nitral-ai-sekhmet-aleph-_7217

submission_id: nitral-ai-sekhmet-aleph-_7217_v1

developer_uid: Nitral-AI

best_of: 16

celo_rating: 1193.77

display_name: Sekhmet_Aleph-L3_1-8B

family_friendly_score: 0.0

formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}

generation_params: {'temperature': 1.25, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 60, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64, 'reward_max_token_input': 256}

is_internal_developer: False

language_model: Nitral-AI/Sekhmet_Aleph-L3.1-8B-v0.1

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: Nitral-AI/Sekhmet_Aleph-

model_name: Sekhmet_Aleph-L3_1-8B

model_num_parameters: 8030261248.0

model_repo: Nitral-AI/Sekhmet_Aleph-L3.1-8B-v0.1

model_size: 8B

num_battles: 13035

num_wins: 6427

ranking_group: single

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'}

reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634

status: torndown

submission_type: basic

timestamp: 2024-07-25T09:34:12+00:00

us_pacific_date: 2024-07-25

win_ratio: 0.4930571538166475

Download Preference Data

Resubmit model

Running pipeline stage MKMLizer
Starting job with name nitral-ai-sekhmet-aleph-7217-v1-mkmlizer
Waiting for job on nitral-ai-sekhmet-aleph-7217-v1-mkmlizer to finish
Connection pool is full, discarding connection: %s. Connection pool size: %s
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: ║     _____            __           __                                ║
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: ║       /___/                                                         ║
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: ║                                                                     ║
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: ║  Version: 0.9.7                                                     ║
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: ║  https://mk1.ai                                                     ║
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: ║                                                                     ║
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: ║  belonging to:                                                      ║
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: ║                                                                     ║
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: ║  Chai Research Corp.                                                ║
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: ║                                                                     ║
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: Downloaded to shared memory in 34.585s
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp2lpuaffk, device:0
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: quantized model in 26.213s
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: Processed model Nitral-AI/Sekhmet_Aleph-L3.1-8B-v0.1 in 60.798s
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-sekhmet-aleph-7217-v1
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-sekhmet-aleph-7217-v1/config.json
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-sekhmet-aleph-7217-v1/special_tokens_map.json
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-sekhmet-aleph-7217-v1/tokenizer_config.json
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-sekhmet-aleph-7217-v1/tokenizer.json
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-sekhmet-aleph-7217-v1/flywheel_model.0.safetensors
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:47,  2.45s/it]
Loading 0:   2%|▏         | 6/291 [00:05<03:07,  1.52it/s]
Loading 0:   5%|▍         | 14/291 [00:05<01:01,  4.52it/s]
Loading 0:   7%|▋         | 20/291 [00:05<00:37,  7.32it/s]
Loading 0:   9%|▉         | 27/291 [00:05<00:22, 11.59it/s]
Loading 0:  11%|█▏        | 33/291 [00:05<00:16, 15.30it/s]
Loading 0:  14%|█▍        | 42/291 [00:05<00:11, 21.94it/s]
Loading 0:  18%|█▊        | 51/291 [00:05<00:08, 28.27it/s]
Loading 0:  21%|██        | 60/291 [00:06<00:08, 28.04it/s]
Loading 0:  23%|██▎       | 68/291 [00:06<00:06, 34.64it/s]
Loading 0:  25%|██▌       | 74/291 [00:06<00:05, 36.35it/s]
Loading 0:  27%|██▋       | 80/291 [00:06<00:05, 39.17it/s]
Loading 0:  30%|██▉       | 87/291 [00:06<00:05, 39.99it/s]
Loading 0:  33%|███▎      | 96/291 [00:06<00:04, 44.42it/s]
Loading 0:  36%|███▌      | 104/291 [00:06<00:03, 51.46it/s]
Loading 0:  38%|███▊      | 110/291 [00:07<00:03, 50.10it/s]
Loading 0:  40%|███▉      | 116/291 [00:07<00:03, 50.07it/s]
Loading 0:  42%|████▏     | 122/291 [00:07<00:03, 52.08it/s]
Loading 0:  44%|████▍     | 128/291 [00:07<00:03, 49.08it/s]
Loading 0:  46%|████▌     | 134/291 [00:07<00:03, 49.45it/s]
Loading 0:  48%|████▊     | 140/291 [00:07<00:03, 50.16it/s]
Loading 0:  50%|█████     | 146/291 [00:07<00:03, 48.32it/s]
Loading 0:  52%|█████▏    | 151/291 [00:07<00:02, 47.69it/s]
Loading 0:  54%|█████▍    | 158/291 [00:08<00:02, 52.45it/s]
Loading 0:  56%|█████▋    | 164/291 [00:08<00:02, 49.45it/s]
Loading 0:  58%|█████▊    | 170/291 [00:08<00:03, 33.71it/s]
Loading 0:  60%|██████    | 176/291 [00:08<00:02, 38.51it/s]
Loading 0:  63%|██████▎   | 182/291 [00:08<00:02, 39.16it/s]
Loading 0:  65%|██████▍   | 188/291 [00:08<00:02, 43.31it/s]
Loading 0:  67%|██████▋   | 195/291 [00:09<00:02, 42.92it/s]
Loading 0:  70%|███████   | 204/291 [00:09<00:01, 46.95it/s]
Loading 0:  73%|███████▎  | 212/291 [00:09<00:01, 54.16it/s]
Loading 0:  75%|███████▍  | 218/291 [00:09<00:01, 52.53it/s]
Loading 0:  77%|███████▋  | 224/291 [00:09<00:01, 52.10it/s]
Loading 0:  79%|███████▉  | 230/291 [00:09<00:01, 53.96it/s]
Loading 0:  81%|████████  | 236/291 [00:09<00:01, 52.06it/s]
Loading 0:  83%|████████▎ | 242/291 [00:09<00:00, 53.26it/s]
Loading 0:  86%|████████▌ | 249/291 [00:10<00:00, 49.10it/s]
Loading 0:  89%|████████▊ | 258/291 [00:10<00:00, 50.95it/s]
Loading 0:  91%|█████████▏| 266/291 [00:10<00:00, 40.46it/s]
Loading 0:  93%|█████████▎| 272/291 [00:10<00:00, 41.02it/s]
Loading 0:  95%|█████████▌| 277/291 [00:10<00:00, 42.46it/s]
Loading 0:  98%|█████████▊| 284/291 [00:10<00:00, 47.94it/s]
Loading 0: 100%|█████████▉| 290/291 [00:10<00:00, 46.36it/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.
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer:   warnings.warn(
nitral-ai-sekhmet-aleph-7217-v1-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.
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer:   warnings.warn(
nitral-ai-sekhmet-aleph-7217-v1-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.
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer:   warnings.warn(
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:05<00:05,  5.45s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  3.91s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  4.14s/it]
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  2.37it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.87it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.53it/s]
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: Saving duration: 1.322s
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.133s
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-sekhmet-aleph-7217-v1_reward/special_tokens_map.json
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-sekhmet-aleph-7217-v1_reward/config.json
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-sekhmet-aleph-7217-v1_reward/tokenizer_config.json
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-sekhmet-aleph-7217-v1_reward/merges.txt
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-sekhmet-aleph-7217-v1_reward/vocab.json
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-sekhmet-aleph-7217-v1_reward/tokenizer.json
nitral-ai-sekhmet-aleph-7217-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-sekhmet-aleph-7217-v1_reward/reward.tensors
Job nitral-ai-sekhmet-aleph-7217-v1-mkmlizer completed after 188.01s with status: succeeded
Stopping job with name nitral-ai-sekhmet-aleph-7217-v1-mkmlizer
Pipeline stage MKMLizer completed in 189.12s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-sekhmet-aleph-7217-v1
Waiting for inference service nitral-ai-sekhmet-aleph-7217-v1 to be ready
Inference service nitral-ai-sekhmet-aleph-7217-v1 ready after 60.414764642715454s
Pipeline stage ISVCDeployer completed in 62.07s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2711567878723145s
Received healthy response to inference request in 1.45048189163208s
Received healthy response to inference request in 1.4529407024383545s
Received healthy response to inference request in 1.429896354675293s
Received healthy response to inference request in 1.4671275615692139s
5 requests
0 failed requests
5th percentile: 1.4340134620666505
10th percentile: 1.4381305694580078
20th percentile: 1.4463647842407226
30th percentile: 1.4509736537933349
40th percentile: 1.4519571781158447
50th percentile: 1.4529407024383545
60th percentile: 1.4586154460906982
70th percentile: 1.464290189743042
80th percentile: 1.6279334068298341
90th percentile: 1.9495450973510744
95th percentile: 2.110350942611694
99th percentile: 2.2389956188201903
mean time: 1.614320659637451
Pipeline stage StressChecker completed in 8.78s
nitral-ai-sekhmet-aleph-_7217_v1 status is now deployed due to DeploymentManager action
nitral-ai-sekhmet-aleph-_7217_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of nitral-ai-sekhmet-aleph-_7217_v1
Running pipeline stage ISVCDeleter
Checking if service nitral-ai-sekhmet-aleph-7217-v1 is running
Tearing down inference service nitral-ai-sekhmet-aleph-7217-v1
Service nitral-ai-sekhmet-aleph-7217-v1 has been torndown
Pipeline stage ISVCDeleter completed in 4.21s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key nitral-ai-sekhmet-aleph-7217-v1/config.json from bucket guanaco-mkml-models
Deleting key nitral-ai-sekhmet-aleph-7217-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key nitral-ai-sekhmet-aleph-7217-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key nitral-ai-sekhmet-aleph-7217-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key nitral-ai-sekhmet-aleph-7217-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key nitral-ai-sekhmet-aleph-7217-v1_reward/config.json from bucket guanaco-reward-models
Deleting key nitral-ai-sekhmet-aleph-7217-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key nitral-ai-sekhmet-aleph-7217-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key nitral-ai-sekhmet-aleph-7217-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key nitral-ai-sekhmet-aleph-7217-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key nitral-ai-sekhmet-aleph-7217-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key nitral-ai-sekhmet-aleph-7217-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.56s
nitral-ai-sekhmet-aleph-_7217_v1 status is now torndown due to DeploymentManager action