developer_uid: shiroe40
submission_id: cycy233-misllm-v4-5_v6
model_name: inference_test_true_bug
model_group: cycy233/misllm_v4.5
status: torndown
timestamp: 2024-05-24T04:20:30+00:00
num_battles: 9206
num_wins: 4646
celo_rating: 1184.82
family_friendly_score: 0.0
submission_type: basic
model_repo: cycy233/misllm_v4.5
model_architecture: MistralForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 7241732096.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: inference_test_true_bug
is_internal_developer: False
language_model: cycy233/misllm_v4.5
model_size: 7B
ranking_group: single
us_pacific_date: 2024-05-23
win_ratio: 0.504670866825983
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': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "### Instruction\nYou are a creative agent roleplaying as a character called {bot_name}. Stay true to the persona given, reply with long and descriptive sentences. Do not be repetitive. This is {bot_name}'s persona:\n{memory}", 'prompt_template': "### Input:\n # {bot_name}'s example conversation: \n{prompt}\n### Response: \n# Based on {bot_name}'s persona and the example conversation, please complete the following actual conversation as the Assistant (as {bot_name}) :\n", 'bot_template': '### {bot_name}: {message}\n', 'user_template': '### {user_name}: {message}\n', 'response_template': '### {bot_name}:', 'truncate_by_message': True}
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': True, 'user_template': '{user_name}: {message}\n'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v4-5-v6-mkmlizer
Waiting for job on cycy233-misllm-v4-5-v6-mkmlizer to finish
cycy233-misllm-v4-5-v6-mkmlizer: Downloaded to shared memory in 18.857s
cycy233-misllm-v4-5-v6-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v4-5-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v4-5-v6-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  34%|███▎      | 98/291 [00:01<00:02, 90.86it/s]
Loading 0:  70%|███████   | 204/291 [00:02<00:00, 101.50it/s]
Loading 0: 100%|██████████| 291/291 [00:03<00:00, 85.72it/s] 
                                                            
You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v4-5-v6-mkmlizer: quantized model in 11.585s
cycy233-misllm-v4-5-v6-mkmlizer: Processed model cycy233/misllm_v4.5 in 31.429s
cycy233-misllm-v4-5-v6-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v4-5-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v4-5-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v4-5-v6
cycy233-misllm-v4-5-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v4-5-v6/config.json
cycy233-misllm-v4-5-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v4-5-v6/special_tokens_map.json
cycy233-misllm-v4-5-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v4-5-v6/tokenizer_config.json
cycy233-misllm-v4-5-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v4-5-v6/tokenizer.model
cycy233-misllm-v4-5-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v4-5-v6/tokenizer.json
cycy233-misllm-v4-5-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-misllm-v4-5-v6/flywheel_model.0.safetensors
cycy233-misllm-v4-5-v6-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v4-5-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.
cycy233-misllm-v4-5-v6-mkmlizer:   warnings.warn(
cycy233-misllm-v4-5-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.
cycy233-misllm-v4-5-v6-mkmlizer:   warnings.warn(
cycy233-misllm-v4-5-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.
cycy233-misllm-v4-5-v6-mkmlizer:   warnings.warn(
cycy233-misllm-v4-5-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()
cycy233-misllm-v4-5-v6-mkmlizer:   return self.fget.__get__(instance, owner)()
cycy233-misllm-v4-5-v6-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v4-5-v6-mkmlizer: Saving duration: 0.327s
cycy233-misllm-v4-5-v6-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.345s
cycy233-misllm-v4-5-v6-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v4-5-v6-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v4-5-v6-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v4-5-v6_reward
cycy233-misllm-v4-5-v6-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-misllm-v4-5-v6_reward/config.json
cycy233-misllm-v4-5-v6-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-misllm-v4-5-v6_reward/special_tokens_map.json
cycy233-misllm-v4-5-v6-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-misllm-v4-5-v6_reward/tokenizer_config.json
cycy233-misllm-v4-5-v6-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-misllm-v4-5-v6_reward/merges.txt
cycy233-misllm-v4-5-v6-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-misllm-v4-5-v6_reward/vocab.json
cycy233-misllm-v4-5-v6-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-misllm-v4-5-v6_reward/tokenizer.json
cycy233-misllm-v4-5-v6-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v4-5-v6_reward/reward.tensors
Job cycy233-misllm-v4-5-v6-mkmlizer completed after 65.54s with status: succeeded
Stopping job with name cycy233-misllm-v4-5-v6-mkmlizer
Pipeline stage MKMLizer completed in 69.42s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.07s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v4-5-v6
Waiting for inference service cycy233-misllm-v4-5-v6 to be ready
Inference service cycy233-misllm-v4-5-v6 ready after 110.61887502670288s
Pipeline stage ISVCDeployer completed in 119.21s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0930533409118652s
Received healthy response to inference request in 1.171891450881958s
Received healthy response to inference request in 1.2094287872314453s
Received healthy response to inference request in 1.1563925743103027s
Received healthy response to inference request in 1.1760995388031006s
5 requests
0 failed requests
5th percentile: 1.1594923496246339
10th percentile: 1.1625921249389648
20th percentile: 1.1687916755676269
30th percentile: 1.1727330684661865
40th percentile: 1.1744163036346436
50th percentile: 1.1760995388031006
60th percentile: 1.1894312381744385
70th percentile: 1.2027629375457765
80th percentile: 1.3861536979675295
90th percentile: 1.7396035194396973
95th percentile: 1.916328430175781
99th percentile: 2.0577083587646485
mean time: 1.3613731384277343
Pipeline stage StressChecker completed in 7.30s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.02s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.06s
cycy233-misllm-v4-5_v6 status is now deployed due to DeploymentManager action
cycy233-misllm-v4-5_v6 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-misllm-v4-5_v6
Running pipeline stage ISVCDeleter
Checking if service cycy233-misllm-v4-5-v6 is running
Tearing down inference service cycy233-misllm-v4-5-v6
Toredown service cycy233-misllm-v4-5-v6
Pipeline stage ISVCDeleter completed in 4.43s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-misllm-v4-5-v6/config.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v4-5-v6/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v4-5-v6/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v4-5-v6/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v4-5-v6/tokenizer.model from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v4-5-v6/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-misllm-v4-5-v6_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v4-5-v6_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-misllm-v4-5-v6_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-misllm-v4-5-v6_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v4-5-v6_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v4-5-v6_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v4-5-v6_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.84s
cycy233-misllm-v4-5_v6 status is now torndown due to DeploymentManager action