submission_id: nitral-ai-hathor-l3-8b-v-01_v5
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': 0.08, '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}
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: 2024-06-07T17:38:07+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: 8747
num_wins: 4722
celo_rating: 1218.36
safety_score: 0.95
propriety_score: 0.6756329113924051
propriety_total_count: 632.0
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: 0.5398422316222705
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer
Waiting for job on nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer to finish
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: ║ _____ __ __ ║
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: ║ /___/ ║
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: ║ Version: 0.8.14 ║
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: ║ https://mk1.ai ║
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: ║ belonging to: ║
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-hathor-l3-8b-v-01-v5-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-v5-mkmlizer: warnings.warn(warning_message, FutureWarning)
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: Downloaded to shared memory in 57.759s
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:20, 2.35s/it] Loading 0: 5%|▍ | 14/291 [00:04<01:10, 3.93it/s] Loading 0: 9%|▉ | 27/291 [00:04<00:29, 8.98it/s] Loading 0: 14%|█▎ | 40/291 [00:05<00:16, 15.52it/s] Loading 0: 18%|█▊ | 51/291 [00:05<00:10, 22.12it/s] Loading 0: 21%|██▏ | 62/291 [00:05<00:09, 24.85it/s] Loading 0: 26%|██▌ | 76/291 [00:05<00:05, 35.95it/s] Loading 0: 30%|██▉ | 87/291 [00:05<00:04, 44.33it/s] Loading 0: 35%|███▌ | 103/291 [00:05<00:03, 60.53it/s] Loading 0: 40%|███▉ | 115/291 [00:05<00:02, 68.87it/s] Loading 0: 45%|████▍ | 130/291 [00:06<00:01, 83.48it/s] Loading 0: 49%|████▉ | 142/291 [00:06<00:01, 88.68it/s] Loading 0: 54%|█████▍ | 157/291 [00:06<00:01, 100.24it/s] Loading 0: 58%|█████▊ | 170/291 [00:06<00:01, 65.14it/s] Loading 0: 63%|██████▎ | 184/291 [00:06<00:01, 77.03it/s] Loading 0: 67%|██████▋ | 195/291 [00:06<00:01, 81.73it/s] Loading 0: 73%|███████▎ | 211/291 [00:06<00:00, 97.26it/s] Loading 0: 77%|███████▋ | 223/291 [00:07<00:00, 99.63it/s] Loading 0: 82%|████████▏ | 238/291 [00:07<00:00, 110.22it/s] Loading 0: 86%|████████▋ | 251/291 [00:07<00:00, 107.10it/s] Loading 0: 91%|█████████ | 265/291 [00:07<00:00, 114.17it/s] Loading 0: 96%|█████████▌| 278/291 [00:07<00:00, 69.54it/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-v5-mkmlizer: quantized model in 23.777s
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: Processed model Nitral-AI/Hathor-L3-8B-v.01 in 84.063s
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v5
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v5/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v5/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v5/config.json
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v5/tokenizer.json
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v5/flywheel_model.0.safetensors
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
nitral-ai-hathor-l3-8b-v-01-v5-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-v5-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v5-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-v5-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v5-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-v5-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v5-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-v5-mkmlizer: return self.fget.__get__(instance, owner)()
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: Saving duration: 0.393s
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 23.007s
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: WARNING: Retrying failed request: /?location ([Errno 110] Connection timed out)
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: WARNING: Waiting 3 sec...
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v5_reward
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v5_reward/config.json
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v5_reward/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v5_reward/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v5_reward/merges.txt
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v5_reward/vocab.json
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v5_reward/tokenizer.json
nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v5_reward/reward.tensors
Job nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer completed after 268.19s with status: succeeded
Stopping job with name nitral-ai-hathor-l3-8b-v-01-v5-mkmlizer
Pipeline stage MKMLizer completed in 268.58s
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-v5
Waiting for inference service nitral-ai-hathor-l3-8b-v-01-v5 to be ready
Inference service nitral-ai-hathor-l3-8b-v-01-v5 ready after 40.23126721382141s
Pipeline stage ISVCDeployer completed in 45.96s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.197869062423706s
Received healthy response to inference request in 1.3566560745239258s
Received healthy response to inference request in 1.3196330070495605s
Received healthy response to inference request in 1.308690071105957s
Received healthy response to inference request in 1.3426880836486816s
5 requests
0 failed requests
5th percentile: 1.3108786582946776
10th percentile: 1.3130672454833985
20th percentile: 1.31744441986084
30th percentile: 1.3242440223693848
40th percentile: 1.3334660530090332
50th percentile: 1.3426880836486816
60th percentile: 1.3482752799987794
70th percentile: 1.353862476348877
80th percentile: 1.524898672103882
90th percentile: 1.8613838672637941
95th percentile: 2.0296264648437496
99th percentile: 2.1642205429077146
mean time: 1.5051072597503663
Pipeline stage StressChecker completed in 8.38s
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_v5 status is now deployed due to DeploymentManager action
nitral-ai-hathor-l3-8b-v-01_v5 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics