r136a1-ayam-2x8b

developer_uid: R136a1
submission_id: r136a1-ayam-2x8b_v1
model_name: r136a1-ayam-2x8b_v1
model_group: R136a1/Ayam-2x8B
status: torndown
timestamp: 2024-06-11T17:23:17+00:00
num_battles: 24128
num_wins: 12090
celo_rating: 1179.19
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: 0.5010775862068966
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, '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-v1-mkmlizer
Waiting for job on r136a1-ayam-2x8b-v1-mkmlizer to finish
r136a1-ayam-2x8b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
r136a1-ayam-2x8b-v1-mkmlizer: ║     _____            __           __                                ║
r136a1-ayam-2x8b-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
r136a1-ayam-2x8b-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
r136a1-ayam-2x8b-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
r136a1-ayam-2x8b-v1-mkmlizer: ║       /___/                                                         ║
r136a1-ayam-2x8b-v1-mkmlizer: ║                                                                     ║
r136a1-ayam-2x8b-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
r136a1-ayam-2x8b-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
r136a1-ayam-2x8b-v1-mkmlizer: ║  https://mk1.ai                                                     ║
r136a1-ayam-2x8b-v1-mkmlizer: ║                                                                     ║
r136a1-ayam-2x8b-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
r136a1-ayam-2x8b-v1-mkmlizer: ║  belonging to:                                                      ║
r136a1-ayam-2x8b-v1-mkmlizer: ║                                                                     ║
r136a1-ayam-2x8b-v1-mkmlizer: ║  Chai Research Corp.                                                ║
r136a1-ayam-2x8b-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
r136a1-ayam-2x8b-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
r136a1-ayam-2x8b-v1-mkmlizer: ║                                                                     ║
r136a1-ayam-2x8b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
r136a1-ayam-2x8b-v1-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-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
r136a1-ayam-2x8b-v1-mkmlizer: Downloaded to shared memory in 49.391s
r136a1-ayam-2x8b-v1-mkmlizer: quantizing model to /dev/shm/model_cache
r136a1-ayam-2x8b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
r136a1-ayam-2x8b-v1-mkmlizer: 
Loading 0:   0%|          | 0/419 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/419 [00:00<00:06, 59.20it/s]
Loading 0:   4%|▍         | 17/419 [00:00<00:04, 80.55it/s]
Loading 0:   7%|▋         | 28/419 [00:00<00:04, 89.16it/s]
Loading 0:  10%|▉         | 40/419 [00:00<00:04, 94.58it/s]
Loading 0:  12%|█▏        | 52/419 [00:00<00:03, 98.60it/s]
Loading 0:  15%|█▌        | 63/419 [00:00<00:06, 51.52it/s]
Loading 0:  17%|█▋        | 73/419 [00:01<00:05, 60.35it/s]
Loading 0:  20%|██        | 85/419 [00:01<00:04, 72.18it/s]
Loading 0:  23%|██▎       | 95/419 [00:01<00:04, 75.27it/s]
Loading 0:  25%|██▌       | 106/419 [00:01<00:03, 83.21it/s]
Loading 0:  28%|██▊       | 118/419 [00:01<00:03, 87.93it/s]
Loading 0:  31%|███       | 129/419 [00:01<00:03, 90.12it/s]
Loading 0:  33%|███▎      | 139/419 [00:01<00:03, 88.24it/s]
Loading 0:  36%|███▌      | 149/419 [00:02<00:05, 45.09it/s]
Loading 0:  38%|███▊      | 161/419 [00:02<00:04, 55.67it/s]
Loading 0:  41%|████      | 172/419 [00:02<00:03, 63.91it/s]
Loading 0:  44%|████▍     | 184/419 [00:02<00:03, 73.33it/s]
Loading 0:  47%|████▋     | 196/419 [00:02<00:02, 79.78it/s]
Loading 0:  49%|████▉     | 206/419 [00:02<00:02, 84.04it/s]
Loading 0:  52%|█████▏    | 216/419 [00:03<00:04, 48.32it/s]
Loading 0:  53%|█████▎    | 224/419 [00:03<00:03, 49.36it/s]
Loading 0:  56%|█████▌    | 233/419 [00:03<00:03, 56.04it/s]
Loading 0:  58%|█████▊    | 243/419 [00:03<00:02, 64.29it/s]
Loading 0:  61%|██████    | 254/419 [00:03<00:02, 73.64it/s]
Loading 0:  63%|██████▎   | 263/419 [00:03<00:02, 76.97it/s]
Loading 0:  65%|██████▍   | 272/419 [00:03<00:01, 76.93it/s]
Loading 0:  68%|██████▊   | 286/419 [00:04<00:01, 91.98it/s]
Loading 0:  71%|███████   | 296/419 [00:04<00:02, 48.49it/s]
Loading 0:  73%|███████▎  | 305/419 [00:04<00:02, 54.74it/s]
Loading 0:  75%|███████▌  | 315/419 [00:04<00:01, 62.93it/s]
Loading 0:  78%|███████▊  | 325/419 [00:04<00:01, 70.67it/s]
Loading 0:  80%|███████▉  | 334/419 [00:04<00:01, 73.56it/s]
Loading 0:  82%|████████▏ | 343/419 [00:05<00:01, 74.89it/s]
Loading 0:  84%|████████▍ | 354/419 [00:05<00:00, 82.67it/s]
Loading 0:  88%|████████▊ | 367/419 [00:20<00:00, 82.67it/s]
Loading 0:  88%|████████▊ | 368/419 [00:20<00:21,  2.34it/s]
Loading 0:  95%|█████████▍| 398/419 [00:20<00:04,  4.99it/s]
Loading 0:  99%|█████████▊| 413/419 [00:20<00:00,  6.79it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
r136a1-ayam-2x8b-v1-mkmlizer: quantized model in 27.901s
r136a1-ayam-2x8b-v1-mkmlizer: Processed model R136a1/Ayam-2x8B in 79.153s
r136a1-ayam-2x8b-v1-mkmlizer: creating bucket guanaco-mkml-models
r136a1-ayam-2x8b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
r136a1-ayam-2x8b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/r136a1-ayam-2x8b-v1
r136a1-ayam-2x8b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/r136a1-ayam-2x8b-v1/config.json
r136a1-ayam-2x8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/r136a1-ayam-2x8b-v1/tokenizer_config.json
r136a1-ayam-2x8b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/r136a1-ayam-2x8b-v1/special_tokens_map.json
r136a1-ayam-2x8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/r136a1-ayam-2x8b-v1/tokenizer.json
r136a1-ayam-2x8b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/r136a1-ayam-2x8b-v1/flywheel_model.1.safetensors
r136a1-ayam-2x8b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/r136a1-ayam-2x8b-v1/flywheel_model.0.safetensors
r136a1-ayam-2x8b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
r136a1-ayam-2x8b-v1-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-v1-mkmlizer:   warnings.warn(
r136a1-ayam-2x8b-v1-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-v1-mkmlizer:   warnings.warn(
r136a1-ayam-2x8b-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()
r136a1-ayam-2x8b-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
r136a1-ayam-2x8b-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
r136a1-ayam-2x8b-v1-mkmlizer: Saving duration: 0.282s
r136a1-ayam-2x8b-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.008s
r136a1-ayam-2x8b-v1-mkmlizer: creating bucket guanaco-reward-models
r136a1-ayam-2x8b-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
r136a1-ayam-2x8b-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/r136a1-ayam-2x8b-v1_reward
r136a1-ayam-2x8b-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/r136a1-ayam-2x8b-v1_reward/special_tokens_map.json
r136a1-ayam-2x8b-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/r136a1-ayam-2x8b-v1_reward/config.json
r136a1-ayam-2x8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/r136a1-ayam-2x8b-v1_reward/tokenizer_config.json
r136a1-ayam-2x8b-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/r136a1-ayam-2x8b-v1_reward/merges.txt
r136a1-ayam-2x8b-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/r136a1-ayam-2x8b-v1_reward/vocab.json
r136a1-ayam-2x8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/r136a1-ayam-2x8b-v1_reward/tokenizer.json
r136a1-ayam-2x8b-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/r136a1-ayam-2x8b-v1_reward/reward.tensors
Job r136a1-ayam-2x8b-v1-mkmlizer completed after 103.87s with status: succeeded
Stopping job with name r136a1-ayam-2x8b-v1-mkmlizer
Pipeline stage MKMLizer completed in 108.04s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service r136a1-ayam-2x8b-v1
Waiting for inference service r136a1-ayam-2x8b-v1 to be ready
Inference service r136a1-ayam-2x8b-v1 ready after 40.324111223220825s
Pipeline stage ISVCDeployer completed in 47.98s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.987136125564575s
Received healthy response to inference request in 2.017122745513916s
Received healthy response to inference request in 1.9979934692382812s
Received healthy response to inference request in 1.5476222038269043s
Received healthy response to inference request in 1.9442517757415771s
5 requests
0 failed requests
5th percentile: 1.6269481182098389
10th percentile: 1.7062740325927734
20th percentile: 1.8649258613586426
30th percentile: 1.955000114440918
40th percentile: 1.9764967918395997
50th percentile: 1.9979934692382812
60th percentile: 2.005645179748535
70th percentile: 2.013296890258789
80th percentile: 2.211125421524048
90th percentile: 2.5991307735443114
95th percentile: 2.793133449554443
99th percentile: 2.9483355903625488
mean time: 2.0988252639770506
Pipeline stage StressChecker completed in 11.10s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.06s
r136a1-ayam-2x8b_v1 status is now deployed due to DeploymentManager action
r136a1-ayam-2x8b_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of r136a1-ayam-2x8b_v1
Running pipeline stage ISVCDeleter
Checking if service r136a1-ayam-2x8b-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.12s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key r136a1-ayam-2x8b-v1/config.json from bucket guanaco-mkml-models
Deleting key r136a1-ayam-2x8b-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key r136a1-ayam-2x8b-v1/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key r136a1-ayam-2x8b-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key r136a1-ayam-2x8b-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key r136a1-ayam-2x8b-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key r136a1-ayam-2x8b-v1_reward/config.json from bucket guanaco-reward-models
Deleting key r136a1-ayam-2x8b-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key r136a1-ayam-2x8b-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key r136a1-ayam-2x8b-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key r136a1-ayam-2x8b-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key r136a1-ayam-2x8b-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key r136a1-ayam-2x8b-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.84s
r136a1-ayam-2x8b_v1 status is now torndown due to DeploymentManager action