locutusque-apollo-0-2-ll_3902

developer_uid: Locutusque

submission_id: locutusque-apollo-0-2-ll_3902_v3

model_name: locutusque-apollo-0-2-ll_3902_v3

model_group: Locutusque/Apollo-0.2-Ll

status: torndown

timestamp: 2024-07-24T00:36:16+00:00

num_battles: 12217

num_wins: 5812

celo_rating: 1173.89

family_friendly_score: 0.0

submission_type: basic

model_repo: Locutusque/Apollo-0.2-Llama-3-8B

model_architecture: LlamaForCausalLM

reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2

model_num_parameters: 8030261248.0

best_of: 4

max_input_tokens: 512

max_output_tokens: 64

display_name: locutusque-apollo-0-2-ll_3902_v3

is_internal_developer: False

language_model: Locutusque/Apollo-0.2-Llama-3-8B

model_size: 8B

ranking_group: single

us_pacific_date: 2024-07-23

win_ratio: 0.4757305394122943

generation_params: {'temperature': 0.8, 'top_p': 0.95, 'min_p': 0.1, 'top_k': 40, 'presence_penalty': 0.05, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64, 'reward_max_token_input': 1024}

formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{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
Failed to get response for submission chaiml-sao10k-l3-rp-v3-3_v51: ('http://chaiml-sao10k-l3-rp-v3-3-v51-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Starting job with name locutusque-apollo-0-2-ll-3902-v3-mkmlizer
Waiting for job on locutusque-apollo-0-2-ll-3902-v3-mkmlizer to finish
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: ║     _____            __           __                                ║
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: ║       /___/                                                         ║
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: ║                                                                     ║
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: ║  Version: 0.9.5.post3                                               ║
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: ║  https://mk1.ai                                                     ║
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: ║                                                                     ║
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: ║  belonging to:                                                      ║
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: ║                                                                     ║
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: ║  Chai Research Corp.                                                ║
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: ║                                                                     ║
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: Downloaded to shared memory in 49.289s
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpfcrj4rzf, device:0
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:02, 121.50it/s]
Loading 0:   9%|▉         | 26/291 [00:00<00:03, 74.44it/s] 
Loading 0:  14%|█▎        | 40/291 [00:00<00:02, 93.35it/s]
Loading 0:  19%|█▉        | 56/291 [00:00<00:02, 108.48it/s]
Loading 0:  23%|██▎       | 68/291 [00:00<00:02, 88.73it/s] 
Loading 0:  28%|██▊       | 81/291 [00:00<00:02, 98.88it/s]
Loading 0:  32%|███▏      | 94/291 [00:00<00:01, 107.00it/s]
Loading 0:  36%|███▋      | 106/291 [00:01<00:02, 87.89it/s]
Loading 0:  42%|████▏     | 121/291 [00:01<00:01, 99.77it/s]
Loading 0:  47%|████▋     | 137/291 [00:01<00:01, 110.69it/s]
Loading 0:  51%|█████     | 149/291 [00:01<00:01, 88.53it/s] 
Loading 0:  57%|█████▋    | 166/291 [00:01<00:01, 103.41it/s]
Loading 0:  62%|██████▏   | 181/291 [00:01<00:00, 114.31it/s]
Loading 0:  67%|██████▋   | 194/291 [00:02<00:01, 89.18it/s] 
Loading 0:  73%|███████▎  | 211/291 [00:02<00:00, 103.00it/s]
Loading 0:  77%|███████▋  | 223/291 [00:02<00:00, 89.29it/s] 
Loading 0:  80%|████████  | 234/291 [00:02<00:00, 92.91it/s]
Loading 0:  85%|████████▍ | 247/291 [00:02<00:00, 101.15it/s]
Loading 0:  90%|█████████ | 263/291 [00:02<00:00, 91.20it/s] 
Loading 0:  94%|█████████▍| 274/291 [00:02<00:00, 93.92it/s]
Loading 0:  99%|█████████▉| 289/291 [00:02<00:00, 106.97it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: quantized model in 22.884s
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: Processed model Locutusque/Apollo-0.2-Llama-3-8B in 72.173s
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: creating bucket guanaco-mkml-models
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/locutusque-apollo-0-2-ll-3902-v3
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/locutusque-apollo-0-2-ll-3902-v3/special_tokens_map.json
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/locutusque-apollo-0-2-ll-3902-v3/config.json
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/locutusque-apollo-0-2-ll-3902-v3/tokenizer_config.json
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/locutusque-apollo-0-2-ll-3902-v3/tokenizer.json
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/locutusque-apollo-0-2-ll-3902-v3/flywheel_model.0.safetensors
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
locutusque-apollo-0-2-ll-3902-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.
locutusque-apollo-0-2-ll-3902-v3-mkmlizer:   warnings.warn(
locutusque-apollo-0-2-ll-3902-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.
locutusque-apollo-0-2-ll-3902-v3-mkmlizer:   warnings.warn(
locutusque-apollo-0-2-ll-3902-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.
locutusque-apollo-0-2-ll-3902-v3-mkmlizer:   warnings.warn(
Failed to get response for submission chaiml-sao10k-l3-rp-v3-3_v51: ('http://chaiml-sao10k-l3-rp-v3-3-v51-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission chaiml-sao10k-l3-rp-v3-3_v51: ('http://chaiml-sao10k-l3-rp-v3-3-v51-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: Saving duration: 0.323s
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.710s
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: creating bucket guanaco-reward-models
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/locutusque-apollo-0-2-ll-3902-v3_reward
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/locutusque-apollo-0-2-ll-3902-v3_reward/config.json
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/locutusque-apollo-0-2-ll-3902-v3_reward/special_tokens_map.json
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/locutusque-apollo-0-2-ll-3902-v3_reward/tokenizer_config.json
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/locutusque-apollo-0-2-ll-3902-v3_reward/merges.txt
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/locutusque-apollo-0-2-ll-3902-v3_reward/vocab.json
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/locutusque-apollo-0-2-ll-3902-v3_reward/tokenizer.json
locutusque-apollo-0-2-ll-3902-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/locutusque-apollo-0-2-ll-3902-v3_reward/reward.tensors
Job locutusque-apollo-0-2-ll-3902-v3-mkmlizer completed after 105.3s with status: succeeded
Stopping job with name locutusque-apollo-0-2-ll-3902-v3-mkmlizer
Pipeline stage MKMLizer completed in 106.32s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service locutusque-apollo-0-2-ll-3902-v3
Waiting for inference service locutusque-apollo-0-2-ll-3902-v3 to be ready
Failed to get response for submission undi95-meta-llama-3-70b_6209_v18: ('http://undi95-meta-llama-3-70b-6209-v18-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:40688->127.0.0.1:8080: read: connection reset by peer\n')
Inference service locutusque-apollo-0-2-ll-3902-v3 ready after 50.49710202217102s
Pipeline stage ISVCDeployer completed in 52.24s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0997848510742188s
Received healthy response to inference request in 1.1345911026000977s
Received healthy response to inference request in 1.13480544090271s
Received healthy response to inference request in 1.1467866897583008s
Received healthy response to inference request in 1.3670647144317627s
5 requests
0 failed requests
5th percentile: 1.13463397026062
10th percentile: 1.1346768379211425
20th percentile: 1.1347625732421875
30th percentile: 1.137201690673828
40th percentile: 1.1419941902160644
50th percentile: 1.1467866897583008
60th percentile: 1.2348978996276856
70th percentile: 1.3230091094970702
80th percentile: 1.513608741760254
90th percentile: 1.8066967964172365
95th percentile: 1.9532408237457275
99th percentile: 2.0704760456085203
mean time: 1.376606559753418
Pipeline stage StressChecker completed in 7.56s
locutusque-apollo-0-2-ll_3902_v3 status is now deployed due to DeploymentManager action
locutusque-apollo-0-2-ll_3902_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of locutusque-apollo-0-2-ll_3902_v3
Running pipeline stage ISVCDeleter
Checking if service locutusque-apollo-0-2-ll-3902-v3 is running
Tearing down inference service locutusque-apollo-0-2-ll-3902-v3
Service locutusque-apollo-0-2-ll-3902-v3 has been torndown
Pipeline stage ISVCDeleter completed in 4.87s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key locutusque-apollo-0-2-ll-3902-v3/config.json from bucket guanaco-mkml-models
Deleting key locutusque-apollo-0-2-ll-3902-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key locutusque-apollo-0-2-ll-3902-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key locutusque-apollo-0-2-ll-3902-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key locutusque-apollo-0-2-ll-3902-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key locutusque-apollo-0-2-ll-3902-v3_reward/config.json from bucket guanaco-reward-models
Deleting key locutusque-apollo-0-2-ll-3902-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key locutusque-apollo-0-2-ll-3902-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key locutusque-apollo-0-2-ll-3902-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key locutusque-apollo-0-2-ll-3902-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key locutusque-apollo-0-2-ll-3902-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key locutusque-apollo-0-2-ll-3902-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.28s
locutusque-apollo-0-2-ll_3902_v3 status is now torndown due to DeploymentManager action