submission_id: nitral-ai-hathor-l3-8b-v-02_v9
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: 2024-06-12T00:23:24+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: 30538
num_wins: 17110
celo_rating: 1211.19
propriety_score: 0.6785084202085004
propriety_total_count: 12470.0
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: 0.5602855458772676
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer
Waiting for job on nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer to finish
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: ║ _____ __ __ ║
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: ║ /___/ ║
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: ║ Version: 0.8.14 ║
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: ║ https://mk1.ai ║
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: ║ belonging to: ║
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-hathor-l3-8b-v-02-v9-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-v9-mkmlizer: warnings.warn(warning_message, FutureWarning)
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: Downloaded to shared memory in 13.890s
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<09:49, 2.04s/it] Loading 0: 8%|▊ | 23/291 [00:04<00:35, 7.55it/s] Loading 0: 15%|█▌ | 45/291 [00:04<00:14, 17.29it/s] Loading 0: 21%|██ | 61/291 [00:04<00:10, 22.65it/s] Loading 0: 29%|██▉ | 85/291 [00:04<00:05, 37.98it/s] Loading 0: 36%|███▌ | 105/291 [00:04<00:03, 52.51it/s] Loading 0: 45%|████▍ | 130/291 [00:04<00:02, 74.96it/s] Loading 0: 52%|█████▏ | 150/291 [00:05<00:01, 91.79it/s] Loading 0: 58%|█████▊ | 170/291 [00:05<00:01, 78.66it/s] Loading 0: 66%|██████▋ | 193/291 [00:05<00:00, 100.33it/s] Loading 0: 73%|███████▎ | 213/291 [00:05<00:00, 116.09it/s] Loading 0: 82%|████████▏ | 238/291 [00:05<00:00, 140.82it/s] Loading 0: 89%|████████▊ | 258/291 [00:05<00:00, 151.12it/s] Loading 0: 96%|█████████▌| 278/291 [00:06<00:00, 105.35it/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-v9-mkmlizer: quantized model in 17.125s
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: Processed model Nitral-AI/Hathor-L3-8B-v.02 in 31.928s
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-02-v9
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-02-v9/config.json
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-02-v9/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-02-v9/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-02-v9/tokenizer.json
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-02-v9/flywheel_model.0.safetensors
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
nitral-ai-hathor-l3-8b-v-02-v9-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-v9-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-02-v9-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-v9-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-02-v9-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-v9-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-02-v9-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-v9-mkmlizer: return self.fget.__get__(instance, owner)()
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: Saving duration: 0.220s
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.264s
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-02-v9_reward
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-02-v9_reward/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-02-v9_reward/vocab.json
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-02-v9_reward/config.json
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-02-v9_reward/merges.txt
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-02-v9_reward/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-02-v9_reward/tokenizer.json
nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-02-v9_reward/reward.tensors
Job nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer completed after 52.84s with status: succeeded
Stopping job with name nitral-ai-hathor-l3-8b-v-02-v9-mkmlizer
Pipeline stage MKMLizer completed in 53.26s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-hathor-l3-8b-v-02-v9
Waiting for inference service nitral-ai-hathor-l3-8b-v-02-v9 to be ready
Inference service nitral-ai-hathor-l3-8b-v-02-v9 ready after 30.229705810546875s
Pipeline stage ISVCDeployer completed in 35.86s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1385488510131836s
Received healthy response to inference request in 1.332777976989746s
Received healthy response to inference request in 1.2884643077850342s
Received healthy response to inference request in 1.2916076183319092s
Received healthy response to inference request in 1.3533084392547607s
5 requests
0 failed requests
5th percentile: 1.2890929698944091
10th percentile: 1.289721632003784
20th percentile: 1.2909789562225342
30th percentile: 1.2998416900634766
40th percentile: 1.3163098335266112
50th percentile: 1.332777976989746
60th percentile: 1.340990161895752
70th percentile: 1.3492023468017578
80th percentile: 1.5103565216064454
90th percentile: 1.8244526863098145
95th percentile: 1.981500768661499
99th percentile: 2.1071392345428466
mean time: 1.4809414386749267
Pipeline stage StressChecker completed in 8.06s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.08s
nitral-ai-hathor-l3-8b-v-02_v9 status is now deployed due to DeploymentManager action
nitral-ai-hathor-l3-8b-v-02_v9 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics