r136a1-ayam-2x8b

developer_uid: R136a1
submission_id: r136a1-ayam-2x8b_v2
model_name: r136a1-ayam-2x8b_v1
model_group: R136a1/Ayam-2x8B
status: torndown
timestamp: 2024-06-11T17:23:47+00:00
num_battles: 24032
num_wins: 12207
celo_rating: 1183.2
family_friendly_score: 0.0
submission_type: basic
model_repo: R136a1/Ayam-2x8B
model_architecture: MixtralForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 13667667968.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: r136a1-ayam-2x8b_v1
is_internal_developer: False
language_model: R136a1/Ayam-2x8B
model_size: 14B
ranking_group: single
us_pacific_date: 2024-06-11
win_ratio: 0.5079477363515313
generation_params: {'temperature': 1.15, 'top_p': 1.0, 'min_p': 0.075, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
model_eval_status: success
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 r136a1-ayam-2x8b-v2-mkmlizer
Waiting for job on r136a1-ayam-2x8b-v2-mkmlizer to finish
r136a1-ayam-2x8b-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
r136a1-ayam-2x8b-v2-mkmlizer: ║     _____            __           __                                ║
r136a1-ayam-2x8b-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
r136a1-ayam-2x8b-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
r136a1-ayam-2x8b-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
r136a1-ayam-2x8b-v2-mkmlizer: ║       /___/                                                         ║
r136a1-ayam-2x8b-v2-mkmlizer: ║                                                                     ║
r136a1-ayam-2x8b-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
r136a1-ayam-2x8b-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
r136a1-ayam-2x8b-v2-mkmlizer: ║  https://mk1.ai                                                     ║
r136a1-ayam-2x8b-v2-mkmlizer: ║                                                                     ║
r136a1-ayam-2x8b-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
r136a1-ayam-2x8b-v2-mkmlizer: ║  belonging to:                                                      ║
r136a1-ayam-2x8b-v2-mkmlizer: ║                                                                     ║
r136a1-ayam-2x8b-v2-mkmlizer: ║  Chai Research Corp.                                                ║
r136a1-ayam-2x8b-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
r136a1-ayam-2x8b-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
r136a1-ayam-2x8b-v2-mkmlizer: ║                                                                     ║
r136a1-ayam-2x8b-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
r136a1-ayam-2x8b-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
r136a1-ayam-2x8b-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
r136a1-ayam-2x8b-v2-mkmlizer: Downloaded to shared memory in 37.339s
r136a1-ayam-2x8b-v2-mkmlizer: quantizing model to /dev/shm/model_cache
r136a1-ayam-2x8b-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
r136a1-ayam-2x8b-v2-mkmlizer: 
Loading 0:   0%|          | 0/419 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/419 [00:00<00:06, 60.77it/s]
Loading 0:   4%|▍         | 18/419 [00:00<00:04, 85.04it/s]
Loading 0:   7%|▋         | 29/419 [00:00<00:04, 91.00it/s]
Loading 0:  10%|▉         | 40/419 [00:00<00:03, 95.01it/s]
Loading 0:  12%|█▏        | 51/419 [00:00<00:03, 98.48it/s]
Loading 0:  15%|█▌        | 63/419 [00:01<00:07, 48.32it/s]
Loading 0:  17%|█▋        | 72/419 [00:01<00:06, 55.16it/s]
Loading 0:  20%|██        | 85/419 [00:01<00:04, 68.64it/s]
Loading 0:  23%|██▎       | 95/419 [00:01<00:04, 74.63it/s]
Loading 0:  25%|██▌       | 106/419 [00:01<00:03, 81.27it/s]
Loading 0:  28%|██▊       | 117/419 [00:01<00:03, 86.54it/s]
Loading 0:  30%|███       | 127/419 [00:01<00:03, 88.25it/s]
Loading 0:  33%|███▎      | 137/419 [00:01<00:03, 88.50it/s]
Loading 0:  35%|███▌      | 147/419 [00:02<00:06, 42.89it/s]
Loading 0:  38%|███▊      | 158/419 [00:02<00:04, 52.95it/s]
Loading 0:  40%|████      | 168/419 [00:02<00:04, 61.16it/s]
Loading 0:  42%|████▏     | 177/419 [00:02<00:03, 65.33it/s]
Loading 0:  44%|████▍     | 186/419 [00:02<00:03, 70.04it/s]
Loading 0:  47%|████▋     | 197/419 [00:02<00:02, 78.27it/s]
Loading 0:  50%|████▉     | 208/419 [00:02<00:02, 84.65it/s]
Loading 0:  52%|█████▏    | 218/419 [00:03<00:04, 44.53it/s]
Loading 0:  54%|█████▍    | 226/419 [00:03<00:03, 49.88it/s]
Loading 0:  56%|█████▌    | 234/419 [00:03<00:03, 53.90it/s]
Loading 0:  58%|█████▊    | 245/419 [00:03<00:02, 62.77it/s]
Loading 0:  61%|██████    | 256/419 [00:03<00:02, 71.69it/s]
Loading 0:  64%|██████▎   | 267/419 [00:03<00:01, 79.76it/s]
Loading 0:  66%|██████▋   | 278/419 [00:04<00:01, 86.09it/s]
Loading 0:  69%|██████▉   | 289/419 [00:04<00:02, 47.08it/s]
Loading 0:  71%|███████   | 297/419 [00:04<00:02, 51.22it/s]
Loading 0:  73%|███████▎  | 306/419 [00:04<00:01, 58.10it/s]
Loading 0:  76%|███████▌  | 317/419 [00:04<00:01, 68.29it/s]
Loading 0:  78%|███████▊  | 328/419 [00:04<00:01, 77.11it/s]
Loading 0:  81%|████████  | 339/419 [00:05<00:00, 84.77it/s]
Loading 0:  84%|████████▎ | 350/419 [00:05<00:00, 90.20it/s]
Loading 0:  86%|████████▌ | 360/419 [00:05<00:00, 91.67it/s]
Loading 0:  88%|████████▊ | 370/419 [00:20<00:22,  2.20it/s]
Loading 0:  95%|█████████▍| 396/419 [00:20<00:05,  4.53it/s]
Loading 0:  98%|█████████▊| 410/419 [00:20<00:01,  6.20it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
r136a1-ayam-2x8b-v2-mkmlizer: quantized model in 27.762s
r136a1-ayam-2x8b-v2-mkmlizer: Processed model R136a1/Ayam-2x8B in 67.428s
r136a1-ayam-2x8b-v2-mkmlizer: creating bucket guanaco-mkml-models
r136a1-ayam-2x8b-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
r136a1-ayam-2x8b-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/r136a1-ayam-2x8b-v2
r136a1-ayam-2x8b-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/r136a1-ayam-2x8b-v2/config.json
r136a1-ayam-2x8b-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/r136a1-ayam-2x8b-v2/special_tokens_map.json
r136a1-ayam-2x8b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/r136a1-ayam-2x8b-v2/tokenizer_config.json
r136a1-ayam-2x8b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/r136a1-ayam-2x8b-v2/tokenizer.json
r136a1-ayam-2x8b-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/r136a1-ayam-2x8b-v2/flywheel_model.0.safetensors
r136a1-ayam-2x8b-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
r136a1-ayam-2x8b-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:913: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
r136a1-ayam-2x8b-v2-mkmlizer:   warnings.warn(
r136a1-ayam-2x8b-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:757: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
r136a1-ayam-2x8b-v2-mkmlizer:   warnings.warn(
r136a1-ayam-2x8b-v2-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.
r136a1-ayam-2x8b-v2-mkmlizer:   warnings.warn(
r136a1-ayam-2x8b-v2-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()
r136a1-ayam-2x8b-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
r136a1-ayam-2x8b-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
r136a1-ayam-2x8b-v2-mkmlizer: Saving duration: 0.244s
r136a1-ayam-2x8b-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.027s
r136a1-ayam-2x8b-v2-mkmlizer: creating bucket guanaco-reward-models
r136a1-ayam-2x8b-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
r136a1-ayam-2x8b-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/r136a1-ayam-2x8b-v2_reward
r136a1-ayam-2x8b-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/r136a1-ayam-2x8b-v2_reward/special_tokens_map.json
r136a1-ayam-2x8b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/r136a1-ayam-2x8b-v2_reward/tokenizer_config.json
r136a1-ayam-2x8b-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/r136a1-ayam-2x8b-v2_reward/vocab.json
r136a1-ayam-2x8b-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/r136a1-ayam-2x8b-v2_reward/config.json
r136a1-ayam-2x8b-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/r136a1-ayam-2x8b-v2_reward/merges.txt
r136a1-ayam-2x8b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/r136a1-ayam-2x8b-v2_reward/tokenizer.json
r136a1-ayam-2x8b-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/r136a1-ayam-2x8b-v2_reward/reward.tensors
Job r136a1-ayam-2x8b-v2-mkmlizer completed after 94.66s with status: succeeded
Stopping job with name r136a1-ayam-2x8b-v2-mkmlizer
Pipeline stage MKMLizer completed in 98.36s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service r136a1-ayam-2x8b-v2
Waiting for inference service r136a1-ayam-2x8b-v2 to be ready
Inference service r136a1-ayam-2x8b-v2 ready after 40.267139196395874s
Pipeline stage ISVCDeployer completed in 47.51s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8872222900390625s
Received healthy response to inference request in 1.9920969009399414s
Received healthy response to inference request in 1.9652495384216309s
Received healthy response to inference request in 2.002795457839966s
Received healthy response to inference request in 1.6935384273529053s
5 requests
0 failed requests
5th percentile: 1.7478806495666503
10th percentile: 1.8022228717803954
20th percentile: 1.9109073162078858
30th percentile: 1.970619010925293
40th percentile: 1.981357955932617
50th percentile: 1.9920969009399414
60th percentile: 1.9963763236999512
70th percentile: 2.000655746459961
80th percentile: 2.179680824279785
90th percentile: 2.533451557159424
95th percentile: 2.710336923599243
99th percentile: 2.851845216751099
mean time: 2.108180522918701
Pipeline stage StressChecker completed in 11.19s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.03s
M-Eval Dataset for topic stay_in_character is loaded
r136a1-ayam-2x8b_v2 status is now deployed due to DeploymentManager action
r136a1-ayam-2x8b_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of r136a1-ayam-2x8b_v2
Running pipeline stage ISVCDeleter
Checking if service r136a1-ayam-2x8b-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.36s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key r136a1-ayam-2x8b-v2/config.json from bucket guanaco-mkml-models
Deleting key r136a1-ayam-2x8b-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key r136a1-ayam-2x8b-v2/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key r136a1-ayam-2x8b-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key r136a1-ayam-2x8b-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key r136a1-ayam-2x8b-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key r136a1-ayam-2x8b-v2_reward/config.json from bucket guanaco-reward-models
Deleting key r136a1-ayam-2x8b-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key r136a1-ayam-2x8b-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key r136a1-ayam-2x8b-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key r136a1-ayam-2x8b-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key r136a1-ayam-2x8b-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key r136a1-ayam-2x8b-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.80s
r136a1-ayam-2x8b_v2 status is now torndown due to DeploymentManager action