nitral-ai-hathor-l3-8b-v-01

submission_id: nitral-ai-hathor-l3-8b-v-01_v39

developer_uid: robert_irvine

best_of: 16

celo_rating: 1133.37

display_name: nitral-ai-hathor-l3-8b-v-01_v39

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': 0.95, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}

is_internal_developer: True

language_model: Nitral-AI/Hathor-L3-8B-v.01

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: Nitral-AI/Hathor-L3-8B-v

model_name: nitral-ai-hathor-l3-8b-v-01_v39

model_num_parameters: 8030261248.0

model_repo: Nitral-AI/Hathor-L3-8B-v.01

model_size: 8B

num_battles: 121375

num_wins: 49777

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: Jellywibble/CHAI_alignment_reward_model

status: torndown

submission_type: basic

timestamp: 2024-07-05T23:04:13+00:00

us_pacific_date: 2024-07-05

win_ratio: 0.4101091658084449

Resubmit model

Running pipeline stage MKMLizer
Starting job with name nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer
Waiting for job on nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer to finish
Stopping job with name nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer
%s, retrying in %s seconds...
Starting job with name nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer
Waiting for job on nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer to finish
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: ║     _____            __           __                                ║
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: ║       /___/                                                         ║
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: ║                                                                     ║
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: ║  Version: 0.8.14                                                    ║
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: ║  https://mk1.ai                                                     ║
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: ║                                                                     ║
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: ║  The license key for the current software has been verified as      ║
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: ║  belonging to:                                                      ║
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: ║                                                                     ║
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: ║  Chai Research Corp.                                                ║
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: ║                                                                     ║
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: Downloaded to shared memory in 21.368s
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:35,  2.41s/it]
Loading 0:   4%|▍         | 13/291 [00:04<01:17,  3.57it/s]
Loading 0:   8%|▊         | 23/291 [00:05<00:36,  7.37it/s]
Loading 0:  12%|█▏        | 35/291 [00:05<00:19, 13.37it/s]
Loading 0:  17%|█▋        | 49/291 [00:05<00:10, 22.17it/s]
Loading 0:  21%|██        | 60/291 [00:05<00:09, 23.55it/s]
Loading 0:  25%|██▌       | 74/291 [00:05<00:06, 34.26it/s]
Loading 0:  29%|██▉       | 85/291 [00:05<00:04, 42.86it/s]
Loading 0:  33%|███▎      | 96/291 [00:05<00:03, 50.36it/s]
Loading 0:  38%|███▊      | 112/291 [00:06<00:02, 65.97it/s]
Loading 0:  42%|████▏     | 123/291 [00:06<00:02, 71.14it/s]
Loading 0:  46%|████▌     | 134/291 [00:06<00:02, 74.83it/s]
Loading 0:  51%|█████     | 148/291 [00:06<00:01, 86.03it/s]
Loading 0:  55%|█████▍    | 159/291 [00:06<00:01, 88.29it/s]
Loading 0:  58%|█████▊    | 170/291 [00:06<00:02, 59.89it/s]
Loading 0:  63%|██████▎   | 184/291 [00:07<00:01, 73.47it/s]
Loading 0:  67%|██████▋   | 195/291 [00:07<00:01, 78.44it/s]
Loading 0:  73%|███████▎  | 211/291 [00:07<00:00, 94.34it/s]
Loading 0:  77%|███████▋  | 223/291 [00:07<00:00, 96.92it/s]
Loading 0:  82%|████████▏ | 238/291 [00:07<00:00, 107.53it/s]
Loading 0:  86%|████████▌ | 250/291 [00:07<00:00, 105.34it/s]
Loading 0:  91%|█████████ | 265/291 [00:07<00:00, 114.54it/s]
Loading 0:  96%|█████████▌| 278/291 [00:08<00:00, 68.77it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: quantized model in 24.778s
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: Processed model Nitral-AI/Hathor-L3-8B-v.01 in 46.147s
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v39
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v39/config.json
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v39/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v39/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v39/tokenizer.json
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v39/flywheel_model.0.safetensors
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: loading reward model from Jellywibble/CHAI_alignment_reward_model
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer:   warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer:   warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer:   warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:468: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer:   warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: Saving duration: 0.156s
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: Processed model Jellywibble/CHAI_alignment_reward_model in 2.256s
nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v39_reward/reward.tensors
Job nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer completed after 76.48s with status: succeeded
Stopping job with name nitral-ai-hathor-l3-8b-v-01-v39-mkmlizer
Pipeline stage MKMLizer completed in 77.82s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-hathor-l3-8b-v-01-v39
Waiting for inference service nitral-ai-hathor-l3-8b-v-01-v39 to be ready
Inference service nitral-ai-hathor-l3-8b-v-01-v39 ready after 40.24290895462036s
Pipeline stage ISVCDeployer completed in 47.39s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.973872184753418s
Received healthy response to inference request in 1.2799856662750244s
Received healthy response to inference request in 1.243818759918213s
Received healthy response to inference request in 1.221236228942871s
Received healthy response to inference request in 1.2844574451446533s
5 requests
0 failed requests
5th percentile: 1.2257527351379394
10th percentile: 1.2302692413330079
20th percentile: 1.2393022537231446
30th percentile: 1.2510521411895752
40th percentile: 1.2655189037322998
50th percentile: 1.2799856662750244
60th percentile: 1.281774377822876
70th percentile: 1.2835630893707275
80th percentile: 1.4223403930664062
90th percentile: 1.698106288909912
95th percentile: 1.835989236831665
99th percentile: 1.9462955951690672
mean time: 1.400674057006836
Pipeline stage StressChecker completed in 7.62s
nitral-ai-hathor-l3-8b-v-01_v39 status is now deployed due to DeploymentManager action
nitral-ai-hathor-l3-8b-v-01_v39 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of nitral-ai-hathor-l3-8b-v-01_v39
Running pipeline stage ISVCDeleter
Checking if service nitral-ai-hathor-l3-8b-v-01-v39 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.62s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key nitral-ai-hathor-l3-8b-v-01-v39/config.json from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v39/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v39/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v39/tokenizer.json from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v39/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key nitral-ai-hathor-l3-8b-v-01-v39_reward/config.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v39_reward/merges.txt from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v39_reward/reward.tensors from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v39_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v39_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v39_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v39_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.55s
nitral-ai-hathor-l3-8b-v-01_v39 status is now torndown due to DeploymentManager action