submission_id: pawankrd-cosmosrp_v64
developer_uid: PawanOsman
status: inactive
model_repo: PawanKrd/CosmosRP
reward_repo: Jellywibble/gpt2_xl_pairwise_89m_step_347634
generation_params: {'temperature': 1.0, '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: 2024-07-13T06:10:39+00:00
model_name: pawankrd-cosmosrp_v64
model_group: PawanKrd/CosmosRP
num_battles: 112573
num_wins: 62783
celo_rating: 1266.54
propriety_score: 0.7287871853546911
propriety_total_count: 10925.0
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_v64
ineligible_reason: None
language_model: PawanKrd/CosmosRP
model_size: 8B
reward_model: Jellywibble/gpt2_xl_pairwise_89m_step_347634
us_pacific_date: 2024-07-12
win_ratio: 0.5577092197951552
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name pawankrd-cosmosrp-v64-mkmlizer
Waiting for job on pawankrd-cosmosrp-v64-mkmlizer to finish
pawankrd-cosmosrp-v64-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
pawankrd-cosmosrp-v64-mkmlizer: ║ _____ __ __ ║
pawankrd-cosmosrp-v64-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
pawankrd-cosmosrp-v64-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
pawankrd-cosmosrp-v64-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
pawankrd-cosmosrp-v64-mkmlizer: ║ /___/ ║
pawankrd-cosmosrp-v64-mkmlizer: ║ ║
pawankrd-cosmosrp-v64-mkmlizer: ║ Version: 0.8.14 ║
pawankrd-cosmosrp-v64-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
pawankrd-cosmosrp-v64-mkmlizer: ║ https://mk1.ai ║
pawankrd-cosmosrp-v64-mkmlizer: ║ ║
pawankrd-cosmosrp-v64-mkmlizer: ║ The license key for the current software has been verified as ║
pawankrd-cosmosrp-v64-mkmlizer: ║ belonging to: ║
pawankrd-cosmosrp-v64-mkmlizer: ║ ║
pawankrd-cosmosrp-v64-mkmlizer: ║ Chai Research Corp. ║
pawankrd-cosmosrp-v64-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
pawankrd-cosmosrp-v64-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
pawankrd-cosmosrp-v64-mkmlizer: ║ ║
pawankrd-cosmosrp-v64-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
pawankrd-cosmosrp-v64-mkmlizer: Downloaded to shared memory in 24.870s
pawankrd-cosmosrp-v64-mkmlizer: quantizing model to /dev/shm/model_cache
pawankrd-cosmosrp-v64-mkmlizer: Saving flywheel model at /dev/shm/model_cache
pawankrd-cosmosrp-v64-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:05<12:05, 2.51s/it] Loading 0: 4%|▍ | 11/291 [00:05<01:37, 2.88it/s] Loading 0: 7%|▋ | 20/291 [00:05<00:43, 6.18it/s] Loading 0: 10%|▉ | 28/291 [00:05<00:26, 9.97it/s] Loading 0: 12%|█▏ | 36/291 [00:05<00:18, 13.58it/s] Loading 0: 15%|█▌ | 45/291 [00:05<00:12, 19.78it/s] Loading 0: 19%|█▊ | 54/291 [00:05<00:08, 27.05it/s] Loading 0: 21%|██▏ | 62/291 [00:06<00:09, 23.69it/s] Loading 0: 24%|██▍ | 71/291 [00:06<00:07, 31.29it/s] Loading 0: 28%|██▊ | 81/291 [00:06<00:05, 40.88it/s] Loading 0: 33%|███▎ | 95/291 [00:06<00:03, 56.02it/s] Loading 0: 37%|███▋ | 109/291 [00:06<00:02, 71.48it/s] Loading 0: 42%|████▏ | 121/291 [00:06<00:02, 79.74it/s] Loading 0: 45%|████▌ | 132/291 [00:06<00:02, 76.79it/s] Loading 0: 49%|████▉ | 142/291 [00:06<00:01, 81.83it/s] Loading 0: 52%|█████▏ | 152/291 [00:07<00:01, 85.80it/s] Loading 0: 56%|█████▌ | 162/291 [00:07<00:01, 87.41it/s] Loading 0: 59%|█████▉ | 172/291 [00:07<00:02, 50.08it/s] Loading 0: 64%|██████▎ | 185/291 [00:07<00:01, 62.91it/s] Loading 0: 67%|██████▋ | 195/291 [00:07<00:01, 68.47it/s] Loading 0: 70%|███████ | 204/291 [00:07<00:01, 71.80it/s] Loading 0: 73%|███████▎ | 213/291 [00:08<00:01, 69.53it/s] Loading 0: 76%|███████▋ | 222/291 [00:08<00:00, 74.17it/s] Loading 0: 79%|███████▉ | 231/291 [00:08<00:00, 78.10it/s] Loading 0: 83%|████████▎ | 241/291 [00:08<00:00, 83.68it/s] Loading 0: 86%|████████▌ | 250/291 [00:08<00:00, 84.39it/s] Loading 0: 89%|████████▉ | 259/291 [00:08<00:00, 85.49it/s] Loading 0: 92%|█████████▏| 268/291 [00:08<00:00, 48.50it/s] Loading 0: 97%|█████████▋| 283/291 [00:09<00:00, 64.75it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
pawankrd-cosmosrp-v64-mkmlizer: quantized model in 30.286s
pawankrd-cosmosrp-v64-mkmlizer: Processed model PawanKrd/CosmosRP in 55.156s
pawankrd-cosmosrp-v64-mkmlizer: creating bucket guanaco-mkml-models
pawankrd-cosmosrp-v64-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
pawankrd-cosmosrp-v64-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/pawankrd-cosmosrp-v64
pawankrd-cosmosrp-v64-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v64/tokenizer.json
pawankrd-cosmosrp-v64-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v64/special_tokens_map.json
pawankrd-cosmosrp-v64-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v64/tokenizer_config.json
pawankrd-cosmosrp-v64-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v64/config.json
pawankrd-cosmosrp-v64-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/pawankrd-cosmosrp-v64/flywheel_model.0.safetensors
pawankrd-cosmosrp-v64-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
pawankrd-cosmosrp-v64-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-v64-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v64-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-v64-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v64-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-v64-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v64-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-v64-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v64-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-v64-mkmlizer: return self.fget.__get__(instance, owner)()
pawankrd-cosmosrp-v64-mkmlizer: Saving duration: 3.973s
pawankrd-cosmosrp-v64-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 18.065s
pawankrd-cosmosrp-v64-mkmlizer: creating bucket guanaco-reward-models
pawankrd-cosmosrp-v64-mkmlizer: Bucket 's3://guanaco-reward-models/' created
pawankrd-cosmosrp-v64-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/pawankrd-cosmosrp-v64_reward
pawankrd-cosmosrp-v64-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v64_reward/config.json
pawankrd-cosmosrp-v64-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/pawankrd-cosmosrp-v64_reward/special_tokens_map.json
pawankrd-cosmosrp-v64-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v64_reward/tokenizer_config.json
pawankrd-cosmosrp-v64-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/pawankrd-cosmosrp-v64_reward/merges.txt
pawankrd-cosmosrp-v64-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/pawankrd-cosmosrp-v64_reward/tokenizer.json
pawankrd-cosmosrp-v64-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/pawankrd-cosmosrp-v64_reward/vocab.json
pawankrd-cosmosrp-v64-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/pawankrd-cosmosrp-v64_reward/reward.tensors
Job pawankrd-cosmosrp-v64-mkmlizer completed after 227.3s with status: succeeded
Stopping job with name pawankrd-cosmosrp-v64-mkmlizer
Pipeline stage MKMLizer completed in 228.40s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service pawankrd-cosmosrp-v64
Waiting for inference service pawankrd-cosmosrp-v64 to be ready
Inference service pawankrd-cosmosrp-v64 ready after 50.23192644119263s
Pipeline stage ISVCDeployer completed in 57.14s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5966625213623047s
Received healthy response to inference request in 1.7448785305023193s
Received healthy response to inference request in 1.5469167232513428s
Received healthy response to inference request in 6.184978246688843s
Received healthy response to inference request in 4.012150764465332s
5 requests
0 failed requests
5th percentile: 1.5865090847015382
10th percentile: 1.6261014461517334
20th percentile: 1.705286169052124
30th percentile: 1.9152353286743165
40th percentile: 2.2559489250183105
50th percentile: 2.5966625213623047
60th percentile: 3.1628578186035154
70th percentile: 3.729053115844726
80th percentile: 4.446716260910034
90th percentile: 5.315847253799439
95th percentile: 5.7504127502441404
99th percentile: 6.098065147399902
mean time: 3.217117357254028
Pipeline stage StressChecker completed in 17.01s
pawankrd-cosmosrp_v64 status is now deployed due to DeploymentManager action
pawankrd-cosmosrp_v64 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics