developer_uid: R136a1
submission_id: r136a1-slerp8bv1_v1
model_name: r136a1-slerp8bv1_v1
model_group: R136a1/Slerp8Bv1
status: torndown
timestamp: 2024-06-25T05:34:48+00:00
num_battles: 24124
num_wins: 13089
celo_rating: 1214.49
family_friendly_score: 0.0
submission_type: basic
model_repo: R136a1/Slerp8Bv1
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-slerp8bv1_v1
is_internal_developer: False
language_model: R136a1/Slerp8Bv1
model_size: 8B
ranking_group: single
us_pacific_date: 2024-06-24
win_ratio: 0.5425717128171116
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-slerp8bv1-v1-mkmlizer
Waiting for job on r136a1-slerp8bv1-v1-mkmlizer to finish
r136a1-slerp8bv1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
r136a1-slerp8bv1-v1-mkmlizer: ║     _____            __           __                                ║
r136a1-slerp8bv1-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
r136a1-slerp8bv1-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
r136a1-slerp8bv1-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
r136a1-slerp8bv1-v1-mkmlizer: ║       /___/                                                         ║
r136a1-slerp8bv1-v1-mkmlizer: ║                                                                     ║
r136a1-slerp8bv1-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
r136a1-slerp8bv1-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
r136a1-slerp8bv1-v1-mkmlizer: ║  https://mk1.ai                                                     ║
r136a1-slerp8bv1-v1-mkmlizer: ║                                                                     ║
r136a1-slerp8bv1-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
r136a1-slerp8bv1-v1-mkmlizer: ║  belonging to:                                                      ║
r136a1-slerp8bv1-v1-mkmlizer: ║                                                                     ║
r136a1-slerp8bv1-v1-mkmlizer: ║  Chai Research Corp.                                                ║
r136a1-slerp8bv1-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
r136a1-slerp8bv1-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
r136a1-slerp8bv1-v1-mkmlizer: ║                                                                     ║
r136a1-slerp8bv1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
r136a1-slerp8bv1-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-slerp8bv1-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
r136a1-slerp8bv1-v1-mkmlizer: Downloaded to shared memory in 29.761s
r136a1-slerp8bv1-v1-mkmlizer: quantizing model to /dev/shm/model_cache
r136a1-slerp8bv1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
r136a1-slerp8bv1-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:14,  2.33s/it]
Loading 0:   5%|▌         | 15/291 [00:04<01:04,  4.27it/s]
Loading 0:  11%|█▏        | 33/291 [00:04<00:22, 11.38it/s]
Loading 0:  18%|█▊        | 51/291 [00:04<00:11, 20.49it/s]
Loading 0:  22%|██▏       | 65/291 [00:05<00:09, 24.78it/s]
Loading 0:  27%|██▋       | 80/291 [00:05<00:06, 34.85it/s]
Loading 0:  33%|███▎      | 96/291 [00:05<00:04, 47.37it/s]
Loading 0:  39%|███▉      | 114/291 [00:05<00:02, 63.37it/s]
Loading 0:  45%|████▌     | 131/291 [00:05<00:02, 79.48it/s]
Loading 0:  51%|█████     | 149/291 [00:05<00:01, 95.50it/s]
Loading 0:  57%|█████▋    | 166/291 [00:06<00:01, 70.98it/s]
Loading 0:  63%|██████▎   | 184/291 [00:06<00:01, 86.71it/s]
Loading 0:  69%|██████▉   | 202/291 [00:06<00:00, 101.07it/s]
Loading 0:  76%|███████▌  | 220/291 [00:06<00:00, 114.52it/s]
Loading 0:  82%|████████▏ | 238/291 [00:06<00:00, 125.71it/s]
Loading 0:  88%|████████▊ | 256/291 [00:06<00:00, 136.41it/s]
Loading 0:  93%|█████████▎| 272/291 [00:07<00:00, 89.93it/s] 
Loading 0:  99%|█████████▉| 288/291 [00:07<00:00, 102.07it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
r136a1-slerp8bv1-v1-mkmlizer: quantized model in 23.527s
r136a1-slerp8bv1-v1-mkmlizer: Processed model R136a1/Slerp8Bv1 in 55.887s
r136a1-slerp8bv1-v1-mkmlizer: creating bucket guanaco-mkml-models
r136a1-slerp8bv1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
r136a1-slerp8bv1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/r136a1-slerp8bv1-v1
r136a1-slerp8bv1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/r136a1-slerp8bv1-v1/tokenizer_config.json
r136a1-slerp8bv1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/r136a1-slerp8bv1-v1/config.json
r136a1-slerp8bv1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/r136a1-slerp8bv1-v1/tokenizer.json
r136a1-slerp8bv1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/r136a1-slerp8bv1-v1/special_tokens_map.json
r136a1-slerp8bv1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/r136a1-slerp8bv1-v1/flywheel_model.0.safetensors
r136a1-slerp8bv1-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
r136a1-slerp8bv1-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-slerp8bv1-v1-mkmlizer:   warnings.warn(
r136a1-slerp8bv1-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-slerp8bv1-v1-mkmlizer:   warnings.warn(
r136a1-slerp8bv1-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-slerp8bv1-v1-mkmlizer:   warnings.warn(
r136a1-slerp8bv1-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-slerp8bv1-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
r136a1-slerp8bv1-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
r136a1-slerp8bv1-v1-mkmlizer: Saving duration: 0.454s
r136a1-slerp8bv1-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 8.190s
r136a1-slerp8bv1-v1-mkmlizer: creating bucket guanaco-reward-models
r136a1-slerp8bv1-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
r136a1-slerp8bv1-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/r136a1-slerp8bv1-v1_reward
r136a1-slerp8bv1-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/r136a1-slerp8bv1-v1_reward/config.json
r136a1-slerp8bv1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/r136a1-slerp8bv1-v1_reward/tokenizer_config.json
r136a1-slerp8bv1-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/r136a1-slerp8bv1-v1_reward/special_tokens_map.json
r136a1-slerp8bv1-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/r136a1-slerp8bv1-v1_reward/merges.txt
r136a1-slerp8bv1-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/r136a1-slerp8bv1-v1_reward/vocab.json
r136a1-slerp8bv1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/r136a1-slerp8bv1-v1_reward/tokenizer.json
r136a1-slerp8bv1-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/r136a1-slerp8bv1-v1_reward/reward.tensors
Job r136a1-slerp8bv1-v1-mkmlizer completed after 84.17s with status: succeeded
Stopping job with name r136a1-slerp8bv1-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.66s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Creating inference service r136a1-slerp8bv1-v1
Waiting for inference service r136a1-slerp8bv1-v1 to be ready
Inference service r136a1-slerp8bv1-v1 ready after 40.21167302131653s
Pipeline stage ISVCDeployer completed in 46.17s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2380447387695312s
Received healthy response to inference request in 1.350128412246704s
Received healthy response to inference request in 1.3464882373809814s
Received healthy response to inference request in 1.2873759269714355s
Received healthy response to inference request in 1.2457530498504639s
5 requests
0 failed requests
5th percentile: 1.2540776252746582
10th percentile: 1.2624022006988525
20th percentile: 1.2790513515472413
30th percentile: 1.2991983890533447
40th percentile: 1.322843313217163
50th percentile: 1.3464882373809814
60th percentile: 1.3479443073272706
70th percentile: 1.3494003772735597
80th percentile: 1.5277116775512698
90th percentile: 1.8828782081604005
95th percentile: 2.0604614734649656
99th percentile: 2.202528085708618
mean time: 1.4935580730438232
Pipeline stage StressChecker completed in 8.50s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.04s
r136a1-slerp8bv1_v1 status is now deployed due to DeploymentManager action
r136a1-slerp8bv1_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of r136a1-slerp8bv1_v1
Running pipeline stage ISVCDeleter
Checking if service r136a1-slerp8bv1-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.46s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key r136a1-slerp8bv1-v1/config.json from bucket guanaco-mkml-models
Deleting key r136a1-slerp8bv1-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key r136a1-slerp8bv1-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key r136a1-slerp8bv1-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key r136a1-slerp8bv1-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key r136a1-slerp8bv1-v1_reward/config.json from bucket guanaco-reward-models
Deleting key r136a1-slerp8bv1-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key r136a1-slerp8bv1-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key r136a1-slerp8bv1-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key r136a1-slerp8bv1-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key r136a1-slerp8bv1-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key r136a1-slerp8bv1-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.38s
r136a1-slerp8bv1_v1 status is now torndown due to DeploymentManager action