v000000-l3-8b-megaserpentine

developer_uid: v000000

submission_id: v000000-l3-8b-megaserpentine_v2

model_name: v000000-l3-8b-megaserpentine_v2

model_group: v000000/L3-8B-MegaSerpen

status: torndown

timestamp: 2024-06-18T07:31:01+00:00

num_battles: 23671

num_wins: 12002

celo_rating: 1203.79

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_v2

is_internal_developer: False

language_model: v000000/L3-8B-MegaSerpentine

model_size: 8B

ranking_group: single

us_pacific_date: 2024-06-18

win_ratio: 0.5070339233661443

generation_params: {'temperature': 1.22, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 85, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>', '{user_name}:', '<|end_of_text|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}

formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{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-v2-mkmlizer
Waiting for job on v000000-l3-8b-megaserpentine-v2-mkmlizer to finish
v000000-l3-8b-megaserpentine-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
v000000-l3-8b-megaserpentine-v2-mkmlizer: ║     _____            __           __                                ║
v000000-l3-8b-megaserpentine-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
v000000-l3-8b-megaserpentine-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
v000000-l3-8b-megaserpentine-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
v000000-l3-8b-megaserpentine-v2-mkmlizer: ║       /___/                                                         ║
v000000-l3-8b-megaserpentine-v2-mkmlizer: ║                                                                     ║
v000000-l3-8b-megaserpentine-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
v000000-l3-8b-megaserpentine-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
v000000-l3-8b-megaserpentine-v2-mkmlizer: ║  https://mk1.ai                                                     ║
v000000-l3-8b-megaserpentine-v2-mkmlizer: ║                                                                     ║
v000000-l3-8b-megaserpentine-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
v000000-l3-8b-megaserpentine-v2-mkmlizer: ║  belonging to:                                                      ║
v000000-l3-8b-megaserpentine-v2-mkmlizer: ║                                                                     ║
v000000-l3-8b-megaserpentine-v2-mkmlizer: ║  Chai Research Corp.                                                ║
v000000-l3-8b-megaserpentine-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
v000000-l3-8b-megaserpentine-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
v000000-l3-8b-megaserpentine-v2-mkmlizer: ║                                                                     ║
v000000-l3-8b-megaserpentine-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
v000000-l3-8b-megaserpentine-v2-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-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
v000000-l3-8b-megaserpentine-v2-mkmlizer: Downloaded to shared memory in 21.533s
v000000-l3-8b-megaserpentine-v2-mkmlizer: quantizing model to /dev/shm/model_cache
v000000-l3-8b-megaserpentine-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
v000000-l3-8b-megaserpentine-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<10:58,  2.28s/it]
Loading 0:   5%|▌         | 15/291 [00:04<01:03,  4.37it/s]
Loading 0:  11%|█▏        | 33/291 [00:04<00:22, 11.62it/s]
Loading 0:  18%|█▊        | 51/291 [00:04<00:11, 20.89it/s]
Loading 0:  22%|██▏       | 65/291 [00:05<00:09, 24.71it/s]
Loading 0:  26%|██▋       | 77/291 [00:05<00:06, 32.33it/s]
Loading 0:  32%|███▏      | 94/291 [00:05<00:04, 46.24it/s]
Loading 0:  38%|███▊      | 112/291 [00:05<00:02, 62.51it/s]
Loading 0:  45%|████▍     | 130/291 [00:05<00:02, 79.66it/s]
Loading 0:  51%|█████     | 148/291 [00:05<00:01, 96.49it/s]
Loading 0:  57%|█████▋    | 166/291 [00:06<00:01, 74.45it/s]
Loading 0:  63%|██████▎   | 184/291 [00:06<00:01, 89.36it/s]
Loading 0:  69%|██████▉   | 202/291 [00:06<00:00, 103.22it/s]
Loading 0:  76%|███████▌  | 220/291 [00:06<00:00, 116.03it/s]
Loading 0:  82%|████████▏ | 238/291 [00:06<00:00, 128.47it/s]
Loading 0:  88%|████████▊ | 256/291 [00:06<00:00, 138.11it/s]
Loading 0:  93%|█████████▎| 272/291 [00:07<00:00, 87.70it/s] 
Loading 0:  98%|█████████▊| 285/291 [00:07<00:00, 94.54it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
v000000-l3-8b-megaserpentine-v2-mkmlizer: quantized model in 23.095s
v000000-l3-8b-megaserpentine-v2-mkmlizer: Processed model v000000/L3-8B-MegaSerpentine in 47.204s
v000000-l3-8b-megaserpentine-v2-mkmlizer: creating bucket guanaco-mkml-models
v000000-l3-8b-megaserpentine-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
v000000-l3-8b-megaserpentine-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/v000000-l3-8b-megaserpentine-v2
v000000-l3-8b-megaserpentine-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/v000000-l3-8b-megaserpentine-v2/config.json
v000000-l3-8b-megaserpentine-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/v000000-l3-8b-megaserpentine-v2/tokenizer_config.json
v000000-l3-8b-megaserpentine-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/v000000-l3-8b-megaserpentine-v2/special_tokens_map.json
v000000-l3-8b-megaserpentine-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/v000000-l3-8b-megaserpentine-v2/tokenizer.json
v000000-l3-8b-megaserpentine-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/v000000-l3-8b-megaserpentine-v2/flywheel_model.0.safetensors
v000000-l3-8b-megaserpentine-v2-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-v2-mkmlizer:   warnings.warn(
v000000-l3-8b-megaserpentine-v2-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-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
v000000-l3-8b-megaserpentine-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
v000000-l3-8b-megaserpentine-v2-mkmlizer: Saving duration: 0.432s
v000000-l3-8b-megaserpentine-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.289s
v000000-l3-8b-megaserpentine-v2-mkmlizer: creating bucket guanaco-reward-models
v000000-l3-8b-megaserpentine-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
v000000-l3-8b-megaserpentine-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/v000000-l3-8b-megaserpentine-v2_reward
v000000-l3-8b-megaserpentine-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/v000000-l3-8b-megaserpentine-v2_reward/config.json
v000000-l3-8b-megaserpentine-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/v000000-l3-8b-megaserpentine-v2_reward/special_tokens_map.json
v000000-l3-8b-megaserpentine-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/v000000-l3-8b-megaserpentine-v2_reward/tokenizer_config.json
v000000-l3-8b-megaserpentine-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/v000000-l3-8b-megaserpentine-v2_reward/merges.txt
v000000-l3-8b-megaserpentine-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/v000000-l3-8b-megaserpentine-v2_reward/vocab.json
v000000-l3-8b-megaserpentine-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/v000000-l3-8b-megaserpentine-v2_reward/tokenizer.json
v000000-l3-8b-megaserpentine-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/v000000-l3-8b-megaserpentine-v2_reward/reward.tensors
Job v000000-l3-8b-megaserpentine-v2-mkmlizer completed after 72.55s with status: succeeded
Stopping job with name v000000-l3-8b-megaserpentine-v2-mkmlizer
Pipeline stage MKMLizer completed in 75.76s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service v000000-l3-8b-megaserpentine-v2
Waiting for inference service v000000-l3-8b-megaserpentine-v2 to be ready
Inference service v000000-l3-8b-megaserpentine-v2 ready after 50.33966398239136s
Pipeline stage ISVCDeployer completed in 57.29s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0636672973632812s
Received healthy response to inference request in 1.2845587730407715s
Received healthy response to inference request in 1.256612777709961s
Received healthy response to inference request in 1.2521708011627197s
Received healthy response to inference request in 1.2902376651763916s
5 requests
0 failed requests
5th percentile: 1.253059196472168
10th percentile: 1.2539475917816163
20th percentile: 1.2557243824005127
30th percentile: 1.262201976776123
40th percentile: 1.2733803749084474
50th percentile: 1.2845587730407715
60th percentile: 1.2868303298950194
70th percentile: 1.2891018867492676
80th percentile: 1.4449235916137697
90th percentile: 1.7542954444885255
95th percentile: 1.9089813709259031
99th percentile: 2.0327301120758055
mean time: 1.429449462890625
Pipeline stage StressChecker completed in 7.80s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
v000000-l3-8b-megaserpentine_v2 status is now deployed due to DeploymentManager action
v000000-l3-8b-megaserpentine_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of v000000-l3-8b-megaserpentine_v2
Running pipeline stage ISVCDeleter
Checking if service v000000-l3-8b-megaserpentine-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.53s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key v000000-l3-8b-megaserpentine-v2/config.json from bucket guanaco-mkml-models
Deleting key v000000-l3-8b-megaserpentine-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key v000000-l3-8b-megaserpentine-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key v000000-l3-8b-megaserpentine-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key v000000-l3-8b-megaserpentine-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key v000000-l3-8b-megaserpentine-v2_reward/config.json from bucket guanaco-reward-models
Deleting key v000000-l3-8b-megaserpentine-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key v000000-l3-8b-megaserpentine-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key v000000-l3-8b-megaserpentine-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key v000000-l3-8b-megaserpentine-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key v000000-l3-8b-megaserpentine-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key v000000-l3-8b-megaserpentine-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.81s
v000000-l3-8b-megaserpentine_v2 status is now torndown due to DeploymentManager action