submission_id: nitral-ai-hathor-l3-8b-v-02_v6
developer_uid: Nitral-AI
status: inactive
model_repo: Nitral-AI/Hathor-L3-8B-v.02
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', '<|end_header_id|>', '<|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: 2024-06-11T22:09:20+00:00
model_name: nitral-ai-hathor-l3-8b-v-02_ok
model_eval_status: success
model_group: Nitral-AI/Hathor-L3-8B-v
num_battles: 30755
num_wins: 16826
celo_rating: 1219.19
propriety_score: 0.6866389500285318
propriety_total_count: 12267.0
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-02_ok
ineligible_reason: None
language_model: Nitral-AI/Hathor-L3-8B-v.02
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-11
win_ratio: 0.5470980328401885
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer
Waiting for job on nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer to finish
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: ║ _____ __ __ ║
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: ║ /___/ ║
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: ║ Version: 0.8.14 ║
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: ║ https://mk1.ai ║
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: ║ belonging to: ║
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-hathor-l3-8b-v-02-v6-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-02-v6-mkmlizer: warnings.warn(warning_message, FutureWarning)
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: Downloaded to shared memory in 17.296s
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<09:59, 2.07s/it] Loading 0: 8%|▊ | 23/291 [00:04<00:36, 7.43it/s] Loading 0: 15%|█▌ | 45/291 [00:04<00:14, 17.02it/s] Loading 0: 21%|██ | 61/291 [00:04<00:10, 22.39it/s] Loading 0: 29%|██▉ | 85/291 [00:04<00:05, 37.56it/s] Loading 0: 36%|███▌ | 105/291 [00:04<00:03, 51.99it/s] Loading 0: 45%|████▍ | 130/291 [00:05<00:02, 74.14it/s] Loading 0: 52%|█████▏ | 150/291 [00:05<00:01, 90.79it/s] Loading 0: 58%|█████▊ | 169/291 [00:05<00:01, 77.43it/s] Loading 0: 66%|██████▋ | 193/291 [00:05<00:00, 100.39it/s] Loading 0: 73%|███████▎ | 213/291 [00:05<00:00, 115.62it/s] Loading 0: 82%|████████▏ | 238/291 [00:05<00:00, 139.96it/s] Loading 0: 89%|████████▊ | 258/291 [00:05<00:00, 150.05it/s] Loading 0: 96%|█████████▌| 278/291 [00:06<00:00, 104.41it/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-02-v6-mkmlizer: quantized model in 17.034s
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: Processed model Nitral-AI/Hathor-L3-8B-v.02 in 35.257s
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-02-v6
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-02-v6/config.json
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-02-v6/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-02-v6/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-02-v6/tokenizer.json
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
nitral-ai-hathor-l3-8b-v-02-v6-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-02-v6-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-02-v6-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-02-v6-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-02-v6-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-02-v6-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-02-v6-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-02-v6-mkmlizer: return self.fget.__get__(instance, owner)()
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: Saving duration: 0.225s
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.453s
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-02-v6_reward
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-02-v6_reward/config.json
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-02-v6_reward/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-02-v6_reward/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-02-v6_reward/merges.txt
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-02-v6_reward/vocab.json
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-02-v6_reward/tokenizer.json
nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-02-v6_reward/reward.tensors
Job nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer completed after 64.79s with status: succeeded
Stopping job with name nitral-ai-hathor-l3-8b-v-02-v6-mkmlizer
Pipeline stage MKMLizer completed in 65.48s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-hathor-l3-8b-v-02-v6
Waiting for inference service nitral-ai-hathor-l3-8b-v-02-v6 to be ready
Inference service nitral-ai-hathor-l3-8b-v-02-v6 ready after 40.24739074707031s
Pipeline stage ISVCDeployer completed in 46.26s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1523656845092773s
Received healthy response to inference request in 1.3262078762054443s
Received healthy response to inference request in 1.3055567741394043s
Received healthy response to inference request in 1.3128678798675537s
Received healthy response to inference request in 1.3383541107177734s
5 requests
0 failed requests
5th percentile: 1.3070189952850342
10th percentile: 1.308481216430664
20th percentile: 1.3114056587219238
30th percentile: 1.315535879135132
40th percentile: 1.3208718776702881
50th percentile: 1.3262078762054443
60th percentile: 1.331066370010376
70th percentile: 1.3359248638153076
80th percentile: 1.5011564254760743
90th percentile: 1.8267610549926758
95th percentile: 1.9895633697509765
99th percentile: 2.119805221557617
mean time: 1.4870704650878905
Pipeline stage StressChecker completed in 8.05s
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-02_v6 status is now deployed due to DeploymentManager action
nitral-ai-hathor-l3-8b-v-02_v6 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics