developer_uid: Nitral-AI
submission_id: nitral-ai-hathor-l3-8b-v-02_v19
model_name: nitral-ai-hathor-l3-8b-v02
model_group: Nitral-AI/Hathor-L3-8B-v
status: torndown
timestamp: 2024-07-04T23:26:03+00:00
num_battles: 32670
num_wins: 16375
celo_rating: 1202.38
family_friendly_score: 0.0
submission_type: basic
model_repo: Nitral-AI/Hathor-L3-8B-v.02
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: nitral-ai-hathor-l3-8b-v02
is_internal_developer: False
language_model: Nitral-AI/Hathor-L3-8B-v.02
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-04
win_ratio: 0.5012243648607285
generation_params: {'temperature': 1.25, 'top_p': 1.0, 'min_p': 0.03, 'top_k': 60, 'presence_penalty': 0.02, 'frequency_penalty': 0.05, 'stopping_words': ['\n', '<|end_header_id|>', '<|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': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', '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-02-v19-mkmlizer
Waiting for job on nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer to finish
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: ║ _____ __ __ ║
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: ║ /___/ ║
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: ║ Version: 0.8.14 ║
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: ║ https://mk1.ai ║
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: ║ belonging to: ║
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: Downloaded to shared memory in 26.806s
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:05<13:44, 2.85s/it] Loading 0: 5%|▍ | 14/291 [00:05<01:24, 3.26it/s] Loading 0: 9%|▉ | 27/291 [00:05<00:35, 7.51it/s] Loading 0: 14%|█▍ | 41/291 [00:06<00:18, 13.46it/s] Loading 0: 19%|█▊ | 54/291 [00:06<00:11, 20.50it/s] Loading 0: 22%|██▏ | 65/291 [00:06<00:10, 20.72it/s] Loading 0: 26%|██▋ | 77/291 [00:06<00:07, 28.22it/s] Loading 0: 31%|███ | 89/291 [00:06<00:05, 37.37it/s] Loading 0: 35%|███▌ | 103/291 [00:06<00:03, 49.65it/s] Loading 0: 39%|███▉ | 114/291 [00:07<00:03, 56.63it/s] Loading 0: 45%|████▍ | 130/291 [00:07<00:02, 72.91it/s] Loading 0: 49%|████▉ | 142/291 [00:07<00:01, 80.28it/s] Loading 0: 54%|█████▍ | 157/291 [00:07<00:01, 92.52it/s] Loading 0: 58%|█████▊ | 169/291 [00:07<00:02, 49.95it/s] Loading 0: 63%|██████▎ | 184/291 [00:08<00:01, 63.31it/s] Loading 0: 67%|██████▋ | 195/291 [00:08<00:01, 69.54it/s] Loading 0: 73%|███████▎ | 211/291 [00:08<00:00, 84.30it/s] Loading 0: 77%|███████▋ | 223/291 [00:08<00:00, 87.28it/s] Loading 0: 82%|████████▏ | 238/291 [00:08<00:00, 99.10it/s] Loading 0: 86%|████████▌ | 250/291 [00:08<00:00, 100.40it/s] Loading 0: 91%|█████████ | 265/291 [00:08<00:00, 106.85it/s] Loading 0: 95%|█████████▌| 277/291 [00:09<00:00, 53.61it/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-02-v19-mkmlizer: quantized model in 29.948s
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: Processed model Nitral-AI/Hathor-L3-8B-v.02 in 56.755s
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-02-v19
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-02-v19/config.json
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-02-v19/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-02-v19/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-02-v19/tokenizer.json
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-02-v19/flywheel_model.0.safetensors
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
nitral-ai-hathor-l3-8b-v-02-v19-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-02-v19-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-02-v19-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-02-v19-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-02-v19-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-02-v19-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: /opt/conda/lib/python3.10/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: return self.fget.__get__(instance, owner)()
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: Saving duration: 0.518s
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.471s
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-02-v19_reward
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-02-v19_reward/config.json
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-02-v19_reward/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-02-v19_reward/vocab.json
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-02-v19_reward/merges.txt
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-02-v19_reward/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-02-v19_reward/tokenizer.json
nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-02-v19_reward/reward.tensors
Job nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer completed after 84.79s with status: succeeded
Stopping job with name nitral-ai-hathor-l3-8b-v-02-v19-mkmlizer
Pipeline stage MKMLizer completed in 85.57s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-hathor-l3-8b-v-02-v19
Waiting for inference service nitral-ai-hathor-l3-8b-v-02-v19 to be ready
Inference service nitral-ai-hathor-l3-8b-v-02-v19 ready after 40.21427607536316s
Pipeline stage ISVCDeployer completed in 47.12s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.101457357406616s
Received healthy response to inference request in 1.334308385848999s
Received healthy response to inference request in 1.3140463829040527s
Received healthy response to inference request in 1.2750873565673828s
Received healthy response to inference request in 1.3502318859100342s
5 requests
0 failed requests
5th percentile: 1.2828791618347168
10th percentile: 1.2906709671020509
20th percentile: 1.3062545776367187
30th percentile: 1.318098783493042
40th percentile: 1.3262035846710205
50th percentile: 1.334308385848999
60th percentile: 1.3406777858734131
70th percentile: 1.3470471858978272
80th percentile: 1.5004769802093507
90th percentile: 1.8009671688079836
95th percentile: 1.9512122631072997
99th percentile: 2.0714083385467528
mean time: 1.475026273727417
Pipeline stage StressChecker completed in 8.18s
nitral-ai-hathor-l3-8b-v-02_v19 status is now deployed due to DeploymentManager action
nitral-ai-hathor-l3-8b-v-02_v19 status is now inactive due to auto deactivation removed underperforming models
nitral-ai-hathor-l3-8b-v-02_v19 status is now deployed due to admin request
nitral-ai-hathor-l3-8b-v-02_v19 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of nitral-ai-hathor-l3-8b-v-02_v19
Running pipeline stage ISVCDeleter
Checking if service nitral-ai-hathor-l3-8b-v-02-v19 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.14s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key nitral-ai-hathor-l3-8b-v-02-v19/config.json from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-02-v19/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-02-v19/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-02-v19/tokenizer.json from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-02-v19/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key nitral-ai-hathor-l3-8b-v-02-v19_reward/config.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-02-v19_reward/merges.txt from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-02-v19_reward/reward.tensors from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-02-v19_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-02-v19_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-02-v19_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-02-v19_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.61s
nitral-ai-hathor-l3-8b-v-02_v19 status is now torndown due to DeploymentManager action