developer_uid: PawanOsman
submission_id: pawankrd-cosmosrp_v68
model_name: pawankrd-cosmosrp_v68
model_group: PawanKrd/CosmosRP
status: torndown
timestamp: 2024-07-13T22:17:48+00:00
num_battles: 149073
num_wins: 89173
celo_rating: 1263.13
family_friendly_score: 0.0
submission_type: basic
model_repo: PawanKrd/CosmosRP
model_architecture: LlamaForCausalLM
reward_repo: Jellywibble/gpt2_xl_pairwise_89m_step_347634
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: pawankrd-cosmosrp_v68
is_internal_developer: False
language_model: PawanKrd/CosmosRP
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-13
win_ratio: 0.5981834403278931
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: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name pawankrd-cosmosrp-v68-mkmlizer
Waiting for job on pawankrd-cosmosrp-v68-mkmlizer to finish
pawankrd-cosmosrp-v68-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
pawankrd-cosmosrp-v68-mkmlizer: ║ _____ __ __ ║
pawankrd-cosmosrp-v68-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
pawankrd-cosmosrp-v68-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
pawankrd-cosmosrp-v68-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
pawankrd-cosmosrp-v68-mkmlizer: ║ /___/ ║
pawankrd-cosmosrp-v68-mkmlizer: ║ ║
pawankrd-cosmosrp-v68-mkmlizer: ║ Version: 0.8.14 ║
pawankrd-cosmosrp-v68-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
pawankrd-cosmosrp-v68-mkmlizer: ║ https://mk1.ai ║
pawankrd-cosmosrp-v68-mkmlizer: ║ ║
pawankrd-cosmosrp-v68-mkmlizer: ║ The license key for the current software has been verified as ║
pawankrd-cosmosrp-v68-mkmlizer: ║ belonging to: ║
pawankrd-cosmosrp-v68-mkmlizer: ║ ║
pawankrd-cosmosrp-v68-mkmlizer: ║ Chai Research Corp. ║
pawankrd-cosmosrp-v68-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
pawankrd-cosmosrp-v68-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
pawankrd-cosmosrp-v68-mkmlizer: ║ ║
pawankrd-cosmosrp-v68-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
pawankrd-cosmosrp-v68-mkmlizer: Downloaded to shared memory in 36.964s
pawankrd-cosmosrp-v68-mkmlizer: quantizing model to /dev/shm/model_cache
pawankrd-cosmosrp-v68-mkmlizer: Saving flywheel model at /dev/shm/model_cache
pawankrd-cosmosrp-v68-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:05<13:48, 2.87s/it] Loading 0: 4%|▍ | 13/291 [00:05<01:32, 3.01it/s] Loading 0: 8%|▊ | 24/291 [00:05<00:40, 6.58it/s] Loading 0: 14%|█▎ | 40/291 [00:06<00:18, 13.52it/s] Loading 0: 18%|█▊ | 51/291 [00:06<00:12, 19.23it/s] Loading 0: 21%|██▏ | 62/291 [00:06<00:11, 20.03it/s] Loading 0: 26%|██▌ | 76/291 [00:06<00:07, 29.40it/s] Loading 0: 30%|██▉ | 87/291 [00:06<00:05, 37.00it/s] Loading 0: 35%|███▌ | 103/291 [00:07<00:03, 50.44it/s] Loading 0: 39%|███▉ | 114/291 [00:07<00:03, 55.12it/s] Loading 0: 45%|████▍ | 130/291 [00:07<00:02, 71.33it/s] Loading 0: 49%|████▉ | 142/291 [00:07<00:01, 78.15it/s] Loading 0: 54%|█████▍ | 157/291 [00:07<00:01, 89.69it/s] Loading 0: 58%|█████▊ | 169/291 [00:08<00:02, 50.00it/s] Loading 0: 63%|██████▎ | 184/291 [00:08<00:01, 63.29it/s] Loading 0: 67%|██████▋ | 195/291 [00:08<00:01, 68.61it/s] Loading 0: 73%|███████▎ | 211/291 [00:08<00:00, 85.02it/s] Loading 0: 77%|███████▋ | 223/291 [00:08<00:00, 90.11it/s] Loading 0: 82%|████████▏ | 238/291 [00:08<00:00, 101.43it/s] Loading 0: 86%|████████▋ | 251/291 [00:08<00:00, 105.20it/s] Loading 0: 91%|█████████ | 265/291 [00:08<00:00, 112.02it/s] Loading 0: 96%|█████████▌| 278/291 [00:09<00:00, 57.12it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
pawankrd-cosmosrp-v68-mkmlizer: quantized model in 30.055s
pawankrd-cosmosrp-v68-mkmlizer: Processed model PawanKrd/CosmosRP in 67.022s
pawankrd-cosmosrp-v68-mkmlizer: creating bucket guanaco-mkml-models
pawankrd-cosmosrp-v68-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
pawankrd-cosmosrp-v68-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/pawankrd-cosmosrp-v68
pawankrd-cosmosrp-v68-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v68/special_tokens_map.json
pawankrd-cosmosrp-v68-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v68/config.json
pawankrd-cosmosrp-v68-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v68/tokenizer_config.json
pawankrd-cosmosrp-v68-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v68/tokenizer.json
pawankrd-cosmosrp-v68-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/pawankrd-cosmosrp-v68/flywheel_model.0.safetensors
pawankrd-cosmosrp-v68-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
pawankrd-cosmosrp-v68-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-v68-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v68-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-v68-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v68-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-v68-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v68-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-v68-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v68-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-v68-mkmlizer: return self.fget.__get__(instance, owner)()
pawankrd-cosmosrp-v68-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
Job pawankrd-cosmosrp-v68-mkmlizer completed after 119.05s with status: succeeded
Stopping job with name pawankrd-cosmosrp-v68-mkmlizer
Pipeline stage MKMLizer completed in 120.08s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service pawankrd-cosmosrp-v68
Waiting for inference service pawankrd-cosmosrp-v68 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service pawankrd-cosmosrp-v68 ready after 50.249966621398926s
Pipeline stage ISVCDeployer completed in 56.58s
Running pipeline stage StressChecker
Received healthy response to inference request in 5.948632001876831s
Received healthy response to inference request in 2.8730239868164062s
Received healthy response to inference request in 4.624162197113037s
Received healthy response to inference request in 1.5223798751831055s
Received healthy response to inference request in 3.3331847190856934s
5 requests
0 failed requests
5th percentile: 1.7925086975097657
10th percentile: 2.062637519836426
20th percentile: 2.602895164489746
30th percentile: 2.965056133270264
40th percentile: 3.1491204261779786
50th percentile: 3.3331847190856934
60th percentile: 3.8495757102966306
70th percentile: 4.365966701507568
80th percentile: 4.889056158065796
90th percentile: 5.418844079971313
95th percentile: 5.683738040924072
99th percentile: 5.895653209686279
mean time: 3.6602765560150146
Pipeline stage StressChecker completed in 18.86s
pawankrd-cosmosrp_v68 status is now deployed due to DeploymentManager action
pawankrd-cosmosrp_v68 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of pawankrd-cosmosrp_v68
Running pipeline stage ISVCDeleter
Checking if service pawankrd-cosmosrp-v68 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.99s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key pawankrd-cosmosrp-v68/config.json from bucket guanaco-mkml-models
Deleting key pawankrd-cosmosrp-v68/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key pawankrd-cosmosrp-v68/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key pawankrd-cosmosrp-v68/tokenizer.json from bucket guanaco-mkml-models
Deleting key pawankrd-cosmosrp-v68/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key pawankrd-cosmosrp-v68_reward/config.json from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-v68_reward/merges.txt from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-v68_reward/reward.tensors from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-v68_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-v68_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-v68_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-v68_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.85s
pawankrd-cosmosrp_v68 status is now torndown due to DeploymentManager action