developer_uid: R136a1
submission_id: r136a1-slerp8bv2_v2
model_name: r136a1-slerp8bv2_v1
model_group: R136a1/Slerp8Bv2
status: torndown
timestamp: 2024-06-25T12:25:32+00:00
num_battles: 307563
num_wins: 143689
celo_rating: 1210.11
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: 2024-06-25
win_ratio: 0.46718558474198785
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 40, '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-v2-mkmlizer
Waiting for job on r136a1-slerp8bv2-v2-mkmlizer to finish
Stopping job with name r136a1-slerp8bv2-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name r136a1-slerp8bv2-v2-mkmlizer
Waiting for job on r136a1-slerp8bv2-v2-mkmlizer to finish
r136a1-slerp8bv2-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
r136a1-slerp8bv2-v2-mkmlizer: ║     _____            __           __                                ║
r136a1-slerp8bv2-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
r136a1-slerp8bv2-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
r136a1-slerp8bv2-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
r136a1-slerp8bv2-v2-mkmlizer: ║       /___/                                                         ║
r136a1-slerp8bv2-v2-mkmlizer: ║                                                                     ║
r136a1-slerp8bv2-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
r136a1-slerp8bv2-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
r136a1-slerp8bv2-v2-mkmlizer: ║  https://mk1.ai                                                     ║
r136a1-slerp8bv2-v2-mkmlizer: ║                                                                     ║
r136a1-slerp8bv2-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
r136a1-slerp8bv2-v2-mkmlizer: ║  belonging to:                                                      ║
r136a1-slerp8bv2-v2-mkmlizer: ║                                                                     ║
r136a1-slerp8bv2-v2-mkmlizer: ║  Chai Research Corp.                                                ║
r136a1-slerp8bv2-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
r136a1-slerp8bv2-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
r136a1-slerp8bv2-v2-mkmlizer: ║                                                                     ║
r136a1-slerp8bv2-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
r136a1-slerp8bv2-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-slerp8bv2-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
Failed to get response for submission blend_hujok_2024-06-25: ('http://mistralai-mixtral-8x7b-3473-v46-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission blend_hujok_2024-06-25: ('http://mistralai-mixtral-8x7b-3473-v46-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission blend_hujok_2024-06-25: ('http://mistralai-mixtral-8x7b-3473-v46-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission blend_hujok_2024-06-25: ('http://mistralai-mixtral-8x7b-3473-v46-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
r136a1-slerp8bv2-v2-mkmlizer: Downloaded to shared memory in 21.366s
r136a1-slerp8bv2-v2-mkmlizer: quantizing model to /dev/shm/model_cache
r136a1-slerp8bv2-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission blend_hujok_2024-06-25: ('http://mistralai-mixtral-8x7b-3473-v46-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission blend_hujok_2024-06-25: ('http://mistralai-mixtral-8x7b-3473-v46-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission blend_tugeb_2024-06-25: ('http://mistralai-mixtral-8x7b-3473-v46-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
r136a1-slerp8bv2-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<10:08,  2.11s/it]
Loading 0:   5%|▌         | 15/291 [00:04<00:58,  4.71it/s]
Loading 0:  11%|█         | 32/291 [00:04<00:21, 12.07it/s]
Loading 0:  17%|█▋        | 49/291 [00:04<00:11, 21.48it/s]
Loading 0:  22%|██▏       | 63/291 [00:04<00:09, 24.57it/s]
Loading 0:  27%|██▋       | 78/291 [00:05<00:06, 34.75it/s]
Loading 0:  33%|███▎      | 96/291 [00:05<00:03, 49.53it/s]
Loading 0:  39%|███▉      | 114/291 [00:05<00:02, 65.62it/s]
Loading 0:  45%|████▌     | 132/291 [00:05<00:01, 82.14it/s]
Loading 0:  52%|█████▏    | 150/291 [00:05<00:01, 98.09it/s]
Loading 0:  57%|█████▋    | 166/291 [00:05<00:01, 68.87it/s]
Loading 0:  62%|██████▏   | 180/291 [00:05<00:01, 79.42it/s]
Loading 0:  67%|██████▋   | 195/291 [00:06<00:01, 89.92it/s]
Loading 0:  73%|███████▎  | 212/291 [00:06<00:00, 105.11it/s]
Loading 0:  79%|███████▊  | 229/291 [00:06<00:00, 118.06it/s]
Loading 0:  84%|████████▍ | 244/291 [00:06<00:00, 124.30it/s]
Loading 0:  89%|████████▉ | 259/291 [00:06<00:00, 127.23it/s]
Loading 0:  94%|█████████▍| 274/291 [00:06<00:00, 71.01it/s] 
Loading 0:  99%|█████████▉| 289/291 [00:07<00:00, 83.78it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
r136a1-slerp8bv2-v2-mkmlizer: quantized model in 19.276s
r136a1-slerp8bv2-v2-mkmlizer: Processed model R136a1/Slerp8Bv2 in 41.668s
r136a1-slerp8bv2-v2-mkmlizer: creating bucket guanaco-mkml-models
r136a1-slerp8bv2-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
r136a1-slerp8bv2-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/r136a1-slerp8bv2-v2
r136a1-slerp8bv2-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/r136a1-slerp8bv2-v2/config.json
r136a1-slerp8bv2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/r136a1-slerp8bv2-v2/tokenizer_config.json
r136a1-slerp8bv2-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/r136a1-slerp8bv2-v2/special_tokens_map.json
r136a1-slerp8bv2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/r136a1-slerp8bv2-v2/tokenizer.json
Failed to get response for submission blend_hujok_2024-06-25: ('http://mistralai-mixtral-8x7b-3473-v46-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
r136a1-slerp8bv2-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/r136a1-slerp8bv2-v2/flywheel_model.0.safetensors
r136a1-slerp8bv2-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
r136a1-slerp8bv2-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-slerp8bv2-v2-mkmlizer:   warnings.warn(
r136a1-slerp8bv2-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-slerp8bv2-v2-mkmlizer:   warnings.warn(
r136a1-slerp8bv2-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-slerp8bv2-v2-mkmlizer:   warnings.warn(
r136a1-slerp8bv2-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-slerp8bv2-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
r136a1-slerp8bv2-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
r136a1-slerp8bv2-v2-mkmlizer: Saving duration: 0.288s
r136a1-slerp8bv2-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.463s
r136a1-slerp8bv2-v2-mkmlizer: creating bucket guanaco-reward-models
Failed to get response for submission blend_tugeb_2024-06-25: ('http://mistralai-mixtral-8x7b-3473-v46-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
r136a1-slerp8bv2-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/r136a1-slerp8bv2-v2_reward/config.json
r136a1-slerp8bv2-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/r136a1-slerp8bv2-v2_reward/special_tokens_map.json
r136a1-slerp8bv2-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/r136a1-slerp8bv2-v2_reward/tokenizer_config.json
r136a1-slerp8bv2-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/r136a1-slerp8bv2-v2_reward/merges.txt
r136a1-slerp8bv2-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/r136a1-slerp8bv2-v2_reward/vocab.json
r136a1-slerp8bv2-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/r136a1-slerp8bv2-v2_reward/tokenizer.json
r136a1-slerp8bv2-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/r136a1-slerp8bv2-v2_reward/reward.tensors
Job r136a1-slerp8bv2-v2-mkmlizer completed after 74.65s with status: succeeded
Stopping job with name r136a1-slerp8bv2-v2-mkmlizer
Pipeline stage MKMLizer completed in 75.56s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service r136a1-slerp8bv2-v2
Failed to get response for submission blend_tugeb_2024-06-25: ('http://mistralai-mixtral-8x7b-3473-v46-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Waiting for inference service r136a1-slerp8bv2-v2 to be ready
Failed to get response for submission blend_tugeb_2024-06-25: ('http://mistralai-mixtral-8x7b-3473-v46-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission blend_tugeb_2024-06-25: ('http://mistralai-mixtral-8x7b-3473-v46-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission blend_tugeb_2024-06-25: ('http://mistralai-mixtral-8x7b-3473-v46-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission blend_hujok_2024-06-25: ('http://mistralai-mixtral-8x7b-3473-v46-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Inference service r136a1-slerp8bv2-v2 ready after 40.302507400512695s
Pipeline stage ISVCDeployer completed in 46.14s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3690643310546875s
Failed to get response for submission blend_tugeb_2024-06-25: ('http://mistralai-mixtral-8x7b-3473-v46-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission blend_hujok_2024-06-25: ('http://mistralai-mixtral-8x7b-3473-v46-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Received healthy response to inference request in 1.407578945159912s
Received healthy response to inference request in 1.3324580192565918s
Received healthy response to inference request in 1.3569965362548828s
Received healthy response to inference request in 1.2774922847747803s
5 requests
0 failed requests
5th percentile: 1.2884854316711425
10th percentile: 1.299478578567505
20th percentile: 1.3214648723602296
30th percentile: 1.33736572265625
40th percentile: 1.3471811294555665
50th percentile: 1.3569965362548828
60th percentile: 1.3772294998168946
70th percentile: 1.3974624633789063
80th percentile: 1.5998760223388673
90th percentile: 1.9844701766967774
95th percentile: 2.1767672538757323
99th percentile: 2.3306049156188964
mean time: 1.548718023300171
Pipeline stage StressChecker completed in 8.53s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.05s
r136a1-slerp8bv2_v2 status is now deployed due to DeploymentManager action
r136a1-slerp8bv2_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of r136a1-slerp8bv2_v2
Running pipeline stage ISVCDeleter
Checking if service r136a1-slerp8bv2-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.80s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key r136a1-slerp8bv2-v2/config.json from bucket guanaco-mkml-models
Deleting key r136a1-slerp8bv2-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key r136a1-slerp8bv2-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key r136a1-slerp8bv2-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key r136a1-slerp8bv2-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key r136a1-slerp8bv2-v2_reward/config.json from bucket guanaco-reward-models
Deleting key r136a1-slerp8bv2-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key r136a1-slerp8bv2-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key r136a1-slerp8bv2-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key r136a1-slerp8bv2-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key r136a1-slerp8bv2-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key r136a1-slerp8bv2-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.73s
r136a1-slerp8bv2_v2 status is now torndown due to DeploymentManager action