submission_id: pawankrd-cosmosrp_v46
developer_uid: PawanOsman
status: inactive
model_repo: PawanKrd/CosmosRP
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.9, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, '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': "<|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: 2024-07-08T13:45:53+00:00
model_name: pawankrd-cosmosrp_v46
model_group: PawanKrd/CosmosRP
num_battles: 31106
num_wins: 17099
celo_rating: 1239.5
alignment_score: None
alignment_samples: 0
propriety_score: 0.6942698706099815
propriety_total_count: 5410.0
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_v46
ineligible_reason: None
language_model: PawanKrd/CosmosRP
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-08
win_ratio: 0.5497010223108082
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name pawankrd-cosmosrp-v46-mkmlizer
Waiting for job on pawankrd-cosmosrp-v46-mkmlizer to finish
pawankrd-cosmosrp-v46-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
pawankrd-cosmosrp-v46-mkmlizer: ║ _____ __ __ ║
pawankrd-cosmosrp-v46-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
pawankrd-cosmosrp-v46-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
pawankrd-cosmosrp-v46-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
pawankrd-cosmosrp-v46-mkmlizer: ║ /___/ ║
pawankrd-cosmosrp-v46-mkmlizer: ║ ║
pawankrd-cosmosrp-v46-mkmlizer: ║ Version: 0.8.14 ║
pawankrd-cosmosrp-v46-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
pawankrd-cosmosrp-v46-mkmlizer: ║ https://mk1.ai ║
pawankrd-cosmosrp-v46-mkmlizer: ║ ║
pawankrd-cosmosrp-v46-mkmlizer: ║ The license key for the current software has been verified as ║
pawankrd-cosmosrp-v46-mkmlizer: ║ belonging to: ║
pawankrd-cosmosrp-v46-mkmlizer: ║ ║
pawankrd-cosmosrp-v46-mkmlizer: ║ Chai Research Corp. ║
pawankrd-cosmosrp-v46-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
pawankrd-cosmosrp-v46-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
pawankrd-cosmosrp-v46-mkmlizer: ║ ║
pawankrd-cosmosrp-v46-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
pawankrd-cosmosrp-v46-mkmlizer: Downloaded to shared memory in 42.801s
pawankrd-cosmosrp-v46-mkmlizer: quantizing model to /dev/shm/model_cache
pawankrd-cosmosrp-v46-mkmlizer: Saving flywheel model at /dev/shm/model_cache
pawankrd-cosmosrp-v46-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:02, 99.31it/s] Loading 0: 8%|▊ | 22/291 [00:00<00:02, 92.88it/s] Loading 0: 11%|█ | 32/291 [00:00<00:03, 84.87it/s] Loading 0: 14%|█▍ | 42/291 [00:00<00:02, 90.11it/s] Loading 0: 20%|█▉ | 57/291 [00:00<00:02, 105.29it/s] Loading 0: 23%|██▎ | 68/291 [00:00<00:02, 102.97it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:03, 60.78it/s] Loading 0: 32%|███▏ | 92/291 [00:01<00:03, 66.04it/s] Loading 0: 35%|███▌ | 102/291 [00:01<00:02, 69.80it/s] Loading 0: 38%|███▊ | 111/291 [00:01<00:02, 72.97it/s] Loading 0: 41%|████ | 120/291 [00:01<00:02, 75.74it/s] Loading 0: 44%|████▍ | 129/291 [00:01<00:02, 76.68it/s] Loading 0: 47%|████▋ | 138/291 [00:01<00:01, 78.29it/s] Loading 0: 51%|█████ | 148/291 [00:01<00:01, 81.34it/s] Loading 0: 54%|█████▍ | 157/291 [00:01<00:01, 82.41it/s] Loading 0: 57%|█████▋ | 167/291 [00:02<00:01, 83.96it/s] Loading 0: 62%|██████▏ | 180/291 [00:02<00:01, 94.57it/s] Loading 0: 65%|██████▌ | 190/291 [00:02<00:01, 52.22it/s] Loading 0: 69%|██████▉ | 201/291 [00:02<00:01, 61.40it/s] Loading 0: 73%|███████▎ | 211/291 [00:02<00:01, 67.79it/s] Loading 0: 76%|███████▌ | 221/291 [00:02<00:00, 74.76it/s] Loading 0: 81%|████████▏ | 237/291 [00:03<00:00, 91.01it/s] Loading 0: 85%|████████▌ | 248/291 [00:03<00:00, 87.41it/s] Loading 0: 91%|█████████ | 264/291 [00:03<00:00, 100.23it/s] Loading 0: 95%|█████████▍| 275/291 [00:03<00:00, 90.87it/s] Loading 0: 99%|█████████▊| 287/291 [00:09<00:00, 6.20it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
pawankrd-cosmosrp-v46-mkmlizer: quantized model in 26.137s
pawankrd-cosmosrp-v46-mkmlizer: Processed model PawanKrd/CosmosRP in 68.938s
pawankrd-cosmosrp-v46-mkmlizer: creating bucket guanaco-mkml-models
pawankrd-cosmosrp-v46-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
pawankrd-cosmosrp-v46-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/pawankrd-cosmosrp-v46
pawankrd-cosmosrp-v46-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v46/config.json
pawankrd-cosmosrp-v46-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v46/special_tokens_map.json
pawankrd-cosmosrp-v46-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v46/tokenizer_config.json
pawankrd-cosmosrp-v46-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v46/tokenizer.json
pawankrd-cosmosrp-v46-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/pawankrd-cosmosrp-v46/flywheel_model.0.safetensors
pawankrd-cosmosrp-v46-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-v46-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v46-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-v46-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v46-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-v46-mkmlizer: return self.fget.__get__(instance, owner)()
pawankrd-cosmosrp-v46-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
pawankrd-cosmosrp-v46-mkmlizer: Saving duration: 0.478s
pawankrd-cosmosrp-v46-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.835s
pawankrd-cosmosrp-v46-mkmlizer: creating bucket guanaco-reward-models
pawankrd-cosmosrp-v46-mkmlizer: Bucket 's3://guanaco-reward-models/' created
pawankrd-cosmosrp-v46-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/pawankrd-cosmosrp-v46_reward
pawankrd-cosmosrp-v46-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/pawankrd-cosmosrp-v46_reward/special_tokens_map.json
pawankrd-cosmosrp-v46-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v46_reward/tokenizer_config.json
pawankrd-cosmosrp-v46-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v46_reward/config.json
pawankrd-cosmosrp-v46-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/pawankrd-cosmosrp-v46_reward/merges.txt
pawankrd-cosmosrp-v46-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/pawankrd-cosmosrp-v46_reward/vocab.json
pawankrd-cosmosrp-v46-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/pawankrd-cosmosrp-v46_reward/tokenizer.json
pawankrd-cosmosrp-v46-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/pawankrd-cosmosrp-v46_reward/reward.tensors
Job pawankrd-cosmosrp-v46-mkmlizer completed after 114.71s with status: succeeded
Stopping job with name pawankrd-cosmosrp-v46-mkmlizer
Pipeline stage MKMLizer completed in 115.91s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service pawankrd-cosmosrp-v46
Waiting for inference service pawankrd-cosmosrp-v46 to be ready
Inference service pawankrd-cosmosrp-v46 ready after 50.23412322998047s
Pipeline stage ISVCDeployer completed in 57.25s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1242923736572266s
Received healthy response to inference request in 1.421234369277954s
Received healthy response to inference request in 1.4306800365447998s
Received healthy response to inference request in 1.375396490097046s
Received healthy response to inference request in 1.344444990158081s
5 requests
0 failed requests
5th percentile: 1.350635290145874
10th percentile: 1.356825590133667
20th percentile: 1.369206190109253
30th percentile: 1.3845640659332275
40th percentile: 1.4028992176055908
50th percentile: 1.421234369277954
60th percentile: 1.4250126361846924
70th percentile: 1.4287909030914308
80th percentile: 1.5694025039672852
90th percentile: 1.846847438812256
95th percentile: 1.9855699062347412
99th percentile: 2.0965478801727295
mean time: 1.5392096519470215
Pipeline stage StressChecker completed in 8.33s
pawankrd-cosmosrp_v46 status is now deployed due to DeploymentManager action
pawankrd-cosmosrp_v46 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics