submission_id: pawankrd-cosmosrp_v47
developer_uid: PawanOsman
status: inactive
model_repo: PawanKrd/CosmosRP
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.9, '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: 2024-07-08T21:37:42+00:00
model_name: pawankrd-cosmosrp_v47
model_group: PawanKrd/CosmosRP
num_battles: 31531
num_wins: 15322
celo_rating: 1185.38
propriety_score: 0.7454215775158658
propriety_total_count: 5515.0
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_v47
ineligible_reason: None
language_model: PawanKrd/CosmosRP
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-08
win_ratio: 0.48593447718118676
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name pawankrd-cosmosrp-v47-mkmlizer
Waiting for job on pawankrd-cosmosrp-v47-mkmlizer to finish
pawankrd-cosmosrp-v47-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
pawankrd-cosmosrp-v47-mkmlizer: ║ _____ __ __ ║
pawankrd-cosmosrp-v47-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
pawankrd-cosmosrp-v47-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
pawankrd-cosmosrp-v47-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
pawankrd-cosmosrp-v47-mkmlizer: ║ /___/ ║
pawankrd-cosmosrp-v47-mkmlizer: ║ ║
pawankrd-cosmosrp-v47-mkmlizer: ║ Version: 0.8.14 ║
pawankrd-cosmosrp-v47-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
pawankrd-cosmosrp-v47-mkmlizer: ║ https://mk1.ai ║
pawankrd-cosmosrp-v47-mkmlizer: ║ ║
pawankrd-cosmosrp-v47-mkmlizer: ║ The license key for the current software has been verified as ║
pawankrd-cosmosrp-v47-mkmlizer: ║ belonging to: ║
pawankrd-cosmosrp-v47-mkmlizer: ║ ║
pawankrd-cosmosrp-v47-mkmlizer: ║ Chai Research Corp. ║
pawankrd-cosmosrp-v47-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
pawankrd-cosmosrp-v47-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
pawankrd-cosmosrp-v47-mkmlizer: ║ ║
pawankrd-cosmosrp-v47-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
pawankrd-cosmosrp-v47-mkmlizer: Downloaded to shared memory in 31.687s
pawankrd-cosmosrp-v47-mkmlizer: quantizing model to /dev/shm/model_cache
pawankrd-cosmosrp-v47-mkmlizer: Saving flywheel model at /dev/shm/model_cache
pawankrd-cosmosrp-v47-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 3%|▎ | 9/291 [00:00<00:03, 84.02it/s] Loading 0: 7%|▋ | 19/291 [00:00<00:02, 92.34it/s] Loading 0: 10%|▉ | 29/291 [00:00<00:02, 95.67it/s] Loading 0: 13%|█▎ | 39/291 [00:00<00:02, 86.74it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:02, 88.44it/s] Loading 0: 20%|██ | 59/291 [00:00<00:02, 90.71it/s] Loading 0: 26%|██▌ | 75/291 [00:00<00:02, 106.70it/s] Loading 0: 30%|██▉ | 86/291 [00:01<00:03, 56.12it/s] Loading 0: 34%|███▎ | 98/291 [00:01<00:02, 66.94it/s] Loading 0: 38%|███▊ | 111/291 [00:01<00:02, 76.37it/s] Loading 0: 42%|████▏ | 121/291 [00:01<00:02, 76.87it/s] Loading 0: 45%|████▌ | 131/291 [00:01<00:02, 77.73it/s] Loading 0: 48%|████▊ | 140/291 [00:01<00:01, 79.77it/s] Loading 0: 51%|█████ | 149/291 [00:01<00:01, 81.80it/s] Loading 0: 56%|█████▌ | 162/291 [00:01<00:01, 93.58it/s] Loading 0: 59%|█████▉ | 173/291 [00:02<00:01, 96.85it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 64.19it/s] Loading 0: 67%|██████▋ | 196/291 [00:02<00:01, 64.91it/s] Loading 0: 71%|███████ | 206/291 [00:02<00:01, 71.62it/s] Loading 0: 75%|███████▌ | 219/291 [00:02<00:00, 79.80it/s] Loading 0: 79%|███████▊ | 229/291 [00:02<00:00, 80.12it/s] Loading 0: 82%|████████▏ | 238/291 [00:03<00:00, 82.26it/s] Loading 0: 85%|████████▍ | 247/291 [00:03<00:00, 83.10it/s] Loading 0: 88%|████████▊ | 256/291 [00:03<00:00, 83.63it/s] Loading 0: 91%|█████████ | 265/291 [00:03<00:00, 84.17it/s] Loading 0: 94%|█████████▍| 274/291 [00:03<00:00, 85.46it/s] Loading 0: 97%|█████████▋| 283/291 [00:03<00:00, 85.39it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
pawankrd-cosmosrp-v47-mkmlizer: quantized model in 25.198s
pawankrd-cosmosrp-v47-mkmlizer: Processed model PawanKrd/CosmosRP in 56.886s
pawankrd-cosmosrp-v47-mkmlizer: creating bucket guanaco-mkml-models
pawankrd-cosmosrp-v47-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
pawankrd-cosmosrp-v47-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/pawankrd-cosmosrp-v47
pawankrd-cosmosrp-v47-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v47/config.json
pawankrd-cosmosrp-v47-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v47/special_tokens_map.json
pawankrd-cosmosrp-v47-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v47/tokenizer_config.json
pawankrd-cosmosrp-v47-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v47/tokenizer.json
pawankrd-cosmosrp-v47-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/pawankrd-cosmosrp-v47/flywheel_model.0.safetensors
pawankrd-cosmosrp-v47-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
pawankrd-cosmosrp-v47-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-v47-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v47-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-v47-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v47-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-v47-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v47-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-v47-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v47-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-v47-mkmlizer: return self.fget.__get__(instance, owner)()
pawankrd-cosmosrp-v47-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
pawankrd-cosmosrp-v47-mkmlizer: Saving duration: 0.423s
pawankrd-cosmosrp-v47-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.951s
pawankrd-cosmosrp-v47-mkmlizer: creating bucket guanaco-reward-models
pawankrd-cosmosrp-v47-mkmlizer: Bucket 's3://guanaco-reward-models/' created
pawankrd-cosmosrp-v47-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/pawankrd-cosmosrp-v47_reward
pawankrd-cosmosrp-v47-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v47_reward/config.json
pawankrd-cosmosrp-v47-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/pawankrd-cosmosrp-v47_reward/special_tokens_map.json
pawankrd-cosmosrp-v47-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v47_reward/tokenizer_config.json
pawankrd-cosmosrp-v47-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/pawankrd-cosmosrp-v47_reward/merges.txt
pawankrd-cosmosrp-v47-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/pawankrd-cosmosrp-v47_reward/vocab.json
pawankrd-cosmosrp-v47-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/pawankrd-cosmosrp-v47_reward/tokenizer.json
pawankrd-cosmosrp-v47-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/pawankrd-cosmosrp-v47_reward/reward.tensors
Job pawankrd-cosmosrp-v47-mkmlizer completed after 83.38s with status: succeeded
Stopping job with name pawankrd-cosmosrp-v47-mkmlizer
Pipeline stage MKMLizer completed in 84.17s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service pawankrd-cosmosrp-v47
Waiting for inference service pawankrd-cosmosrp-v47 to be ready
Inference service pawankrd-cosmosrp-v47 ready after 40.24595904350281s
Pipeline stage ISVCDeployer completed in 47.17s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.163364887237549s
Received healthy response to inference request in 1.3757810592651367s
Received healthy response to inference request in 1.335608720779419s
Received healthy response to inference request in 1.3225970268249512s
Received healthy response to inference request in 1.2587356567382812s
5 requests
0 failed requests
5th percentile: 1.2715079307556152
10th percentile: 1.2842802047729491
20th percentile: 1.3098247528076172
30th percentile: 1.3251993656158447
40th percentile: 1.3304040431976318
50th percentile: 1.335608720779419
60th percentile: 1.351677656173706
70th percentile: 1.3677465915679932
80th percentile: 1.5332978248596192
90th percentile: 1.8483313560485841
95th percentile: 2.005848121643066
99th percentile: 2.131861534118652
mean time: 1.4912174701690675
Pipeline stage StressChecker completed in 8.16s
pawankrd-cosmosrp_v47 status is now deployed due to DeploymentManager action
pawankrd-cosmosrp_v47 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics