submission_id: hastagaras-jakal-001_v1
developer_uid: Hastagaras
best_of: 16
celo_rating: 1202.47
display_name: hehe
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': 1.5, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 45, '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: False
language_model: Hastagaras/Jakal.001
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: Hastagaras/Jakal.001
model_name: hehe
model_num_parameters: 8030261248.0
model_repo: Hastagaras/Jakal.001
model_size: 8B
num_battles: 14704
num_wins: 7666
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/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-07-04T02:13:00+00:00
us_pacific_date: 2024-07-03
win_ratio: 0.5213547334058759
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-jakal-001-v1-mkmlizer
Waiting for job on hastagaras-jakal-001-v1-mkmlizer to finish
Stopping job with name hastagaras-jakal-001-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name hastagaras-jakal-001-v1-mkmlizer
Waiting for job on hastagaras-jakal-001-v1-mkmlizer to finish
hastagaras-jakal-001-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-jakal-001-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-jakal-001-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-jakal-001-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-jakal-001-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-jakal-001-v1-mkmlizer: ║ /___/ ║
hastagaras-jakal-001-v1-mkmlizer: ║ ║
hastagaras-jakal-001-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-jakal-001-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-jakal-001-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-jakal-001-v1-mkmlizer: ║ ║
hastagaras-jakal-001-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-jakal-001-v1-mkmlizer: ║ belonging to: ║
hastagaras-jakal-001-v1-mkmlizer: ║ ║
hastagaras-jakal-001-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-jakal-001-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-jakal-001-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-jakal-001-v1-mkmlizer: ║ ║
hastagaras-jakal-001-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-jakal-001-v1-mkmlizer: Downloaded to shared memory in 50.331s
hastagaras-jakal-001-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-jakal-001-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-jakal-001-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:50, 2.46s/it] Loading 0: 4%|▍ | 13/291 [00:05<01:19, 3.50it/s] Loading 0: 8%|▊ | 24/291 [00:05<00:35, 7.57it/s] Loading 0: 14%|█▎ | 40/291 [00:05<00:16, 15.40it/s] Loading 0: 18%|█▊ | 51/291 [00:05<00:11, 21.68it/s] Loading 0: 21%|██ | 61/291 [00:05<00:09, 23.28it/s] Loading 0: 26%|██▌ | 76/291 [00:05<00:06, 34.75it/s] Loading 0: 30%|██▉ | 87/291 [00:05<00:04, 41.98it/s] Loading 0: 35%|███▌ | 103/291 [00:06<00:03, 57.35it/s] Loading 0: 39%|███▉ | 114/291 [00:06<00:02, 64.04it/s] Loading 0: 45%|████▍ | 130/291 [00:06<00:02, 79.98it/s] Loading 0: 49%|████▉ | 142/291 [00:06<00:01, 84.81it/s] Loading 0: 54%|█████▍ | 157/291 [00:06<00:01, 96.60it/s] Loading 0: 58%|█████▊ | 169/291 [00:06<00:01, 63.17it/s] Loading 0: 63%|██████▎ | 184/291 [00:07<00:01, 75.92it/s] Loading 0: 67%|██████▋ | 195/291 [00:07<00:01, 79.39it/s] Loading 0: 71%|███████▏ | 208/291 [00:07<00:00, 89.90it/s] Loading 0: 76%|███████▌ | 220/291 [00:07<00:00, 96.37it/s] Loading 0: 80%|███████▉ | 232/291 [00:07<00:00, 97.20it/s] Loading 0: 85%|████████▍ | 247/291 [00:07<00:00, 106.02it/s] Loading 0: 89%|████████▉ | 259/291 [00:07<00:00, 103.34it/s] Loading 0: 93%|█████████▎| 270/291 [00:08<00:00, 64.51it/s] Loading 0: 97%|█████████▋| 283/291 [00:08<00:00, 76.34it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-jakal-001-v1-mkmlizer: quantized model in 24.702s
hastagaras-jakal-001-v1-mkmlizer: Processed model Hastagaras/Jakal.001 in 75.033s
hastagaras-jakal-001-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-jakal-001-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-jakal-001-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-jakal-001-v1
hastagaras-jakal-001-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-jakal-001-v1/config.json
hastagaras-jakal-001-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-jakal-001-v1/tokenizer_config.json
hastagaras-jakal-001-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-jakal-001-v1/special_tokens_map.json
hastagaras-jakal-001-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-jakal-001-v1/tokenizer.json
hastagaras-jakal-001-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-jakal-001-v1/flywheel_model.0.safetensors
hastagaras-jakal-001-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-jakal-001-v1-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.
hastagaras-jakal-001-v1-mkmlizer: warnings.warn(
hastagaras-jakal-001-v1-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`.
hastagaras-jakal-001-v1-mkmlizer: warnings.warn(
hastagaras-jakal-001-v1-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.
hastagaras-jakal-001-v1-mkmlizer: warnings.warn(
hastagaras-jakal-001-v1-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.
hastagaras-jakal-001-v1-mkmlizer: warnings.warn(
hastagaras-jakal-001-v1-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()
hastagaras-jakal-001-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-jakal-001-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-jakal-001-v1-mkmlizer: Saving duration: 0.398s
hastagaras-jakal-001-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.970s
hastagaras-jakal-001-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-jakal-001-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-jakal-001-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-jakal-001-v1_reward
hastagaras-jakal-001-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-jakal-001-v1_reward/tokenizer_config.json
hastagaras-jakal-001-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-jakal-001-v1_reward/merges.txt
hastagaras-jakal-001-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-jakal-001-v1_reward/config.json
hastagaras-jakal-001-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-jakal-001-v1_reward/special_tokens_map.json
hastagaras-jakal-001-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-jakal-001-v1_reward/tokenizer.json
hastagaras-jakal-001-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-jakal-001-v1_reward/vocab.json
hastagaras-jakal-001-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-jakal-001-v1_reward/reward.tensors
Job hastagaras-jakal-001-v1-mkmlizer completed after 115.11s with status: succeeded
Stopping job with name hastagaras-jakal-001-v1-mkmlizer
Pipeline stage MKMLizer completed in 116.65s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-jakal-001-v1
Waiting for inference service hastagaras-jakal-001-v1 to be ready
Inference service hastagaras-jakal-001-v1 ready after 50.23478364944458s
Pipeline stage ISVCDeployer completed in 57.40s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0065555572509766s
Received healthy response to inference request in 1.3291385173797607s
Received healthy response to inference request in 1.297935962677002s
Received healthy response to inference request in 1.2733683586120605s
Received healthy response to inference request in 1.331268072128296s
5 requests
0 failed requests
5th percentile: 1.2782818794250488
10th percentile: 1.283195400238037
20th percentile: 1.2930224418640137
30th percentile: 1.3041764736175536
40th percentile: 1.3166574954986572
50th percentile: 1.3291385173797607
60th percentile: 1.3299903392791748
70th percentile: 1.3308421611785888
80th percentile: 1.466325569152832
90th percentile: 1.7364405632019044
95th percentile: 1.8714980602264404
99th percentile: 1.9795440578460692
mean time: 1.4476532936096191
Pipeline stage StressChecker completed in 7.94s
hastagaras-jakal-001_v1 status is now deployed due to DeploymentManager action
hastagaras-jakal-001_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-jakal-001_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-jakal-001-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 5.22s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-jakal-001-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-jakal-001-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-jakal-001-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-jakal-001-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-jakal-001-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-jakal-001-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-jakal-001-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-jakal-001-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-jakal-001-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-jakal-001-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-jakal-001-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-jakal-001-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.52s
hastagaras-jakal-001_v1 status is now torndown due to DeploymentManager action