submission_id: cycy233-l3-klee-v2-e2-0_v1
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3-klee-v2-e2.0
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': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{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: 2024-07-02T02:23:19+00:00
model_name: auto
model_group: cycy233/L3-klee-v2-e2.0
num_battles: 10883
num_wins: 5510
celo_rating: 1180.77
propriety_score: 0.6982529434105583
propriety_total_count: 5266.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: auto
ineligible_reason: None
language_model: cycy233/L3-klee-v2-e2.0
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-01
win_ratio: 0.5062942203436552
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-klee-v2-e2-0-v1-mkmlizer
Waiting for job on cycy233-l3-klee-v2-e2-0-v1-mkmlizer to finish
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: ║ /___/ ║
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: ║ ║
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: ║ ║
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: ║ ║
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: ║ ║
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: Downloaded to shared memory in 41.519s
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:03, 66.95it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 79.37it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 115.49it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: quantized model in 24.161s
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: Processed model cycy233/L3-klee-v2-e2.0 in 65.681s
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-klee-v2-e2-0-v1
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-klee-v2-e2-0-v1/special_tokens_map.json
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-klee-v2-e2-0-v1/tokenizer_config.json
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-klee-v2-e2-0-v1/config.json
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-klee-v2-e2-0-v1/tokenizer.json
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-klee-v2-e2-0-v1/flywheel_model.0.safetensors
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: warnings.warn(
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: warnings.warn(
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: warnings.warn(
cycy233-l3-klee-v2-e2-0-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.
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: warnings.warn(
cycy233-l3-klee-v2-e2-0-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()
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: Saving duration: 0.389s
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.866s
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-klee-v2-e2-0-v1_reward
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-klee-v2-e2-0-v1_reward/config.json
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-klee-v2-e2-0-v1_reward/special_tokens_map.json
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-klee-v2-e2-0-v1_reward/tokenizer_config.json
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-klee-v2-e2-0-v1_reward/vocab.json
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-klee-v2-e2-0-v1_reward/merges.txt
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-klee-v2-e2-0-v1_reward/tokenizer.json
cycy233-l3-klee-v2-e2-0-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-klee-v2-e2-0-v1_reward/reward.tensors
Failed to get response for submission neversleep-noromaid-v0-_8068_v36: ('http://neversleep-noromaid-v0-8068-v36-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:59818->127.0.0.1:8080: read: connection reset by peer\n')
Job cycy233-l3-klee-v2-e2-0-v1-mkmlizer completed after 114.27s with status: succeeded
Stopping job with name cycy233-l3-klee-v2-e2-0-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.05s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-klee-v2-e2-0-v1
Waiting for inference service cycy233-l3-klee-v2-e2-0-v1 to be ready
Inference service cycy233-l3-klee-v2-e2-0-v1 ready after 40.235246419906616s
Pipeline stage ISVCDeployer completed in 47.38s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2445693016052246s
Received healthy response to inference request in 1.3842613697052002s
Received healthy response to inference request in 1.3459038734436035s
Received healthy response to inference request in 1.3087575435638428s
Received healthy response to inference request in 1.3661208152770996s
5 requests
0 failed requests
5th percentile: 1.3161868095397948
10th percentile: 1.3236160755157471
20th percentile: 1.3384746074676515
30th percentile: 1.3499472618103028
40th percentile: 1.358034038543701
50th percentile: 1.3661208152770996
60th percentile: 1.3733770370483398
70th percentile: 1.38063325881958
80th percentile: 1.5563229560852052
90th percentile: 1.900446128845215
95th percentile: 2.0725077152252194
99th percentile: 2.2101569843292235
mean time: 1.5299225807189942
Pipeline stage StressChecker completed in 8.38s
cycy233-l3-klee-v2-e2-0_v1 status is now deployed due to DeploymentManager action
cycy233-l3-klee-v2-e2-0_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics