submission_id: pawankrd-cosmosrp_v66
developer_uid: PawanOsman
status: inactive
model_repo: PawanKrd/CosmosRP
reward_repo: Jellywibble/gpt2_xl_pairwise_89m_step_347634
generation_params: {'temperature': 1.2, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<', '>'], 'max_input_tokens': 512, 'best_of': 16, '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: 2024-07-13T08:06:08+00:00
model_name: pawankrd-cosmosrp_v66
model_group: PawanKrd/CosmosRP
num_battles: 353310
num_wins: 198459
celo_rating: 1272.06
propriety_score: 0.724559158702867
propriety_total_count: 50018.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: pawankrd-cosmosrp_v66
ineligible_reason: None
language_model: PawanKrd/CosmosRP
model_size: 8B
reward_model: Jellywibble/gpt2_xl_pairwise_89m_step_347634
us_pacific_date: 2024-07-13
win_ratio: 0.561713509382695
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name pawankrd-cosmosrp-v66-mkmlizer
Waiting for job on pawankrd-cosmosrp-v66-mkmlizer to finish
pawankrd-cosmosrp-v66-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
pawankrd-cosmosrp-v66-mkmlizer: ║ _____ __ __ ║
pawankrd-cosmosrp-v66-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
pawankrd-cosmosrp-v66-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
pawankrd-cosmosrp-v66-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
pawankrd-cosmosrp-v66-mkmlizer: ║ /___/ ║
pawankrd-cosmosrp-v66-mkmlizer: ║ ║
pawankrd-cosmosrp-v66-mkmlizer: ║ Version: 0.8.14 ║
pawankrd-cosmosrp-v66-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
pawankrd-cosmosrp-v66-mkmlizer: ║ https://mk1.ai ║
pawankrd-cosmosrp-v66-mkmlizer: ║ ║
pawankrd-cosmosrp-v66-mkmlizer: ║ The license key for the current software has been verified as ║
pawankrd-cosmosrp-v66-mkmlizer: ║ belonging to: ║
pawankrd-cosmosrp-v66-mkmlizer: ║ ║
pawankrd-cosmosrp-v66-mkmlizer: ║ Chai Research Corp. ║
pawankrd-cosmosrp-v66-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
pawankrd-cosmosrp-v66-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
pawankrd-cosmosrp-v66-mkmlizer: ║ ║
pawankrd-cosmosrp-v66-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
pawankrd-cosmosrp-v66-mkmlizer: Downloaded to shared memory in 37.921s
pawankrd-cosmosrp-v66-mkmlizer: quantizing model to /dev/shm/model_cache
pawankrd-cosmosrp-v66-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission mistralai-mixtral-8x7b-_3473_v61: ('http://mistralai-mixtral-8x7b-3473-v61-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:48438->127.0.0.1:8080: read: connection reset by peer\n')
pawankrd-cosmosrp-v66-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:05<13:21, 2.77s/it] Loading 0: 5%|▍ | 14/291 [00:05<01:22, 3.36it/s] Loading 0: 11%|█ | 31/291 [00:05<00:28, 9.07it/s] Loading 0: 14%|█▍ | 42/291 [00:05<00:18, 13.76it/s] Loading 0: 20%|█▉ | 58/291 [00:05<00:10, 22.85it/s] Loading 0: 24%|██▍ | 71/291 [00:06<00:09, 24.11it/s] Loading 0: 29%|██▉ | 85/291 [00:06<00:06, 33.57it/s] Loading 0: 33%|███▎ | 96/291 [00:06<00:04, 41.11it/s] Loading 0: 38%|███▊ | 112/291 [00:06<00:03, 56.12it/s] Loading 0: 43%|████▎ | 124/291 [00:06<00:02, 65.58it/s] Loading 0: 48%|████▊ | 139/291 [00:06<00:01, 80.53it/s] Loading 0: 52%|█████▏ | 152/291 [00:07<00:01, 87.79it/s] Loading 0: 57%|█████▋ | 166/291 [00:07<00:02, 55.40it/s] Loading 0: 61%|██████ | 177/291 [00:07<00:01, 62.32it/s] Loading 0: 66%|██████▋ | 193/291 [00:07<00:01, 78.57it/s] Loading 0: 70%|███████ | 205/291 [00:07<00:01, 85.87it/s] Loading 0: 76%|███████▌ | 221/291 [00:07<00:00, 98.53it/s] Loading 0: 81%|████████ | 236/291 [00:08<00:00, 110.17it/s] Loading 0: 86%|████████▌ | 249/291 [00:08<00:00, 106.97it/s] Loading 0: 91%|█████████ | 265/291 [00:08<00:00, 119.42it/s] Loading 0: 96%|█████████▌| 279/291 [00:08<00:00, 64.01it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
pawankrd-cosmosrp-v66-mkmlizer: quantized model in 28.917s
pawankrd-cosmosrp-v66-mkmlizer: Processed model PawanKrd/CosmosRP in 66.839s
pawankrd-cosmosrp-v66-mkmlizer: creating bucket guanaco-mkml-models
pawankrd-cosmosrp-v66-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
pawankrd-cosmosrp-v66-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/pawankrd-cosmosrp-v66
pawankrd-cosmosrp-v66-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v66/config.json
pawankrd-cosmosrp-v66-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v66/tokenizer_config.json
pawankrd-cosmosrp-v66-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v66/tokenizer.json
pawankrd-cosmosrp-v66-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v66/special_tokens_map.json
pawankrd-cosmosrp-v66-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/pawankrd-cosmosrp-v66/flywheel_model.0.safetensors
pawankrd-cosmosrp-v66-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
pawankrd-cosmosrp-v66-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-v66-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v66-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-v66-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v66-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-v66-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v66-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.
pawankrd-cosmosrp-v66-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v66-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-v66-mkmlizer: return self.fget.__get__(instance, owner)()
pawankrd-cosmosrp-v66-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
pawankrd-cosmosrp-v66-mkmlizer: Saving duration: 2.258s
pawankrd-cosmosrp-v66-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 16.742s
pawankrd-cosmosrp-v66-mkmlizer: creating bucket guanaco-reward-models
pawankrd-cosmosrp-v66-mkmlizer: Bucket 's3://guanaco-reward-models/' created
pawankrd-cosmosrp-v66-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/pawankrd-cosmosrp-v66_reward
pawankrd-cosmosrp-v66-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v66_reward/config.json
pawankrd-cosmosrp-v66-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/pawankrd-cosmosrp-v66_reward/special_tokens_map.json
pawankrd-cosmosrp-v66-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/pawankrd-cosmosrp-v66_reward/merges.txt
pawankrd-cosmosrp-v66-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/pawankrd-cosmosrp-v66_reward/tokenizer.json
pawankrd-cosmosrp-v66-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v66_reward/tokenizer_config.json
pawankrd-cosmosrp-v66-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/pawankrd-cosmosrp-v66_reward/vocab.json
pawankrd-cosmosrp-v66-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/pawankrd-cosmosrp-v66_reward/reward.tensors
Job pawankrd-cosmosrp-v66-mkmlizer completed after 115.19s with status: succeeded
Stopping job with name pawankrd-cosmosrp-v66-mkmlizer
Pipeline stage MKMLizer completed in 115.95s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service pawankrd-cosmosrp-v66
Waiting for inference service pawankrd-cosmosrp-v66 to be ready
Inference service pawankrd-cosmosrp-v66 ready after 50.48407959938049s
Pipeline stage ISVCDeployer completed in 59.16s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.394901752471924s
Received healthy response to inference request in 1.5862030982971191s
Received healthy response to inference request in 1.5713646411895752s
Received healthy response to inference request in 1.5306851863861084s
Received healthy response to inference request in 1.4811155796051025s
5 requests
0 failed requests
5th percentile: 1.4910295009613037
10th percentile: 1.5009434223175049
20th percentile: 1.5207712650299072
30th percentile: 1.5388210773468018
40th percentile: 1.5550928592681885
50th percentile: 1.5713646411895752
60th percentile: 1.5773000240325927
70th percentile: 1.5832354068756103
80th percentile: 1.7479428291320802
90th percentile: 2.071422290802002
95th percentile: 2.2331620216369625
99th percentile: 2.3625538063049314
mean time: 1.7128540515899657
Pipeline stage StressChecker completed in 9.15s
pawankrd-cosmosrp_v66 status is now deployed due to DeploymentManager action
pawankrd-cosmosrp_v66 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics