developer_uid: zonemercy
submission_id: nousresearch-meta-llama_4941_v93
model_name: meta-bo1-base
model_group: NousResearch/Meta-Llama-
status: torndown
timestamp: 2024-07-29T18:23:58+00:00
num_battles: 12561
num_wins: 5075
celo_rating: 1114.48
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: 2024-07-29
win_ratio: 0.4040283416925404
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-v93-mkmlizer
Waiting for job on nousresearch-meta-llama-4941-v93-mkmlizer to finish
nousresearch-meta-llama-4941-v93-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nousresearch-meta-llama-4941-v93-mkmlizer: ║     _____            __           __                                ║
nousresearch-meta-llama-4941-v93-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
nousresearch-meta-llama-4941-v93-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
nousresearch-meta-llama-4941-v93-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
nousresearch-meta-llama-4941-v93-mkmlizer: ║       /___/                                                         ║
nousresearch-meta-llama-4941-v93-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4941-v93-mkmlizer: ║  Version: 0.9.7                                                     ║
nousresearch-meta-llama-4941-v93-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
nousresearch-meta-llama-4941-v93-mkmlizer: ║  https://mk1.ai                                                     ║
nousresearch-meta-llama-4941-v93-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4941-v93-mkmlizer: ║  The license key for the current software has been verified as      ║
nousresearch-meta-llama-4941-v93-mkmlizer: ║  belonging to:                                                      ║
nousresearch-meta-llama-4941-v93-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4941-v93-mkmlizer: ║  Chai Research Corp.                                                ║
nousresearch-meta-llama-4941-v93-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
nousresearch-meta-llama-4941-v93-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
nousresearch-meta-llama-4941-v93-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4941-v93-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nousresearch-meta-llama-4941-v93-mkmlizer: Downloaded to shared memory in 22.634s
nousresearch-meta-llama-4941-v93-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmps47ml2gz, device:0
nousresearch-meta-llama-4941-v93-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nousresearch-meta-llama-4941-v93-mkmlizer: quantized model in 26.483s
nousresearch-meta-llama-4941-v93-mkmlizer: Processed model NousResearch/Meta-Llama-3-8B-Instruct in 49.117s
nousresearch-meta-llama-4941-v93-mkmlizer: creating bucket guanaco-mkml-models
nousresearch-meta-llama-4941-v93-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nousresearch-meta-llama-4941-v93-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v93
nousresearch-meta-llama-4941-v93-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v93/config.json
nousresearch-meta-llama-4941-v93-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v93/special_tokens_map.json
nousresearch-meta-llama-4941-v93-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v93/tokenizer_config.json
nousresearch-meta-llama-4941-v93-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v93/tokenizer.json
nousresearch-meta-llama-4941-v93-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v93/flywheel_model.0.safetensors
nousresearch-meta-llama-4941-v93-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
nousresearch-meta-llama-4941-v93-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:07, 38.77it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:05, 49.27it/s]
Loading 0:   8%|▊         | 23/291 [00:00<00:05, 51.66it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:04, 59.74it/s]
Loading 0:  13%|█▎        | 38/291 [00:00<00:04, 55.22it/s]
Loading 0:  15%|█▌        | 44/291 [00:00<00:04, 54.97it/s]
Loading 0:  17%|█▋        | 50/291 [00:00<00:04, 48.26it/s]
Loading 0:  20%|██        | 59/291 [00:01<00:04, 50.11it/s]
Loading 0:  23%|██▎       | 68/291 [00:01<00:04, 51.16it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:03, 56.60it/s]
Loading 0:  28%|██▊       | 82/291 [00:01<00:03, 53.08it/s]
Loading 0:  30%|███       | 88/291 [00:01<00:05, 38.47it/s]
Loading 0:  33%|███▎      | 95/291 [00:01<00:04, 39.60it/s]
Loading 0:  35%|███▌      | 102/291 [00:02<00:04, 45.51it/s]
Loading 0:  37%|███▋      | 108/291 [00:02<00:03, 47.99it/s]
Loading 0:  39%|███▉      | 114/291 [00:02<00:04, 43.04it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 48.38it/s]
Loading 0:  44%|████▎     | 127/291 [00:02<00:03, 47.05it/s]
Loading 0:  46%|████▌     | 133/291 [00:02<00:03, 47.89it/s]
Loading 0:  48%|████▊     | 140/291 [00:02<00:03, 45.73it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:02, 52.73it/s]
Loading 0:  53%|█████▎    | 154/291 [00:03<00:02, 48.17it/s]
Loading 0:  55%|█████▍    | 160/291 [00:03<00:02, 49.25it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:02, 51.75it/s]
Loading 0:  59%|█████▉    | 172/291 [00:03<00:02, 48.91it/s]
Loading 0:  62%|██████▏   | 179/291 [00:03<00:02, 52.41it/s]
Loading 0:  64%|██████▎   | 185/291 [00:03<00:01, 53.76it/s]
Loading 0:  66%|██████▌   | 191/291 [00:04<00:02, 35.53it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:02, 37.61it/s]
Loading 0:  70%|██████▉   | 203/291 [00:04<00:02, 39.04it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:01, 46.80it/s]
Loading 0:  75%|███████▍  | 217/291 [00:04<00:01, 45.78it/s]
Loading 0:  76%|███████▋  | 222/291 [00:04<00:01, 46.18it/s]
Loading 0:  79%|███████▊  | 229/291 [00:04<00:01, 51.16it/s]
Loading 0:  81%|████████  | 235/291 [00:04<00:01, 47.66it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:01, 49.27it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:00, 52.00it/s]
Loading 0:  87%|████████▋ | 253/291 [00:05<00:00, 46.49it/s]
Loading 0:  89%|████████▊ | 258/291 [00:05<00:00, 45.03it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 50.81it/s]
Loading 0:  93%|█████████▎| 271/291 [00:05<00:00, 48.44it/s]
Loading 0:  95%|█████████▌| 277/291 [00:05<00:00, 49.41it/s]
Loading 0:  97%|█████████▋| 283/291 [00:05<00:00, 44.55it/s]
Loading 0:  99%|█████████▉| 288/291 [00:11<00:00,  3.31it/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.
nousresearch-meta-llama-4941-v93-mkmlizer:   warnings.warn(
nousresearch-meta-llama-4941-v93-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.
nousresearch-meta-llama-4941-v93-mkmlizer:   warnings.warn(
nousresearch-meta-llama-4941-v93-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-v93-mkmlizer:   warnings.warn(
nousresearch-meta-llama-4941-v93-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:05<00:05,  5.75s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  4.11s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  4.36s/it]
nousresearch-meta-llama-4941-v93-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  2.17it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.65it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.31it/s]
nousresearch-meta-llama-4941-v93-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nousresearch-meta-llama-4941-v93-mkmlizer: Saving duration: 1.349s
nousresearch-meta-llama-4941-v93-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.575s
nousresearch-meta-llama-4941-v93-mkmlizer: creating bucket guanaco-reward-models
nousresearch-meta-llama-4941-v93-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nousresearch-meta-llama-4941-v93-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nousresearch-meta-llama-4941-v93_reward
nousresearch-meta-llama-4941-v93-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v93_reward/special_tokens_map.json
nousresearch-meta-llama-4941-v93-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v93_reward/config.json
nousresearch-meta-llama-4941-v93-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v93_reward/tokenizer_config.json
nousresearch-meta-llama-4941-v93-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nousresearch-meta-llama-4941-v93_reward/merges.txt
nousresearch-meta-llama-4941-v93-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v93_reward/vocab.json
nousresearch-meta-llama-4941-v93-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v93_reward/tokenizer.json
nousresearch-meta-llama-4941-v93-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nousresearch-meta-llama-4941-v93_reward/reward.tensors
Connection pool is full, discarding connection: %s. Connection pool size: %s
Job nousresearch-meta-llama-4941-v93-mkmlizer completed after 95.95s with status: succeeded
Stopping job with name nousresearch-meta-llama-4941-v93-mkmlizer
Pipeline stage MKMLizer completed in 97.00s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service nousresearch-meta-llama-4941-v93
Waiting for inference service nousresearch-meta-llama-4941-v93 to be ready
Inference service nousresearch-meta-llama-4941-v93 ready after 111.02032279968262s
Pipeline stage ISVCDeployer completed in 113.16s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8497188091278076s
Received healthy response to inference request in 1.0546119213104248s
Received healthy response to inference request in 0.866297721862793s
Received healthy response to inference request in 0.3743925094604492s
Received healthy response to inference request in 0.8178143501281738s
5 requests
0 failed requests
5th percentile: 0.46307687759399413
10th percentile: 0.551761245727539
20th percentile: 0.729129981994629
30th percentile: 0.8275110244750976
40th percentile: 0.8469043731689453
50th percentile: 0.866297721862793
60th percentile: 0.9416234016418457
70th percentile: 1.0169490814208983
80th percentile: 1.2136332988739016
90th percentile: 1.5316760540008545
95th percentile: 1.6906974315643308
99th percentile: 1.8179145336151123
mean time: 0.9925670623779297
Pipeline stage StressChecker completed in 5.65s
nousresearch-meta-llama_4941_v93 status is now deployed due to DeploymentManager action
nousresearch-meta-llama_4941_v93 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of nousresearch-meta-llama_4941_v93
Running pipeline stage ISVCDeleter
Checking if service nousresearch-meta-llama-4941-v93 is running
Tearing down inference service nousresearch-meta-llama-4941-v93
Service nousresearch-meta-llama-4941-v93 has been torndown
Pipeline stage ISVCDeleter completed in 4.77s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key nousresearch-meta-llama-4941-v93/config.json from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4941-v93/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4941-v93/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4941-v93/tokenizer.json from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4941-v93/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key nousresearch-meta-llama-4941-v93_reward/config.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v93_reward/merges.txt from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v93_reward/reward.tensors from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v93_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v93_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v93_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v93_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.37s
nousresearch-meta-llama_4941_v93 status is now torndown due to DeploymentManager action