developer_uid: v000000
submission_id: v000000-l3-8b-megaserpentine_v5
model_name: v000000-l3-8b-megaserpentine_v5
model_group: v000000/L3-8B-MegaSerpen
status: torndown
timestamp: 2024-06-18T07:45:42+00:00
num_battles: 19919
num_wins: 10363
celo_rating: 1212.38
family_friendly_score: 0.0
submission_type: basic
model_repo: v000000/L3-8B-MegaSerpentine
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: v000000-l3-8b-megaserpentine_v5
is_internal_developer: False
language_model: v000000/L3-8B-MegaSerpentine
model_size: 8B
ranking_group: single
us_pacific_date: 2024-06-18
win_ratio: 0.5202570410161153
generation_params: {'temperature': 1.3, 'top_p': 0.95, 'min_p': 0.08, 'top_k': 80, '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': "<|begin_of_text|><|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 v000000-l3-8b-megaserpentine-v5-mkmlizer
Waiting for job on v000000-l3-8b-megaserpentine-v5-mkmlizer to finish
v000000-l3-8b-megaserpentine-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
v000000-l3-8b-megaserpentine-v5-mkmlizer: ║     _____            __           __                                ║
v000000-l3-8b-megaserpentine-v5-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
v000000-l3-8b-megaserpentine-v5-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
v000000-l3-8b-megaserpentine-v5-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
v000000-l3-8b-megaserpentine-v5-mkmlizer: ║       /___/                                                         ║
v000000-l3-8b-megaserpentine-v5-mkmlizer: ║                                                                     ║
v000000-l3-8b-megaserpentine-v5-mkmlizer: ║  Version: 0.8.14                                                    ║
v000000-l3-8b-megaserpentine-v5-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
v000000-l3-8b-megaserpentine-v5-mkmlizer: ║  https://mk1.ai                                                     ║
v000000-l3-8b-megaserpentine-v5-mkmlizer: ║                                                                     ║
v000000-l3-8b-megaserpentine-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
v000000-l3-8b-megaserpentine-v5-mkmlizer: ║  belonging to:                                                      ║
v000000-l3-8b-megaserpentine-v5-mkmlizer: ║                                                                     ║
v000000-l3-8b-megaserpentine-v5-mkmlizer: ║  Chai Research Corp.                                                ║
v000000-l3-8b-megaserpentine-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
v000000-l3-8b-megaserpentine-v5-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
v000000-l3-8b-megaserpentine-v5-mkmlizer: ║                                                                     ║
v000000-l3-8b-megaserpentine-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
v000000-l3-8b-megaserpentine-v5-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.
v000000-l3-8b-megaserpentine-v5-mkmlizer:   warnings.warn(warning_message, FutureWarning)
v000000-l3-8b-megaserpentine-v5-mkmlizer: Downloaded to shared memory in 15.468s
v000000-l3-8b-megaserpentine-v5-mkmlizer: quantizing model to /dev/shm/model_cache
v000000-l3-8b-megaserpentine-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
v000000-l3-8b-megaserpentine-v5-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:07,  2.31s/it]
Loading 0:   5%|▌         | 15/291 [00:04<01:03,  4.32it/s]
Loading 0:  11%|█▏        | 33/291 [00:04<00:22, 11.46it/s]
Loading 0:  18%|█▊        | 51/291 [00:04<00:11, 20.61it/s]
Loading 0:  22%|██▏       | 65/291 [00:05<00:09, 24.56it/s]
Loading 0:  27%|██▋       | 78/291 [00:05<00:06, 32.83it/s]
Loading 0:  33%|███▎      | 96/291 [00:05<00:04, 47.17it/s]
Loading 0:  39%|███▉      | 114/291 [00:05<00:02, 62.85it/s]
Loading 0:  45%|████▌     | 132/291 [00:05<00:02, 78.90it/s]
Loading 0:  51%|█████     | 149/291 [00:05<00:01, 94.38it/s]
Loading 0:  57%|█████▋    | 166/291 [00:06<00:01, 70.29it/s]
Loading 0:  62%|██████▏   | 181/291 [00:06<00:01, 82.43it/s]
Loading 0:  67%|██████▋   | 195/291 [00:06<00:01, 92.58it/s]
Loading 0:  73%|███████▎  | 213/291 [00:06<00:00, 107.77it/s]
Loading 0:  79%|███████▉  | 231/291 [00:06<00:00, 120.80it/s]
Loading 0:  86%|████████▌ | 249/291 [00:06<00:00, 130.66it/s]
Loading 0:  91%|█████████▏| 266/291 [00:07<00:00, 86.41it/s] 
Loading 0:  97%|█████████▋| 283/291 [00:07<00:00, 101.11it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
v000000-l3-8b-megaserpentine-v5-mkmlizer: quantized model in 23.552s
v000000-l3-8b-megaserpentine-v5-mkmlizer: Processed model v000000/L3-8B-MegaSerpentine in 41.711s
v000000-l3-8b-megaserpentine-v5-mkmlizer: creating bucket guanaco-mkml-models
v000000-l3-8b-megaserpentine-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
v000000-l3-8b-megaserpentine-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/v000000-l3-8b-megaserpentine-v5
v000000-l3-8b-megaserpentine-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/v000000-l3-8b-megaserpentine-v5/special_tokens_map.json
v000000-l3-8b-megaserpentine-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/v000000-l3-8b-megaserpentine-v5/tokenizer_config.json
v000000-l3-8b-megaserpentine-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/v000000-l3-8b-megaserpentine-v5/config.json
v000000-l3-8b-megaserpentine-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/v000000-l3-8b-megaserpentine-v5/tokenizer.json
v000000-l3-8b-megaserpentine-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/v000000-l3-8b-megaserpentine-v5/flywheel_model.0.safetensors
v000000-l3-8b-megaserpentine-v5-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
v000000-l3-8b-megaserpentine-v5-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.
v000000-l3-8b-megaserpentine-v5-mkmlizer:   warnings.warn(
v000000-l3-8b-megaserpentine-v5-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.
v000000-l3-8b-megaserpentine-v5-mkmlizer:   warnings.warn(
v000000-l3-8b-megaserpentine-v5-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.
v000000-l3-8b-megaserpentine-v5-mkmlizer:   warnings.warn(
v000000-l3-8b-megaserpentine-v5-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()
v000000-l3-8b-megaserpentine-v5-mkmlizer:   return self.fget.__get__(instance, owner)()
v000000-l3-8b-megaserpentine-v5-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
v000000-l3-8b-megaserpentine-v5-mkmlizer: Saving duration: 0.428s
v000000-l3-8b-megaserpentine-v5-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.049s
v000000-l3-8b-megaserpentine-v5-mkmlizer: creating bucket guanaco-reward-models
v000000-l3-8b-megaserpentine-v5-mkmlizer: Bucket 's3://guanaco-reward-models/' created
v000000-l3-8b-megaserpentine-v5-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/v000000-l3-8b-megaserpentine-v5_reward
v000000-l3-8b-megaserpentine-v5-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/v000000-l3-8b-megaserpentine-v5_reward/tokenizer_config.json
v000000-l3-8b-megaserpentine-v5-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/v000000-l3-8b-megaserpentine-v5_reward/config.json
v000000-l3-8b-megaserpentine-v5-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/v000000-l3-8b-megaserpentine-v5_reward/special_tokens_map.json
v000000-l3-8b-megaserpentine-v5-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/v000000-l3-8b-megaserpentine-v5_reward/merges.txt
v000000-l3-8b-megaserpentine-v5-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/v000000-l3-8b-megaserpentine-v5_reward/vocab.json
v000000-l3-8b-megaserpentine-v5-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/v000000-l3-8b-megaserpentine-v5_reward/tokenizer.json
v000000-l3-8b-megaserpentine-v5-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/v000000-l3-8b-megaserpentine-v5_reward/reward.tensors
Job v000000-l3-8b-megaserpentine-v5-mkmlizer completed after 72.86s with status: succeeded
Stopping job with name v000000-l3-8b-megaserpentine-v5-mkmlizer
Pipeline stage MKMLizer completed in 76.44s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service v000000-l3-8b-megaserpentine-v5
Waiting for inference service v000000-l3-8b-megaserpentine-v5 to be ready
Inference service v000000-l3-8b-megaserpentine-v5 ready after 90.426593542099s
Pipeline stage ISVCDeployer completed in 97.77s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1748876571655273s
Received healthy response to inference request in 1.3313827514648438s
Received healthy response to inference request in 1.3069896697998047s
Received healthy response to inference request in 1.2925810813903809s
Received healthy response to inference request in 1.338174819946289s
5 requests
0 failed requests
5th percentile: 1.2954627990722656
10th percentile: 1.2983445167541503
20th percentile: 1.30410795211792
30th percentile: 1.3118682861328126
40th percentile: 1.3216255187988282
50th percentile: 1.3313827514648438
60th percentile: 1.334099578857422
70th percentile: 1.33681640625
80th percentile: 1.5055173873901369
90th percentile: 1.8402025222778322
95th percentile: 2.0075450897216793
99th percentile: 2.1414191436767576
mean time: 1.4888031959533692
Pipeline stage StressChecker completed in 8.20s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
v000000-l3-8b-megaserpentine_v5 status is now deployed due to DeploymentManager action
v000000-l3-8b-megaserpentine_v5 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of v000000-l3-8b-megaserpentine_v5
Running pipeline stage ISVCDeleter
Checking if service v000000-l3-8b-megaserpentine-v5 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.65s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key v000000-l3-8b-megaserpentine-v5/config.json from bucket guanaco-mkml-models
Deleting key v000000-l3-8b-megaserpentine-v5/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key v000000-l3-8b-megaserpentine-v5/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key v000000-l3-8b-megaserpentine-v5/tokenizer.json from bucket guanaco-mkml-models
Deleting key v000000-l3-8b-megaserpentine-v5/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key v000000-l3-8b-megaserpentine-v5_reward/config.json from bucket guanaco-reward-models
Deleting key v000000-l3-8b-megaserpentine-v5_reward/merges.txt from bucket guanaco-reward-models
Deleting key v000000-l3-8b-megaserpentine-v5_reward/reward.tensors from bucket guanaco-reward-models
Deleting key v000000-l3-8b-megaserpentine-v5_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key v000000-l3-8b-megaserpentine-v5_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key v000000-l3-8b-megaserpentine-v5_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key v000000-l3-8b-megaserpentine-v5_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.83s
v000000-l3-8b-megaserpentine_v5 status is now torndown due to DeploymentManager action