trace2333-pippa-llama2-v0

submission_id: trace2333-pippa-llama2-v0_v2

developer_uid: Trace2333

best_of: 4

display_name: trace2333-pippa-llama2-v0_v2

family_friendly_score: 0.0

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}

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}

ineligible_reason: model is not deployable

is_internal_developer: False

language_model: Trace2333/pippa_llama2_v0

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_eval_status: error

model_group: Trace2333/pippa_llama2_v

model_name: trace2333-pippa-llama2-v0_v2

model_num_parameters: 6738415616.0

model_repo: Trace2333/pippa_llama2_v0

model_size: 7B

num_battles: 550

num_wins: 195

ranking_group: single

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'}

reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2

status: rejected

submission_type: basic

timestamp: 2024-06-12T04:15:13+00:00

us_pacific_date: 2024-06-11

win_ratio: 0.35454545454545455

Resubmit model

Running pipeline stage MKMLizer
Starting job with name trace2333-pippa-llama2-v0-v2-mkmlizer
Waiting for job on trace2333-pippa-llama2-v0-v2-mkmlizer to finish
trace2333-pippa-llama2-v0-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-pippa-llama2-v0-v2-mkmlizer: ║     _____            __           __                                ║
trace2333-pippa-llama2-v0-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-pippa-llama2-v0-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-pippa-llama2-v0-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-pippa-llama2-v0-v2-mkmlizer: ║       /___/                                                         ║
trace2333-pippa-llama2-v0-v2-mkmlizer: ║                                                                     ║
trace2333-pippa-llama2-v0-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
trace2333-pippa-llama2-v0-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-pippa-llama2-v0-v2-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-pippa-llama2-v0-v2-mkmlizer: ║                                                                     ║
trace2333-pippa-llama2-v0-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-pippa-llama2-v0-v2-mkmlizer: ║  belonging to:                                                      ║
trace2333-pippa-llama2-v0-v2-mkmlizer: ║                                                                     ║
trace2333-pippa-llama2-v0-v2-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-pippa-llama2-v0-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-pippa-llama2-v0-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
trace2333-pippa-llama2-v0-v2-mkmlizer: ║                                                                     ║
trace2333-pippa-llama2-v0-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-pippa-llama2-v0-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.
trace2333-pippa-llama2-v0-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
trace2333-pippa-llama2-v0-v2-mkmlizer: Downloaded to shared memory in 42.206s
trace2333-pippa-llama2-v0-v2-mkmlizer: quantizing model to /dev/shm/model_cache
trace2333-pippa-llama2-v0-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-pippa-llama2-v0-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   3%|▎         | 9/291 [00:00<00:03, 88.97it/s]
Loading 0:   6%|▌         | 18/291 [00:00<00:03, 86.42it/s]
Loading 0:   9%|▉         | 27/291 [00:00<00:03, 86.09it/s]
Loading 0:  12%|█▏        | 36/291 [00:00<00:02, 86.14it/s]
Loading 0:  15%|█▌        | 45/291 [00:00<00:02, 86.10it/s]
Loading 0:  19%|█▊        | 54/291 [00:00<00:05, 42.21it/s]
Loading 0:  23%|██▎       | 66/291 [00:01<00:04, 55.36it/s]
Loading 0:  25%|██▌       | 74/291 [00:01<00:03, 60.04it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:03, 66.60it/s]
Loading 0:  32%|███▏      | 92/291 [00:01<00:02, 72.28it/s]
Loading 0:  35%|███▍      | 101/291 [00:01<00:02, 76.71it/s]
Loading 0:  38%|███▊      | 110/291 [00:01<00:04, 43.99it/s]
Loading 0:  41%|████      | 118/291 [00:01<00:03, 49.71it/s]
Loading 0:  44%|████▎     | 127/291 [00:02<00:02, 57.28it/s]
Loading 0:  47%|████▋     | 136/291 [00:02<00:02, 64.11it/s]
Loading 0:  50%|████▉     | 145/291 [00:02<00:02, 69.95it/s]
Loading 0:  53%|█████▎    | 154/291 [00:02<00:01, 74.73it/s]
Loading 0:  56%|█████▌    | 163/291 [00:02<00:02, 44.41it/s]
Loading 0:  59%|█████▉    | 172/291 [00:02<00:02, 52.13it/s]
Loading 0:  62%|██████▏   | 181/291 [00:02<00:01, 59.32it/s]
Loading 0:  65%|██████▌   | 190/291 [00:03<00:01, 65.63it/s]
Loading 0:  68%|██████▊   | 199/291 [00:03<00:01, 70.82it/s]
Loading 0:  71%|███████▏  | 208/291 [00:03<00:01, 75.31it/s]
Loading 0:  75%|███████▍  | 217/291 [00:03<00:01, 44.92it/s]
Loading 0:  78%|███████▊  | 226/291 [00:03<00:01, 52.47it/s]
Loading 0:  81%|████████  | 235/291 [00:03<00:00, 59.57it/s]
Loading 0:  84%|████████▍ | 244/291 [00:03<00:00, 65.79it/s]
Loading 0:  87%|████████▋ | 253/291 [00:04<00:00, 71.15it/s]
Loading 0:  90%|█████████ | 262/291 [00:04<00:00, 75.62it/s]
Loading 0:  93%|█████████▎| 271/291 [00:05<00:01, 16.13it/s]
Loading 0:  97%|█████████▋| 281/291 [00:05<00:00, 22.04it/s]
Loading 0: 100%|█████████▉| 290/291 [00:05<00:00, 28.20it/s]
                                                            
You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
trace2333-pippa-llama2-v0-v2-mkmlizer: quantized model in 12.867s
trace2333-pippa-llama2-v0-v2-mkmlizer: Processed model Trace2333/pippa_llama2_v0 in 56.787s
trace2333-pippa-llama2-v0-v2-mkmlizer: creating bucket guanaco-mkml-models
trace2333-pippa-llama2-v0-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-pippa-llama2-v0-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-pippa-llama2-v0-v2
trace2333-pippa-llama2-v0-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-pippa-llama2-v0-v2/config.json
trace2333-pippa-llama2-v0-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-pippa-llama2-v0-v2/special_tokens_map.json
trace2333-pippa-llama2-v0-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-pippa-llama2-v0-v2/tokenizer_config.json
trace2333-pippa-llama2-v0-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/trace2333-pippa-llama2-v0-v2/tokenizer.model
trace2333-pippa-llama2-v0-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-pippa-llama2-v0-v2/tokenizer.json
trace2333-pippa-llama2-v0-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-pippa-llama2-v0-v2/flywheel_model.0.safetensors
trace2333-pippa-llama2-v0-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
trace2333-pippa-llama2-v0-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.
trace2333-pippa-llama2-v0-v2-mkmlizer:   warnings.warn(
trace2333-pippa-llama2-v0-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.
trace2333-pippa-llama2-v0-v2-mkmlizer:   warnings.warn(
trace2333-pippa-llama2-v0-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.
trace2333-pippa-llama2-v0-v2-mkmlizer:   warnings.warn(
trace2333-pippa-llama2-v0-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()
trace2333-pippa-llama2-v0-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
trace2333-pippa-llama2-v0-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
trace2333-pippa-llama2-v0-v2-mkmlizer: Saving duration: 0.305s
trace2333-pippa-llama2-v0-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.150s
trace2333-pippa-llama2-v0-v2-mkmlizer: creating bucket guanaco-reward-models
trace2333-pippa-llama2-v0-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
trace2333-pippa-llama2-v0-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/trace2333-pippa-llama2-v0-v2_reward
trace2333-pippa-llama2-v0-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/trace2333-pippa-llama2-v0-v2_reward/config.json
trace2333-pippa-llama2-v0-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/trace2333-pippa-llama2-v0-v2_reward/special_tokens_map.json
trace2333-pippa-llama2-v0-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/trace2333-pippa-llama2-v0-v2_reward/tokenizer_config.json
trace2333-pippa-llama2-v0-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/trace2333-pippa-llama2-v0-v2_reward/merges.txt
trace2333-pippa-llama2-v0-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/trace2333-pippa-llama2-v0-v2_reward/vocab.json
trace2333-pippa-llama2-v0-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/trace2333-pippa-llama2-v0-v2_reward/tokenizer.json
trace2333-pippa-llama2-v0-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/trace2333-pippa-llama2-v0-v2_reward/reward.tensors
Job trace2333-pippa-llama2-v0-v2-mkmlizer completed after 84.34s with status: succeeded
Stopping job with name trace2333-pippa-llama2-v0-v2-mkmlizer
Pipeline stage MKMLizer completed in 85.02s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-pippa-llama2-v0-v2
Waiting for inference service trace2333-pippa-llama2-v0-v2 to be ready
Inference service trace2333-pippa-llama2-v0-v2 ready after 90.50140309333801s
Pipeline stage ISVCDeployer completed in 96.29s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.568101167678833s
Received healthy response to inference request in 0.7855589389801025s
Received healthy response to inference request in 0.5804107189178467s
Received healthy response to inference request in 0.9855301380157471s
Received healthy response to inference request in 0.9896955490112305s
5 requests
0 failed requests
5th percentile: 0.6214403629302978
10th percentile: 0.662470006942749
20th percentile: 0.7445292949676514
30th percentile: 0.8255531787872314
40th percentile: 0.9055416584014893
50th percentile: 0.9855301380157471
60th percentile: 0.9871963024139404
70th percentile: 0.9888624668121337
80th percentile: 1.1053766727447512
90th percentile: 1.336738920211792
95th percentile: 1.4524200439453123
99th percentile: 1.5449649429321288
mean time: 0.9818593025207519
Pipeline stage StressChecker completed in 5.58s
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 0.04s
M-Eval Dataset for topic stay_in_character is loaded
trace2333-pippa-llama2-v0_v2 status is now deployed due to DeploymentManager action
trace2333-pippa-llama2-v0_v2 status is now rejected due to a failure to get M-Eval score. Please try again in five minutes.