nitral-ai-hathor-l3-8b-v-01

submission_id: nitral-ai-hathor-l3-8b-v-01_v12
developer_uid: robert_irvine
best_of: 16
celo_rating: 1235.49
display_name: nitral-ai-hathor-l3-8b-v-01_v12
family_friendly_score: 0.0
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}
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}
is_internal_developer: True
language_model: Nitral-AI/Hathor-L3-8B-v.01
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: Nitral-AI/Hathor-L3-8B-v
model_name: nitral-ai-hathor-l3-8b-v-01_v12
model_num_parameters: 8030261248.0
model_repo: Nitral-AI/Hathor-L3-8B-v.01
model_size: 8B
num_battles: 32705
num_wins: 18465
ranking_group: single
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'}
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
status: torndown
submission_type: basic
timestamp: 2024-07-05T17:06:59+00:00
us_pacific_date: 2024-07-05
win_ratio: 0.5645925699434338
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer
Waiting for job on nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer to finish
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: ║     _____            __           __                                ║
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: ║       /___/                                                         ║
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: ║                                                                     ║
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: ║  Version: 0.8.14                                                    ║
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: ║  https://mk1.ai                                                     ║
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: ║                                                                     ║
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: ║  The license key for the current software has been verified as      ║
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: ║  belonging to:                                                      ║
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: ║                                                                     ║
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: ║  Chai Research Corp.                                                ║
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: ║                                                                     ║
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: Downloaded to shared memory in 45.789s
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:05<13:13,  2.74s/it]
Loading 0:   5%|▍         | 14/291 [00:05<01:21,  3.40it/s]
Loading 0:  11%|█         | 31/291 [00:05<00:28,  9.17it/s]
Loading 0:  14%|█▍        | 42/291 [00:05<00:17, 13.94it/s]
Loading 0:  20%|██        | 59/291 [00:05<00:09, 23.60it/s]
Loading 0:  25%|██▍       | 72/291 [00:06<00:08, 26.56it/s]
Loading 0:  30%|██▉       | 86/291 [00:06<00:05, 36.25it/s]
Loading 0:  35%|███▌      | 103/291 [00:06<00:03, 50.25it/s]
Loading 0:  40%|███▉      | 115/291 [00:06<00:02, 59.40it/s]
Loading 0:  45%|████▌     | 131/291 [00:06<00:02, 73.87it/s]
Loading 0:  51%|█████     | 148/291 [00:06<00:01, 89.03it/s]
Loading 0:  56%|█████▌    | 162/291 [00:06<00:01, 97.07it/s]
Loading 0:  60%|██████    | 175/291 [00:07<00:01, 68.39it/s]
Loading 0:  64%|██████▍   | 186/291 [00:07<00:01, 75.26it/s]
Loading 0:  70%|██████▉   | 203/291 [00:07<00:00, 91.26it/s]
Loading 0:  75%|███████▍  | 217/291 [00:07<00:00, 100.91it/s]
Loading 0:  79%|███████▉  | 230/291 [00:07<00:00, 106.69it/s]
Loading 0:  85%|████████▍ | 247/291 [00:07<00:00, 118.04it/s]
Loading 0:  90%|████████▉ | 261/291 [00:07<00:00, 118.28it/s]
Loading 0:  94%|█████████▍| 274/291 [00:08<00:00, 74.59it/s] 
Loading 0:  98%|█████████▊| 285/291 [00:08<00:00, 80.62it/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-v12-mkmlizer: quantized model in 24.798s
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: Processed model Nitral-AI/Hathor-L3-8B-v.01 in 70.587s
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v12
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v12/config.json
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v12/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v12/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v12/tokenizer.json
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v12/flywheel_model.0.safetensors
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
nitral-ai-hathor-l3-8b-v-01-v12-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-v12-mkmlizer:   warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v12-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-v12-mkmlizer:   warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v12-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-v12-mkmlizer:   warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:15<00:15, 15.81s/it]
Downloading shards: 100%|██████████| 2/2 [00:26<00:00, 12.70s/it]
Downloading shards: 100%|██████████| 2/2 [00:26<00:00, 13.17s/it]
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  1.36it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  2.32it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  2.10it/s]
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: Saving duration: 1.728s
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 31.403s
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: ERROR: [Errno -3] Temporary failure in name resolution
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: ERROR: Connection Error: Error resolving a server hostname.
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: Please check the servers address specified in 'host_base', 'host_bucket', 'cloudfront_host', 'website_endpoint'
Job nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer completed after 135.39s with status: failed
Stopping job with name nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer
%s, retrying in %s seconds...
Starting job with name nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer
Waiting for job on nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer to finish
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: ║     _____            __           __                                ║
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: ║       /___/                                                         ║
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: ║                                                                     ║
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: ║  Version: 0.8.14                                                    ║
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: ║  https://mk1.ai                                                     ║
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: ║                                                                     ║
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: ║  The license key for the current software has been verified as      ║
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: ║  belonging to:                                                      ║
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: ║                                                                     ║
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: ║  Chai Research Corp.                                                ║
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: ║                                                                     ║
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: Downloaded to shared memory in 31.274s
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:05<12:11,  2.53s/it]
Loading 0:   4%|▍         | 13/291 [00:05<01:21,  3.40it/s]
Loading 0:   8%|▊         | 24/291 [00:05<00:36,  7.37it/s]
Loading 0:  14%|█▎        | 40/291 [00:05<00:16, 15.00it/s]
Loading 0:  18%|█▊        | 51/291 [00:05<00:11, 21.08it/s]
Loading 0:  21%|██        | 61/291 [00:05<00:10, 22.82it/s]
Loading 0:  26%|██▌       | 76/291 [00:05<00:06, 34.09it/s]
Loading 0:  30%|██▉       | 87/291 [00:06<00:04, 41.81it/s]
Loading 0:  35%|███▌      | 103/291 [00:06<00:03, 56.92it/s]
Loading 0:  39%|███▉      | 114/291 [00:06<00:02, 63.73it/s]
Loading 0:  45%|████▍     | 130/291 [00:06<00:02, 79.64it/s]
Loading 0:  49%|████▉     | 142/291 [00:06<00:01, 84.63it/s]
Loading 0:  54%|█████▍    | 157/291 [00:06<00:01, 96.46it/s]
Loading 0:  58%|█████▊    | 169/291 [00:07<00:01, 62.07it/s]
Loading 0:  63%|██████▎   | 184/291 [00:07<00:01, 75.40it/s]
Loading 0:  67%|██████▋   | 195/291 [00:07<00:01, 79.51it/s]
Loading 0:  73%|███████▎  | 211/291 [00:07<00:00, 94.04it/s]
Loading 0:  77%|███████▋  | 223/291 [00:07<00:00, 95.84it/s]
Loading 0:  82%|████████▏ | 238/291 [00:07<00:00, 105.06it/s]
Loading 0:  86%|████████▌ | 250/291 [00:07<00:00, 103.79it/s]
Loading 0:  91%|█████████ | 265/291 [00:07<00:00, 111.83it/s]
Loading 0:  95%|█████████▌| 277/291 [00:08<00:00, 66.99it/s] 
Loading 0:  99%|█████████▉| 288/291 [00:08<00:00, 74.63it/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-v12-mkmlizer: quantized model in 25.244s
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: Processed model Nitral-AI/Hathor-L3-8B-v.01 in 56.519s
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v12
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v12/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v12/config.json
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v12/tokenizer.json
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v12/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v12/flywheel_model.0.safetensors
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
nitral-ai-hathor-l3-8b-v-01-v12-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-v12-mkmlizer:   warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v12-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-v12-mkmlizer:   warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v12-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-v12-mkmlizer:   warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v12-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-v12-mkmlizer:   warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:08<00:08,  8.18s/it]
Downloading shards: 100%|██████████| 2/2 [00:09<00:00,  4.28s/it]
Downloading shards: 100%|██████████| 2/2 [00:09<00:00,  4.87s/it]
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  1.72it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  2.90it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  2.63it/s]
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: Saving duration: 1.721s
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.680s
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v12_reward
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v12_reward/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v12_reward/config.json
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v12_reward/merges.txt
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v12_reward/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v12_reward/vocab.json
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v12_reward/tokenizer.json
nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v12_reward/reward.tensors
Job nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer completed after 115.98s with status: succeeded
Stopping job with name nitral-ai-hathor-l3-8b-v-01-v12-mkmlizer
Pipeline stage MKMLizer completed in 252.82s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-hathor-l3-8b-v-01-v12
Waiting for inference service nitral-ai-hathor-l3-8b-v-01-v12 to be ready
Inference service nitral-ai-hathor-l3-8b-v-01-v12 ready after 40.29414987564087s
Pipeline stage ISVCDeployer completed in 47.63s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.300661563873291s
Received healthy response to inference request in 1.5757036209106445s
Received healthy response to inference request in 1.5683329105377197s
Received healthy response to inference request in 1.5175457000732422s
Received healthy response to inference request in 1.615959882736206s
5 requests
0 failed requests
5th percentile: 1.5277031421661378
10th percentile: 1.5378605842590332
20th percentile: 1.5581754684448241
30th percentile: 1.5698070526123047
40th percentile: 1.5727553367614746
50th percentile: 1.5757036209106445
60th percentile: 1.591806125640869
70th percentile: 1.6079086303710937
80th percentile: 1.7529002189636231
90th percentile: 2.026780891418457
95th percentile: 2.163721227645874
99th percentile: 2.2732734966278074
mean time: 1.7156407356262207
Pipeline stage StressChecker completed in 9.53s
nitral-ai-hathor-l3-8b-v-01_v12 status is now deployed due to DeploymentManager action
nitral-ai-hathor-l3-8b-v-01_v12 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of nitral-ai-hathor-l3-8b-v-01_v12
Running pipeline stage ISVCDeleter
Checking if service nitral-ai-hathor-l3-8b-v-01-v12 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.73s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key nitral-ai-hathor-l3-8b-v-01-v12/config.json from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v12/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v12/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v12/tokenizer.json from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v12/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key nitral-ai-hathor-l3-8b-v-01-v12_reward/config.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v12_reward/merges.txt from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v12_reward/reward.tensors from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v12_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v12_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v12_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v12_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.91s
nitral-ai-hathor-l3-8b-v-01_v12 status is now torndown due to DeploymentManager action