submission_id: nitral-ai-hathor-l3-8b-v-01_v2
developer_uid: Nitral-AI
status: inactive
model_repo: Nitral-AI/Hathor-L3-8B-v.01
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.03, '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}
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}
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}:', 'truncate_by_message': False}
timestamp: 2024-06-07T17:00:05+00:00
model_name: nitral-ai-hathor-l3-8b-v-01_v1
model_eval_status: success
model_group: Nitral-AI/Hathor-L3-8B-v
num_battles: 17351
num_wins: 9345
celo_rating: 1214.88
safety_score: 0.92
propriety_score: 0.6467391304347826
propriety_total_count: 1288.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: nitral-ai-hathor-l3-8b-v-01_v1
ineligible_reason: propriety_total_count < 5000
language_model: Nitral-AI/Hathor-L3-8B-v.01
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-07
win_ratio: 0.5385856722955449
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer
Waiting for job on nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer to finish
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: ║ _____ __ __ ║
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: ║ /___/ ║
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: ║ Version: 0.8.14 ║
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: ║ https://mk1.ai ║
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: ║ belonging to: ║
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:03<09:32, 1.98s/it] Loading 0: 8%|▊ | 23/291 [00:04<00:34, 7.76it/s] Loading 0: 15%|█▌ | 45/291 [00:04<00:13, 17.77it/s] Loading 0: 21%|██▏ | 62/291 [00:04<00:09, 23.70it/s] Loading 0: 29%|██▉ | 85/291 [00:04<00:05, 38.49it/s] Loading 0: 36%|███▌ | 105/291 [00:04<00:03, 53.17it/s] Loading 0: 45%|████▍ | 130/291 [00:04<00:02, 75.89it/s] Loading 0: 52%|█████▏ | 150/291 [00:04<00:01, 92.82it/s] Loading 0: 58%|█████▊ | 169/291 [00:05<00:01, 78.27it/s] Loading 0: 66%|██████▋ | 193/291 [00:05<00:00, 101.07it/s] Loading 0: 73%|███████▎ | 213/291 [00:05<00:00, 116.22it/s] Loading 0: 82%|████████▏ | 238/291 [00:05<00:00, 140.07it/s] Loading 0: 89%|████████▊ | 258/291 [00:05<00:00, 150.40it/s] Loading 0: 96%|█████████▌| 278/291 [00:06<00:00, 104.84it/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-v2-mkmlizer: quantized model in 16.529s
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: Processed model Nitral-AI/Hathor-L3-8B-v.01 in 35.411s
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v2
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v2/tokenizer.json
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v2/config.json
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v2/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v2/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:913: 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-v2-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:757: 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-v2-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v2-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-v2-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: return self.fget.__get__(instance, owner)()
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: Saving duration: 0.209s
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.936s
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v2_reward
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v2_reward/config.json
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v2_reward/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v2_reward/vocab.json
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v2_reward/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v2_reward/merges.txt
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v2_reward/tokenizer.json
nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v2_reward/reward.tensors
Job nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer completed after 63.06s with status: succeeded
Stopping job with name nitral-ai-hathor-l3-8b-v-01-v2-mkmlizer
Pipeline stage MKMLizer completed in 63.80s
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-v2
Waiting for inference service nitral-ai-hathor-l3-8b-v-01-v2 to be ready
Inference service nitral-ai-hathor-l3-8b-v-01-v2 ready after 60.38072657585144s
Pipeline stage ISVCDeployer completed in 66.18s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1249947547912598s
Received healthy response to inference request in 1.3894119262695312s
Received healthy response to inference request in 1.323066234588623s
Received healthy response to inference request in 1.3138248920440674s
Received healthy response to inference request in 1.3466136455535889s
5 requests
0 failed requests
5th percentile: 1.3156731605529786
10th percentile: 1.3175214290618897
20th percentile: 1.3212179660797119
30th percentile: 1.3277757167816162
40th percentile: 1.3371946811676025
50th percentile: 1.3466136455535889
60th percentile: 1.3637329578399657
70th percentile: 1.3808522701263428
80th percentile: 1.536528491973877
90th percentile: 1.8307616233825685
95th percentile: 1.977878189086914
99th percentile: 2.0955714416503906
mean time: 1.499582290649414
Pipeline stage StressChecker completed in 8.14s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
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
nitral-ai-hathor-l3-8b-v-01_v2 status is now deployed due to DeploymentManager action
nitral-ai-hathor-l3-8b-v-01_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics