submission_id: nitral-ai-hathor-l3-8b-v-01_v32
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': "{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: 2024-07-05T22:30:30+00:00
model_name: nitral-ai-hathor-l3-8b-v-01_v32
model_group: Nitral-AI/Hathor-L3-8B-v
num_battles: 121468
num_wins: 63405
celo_rating: 1206.44
propriety_score: 0.7227132974634897
propriety_total_count: 20816.0
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_v32
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: 2024-07-05
win_ratio: 0.5219893305232653
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer
Waiting for job on nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer to finish
nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer: ║ _____ __ __ ║
nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer: ║ /___/ ║
nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer: ║ Version: 0.8.14 ║
nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer: ║ https://mk1.ai ║
nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer: ║ belonging to: ║
nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:28, 2.38s/it] Loading 0: 4%|▍ | 13/291 [00:04<01:17, 3.61it/s] Loading 0: 8%|▊ | 24/291 [00:04<00:34, 7.79it/s] Loading 0: 14%|█▎ | 40/291 [00:05<00:15, 15.83it/s] Loading 0: 18%|█▊ | 51/291 [00:05<00:10, 22.19it/s] Loading 0: 21%|██ | 61/291 [00:05<00:09, 23.56it/s] Loading 0: 26%|██▌ | 76/291 [00:05<00:06, 34.83it/s] Loading 0: 30%|██▉ | 86/291 [00:05<00:04, 42.33it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:03, 50.30it/s] Loading 0: 38%|███▊ | 112/291 [00:06<00:02, 66.62it/s] Loading 0: 42%|████▏ | 123/291 [00:06<00:02, 71.33it/s] Loading 0: 48%|████▊ | 139/291 [00:06<00:01, 85.89it/s] Loading 0: 52%|█████▏ | 151/291 [00:06<00:01, 88.11it/s] Loading 0: 56%|█████▋ | 164/291 [00:06<00:01, 97.52it/s] Loading 0: 60%|██████ | 176/291 [00:06<00:01, 59.74it/s] Loading 0: 64%|██████▍ | 186/291 [00:07<00:01, 66.12it/s] Loading 0: 69%|██████▊ | 200/291 [00:07<00:01, 80.26it/s] Loading 0: 73%|███████▎ | 211/291 [00:07<00:00, 84.83it/s] Loading 0: 76%|███████▋ | 222/291 [00:07<00:00, 84.85it/s] Loading 0: 81%|████████ | 235/291 [00:07<00:00, 94.99it/s] Loading 0: 85%|████████▍ | 247/291 [00:07<00:00, 99.38it/s] Loading 0: 89%|████████▊ | 258/291 [00:07<00:00, 95.41it/s] Loading 0: 92%|█████████▏| 269/291 [00:08<00:00, 59.46it/s] Loading 0: 97%|█████████▋| 283/291 [00:08<00:00, 72.86it/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-v32-mkmlizer: quantized model in 25.065s
nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer: Processed model Nitral-AI/Hathor-L3-8B-v.01 in 45.144s
nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v32
nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v32/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v32/config.json
nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v32/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v32/tokenizer.json
nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v32/flywheel_model.0.safetensors
nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer: loading reward model from Jellywibble/CHAI_alignment_reward_model
nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:950: 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-v32-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v32_reward
nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v32_reward/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v32_reward/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v32_reward/config.json
nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v32_reward/vocab.json
nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v32_reward/merges.txt
nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v32_reward/tokenizer.json
nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v32_reward/reward.tensors
Job nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer completed after 70.33s with status: succeeded
Stopping job with name nitral-ai-hathor-l3-8b-v-01-v32-mkmlizer
Pipeline stage MKMLizer completed in 72.44s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.51s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-hathor-l3-8b-v-01-v32
Waiting for inference service nitral-ai-hathor-l3-8b-v-01-v32 to be ready
Inference service nitral-ai-hathor-l3-8b-v-01-v32 ready after 60.88478994369507s
Pipeline stage ISVCDeployer completed in 67.55s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.000169515609741s
Received healthy response to inference request in 1.4688656330108643s
Received healthy response to inference request in 1.4836020469665527s
Received healthy response to inference request in 1.4401235580444336s
Received healthy response to inference request in 1.533660650253296s
5 requests
0 failed requests
5th percentile: 1.4458719730377196
10th percentile: 1.451620388031006
20th percentile: 1.4631172180175782
30th percentile: 1.471812915802002
40th percentile: 1.4777074813842774
50th percentile: 1.4836020469665527
60th percentile: 1.50362548828125
70th percentile: 1.5236489295959472
80th percentile: 1.626962423324585
90th percentile: 1.813565969467163
95th percentile: 1.9068677425384521
99th percentile: 1.9815091609954834
mean time: 1.5852842807769776
Pipeline stage StressChecker completed in 10.79s
nitral-ai-hathor-l3-8b-v-01_v32 status is now deployed due to DeploymentManager action
nitral-ai-hathor-l3-8b-v-01_v32 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics