submission_id: pawankrd-cosmosrp_v57
developer_uid: PawanOsman
status: inactive
model_repo: PawanKrd/CosmosRP
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.5, '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: 2024-07-10T07:53:06+00:00
model_name: pawankrd-cosmosrp_v57
model_group: PawanKrd/CosmosRP
num_battles: 36770
num_wins: 17771
celo_rating: 1178.89
propriety_score: 0.751818916734034
propriety_total_count: 6185.0
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_v57
ineligible_reason: None
language_model: PawanKrd/CosmosRP
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-10
win_ratio: 0.48330160456894206
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name pawankrd-cosmosrp-v57-mkmlizer
Waiting for job on pawankrd-cosmosrp-v57-mkmlizer to finish
pawankrd-cosmosrp-v57-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
pawankrd-cosmosrp-v57-mkmlizer: ║ _____ __ __ ║
pawankrd-cosmosrp-v57-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
pawankrd-cosmosrp-v57-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
pawankrd-cosmosrp-v57-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
pawankrd-cosmosrp-v57-mkmlizer: ║ /___/ ║
pawankrd-cosmosrp-v57-mkmlizer: ║ ║
pawankrd-cosmosrp-v57-mkmlizer: ║ Version: 0.8.14 ║
pawankrd-cosmosrp-v57-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
pawankrd-cosmosrp-v57-mkmlizer: ║ https://mk1.ai ║
pawankrd-cosmosrp-v57-mkmlizer: ║ ║
pawankrd-cosmosrp-v57-mkmlizer: ║ The license key for the current software has been verified as ║
pawankrd-cosmosrp-v57-mkmlizer: ║ belonging to: ║
pawankrd-cosmosrp-v57-mkmlizer: ║ ║
pawankrd-cosmosrp-v57-mkmlizer: ║ Chai Research Corp. ║
pawankrd-cosmosrp-v57-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
pawankrd-cosmosrp-v57-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
pawankrd-cosmosrp-v57-mkmlizer: ║ ║
pawankrd-cosmosrp-v57-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
pawankrd-cosmosrp-v57-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 116.64it/s] Loading 0: 10%|▉ | 28/291 [00:00<00:01, 134.23it/s] Loading 0: 14%|█▍ | 42/291 [00:00<00:02, 124.17it/s] Loading 0: 20%|█▉ | 57/291 [00:00<00:01, 131.51it/s] Loading 0: 24%|██▍ | 71/291 [00:00<00:01, 129.30it/s] Loading 0: 29%|██▉ | 85/291 [00:01<00:03, 59.28it/s] Loading 0: 34%|███▍ | 99/291 [00:01<00:02, 72.74it/s] Loading 0: 38%|███▊ | 112/291 [00:01<00:02, 81.37it/s] Loading 0: 43%|████▎ | 126/291 [00:01<00:01, 93.53it/s] Loading 0: 48%|████▊ | 139/291 [00:01<00:01, 98.68it/s] Loading 0: 53%|█████▎ | 154/291 [00:01<00:01, 110.86it/s] Loading 0: 57%|█████▋ | 167/291 [00:01<00:01, 109.51it/s] Loading 0: 62%|██████▏ | 181/291 [00:01<00:00, 117.37it/s] Loading 0: 67%|██████▋ | 194/291 [00:02<00:01, 61.22it/s] Loading 0: 73%|███████▎ | 211/291 [00:02<00:01, 76.73it/s] Loading 0: 77%|███████▋ | 225/291 [00:02<00:00, 88.15it/s] Loading 0: 82%|████████▏ | 238/291 [00:02<00:00, 95.35it/s] Loading 0: 88%|████████▊ | 255/291 [00:02<00:00, 107.99it/s] Loading 0: 92%|█████████▏| 268/291 [00:02<00:00, 111.91it/s] Loading 0: 97%|█████████▋| 281/291 [00:02<00:00, 114.97it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
pawankrd-cosmosrp-v57-mkmlizer: quantized model in 29.078s
pawankrd-cosmosrp-v57-mkmlizer: Processed model PawanKrd/CosmosRP in 55.812s
pawankrd-cosmosrp-v57-mkmlizer: creating bucket guanaco-mkml-models
pawankrd-cosmosrp-v57-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
pawankrd-cosmosrp-v57-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/pawankrd-cosmosrp-v57
pawankrd-cosmosrp-v57-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v57/config.json
pawankrd-cosmosrp-v57-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v57/tokenizer_config.json
pawankrd-cosmosrp-v57-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v57/special_tokens_map.json
pawankrd-cosmosrp-v57-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v57/tokenizer.json
pawankrd-cosmosrp-v57-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/pawankrd-cosmosrp-v57/flywheel_model.0.safetensors
pawankrd-cosmosrp-v57-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
pawankrd-cosmosrp-v57-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-v57-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v57-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-v57-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v57-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-v57-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v57-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-v57-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v57-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-v57-mkmlizer: return self.fget.__get__(instance, owner)()
pawankrd-cosmosrp-v57-mkmlizer: Saving duration: 0.525s
pawankrd-cosmosrp-v57-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.740s
pawankrd-cosmosrp-v57-mkmlizer: creating bucket guanaco-reward-models
pawankrd-cosmosrp-v57-mkmlizer: Bucket 's3://guanaco-reward-models/' created
pawankrd-cosmosrp-v57-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/pawankrd-cosmosrp-v57_reward
pawankrd-cosmosrp-v57-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v57_reward/config.json
pawankrd-cosmosrp-v57-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v57_reward/tokenizer_config.json
pawankrd-cosmosrp-v57-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/pawankrd-cosmosrp-v57_reward/special_tokens_map.json
pawankrd-cosmosrp-v57-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/pawankrd-cosmosrp-v57_reward/vocab.json
pawankrd-cosmosrp-v57-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/pawankrd-cosmosrp-v57_reward/merges.txt
pawankrd-cosmosrp-v57-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/pawankrd-cosmosrp-v57_reward/tokenizer.json
pawankrd-cosmosrp-v57-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/pawankrd-cosmosrp-v57_reward/reward.tensors
Job pawankrd-cosmosrp-v57-mkmlizer completed after 83.32s with status: succeeded
Stopping job with name pawankrd-cosmosrp-v57-mkmlizer
Pipeline stage MKMLizer completed in 84.21s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.15s
Running pipeline stage ISVCDeployer
Creating inference service pawankrd-cosmosrp-v57
Waiting for inference service pawankrd-cosmosrp-v57 to be ready
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Inference service pawankrd-cosmosrp-v57 ready after 40.179949045181274s
Pipeline stage ISVCDeployer completed in 47.37s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0757009983062744s
Received healthy response to inference request in 1.375913381576538s
Received healthy response to inference request in 1.352294921875s
Received healthy response to inference request in 1.316371202468872s
Received healthy response to inference request in 1.2875831127166748s
5 requests
0 failed requests
5th percentile: 1.2933407306671143
10th percentile: 1.2990983486175538
20th percentile: 1.3106135845184326
30th percentile: 1.3235559463500977
40th percentile: 1.3379254341125488
50th percentile: 1.352294921875
60th percentile: 1.3617423057556153
70th percentile: 1.3711896896362306
80th percentile: 1.5158709049224854
90th percentile: 1.79578595161438
95th percentile: 1.935743474960327
99th percentile: 2.0477094936370848
mean time: 1.481572723388672
Pipeline stage StressChecker completed in 8.21s
pawankrd-cosmosrp_v57 status is now deployed due to DeploymentManager action
pawankrd-cosmosrp_v57 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics