submission_id: inv-exponenta-alpha-7b_v2
developer_uid: Inv
status: inactive
model_repo: Inv/Exponenta-Alpha-7B
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, '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}
formatter: {'memory_template': 'This is an entertaining conversation. You are {bot_name} who has the persona: {memory}.\nPlay the role of {bot_name}. Engage in a chat with {user_name} while staying in character. You should create a fun dialogue which entertains {user_name}.\n####\n', 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:'}
reward_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}:'}
timestamp: 2024-03-28T19:52:14+00:00
model_name: inv-exponenta-alpha-7b_v2
model_eval_status: success
safety_score: 0.98
entertaining: 7.14
stay_in_character: 8.62
user_preference: 7.66
double_thumbs_up: 738
thumbs_up: 1018
thumbs_down: 443
num_battles: 96042
num_wins: 51386
win_ratio: 0.5350367547531288
celo_rating: 1182.39
Resubmit model
Running pipeline stage MKMLizer
Starting job with name inv-exponenta-alpha-7b-v2-mkmlizer
Waiting for job on inv-exponenta-alpha-7b-v2-mkmlizer to finish
inv-exponenta-alpha-7b-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
inv-exponenta-alpha-7b-v2-mkmlizer: ║ _____ __ __ ║
inv-exponenta-alpha-7b-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
inv-exponenta-alpha-7b-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
inv-exponenta-alpha-7b-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
inv-exponenta-alpha-7b-v2-mkmlizer: ║ /___/ ║
inv-exponenta-alpha-7b-v2-mkmlizer: ║ ║
inv-exponenta-alpha-7b-v2-mkmlizer: ║ Version: 0.6.11 ║
inv-exponenta-alpha-7b-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
inv-exponenta-alpha-7b-v2-mkmlizer: ║ ║
inv-exponenta-alpha-7b-v2-mkmlizer: ║ The license key for the current software has been verified as ║
inv-exponenta-alpha-7b-v2-mkmlizer: ║ belonging to: ║
inv-exponenta-alpha-7b-v2-mkmlizer: ║ ║
inv-exponenta-alpha-7b-v2-mkmlizer: ║ Chai Research Corp. ║
inv-exponenta-alpha-7b-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
inv-exponenta-alpha-7b-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
inv-exponenta-alpha-7b-v2-mkmlizer: ║ ║
inv-exponenta-alpha-7b-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
inv-exponenta-alpha-7b-v2-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 15.1MB/s]
inv-exponenta-alpha-7b-v2-mkmlizer: README.md: 0%| | 0.00/1.16k [00:00<?, ?B/s] README.md: 100%|██████████| 1.16k/1.16k [00:00<00:00, 11.0MB/s]
inv-exponenta-alpha-7b-v2-mkmlizer: config.json: 0%| | 0.00/641 [00:00<?, ?B/s] config.json: 100%|██████████| 641/641 [00:00<00:00, 7.53MB/s]
inv-exponenta-alpha-7b-v2-mkmlizer: mergekit_config.yml: 0%| | 0.00/552 [00:00<?, ?B/s] mergekit_config.yml: 100%|██████████| 552/552 [00:00<00:00, 4.91MB/s]
inv-exponenta-alpha-7b-v2-mkmlizer: model-00001-of-00008.safetensors: 0%| | 0.00/1.98G [00:00<?, ?B/s] model-00001-of-00008.safetensors: 1%| | 21.0M/1.98G [00:00<00:11, 166MB/s] model-00001-of-00008.safetensors: 2%|▏ | 41.9M/1.98G [00:00<00:12, 159MB/s] model-00001-of-00008.safetensors: 6%|▌ | 115M/1.98G [00:00<00:04, 375MB/s] model-00001-of-00008.safetensors: 12%|█▏ | 231M/1.98G [00:00<00:02, 618MB/s] model-00001-of-00008.safetensors: 20%|█▉ | 388M/1.98G [00:00<00:01, 905MB/s] model-00001-of-00008.safetensors: 25%|██▌ | 503M/1.98G [00:00<00:01, 964MB/s] model-00001-of-00008.safetensors: 33%|███▎ | 661M/1.98G [00:00<00:01, 1.15GB/s] model-00001-of-00008.safetensors: 40%|███▉ | 786M/1.98G [00:00<00:01, 1.15GB/s] model-00001-of-00008.safetensors: 48%|████▊ | 954M/1.98G [00:01<00:00, 1.29GB/s] model-00001-of-00008.safetensors: 58%|█████▊ | 1.15G/1.98G [00:01<00:00, 1.49GB/s] model-00001-of-00008.safetensors: 72%|███████▏ | 1.43G/1.98G [00:01<00:00, 1.85GB/s] model-00001-of-00008.safetensors: 94%|█████████▎| 1.85G/1.98G [00:01<00:00, 2.52GB/s] model-00001-of-00008.safetensors: 100%|█████████▉| 1.98G/1.98G [00:01<00:00, 1.45GB/s]
inv-exponenta-alpha-7b-v2-mkmlizer: model-00002-of-00008.safetensors: 0%| | 0.00/1.95G [00:00<?, ?B/s] model-00002-of-00008.safetensors: 1%| | 10.5M/1.95G [00:00<00:22, 85.5MB/s] model-00002-of-00008.safetensors: 6%|▌ | 115M/1.95G [00:00<00:03, 582MB/s] model-00002-of-00008.safetensors: 11%|█ | 210M/1.95G [00:00<00:02, 713MB/s] model-00002-of-00008.safetensors: 17%|█▋ | 336M/1.95G [00:00<00:01, 912MB/s] model-00002-of-00008.safetensors: 25%|██▌ | 493M/1.95G [00:00<00:01, 1.13GB/s] model-00002-of-00008.safetensors: 33%|███▎ | 640M/1.95G [00:00<00:01, 1.24GB/s] model-00002-of-00008.safetensors: 40%|███▉ | 776M/1.95G [00:00<00:00, 1.25GB/s] model-00002-of-00008.safetensors: 47%|████▋ | 923M/1.95G [00:00<00:00, 1.30GB/s] model-00002-of-00008.safetensors: 58%|█████▊ | 1.12G/1.95G [00:00<00:00, 1.50GB/s] model-00002-of-00008.safetensors: 69%|██████▉ | 1.34G/1.95G [00:01<00:00, 1.70GB/s] model-00002-of-00008.safetensors: 94%|█████████▍| 1.83G/1.95G [00:01<00:00, 2.65GB/s] model-00002-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:01<00:00, 1.60GB/s]
inv-exponenta-alpha-7b-v2-mkmlizer: model-00003-of-00008.safetensors: 0%| | 0.00/1.95G [00:00<?, ?B/s] model-00003-of-00008.safetensors: 1%| | 10.5M/1.95G [00:00<00:29, 65.1MB/s] model-00003-of-00008.safetensors: 5%|▌ | 105M/1.95G [00:00<00:03, 469MB/s] model-00003-of-00008.safetensors: 11%|█ | 210M/1.95G [00:00<00:02, 658MB/s] model-00003-of-00008.safetensors: 18%|█▊ | 346M/1.95G [00:00<00:01, 887MB/s] model-00003-of-00008.safetensors: 23%|██▎ | 451M/1.95G [00:00<00:01, 921MB/s] model-00003-of-00008.safetensors: 29%|██▉ | 566M/1.95G [00:00<00:01, 936MB/s] model-00003-of-00008.safetensors: 39%|███▉ | 755M/1.95G [00:00<00:01, 1.17GB/s] model-00003-of-00008.safetensors: 49%|████▉ | 954M/1.95G [00:00<00:00, 1.33GB/s] model-00003-of-00008.safetensors: 66%|██████▋ | 1.29G/1.95G [00:01<00:00, 1.88GB/s] model-00003-of-00008.safetensors: 80%|████████ | 1.56G/1.95G [00:01<00:00, 2.09GB/s] model-00003-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:01<00:00, 1.54GB/s]
inv-exponenta-alpha-7b-v2-mkmlizer: model-00007-of-00008.safetensors: 0%| | 0.00/1.95G [00:00<?, ?B/s] model-00007-of-00008.safetensors: 1%| | 10.5M/1.95G [00:00<00:26, 73.3MB/s] model-00007-of-00008.safetensors: 8%|▊ | 157M/1.95G [00:00<00:02, 711MB/s] model-00007-of-00008.safetensors: 15%|█▍ | 283M/1.95G [00:00<00:01, 905MB/s] model-00007-of-00008.safetensors: 20%|█▉ | 388M/1.95G [00:00<00:02, 773MB/s] model-00007-of-00008.safetensors: 24%|██▍ | 472M/1.95G [00:00<00:02, 649MB/s] model-00007-of-00008.safetensors: 32%|███▏ | 619M/1.95G [00:00<00:01, 834MB/s] model-00007-of-00008.safetensors: 57%|█████▋ | 1.10G/1.95G [00:00<00:00, 1.84GB/s] model-00007-of-00008.safetensors: 75%|███████▌ | 1.47G/1.95G [00:01<00:00, 2.33GB/s] model-00007-of-00008.safetensors: 90%|█████████ | 1.76G/1.95G [00:01<00:00, 2.48GB/s] model-00007-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:01<00:00, 1.63GB/s]
inv-exponenta-alpha-7b-v2-mkmlizer: model-00008-of-00008.safetensors: 0%| | 0.00/872M [00:00<?, ?B/s] model-00008-of-00008.safetensors: 1%| | 10.5M/872M [00:00<00:10, 79.9MB/s] model-00008-of-00008.safetensors: 9%|▊ | 75.5M/872M [00:00<00:02, 361MB/s] model-00008-of-00008.safetensors: 19%|█▉ | 170M/872M [00:00<00:01, 601MB/s] model-00008-of-00008.safetensors: 33%|███▎ | 285M/872M [00:00<00:00, 722MB/s] model-00008-of-00008.safetensors: 69%|██████▉ | 600M/872M [00:00<00:00, 1.50GB/s] model-00008-of-00008.safetensors: 100%|█████████▉| 872M/872M [00:00<00:00, 1.39GB/s]
inv-exponenta-alpha-7b-v2-mkmlizer: model.safetensors.index.json: 0%| | 0.00/22.8k [00:00<?, ?B/s] model.safetensors.index.json: 100%|██████████| 22.8k/22.8k [00:00<00:00, 145MB/s]
inv-exponenta-alpha-7b-v2-mkmlizer: special_tokens_map.json: 0%| | 0.00/414 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 414/414 [00:00<00:00, 6.14MB/s]
inv-exponenta-alpha-7b-v2-mkmlizer: tokenizer.json: 0%| | 0.00/1.80M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 1.80M/1.80M [00:00<00:00, 50.5MB/s]
inv-exponenta-alpha-7b-v2-mkmlizer: tokenizer.model: 0%| | 0.00/493k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 63.2MB/s]
inv-exponenta-alpha-7b-v2-mkmlizer: tokenizer_config.json: 0%| | 0.00/967 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 967/967 [00:00<00:00, 8.16MB/s]
inv-exponenta-alpha-7b-v2-mkmlizer: Downloaded to shared memory in 13.110s
inv-exponenta-alpha-7b-v2-mkmlizer: quantizing model to /dev/shm/model_cache
inv-exponenta-alpha-7b-v2-mkmlizer: Saving mkml model at /dev/shm/model_cache
inv-exponenta-alpha-7b-v2-mkmlizer: Reading /tmp/tmpbnikfj71/model.safetensors.index.json
inv-exponenta-alpha-7b-v2-mkmlizer: Profiling: 0%| | 0/291 [00:00<?, ?it/s] Profiling: 0%| | 1/291 [00:00<01:19, 3.63it/s] Profiling: 5%|▌ | 15/291 [00:00<00:05, 49.06it/s] Profiling: 11%|█▏ | 33/291 [00:00<00:02, 90.11it/s] Profiling: 16%|█▌ | 46/291 [00:00<00:03, 78.66it/s] Profiling: 22%|██▏ | 64/291 [00:00<00:02, 103.31it/s] Profiling: 27%|██▋ | 80/291 [00:01<00:02, 91.04it/s] Profiling: 34%|███▎ | 98/291 [00:01<00:01, 109.56it/s] Profiling: 40%|███▉ | 116/291 [00:01<00:01, 124.22it/s] Profiling: 45%|████▌ | 131/291 [00:01<00:01, 101.99it/s] Profiling: 50%|████▉ | 145/291 [00:01<00:01, 108.81it/s] Profiling: 55%|█████▍ | 160/291 [00:03<00:04, 26.83it/s] Profiling: 62%|██████▏ | 180/291 [00:03<00:02, 38.88it/s] Profiling: 68%|██████▊ | 197/291 [00:04<00:03, 24.30it/s] Profiling: 73%|███████▎ | 211/291 [00:04<00:02, 31.08it/s] Profiling: 79%|███████▉ | 231/291 [00:04<00:01, 40.96it/s] Profiling: 86%|████████▌ | 250/291 [00:04<00:00, 54.47it/s] Profiling: 93%|█████████▎| 271/291 [00:04<00:00, 72.58it/s] Profiling: 98%|█████████▊| 286/291 [00:05<00:00, 73.12it/s] Profiling: 100%|██████████| 291/291 [00:05<00:00, 55.40it/s]
inv-exponenta-alpha-7b-v2-mkmlizer: quantized model in 15.787s
inv-exponenta-alpha-7b-v2-mkmlizer: Processed model Inv/Exponenta-Alpha-7B in 29.952s
inv-exponenta-alpha-7b-v2-mkmlizer: creating bucket guanaco-mkml-models
inv-exponenta-alpha-7b-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
inv-exponenta-alpha-7b-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/inv-exponenta-alpha-7b-v2
inv-exponenta-alpha-7b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/inv-exponenta-alpha-7b-v2/tokenizer_config.json
inv-exponenta-alpha-7b-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/inv-exponenta-alpha-7b-v2/config.json
inv-exponenta-alpha-7b-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/inv-exponenta-alpha-7b-v2/special_tokens_map.json
inv-exponenta-alpha-7b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/inv-exponenta-alpha-7b-v2/tokenizer.model
inv-exponenta-alpha-7b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/inv-exponenta-alpha-7b-v2/tokenizer.json
inv-exponenta-alpha-7b-v2-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/inv-exponenta-alpha-7b-v2/mkml_model.tensors
inv-exponenta-alpha-7b-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
inv-exponenta-alpha-7b-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:1067: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
inv-exponenta-alpha-7b-v2-mkmlizer: warnings.warn(
inv-exponenta-alpha-7b-v2-mkmlizer: config.json: 0%| | 0.00/1.05k [00:00<?, ?B/s] config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 12.6MB/s]
inv-exponenta-alpha-7b-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:690: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
inv-exponenta-alpha-7b-v2-mkmlizer: warnings.warn(
inv-exponenta-alpha-7b-v2-mkmlizer: tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 1.80MB/s]
inv-exponenta-alpha-7b-v2-mkmlizer: vocab.json: 0%| | 0.00/1.04M [00:00<?, ?B/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 26.0MB/s]
inv-exponenta-alpha-7b-v2-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 16.4MB/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 16.3MB/s]
inv-exponenta-alpha-7b-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:472: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
inv-exponenta-alpha-7b-v2-mkmlizer: warnings.warn(
inv-exponenta-alpha-7b-v2-mkmlizer: pytorch_model.bin: 0%| | 0.00/1.44G [00:00<?, ?B/s] pytorch_model.bin: 1%|▏ | 21.0M/1.44G [00:00<00:08, 176MB/s] pytorch_model.bin: 7%|▋ | 105M/1.44G [00:00<00:02, 493MB/s] pytorch_model.bin: 15%|█▌ | 220M/1.44G [00:00<00:01, 695MB/s] pytorch_model.bin: 23%|██▎ | 325M/1.44G [00:00<00:01, 780MB/s] pytorch_model.bin: 28%|██▊ | 409M/1.44G [00:00<00:01, 663MB/s] pytorch_model.bin: 33%|███▎ | 482M/1.44G [00:00<00:01, 614MB/s] pytorch_model.bin: 39%|███▉ | 566M/1.44G [00:00<00:01, 665MB/s] pytorch_model.bin: 57%|█████▋ | 828M/1.44G [00:00<00:00, 1.16GB/s] pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:01<00:00, 1.28GB/s]
inv-exponenta-alpha-7b-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
inv-exponenta-alpha-7b-v2-mkmlizer: Saving duration: 0.272s
inv-exponenta-alpha-7b-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.897s
inv-exponenta-alpha-7b-v2-mkmlizer: creating bucket guanaco-reward-models
inv-exponenta-alpha-7b-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
inv-exponenta-alpha-7b-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/inv-exponenta-alpha-7b-v2_reward
inv-exponenta-alpha-7b-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/inv-exponenta-alpha-7b-v2_reward/config.json
inv-exponenta-alpha-7b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/inv-exponenta-alpha-7b-v2_reward/tokenizer_config.json
inv-exponenta-alpha-7b-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/inv-exponenta-alpha-7b-v2_reward/special_tokens_map.json
inv-exponenta-alpha-7b-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/inv-exponenta-alpha-7b-v2_reward/merges.txt
inv-exponenta-alpha-7b-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/inv-exponenta-alpha-7b-v2_reward/vocab.json
inv-exponenta-alpha-7b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/inv-exponenta-alpha-7b-v2_reward/tokenizer.json
inv-exponenta-alpha-7b-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/inv-exponenta-alpha-7b-v2_reward/reward.tensors
Job inv-exponenta-alpha-7b-v2-mkmlizer completed after 58.88s with status: succeeded
Stopping job with name inv-exponenta-alpha-7b-v2-mkmlizer
Pipeline stage MKMLizer completed in 63.85s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service inv-exponenta-alpha-7b-v2
Waiting for inference service inv-exponenta-alpha-7b-v2 to be ready
Inference service inv-exponenta-alpha-7b-v2 ready after 40.29902672767639s
Pipeline stage ISVCDeployer completed in 47.75s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7364072799682617s
Received healthy response to inference request in 1.183783769607544s
Received healthy response to inference request in 1.2091610431671143s
Received healthy response to inference request in 1.1946418285369873s
Received healthy response to inference request in 1.1929264068603516s
5 requests
0 failed requests
5th percentile: 1.1856122970581056
10th percentile: 1.187440824508667
20th percentile: 1.19109787940979
30th percentile: 1.1932694911956787
40th percentile: 1.193955659866333
50th percentile: 1.1946418285369873
60th percentile: 1.2004495143890381
70th percentile: 1.206257200241089
80th percentile: 1.3146102905273438
90th percentile: 1.5255087852478029
95th percentile: 1.6309580326080322
99th percentile: 1.7153174304962158
mean time: 1.3033840656280518
Pipeline stage StressChecker completed in 7.37s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.05s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.05s
M-Eval Dataset for topic stay_in_character is loaded
inv-exponenta-alpha-7b_v2 status is now deployed due to DeploymentManager action
inv-exponenta-alpha-7b_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics