developer_uid: v000000
submission_id: v000000-l3-8b-megaserpentine_v3
model_name: v000000-l3-8b-megaserpentine_v3
model_group: v000000/L3-8B-MegaSerpen
status: torndown
timestamp: 2024-06-18T07:32:35+00:00
num_battles: 23282
num_wins: 12104
celo_rating: 1211.62
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_v3
is_internal_developer: False
language_model: v000000/L3-8B-MegaSerpentine
model_size: 8B
ranking_group: single
us_pacific_date: 2024-06-18
win_ratio: 0.5198866076797526
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-v3-mkmlizer
Waiting for job on v000000-l3-8b-megaserpentine-v3-mkmlizer to finish
v000000-l3-8b-megaserpentine-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
v000000-l3-8b-megaserpentine-v3-mkmlizer: ║     _____            __           __                                ║
v000000-l3-8b-megaserpentine-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
v000000-l3-8b-megaserpentine-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
v000000-l3-8b-megaserpentine-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
v000000-l3-8b-megaserpentine-v3-mkmlizer: ║       /___/                                                         ║
v000000-l3-8b-megaserpentine-v3-mkmlizer: ║                                                                     ║
v000000-l3-8b-megaserpentine-v3-mkmlizer: ║  Version: 0.8.14                                                    ║
v000000-l3-8b-megaserpentine-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
v000000-l3-8b-megaserpentine-v3-mkmlizer: ║  https://mk1.ai                                                     ║
v000000-l3-8b-megaserpentine-v3-mkmlizer: ║                                                                     ║
v000000-l3-8b-megaserpentine-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
v000000-l3-8b-megaserpentine-v3-mkmlizer: ║  belonging to:                                                      ║
v000000-l3-8b-megaserpentine-v3-mkmlizer: ║                                                                     ║
v000000-l3-8b-megaserpentine-v3-mkmlizer: ║  Chai Research Corp.                                                ║
v000000-l3-8b-megaserpentine-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
v000000-l3-8b-megaserpentine-v3-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
v000000-l3-8b-megaserpentine-v3-mkmlizer: ║                                                                     ║
v000000-l3-8b-megaserpentine-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
v000000-l3-8b-megaserpentine-v3-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-v3-mkmlizer:   warnings.warn(warning_message, FutureWarning)
v000000-l3-8b-megaserpentine-v3-mkmlizer: Downloaded to shared memory in 16.655s
v000000-l3-8b-megaserpentine-v3-mkmlizer: quantizing model to /dev/shm/model_cache
v000000-l3-8b-megaserpentine-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
v000000-l3-8b-megaserpentine-v3-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<10:51,  2.26s/it]
Loading 0:   4%|▍         | 13/291 [00:04<01:13,  3.80it/s]
Loading 0:  11%|█         | 31/291 [00:04<00:23, 11.11it/s]
Loading 0:  16%|█▌        | 46/291 [00:04<00:12, 18.89it/s]
Loading 0:  21%|██        | 60/291 [00:05<00:10, 22.82it/s]
Loading 0:  26%|██▋       | 77/291 [00:05<00:06, 34.56it/s]
Loading 0:  33%|███▎      | 95/291 [00:05<00:04, 48.80it/s]
Loading 0:  39%|███▉      | 113/291 [00:05<00:02, 64.60it/s]
Loading 0:  45%|████▌     | 131/291 [00:05<00:01, 81.22it/s]
Loading 0:  51%|█████     | 149/291 [00:05<00:01, 97.44it/s]
Loading 0:  57%|█████▋    | 166/291 [00:06<00:01, 74.82it/s]
Loading 0:  63%|██████▎   | 184/291 [00:06<00:01, 89.55it/s]
Loading 0:  69%|██████▊   | 200/291 [00:06<00:00, 102.24it/s]
Loading 0:  74%|███████▍  | 216/291 [00:06<00:00, 113.62it/s]
Loading 0:  79%|███████▉  | 231/291 [00:06<00:00, 120.07it/s]
Loading 0:  86%|████████▌ | 249/291 [00:06<00:00, 131.25it/s]
Loading 0:  91%|█████████▏| 266/291 [00:06<00:00, 87.93it/s] 
Loading 0:  98%|█████████▊| 284/291 [00:07<00:00, 103.82it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
v000000-l3-8b-megaserpentine-v3-mkmlizer: quantized model in 22.995s
v000000-l3-8b-megaserpentine-v3-mkmlizer: Processed model v000000/L3-8B-MegaSerpentine in 42.221s
v000000-l3-8b-megaserpentine-v3-mkmlizer: creating bucket guanaco-mkml-models
v000000-l3-8b-megaserpentine-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
v000000-l3-8b-megaserpentine-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/v000000-l3-8b-megaserpentine-v3
v000000-l3-8b-megaserpentine-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/v000000-l3-8b-megaserpentine-v3/tokenizer_config.json
v000000-l3-8b-megaserpentine-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/v000000-l3-8b-megaserpentine-v3/special_tokens_map.json
v000000-l3-8b-megaserpentine-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/v000000-l3-8b-megaserpentine-v3/config.json
v000000-l3-8b-megaserpentine-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/v000000-l3-8b-megaserpentine-v3/tokenizer.json
v000000-l3-8b-megaserpentine-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/v000000-l3-8b-megaserpentine-v3/flywheel_model.0.safetensors
v000000-l3-8b-megaserpentine-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
v000000-l3-8b-megaserpentine-v3-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-v3-mkmlizer:   warnings.warn(
v000000-l3-8b-megaserpentine-v3-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-v3-mkmlizer:   warnings.warn(
v000000-l3-8b-megaserpentine-v3-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-v3-mkmlizer:   warnings.warn(
v000000-l3-8b-megaserpentine-v3-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-v3-mkmlizer:   return self.fget.__get__(instance, owner)()
v000000-l3-8b-megaserpentine-v3-mkmlizer: Saving duration: 0.439s
v000000-l3-8b-megaserpentine-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.277s
v000000-l3-8b-megaserpentine-v3-mkmlizer: creating bucket guanaco-reward-models
v000000-l3-8b-megaserpentine-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
v000000-l3-8b-megaserpentine-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/v000000-l3-8b-megaserpentine-v3_reward
v000000-l3-8b-megaserpentine-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/v000000-l3-8b-megaserpentine-v3_reward/tokenizer_config.json
v000000-l3-8b-megaserpentine-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/v000000-l3-8b-megaserpentine-v3_reward/merges.txt
v000000-l3-8b-megaserpentine-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/v000000-l3-8b-megaserpentine-v3_reward/config.json
v000000-l3-8b-megaserpentine-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/v000000-l3-8b-megaserpentine-v3_reward/vocab.json
v000000-l3-8b-megaserpentine-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/v000000-l3-8b-megaserpentine-v3_reward/special_tokens_map.json
v000000-l3-8b-megaserpentine-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/v000000-l3-8b-megaserpentine-v3_reward/tokenizer.json
v000000-l3-8b-megaserpentine-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/v000000-l3-8b-megaserpentine-v3_reward/reward.tensors
Job v000000-l3-8b-megaserpentine-v3-mkmlizer completed after 73.0s with status: succeeded
Stopping job with name v000000-l3-8b-megaserpentine-v3-mkmlizer
Pipeline stage MKMLizer completed in 76.42s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service v000000-l3-8b-megaserpentine-v3
Waiting for inference service v000000-l3-8b-megaserpentine-v3 to be ready
Inference service v000000-l3-8b-megaserpentine-v3 ready after 40.335331201553345s
Pipeline stage ISVCDeployer completed in 47.15s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2351880073547363s
Received healthy response to inference request in 1.3938441276550293s
%s, retrying in %s seconds...
Received healthy response to inference request in 1.306816577911377s
Received healthy response to inference request in 1.3503432273864746s
Received healthy response to inference request in 1.3245375156402588s
Received healthy response to inference request in 1.3038418292999268s
Received healthy response to inference request in 1.3570575714111328s
5 requests
0 failed requests
5th percentile: 1.3044367790222169
10th percentile: 1.3050317287445068
20th percentile: 1.3062216281890868
30th percentile: 1.3103607654571534
40th percentile: 1.317449140548706
50th percentile: 1.3245375156402588
60th percentile: 1.334859800338745
70th percentile: 1.3451820850372314
80th percentile: 1.3516860961914063
90th percentile: 1.3543718338012696
95th percentile: 1.355714702606201
99th percentile: 1.3567889976501464
mean time: 1.328519344329834
Pipeline stage StressChecker completed in 31.04s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
v000000-l3-8b-megaserpentine_v3 status is now deployed due to DeploymentManager action
v000000-l3-8b-megaserpentine_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of v000000-l3-8b-megaserpentine_v3
Running pipeline stage ISVCDeleter
Checking if service v000000-l3-8b-megaserpentine-v3 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.76s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key v000000-l3-8b-megaserpentine-v3/config.json from bucket guanaco-mkml-models
Deleting key v000000-l3-8b-megaserpentine-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key v000000-l3-8b-megaserpentine-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key v000000-l3-8b-megaserpentine-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key v000000-l3-8b-megaserpentine-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key v000000-l3-8b-megaserpentine-v3_reward/config.json from bucket guanaco-reward-models
Deleting key v000000-l3-8b-megaserpentine-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key v000000-l3-8b-megaserpentine-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key v000000-l3-8b-megaserpentine-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key v000000-l3-8b-megaserpentine-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key v000000-l3-8b-megaserpentine-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key v000000-l3-8b-megaserpentine-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.73s
v000000-l3-8b-megaserpentine_v3 status is now torndown due to DeploymentManager action