submission_id: nitral-ai-hathor-l3-8b-v-01_v3
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': 1.25, '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: 2024-06-07T17:10:48+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: 13519
num_wins: 7172
celo_rating: 1211.51
safety_score: 0.93
propriety_score: 0.6535750251762337
propriety_total_count: 993.0
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: 0.5305126118795769
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer
Waiting for job on nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer to finish
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: ║ _____ __ __ ║
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: ║ /___/ ║
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: ║ Version: 0.8.14 ║
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: ║ https://mk1.ai ║
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: ║ belonging to: ║
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-hathor-l3-8b-v-01-v3-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-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: Downloaded to shared memory in 21.921s
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<09:59, 2.08s/it] Loading 0: 5%|▌ | 15/291 [00:04<00:57, 4.78it/s] Loading 0: 11%|█ | 32/291 [00:04<00:21, 12.25it/s] Loading 0: 17%|█▋ | 50/291 [00:04<00:10, 22.23it/s] Loading 0: 22%|██▏ | 64/291 [00:04<00:08, 25.93it/s] Loading 0: 27%|██▋ | 79/291 [00:04<00:05, 36.46it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:03, 50.46it/s] Loading 0: 39%|███▉ | 114/291 [00:05<00:02, 66.89it/s] Loading 0: 45%|████▌ | 132/291 [00:05<00:01, 83.62it/s] Loading 0: 52%|█████▏ | 150/291 [00:05<00:01, 99.82it/s] Loading 0: 57%|█████▋ | 166/291 [00:05<00:01, 73.46it/s] Loading 0: 62%|██████▏ | 179/291 [00:05<00:01, 78.85it/s] Loading 0: 67%|██████▋ | 194/291 [00:05<00:01, 90.55it/s] Loading 0: 73%|███████▎ | 211/291 [00:06<00:00, 106.19it/s] Loading 0: 78%|███████▊ | 228/291 [00:06<00:00, 120.44it/s] Loading 0: 84%|████████▎ | 243/291 [00:06<00:00, 125.30it/s] Loading 0: 89%|████████▊ | 258/291 [00:06<00:00, 128.75it/s] Loading 0: 94%|█████████▍| 273/291 [00:06<00:00, 81.49it/s] Loading 0: 98%|█████████▊| 285/291 [00:06<00:00, 88.26it/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-v3-mkmlizer: quantized model in 18.827s
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: Processed model Nitral-AI/Hathor-L3-8B-v.01 in 41.740s
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v3
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v3/config.json
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v3/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v3/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v3/tokenizer.json
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
nitral-ai-hathor-l3-8b-v-01-v3-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-v3-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v3-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-v3-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v3-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-v3-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v3-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-v3-mkmlizer: return self.fget.__get__(instance, owner)()
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: Saving duration: 0.294s
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.985s
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v3_reward
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v3_reward/config.json
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v3_reward/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v3_reward/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v3_reward/merges.txt
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v3_reward/vocab.json
nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v3_reward/tokenizer.json
Job nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer completed after 77.58s with status: succeeded
Stopping job with name nitral-ai-hathor-l3-8b-v-01-v3-mkmlizer
Pipeline stage MKMLizer completed in 78.04s
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-v3
Waiting for inference service nitral-ai-hathor-l3-8b-v-01-v3 to be ready
Inference service nitral-ai-hathor-l3-8b-v-01-v3 ready after 413.57016682624817s
Pipeline stage ISVCDeployer completed in 420.81s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0812671184539795s
Received healthy response to inference request in 1.3825678825378418s
Received healthy response to inference request in 1.3548107147216797s
Received healthy response to inference request in 1.3333911895751953s
Received healthy response to inference request in 6.892122268676758s
5 requests
0 failed requests
5th percentile: 1.3376750946044922
10th percentile: 1.341958999633789
20th percentile: 1.3505268096923828
30th percentile: 1.3603621482849122
40th percentile: 1.371465015411377
50th percentile: 1.3825678825378418
60th percentile: 1.6620475769042968
70th percentile: 1.9415272712707519
80th percentile: 3.0434381484985362
90th percentile: 4.967780208587647
95th percentile: 5.929951238632201
99th percentile: 6.699688062667846
mean time: 2.608831834793091
Pipeline stage StressChecker completed in 13.65s
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 0.04s
M-Eval Dataset for topic stay_in_character is loaded
nitral-ai-hathor-l3-8b-v-01_v3 status is now deployed due to DeploymentManager action
nitral-ai-hathor-l3-8b-v-01_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics