submission_id: pawankrd-cosmosrp_v61
developer_uid: PawanOsman
status: inactive
model_repo: PawanKrd/CosmosRP
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.2, 'top_p': 0.95, 'min_p': 0.08, 'top_k': 60, '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: 2024-07-12T19:37:46+00:00
model_name: pawankrd-cosmosrp_v61
model_group: PawanKrd/CosmosRP
num_battles: 25730
num_wins: 14062
celo_rating: 1227.0
alignment_score: None
alignment_samples: 0
propriety_score: 0.7252262529469922
propriety_total_count: 13149.0
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_v61
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: 0.546521570151574
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name pawankrd-cosmosrp-v61-mkmlizer
Waiting for job on pawankrd-cosmosrp-v61-mkmlizer to finish
pawankrd-cosmosrp-v61-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
pawankrd-cosmosrp-v61-mkmlizer: ║ _____ __ __ ║
pawankrd-cosmosrp-v61-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
pawankrd-cosmosrp-v61-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
pawankrd-cosmosrp-v61-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
pawankrd-cosmosrp-v61-mkmlizer: ║ /___/ ║
pawankrd-cosmosrp-v61-mkmlizer: ║ ║
pawankrd-cosmosrp-v61-mkmlizer: ║ Version: 0.8.14 ║
pawankrd-cosmosrp-v61-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
pawankrd-cosmosrp-v61-mkmlizer: ║ https://mk1.ai ║
pawankrd-cosmosrp-v61-mkmlizer: ║ ║
pawankrd-cosmosrp-v61-mkmlizer: ║ The license key for the current software has been verified as ║
pawankrd-cosmosrp-v61-mkmlizer: ║ belonging to: ║
pawankrd-cosmosrp-v61-mkmlizer: ║ ║
pawankrd-cosmosrp-v61-mkmlizer: ║ Chai Research Corp. ║
pawankrd-cosmosrp-v61-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
pawankrd-cosmosrp-v61-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
pawankrd-cosmosrp-v61-mkmlizer: ║ ║
pawankrd-cosmosrp-v61-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
pawankrd-cosmosrp-v61-mkmlizer: Downloaded to shared memory in 22.715s
pawankrd-cosmosrp-v61-mkmlizer: quantizing model to /dev/shm/model_cache
pawankrd-cosmosrp-v61-mkmlizer: Saving flywheel model at /dev/shm/model_cache
pawankrd-cosmosrp-v61-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:05<13:15, 2.75s/it] Loading 0: 5%|▍ | 14/291 [00:05<01:21, 3.38it/s] Loading 0: 10%|▉ | 28/291 [00:05<00:32, 8.14it/s] Loading 0: 14%|█▍ | 41/291 [00:05<00:18, 13.87it/s] Loading 0: 19%|█▉ | 56/291 [00:05<00:10, 22.46it/s] Loading 0: 24%|██▎ | 69/291 [00:06<00:09, 23.72it/s] Loading 0: 29%|██▉ | 85/291 [00:06<00:05, 34.80it/s] Loading 0: 33%|███▎ | 97/291 [00:06<00:04, 43.26it/s] Loading 0: 38%|███▊ | 110/291 [00:06<00:03, 54.40it/s] Loading 0: 42%|████▏ | 122/291 [00:06<00:02, 64.02it/s] Loading 0: 46%|████▌ | 134/291 [00:06<00:02, 73.53it/s] Loading 0: 51%|█████ | 148/291 [00:07<00:01, 86.01it/s] Loading 0: 55%|█████▌ | 161/291 [00:07<00:01, 92.96it/s] Loading 0: 59%|█████▉ | 173/291 [00:07<00:02, 55.37it/s] Loading 0: 63%|██████▎ | 184/291 [00:07<00:01, 63.32it/s] Loading 0: 67%|██████▋ | 195/291 [00:07<00:01, 71.20it/s] Loading 0: 73%|███████▎ | 211/291 [00:07<00:00, 88.27it/s] Loading 0: 77%|███████▋ | 223/291 [00:08<00:00, 94.10it/s] Loading 0: 82%|████████▏ | 238/291 [00:08<00:00, 106.71it/s] Loading 0: 86%|████████▋ | 251/291 [00:08<00:00, 109.40it/s] Loading 0: 91%|█████████▏| 266/291 [00:08<00:00, 62.19it/s] Loading 0: 96%|█████████▌| 279/291 [00:08<00:00, 72.79it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
pawankrd-cosmosrp-v61-mkmlizer: quantized model in 28.700s
pawankrd-cosmosrp-v61-mkmlizer: Processed model PawanKrd/CosmosRP in 51.416s
pawankrd-cosmosrp-v61-mkmlizer: creating bucket guanaco-mkml-models
pawankrd-cosmosrp-v61-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
pawankrd-cosmosrp-v61-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/pawankrd-cosmosrp-v61
pawankrd-cosmosrp-v61-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v61/tokenizer_config.json
pawankrd-cosmosrp-v61-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v61/special_tokens_map.json
pawankrd-cosmosrp-v61-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v61/config.json
pawankrd-cosmosrp-v61-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v61/tokenizer.json
pawankrd-cosmosrp-v61-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/pawankrd-cosmosrp-v61/flywheel_model.0.safetensors
pawankrd-cosmosrp-v61-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
pawankrd-cosmosrp-v61-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-v61-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v61-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-v61-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v61-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-v61-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v61-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-v61-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v61-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-v61-mkmlizer: return self.fget.__get__(instance, owner)()
pawankrd-cosmosrp-v61-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
pawankrd-cosmosrp-v61-mkmlizer: Saving duration: 0.505s
pawankrd-cosmosrp-v61-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.513s
pawankrd-cosmosrp-v61-mkmlizer: creating bucket guanaco-reward-models
pawankrd-cosmosrp-v61-mkmlizer: Bucket 's3://guanaco-reward-models/' created
pawankrd-cosmosrp-v61-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/pawankrd-cosmosrp-v61_reward
pawankrd-cosmosrp-v61-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v61_reward/config.json
pawankrd-cosmosrp-v61-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/pawankrd-cosmosrp-v61_reward/vocab.json
pawankrd-cosmosrp-v61-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v61_reward/tokenizer_config.json
pawankrd-cosmosrp-v61-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/pawankrd-cosmosrp-v61_reward/merges.txt
pawankrd-cosmosrp-v61-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/pawankrd-cosmosrp-v61_reward/special_tokens_map.json
pawankrd-cosmosrp-v61-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/pawankrd-cosmosrp-v61_reward/tokenizer.json
pawankrd-cosmosrp-v61-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/pawankrd-cosmosrp-v61_reward/reward.tensors
Job pawankrd-cosmosrp-v61-mkmlizer completed after 83.94s with status: succeeded
Stopping job with name pawankrd-cosmosrp-v61-mkmlizer
Pipeline stage MKMLizer completed in 85.20s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service pawankrd-cosmosrp-v61
Waiting for inference service pawankrd-cosmosrp-v61 to be ready
Inference service pawankrd-cosmosrp-v61 ready after 40.253403663635254s
Pipeline stage ISVCDeployer completed in 47.10s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1100988388061523s
Received healthy response to inference request in 1.432135820388794s
Received healthy response to inference request in 1.4334094524383545s
Received healthy response to inference request in 1.3189213275909424s
Received healthy response to inference request in 1.264085292816162s
5 requests
0 failed requests
5th percentile: 1.2750524997711181
10th percentile: 1.2860197067260741
20th percentile: 1.3079541206359864
30th percentile: 1.3415642261505127
40th percentile: 1.3868500232696532
50th percentile: 1.432135820388794
60th percentile: 1.4326452732086181
70th percentile: 1.4331547260284423
80th percentile: 1.568747329711914
90th percentile: 1.8394230842590333
95th percentile: 1.9747609615325927
99th percentile: 2.0830312633514403
mean time: 1.511730146408081
Pipeline stage StressChecker completed in 8.22s
pawankrd-cosmosrp_v61 status is now deployed due to DeploymentManager action
pawankrd-cosmosrp_v61 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics