trace2333-pippa-bm-llama2-v0

developer_uid: Trace2333
submission_id: trace2333-pippa-bm-llama2-v0_v1
model_name: trace2333-pippa-bm-llama2-v0_v1
model_group: Trace2333/pippa_bm_llama
status: torndown
timestamp: 2024-06-15T17:49:17+00:00
num_battles: 11792
num_wins: 4684
celo_rating: 1097.9
family_friendly_score: 0.0
submission_type: basic
model_repo: Trace2333/pippa_bm_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-bm-llama2-v0_v1
is_internal_developer: False
language_model: Trace2333/pippa_bm_llama2_v0
model_size: 7B
ranking_group: single
us_pacific_date: 2024-06-15
win_ratio: 0.39721845318860244
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': '{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'}
model_eval_status: success
Resubmit model
Running pipeline stage MKMLizer
Starting job with name trace2333-pippa-bm-llama2-v0-v1-mkmlizer
Waiting for job on trace2333-pippa-bm-llama2-v0-v1-mkmlizer to finish
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: ║     _____            __           __                                ║
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: ║       /___/                                                         ║
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: ║                                                                     ║
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: ║                                                                     ║
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: ║  belonging to:                                                      ║
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: ║                                                                     ║
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: ║                                                                     ║
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-pippa-bm-llama2-v0-v1-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-bm-llama2-v0-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: Downloaded to shared memory in 70.485s
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: quantizing model to /dev/shm/model_cache
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:04, 66.41it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:04, 60.79it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:03, 68.23it/s]
Loading 0:  10%|█         | 30/291 [00:00<00:03, 71.41it/s]
Loading 0:  13%|█▎        | 38/291 [00:00<00:03, 73.06it/s]
Loading 0:  16%|█▌        | 46/291 [00:00<00:03, 67.67it/s]
Loading 0:  18%|█▊        | 53/291 [00:01<00:06, 38.13it/s]
Loading 0:  21%|██▏       | 62/291 [00:01<00:04, 47.45it/s]
Loading 0:  24%|██▎       | 69/291 [00:01<00:04, 52.22it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:03, 53.75it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:03, 56.23it/s]
Loading 0:  31%|███       | 90/291 [00:01<00:03, 56.73it/s]
Loading 0:  34%|███▎      | 98/291 [00:01<00:03, 61.99it/s]
Loading 0:  36%|███▌      | 105/291 [00:02<00:04, 41.43it/s]
Loading 0:  38%|███▊      | 111/291 [00:02<00:04, 43.26it/s]
Loading 0:  41%|████      | 118/291 [00:02<00:03, 48.83it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:03, 51.33it/s]
Loading 0:  45%|████▌     | 131/291 [00:02<00:03, 53.31it/s]
Loading 0:  48%|████▊     | 139/291 [00:02<00:02, 59.44it/s]
Loading 0:  51%|█████     | 147/291 [00:02<00:02, 64.37it/s]
Loading 0:  53%|█████▎    | 154/291 [00:02<00:02, 65.42it/s]
Loading 0:  55%|█████▌    | 161/291 [00:03<00:03, 38.19it/s]
Loading 0:  57%|█████▋    | 167/291 [00:03<00:03, 40.97it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:02, 48.92it/s]
Loading 0:  63%|██████▎   | 183/291 [00:03<00:01, 55.89it/s]
Loading 0:  66%|██████▌   | 191/291 [00:03<00:01, 61.76it/s]
Loading 0:  68%|██████▊   | 199/291 [00:03<00:01, 61.64it/s]
Loading 0:  71%|███████   | 206/291 [00:03<00:01, 62.82it/s]
Loading 0:  73%|███████▎  | 213/291 [00:04<00:01, 40.72it/s]
Loading 0:  75%|███████▌  | 219/291 [00:04<00:01, 42.60it/s]
Loading 0:  78%|███████▊  | 226/291 [00:04<00:01, 47.99it/s]
Loading 0:  80%|████████  | 233/291 [00:04<00:01, 52.24it/s]
Loading 0:  82%|████████▏ | 239/291 [00:04<00:00, 53.15it/s]
Loading 0:  85%|████████▌ | 248/291 [00:04<00:00, 58.45it/s]
Loading 0:  88%|████████▊ | 256/291 [00:04<00:00, 63.86it/s]
Loading 0:  91%|█████████ | 265/291 [00:04<00:00, 69.87it/s]
Loading 0:  94%|█████████▍| 273/291 [00:06<00:01, 13.28it/s]
Loading 0:  96%|█████████▌| 279/291 [00:06<00:00, 16.32it/s]
Loading 0:  98%|█████████▊| 285/291 [00:06<00:00, 20.01it/s]
                                                            
You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: quantized model in 16.699s
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: Processed model Trace2333/pippa_bm_llama2_v0 in 91.814s
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: creating bucket guanaco-mkml-models
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-pippa-bm-llama2-v0-v1
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-pippa-bm-llama2-v0-v1/special_tokens_map.json
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-pippa-bm-llama2-v0-v1/config.json
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-pippa-bm-llama2-v0-v1/tokenizer_config.json
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/trace2333-pippa-bm-llama2-v0-v1/tokenizer.model
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-pippa-bm-llama2-v0-v1/tokenizer.json
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-pippa-bm-llama2-v0-v1/flywheel_model.0.safetensors
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
trace2333-pippa-bm-llama2-v0-v1-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-bm-llama2-v0-v1-mkmlizer:   warnings.warn(
trace2333-pippa-bm-llama2-v0-v1-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-bm-llama2-v0-v1-mkmlizer:   warnings.warn(
trace2333-pippa-bm-llama2-v0-v1-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-bm-llama2-v0-v1-mkmlizer:   warnings.warn(
trace2333-pippa-bm-llama2-v0-v1-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-bm-llama2-v0-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: Saving duration: 0.406s
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 32.339s
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: creating bucket guanaco-reward-models
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/trace2333-pippa-bm-llama2-v0-v1_reward
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/trace2333-pippa-bm-llama2-v0-v1_reward/config.json
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/trace2333-pippa-bm-llama2-v0-v1_reward/special_tokens_map.json
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/trace2333-pippa-bm-llama2-v0-v1_reward/tokenizer_config.json
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/trace2333-pippa-bm-llama2-v0-v1_reward/merges.txt
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/trace2333-pippa-bm-llama2-v0-v1_reward/vocab.json
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/trace2333-pippa-bm-llama2-v0-v1_reward/tokenizer.json
trace2333-pippa-bm-llama2-v0-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/trace2333-pippa-bm-llama2-v0-v1_reward/reward.tensors
Job trace2333-pippa-bm-llama2-v0-v1-mkmlizer completed after 144.41s with status: succeeded
Stopping job with name trace2333-pippa-bm-llama2-v0-v1-mkmlizer
Pipeline stage MKMLizer completed in 148.81s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-pippa-bm-llama2-v0-v1
Waiting for inference service trace2333-pippa-bm-llama2-v0-v1 to be ready
Inference service trace2333-pippa-bm-llama2-v0-v1 ready after 50.60172891616821s
Pipeline stage ISVCDeployer completed in 58.23s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9444477558135986s
Received healthy response to inference request in 0.5593523979187012s
Received healthy response to inference request in 0.7944931983947754s
Received healthy response to inference request in 0.9766058921813965s
Received healthy response to inference request in 0.8977329730987549s
5 requests
0 failed requests
5th percentile: 0.606380558013916
10th percentile: 0.6534087181091308
20th percentile: 0.7474650382995606
30th percentile: 0.8151411533355712
40th percentile: 0.8564370632171631
50th percentile: 0.8977329730987549
60th percentile: 0.9292821407318115
70th percentile: 0.9608313083648682
80th percentile: 1.170174264907837
90th percentile: 1.557311010360718
95th percentile: 1.750879383087158
99th percentile: 1.9057340812683106
mean time: 1.0345264434814454
Pipeline stage StressChecker completed in 5.81s
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-bm-llama2-v0_v1 status is now deployed due to DeploymentManager action
trace2333-pippa-bm-llama2-v0_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of trace2333-pippa-bm-llama2-v0_v1
Running pipeline stage ISVCDeleter
Checking if service trace2333-pippa-bm-llama2-v0-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.42s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key trace2333-pippa-bm-llama2-v0-v1/config.json from bucket guanaco-mkml-models
Deleting key trace2333-pippa-bm-llama2-v0-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key trace2333-pippa-bm-llama2-v0-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key trace2333-pippa-bm-llama2-v0-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key trace2333-pippa-bm-llama2-v0-v1/tokenizer.model from bucket guanaco-mkml-models
Deleting key trace2333-pippa-bm-llama2-v0-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key trace2333-pippa-bm-llama2-v0-v1_reward/config.json from bucket guanaco-reward-models
Deleting key trace2333-pippa-bm-llama2-v0-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key trace2333-pippa-bm-llama2-v0-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key trace2333-pippa-bm-llama2-v0-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key trace2333-pippa-bm-llama2-v0-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key trace2333-pippa-bm-llama2-v0-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key trace2333-pippa-bm-llama2-v0-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.21s
trace2333-pippa-bm-llama2-v0_v1 status is now torndown due to DeploymentManager action