developer_uid: Nitral-AI
submission_id: nitral-ai-hathor-aleph-l_2929_v4
model_name: nitral-ai-hathor-aleph
model_group: Nitral-AI/Hathor_Aleph-L
status: torndown
timestamp: 2024-07-04T23:41:09+00:00
num_battles: 34027
num_wins: 17334
celo_rating: 1204.01
family_friendly_score: 0.0
submission_type: basic
model_repo: Nitral-AI/Hathor_Aleph-L3-8B-v0.72
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-aleph
is_internal_developer: False
language_model: Nitral-AI/Hathor_Aleph-L3-8B-v0.72
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-04
win_ratio: 0.5094189908014224
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': "{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-aleph-l-2929-v4-mkmlizer
Waiting for job on nitral-ai-hathor-aleph-l-2929-v4-mkmlizer to finish
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: ║     _____            __           __                                ║
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: ║       /___/                                                         ║
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: ║                                                                     ║
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: ║  Version: 0.8.14                                                    ║
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: ║  https://mk1.ai                                                     ║
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: ║                                                                     ║
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: ║  belonging to:                                                      ║
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: ║                                                                     ║
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: ║  Chai Research Corp.                                                ║
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: ║                                                                     ║
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: Downloaded to shared memory in 44.078s
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<10:56,  2.27s/it]
Loading 0:   5%|▌         | 15/291 [00:04<01:02,  4.39it/s]
Loading 0:  11%|█▏        | 33/291 [00:04<00:22, 11.66it/s]
Loading 0:  18%|█▊        | 51/291 [00:04<00:11, 20.97it/s]
Loading 0:  22%|██▏       | 65/291 [00:05<00:09, 25.07it/s]
Loading 0:  27%|██▋       | 79/291 [00:05<00:06, 34.43it/s]
Loading 0:  33%|███▎      | 96/291 [00:05<00:04, 47.94it/s]
Loading 0:  39%|███▉      | 113/291 [00:05<00:02, 62.64it/s]
Loading 0:  45%|████▍     | 130/291 [00:05<00:02, 78.84it/s]
Loading 0:  51%|█████     | 148/291 [00:05<00:01, 94.64it/s]
Loading 0:  57%|█████▋    | 166/291 [00:06<00:01, 73.31it/s]
Loading 0:  62%|██████▏   | 180/291 [00:06<00:01, 83.79it/s]
Loading 0:  67%|██████▋   | 195/291 [00:06<00:01, 94.95it/s]
Loading 0:  73%|███████▎  | 213/291 [00:06<00:00, 110.21it/s]
Loading 0:  79%|███████▉  | 231/291 [00:06<00:00, 122.78it/s]
Loading 0:  86%|████████▌ | 249/291 [00:06<00:00, 132.60it/s]
Loading 0:  91%|█████████▏| 266/291 [00:07<00:00, 87.03it/s] 
Loading 0:  98%|█████████▊| 284/291 [00:07<00:00, 101.56it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: quantized model in 23.014s
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: Processed model Nitral-AI/Hathor_Aleph-L3-8B-v0.72 in 67.093s
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-hathor-aleph-l-2929-v4
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-hathor-aleph-l-2929-v4/config.json
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-hathor-aleph-l-2929-v4/special_tokens_map.json
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-hathor-aleph-l-2929-v4/tokenizer_config.json
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-hathor-aleph-l-2929-v4/tokenizer.json
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-hathor-aleph-l-2929-v4/flywheel_model.0.safetensors
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
nitral-ai-hathor-aleph-l-2929-v4-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-aleph-l-2929-v4-mkmlizer:   warnings.warn(
nitral-ai-hathor-aleph-l-2929-v4-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-aleph-l-2929-v4-mkmlizer:   warnings.warn(
nitral-ai-hathor-aleph-l-2929-v4-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-aleph-l-2929-v4-mkmlizer:   warnings.warn(
nitral-ai-hathor-aleph-l-2929-v4-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-aleph-l-2929-v4-mkmlizer:   warnings.warn(
nitral-ai-hathor-aleph-l-2929-v4-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-aleph-l-2929-v4-mkmlizer:   return self.fget.__get__(instance, owner)()
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: Saving duration: 0.404s
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.543s
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-hathor-aleph-l-2929-v4_reward
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-hathor-aleph-l-2929-v4_reward/config.json
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-hathor-aleph-l-2929-v4_reward/tokenizer_config.json
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-hathor-aleph-l-2929-v4_reward/special_tokens_map.json
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-hathor-aleph-l-2929-v4_reward/merges.txt
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-hathor-aleph-l-2929-v4_reward/vocab.json
nitral-ai-hathor-aleph-l-2929-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-hathor-aleph-l-2929-v4_reward/tokenizer.json
Job nitral-ai-hathor-aleph-l-2929-v4-mkmlizer completed after 104.06s with status: succeeded
Stopping job with name nitral-ai-hathor-aleph-l-2929-v4-mkmlizer
Pipeline stage MKMLizer completed in 104.90s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-hathor-aleph-l-2929-v4
Waiting for inference service nitral-ai-hathor-aleph-l-2929-v4 to be ready
Inference service nitral-ai-hathor-aleph-l-2929-v4 ready after 30.153786659240723s
Pipeline stage ISVCDeployer completed in 36.90s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9708836078643799s
Received healthy response to inference request in 1.3356096744537354s
Received healthy response to inference request in 1.2893667221069336s
Received healthy response to inference request in 1.2415010929107666s
Received healthy response to inference request in 1.3053491115570068s
5 requests
0 failed requests
5th percentile: 1.25107421875
10th percentile: 1.2606473445892334
20th percentile: 1.2797935962677003
30th percentile: 1.2925631999969482
40th percentile: 1.2989561557769775
50th percentile: 1.3053491115570068
60th percentile: 1.3174533367156982
70th percentile: 1.3295575618743896
80th percentile: 1.4626644611358643
90th percentile: 1.7167740345001221
95th percentile: 1.8438288211822509
99th percentile: 1.945472650527954
mean time: 1.4285420417785644
Pipeline stage StressChecker completed in 7.87s
nitral-ai-hathor-aleph-l_2929_v4 status is now deployed due to DeploymentManager action
nitral-ai-hathor-aleph-l_2929_v4 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of nitral-ai-hathor-aleph-l_2929_v4
Running pipeline stage ISVCDeleter
Checking if service nitral-ai-hathor-aleph-l-2929-v4 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.62s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key nitral-ai-hathor-aleph-l-2929-v4/config.json from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-aleph-l-2929-v4/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-aleph-l-2929-v4/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-aleph-l-2929-v4/tokenizer.json from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-aleph-l-2929-v4/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key nitral-ai-hathor-aleph-l-2929-v4_reward/config.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-aleph-l-2929-v4_reward/merges.txt from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-aleph-l-2929-v4_reward/reward.tensors from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-aleph-l-2929-v4_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-aleph-l-2929-v4_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-aleph-l-2929-v4_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-aleph-l-2929-v4_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.55s
nitral-ai-hathor-aleph-l_2929_v4 status is now torndown due to DeploymentManager action