trace2333-realme-llama2-v0

submission_id: trace2333-realme-llama2-v0_v2
developer_uid: Trace2333
best_of: 4
celo_rating: 1092.76
display_name: trace2333-realme-llama2-v0_v1
family_friendly_score: 0.0
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}
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': ['</s>'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
is_internal_developer: False
language_model: Trace2333/realme_llama2_v0
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: Trace2333/realme_llama2_
model_name: trace2333-realme-llama2-v0_v1
model_num_parameters: 6738415616.0
model_repo: Trace2333/realme_llama2_v0
model_size: 7B
num_battles: 13699
num_wins: 5175
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: torndown
submission_type: basic
timestamp: 2024-06-30T10:37:15+00:00
us_pacific_date: 2024-06-30
win_ratio: 0.37776480035039056
Resubmit model
Running pipeline stage MKMLizer
Starting job with name trace2333-realme-llama2-v0-v2-mkmlizer
Waiting for job on trace2333-realme-llama2-v0-v2-mkmlizer to finish
trace2333-realme-llama2-v0-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-realme-llama2-v0-v2-mkmlizer: ║     _____            __           __                                ║
trace2333-realme-llama2-v0-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-realme-llama2-v0-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-realme-llama2-v0-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-realme-llama2-v0-v2-mkmlizer: ║       /___/                                                         ║
trace2333-realme-llama2-v0-v2-mkmlizer: ║                                                                     ║
trace2333-realme-llama2-v0-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
trace2333-realme-llama2-v0-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-realme-llama2-v0-v2-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-realme-llama2-v0-v2-mkmlizer: ║                                                                     ║
trace2333-realme-llama2-v0-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-realme-llama2-v0-v2-mkmlizer: ║  belonging to:                                                      ║
trace2333-realme-llama2-v0-v2-mkmlizer: ║                                                                     ║
trace2333-realme-llama2-v0-v2-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-realme-llama2-v0-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-realme-llama2-v0-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
trace2333-realme-llama2-v0-v2-mkmlizer: ║                                                                     ║
trace2333-realme-llama2-v0-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-realme-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-realme-llama2-v0-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
trace2333-realme-llama2-v0-v2-mkmlizer: Downloaded to shared memory in 43.436s
trace2333-realme-llama2-v0-v2-mkmlizer: quantizing model to /dev/shm/model_cache
trace2333-realme-llama2-v0-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-realme-llama2-v0-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:02, 102.55it/s]
Loading 0:   8%|▊         | 23/291 [00:00<00:03, 88.63it/s] 
Loading 0:  12%|█▏        | 34/291 [00:00<00:02, 96.45it/s]
Loading 0:  15%|█▌        | 44/291 [00:00<00:02, 95.92it/s]
Loading 0:  19%|█▊        | 54/291 [00:00<00:04, 47.79it/s]
Loading 0:  23%|██▎       | 66/291 [00:00<00:03, 60.62it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:03, 68.07it/s]
Loading 0:  30%|██▉       | 87/291 [00:01<00:02, 77.67it/s]
Loading 0:  33%|███▎      | 97/291 [00:01<00:02, 78.94it/s]
Loading 0:  37%|███▋      | 107/291 [00:01<00:03, 51.54it/s]
Loading 0:  40%|████      | 117/291 [00:01<00:02, 59.54it/s]
Loading 0:  44%|████▎     | 127/291 [00:01<00:02, 67.23it/s]
Loading 0:  47%|████▋     | 138/291 [00:01<00:02, 74.48it/s]
Loading 0:  51%|█████     | 148/291 [00:02<00:01, 77.72it/s]
Loading 0:  55%|█████▍    | 159/291 [00:02<00:02, 55.84it/s]
Loading 0:  57%|█████▋    | 167/291 [00:02<00:02, 53.29it/s]
Loading 0:  61%|██████    | 178/291 [00:02<00:01, 63.52it/s]
Loading 0:  65%|██████▍   | 188/291 [00:02<00:01, 70.34it/s]
Loading 0:  68%|██████▊   | 197/291 [00:02<00:01, 74.45it/s]
Loading 0:  71%|███████   | 206/291 [00:03<00:01, 76.55it/s]
Loading 0:  74%|███████▍  | 215/291 [00:03<00:01, 49.76it/s]
Loading 0:  77%|███████▋  | 225/291 [00:03<00:01, 58.41it/s]
Loading 0:  81%|████████  | 235/291 [00:03<00:00, 67.01it/s]
Loading 0:  85%|████████▍ | 246/291 [00:03<00:00, 74.84it/s]
Loading 0:  88%|████████▊ | 256/291 [00:03<00:00, 77.21it/s]
Loading 0:  92%|█████████▏| 267/291 [00:05<00:01, 17.66it/s]
Loading 0:  95%|█████████▍| 275/291 [00:05<00:00, 21.78it/s]
Loading 0:  97%|█████████▋| 283/291 [00:05<00:00, 25.54it/s]
                                                            
You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
trace2333-realme-llama2-v0-v2-mkmlizer: quantized model in 15.774s
trace2333-realme-llama2-v0-v2-mkmlizer: Processed model Trace2333/realme_llama2_v0 in 63.482s
trace2333-realme-llama2-v0-v2-mkmlizer: creating bucket guanaco-mkml-models
trace2333-realme-llama2-v0-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-realme-llama2-v0-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-realme-llama2-v0-v2
trace2333-realme-llama2-v0-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-realme-llama2-v0-v2/config.json
trace2333-realme-llama2-v0-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-realme-llama2-v0-v2/tokenizer_config.json
trace2333-realme-llama2-v0-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-realme-llama2-v0-v2/special_tokens_map.json
trace2333-realme-llama2-v0-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-realme-llama2-v0-v2/tokenizer.json
trace2333-realme-llama2-v0-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/trace2333-realme-llama2-v0-v2/tokenizer.model
trace2333-realme-llama2-v0-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-realme-llama2-v0-v2/flywheel_model.0.safetensors
trace2333-realme-llama2-v0-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
trace2333-realme-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-realme-llama2-v0-v2-mkmlizer:   warnings.warn(
trace2333-realme-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-realme-llama2-v0-v2-mkmlizer:   warnings.warn(
trace2333-realme-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-realme-llama2-v0-v2-mkmlizer:   warnings.warn(
trace2333-realme-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-realme-llama2-v0-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
trace2333-realme-llama2-v0-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
trace2333-realme-llama2-v0-v2-mkmlizer: Saving duration: 0.410s
trace2333-realme-llama2-v0-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.431s
trace2333-realme-llama2-v0-v2-mkmlizer: creating bucket guanaco-reward-models
trace2333-realme-llama2-v0-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
trace2333-realme-llama2-v0-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/trace2333-realme-llama2-v0-v2_reward
trace2333-realme-llama2-v0-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/trace2333-realme-llama2-v0-v2_reward/config.json
trace2333-realme-llama2-v0-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/trace2333-realme-llama2-v0-v2_reward/tokenizer_config.json
trace2333-realme-llama2-v0-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/trace2333-realme-llama2-v0-v2_reward/merges.txt
trace2333-realme-llama2-v0-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/trace2333-realme-llama2-v0-v2_reward/special_tokens_map.json
trace2333-realme-llama2-v0-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/trace2333-realme-llama2-v0-v2_reward/vocab.json
trace2333-realme-llama2-v0-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/trace2333-realme-llama2-v0-v2_reward/tokenizer.json
trace2333-realme-llama2-v0-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/trace2333-realme-llama2-v0-v2_reward/reward.tensors
Job trace2333-realme-llama2-v0-v2-mkmlizer completed after 83.44s with status: succeeded
Stopping job with name trace2333-realme-llama2-v0-v2-mkmlizer
Pipeline stage MKMLizer completed in 84.26s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-realme-llama2-v0-v2
Waiting for inference service trace2333-realme-llama2-v0-v2 to be ready
Tearing down inference service trace2333-realme-llama2-v0-v2
%s, retrying in %s seconds...
Creating inference service trace2333-realme-llama2-v0-v2
Waiting for inference service trace2333-realme-llama2-v0-v2 to be ready
Tearing down inference service trace2333-realme-llama2-v0-v2
%s, retrying in %s seconds...
Creating inference service trace2333-realme-llama2-v0-v2
Waiting for inference service trace2333-realme-llama2-v0-v2 to be ready
Inference service trace2333-realme-llama2-v0-v2 ready after 50.219449281692505s
Pipeline stage ISVCDeployer completed in 88.80s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9041428565979004s
Received healthy response to inference request in 0.7927312850952148s
Received healthy response to inference request in 0.9047996997833252s
Received healthy response to inference request in 0.8422887325286865s
Received healthy response to inference request in 0.5626864433288574s
5 requests
0 failed requests
5th percentile: 0.6086954116821289
10th percentile: 0.6547043800354004
20th percentile: 0.7467223167419433
30th percentile: 0.8026427745819091
40th percentile: 0.8224657535552978
50th percentile: 0.8422887325286865
60th percentile: 0.867293119430542
70th percentile: 0.8922975063323975
80th percentile: 1.1046683311462404
90th percentile: 1.5044055938720704
95th percentile: 1.7042742252349852
99th percentile: 1.8641691303253174
mean time: 1.0013298034667968
Pipeline stage StressChecker completed in 5.82s
trace2333-realme-llama2-v0_v2 status is now deployed due to DeploymentManager action
trace2333-realme-llama2-v0_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of trace2333-realme-llama2-v0_v2
Running pipeline stage ISVCDeleter
Checking if service trace2333-realme-llama2-v0-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.53s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key trace2333-realme-llama2-v0-v2/config.json from bucket guanaco-mkml-models
Deleting key trace2333-realme-llama2-v0-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key trace2333-realme-llama2-v0-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key trace2333-realme-llama2-v0-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key trace2333-realme-llama2-v0-v2/tokenizer.model from bucket guanaco-mkml-models
Deleting key trace2333-realme-llama2-v0-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key trace2333-realme-llama2-v0-v2_reward/config.json from bucket guanaco-reward-models
Deleting key trace2333-realme-llama2-v0-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key trace2333-realme-llama2-v0-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key trace2333-realme-llama2-v0-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key trace2333-realme-llama2-v0-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key trace2333-realme-llama2-v0-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key trace2333-realme-llama2-v0-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.71s
trace2333-realme-llama2-v0_v2 status is now torndown due to DeploymentManager action