submission_id: pawankrd-cosmosrp_v51
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: 2024-07-09T18:51:10+00:00
model_name: pawankrd-cosmosrp_v51
model_group: PawanKrd/CosmosRP
num_battles: 30086
num_wins: 14706
celo_rating: 1184.82
propriety_score: 0.766372677800713
propriety_total_count: 5329.0
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_v51
ineligible_reason: None
language_model: PawanKrd/CosmosRP
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-09
win_ratio: 0.4887987768397261
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name pawankrd-cosmosrp-v51-mkmlizer
Waiting for job on pawankrd-cosmosrp-v51-mkmlizer to finish
pawankrd-cosmosrp-v51-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
pawankrd-cosmosrp-v51-mkmlizer: ║ _____ __ __ ║
pawankrd-cosmosrp-v51-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
pawankrd-cosmosrp-v51-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
pawankrd-cosmosrp-v51-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
pawankrd-cosmosrp-v51-mkmlizer: ║ /___/ ║
pawankrd-cosmosrp-v51-mkmlizer: ║ ║
pawankrd-cosmosrp-v51-mkmlizer: ║ Version: 0.8.14 ║
pawankrd-cosmosrp-v51-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
pawankrd-cosmosrp-v51-mkmlizer: ║ https://mk1.ai ║
pawankrd-cosmosrp-v51-mkmlizer: ║ ║
pawankrd-cosmosrp-v51-mkmlizer: ║ The license key for the current software has been verified as ║
pawankrd-cosmosrp-v51-mkmlizer: ║ belonging to: ║
pawankrd-cosmosrp-v51-mkmlizer: ║ ║
pawankrd-cosmosrp-v51-mkmlizer: ║ Chai Research Corp. ║
pawankrd-cosmosrp-v51-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
pawankrd-cosmosrp-v51-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
pawankrd-cosmosrp-v51-mkmlizer: ║ ║
pawankrd-cosmosrp-v51-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
pawankrd-cosmosrp-v51-mkmlizer: Downloaded to shared memory in 39.715s
pawankrd-cosmosrp-v51-mkmlizer: quantizing model to /dev/shm/model_cache
pawankrd-cosmosrp-v51-mkmlizer: Saving flywheel model at /dev/shm/model_cache
pawankrd-cosmosrp-v51-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 111.13it/s] Loading 0: 9%|▉ | 26/291 [00:00<00:02, 119.87it/s] Loading 0: 13%|█▎ | 39/291 [00:00<00:02, 122.29it/s] Loading 0: 18%|█▊ | 52/291 [00:00<00:02, 117.06it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 120.08it/s] Loading 0: 27%|██▋ | 79/291 [00:00<00:01, 118.01it/s] Loading 0: 31%|███▏ | 91/291 [00:01<00:03, 56.70it/s] Loading 0: 35%|███▌ | 103/291 [00:01<00:02, 66.71it/s] Loading 0: 40%|███▉ | 116/291 [00:01<00:02, 78.41it/s] Loading 0: 45%|████▍ | 130/291 [00:01<00:01, 88.36it/s] Loading 0: 49%|████▉ | 142/291 [00:01<00:01, 95.27it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:01, 104.34it/s] Loading 0: 58%|█████▊ | 168/291 [00:01<00:01, 103.57it/s] Loading 0: 62%|██████▏ | 181/291 [00:01<00:01, 108.75it/s] Loading 0: 66%|██████▋ | 193/291 [00:02<00:01, 57.91it/s] Loading 0: 71%|███████ | 207/291 [00:02<00:01, 70.74it/s] Loading 0: 75%|███████▌ | 219/291 [00:02<00:00, 80.03it/s] Loading 0: 79%|███████▉ | 230/291 [00:02<00:00, 85.03it/s] Loading 0: 85%|████████▍ | 246/291 [00:02<00:00, 101.00it/s] Loading 0: 89%|████████▊ | 258/291 [00:02<00:00, 102.90it/s] Loading 0: 94%|█████████▍| 273/291 [00:02<00:00, 112.72it/s] Loading 0: 98%|█████████▊| 286/291 [00:03<00:00, 115.92it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
pawankrd-cosmosrp-v51-mkmlizer: quantized model in 29.212s
pawankrd-cosmosrp-v51-mkmlizer: Processed model PawanKrd/CosmosRP in 68.927s
pawankrd-cosmosrp-v51-mkmlizer: creating bucket guanaco-mkml-models
pawankrd-cosmosrp-v51-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
pawankrd-cosmosrp-v51-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/pawankrd-cosmosrp-v51
pawankrd-cosmosrp-v51-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v51/tokenizer_config.json
pawankrd-cosmosrp-v51-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v51/special_tokens_map.json
pawankrd-cosmosrp-v51-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v51/config.json
pawankrd-cosmosrp-v51-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v51/tokenizer.json
pawankrd-cosmosrp-v51-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/pawankrd-cosmosrp-v51/flywheel_model.0.safetensors
pawankrd-cosmosrp-v51-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
pawankrd-cosmosrp-v51-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-v51-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v51-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-v51-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v51-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-v51-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v51-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-v51-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v51-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-v51-mkmlizer: return self.fget.__get__(instance, owner)()
pawankrd-cosmosrp-v51-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
pawankrd-cosmosrp-v51-mkmlizer: Saving duration: 0.519s
pawankrd-cosmosrp-v51-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.742s
pawankrd-cosmosrp-v51-mkmlizer: creating bucket guanaco-reward-models
pawankrd-cosmosrp-v51-mkmlizer: Bucket 's3://guanaco-reward-models/' created
pawankrd-cosmosrp-v51-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/pawankrd-cosmosrp-v51_reward
pawankrd-cosmosrp-v51-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v51_reward/config.json
pawankrd-cosmosrp-v51-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/pawankrd-cosmosrp-v51_reward/special_tokens_map.json
pawankrd-cosmosrp-v51-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v51_reward/tokenizer_config.json
pawankrd-cosmosrp-v51-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/pawankrd-cosmosrp-v51_reward/vocab.json
pawankrd-cosmosrp-v51-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/pawankrd-cosmosrp-v51_reward/merges.txt
pawankrd-cosmosrp-v51-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/pawankrd-cosmosrp-v51_reward/tokenizer.json
pawankrd-cosmosrp-v51-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/pawankrd-cosmosrp-v51_reward/reward.tensors
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Job pawankrd-cosmosrp-v51-mkmlizer completed after 146.93s with status: succeeded
Stopping job with name pawankrd-cosmosrp-v51-mkmlizer
Pipeline stage MKMLizer completed in 147.73s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service pawankrd-cosmosrp-v51
Waiting for inference service pawankrd-cosmosrp-v51 to be ready
Connection pool is full, discarding connection: %s
Inference service pawankrd-cosmosrp-v51 ready after 40.21588969230652s
Pipeline stage ISVCDeployer completed in 46.89s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.110585927963257s
Received healthy response to inference request in 1.3684196472167969s
Received healthy response to inference request in 1.3444297313690186s
Received healthy response to inference request in 1.3150174617767334s
Received healthy response to inference request in 1.2688701152801514s
5 requests
0 failed requests
5th percentile: 1.2780995845794678
10th percentile: 1.2873290538787843
20th percentile: 1.305787992477417
30th percentile: 1.3208999156951904
40th percentile: 1.3326648235321046
50th percentile: 1.3444297313690186
60th percentile: 1.35402569770813
70th percentile: 1.3636216640472412
80th percentile: 1.516852903366089
90th percentile: 1.813719415664673
95th percentile: 1.9621526718139648
99th percentile: 2.0808992767333985
mean time: 1.4814645767211914
Pipeline stage StressChecker completed in 8.04s
pawankrd-cosmosrp_v51 status is now deployed due to DeploymentManager action
pawankrd-cosmosrp_v51 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics