submission_id: pawankrd-cosmosrp_v58
developer_uid: PawanOsman
status: inactive
model_repo: PawanKrd/CosmosRP
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.8, '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: 2024-07-12T18:04:12+00:00
model_name: pawankrd-cosmosrp_v58
model_group: PawanKrd/CosmosRP
num_battles: 12323
num_wins: 6768
celo_rating: 1222.02
propriety_score: 0.7251118999845655
propriety_total_count: 6479.0
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_v58
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: 0.5492169114663638
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name pawankrd-cosmosrp-v58-mkmlizer
Waiting for job on pawankrd-cosmosrp-v58-mkmlizer to finish
pawankrd-cosmosrp-v58-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
pawankrd-cosmosrp-v58-mkmlizer: ║ _____ __ __ ║
pawankrd-cosmosrp-v58-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
pawankrd-cosmosrp-v58-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
pawankrd-cosmosrp-v58-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
pawankrd-cosmosrp-v58-mkmlizer: ║ /___/ ║
pawankrd-cosmosrp-v58-mkmlizer: ║ ║
pawankrd-cosmosrp-v58-mkmlizer: ║ Version: 0.8.14 ║
pawankrd-cosmosrp-v58-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
pawankrd-cosmosrp-v58-mkmlizer: ║ https://mk1.ai ║
pawankrd-cosmosrp-v58-mkmlizer: ║ ║
pawankrd-cosmosrp-v58-mkmlizer: ║ The license key for the current software has been verified as ║
pawankrd-cosmosrp-v58-mkmlizer: ║ belonging to: ║
pawankrd-cosmosrp-v58-mkmlizer: ║ ║
pawankrd-cosmosrp-v58-mkmlizer: ║ Chai Research Corp. ║
pawankrd-cosmosrp-v58-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
pawankrd-cosmosrp-v58-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
pawankrd-cosmosrp-v58-mkmlizer: ║ ║
pawankrd-cosmosrp-v58-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
pawankrd-cosmosrp-v58-mkmlizer: Downloaded to shared memory in 40.834s
pawankrd-cosmosrp-v58-mkmlizer: quantizing model to /dev/shm/model_cache
pawankrd-cosmosrp-v58-mkmlizer: Saving flywheel model at /dev/shm/model_cache
pawankrd-cosmosrp-v58-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, 13.77it/s] Loading 0: 20%|█▉ | 58/291 [00:05<00:10, 22.89it/s] Loading 0: 24%|██▍ | 71/291 [00:06<00:09, 24.16it/s] Loading 0: 29%|██▉ | 85/291 [00:06<00:06, 33.62it/s] Loading 0: 33%|███▎ | 96/291 [00:06<00:04, 41.20it/s] Loading 0: 38%|███▊ | 112/291 [00:06<00:03, 56.35it/s] Loading 0: 43%|████▎ | 125/291 [00:06<00:02, 66.84it/s] Loading 0: 48%|████▊ | 139/291 [00:06<00:01, 78.98it/s] Loading 0: 52%|█████▏ | 152/291 [00:07<00:01, 86.56it/s] Loading 0: 57%|█████▋ | 166/291 [00:07<00:02, 53.58it/s] Loading 0: 61%|██████ | 177/291 [00:07<00:01, 61.22it/s] Loading 0: 66%|██████▋ | 193/291 [00:07<00:01, 77.80it/s] Loading 0: 70%|███████ | 205/291 [00:07<00:01, 85.00it/s] Loading 0: 76%|███████▌ | 220/291 [00:08<00:00, 96.76it/s] Loading 0: 80%|████████ | 233/291 [00:08<00:00, 100.53it/s] Loading 0: 85%|████████▍ | 247/291 [00:08<00:00, 109.76it/s] Loading 0: 89%|████████▉ | 260/291 [00:08<00:00, 112.53it/s] Loading 0: 94%|█████████▍| 273/291 [00:08<00:00, 62.69it/s] Loading 0: 98%|█████████▊| 284/291 [00:08<00:00, 69.83it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
pawankrd-cosmosrp-v58-mkmlizer: quantized model in 29.254s
pawankrd-cosmosrp-v58-mkmlizer: Processed model PawanKrd/CosmosRP in 70.089s
pawankrd-cosmosrp-v58-mkmlizer: creating bucket guanaco-mkml-models
pawankrd-cosmosrp-v58-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
pawankrd-cosmosrp-v58-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/pawankrd-cosmosrp-v58
pawankrd-cosmosrp-v58-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v58/config.json
pawankrd-cosmosrp-v58-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v58/special_tokens_map.json
pawankrd-cosmosrp-v58-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v58/tokenizer.json
pawankrd-cosmosrp-v58-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v58/tokenizer_config.json
pawankrd-cosmosrp-v58-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/pawankrd-cosmosrp-v58/flywheel_model.0.safetensors
pawankrd-cosmosrp-v58-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
pawankrd-cosmosrp-v58-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-v58-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v58-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-v58-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v58-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-v58-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v58-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-v58-mkmlizer: return self.fget.__get__(instance, owner)()
pawankrd-cosmosrp-v58-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
pawankrd-cosmosrp-v58-mkmlizer: Saving duration: 0.537s
pawankrd-cosmosrp-v58-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.407s
pawankrd-cosmosrp-v58-mkmlizer: creating bucket guanaco-reward-models
pawankrd-cosmosrp-v58-mkmlizer: Bucket 's3://guanaco-reward-models/' created
pawankrd-cosmosrp-v58-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/pawankrd-cosmosrp-v58_reward
pawankrd-cosmosrp-v58-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/pawankrd-cosmosrp-v58_reward/special_tokens_map.json
pawankrd-cosmosrp-v58-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v58_reward/config.json
pawankrd-cosmosrp-v58-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v58_reward/tokenizer_config.json
pawankrd-cosmosrp-v58-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/pawankrd-cosmosrp-v58_reward/merges.txt
pawankrd-cosmosrp-v58-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/pawankrd-cosmosrp-v58_reward/vocab.json
pawankrd-cosmosrp-v58-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/pawankrd-cosmosrp-v58_reward/tokenizer.json
pawankrd-cosmosrp-v58-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/pawankrd-cosmosrp-v58_reward/reward.tensors
Job pawankrd-cosmosrp-v58-mkmlizer completed after 116.38s with status: succeeded
Stopping job with name pawankrd-cosmosrp-v58-mkmlizer
Pipeline stage MKMLizer completed in 117.27s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service pawankrd-cosmosrp-v58
Waiting for inference service pawankrd-cosmosrp-v58 to be ready
Inference service pawankrd-cosmosrp-v58 ready after 40.202232837677s
Pipeline stage ISVCDeployer completed in 47.73s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1073110103607178s
Received healthy response to inference request in 1.367985725402832s
Received healthy response to inference request in 1.9521126747131348s
Received healthy response to inference request in 1.313232421875s
Received healthy response to inference request in 1.2534520626068115s
5 requests
0 failed requests
5th percentile: 1.2654081344604493
10th percentile: 1.2773642063140869
20th percentile: 1.3012763500213622
30th percentile: 1.3241830825805665
40th percentile: 1.3460844039916993
50th percentile: 1.367985725402832
60th percentile: 1.601636505126953
70th percentile: 1.8352872848510742
80th percentile: 1.9831523418426513
90th percentile: 2.0452316761016847
95th percentile: 2.076271343231201
99th percentile: 2.1011030769348142
mean time: 1.5988187789916992
Pipeline stage StressChecker completed in 8.70s
pawankrd-cosmosrp_v58 status is now deployed due to DeploymentManager action
pawankrd-cosmosrp_v58 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics