submission_id: nitral-ai-hathor-l3-8b-v-01_v48
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: 2024-07-08T21:16:43+00:00
model_name: nitral-ai-hathor-l3-8b-v-01_v48
model_group: Nitral-AI/Hathor-L3-8B-v
num_battles: 31445
num_wins: 13035
celo_rating: 1139.12
alignment_score: None
alignment_samples: 0
propriety_score: 0.7529347028613352
propriety_total_count: 5452.0
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_v48
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: 2024-07-08
win_ratio: 0.4145333121322945
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer
Waiting for job on nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer to finish
nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer: ║ _____ __ __ ║
nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer: ║ /___/ ║
nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer: ║ Version: 0.8.14 ║
nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer: ║ https://mk1.ai ║
nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer: ║ belonging to: ║
nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer: Downloaded to shared memory in 26.171s
nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-01-v48-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, 3.32it/s] Loading 0: 10%|▉ | 28/291 [00:05<00:32, 7.97it/s] Loading 0: 14%|█▍ | 41/291 [00:05<00:18, 13.59it/s] Loading 0: 19%|█▉ | 55/291 [00:06<00:11, 21.36it/s] Loading 0: 23%|██▎ | 67/291 [00:06<00:09, 22.48it/s] Loading 0: 27%|██▋ | 78/291 [00:06<00:07, 29.44it/s] Loading 0: 32%|███▏ | 94/291 [00:06<00:04, 42.81it/s] Loading 0: 36%|███▋ | 106/291 [00:06<00:03, 50.90it/s] Loading 0: 42%|████▏ | 121/291 [00:06<00:02, 64.93it/s] Loading 0: 46%|████▌ | 133/291 [00:07<00:02, 73.37it/s] Loading 0: 51%|█████ | 148/291 [00:07<00:01, 87.90it/s] Loading 0: 55%|█████▌ | 161/291 [00:07<00:01, 95.17it/s] Loading 0: 60%|█████▉ | 174/291 [00:07<00:02, 57.76it/s] Loading 0: 64%|██████▎ | 185/291 [00:07<00:01, 64.49it/s] Loading 0: 68%|██████▊ | 199/291 [00:07<00:01, 77.59it/s] Loading 0: 73%|███████▎ | 212/291 [00:08<00:00, 86.52it/s] Loading 0: 77%|███████▋ | 225/291 [00:08<00:00, 95.54it/s] Loading 0: 82%|████████▏ | 238/291 [00:08<00:00, 101.11it/s] Loading 0: 86%|████████▌ | 250/291 [00:08<00:00, 103.60it/s] Loading 0: 91%|█████████ | 265/291 [00:08<00:00, 112.79it/s] Loading 0: 96%|█████████▌| 278/291 [00:08<00:00, 58.88it/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-v48-mkmlizer: quantized model in 29.226s
nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer: Processed model Nitral-AI/Hathor-L3-8B-v.01 in 55.398s
nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v48
nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v48/flywheel_model.0.safetensors
nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer: loading reward model from Jellywibble/CHAI_alignment_reward_model
nitral-ai-hathor-l3-8b-v-01-v48-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-v48-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v48-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-v48-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v48-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-v48-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v48-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-v48-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer: Saving duration: 0.185s
nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer: Processed model Jellywibble/CHAI_alignment_reward_model in 2.344s
nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v48_reward
nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v48_reward/merges.txt
nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v48_reward/vocab.json
nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v48_reward/config.json
nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v48_reward/tokenizer.json
nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v48_reward/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v48_reward/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v48_reward/reward.tensors
Job nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer completed after 83.76s with status: succeeded
Stopping job with name nitral-ai-hathor-l3-8b-v-01-v48-mkmlizer
Pipeline stage MKMLizer completed in 84.71s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-hathor-l3-8b-v-01-v48
Waiting for inference service nitral-ai-hathor-l3-8b-v-01-v48 to be ready
Inference service nitral-ai-hathor-l3-8b-v-01-v48 ready after 40.20773410797119s
Pipeline stage ISVCDeployer completed in 47.12s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.045750856399536s
Received healthy response to inference request in 1.2734706401824951s
Received healthy response to inference request in 1.271550178527832s
Received healthy response to inference request in 1.234715461730957s
Received healthy response to inference request in 1.2509076595306396s
5 requests
0 failed requests
5th percentile: 1.2379539012908936
10th percentile: 1.24119234085083
20th percentile: 1.2476692199707031
30th percentile: 1.2550361633300782
40th percentile: 1.263293170928955
50th percentile: 1.271550178527832
60th percentile: 1.2723183631896973
70th percentile: 1.2730865478515625
80th percentile: 1.4279266834259035
90th percentile: 1.73683876991272
95th percentile: 1.8912948131561278
99th percentile: 2.0148596477508542
mean time: 1.415278959274292
Pipeline stage StressChecker completed in 7.83s
nitral-ai-hathor-l3-8b-v-01_v48 status is now deployed due to DeploymentManager action
nitral-ai-hathor-l3-8b-v-01_v48 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics