submission_id: cycy233-misllm-v9-0-3_v7
developer_uid: shiroe40
status: inactive
model_repo: cycy233/misllm_v9.0.3
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': 16, 'max_output_tokens': 64}
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': True}
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': True}
timestamp: 2024-06-19T07:34:33+00:00
model_name: base
model_group: cycy233/misllm_v9.0.3
num_battles: 16195
num_wins: 7951
celo_rating: 1178.11
propriety_score: 0.6986040609137056
propriety_total_count: 9456.0
submission_type: basic
model_architecture: MistralForCausalLM
model_num_parameters: 7248023552.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: base
ineligible_reason: None
language_model: cycy233/misllm_v9.0.3
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-19
win_ratio: 0.4909539981475764
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v9-0-3-v7-mkmlizer
Waiting for job on cycy233-misllm-v9-0-3-v7-mkmlizer to finish
cycy233-misllm-v9-0-3-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v9-0-3-v7-mkmlizer: ║ _____ __ __ ║
cycy233-misllm-v9-0-3-v7-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-misllm-v9-0-3-v7-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-misllm-v9-0-3-v7-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-misllm-v9-0-3-v7-mkmlizer: ║ /___/ ║
cycy233-misllm-v9-0-3-v7-mkmlizer: ║ ║
cycy233-misllm-v9-0-3-v7-mkmlizer: ║ Version: 0.8.14 ║
cycy233-misllm-v9-0-3-v7-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-misllm-v9-0-3-v7-mkmlizer: ║ https://mk1.ai ║
cycy233-misllm-v9-0-3-v7-mkmlizer: ║ ║
cycy233-misllm-v9-0-3-v7-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-misllm-v9-0-3-v7-mkmlizer: ║ belonging to: ║
cycy233-misllm-v9-0-3-v7-mkmlizer: ║ ║
cycy233-misllm-v9-0-3-v7-mkmlizer: ║ Chai Research Corp. ║
cycy233-misllm-v9-0-3-v7-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-misllm-v9-0-3-v7-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-misllm-v9-0-3-v7-mkmlizer: ║ ║
cycy233-misllm-v9-0-3-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v9-0-3-v7-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.
cycy233-misllm-v9-0-3-v7-mkmlizer: warnings.warn(warning_message, FutureWarning)
Failed to get response for submission cycy233-misllm-v9-0-3_v2: ('http://cycy233-misllm-v9-0-3-v2-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', '')
cycy233-misllm-v9-0-3-v7-mkmlizer: Downloaded to shared memory in 16.704s
cycy233-misllm-v9-0-3-v7-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v9-0-3-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v9-0-3-v7-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 34%|███▎ | 98/291 [00:01<00:02, 83.03it/s] Loading 0: 70%|███████ | 204/291 [00:02<00:00, 99.28it/s] Loading 0: 100%|██████████| 291/291 [00:03<00:00, 81.87it/s] You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v9-0-3-v7-mkmlizer: quantized model in 14.938s
cycy233-misllm-v9-0-3-v7-mkmlizer: Processed model cycy233/misllm_v9.0.3 in 33.811s
cycy233-misllm-v9-0-3-v7-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v9-0-3-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v9-0-3-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v9-0-3-v7
cycy233-misllm-v9-0-3-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v9-0-3-v7/config.json
cycy233-misllm-v9-0-3-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v9-0-3-v7/special_tokens_map.json
cycy233-misllm-v9-0-3-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v9-0-3-v7/tokenizer.json
cycy233-misllm-v9-0-3-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v9-0-3-v7/tokenizer_config.json
cycy233-misllm-v9-0-3-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v9-0-3-v7/tokenizer.model
cycy233-misllm-v9-0-3-v7-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v9-0-3-v7-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-v9-0-3-v7-mkmlizer: warnings.warn(
cycy233-misllm-v9-0-3-v7-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-v9-0-3-v7-mkmlizer: warnings.warn(
cycy233-misllm-v9-0-3-v7-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-v9-0-3-v7-mkmlizer: warnings.warn(
cycy233-misllm-v9-0-3-v7-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-v9-0-3-v7-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-misllm-v9-0-3-v7-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v9-0-3-v7-mkmlizer: Saving duration: 0.391s
cycy233-misllm-v9-0-3-v7-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.175s
cycy233-misllm-v9-0-3-v7-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v9-0-3-v7-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v9-0-3-v7-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v9-0-3-v7_reward
cycy233-misllm-v9-0-3-v7-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-misllm-v9-0-3-v7_reward/special_tokens_map.json
cycy233-misllm-v9-0-3-v7-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-misllm-v9-0-3-v7_reward/config.json
cycy233-misllm-v9-0-3-v7-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-misllm-v9-0-3-v7_reward/tokenizer_config.json
cycy233-misllm-v9-0-3-v7-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-misllm-v9-0-3-v7_reward/vocab.json
cycy233-misllm-v9-0-3-v7-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-misllm-v9-0-3-v7_reward/merges.txt
cycy233-misllm-v9-0-3-v7-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-misllm-v9-0-3-v7_reward/tokenizer.json
cycy233-misllm-v9-0-3-v7-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v9-0-3-v7_reward/reward.tensors
Job cycy233-misllm-v9-0-3-v7-mkmlizer completed after 52.51s with status: succeeded
Stopping job with name cycy233-misllm-v9-0-3-v7-mkmlizer
Pipeline stage MKMLizer completed in 56.64s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v9-0-3-v7
Waiting for inference service cycy233-misllm-v9-0-3-v7 to be ready
Failed to get response for submission cycy233-misllm-v9-0-3_v2: ('http://cycy233-misllm-v9-0-3-v2-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission cycy233-misllm-v9-0-3_v2: ('http://cycy233-misllm-v9-0-3-v2-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission cycy233-misllm-v9-0-3_v2: ('http://cycy233-misllm-v9-0-3-v2-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', '')
Inference service cycy233-misllm-v9-0-3-v7 ready after 80.41353964805603s
Pipeline stage ISVCDeployer completed in 87.68s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9347846508026123s
Received healthy response to inference request in 1.1580936908721924s
Received healthy response to inference request in 1.040013313293457s
Received healthy response to inference request in 0.9766769409179688s
Received healthy response to inference request in 0.8414962291717529s
5 requests
0 failed requests
5th percentile: 0.868532371520996
10th percentile: 0.8955685138702393
20th percentile: 0.9496407985687256
30th percentile: 0.9893442153930664
40th percentile: 1.0146787643432618
50th percentile: 1.040013313293457
60th percentile: 1.0872454643249512
70th percentile: 1.1344776153564453
80th percentile: 1.3134318828582765
90th percentile: 1.6241082668304445
95th percentile: 1.7794464588165282
99th percentile: 1.9037170124053955
mean time: 1.1902129650115967
Pipeline stage StressChecker completed in 6.90s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.04s
cycy233-misllm-v9-0-3_v7 status is now deployed due to DeploymentManager action
cycy233-misllm-v9-0-3_v7 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics