submission_id: cycy233-l3-duduk-v0-e1-5_v1
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3-duduk-v0-e1.5
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}
timestamp: 2024-06-28T03:30:53+00:00
model_name: auto
model_group: cycy233/L3-duduk-v0-e1.5
num_battles: 19876
num_wins: 10081
celo_rating: 1188.76
propriety_score: 0.6999786004707896
propriety_total_count: 9346.0
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-duduk-v0-e1.5
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-27
win_ratio: 0.5071946065606762
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-duduk-v0-e1-5-v1-mkmlizer
Waiting for job on cycy233-l3-duduk-v0-e1-5-v1-mkmlizer to finish
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: ║ /___/ ║
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: ║ ║
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: ║ ║
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: ║ ║
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: ║ ║
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-duduk-v0-e1-5-v1-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-l3-duduk-v0-e1-5-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 81.69it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 94.79it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 138.07it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: quantized model in 23.974s
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: Processed model cycy233/L3-duduk-v0-e1.5 in 64.110s
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-duduk-v0-e1-5-v1
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-duduk-v0-e1-5-v1/tokenizer_config.json
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-duduk-v0-e1-5-v1/config.json
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-duduk-v0-e1-5-v1/special_tokens_map.json
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-duduk-v0-e1-5-v1/tokenizer.json
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-duduk-v0-e1-5-v1/flywheel_model.0.safetensors
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-duduk-v0-e1-5-v1-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-l3-duduk-v0-e1-5-v1-mkmlizer: warnings.warn(
cycy233-l3-duduk-v0-e1-5-v1-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-l3-duduk-v0-e1-5-v1-mkmlizer: warnings.warn(
cycy233-l3-duduk-v0-e1-5-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-duduk-v0-e1-5-v1-mkmlizer: warnings.warn(
Connection pool is full, discarding connection: %s
cycy233-l3-duduk-v0-e1-5-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-duduk-v0-e1-5-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: Saving duration: 0.403s
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.242s
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-duduk-v0-e1-5-v1_reward
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-duduk-v0-e1-5-v1_reward/special_tokens_map.json
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-duduk-v0-e1-5-v1_reward/tokenizer_config.json
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-duduk-v0-e1-5-v1_reward/vocab.json
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-duduk-v0-e1-5-v1_reward/merges.txt
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-duduk-v0-e1-5-v1_reward/tokenizer.json
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-duduk-v0-e1-5-v1_reward/config.json
cycy233-l3-duduk-v0-e1-5-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-duduk-v0-e1-5-v1_reward/reward.tensors
Job cycy233-l3-duduk-v0-e1-5-v1-mkmlizer completed after 93.58s with status: succeeded
Stopping job with name cycy233-l3-duduk-v0-e1-5-v1-mkmlizer
Pipeline stage MKMLizer completed in 94.51s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-duduk-v0-e1-5-v1
Waiting for inference service cycy233-l3-duduk-v0-e1-5-v1 to be ready
Inference service cycy233-l3-duduk-v0-e1-5-v1 ready after 231.3519687652588s
Pipeline stage ISVCDeployer completed in 239.77s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3913989067077637s
Received healthy response to inference request in 1.3224527835845947s
Received healthy response to inference request in 1.3247790336608887s
Received healthy response to inference request in 1.269529104232788s
Received healthy response to inference request in 1.3396000862121582s
5 requests
0 failed requests
5th percentile: 1.2801138401031493
10th percentile: 1.2906985759735108
20th percentile: 1.3118680477142335
30th percentile: 1.3229180335998536
40th percentile: 1.3238485336303711
50th percentile: 1.3247790336608887
60th percentile: 1.3307074546813964
70th percentile: 1.3366358757019043
80th percentile: 1.5499598503112795
90th percentile: 1.9706793785095216
95th percentile: 2.1810391426086424
99th percentile: 2.3493269538879393
mean time: 1.5295519828796387
Pipeline stage StressChecker completed in 8.41s
cycy233-l3-duduk-v0-e1-5_v1 status is now deployed due to DeploymentManager action
cycy233-l3-duduk-v0-e1-5_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics