 [00:02<00:02, 54.71it/s]
Loading 0:  52%|█████▏    | 151/291 [00:02<00:02, 54.07it/s]
Loading 0:  54%|█████▍    | 158/291 [00:03<00:02, 47.39it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:02, 54.06it/s]
Loading 0:  59%|█████▉    | 172/291 [00:03<00:02, 50.25it/s]
Loading 0:  62%|██████▏   | 179/291 [00:03<00:02, 54.54it/s]
Loading 0:  64%|██████▎   | 185/291 [00:03<00:01, 54.29it/s]
Loading 0:  66%|██████▌   | 191/291 [00:03<00:02, 35.01it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:02, 35.64it/s]
Loading 0:  69%|██████▉   | 201/291 [00:04<00:02, 38.34it/s]
Loading 0:  71%|███████   | 206/291 [00:04<00:02, 39.78it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:01, 41.95it/s]
Loading 0:  75%|███████▍  | 217/291 [00:04<00:01, 42.19it/s]
Loading 0:  77%|███████▋  | 223/291 [00:04<00:01, 46.42it/s]
Loading 0:  79%|███████▉  | 230/291 [00:04<00:01, 44.91it/s]
Loading 0:  82%|████████▏ | 239/291 [00:04<00:01, 47.87it/s]
Loading 0:  85%|████████▌ | 248/291 [00:05<00:00, 50.45it/s]
Loading 0:  88%|████████▊ | 257/291 [00:05<00:00, 52.74it/s]
Loading 0:  91%|█████████▏| 266/291 [00:05<00:00, 53.54it/s]
Loading 0:  94%|█████████▍| 274/291 [00:05<00:00, 58.94it/s]
Loading 0:  97%|█████████▋| 281/291 [00:05<00:00, 53.32it/s]
Loading 0:  99%|█████████▊| 287/291 [00:11<00:00,  4.22it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-l3-dt-prep-test-v3-mkmlizer: quantized model in 25.597s
hastagaras-l3-dt-prep-test-v3-mkmlizer: Processed model Hastagaras/l3-dt-prep-test in 48.137s
hastagaras-l3-dt-prep-test-v3-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-l3-dt-prep-test-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-l3-dt-prep-test-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-l3-dt-prep-test-v3
hastagaras-l3-dt-prep-test-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-l3-dt-prep-test-v3/special_tokens_map.json
hastagaras-l3-dt-prep-test-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-l3-dt-prep-test-v3/config.json
hastagaras-l3-dt-prep-test-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-l3-dt-prep-test-v3/tokenizer_config.json
hastagaras-l3-dt-prep-test-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-l3-dt-prep-test-v3/tokenizer.json
Failed to get response for submission neversleep-lumimaid-mist_1893_v1: ('http://neversleep-lumimaid-mist-1893-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
hastagaras-l3-dt-prep-test-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-l3-dt-prep-test-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:950: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
hastagaras-l3-dt-prep-test-v3-mkmlizer:   warnings.warn(
hastagaras-l3-dt-prep-test-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:778: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
hastagaras-l3-dt-prep-test-v3-mkmlizer:   warnings.warn(
hastagaras-l3-dt-prep-test-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.
hastagaras-l3-dt-prep-test-v3-mkmlizer:   warnings.warn(
hastagaras-l3-dt-prep-test-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-l3-dt-prep-test-v3-mkmlizer: Saving duration: 0.324s
hastagaras-l3-dt-prep-test-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.201s
hastagaras-l3-dt-prep-test-v3-mkmlizer: creating bucket guanaco-reward-models
hastagaras-l3-dt-prep-test-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-l3-dt-prep-test-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-l3-dt-prep-test-v3_reward
hastagaras-l3-dt-prep-test-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-l3-dt-prep-test-v3_reward/config.json
hastagaras-l3-dt-prep-test-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-l3-dt-prep-test-v3_reward/special_tokens_map.json
hastagaras-l3-dt-prep-test-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-l3-dt-prep-test-v3_reward/tokenizer_config.json
hastagaras-l3-dt-prep-test-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-l3-dt-prep-test-v3_reward/merges.txt
hastagaras-l3-dt-prep-test-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-l3-dt-prep-test-v3_reward/vocab.json
hastagaras-l3-dt-prep-test-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-l3-dt-prep-test-v3_reward/tokenizer.json
Job hastagaras-l3-dt-prep-test-v3-mkmlizer completed after 84.64s with status: succeeded
Stopping job with name hastagaras-l3-dt-prep-test-v3-mkmlizer
Pipeline stage MKMLizer completed in 85.95s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-l3-dt-prep-test-v3
Waiting for inference service hastagaras-l3-dt-prep-test-v3 to be ready
Failed to get response for submission neversleep-lumimaid-mist_1884_v1: ('http://neversleep-lumimaid-mist-1884-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission neversleep-lumimaid-mist_1884_v1: ('http://neversleep-lumimaid-mist-1884-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission neversleep-lumimaid-mist_7954_v1: ('http://neversleep-lumimaid-mist-7954-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission neversleep-lumimaid-mist_1893_v1: ('http://neversleep-lumimaid-mist-1893-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission neversleep-lumimaid-mist_7954_v1: ('http://neversleep-lumimaid-mist-7954-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission neversleep-lumimaid-mist_1884_v1: ('http://neversleep-lumimaid-mist-1884-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Inference service hastagaras-l3-dt-prep-test-v3 ready after 60.63029980659485s
Pipeline stage ISVCDeployer completed in 62.27s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2243664264678955s
Received healthy response to inference request in 1.268824577331543s
Received healthy response to inference request in 1.2594475746154785s
Received healthy response to inference request in 1.252687931060791s
Received healthy response to inference request in 1.2642371654510498s
5 requests
0 failed requests
5th percentile: 1.2540398597717286
10th percentile: 1.255391788482666
20th percentile: 1.258095645904541
30th percentile: 1.2604054927825927
40th percentile: 1.2623213291168214
50th percentile: 1.2642371654510498
60th percentile: 1.2660721302032472
70th percentile: 1.2679070949554443
80th percentile: 1.4599329471588136
90th percentile: 1.8421496868133547
95th percentile: 2.0332580566406246
99th percentile: 2.1861447525024413
mean time: 1.4539127349853516
Pipeline stage StressChecker completed in 7.98s
hastagaras-l3-dt-prep-test_v3 status is now deployed due to DeploymentManager action
hastagaras-l3-dt-prep-test_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-l3-dt-prep-test_v3
Running pipeline stage ISVCDeleter
Checking if service hastagaras-l3-dt-prep-test-v3 is running
Tearing down inference service hastagaras-l3-dt-prep-test-v3
Service hastagaras-l3-dt-prep-test-v3 has been torndown
Pipeline stage ISVCDeleter completed in 5.12s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-l3-dt-prep-test-v3/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-dt-prep-test-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-l3-dt-prep-test-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-dt-prep-test-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-dt-prep-test-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-l3-dt-prep-test-v3_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-dt-prep-test-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-l3-dt-prep-test-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-l3-dt-prep-test-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-dt-prep-test-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-dt-prep-test-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-dt-prep-test-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.25s
hastagaras-l3-dt-prep-test_v3 status is now torndown due to DeploymentManager action