v000000-l3-8b-blueserpentine

developer_uid: v000000

submission_id: v000000-l3-8b-blueserpentine_v2

model_name: v000000-l3-8b-blueserpentine_v2

model_group: v000000/L3-8B-BlueSerpen

status: torndown

timestamp: 2024-06-13T01:43:24+00:00

num_battles: 35372

num_wins: 19282

celo_rating: 1211.84

family_friendly_score: 0.0

submission_type: basic

model_repo: v000000/L3-8B-BlueSerpentine

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-blueserpentine_v2

is_internal_developer: False

language_model: v000000/L3-8B-BlueSerpentine

model_size: 8B

ranking_group: single

us_pacific_date: 2024-06-12

win_ratio: 0.5451204342417731

generation_params: {'temperature': 1.22, 'top_p': 0.95, 'min_p': 0.08, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_of_text|>', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}

formatter: {'memory_template': "<|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'}

model_eval_status: success

Resubmit model

Running pipeline stage MKMLizer
Starting job with name v000000-l3-8b-blueserpentine-v2-mkmlizer
Waiting for job on v000000-l3-8b-blueserpentine-v2-mkmlizer to finish
Failed to get response for submission blend_junes_2024-06-13: name 'requests' is not defined
v000000-l3-8b-blueserpentine-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
v000000-l3-8b-blueserpentine-v2-mkmlizer: ║     _____            __           __                                ║
v000000-l3-8b-blueserpentine-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
v000000-l3-8b-blueserpentine-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
v000000-l3-8b-blueserpentine-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
v000000-l3-8b-blueserpentine-v2-mkmlizer: ║       /___/                                                         ║
v000000-l3-8b-blueserpentine-v2-mkmlizer: ║                                                                     ║
v000000-l3-8b-blueserpentine-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
v000000-l3-8b-blueserpentine-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
v000000-l3-8b-blueserpentine-v2-mkmlizer: ║  https://mk1.ai                                                     ║
v000000-l3-8b-blueserpentine-v2-mkmlizer: ║                                                                     ║
v000000-l3-8b-blueserpentine-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
v000000-l3-8b-blueserpentine-v2-mkmlizer: ║  belonging to:                                                      ║
v000000-l3-8b-blueserpentine-v2-mkmlizer: ║                                                                     ║
v000000-l3-8b-blueserpentine-v2-mkmlizer: ║  Chai Research Corp.                                                ║
v000000-l3-8b-blueserpentine-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
v000000-l3-8b-blueserpentine-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
v000000-l3-8b-blueserpentine-v2-mkmlizer: ║                                                                     ║
v000000-l3-8b-blueserpentine-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
v000000-l3-8b-blueserpentine-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-blueserpentine-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
v000000-l3-8b-blueserpentine-v2-mkmlizer: Downloaded to shared memory in 14.986s
v000000-l3-8b-blueserpentine-v2-mkmlizer: quantizing model to /dev/shm/model_cache
v000000-l3-8b-blueserpentine-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
v000000-l3-8b-blueserpentine-v2-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%|▍         | 14/291 [00:04<01:07,  4.10it/s]
Loading 0:   9%|▉         | 27/291 [00:04<00:28,  9.38it/s]
Loading 0:  14%|█▍        | 41/291 [00:04<00:15, 16.58it/s]
Loading 0:  19%|█▊        | 54/291 [00:04<00:09, 24.93it/s]
Loading 0:  23%|██▎       | 66/291 [00:05<00:08, 25.46it/s]
Loading 0:  26%|██▋       | 77/291 [00:05<00:06, 32.94it/s]
Loading 0:  31%|███▏      | 91/291 [00:05<00:04, 45.10it/s]
Loading 0:  36%|███▌      | 104/291 [00:05<00:03, 56.37it/s]
Loading 0:  41%|████      | 118/291 [00:05<00:02, 69.81it/s]
Loading 0:  45%|████▌     | 131/291 [00:05<00:02, 79.53it/s]
Loading 0:  50%|████▉     | 145/291 [00:06<00:01, 91.22it/s]
Loading 0:  54%|█████▍    | 158/291 [00:06<00:01, 97.51it/s]
Loading 0:  58%|█████▊    | 170/291 [00:06<00:02, 58.63it/s]
Loading 0:  63%|██████▎   | 184/291 [00:06<00:01, 71.63it/s]
Loading 0:  67%|██████▋   | 195/291 [00:06<00:01, 76.98it/s]
Loading 0:  73%|███████▎  | 211/291 [00:06<00:00, 92.03it/s]
Loading 0:  77%|███████▋  | 223/291 [00:07<00:00, 95.61it/s]
Loading 0:  82%|████████▏ | 238/291 [00:07<00:00, 107.39it/s]
Loading 0:  86%|████████▋ | 251/291 [00:07<00:00, 108.53it/s]
Loading 0:  91%|█████████ | 265/291 [00:07<00:00, 115.57it/s]
Loading 0:  96%|█████████▌| 278/291 [00:07<00:00, 64.14it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
v000000-l3-8b-blueserpentine-v2-mkmlizer: quantized model in 19.376s
v000000-l3-8b-blueserpentine-v2-mkmlizer: Processed model v000000/L3-8B-BlueSerpentine in 35.473s
v000000-l3-8b-blueserpentine-v2-mkmlizer: creating bucket guanaco-mkml-models
v000000-l3-8b-blueserpentine-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
v000000-l3-8b-blueserpentine-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/v000000-l3-8b-blueserpentine-v2
v000000-l3-8b-blueserpentine-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/v000000-l3-8b-blueserpentine-v2/config.json
v000000-l3-8b-blueserpentine-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/v000000-l3-8b-blueserpentine-v2/tokenizer_config.json
v000000-l3-8b-blueserpentine-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/v000000-l3-8b-blueserpentine-v2/special_tokens_map.json
v000000-l3-8b-blueserpentine-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/v000000-l3-8b-blueserpentine-v2/tokenizer.json
v000000-l3-8b-blueserpentine-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/v000000-l3-8b-blueserpentine-v2/flywheel_model.0.safetensors
v000000-l3-8b-blueserpentine-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
v000000-l3-8b-blueserpentine-v2-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-blueserpentine-v2-mkmlizer:   warnings.warn(
v000000-l3-8b-blueserpentine-v2-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-blueserpentine-v2-mkmlizer:   warnings.warn(
v000000-l3-8b-blueserpentine-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-blueserpentine-v2-mkmlizer:   warnings.warn(
v000000-l3-8b-blueserpentine-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-blueserpentine-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
v000000-l3-8b-blueserpentine-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
v000000-l3-8b-blueserpentine-v2-mkmlizer: Saving duration: 0.242s
v000000-l3-8b-blueserpentine-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.565s
v000000-l3-8b-blueserpentine-v2-mkmlizer: creating bucket guanaco-reward-models
v000000-l3-8b-blueserpentine-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
v000000-l3-8b-blueserpentine-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/v000000-l3-8b-blueserpentine-v2_reward
v000000-l3-8b-blueserpentine-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/v000000-l3-8b-blueserpentine-v2_reward/config.json
v000000-l3-8b-blueserpentine-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/v000000-l3-8b-blueserpentine-v2_reward/special_tokens_map.json
v000000-l3-8b-blueserpentine-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/v000000-l3-8b-blueserpentine-v2_reward/tokenizer_config.json
v000000-l3-8b-blueserpentine-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/v000000-l3-8b-blueserpentine-v2_reward/merges.txt
v000000-l3-8b-blueserpentine-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/v000000-l3-8b-blueserpentine-v2_reward/vocab.json
v000000-l3-8b-blueserpentine-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/v000000-l3-8b-blueserpentine-v2_reward/tokenizer.json
v000000-l3-8b-blueserpentine-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/v000000-l3-8b-blueserpentine-v2_reward/reward.tensors
Job v000000-l3-8b-blueserpentine-v2-mkmlizer completed after 62.85s with status: succeeded
Stopping job with name v000000-l3-8b-blueserpentine-v2-mkmlizer
Pipeline stage MKMLizer completed in 63.69s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service v000000-l3-8b-blueserpentine-v2
Waiting for inference service v000000-l3-8b-blueserpentine-v2 to be ready
Inference service v000000-l3-8b-blueserpentine-v2 ready after 40.30658531188965s
Pipeline stage ISVCDeployer completed in 46.18s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.280599594116211s
Received healthy response to inference request in 1.360440969467163s
Received healthy response to inference request in 1.347458839416504s
Received healthy response to inference request in 1.2950434684753418s
Received healthy response to inference request in 1.2558255195617676s
5 requests
0 failed requests
5th percentile: 1.2636691093444825
10th percentile: 1.2715126991271972
Failed to get response for submission blend_junes_2024-06-13: name 'requests' is not defined
20th percentile: 1.2871998786926269
30th percentile: 1.3055265426635743
40th percentile: 1.326492691040039
50th percentile: 1.347458839416504
60th percentile: 1.3526516914367677
70th percentile: 1.3578445434570312
80th percentile: 1.5444726943969729
90th percentile: 1.9125361442565918
95th percentile: 2.0965678691864014
99th percentile: 2.243793249130249
mean time: 1.5078736782073974
Pipeline stage StressChecker completed in 8.20s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
v000000-l3-8b-blueserpentine_v2 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
v000000-l3-8b-blueserpentine_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of v000000-l3-8b-blueserpentine_v2
Running pipeline stage ISVCDeleter
Checking if service v000000-l3-8b-blueserpentine-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.12s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key v000000-l3-8b-blueserpentine-v2/config.json from bucket guanaco-mkml-models
Deleting key v000000-l3-8b-blueserpentine-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key v000000-l3-8b-blueserpentine-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key v000000-l3-8b-blueserpentine-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key v000000-l3-8b-blueserpentine-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key v000000-l3-8b-blueserpentine-v2_reward/config.json from bucket guanaco-reward-models
Deleting key v000000-l3-8b-blueserpentine-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key v000000-l3-8b-blueserpentine-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key v000000-l3-8b-blueserpentine-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key v000000-l3-8b-blueserpentine-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key v000000-l3-8b-blueserpentine-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key v000000-l3-8b-blueserpentine-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.06s
v000000-l3-8b-blueserpentine_v2 status is now torndown due to DeploymentManager action