developer_uid: v000000
submission_id: v000000-l3-8b-megaserpentine_v6
model_name: v000000-l3-8b-megaserpentine_v6
model_group: v000000/L3-8B-MegaSerpen
status: torndown
timestamp: 2024-06-18T08:41:28+00:00
num_battles: 29807
num_wins: 15835
celo_rating: 1212.28
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_v6
is_internal_developer: False
language_model: v000000/L3-8B-MegaSerpentine
model_size: 8B
ranking_group: single
us_pacific_date: 2024-06-18
win_ratio: 0.531251048411447
generation_params: {'temperature': 0.95, 'top_p': 0.95, 'min_p': 0.1, 'top_k': 80, 'presence_penalty': 0.1, '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-v6-mkmlizer
Waiting for job on v000000-l3-8b-megaserpentine-v6-mkmlizer to finish
v000000-l3-8b-megaserpentine-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
v000000-l3-8b-megaserpentine-v6-mkmlizer: ║     _____            __           __                                ║
v000000-l3-8b-megaserpentine-v6-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
v000000-l3-8b-megaserpentine-v6-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
v000000-l3-8b-megaserpentine-v6-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
v000000-l3-8b-megaserpentine-v6-mkmlizer: ║       /___/                                                         ║
v000000-l3-8b-megaserpentine-v6-mkmlizer: ║                                                                     ║
v000000-l3-8b-megaserpentine-v6-mkmlizer: ║  Version: 0.8.14                                                    ║
v000000-l3-8b-megaserpentine-v6-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
v000000-l3-8b-megaserpentine-v6-mkmlizer: ║  https://mk1.ai                                                     ║
v000000-l3-8b-megaserpentine-v6-mkmlizer: ║                                                                     ║
v000000-l3-8b-megaserpentine-v6-mkmlizer: ║  The license key for the current software has been verified as      ║
v000000-l3-8b-megaserpentine-v6-mkmlizer: ║  belonging to:                                                      ║
v000000-l3-8b-megaserpentine-v6-mkmlizer: ║                                                                     ║
v000000-l3-8b-megaserpentine-v6-mkmlizer: ║  Chai Research Corp.                                                ║
v000000-l3-8b-megaserpentine-v6-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
v000000-l3-8b-megaserpentine-v6-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
v000000-l3-8b-megaserpentine-v6-mkmlizer: ║                                                                     ║
v000000-l3-8b-megaserpentine-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
v000000-l3-8b-megaserpentine-v6-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-v6-mkmlizer:   warnings.warn(warning_message, FutureWarning)
v000000-l3-8b-megaserpentine-v6-mkmlizer: Downloaded to shared memory in 18.972s
v000000-l3-8b-megaserpentine-v6-mkmlizer: quantizing model to /dev/shm/model_cache
v000000-l3-8b-megaserpentine-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
v000000-l3-8b-megaserpentine-v6-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<01:04,  4.31it/s]
Loading 0:  11%|█▏        | 33/291 [00:04<00:22, 11.47it/s]
Loading 0:  18%|█▊        | 51/291 [00:04<00:11, 20.63it/s]
Loading 0:  22%|██▏       | 65/291 [00:05<00:09, 24.56it/s]
Loading 0:  27%|██▋       | 78/291 [00:05<00:06, 32.93it/s]
Loading 0:  33%|███▎      | 96/291 [00:05<00:04, 47.30it/s]
Loading 0:  38%|███▊      | 112/291 [00:05<00:02, 60.94it/s]
Loading 0:  43%|████▎     | 126/291 [00:05<00:02, 70.88it/s]
Loading 0:  48%|████▊     | 140/291 [00:05<00:01, 82.84it/s]
Loading 0:  54%|█████▍    | 157/291 [00:05<00:01, 100.12it/s]
Loading 0:  59%|█████▉    | 172/291 [00:06<00:01, 69.43it/s] 
Loading 0:  64%|██████▍   | 186/291 [00:06<00:01, 80.98it/s]
Loading 0:  70%|███████   | 204/291 [00:06<00:00, 98.73it/s]
Loading 0:  76%|███████▋  | 222/291 [00:06<00:00, 114.77it/s]
Loading 0:  82%|████████▏ | 240/291 [00:06<00:00, 127.82it/s]
Loading 0:  89%|████████▊ | 258/291 [00:06<00:00, 137.98it/s]
Loading 0:  94%|█████████▍| 274/291 [00:07<00:00, 87.85it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
v000000-l3-8b-megaserpentine-v6-mkmlizer: quantized model in 23.521s
v000000-l3-8b-megaserpentine-v6-mkmlizer: Processed model v000000/L3-8B-MegaSerpentine in 45.094s
v000000-l3-8b-megaserpentine-v6-mkmlizer: creating bucket guanaco-mkml-models
v000000-l3-8b-megaserpentine-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
v000000-l3-8b-megaserpentine-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/v000000-l3-8b-megaserpentine-v6
v000000-l3-8b-megaserpentine-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/v000000-l3-8b-megaserpentine-v6/config.json
v000000-l3-8b-megaserpentine-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/v000000-l3-8b-megaserpentine-v6/special_tokens_map.json
v000000-l3-8b-megaserpentine-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/v000000-l3-8b-megaserpentine-v6/tokenizer_config.json
v000000-l3-8b-megaserpentine-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/v000000-l3-8b-megaserpentine-v6/tokenizer.json
v000000-l3-8b-megaserpentine-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/v000000-l3-8b-megaserpentine-v6/flywheel_model.0.safetensors
v000000-l3-8b-megaserpentine-v6-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
v000000-l3-8b-megaserpentine-v6-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-v6-mkmlizer:   warnings.warn(
v000000-l3-8b-megaserpentine-v6-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-v6-mkmlizer:   warnings.warn(
v000000-l3-8b-megaserpentine-v6-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-v6-mkmlizer:   warnings.warn(
v000000-l3-8b-megaserpentine-v6-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-v6-mkmlizer:   return self.fget.__get__(instance, owner)()
v000000-l3-8b-megaserpentine-v6-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
v000000-l3-8b-megaserpentine-v6-mkmlizer: Saving duration: 0.396s
v000000-l3-8b-megaserpentine-v6-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.790s
v000000-l3-8b-megaserpentine-v6-mkmlizer: creating bucket guanaco-reward-models
v000000-l3-8b-megaserpentine-v6-mkmlizer: Bucket 's3://guanaco-reward-models/' created
v000000-l3-8b-megaserpentine-v6-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/v000000-l3-8b-megaserpentine-v6_reward
v000000-l3-8b-megaserpentine-v6-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/v000000-l3-8b-megaserpentine-v6_reward/config.json
v000000-l3-8b-megaserpentine-v6-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/v000000-l3-8b-megaserpentine-v6_reward/tokenizer_config.json
v000000-l3-8b-megaserpentine-v6-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/v000000-l3-8b-megaserpentine-v6_reward/special_tokens_map.json
v000000-l3-8b-megaserpentine-v6-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/v000000-l3-8b-megaserpentine-v6_reward/vocab.json
v000000-l3-8b-megaserpentine-v6-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/v000000-l3-8b-megaserpentine-v6_reward/merges.txt
v000000-l3-8b-megaserpentine-v6-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/v000000-l3-8b-megaserpentine-v6_reward/tokenizer.json
v000000-l3-8b-megaserpentine-v6-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/v000000-l3-8b-megaserpentine-v6_reward/reward.tensors
Job v000000-l3-8b-megaserpentine-v6-mkmlizer completed after 73.37s with status: succeeded
Stopping job with name v000000-l3-8b-megaserpentine-v6-mkmlizer
Pipeline stage MKMLizer completed in 77.47s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service v000000-l3-8b-megaserpentine-v6
Waiting for inference service v000000-l3-8b-megaserpentine-v6 to be ready
Inference service v000000-l3-8b-megaserpentine-v6 ready after 70.44223356246948s
Pipeline stage ISVCDeployer completed in 77.55s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2298948764801025s
Received healthy response to inference request in 1.4119036197662354s
Received healthy response to inference request in 1.3862049579620361s
Received healthy response to inference request in 1.3441789150238037s
Received healthy response to inference request in 1.4428739547729492s
5 requests
0 failed requests
5th percentile: 1.3525841236114502
10th percentile: 1.3609893321990967
20th percentile: 1.3777997493743896
30th percentile: 1.3913446903228759
40th percentile: 1.4016241550445556
50th percentile: 1.4119036197662354
60th percentile: 1.4242917537689208
70th percentile: 1.4366798877716065
80th percentile: 1.60027813911438
90th percentile: 1.9150865077972412
95th percentile: 2.072490692138672
99th percentile: 2.1984140396118166
mean time: 1.5630112648010255
Pipeline stage StressChecker completed in 8.40s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
v000000-l3-8b-megaserpentine_v6 status is now deployed due to DeploymentManager action
v000000-l3-8b-megaserpentine_v6 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of v000000-l3-8b-megaserpentine_v6
Running pipeline stage ISVCDeleter
Checking if service v000000-l3-8b-megaserpentine-v6 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.20s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key v000000-l3-8b-megaserpentine-v6/config.json from bucket guanaco-mkml-models
Deleting key v000000-l3-8b-megaserpentine-v6/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key v000000-l3-8b-megaserpentine-v6/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key v000000-l3-8b-megaserpentine-v6/tokenizer.json from bucket guanaco-mkml-models
Deleting key v000000-l3-8b-megaserpentine-v6/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key v000000-l3-8b-megaserpentine-v6_reward/config.json from bucket guanaco-reward-models
Deleting key v000000-l3-8b-megaserpentine-v6_reward/merges.txt from bucket guanaco-reward-models
Deleting key v000000-l3-8b-megaserpentine-v6_reward/reward.tensors from bucket guanaco-reward-models
Deleting key v000000-l3-8b-megaserpentine-v6_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key v000000-l3-8b-megaserpentine-v6_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key v000000-l3-8b-megaserpentine-v6_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key v000000-l3-8b-megaserpentine-v6_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.96s
v000000-l3-8b-megaserpentine_v6 status is now torndown due to DeploymentManager action