developer_uid: v000000
submission_id: v000000-l3-8b-megaserpentine_v7
model_name: v000000-l3-8b-megaserpentine_v7
model_group: v000000/L3-8B-MegaSerpen
status: torndown
timestamp: 2024-06-18T10:19:56+00:00
num_battles: 31717
num_wins: 17885
celo_rating: 1214.17
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_v7
is_internal_developer: False
language_model: v000000/L3-8B-MegaSerpentine
model_size: 8B
ranking_group: single
us_pacific_date: 2024-06-18
win_ratio: 0.5638931803133966
generation_params: {'temperature': 1.1, 'top_p': 0.73, 'min_p': 0.11, 'top_k': 190, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>', '<|end_of_text|>', '{user_name}:'], '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-v7-mkmlizer
Waiting for job on v000000-l3-8b-megaserpentine-v7-mkmlizer to finish
v000000-l3-8b-megaserpentine-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
v000000-l3-8b-megaserpentine-v7-mkmlizer: ║     _____            __           __                                ║
v000000-l3-8b-megaserpentine-v7-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
v000000-l3-8b-megaserpentine-v7-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
v000000-l3-8b-megaserpentine-v7-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
v000000-l3-8b-megaserpentine-v7-mkmlizer: ║       /___/                                                         ║
v000000-l3-8b-megaserpentine-v7-mkmlizer: ║                                                                     ║
v000000-l3-8b-megaserpentine-v7-mkmlizer: ║  Version: 0.8.14                                                    ║
v000000-l3-8b-megaserpentine-v7-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
v000000-l3-8b-megaserpentine-v7-mkmlizer: ║  https://mk1.ai                                                     ║
v000000-l3-8b-megaserpentine-v7-mkmlizer: ║                                                                     ║
v000000-l3-8b-megaserpentine-v7-mkmlizer: ║  The license key for the current software has been verified as      ║
v000000-l3-8b-megaserpentine-v7-mkmlizer: ║  belonging to:                                                      ║
v000000-l3-8b-megaserpentine-v7-mkmlizer: ║                                                                     ║
v000000-l3-8b-megaserpentine-v7-mkmlizer: ║  Chai Research Corp.                                                ║
v000000-l3-8b-megaserpentine-v7-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
v000000-l3-8b-megaserpentine-v7-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
v000000-l3-8b-megaserpentine-v7-mkmlizer: ║                                                                     ║
v000000-l3-8b-megaserpentine-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
v000000-l3-8b-megaserpentine-v7-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-v7-mkmlizer:   warnings.warn(warning_message, FutureWarning)
v000000-l3-8b-megaserpentine-v7-mkmlizer: Downloaded to shared memory in 17.716s
v000000-l3-8b-megaserpentine-v7-mkmlizer: quantizing model to /dev/shm/model_cache
v000000-l3-8b-megaserpentine-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
v000000-l3-8b-megaserpentine-v7-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<10:51,  2.25s/it]
Loading 0:   5%|▌         | 15/291 [00:04<01:02,  4.42it/s]
Loading 0:  11%|█▏        | 33/291 [00:04<00:21, 11.75it/s]
Loading 0:  18%|█▊        | 51/291 [00:04<00:11, 21.13it/s]
Loading 0:  22%|██▏       | 65/291 [00:05<00:09, 25.10it/s]
Loading 0:  27%|██▋       | 78/291 [00:05<00:06, 33.61it/s]
Loading 0:  33%|███▎      | 96/291 [00:05<00:04, 48.37it/s]
Loading 0:  39%|███▉      | 114/291 [00:05<00:02, 64.22it/s]
Loading 0:  45%|████▌     | 132/291 [00:05<00:01, 80.53it/s]
Loading 0:  52%|█████▏    | 150/291 [00:05<00:01, 96.87it/s]
Loading 0:  57%|█████▋    | 166/291 [00:06<00:01, 74.15it/s]
Loading 0:  63%|██████▎   | 184/291 [00:06<00:01, 90.02it/s]
Loading 0:  69%|██████▉   | 202/291 [00:06<00:00, 104.81it/s]
Loading 0:  76%|███████▌  | 220/291 [00:06<00:00, 118.05it/s]
Loading 0:  81%|████████  | 236/291 [00:06<00:00, 127.25it/s]
Loading 0:  87%|████████▋ | 252/291 [00:06<00:00, 133.47it/s]
Loading 0:  92%|█████████▏| 268/291 [00:06<00:00, 85.17it/s] 
Loading 0:  98%|█████████▊| 285/291 [00:07<00:00, 98.87it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
v000000-l3-8b-megaserpentine-v7-mkmlizer: quantized model in 23.301s
v000000-l3-8b-megaserpentine-v7-mkmlizer: Processed model v000000/L3-8B-MegaSerpentine in 43.626s
v000000-l3-8b-megaserpentine-v7-mkmlizer: creating bucket guanaco-mkml-models
v000000-l3-8b-megaserpentine-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
v000000-l3-8b-megaserpentine-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/v000000-l3-8b-megaserpentine-v7
v000000-l3-8b-megaserpentine-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/v000000-l3-8b-megaserpentine-v7/tokenizer_config.json
v000000-l3-8b-megaserpentine-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/v000000-l3-8b-megaserpentine-v7/config.json
v000000-l3-8b-megaserpentine-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/v000000-l3-8b-megaserpentine-v7/special_tokens_map.json
v000000-l3-8b-megaserpentine-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/v000000-l3-8b-megaserpentine-v7/tokenizer.json
v000000-l3-8b-megaserpentine-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/v000000-l3-8b-megaserpentine-v7/flywheel_model.0.safetensors
v000000-l3-8b-megaserpentine-v7-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
v000000-l3-8b-megaserpentine-v7-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-v7-mkmlizer:   warnings.warn(
v000000-l3-8b-megaserpentine-v7-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-v7-mkmlizer:   warnings.warn(
v000000-l3-8b-megaserpentine-v7-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-v7-mkmlizer:   warnings.warn(
v000000-l3-8b-megaserpentine-v7-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-v7-mkmlizer:   return self.fget.__get__(instance, owner)()
v000000-l3-8b-megaserpentine-v7-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
v000000-l3-8b-megaserpentine-v7-mkmlizer: Saving duration: 0.415s
v000000-l3-8b-megaserpentine-v7-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.175s
v000000-l3-8b-megaserpentine-v7-mkmlizer: creating bucket guanaco-reward-models
v000000-l3-8b-megaserpentine-v7-mkmlizer: Bucket 's3://guanaco-reward-models/' created
v000000-l3-8b-megaserpentine-v7-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/v000000-l3-8b-megaserpentine-v7_reward
v000000-l3-8b-megaserpentine-v7-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/v000000-l3-8b-megaserpentine-v7_reward/config.json
v000000-l3-8b-megaserpentine-v7-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/v000000-l3-8b-megaserpentine-v7_reward/tokenizer_config.json
v000000-l3-8b-megaserpentine-v7-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/v000000-l3-8b-megaserpentine-v7_reward/merges.txt
v000000-l3-8b-megaserpentine-v7-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/v000000-l3-8b-megaserpentine-v7_reward/vocab.json
v000000-l3-8b-megaserpentine-v7-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/v000000-l3-8b-megaserpentine-v7_reward/special_tokens_map.json
v000000-l3-8b-megaserpentine-v7-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/v000000-l3-8b-megaserpentine-v7_reward/tokenizer.json
v000000-l3-8b-megaserpentine-v7-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/v000000-l3-8b-megaserpentine-v7_reward/reward.tensors
Job v000000-l3-8b-megaserpentine-v7-mkmlizer completed after 63.52s with status: succeeded
Stopping job with name v000000-l3-8b-megaserpentine-v7-mkmlizer
Pipeline stage MKMLizer completed in 76.23s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service v000000-l3-8b-megaserpentine-v7
Waiting for inference service v000000-l3-8b-megaserpentine-v7 to be ready
Inference service v000000-l3-8b-megaserpentine-v7 ready after 40.321024656295776s
Pipeline stage ISVCDeployer completed in 46.18s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.185500144958496s
Received healthy response to inference request in 1.3555891513824463s
Received healthy response to inference request in 1.3324739933013916s
Received healthy response to inference request in 1.3112592697143555s
Received healthy response to inference request in 1.3902599811553955s
5 requests
0 failed requests
5th percentile: 1.3155022144317627
10th percentile: 1.31974515914917
20th percentile: 1.3282310485839843
30th percentile: 1.3370970249176026
40th percentile: 1.3463430881500245
50th percentile: 1.3555891513824463
60th percentile: 1.369457483291626
70th percentile: 1.3833258152008057
80th percentile: 1.5493080139160158
90th percentile: 1.867404079437256
95th percentile: 2.026452112197876
99th percentile: 2.153690538406372
mean time: 1.515016508102417
Pipeline stage StressChecker completed in 8.19s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
v000000-l3-8b-megaserpentine_v7 status is now deployed due to DeploymentManager action
v000000-l3-8b-megaserpentine_v7 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of v000000-l3-8b-megaserpentine_v7
Running pipeline stage ISVCDeleter
Checking if service v000000-l3-8b-megaserpentine-v7 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.63s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key v000000-l3-8b-megaserpentine-v7/config.json from bucket guanaco-mkml-models
Deleting key v000000-l3-8b-megaserpentine-v7/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key v000000-l3-8b-megaserpentine-v7/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key v000000-l3-8b-megaserpentine-v7/tokenizer.json from bucket guanaco-mkml-models
Deleting key v000000-l3-8b-megaserpentine-v7/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key v000000-l3-8b-megaserpentine-v7_reward/config.json from bucket guanaco-reward-models
Deleting key v000000-l3-8b-megaserpentine-v7_reward/merges.txt from bucket guanaco-reward-models
Deleting key v000000-l3-8b-megaserpentine-v7_reward/reward.tensors from bucket guanaco-reward-models
Deleting key v000000-l3-8b-megaserpentine-v7_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key v000000-l3-8b-megaserpentine-v7_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key v000000-l3-8b-megaserpentine-v7_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key v000000-l3-8b-megaserpentine-v7_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.36s
v000000-l3-8b-megaserpentine_v7 status is now torndown due to DeploymentManager action