developer_uid: robert_irvine
submission_id: nitral-ai-hathor-l3-8b-v-01_v56
model_name: nitral-ai-hathor-l3-8b-v-01_v56
model_group: Nitral-AI/Hathor-L3-8B-v
status: torndown
timestamp: 2024-07-09T17:22:18+00:00
num_battles: 30467
num_wins: 15556
celo_rating: 1199.24
family_friendly_score: 0.0
submission_type: basic
model_repo: Nitral-AI/Hathor-L3-8B-v.01
model_architecture: LlamaForCausalLM
reward_repo: Jellywibble/CHAI_alignment_reward_model
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_v56
is_internal_developer: True
language_model: Nitral-AI/Hathor-L3-8B-v.01
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-09
win_ratio: 0.5105852233564184
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: {'bot_template': '{bot_name}: {message}\n', 'memory_template': '', 'prompt_template': '', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer
Waiting for job on nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer to finish
nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer: ║ _____ __ __ ║
nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer: ║ /___/ ║
nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer: ║ Version: 0.8.14 ║
nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer: ║ https://mk1.ai ║
nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer: ║ belonging to: ║
nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer: Downloaded to shared memory in 23.883s
nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:05<13:22, 2.78s/it] Loading 0: 5%|▍ | 14/291 [00:05<01:22, 3.35it/s] Loading 0: 10%|▉ | 29/291 [00:05<00:31, 8.41it/s] Loading 0: 14%|█▍ | 41/291 [00:05<00:18, 13.64it/s] Loading 0: 19%|█▉ | 56/291 [00:05<00:10, 22.20it/s] Loading 0: 24%|██▎ | 69/291 [00:06<00:09, 23.57it/s] Loading 0: 29%|██▉ | 85/291 [00:06<00:05, 34.73it/s] Loading 0: 33%|███▎ | 97/291 [00:06<00:04, 43.41it/s] Loading 0: 38%|███▊ | 112/291 [00:06<00:03, 56.93it/s] Loading 0: 43%|████▎ | 125/291 [00:06<00:02, 67.61it/s] Loading 0: 48%|████▊ | 140/291 [00:06<00:01, 80.01it/s] Loading 0: 53%|█████▎ | 155/291 [00:07<00:01, 93.73it/s] Loading 0: 58%|█████▊ | 169/291 [00:07<00:02, 57.06it/s] Loading 0: 63%|██████▎ | 184/291 [00:07<00:01, 70.79it/s] Loading 0: 67%|██████▋ | 196/291 [00:07<00:01, 78.77it/s] Loading 0: 73%|███████▎ | 211/291 [00:07<00:00, 92.74it/s] Loading 0: 77%|███████▋ | 224/291 [00:07<00:00, 98.45it/s] Loading 0: 82%|████████▏ | 239/291 [00:08<00:00, 106.68it/s] Loading 0: 87%|████████▋ | 254/291 [00:08<00:00, 117.26it/s] Loading 0: 92%|█████████▏| 268/291 [00:08<00:00, 63.57it/s] Loading 0: 96%|█████████▌| 279/291 [00:11<00:01, 11.89it/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-v56-mkmlizer: quantized model in 31.960s
nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer: Processed model Nitral-AI/Hathor-L3-8B-v.01 in 55.844s
nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v56/flywheel_model.0.safetensors
nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer: loading reward model from Jellywibble/CHAI_alignment_reward_model
nitral-ai-hathor-l3-8b-v-01-v56-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-v56-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:778: 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-v56-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer: Saving duration: 1.527s
nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer: Processed model Jellywibble/CHAI_alignment_reward_model in 3.768s
nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v56_reward
nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v56_reward/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v56_reward/config.json
nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v56_reward/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v56_reward/merges.txt
nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v56_reward/vocab.json
nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v56_reward/tokenizer.json
nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v56_reward/reward.tensors
Job nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer completed after 87.98s with status: succeeded
Stopping job with name nitral-ai-hathor-l3-8b-v-01-v56-mkmlizer
Pipeline stage MKMLizer completed in 89.34s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.30s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-hathor-l3-8b-v-01-v56
Waiting for inference service nitral-ai-hathor-l3-8b-v-01-v56 to be ready
Inference service nitral-ai-hathor-l3-8b-v-01-v56 ready after 81.08377313613892s
Pipeline stage ISVCDeployer completed in 87.78s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9434847831726074s
Received healthy response to inference request in 1.547903060913086s
Received healthy response to inference request in 1.3385746479034424s
Received healthy response to inference request in 1.3374197483062744s
Received healthy response to inference request in 1.4221582412719727s
5 requests
0 failed requests
5th percentile: 1.337650728225708
10th percentile: 1.3378817081451415
20th percentile: 1.3383436679840088
30th percentile: 1.3552913665771484
40th percentile: 1.3887248039245605
50th percentile: 1.4221582412719727
60th percentile: 1.472456169128418
70th percentile: 1.5227540969848632
80th percentile: 1.6270194053649902
90th percentile: 1.7852520942687988
95th percentile: 1.8643684387207031
99th percentile: 1.9276615142822267
mean time: 1.5179080963134766
Pipeline stage StressChecker completed in 9.85s
nitral-ai-hathor-l3-8b-v-01_v56 status is now deployed due to DeploymentManager action
nitral-ai-hathor-l3-8b-v-01_v56 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of nitral-ai-hathor-l3-8b-v-01_v56
Running pipeline stage ISVCDeleter
Checking if service nitral-ai-hathor-l3-8b-v-01-v56 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.86s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key nitral-ai-hathor-l3-8b-v-01-v56/config.json from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v56/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v56/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v56/tokenizer.json from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v56/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key nitral-ai-hathor-l3-8b-v-01-v56_reward/config.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v56_reward/merges.txt from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v56_reward/reward.tensors from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v56_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v56_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v56_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v56_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.54s
nitral-ai-hathor-l3-8b-v-01_v56 status is now torndown due to DeploymentManager action