developer_uid: R136a1
submission_id: r136a1-slerp8bv2_v1
model_name: r136a1-slerp8bv2_v1
model_group: R136a1/Slerp8Bv2
status: torndown
timestamp: 2024-06-25T05:36:16+00:00
num_battles: 25749
num_wins: 14125
celo_rating: 1220.51
family_friendly_score: 0.0
submission_type: basic
model_repo: R136a1/Slerp8Bv2
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: r136a1-slerp8bv2_v1
is_internal_developer: False
language_model: R136a1/Slerp8Bv2
model_size: 8B
ranking_group: single
us_pacific_date: 2024-06-24
win_ratio: 0.548564992815255
generation_params: {'temperature': 1.15, 'top_p': 1.0, 'min_p': 0.075, 'top_k': 70, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|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 r136a1-slerp8bv2-v1-mkmlizer
Waiting for job on r136a1-slerp8bv2-v1-mkmlizer to finish
r136a1-slerp8bv2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
r136a1-slerp8bv2-v1-mkmlizer: ║     _____            __           __                                ║
r136a1-slerp8bv2-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
r136a1-slerp8bv2-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
r136a1-slerp8bv2-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
r136a1-slerp8bv2-v1-mkmlizer: ║       /___/                                                         ║
r136a1-slerp8bv2-v1-mkmlizer: ║                                                                     ║
r136a1-slerp8bv2-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
r136a1-slerp8bv2-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
r136a1-slerp8bv2-v1-mkmlizer: ║  https://mk1.ai                                                     ║
r136a1-slerp8bv2-v1-mkmlizer: ║                                                                     ║
r136a1-slerp8bv2-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
r136a1-slerp8bv2-v1-mkmlizer: ║  belonging to:                                                      ║
r136a1-slerp8bv2-v1-mkmlizer: ║                                                                     ║
r136a1-slerp8bv2-v1-mkmlizer: ║  Chai Research Corp.                                                ║
r136a1-slerp8bv2-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
r136a1-slerp8bv2-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
r136a1-slerp8bv2-v1-mkmlizer: ║                                                                     ║
r136a1-slerp8bv2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
r136a1-slerp8bv2-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-slerp8bv2-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
r136a1-slerp8bv2-v1-mkmlizer: Downloaded to shared memory in 34.129s
r136a1-slerp8bv2-v1-mkmlizer: quantizing model to /dev/shm/model_cache
r136a1-slerp8bv2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
r136a1-slerp8bv2-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:24,  2.37s/it]
Loading 0:   5%|▌         | 16/291 [00:04<01:01,  4.51it/s]
Loading 0:  11%|█▏        | 33/291 [00:04<00:23, 11.12it/s]
Loading 0:  18%|█▊        | 51/291 [00:05<00:11, 20.16it/s]
Loading 0:  22%|██▏       | 65/291 [00:05<00:09, 24.57it/s]
Loading 0:  27%|██▋       | 78/291 [00:05<00:06, 33.01it/s]
Loading 0:  33%|███▎      | 96/291 [00:05<00:04, 47.55it/s]
Loading 0:  39%|███▉      | 114/291 [00:05<00:02, 63.65it/s]
Loading 0:  45%|████▌     | 132/291 [00:05<00:01, 80.31it/s]
Loading 0:  52%|█████▏    | 150/291 [00:05<00:01, 96.62it/s]
Loading 0:  57%|█████▋    | 166/291 [00:06<00:01, 73.28it/s]
Loading 0:  63%|██████▎   | 184/291 [00:06<00:01, 88.79it/s]
Loading 0:  69%|██████▉   | 202/291 [00:06<00:00, 104.23it/s]
Loading 0:  76%|███████▌  | 220/291 [00:06<00:00, 118.58it/s]
Loading 0:  82%|████████▏ | 238/291 [00:06<00:00, 131.22it/s]
Loading 0:  88%|████████▊ | 256/291 [00:06<00:00, 140.15it/s]
Loading 0:  94%|█████████▍| 273/291 [00:07<00:00, 92.37it/s] 
Loading 0:  98%|█████████▊| 286/291 [00:07<00:00, 92.77it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
r136a1-slerp8bv2-v1-mkmlizer: quantized model in 23.694s
r136a1-slerp8bv2-v1-mkmlizer: Processed model R136a1/Slerp8Bv2 in 60.417s
r136a1-slerp8bv2-v1-mkmlizer: creating bucket guanaco-mkml-models
r136a1-slerp8bv2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
r136a1-slerp8bv2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/r136a1-slerp8bv2-v1
r136a1-slerp8bv2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/r136a1-slerp8bv2-v1/special_tokens_map.json
r136a1-slerp8bv2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/r136a1-slerp8bv2-v1/tokenizer_config.json
r136a1-slerp8bv2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/r136a1-slerp8bv2-v1/config.json
r136a1-slerp8bv2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/r136a1-slerp8bv2-v1/tokenizer.json
r136a1-slerp8bv2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/r136a1-slerp8bv2-v1/flywheel_model.0.safetensors
r136a1-slerp8bv2-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
r136a1-slerp8bv2-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-slerp8bv2-v1-mkmlizer:   warnings.warn(
r136a1-slerp8bv2-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-slerp8bv2-v1-mkmlizer:   warnings.warn(
r136a1-slerp8bv2-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.
r136a1-slerp8bv2-v1-mkmlizer:   warnings.warn(
r136a1-slerp8bv2-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-slerp8bv2-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
r136a1-slerp8bv2-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
r136a1-slerp8bv2-v1-mkmlizer: Saving duration: 0.438s
r136a1-slerp8bv2-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.005s
r136a1-slerp8bv2-v1-mkmlizer: creating bucket guanaco-reward-models
r136a1-slerp8bv2-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
r136a1-slerp8bv2-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/r136a1-slerp8bv2-v1_reward
r136a1-slerp8bv2-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/r136a1-slerp8bv2-v1_reward/config.json
r136a1-slerp8bv2-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/r136a1-slerp8bv2-v1_reward/special_tokens_map.json
r136a1-slerp8bv2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/r136a1-slerp8bv2-v1_reward/tokenizer_config.json
r136a1-slerp8bv2-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/r136a1-slerp8bv2-v1_reward/vocab.json
r136a1-slerp8bv2-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/r136a1-slerp8bv2-v1_reward/merges.txt
r136a1-slerp8bv2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/r136a1-slerp8bv2-v1_reward/tokenizer.json
r136a1-slerp8bv2-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/r136a1-slerp8bv2-v1_reward/reward.tensors
Job r136a1-slerp8bv2-v1-mkmlizer completed after 83.52s with status: succeeded
Stopping job with name r136a1-slerp8bv2-v1-mkmlizer
Pipeline stage MKMLizer completed in 83.89s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service r136a1-slerp8bv2-v1
Waiting for inference service r136a1-slerp8bv2-v1 to be ready
Inference service r136a1-slerp8bv2-v1 ready after 40.28091359138489s
Pipeline stage ISVCDeployer completed in 45.93s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1768791675567627s
Received healthy response to inference request in 1.3493728637695312s
Received healthy response to inference request in 1.3480024337768555s
Received healthy response to inference request in 1.2837448120117188s
Received healthy response to inference request in 1.24774169921875s
5 requests
0 failed requests
5th percentile: 1.2549423217773437
10th percentile: 1.2621429443359375
20th percentile: 1.276544189453125
30th percentile: 1.2965963363647461
40th percentile: 1.3222993850708007
50th percentile: 1.3480024337768555
60th percentile: 1.3485506057739258
70th percentile: 1.3490987777709962
80th percentile: 1.5148741245269777
90th percentile: 1.8458766460418703
95th percentile: 2.011377906799316
99th percentile: 2.1437789154052735
mean time: 1.4811481952667236
Pipeline stage StressChecker completed in 8.10s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.04s
r136a1-slerp8bv2_v1 status is now deployed due to DeploymentManager action
r136a1-slerp8bv2_v1 status is now inactive due to auto deactivation removed underperforming models
r136a1-slerp8bv2_v1 status is now deployed due to admin request
r136a1-slerp8bv2_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of r136a1-slerp8bv2_v1
Running pipeline stage ISVCDeleter
Checking if service r136a1-slerp8bv2-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.82s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key r136a1-slerp8bv2-v1/config.json from bucket guanaco-mkml-models
Deleting key r136a1-slerp8bv2-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key r136a1-slerp8bv2-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key r136a1-slerp8bv2-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key r136a1-slerp8bv2-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key r136a1-slerp8bv2-v1_reward/config.json from bucket guanaco-reward-models
Deleting key r136a1-slerp8bv2-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key r136a1-slerp8bv2-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key r136a1-slerp8bv2-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key r136a1-slerp8bv2-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key r136a1-slerp8bv2-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key r136a1-slerp8bv2-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.38s
r136a1-slerp8bv2_v1 status is now torndown due to DeploymentManager action