submission_id: cycy233-l3-bm-v0-c4_v1
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3-bm-v0-c4
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': 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: 2024-07-04T02:20:35+00:00
model_name: auto
model_group: cycy233/L3-bm-v0-c4
num_battles: 13969
num_wins: 7158
celo_rating: 1197.05
propriety_score: 0.70509977827051
propriety_total_count: 6765.0
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-bm-v0-c4
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-03
win_ratio: 0.5124203593671701
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-bm-v0-c4-v1-mkmlizer
Waiting for job on cycy233-l3-bm-v0-c4-v1-mkmlizer to finish
cycy233-l3-bm-v0-c4-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-bm-v0-c4-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-bm-v0-c4-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-bm-v0-c4-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-bm-v0-c4-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-bm-v0-c4-v1-mkmlizer: ║ /___/ ║
cycy233-l3-bm-v0-c4-v1-mkmlizer: ║ ║
cycy233-l3-bm-v0-c4-v1-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3-bm-v0-c4-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-bm-v0-c4-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-bm-v0-c4-v1-mkmlizer: ║ ║
cycy233-l3-bm-v0-c4-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-bm-v0-c4-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-bm-v0-c4-v1-mkmlizer: ║ ║
cycy233-l3-bm-v0-c4-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-bm-v0-c4-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-bm-v0-c4-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-l3-bm-v0-c4-v1-mkmlizer: ║ ║
cycy233-l3-bm-v0-c4-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-bm-v0-c4-v1-mkmlizer: Downloaded to shared memory in 42.751s
cycy233-l3-bm-v0-c4-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-bm-v0-c4-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-bm-v0-c4-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:03, 60.03it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 70.59it/s] Loading 0: 99%|█████████▊| 287/291 [00:03<00:00, 102.98it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-bm-v0-c4-v1-mkmlizer: quantized model in 30.355s
cycy233-l3-bm-v0-c4-v1-mkmlizer: Processed model cycy233/L3-bm-v0-c4 in 73.107s
cycy233-l3-bm-v0-c4-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-bm-v0-c4-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-bm-v0-c4-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-bm-v0-c4-v1
cycy233-l3-bm-v0-c4-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-bm-v0-c4-v1/config.json
cycy233-l3-bm-v0-c4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-bm-v0-c4-v1/tokenizer.json
cycy233-l3-bm-v0-c4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-bm-v0-c4-v1/tokenizer_config.json
cycy233-l3-bm-v0-c4-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-bm-v0-c4-v1/special_tokens_map.json
cycy233-l3-bm-v0-c4-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-bm-v0-c4-v1/flywheel_model.0.safetensors
cycy233-l3-bm-v0-c4-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-bm-v0-c4-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-bm-v0-c4-v1-mkmlizer: warnings.warn(
cycy233-l3-bm-v0-c4-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-bm-v0-c4-v1-mkmlizer: warnings.warn(
cycy233-l3-bm-v0-c4-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-bm-v0-c4-v1-mkmlizer: warnings.warn(
cycy233-l3-bm-v0-c4-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-bm-v0-c4-v1-mkmlizer: warnings.warn(
cycy233-l3-bm-v0-c4-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-bm-v0-c4-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-bm-v0-c4-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-bm-v0-c4-v1-mkmlizer: Saving duration: 0.520s
cycy233-l3-bm-v0-c4-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 8.060s
cycy233-l3-bm-v0-c4-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-bm-v0-c4-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-bm-v0-c4-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-bm-v0-c4-v1_reward
cycy233-l3-bm-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-bm-v0-c4-v1_reward/special_tokens_map.json
cycy233-l3-bm-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-bm-v0-c4-v1_reward/config.json
cycy233-l3-bm-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-bm-v0-c4-v1_reward/tokenizer_config.json
cycy233-l3-bm-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-bm-v0-c4-v1_reward/vocab.json
cycy233-l3-bm-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-bm-v0-c4-v1_reward/merges.txt
cycy233-l3-bm-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-bm-v0-c4-v1_reward/tokenizer.json
cycy233-l3-bm-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-bm-v0-c4-v1_reward/reward.tensors
Job cycy233-l3-bm-v0-c4-v1-mkmlizer completed after 106.97s with status: succeeded
Stopping job with name cycy233-l3-bm-v0-c4-v1-mkmlizer
Pipeline stage MKMLizer completed in 108.02s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-bm-v0-c4-v1
Waiting for inference service cycy233-l3-bm-v0-c4-v1 to be ready
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Inference service cycy233-l3-bm-v0-c4-v1 ready after 50.30370116233826s
Pipeline stage ISVCDeployer completed in 57.33s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1400089263916016s
Received healthy response to inference request in 1.1903936862945557s
Received healthy response to inference request in 1.2396986484527588s
Received healthy response to inference request in 1.2711975574493408s
Received healthy response to inference request in 1.2903120517730713s
5 requests
0 failed requests
5th percentile: 1.2002546787261963
10th percentile: 1.210115671157837
20th percentile: 1.2298376560211182
30th percentile: 1.2459984302520752
40th percentile: 1.258597993850708
50th percentile: 1.2711975574493408
60th percentile: 1.278843355178833
70th percentile: 1.286489152908325
80th percentile: 1.4602514266967774
90th percentile: 1.8001301765441895
95th percentile: 1.9700695514678954
99th percentile: 2.1060210514068602
mean time: 1.4263221740722656
Pipeline stage StressChecker completed in 7.91s
cycy233-l3-bm-v0-c4_v1 status is now deployed due to DeploymentManager action
cycy233-l3-bm-v0-c4_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics