trace2333-pippa-llama2-v0

developer_uid: Trace2333
submission_id: trace2333-pippa-llama2-v0_v6
model_name: trace2333-pippa-llama2-v0_v5
model_group: Trace2333/pippa_llama2_v
status: torndown
timestamp: 2024-06-13T03:13:08+00:00
num_battles: 27926
num_wins: 10948
celo_rating: 1106.75
family_friendly_score: 0.0
submission_type: basic
model_repo: Trace2333/pippa_llama2_v0
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 6738415616.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: trace2333-pippa-llama2-v0_v5
is_internal_developer: False
language_model: Trace2333/pippa_llama2_v0
model_size: 7B
ranking_group: single
us_pacific_date: 2024-06-12
win_ratio: 0.3920360953949724
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': 'You: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
model_eval_status: success
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 trace2333-pippa-llama2-v0-v6-mkmlizer
Waiting for job on trace2333-pippa-llama2-v0-v6-mkmlizer to finish
trace2333-pippa-llama2-v0-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-pippa-llama2-v0-v6-mkmlizer: ║     _____            __           __                                ║
trace2333-pippa-llama2-v0-v6-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-pippa-llama2-v0-v6-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-pippa-llama2-v0-v6-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-pippa-llama2-v0-v6-mkmlizer: ║       /___/                                                         ║
trace2333-pippa-llama2-v0-v6-mkmlizer: ║                                                                     ║
trace2333-pippa-llama2-v0-v6-mkmlizer: ║  Version: 0.8.14                                                    ║
trace2333-pippa-llama2-v0-v6-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-pippa-llama2-v0-v6-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-pippa-llama2-v0-v6-mkmlizer: ║                                                                     ║
trace2333-pippa-llama2-v0-v6-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-pippa-llama2-v0-v6-mkmlizer: ║  belonging to:                                                      ║
trace2333-pippa-llama2-v0-v6-mkmlizer: ║                                                                     ║
trace2333-pippa-llama2-v0-v6-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-pippa-llama2-v0-v6-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-pippa-llama2-v0-v6-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
trace2333-pippa-llama2-v0-v6-mkmlizer: ║                                                                     ║
trace2333-pippa-llama2-v0-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-pippa-llama2-v0-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.
trace2333-pippa-llama2-v0-v6-mkmlizer:   warnings.warn(warning_message, FutureWarning)
trace2333-pippa-llama2-v0-v6-mkmlizer: Downloaded to shared memory in 58.866s
trace2333-pippa-llama2-v0-v6-mkmlizer: quantizing model to /dev/shm/model_cache
trace2333-pippa-llama2-v0-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-pippa-llama2-v0-v6-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   3%|▎         | 9/291 [00:00<00:03, 85.91it/s]
Loading 0:   6%|▌         | 18/291 [00:00<00:03, 85.17it/s]
Loading 0:   9%|▉         | 27/291 [00:00<00:03, 85.05it/s]
Loading 0:  12%|█▏        | 36/291 [00:00<00:02, 85.23it/s]
Loading 0:  15%|█▌        | 45/291 [00:00<00:02, 84.98it/s]
Loading 0:  19%|█▊        | 54/291 [00:00<00:05, 41.79it/s]
Loading 0:  23%|██▎       | 66/291 [00:01<00:04, 54.74it/s]
Loading 0:  25%|██▌       | 74/291 [00:01<00:03, 59.84it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:03, 66.42it/s]
Loading 0:  32%|███▏      | 92/291 [00:01<00:02, 71.38it/s]
Loading 0:  35%|███▍      | 101/291 [00:01<00:02, 75.24it/s]
Loading 0:  38%|███▊      | 110/291 [00:01<00:03, 46.33it/s]
Loading 0:  41%|████      | 118/291 [00:01<00:03, 52.38it/s]
Loading 0:  44%|████▎     | 127/291 [00:02<00:02, 59.68it/s]
Loading 0:  47%|████▋     | 136/291 [00:02<00:02, 66.01it/s]
Loading 0:  50%|████▉     | 145/291 [00:02<00:02, 71.60it/s]
Loading 0:  53%|█████▎    | 154/291 [00:02<00:01, 76.28it/s]
Loading 0:  56%|█████▌    | 163/291 [00:02<00:02, 46.46it/s]
Loading 0:  59%|█████▉    | 172/291 [00:02<00:02, 54.18it/s]
Loading 0:  62%|██████▏   | 181/291 [00:02<00:01, 60.80it/s]
Loading 0:  65%|██████▌   | 190/291 [00:03<00:01, 66.78it/s]
Loading 0:  68%|██████▊   | 199/291 [00:03<00:01, 71.80it/s]
Loading 0:  71%|███████▏  | 208/291 [00:03<00:01, 75.53it/s]
Loading 0:  75%|███████▍  | 217/291 [00:03<00:01, 46.24it/s]
Loading 0:  78%|███████▊  | 226/291 [00:03<00:01, 53.75it/s]
Loading 0:  81%|████████  | 235/291 [00:03<00:00, 60.64it/s]
Loading 0:  84%|████████▍ | 244/291 [00:03<00:00, 66.49it/s]
Loading 0:  87%|████████▋ | 253/291 [00:04<00:00, 70.98it/s]
Loading 0:  90%|█████████ | 262/291 [00:04<00:00, 75.48it/s]
Loading 0:  93%|█████████▎| 271/291 [00:05<00:01, 14.93it/s]
Loading 0:  97%|█████████▋| 281/291 [00:05<00:00, 20.56it/s]
Loading 0: 100%|█████████▉| 290/291 [00:06<00:00, 26.55it/s]
                                                            
You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
trace2333-pippa-llama2-v0-v6-mkmlizer: quantized model in 15.789s
trace2333-pippa-llama2-v0-v6-mkmlizer: Processed model Trace2333/pippa_llama2_v0 in 79.218s
trace2333-pippa-llama2-v0-v6-mkmlizer: creating bucket guanaco-mkml-models
trace2333-pippa-llama2-v0-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-pippa-llama2-v0-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-pippa-llama2-v0-v6
trace2333-pippa-llama2-v0-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-pippa-llama2-v0-v6/special_tokens_map.json
trace2333-pippa-llama2-v0-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-pippa-llama2-v0-v6/tokenizer_config.json
trace2333-pippa-llama2-v0-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-pippa-llama2-v0-v6/config.json
trace2333-pippa-llama2-v0-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-pippa-llama2-v0-v6/tokenizer.json
trace2333-pippa-llama2-v0-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/trace2333-pippa-llama2-v0-v6/tokenizer.model
trace2333-pippa-llama2-v0-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-pippa-llama2-v0-v6/flywheel_model.0.safetensors
trace2333-pippa-llama2-v0-v6-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
trace2333-pippa-llama2-v0-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.
trace2333-pippa-llama2-v0-v6-mkmlizer:   warnings.warn(
trace2333-pippa-llama2-v0-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.
trace2333-pippa-llama2-v0-v6-mkmlizer:   warnings.warn(
trace2333-pippa-llama2-v0-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.
trace2333-pippa-llama2-v0-v6-mkmlizer:   warnings.warn(
trace2333-pippa-llama2-v0-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()
trace2333-pippa-llama2-v0-v6-mkmlizer:   return self.fget.__get__(instance, owner)()
trace2333-pippa-llama2-v0-v6-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
trace2333-pippa-llama2-v0-v6-mkmlizer: Saving duration: 0.439s
trace2333-pippa-llama2-v0-v6-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.920s
trace2333-pippa-llama2-v0-v6-mkmlizer: creating bucket guanaco-reward-models
trace2333-pippa-llama2-v0-v6-mkmlizer: Bucket 's3://guanaco-reward-models/' created
trace2333-pippa-llama2-v0-v6-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/trace2333-pippa-llama2-v0-v6_reward
trace2333-pippa-llama2-v0-v6-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/trace2333-pippa-llama2-v0-v6_reward/config.json
trace2333-pippa-llama2-v0-v6-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/trace2333-pippa-llama2-v0-v6_reward/special_tokens_map.json
trace2333-pippa-llama2-v0-v6-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/trace2333-pippa-llama2-v0-v6_reward/merges.txt
trace2333-pippa-llama2-v0-v6-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/trace2333-pippa-llama2-v0-v6_reward/tokenizer_config.json
trace2333-pippa-llama2-v0-v6-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/trace2333-pippa-llama2-v0-v6_reward/vocab.json
trace2333-pippa-llama2-v0-v6-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/trace2333-pippa-llama2-v0-v6_reward/tokenizer.json
trace2333-pippa-llama2-v0-v6-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/trace2333-pippa-llama2-v0-v6_reward/reward.tensors
Job trace2333-pippa-llama2-v0-v6-mkmlizer completed after 103.5s with status: succeeded
Stopping job with name trace2333-pippa-llama2-v0-v6-mkmlizer
Pipeline stage MKMLizer completed in 104.23s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-pippa-llama2-v0-v6
Waiting for inference service trace2333-pippa-llama2-v0-v6 to be ready
Inference service trace2333-pippa-llama2-v0-v6 ready after 30.16825580596924s
Pipeline stage ISVCDeployer completed in 36.01s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.764704704284668s
Received healthy response to inference request in 0.6927919387817383s
Received healthy response to inference request in 0.9941785335540771s
Received healthy response to inference request in 0.5591864585876465s
Received healthy response to inference request in 0.9799985885620117s
5 requests
0 failed requests
5th percentile: 0.5859075546264648
10th percentile: 0.6126286506652832
20th percentile: 0.6660708427429199
30th percentile: 0.750233268737793
40th percentile: 0.8651159286499024
50th percentile: 0.9799985885620117
60th percentile: 0.9856705665588379
70th percentile: 0.9913425445556641
80th percentile: 1.1482837677001954
90th percentile: 1.4564942359924318
95th percentile: 1.6105994701385498
99th percentile: 1.7338836574554444
mean time: 0.9981720447540283
Pipeline stage StressChecker completed in 5.63s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.03s
M-Eval Dataset for topic stay_in_character is loaded
trace2333-pippa-llama2-v0_v6 status is now deployed due to DeploymentManager action
trace2333-pippa-llama2-v0_v6 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of trace2333-pippa-llama2-v0_v6
Running pipeline stage ISVCDeleter
Checking if service trace2333-pippa-llama2-v0-v6 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.21s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key trace2333-pippa-llama2-v0-v6/config.json from bucket guanaco-mkml-models
Deleting key trace2333-pippa-llama2-v0-v6/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key trace2333-pippa-llama2-v0-v6/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key trace2333-pippa-llama2-v0-v6/tokenizer.json from bucket guanaco-mkml-models
Deleting key trace2333-pippa-llama2-v0-v6/tokenizer.model from bucket guanaco-mkml-models
Deleting key trace2333-pippa-llama2-v0-v6/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key trace2333-pippa-llama2-v0-v6_reward/config.json from bucket guanaco-reward-models
Deleting key trace2333-pippa-llama2-v0-v6_reward/merges.txt from bucket guanaco-reward-models
Deleting key trace2333-pippa-llama2-v0-v6_reward/reward.tensors from bucket guanaco-reward-models
Deleting key trace2333-pippa-llama2-v0-v6_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key trace2333-pippa-llama2-v0-v6_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key trace2333-pippa-llama2-v0-v6_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key trace2333-pippa-llama2-v0-v6_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.13s
trace2333-pippa-llama2-v0_v6 status is now torndown due to DeploymentManager action