submission_id: pawankrd-cosmosrp_v60
developer_uid: PawanOsman
status: inactive
model_repo: PawanKrd/CosmosRP
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.6, '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: 2024-07-12T19:37:04+00:00
model_name: pawankrd-cosmosrp_v60
model_group: PawanKrd/CosmosRP
num_battles: 25403
num_wins: 13786
celo_rating: 1224.35
alignment_score: None
alignment_samples: 0
propriety_score: 0.7262448695113451
propriety_total_count: 12913.0
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_v60
ineligible_reason: None
language_model: PawanKrd/CosmosRP
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-12
win_ratio: 0.5426918080541668
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name pawankrd-cosmosrp-v60-mkmlizer
Waiting for job on pawankrd-cosmosrp-v60-mkmlizer to finish
pawankrd-cosmosrp-v60-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
pawankrd-cosmosrp-v60-mkmlizer: ║ _____ __ __ ║
pawankrd-cosmosrp-v60-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
pawankrd-cosmosrp-v60-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
pawankrd-cosmosrp-v60-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
pawankrd-cosmosrp-v60-mkmlizer: ║ /___/ ║
pawankrd-cosmosrp-v60-mkmlizer: ║ ║
pawankrd-cosmosrp-v60-mkmlizer: ║ Version: 0.8.14 ║
pawankrd-cosmosrp-v60-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
pawankrd-cosmosrp-v60-mkmlizer: ║ https://mk1.ai ║
pawankrd-cosmosrp-v60-mkmlizer: ║ ║
pawankrd-cosmosrp-v60-mkmlizer: ║ The license key for the current software has been verified as ║
pawankrd-cosmosrp-v60-mkmlizer: ║ belonging to: ║
pawankrd-cosmosrp-v60-mkmlizer: ║ ║
pawankrd-cosmosrp-v60-mkmlizer: ║ Chai Research Corp. ║
pawankrd-cosmosrp-v60-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
pawankrd-cosmosrp-v60-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
pawankrd-cosmosrp-v60-mkmlizer: ║ ║
pawankrd-cosmosrp-v60-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission blend_tefuf_2024-07-12: ('http://chaiml-sao10k-l3-rp-v3-3-v37-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:38724->127.0.0.1:8080: read: connection reset by peer\n')
pawankrd-cosmosrp-v60-mkmlizer: Downloaded to shared memory in 25.297s
pawankrd-cosmosrp-v60-mkmlizer: quantizing model to /dev/shm/model_cache
pawankrd-cosmosrp-v60-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission blend_limik_2024-07-12: ('Connection aborted.', ConnectionResetError(104, 'Connection reset by peer'))
pawankrd-cosmosrp-v60-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:05<13:19, 2.76s/it] Loading 0: 5%|▍ | 14/291 [00:05<01:22, 3.37it/s] Loading 0: 10%|▉ | 29/291 [00:05<00:31, 8.45it/s] Loading 0: 14%|█▍ | 41/291 [00:05<00:18, 13.68it/s] Loading 0: 20%|█▉ | 57/291 [00:05<00:10, 22.90it/s] Loading 0: 24%|██▍ | 70/291 [00:06<00:09, 24.03it/s] Loading 0: 29%|██▉ | 85/291 [00:06<00:06, 34.21it/s] Loading 0: 33%|███▎ | 96/291 [00:06<00:04, 41.30it/s] Loading 0: 38%|███▊ | 112/291 [00:06<00:03, 55.47it/s] Loading 0: 43%|████▎ | 124/291 [00:06<00:02, 62.59it/s] Loading 0: 48%|████▊ | 139/291 [00:07<00:01, 76.03it/s] Loading 0: 52%|█████▏ | 151/291 [00:07<00:01, 79.96it/s] Loading 0: 57%|█████▋ | 166/291 [00:07<00:02, 51.98it/s] Loading 0: 61%|██████ | 177/291 [00:07<00:01, 58.25it/s] Loading 0: 66%|██████▋ | 193/291 [00:07<00:01, 74.06it/s] Loading 0: 70%|███████ | 204/291 [00:07<00:01, 77.46it/s] Loading 0: 74%|███████▍ | 216/291 [00:08<00:00, 86.00it/s] Loading 0: 79%|███████▊ | 229/291 [00:08<00:00, 93.70it/s] Loading 0: 82%|████████▏ | 240/291 [00:08<00:00, 94.94it/s] Loading 0: 88%|████████▊ | 256/291 [00:08<00:00, 108.73it/s] Loading 0: 92%|█████████▏| 268/291 [00:08<00:00, 56.47it/s] Loading 0: 97%|█████████▋| 283/291 [00:09<00:00, 70.24it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
pawankrd-cosmosrp-v60-mkmlizer: quantized model in 29.204s
pawankrd-cosmosrp-v60-mkmlizer: Processed model PawanKrd/CosmosRP in 54.502s
pawankrd-cosmosrp-v60-mkmlizer: creating bucket guanaco-mkml-models
pawankrd-cosmosrp-v60-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
pawankrd-cosmosrp-v60-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/pawankrd-cosmosrp-v60
pawankrd-cosmosrp-v60-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v60/config.json
pawankrd-cosmosrp-v60-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v60/tokenizer_config.json
pawankrd-cosmosrp-v60-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v60/special_tokens_map.json
pawankrd-cosmosrp-v60-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v60/tokenizer.json
pawankrd-cosmosrp-v60-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/pawankrd-cosmosrp-v60/flywheel_model.0.safetensors
pawankrd-cosmosrp-v60-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
pawankrd-cosmosrp-v60-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-v60-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v60-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-v60-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v60-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-v60-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v60-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-v60-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v60-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
pawankrd-cosmosrp-v60-mkmlizer: Saving duration: 0.514s
pawankrd-cosmosrp-v60-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.722s
pawankrd-cosmosrp-v60-mkmlizer: creating bucket guanaco-reward-models
pawankrd-cosmosrp-v60-mkmlizer: Bucket 's3://guanaco-reward-models/' created
pawankrd-cosmosrp-v60-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/pawankrd-cosmosrp-v60_reward
pawankrd-cosmosrp-v60-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v60_reward/config.json
pawankrd-cosmosrp-v60-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/pawankrd-cosmosrp-v60_reward/special_tokens_map.json
pawankrd-cosmosrp-v60-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/pawankrd-cosmosrp-v60_reward/vocab.json
pawankrd-cosmosrp-v60-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/pawankrd-cosmosrp-v60_reward/merges.txt
pawankrd-cosmosrp-v60-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v60_reward/tokenizer_config.json
pawankrd-cosmosrp-v60-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/pawankrd-cosmosrp-v60_reward/tokenizer.json
pawankrd-cosmosrp-v60-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/pawankrd-cosmosrp-v60_reward/reward.tensors
Job pawankrd-cosmosrp-v60-mkmlizer completed after 94.33s with status: succeeded
Stopping job with name pawankrd-cosmosrp-v60-mkmlizer
Pipeline stage MKMLizer completed in 95.27s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.16s
Running pipeline stage ISVCDeployer
Creating inference service pawankrd-cosmosrp-v60
Waiting for inference service pawankrd-cosmosrp-v60 to be ready
Inference service pawankrd-cosmosrp-v60 ready after 40.21753406524658s
Pipeline stage ISVCDeployer completed in 47.13s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.0970864295959473s
Received healthy response to inference request in 1.7574026584625244s
Failed to get response for submission blend_kobas_2024-07-12: ('Connection aborted.', ConnectionResetError(104, 'Connection reset by peer'))
Received healthy response to inference request in 3.756838083267212s
Received healthy response to inference request in 1.5665175914764404s
Received healthy response to inference request in 4.7143096923828125s
5 requests
0 failed requests
5th percentile: 1.6046946048736572
10th percentile: 1.642871618270874
20th percentile: 1.7192256450653076
30th percentile: 2.025339412689209
40th percentile: 2.5612129211425785
50th percentile: 3.0970864295959473
60th percentile: 3.360987091064453
70th percentile: 3.624887752532959
80th percentile: 3.948332405090332
90th percentile: 4.331321048736572
95th percentile: 4.522815370559692
99th percentile: 4.676010828018188
mean time: 2.978430891036987
Pipeline stage StressChecker completed in 15.65s
pawankrd-cosmosrp_v60 status is now deployed due to DeploymentManager action
pawankrd-cosmosrp_v60 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics