nousresearch-meta-llama_4941

developer_uid: zonemercy
submission_id: nousresearch-meta-llama_4941_v84
model_name: meta-bo1-base
model_group: NousResearch/Meta-Llama-
status: torndown
timestamp: 2024-07-24T23:22:04+00:00
num_battles: 12993
num_wins: 5187
celo_rating: 1114.07
family_friendly_score: 0.0
submission_type: basic
model_repo: NousResearch/Meta-Llama-3-8B-Instruct
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
model_num_parameters: 8030261248.0
best_of: 1
max_input_tokens: 512
max_output_tokens: 64
display_name: meta-bo1-base
is_internal_developer: True
language_model: NousResearch/Meta-Llama-3-8B-Instruct
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-24
win_ratio: 0.3992149619025629
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '<|user|>', '###'], 'max_input_tokens': 512, 'best_of': 1, 'max_output_tokens': 64, 'reward_max_token_input': 256}
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
Starting job with name nousresearch-meta-llama-4941-v84-mkmlizer
Waiting for job on nousresearch-meta-llama-4941-v84-mkmlizer to finish
nousresearch-meta-llama-4941-v84-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nousresearch-meta-llama-4941-v84-mkmlizer: ║     _____            __           __                                ║
nousresearch-meta-llama-4941-v84-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
nousresearch-meta-llama-4941-v84-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
nousresearch-meta-llama-4941-v84-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
nousresearch-meta-llama-4941-v84-mkmlizer: ║       /___/                                                         ║
nousresearch-meta-llama-4941-v84-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4941-v84-mkmlizer: ║  Version: 0.9.6                                                     ║
nousresearch-meta-llama-4941-v84-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
nousresearch-meta-llama-4941-v84-mkmlizer: ║  https://mk1.ai                                                     ║
nousresearch-meta-llama-4941-v84-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4941-v84-mkmlizer: ║  The license key for the current software has been verified as      ║
nousresearch-meta-llama-4941-v84-mkmlizer: ║  belonging to:                                                      ║
nousresearch-meta-llama-4941-v84-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4941-v84-mkmlizer: ║  Chai Research Corp.                                                ║
nousresearch-meta-llama-4941-v84-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
nousresearch-meta-llama-4941-v84-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
nousresearch-meta-llama-4941-v84-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4941-v84-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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', '{"error":"TypeError : SamplingParameters.__init__() got an unexpected keyword argument \'reward_max_tokens\'"}')
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')
nousresearch-meta-llama-4941-v84-mkmlizer: Downloaded to shared memory in 24.040s
nousresearch-meta-llama-4941-v84-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpo48or_cm, device:0
nousresearch-meta-llama-4941-v84-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nousresearch-meta-llama-4941-v84-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:07, 36.35it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:05, 55.17it/s]
Loading 0:   7%|▋         | 19/291 [00:00<00:05, 48.30it/s]
Loading 0:   8%|▊         | 24/291 [00:00<00:05, 48.02it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:05, 47.42it/s]
Loading 0:  14%|█▍        | 41/291 [00:00<00:05, 48.73it/s]
Loading 0:  17%|█▋        | 50/291 [00:01<00:04, 49.65it/s]
Loading 0:  20%|█▉        | 58/291 [00:01<00:04, 55.30it/s]
Loading 0:  22%|██▏       | 64/291 [00:01<00:04, 48.74it/s]
Loading 0:  24%|██▍       | 70/291 [00:01<00:04, 49.41it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:04, 50.33it/s]
Loading 0:  28%|██▊       | 82/291 [00:01<00:04, 47.00it/s]
Loading 0:  30%|██▉       | 87/291 [00:01<00:06, 32.43it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:05, 38.99it/s]
Loading 0:  34%|███▍      | 100/291 [00:02<00:04, 38.77it/s]
Loading 0:  36%|███▌      | 105/291 [00:02<00:04, 39.64it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:03, 45.34it/s]
Loading 0:  41%|████      | 118/291 [00:02<00:03, 43.27it/s]
Loading 0:  42%|████▏     | 123/291 [00:02<00:03, 43.17it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 48.79it/s]
Loading 0:  47%|████▋     | 136/291 [00:02<00:03, 46.07it/s]
Loading 0:  48%|████▊     | 141/291 [00:03<00:03, 44.83it/s]
Loading 0:  51%|█████     | 147/291 [00:03<00:02, 48.57it/s]
Loading 0:  53%|█████▎    | 153/291 [00:03<00:02, 50.32it/s]
Loading 0:  55%|█████▍    | 159/291 [00:03<00:03, 43.58it/s]
Loading 0:  57%|█████▋    | 165/291 [00:03<00:02, 47.06it/s]
Loading 0:  58%|█████▊    | 170/291 [00:03<00:02, 47.23it/s]
Loading 0:  60%|██████    | 176/291 [00:03<00:02, 50.57it/s]
Loading 0:  63%|██████▎   | 182/291 [00:04<00:02, 42.25it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:03, 31.66it/s]
Loading 0:  66%|██████▌   | 191/291 [00:04<00:03, 33.12it/s]
Loading 0:  67%|██████▋   | 195/291 [00:04<00:02, 33.72it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:02, 40.99it/s]
Loading 0:  71%|███████▏  | 208/291 [00:04<00:02, 40.33it/s]
Loading 0:  73%|███████▎  | 213/291 [00:04<00:01, 41.23it/s]
Loading 0:  75%|███████▌  | 219/291 [00:04<00:01, 45.46it/s]
Loading 0:  77%|███████▋  | 224/291 [00:05<00:01, 45.49it/s]
Loading 0:  79%|███████▊  | 229/291 [00:05<00:01, 46.05it/s]
Loading 0:  81%|████████  | 235/291 [00:05<00:01, 44.38it/s]
Loading 0:  82%|████████▏ | 240/291 [00:05<00:01, 44.21it/s]
Loading 0:  85%|████████▍ | 246/291 [00:05<00:00, 47.61it/s]
Loading 0:  86%|████████▋ | 251/291 [00:05<00:00, 47.40it/s]
Loading 0:  88%|████████▊ | 257/291 [00:05<00:00, 42.38it/s]
Loading 0:  91%|█████████ | 264/291 [00:05<00:00, 47.87it/s]
Loading 0:  92%|█████████▏| 269/291 [00:06<00:00, 46.86it/s]
Loading 0:  94%|█████████▍| 274/291 [00:06<00:00, 47.50it/s]
Loading 0:  96%|█████████▌| 280/291 [00:06<00:00, 45.68it/s]
Loading 0:  98%|█████████▊| 285/291 [00:06<00:00, 45.02it/s]
Loading 0: 100%|█████████▉| 290/291 [00:11<00:00,  3.13it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
nousresearch-meta-llama-4941-v84-mkmlizer: quantized model in 26.204s
nousresearch-meta-llama-4941-v84-mkmlizer: Processed model NousResearch/Meta-Llama-3-8B-Instruct in 50.244s
nousresearch-meta-llama-4941-v84-mkmlizer: creating bucket guanaco-mkml-models
nousresearch-meta-llama-4941-v84-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nousresearch-meta-llama-4941-v84-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v84
nousresearch-meta-llama-4941-v84-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v84/config.json
nousresearch-meta-llama-4941-v84-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v84/special_tokens_map.json
nousresearch-meta-llama-4941-v84-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v84/tokenizer_config.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')
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')
nousresearch-meta-llama-4941-v84-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v84/flywheel_model.0.safetensors
nousresearch-meta-llama-4941-v84-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
nousresearch-meta-llama-4941-v84-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.
nousresearch-meta-llama-4941-v84-mkmlizer:   warnings.warn(
nousresearch-meta-llama-4941-v84-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.
nousresearch-meta-llama-4941-v84-mkmlizer:   warnings.warn(
nousresearch-meta-llama-4941-v84-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.
nousresearch-meta-llama-4941-v84-mkmlizer:   warnings.warn(
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_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')
nousresearch-meta-llama-4941-v84-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:05<00:05,  5.89s/it]
Downloading shards: 100%|██████████| 2/2 [00:09<00:00,  4.43s/it]
Downloading shards: 100%|██████████| 2/2 [00:09<00:00,  4.65s/it]
nousresearch-meta-llama-4941-v84-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  2.43it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.97it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.63it/s]
nousresearch-meta-llama-4941-v84-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
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')
nousresearch-meta-llama-4941-v84-mkmlizer: Saving duration: 1.335s
nousresearch-meta-llama-4941-v84-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 14.277s
nousresearch-meta-llama-4941-v84-mkmlizer: creating bucket guanaco-reward-models
nousresearch-meta-llama-4941-v84-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nousresearch-meta-llama-4941-v84-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nousresearch-meta-llama-4941-v84_reward
nousresearch-meta-llama-4941-v84-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v84_reward/config.json
nousresearch-meta-llama-4941-v84-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v84_reward/special_tokens_map.json
nousresearch-meta-llama-4941-v84-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v84_reward/tokenizer_config.json
nousresearch-meta-llama-4941-v84-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nousresearch-meta-llama-4941-v84_reward/merges.txt
nousresearch-meta-llama-4941-v84-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v84_reward/vocab.json
nousresearch-meta-llama-4941-v84-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v84_reward/tokenizer.json
nousresearch-meta-llama-4941-v84-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nousresearch-meta-llama-4941-v84_reward/reward.tensors
Job nousresearch-meta-llama-4941-v84-mkmlizer completed after 148.37s with status: succeeded
Stopping job with name nousresearch-meta-llama-4941-v84-mkmlizer
Pipeline stage MKMLizer completed in 149.37s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service nousresearch-meta-llama-4941-v84
Waiting for inference service nousresearch-meta-llama-4941-v84 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')
Inference service nousresearch-meta-llama-4941-v84 ready after 60.40113425254822s
Pipeline stage ISVCDeployer completed in 62.02s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.854236125946045s
Received healthy response to inference request in 1.007441759109497s
Received healthy response to inference request in 1.0423130989074707s
Received healthy response to inference request in 1.0537619590759277s
Received healthy response to inference request in 1.0466501712799072s
5 requests
0 failed requests
5th percentile: 1.0144160270690918
10th percentile: 1.0213902950286866
20th percentile: 1.035338830947876
30th percentile: 1.043180513381958
40th percentile: 1.0449153423309325
50th percentile: 1.0466501712799072
60th percentile: 1.0494948863983153
70th percentile: 1.0523396015167237
80th percentile: 1.2138567924499513
90th percentile: 1.534046459197998
95th percentile: 1.6941412925720214
99th percentile: 1.8222171592712402
mean time: 1.2008806228637696
Pipeline stage StressChecker completed in 6.70s
nousresearch-meta-llama_4941_v84 status is now deployed due to DeploymentManager action
nousresearch-meta-llama_4941_v84 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of nousresearch-meta-llama_4941_v84
Running pipeline stage ISVCDeleter
Checking if service nousresearch-meta-llama-4941-v84 is running
Tearing down inference service nousresearch-meta-llama-4941-v84
Service nousresearch-meta-llama-4941-v84 has been torndown
Pipeline stage ISVCDeleter completed in 5.35s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key nousresearch-meta-llama-4941-v84/config.json from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4941-v84/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4941-v84/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4941-v84/tokenizer.json from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4941-v84/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key nousresearch-meta-llama-4941-v84_reward/config.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v84_reward/merges.txt from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v84_reward/reward.tensors from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v84_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v84_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v84_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v84_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.84s
nousresearch-meta-llama_4941_v84 status is now torndown due to DeploymentManager action