cycy233-misllm-v5-4

developer_uid: shiroe40

submission_id: cycy233-misllm-v5-4_v4

model_name: infer_test2

model_group: cycy233/misllm_v5.4

status: torndown

timestamp: 2024-05-23T13:39:35+00:00

num_battles: 15286

num_wins: 7951

celo_rating: 1192.95

family_friendly_score: 0.0

submission_type: basic

model_repo: cycy233/misllm_v5.4

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: infer_test2

is_internal_developer: False

language_model: cycy233/misllm_v5.4

model_size: 7B

ranking_group: single

us_pacific_date: 2024-05-23

win_ratio: 0.5201491560905404

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': 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 cycy233-misllm-v5-4-v4-mkmlizer
Stopping job with name cycy233-misllm-v5-4-v4-mkmlizer
%s, retrying in %s seconds...
Stopping job with name cycy233-misllm-v5-4-v4-mkmlizer
%s, retrying in %s seconds...
Stopping job with name cycy233-misllm-v5-4-v4-mkmlizer
%s, retrying in %s seconds...
Starting job with name cycy233-misllm-v5-4-v4-mkmlizer
Waiting for job on cycy233-misllm-v5-4-v4-mkmlizer to finish
cycy233-misllm-v5-4-v4-mkmlizer: Downloaded to shared memory in 14.284s
cycy233-misllm-v5-4-v4-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v5-4-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v5-4-v4-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  34%|███▎      | 98/291 [00:01<00:02, 89.19it/s]
Loading 0:  70%|███████   | 204/291 [00:02<00:00, 98.45it/s]
Loading 0: 100%|██████████| 291/291 [00:03<00:00, 83.52it/s]
                                                            
You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v5-4-v4-mkmlizer: quantized model in 14.765s
cycy233-misllm-v5-4-v4-mkmlizer: Processed model cycy233/misllm_v5.4 in 31.286s
cycy233-misllm-v5-4-v4-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v5-4-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v5-4-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v5-4-v4
cycy233-misllm-v5-4-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v5-4-v4/config.json
cycy233-misllm-v5-4-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v5-4-v4/tokenizer.json
cycy233-misllm-v5-4-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v5-4-v4/tokenizer_config.json
cycy233-misllm-v5-4-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v5-4-v4/tokenizer.model
cycy233-misllm-v5-4-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v5-4-v4/special_tokens_map.json
cycy233-misllm-v5-4-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-misllm-v5-4-v4/flywheel_model.0.safetensors
cycy233-misllm-v5-4-v4-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-v5-4-v4-mkmlizer:   return self.fget.__get__(instance, owner)()
cycy233-misllm-v5-4-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v5-4-v4-mkmlizer: Saving duration: 0.394s
cycy233-misllm-v5-4-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.595s
cycy233-misllm-v5-4-v4-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v5-4-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v5-4-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v5-4-v4_reward
cycy233-misllm-v5-4-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-misllm-v5-4-v4_reward/config.json
cycy233-misllm-v5-4-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-misllm-v5-4-v4_reward/tokenizer_config.json
cycy233-misllm-v5-4-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-misllm-v5-4-v4_reward/merges.txt
cycy233-misllm-v5-4-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-misllm-v5-4-v4_reward/special_tokens_map.json
cycy233-misllm-v5-4-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-misllm-v5-4-v4_reward/vocab.json
cycy233-misllm-v5-4-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-misllm-v5-4-v4_reward/tokenizer.json
cycy233-misllm-v5-4-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v5-4-v4_reward/reward.tensors
Job cycy233-misllm-v5-4-v4-mkmlizer completed after 68.66s with status: succeeded
Stopping job with name cycy233-misllm-v5-4-v4-mkmlizer
Pipeline stage MKMLizer completed in 81.59s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v5-4-v4
Waiting for inference service cycy233-misllm-v5-4-v4 to be ready
Inference service cycy233-misllm-v5-4-v4 ready after 37.37899398803711s
Pipeline stage ISVCDeployer completed in 48.00s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.12591814994812s
Received healthy response to inference request in 1.1704537868499756s
Received healthy response to inference request in 1.179532766342163s
Received healthy response to inference request in 1.178499698638916s
Received healthy response to inference request in 1.1766164302825928s
5 requests
0 failed requests
5th percentile: 1.171686315536499
10th percentile: 1.1729188442230225
20th percentile: 1.1753839015960694
30th percentile: 1.1769930839538574
40th percentile: 1.1777463912963868
50th percentile: 1.178499698638916
60th percentile: 1.1789129257202149
70th percentile: 1.1793261528015138
80th percentile: 1.3688098430633546
90th percentile: 1.7473639965057375
95th percentile: 1.9366410732269286
99th percentile: 2.0880627346038816
mean time: 1.3662041664123534
Pipeline stage StressChecker completed in 7.37s
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
cycy233-misllm-v5-4_v4 status is now deployed due to DeploymentManager action
cycy233-misllm-v5-4_v4 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-misllm-v5-4_v4
Running pipeline stage ISVCDeleter
Checking if service cycy233-misllm-v5-4-v4 is running
Tearing down inference service cycy233-misllm-v5-4-v4
Toredown service cycy233-misllm-v5-4-v4
Pipeline stage ISVCDeleter completed in 3.72s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-misllm-v5-4-v4/config.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v5-4-v4/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v5-4-v4/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v5-4-v4/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v5-4-v4/tokenizer.model from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v5-4-v4/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-misllm-v5-4-v4_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-4-v4_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-4-v4_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-4-v4_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-4-v4_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-4-v4_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-4-v4_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.88s
cycy233-misllm-v5-4_v4 status is now torndown due to DeploymentManager action