submission_id: pawankrd-cosmosrp-experi_5136_v1
developer_uid: PawanOsman
status: inactive
model_repo: PawanKrd/CosmosRP-experimental
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<', '>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "<|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: 2024-07-02T07:39:58+00:00
model_name: pawankrd-cosmosrp-experi_5136_v1
model_group: PawanKrd/CosmosRP-experi
num_battles: 13052
num_wins: 2021
celo_rating: 882.94
propriety_score: 0.6136472849591542
propriety_total_count: 6243.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
display_name: pawankrd-cosmosrp-experi_5136_v1
ineligible_reason: None
language_model: PawanKrd/CosmosRP-experimental
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-02
win_ratio: 0.15484216978240883
Resubmit model
Running pipeline stage MKMLizer
Starting job with name pawankrd-cosmosrp-experi-5136-v1-mkmlizer
Waiting for job on pawankrd-cosmosrp-experi-5136-v1-mkmlizer to finish
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: ║ _____ __ __ ║
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: ║ /___/ ║
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: ║ ║
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: ║ Version: 0.8.14 ║
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: ║ https://mk1.ai ║
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: ║ ║
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: ║ The license key for the current software has been verified as ║
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: ║ belonging to: ║
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: ║ ║
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: ║ Chai Research Corp. ║
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: ║ ║
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: Downloaded to shared memory in 35.086s
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: quantizing model to /dev/shm/model_cache
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:02, 98.08it/s] Loading 0: 8%|▊ | 22/291 [00:00<00:03, 85.01it/s] Loading 0: 11%|█ | 31/291 [00:00<00:03, 84.60it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:02, 83.96it/s] Loading 0: 17%|█▋ | 50/291 [00:00<00:02, 88.81it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:02, 107.73it/s] Loading 0: 26%|██▋ | 77/291 [00:00<00:02, 103.46it/s] Loading 0: 30%|███ | 88/291 [00:01<00:03, 53.70it/s] Loading 0: 35%|███▌ | 102/291 [00:01<00:02, 67.62it/s] Loading 0: 38%|███▊ | 112/291 [00:01<00:02, 73.72it/s] Loading 0: 43%|████▎ | 125/291 [00:01<00:01, 85.03it/s] Loading 0: 47%|████▋ | 138/291 [00:01<00:01, 94.49it/s] Loading 0: 51%|█████ | 149/291 [00:01<00:01, 94.13it/s] Loading 0: 57%|█████▋ | 165/291 [00:01<00:01, 107.34it/s] Loading 0: 62%|██████▏ | 179/291 [00:01<00:00, 112.46it/s] Loading 0: 66%|██████▌ | 191/291 [00:02<00:01, 64.13it/s] Loading 0: 69%|██████▉ | 202/291 [00:02<00:01, 69.78it/s] Loading 0: 74%|███████▍ | 215/291 [00:02<00:00, 80.69it/s] Loading 0: 78%|███████▊ | 228/291 [00:02<00:00, 91.04it/s] Loading 0: 82%|████████▏ | 239/291 [00:02<00:00, 90.45it/s] Loading 0: 86%|████████▋ | 251/291 [00:02<00:00, 96.63it/s] Loading 0: 91%|█████████ | 264/291 [00:03<00:00, 104.74it/s] Loading 0: 95%|█████████▍| 276/291 [00:03<00:00, 100.46it/s] Loading 0: 99%|█████████▊| 287/291 [00:09<00:00, 6.32it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: quantized model in 24.919s
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: Processed model PawanKrd/CosmosRP-experimental in 60.005s
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: creating bucket guanaco-mkml-models
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/pawankrd-cosmosrp-experi-5136-v1
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-experi-5136-v1/config.json
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/pawankrd-cosmosrp-experi-5136-v1/special_tokens_map.json
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-experi-5136-v1/tokenizer_config.json
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/pawankrd-cosmosrp-experi-5136-v1/tokenizer.json
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/pawankrd-cosmosrp-experi-5136-v1/flywheel_model.0.safetensors
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
pawankrd-cosmosrp-experi-5136-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.
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: warnings.warn(
pawankrd-cosmosrp-experi-5136-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`.
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: warnings.warn(
pawankrd-cosmosrp-experi-5136-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.
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: warnings.warn(
Failed to get response for submission neversleep-noromaid-v0-_8068_v108: no entry with id "neversleep-noromaid-v0-_8068_v108" found on database!
pawankrd-cosmosrp-experi-5136-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()
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: return self.fget.__get__(instance, owner)()
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: Saving duration: 0.419s
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.290s
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: creating bucket guanaco-reward-models
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/pawankrd-cosmosrp-experi-5136-v1_reward
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/pawankrd-cosmosrp-experi-5136-v1_reward/special_tokens_map.json
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/pawankrd-cosmosrp-experi-5136-v1_reward/tokenizer_config.json
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/pawankrd-cosmosrp-experi-5136-v1_reward/vocab.json
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/pawankrd-cosmosrp-experi-5136-v1_reward/merges.txt
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/pawankrd-cosmosrp-experi-5136-v1_reward/config.json
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/pawankrd-cosmosrp-experi-5136-v1_reward/tokenizer.json
pawankrd-cosmosrp-experi-5136-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/pawankrd-cosmosrp-experi-5136-v1_reward/reward.tensors
Job pawankrd-cosmosrp-experi-5136-v1-mkmlizer completed after 83.46s with status: succeeded
Stopping job with name pawankrd-cosmosrp-experi-5136-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.53s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service pawankrd-cosmosrp-experi-5136-v1
Waiting for inference service pawankrd-cosmosrp-experi-5136-v1 to be ready
Inference service pawankrd-cosmosrp-experi-5136-v1 ready after 30.14354395866394s
Pipeline stage ISVCDeployer completed in 37.09s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1747243404388428s
Received healthy response to inference request in 1.3750643730163574s
Received healthy response to inference request in 1.2399346828460693s
Received healthy response to inference request in 1.29378080368042s
Received healthy response to inference request in 1.2394111156463623s
5 requests
0 failed requests
5th percentile: 1.2395158290863038
10th percentile: 1.2396205425262452
20th percentile: 1.2398299694061279
30th percentile: 1.2507039070129395
40th percentile: 1.2722423553466797
50th percentile: 1.29378080368042
60th percentile: 1.326294231414795
70th percentile: 1.35880765914917
80th percentile: 1.5349963665008546
90th percentile: 1.8548603534698487
95th percentile: 2.0147923469543456
99th percentile: 2.1427379417419434
mean time: 1.4645830631256103
Pipeline stage StressChecker completed in 8.03s
pawankrd-cosmosrp-experi_5136_v1 status is now deployed due to DeploymentManager action
pawankrd-cosmosrp-experi_5136_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics