submission_id: trace2333-pippa-realme-l_4726_v1
developer_uid: Trace2333
status: inactive
model_repo: Trace2333/pippa_realme_llama2_v0
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
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: {'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}
timestamp: 2024-06-28T07:51:35+00:00
model_name: trace2333-pippa-realme-l_4726_v1
model_group: Trace2333/pippa_realme_l
num_battles: 14137
num_wins: 5375
celo_rating: 1097.78
propriety_score: 0.7323164348736354
propriety_total_count: 6687.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 6738415616.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: trace2333-pippa-realme-l_4726_v1
ineligible_reason: None
language_model: Trace2333/pippa_realme_llama2_v0
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-28
win_ratio: 0.38020796491476266
Resubmit model
Running pipeline stage MKMLizer
Starting job with name trace2333-pippa-realme-l-4726-v1-mkmlizer
Waiting for job on trace2333-pippa-realme-l-4726-v1-mkmlizer to finish
trace2333-pippa-realme-l-4726-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-pippa-realme-l-4726-v1-mkmlizer: ║ _____ __ __ ║
trace2333-pippa-realme-l-4726-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
trace2333-pippa-realme-l-4726-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
trace2333-pippa-realme-l-4726-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
trace2333-pippa-realme-l-4726-v1-mkmlizer: ║ /___/ ║
trace2333-pippa-realme-l-4726-v1-mkmlizer: ║ ║
trace2333-pippa-realme-l-4726-v1-mkmlizer: ║ Version: 0.8.14 ║
trace2333-pippa-realme-l-4726-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
trace2333-pippa-realme-l-4726-v1-mkmlizer: ║ https://mk1.ai ║
trace2333-pippa-realme-l-4726-v1-mkmlizer: ║ ║
trace2333-pippa-realme-l-4726-v1-mkmlizer: ║ The license key for the current software has been verified as ║
trace2333-pippa-realme-l-4726-v1-mkmlizer: ║ belonging to: ║
trace2333-pippa-realme-l-4726-v1-mkmlizer: ║ ║
trace2333-pippa-realme-l-4726-v1-mkmlizer: ║ Chai Research Corp. ║
trace2333-pippa-realme-l-4726-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
trace2333-pippa-realme-l-4726-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
trace2333-pippa-realme-l-4726-v1-mkmlizer: ║ ║
trace2333-pippa-realme-l-4726-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-pippa-realme-l-4726-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-realme-l-4726-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
trace2333-pippa-realme-l-4726-v1-mkmlizer: Downloaded to shared memory in 55.061s
trace2333-pippa-realme-l-4726-v1-mkmlizer: quantizing model to /dev/shm/model_cache
trace2333-pippa-realme-l-4726-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-pippa-realme-l-4726-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 11/291 [00:00<00:02, 109.83it/s] Loading 0: 8%|▊ | 22/291 [00:00<00:03, 89.59it/s] Loading 0: 11%|█ | 32/291 [00:00<00:02, 87.50it/s] Loading 0: 15%|█▍ | 43/291 [00:00<00:02, 94.37it/s] Loading 0: 18%|█▊ | 53/291 [00:00<00:04, 51.91it/s] Loading 0: 22%|██▏ | 65/291 [00:00<00:03, 65.10it/s] Loading 0: 25%|██▌ | 74/291 [00:01<00:03, 67.71it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 71.62it/s] Loading 0: 32%|███▏ | 93/291 [00:01<00:02, 77.75it/s] Loading 0: 35%|███▌ | 102/291 [00:01<00:02, 78.78it/s] Loading 0: 38%|███▊ | 111/291 [00:01<00:03, 49.68it/s] Loading 0: 42%|████▏ | 121/291 [00:01<00:02, 57.51it/s] Loading 0: 45%|████▌ | 131/291 [00:01<00:02, 64.24it/s] Loading 0: 49%|████▉ | 142/291 [00:02<00:02, 73.95it/s] Loading 0: 52%|█████▏ | 152/291 [00:02<00:01, 79.38it/s] Loading 0: 55%|█████▌ | 161/291 [00:02<00:02, 52.81it/s] Loading 0: 58%|█████▊ | 170/291 [00:02<00:02, 59.56it/s] Loading 0: 62%|██████▏ | 180/291 [00:02<00:01, 67.86it/s] Loading 0: 65%|██████▌ | 190/291 [00:02<00:01, 74.19it/s] Loading 0: 69%|██████▉ | 201/291 [00:02<00:01, 79.37it/s] Loading 0: 73%|███████▎ | 212/291 [00:02<00:00, 86.11it/s] Loading 0: 76%|███████▋ | 222/291 [00:03<00:01, 51.43it/s] Loading 0: 80%|███████▉ | 232/291 [00:03<00:00, 59.63it/s] Loading 0: 83%|████████▎ | 242/291 [00:03<00:00, 67.52it/s] Loading 0: 87%|████████▋ | 253/291 [00:03<00:00, 75.82it/s] Loading 0: 90%|█████████ | 263/291 [00:03<00:00, 81.51it/s] Loading 0: 94%|█████████▍| 273/291 [00:05<00:01, 17.23it/s] Loading 0: 97%|█████████▋| 281/291 [00:05<00:00, 21.47it/s] You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
trace2333-pippa-realme-l-4726-v1-mkmlizer: quantized model in 15.245s
trace2333-pippa-realme-l-4726-v1-mkmlizer: Processed model Trace2333/pippa_realme_llama2_v0 in 74.538s
trace2333-pippa-realme-l-4726-v1-mkmlizer: creating bucket guanaco-mkml-models
trace2333-pippa-realme-l-4726-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-pippa-realme-l-4726-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-pippa-realme-l-4726-v1
trace2333-pippa-realme-l-4726-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-pippa-realme-l-4726-v1/config.json
trace2333-pippa-realme-l-4726-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-pippa-realme-l-4726-v1/special_tokens_map.json
trace2333-pippa-realme-l-4726-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/trace2333-pippa-realme-l-4726-v1/tokenizer.model
trace2333-pippa-realme-l-4726-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-pippa-realme-l-4726-v1/tokenizer_config.json
trace2333-pippa-realme-l-4726-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-pippa-realme-l-4726-v1/tokenizer.json
trace2333-pippa-realme-l-4726-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-pippa-realme-l-4726-v1/flywheel_model.0.safetensors
trace2333-pippa-realme-l-4726-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
trace2333-pippa-realme-l-4726-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-realme-l-4726-v1-mkmlizer: warnings.warn(
trace2333-pippa-realme-l-4726-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-realme-l-4726-v1-mkmlizer: warnings.warn(
trace2333-pippa-realme-l-4726-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-realme-l-4726-v1-mkmlizer: warnings.warn(
trace2333-pippa-realme-l-4726-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-realme-l-4726-v1-mkmlizer: return self.fget.__get__(instance, owner)()
trace2333-pippa-realme-l-4726-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
trace2333-pippa-realme-l-4726-v1-mkmlizer: Saving duration: 0.399s
trace2333-pippa-realme-l-4726-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.984s
trace2333-pippa-realme-l-4726-v1-mkmlizer: creating bucket guanaco-reward-models
trace2333-pippa-realme-l-4726-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
trace2333-pippa-realme-l-4726-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/trace2333-pippa-realme-l-4726-v1_reward
trace2333-pippa-realme-l-4726-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/trace2333-pippa-realme-l-4726-v1_reward/special_tokens_map.json
trace2333-pippa-realme-l-4726-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/trace2333-pippa-realme-l-4726-v1_reward/config.json
trace2333-pippa-realme-l-4726-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/trace2333-pippa-realme-l-4726-v1_reward/vocab.json
trace2333-pippa-realme-l-4726-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/trace2333-pippa-realme-l-4726-v1_reward/tokenizer_config.json
trace2333-pippa-realme-l-4726-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/trace2333-pippa-realme-l-4726-v1_reward/merges.txt
trace2333-pippa-realme-l-4726-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/trace2333-pippa-realme-l-4726-v1_reward/tokenizer.json
trace2333-pippa-realme-l-4726-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/trace2333-pippa-realme-l-4726-v1_reward/reward.tensors
Job trace2333-pippa-realme-l-4726-v1-mkmlizer completed after 94.53s with status: succeeded
Stopping job with name trace2333-pippa-realme-l-4726-v1-mkmlizer
Pipeline stage MKMLizer completed in 95.46s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.14s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-pippa-realme-l-4726-v1
Waiting for inference service trace2333-pippa-realme-l-4726-v1 to be ready
Inference service trace2333-pippa-realme-l-4726-v1 ready after 40.16404962539673s
Pipeline stage ISVCDeployer completed in 47.12s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.928544282913208s
Received healthy response to inference request in 0.9894537925720215s
Received healthy response to inference request in 0.9983527660369873s
Received healthy response to inference request in 1.0000801086425781s
Received healthy response to inference request in 0.9939126968383789s
5 requests
0 failed requests
5th percentile: 0.990345573425293
10th percentile: 0.9912373542785644
20th percentile: 0.9930209159851074
30th percentile: 0.9948007106781006
40th percentile: 0.9965767383575439
50th percentile: 0.9983527660369873
60th percentile: 0.9990437030792236
70th percentile: 0.99973464012146
80th percentile: 1.1857729434967044
90th percentile: 1.5571586132049562
95th percentile: 1.7428514480590818
99th percentile: 1.8914057159423827
mean time: 1.1820687294006347
Pipeline stage StressChecker completed in 6.65s
trace2333-pippa-realme-l_4726_v1 status is now deployed due to DeploymentManager action
trace2333-pippa-realme-l_4726_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics