submission_id: nitral-ai-hathor-l3-8b-v-01_v62
developer_uid: robert_irvine
status: inactive
model_repo: Nitral-AI/Hathor-L3-8B-v.01
reward_repo: Jellywibble/CHAI_alignment_reward_model
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': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
timestamp: 2024-07-09T17:37:53+00:00
model_name: nitral-ai-hathor-l3-8b-v-01_v62
model_group: Nitral-AI/Hathor-L3-8B-v
num_battles: 33361
num_wins: 14035
celo_rating: 1138.71
propriety_score: 0.7501780626780626
propriety_total_count: 5616.0
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_v62
ineligible_reason: None
language_model: Nitral-AI/Hathor-L3-8B-v.01
model_size: 8B
reward_model: Jellywibble/CHAI_alignment_reward_model
us_pacific_date: 2024-07-09
win_ratio: 0.42070081832079376
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer
Waiting for job on nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer to finish
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: ║ _____ __ __ ║
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: ║ /___/ ║
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: ║ Version: 0.8.14 ║
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: ║ https://mk1.ai ║
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: ║ belonging to: ║
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: Downloaded to shared memory in 24.613s
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:05<13:31, 2.81s/it] Loading 0: 5%|▍ | 14/291 [00:05<01:23, 3.31it/s] Loading 0: 10%|▉ | 28/291 [00:05<00:33, 7.96it/s] Loading 0: 14%|█▍ | 41/291 [00:05<00:18, 13.56it/s] Loading 0: 19%|█▉ | 55/291 [00:06<00:11, 21.32it/s] Loading 0: 23%|██▎ | 67/291 [00:06<00:09, 22.40it/s] Loading 0: 27%|██▋ | 78/291 [00:06<00:07, 29.27it/s] Loading 0: 32%|███▏ | 94/291 [00:06<00:04, 42.46it/s] Loading 0: 36%|███▌ | 105/291 [00:06<00:03, 50.22it/s] Loading 0: 42%|████▏ | 121/291 [00:06<00:02, 66.38it/s] Loading 0: 46%|████▌ | 133/291 [00:07<00:02, 74.43it/s] Loading 0: 51%|█████ | 148/291 [00:07<00:01, 88.71it/s] Loading 0: 55%|█████▌ | 161/291 [00:07<00:01, 95.50it/s] Loading 0: 60%|█████▉ | 174/291 [00:07<00:02, 56.41it/s] Loading 0: 63%|██████▎ | 184/291 [00:07<00:01, 63.01it/s] Loading 0: 67%|██████▋ | 195/291 [00:07<00:01, 69.28it/s] Loading 0: 73%|███████▎ | 211/291 [00:08<00:00, 85.44it/s] Loading 0: 76%|███████▋ | 222/291 [00:08<00:00, 87.74it/s] Loading 0: 82%|████████▏ | 238/291 [00:08<00:00, 102.61it/s] Loading 0: 86%|████████▌ | 250/291 [00:08<00:00, 104.13it/s] Loading 0: 91%|█████████ | 265/291 [00:08<00:00, 114.04it/s] Loading 0: 96%|█████████▌| 278/291 [00:08<00:00, 59.39it/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-v62-mkmlizer: quantized model in 29.351s
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: Processed model Nitral-AI/Hathor-L3-8B-v.01 in 53.964s
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v62
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v62/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v62/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v62/config.json
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v62/tokenizer.json
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v62/flywheel_model.0.safetensors
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: loading reward model from Jellywibble/CHAI_alignment_reward_model
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: 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-v62-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: 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-v62-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v62-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-v62-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: Saving duration: 0.189s
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: Processed model Jellywibble/CHAI_alignment_reward_model in 2.647s
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v62_reward
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v62_reward/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v62_reward/config.json
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v62_reward/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v62_reward/merges.txt
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v62_reward/vocab.json
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v62_reward/tokenizer.json
nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v62_reward/reward.tensors
Job nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer completed after 83.97s with status: succeeded
Stopping job with name nitral-ai-hathor-l3-8b-v-01-v62-mkmlizer
Pipeline stage MKMLizer completed in 84.88s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-hathor-l3-8b-v-01-v62
Waiting for inference service nitral-ai-hathor-l3-8b-v-01-v62 to be ready
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Inference service nitral-ai-hathor-l3-8b-v-01-v62 ready after 40.31588411331177s
Pipeline stage ISVCDeployer completed in 46.98s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.985870122909546s
Received healthy response to inference request in 1.3014721870422363s
Received healthy response to inference request in 1.2540202140808105s
Received healthy response to inference request in 1.2274162769317627s
Received healthy response to inference request in 1.298783302307129s
5 requests
0 failed requests
5th percentile: 1.2327370643615723
10th percentile: 1.2380578517913818
20th percentile: 1.248699426651001
30th percentile: 1.2629728317260742
40th percentile: 1.2808780670166016
50th percentile: 1.298783302307129
60th percentile: 1.299858856201172
70th percentile: 1.300934410095215
80th percentile: 1.4383517742156984
90th percentile: 1.7121109485626222
95th percentile: 1.8489905357360839
99th percentile: 1.9584942054748535
mean time: 1.4135124206542968
Pipeline stage StressChecker completed in 7.94s
nitral-ai-hathor-l3-8b-v-01_v62 status is now deployed due to DeploymentManager action
nitral-ai-hathor-l3-8b-v-01_v62 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics