submission_id: nitral-ai-hathor-l3-8b-v-01_v16
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': 4, '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: 2024-07-05T18:27:57+00:00
model_name: nitral-ai-hathor-l3-8b-v-01_v16
model_group: Nitral-AI/Hathor-L3-8B-v
num_battles: 31110
num_wins: 13646
celo_rating: 1139.32
propriety_score: 0.7461168639053254
propriety_total_count: 5408.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: nitral-ai-hathor-l3-8b-v-01_v16
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: 0.4386370941819351
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer
Waiting for job on nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer to finish
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: ║ _____ __ __ ║
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: ║ /___/ ║
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: ║ Version: 0.8.14 ║
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: ║ https://mk1.ai ║
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: ║ belonging to: ║
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: Downloaded to shared memory in 28.677s
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:25, 2.37s/it] Loading 0: 5%|▍ | 14/291 [00:04<01:10, 3.91it/s] Loading 0: 9%|▉ | 27/291 [00:04<00:29, 8.94it/s] Loading 0: 14%|█▍ | 41/291 [00:05<00:15, 15.88it/s] Loading 0: 19%|█▉ | 56/291 [00:05<00:09, 25.40it/s] Loading 0: 24%|██▎ | 69/291 [00:05<00:08, 25.74it/s] Loading 0: 29%|██▉ | 85/291 [00:05<00:05, 37.45it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:04, 45.10it/s] Loading 0: 37%|███▋ | 107/291 [00:06<00:03, 48.41it/s] Loading 0: 40%|████ | 117/291 [00:06<00:03, 56.08it/s] Loading 0: 45%|████▍ | 130/291 [00:06<00:02, 67.50it/s] Loading 0: 48%|████▊ | 141/291 [00:06<00:02, 66.44it/s] Loading 0: 53%|█████▎ | 153/291 [00:06<00:01, 76.38it/s] Loading 0: 57%|█████▋ | 166/291 [00:06<00:02, 55.45it/s] Loading 0: 60%|██████ | 176/291 [00:07<00:01, 61.61it/s] Loading 0: 64%|██████▍ | 186/291 [00:07<00:01, 66.55it/s] Loading 0: 69%|██████▉ | 202/291 [00:07<00:01, 82.01it/s] Loading 0: 73%|███████▎ | 212/291 [00:07<00:00, 85.56it/s] Loading 0: 77%|███████▋ | 225/291 [00:07<00:00, 96.12it/s] Loading 0: 82%|████████▏ | 239/291 [00:07<00:00, 103.11it/s] Loading 0: 87%|████████▋ | 253/291 [00:07<00:00, 111.61it/s] Loading 0: 91%|█████████▏| 266/291 [00:08<00:00, 64.06it/s] Loading 0: 96%|█████████▌| 280/291 [00:08<00:00, 76.69it/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-v16-mkmlizer: quantized model in 25.068s
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: Processed model Nitral-AI/Hathor-L3-8B-v.01 in 53.745s
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v16
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v16/config.json
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v16/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v16/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v16/tokenizer.json
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v16/flywheel_model.0.safetensors
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: loading reward model from Jellywibble/CHAI_alignment_reward_model
nitral-ai-hathor-l3-8b-v-01-v16-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-v16-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v16-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-v16-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v16-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-v16-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v16-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-v16-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: Saving duration: 0.159s
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: Processed model Jellywibble/CHAI_alignment_reward_model in 2.436s
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v16_reward
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v16_reward/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v16_reward/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v16_reward/config.json
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v16_reward/merges.txt
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v16_reward/vocab.json
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v16_reward/tokenizer.json
nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v16_reward/reward.tensors
Job nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer completed after 74.42s with status: succeeded
Stopping job with name nitral-ai-hathor-l3-8b-v-01-v16-mkmlizer
Pipeline stage MKMLizer completed in 75.31s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-hathor-l3-8b-v-01-v16
Waiting for inference service nitral-ai-hathor-l3-8b-v-01-v16 to be ready
Retrying (%r) after connection broken by '%r': %s
Inference service nitral-ai-hathor-l3-8b-v-01-v16 ready after 120.73360013961792s
Pipeline stage ISVCDeployer completed in 127.71s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7180616855621338s
Received healthy response to inference request in 1.1549973487854004s
Received healthy response to inference request in 1.139634609222412s
Received healthy response to inference request in 1.128943681716919s
Received healthy response to inference request in 1.1651968955993652s
5 requests
0 failed requests
5th percentile: 1.1310818672180176
10th percentile: 1.1332200527191163
20th percentile: 1.1374964237213134
30th percentile: 1.1427071571350098
40th percentile: 1.148852252960205
50th percentile: 1.1549973487854004
60th percentile: 1.1590771675109863
70th percentile: 1.1631569862365723
80th percentile: 1.275769853591919
90th percentile: 1.4969157695770263
95th percentile: 1.60748872756958
99th percentile: 1.695947093963623
mean time: 1.261366844177246
Pipeline stage StressChecker completed in 7.08s
nitral-ai-hathor-l3-8b-v-01_v16 status is now deployed due to DeploymentManager action
nitral-ai-hathor-l3-8b-v-01_v16 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics