submission_id: pawankrd-cosmosrp_v12
developer_uid: PawanOsman
status: inactive
model_repo: PawanKrd/CosmosRP
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.08, 'top_k': 40, '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: 2024-06-16T12:34:44+00:00
model_name: pawankrd-cosmosrp_v12
model_eval_status: success
model_group: PawanKrd/CosmosRP
num_battles: 39824
num_wins: 22769
celo_rating: 1222.75
propriety_score: 0.7006586741221628
propriety_total_count: 21103.0
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_v12
ineligible_reason: None
language_model: PawanKrd/CosmosRP
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-16
win_ratio: 0.5717406588991563
Resubmit model
Running pipeline stage MKMLizer
Starting job with name pawankrd-cosmosrp-v12-mkmlizer
Waiting for job on pawankrd-cosmosrp-v12-mkmlizer to finish
pawankrd-cosmosrp-v12-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
pawankrd-cosmosrp-v12-mkmlizer: ║ _____ __ __ ║
pawankrd-cosmosrp-v12-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
pawankrd-cosmosrp-v12-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
pawankrd-cosmosrp-v12-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
pawankrd-cosmosrp-v12-mkmlizer: ║ /___/ ║
pawankrd-cosmosrp-v12-mkmlizer: ║ ║
pawankrd-cosmosrp-v12-mkmlizer: ║ Version: 0.8.14 ║
pawankrd-cosmosrp-v12-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
pawankrd-cosmosrp-v12-mkmlizer: ║ https://mk1.ai ║
pawankrd-cosmosrp-v12-mkmlizer: ║ ║
pawankrd-cosmosrp-v12-mkmlizer: ║ The license key for the current software has been verified as ║
pawankrd-cosmosrp-v12-mkmlizer: ║ belonging to: ║
pawankrd-cosmosrp-v12-mkmlizer: ║ ║
pawankrd-cosmosrp-v12-mkmlizer: ║ Chai Research Corp. ║
pawankrd-cosmosrp-v12-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
pawankrd-cosmosrp-v12-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
pawankrd-cosmosrp-v12-mkmlizer: ║ ║
pawankrd-cosmosrp-v12-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
pawankrd-cosmosrp-v12-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
pawankrd-cosmosrp-v12-mkmlizer: warnings.warn(warning_message, FutureWarning)
pawankrd-cosmosrp-v12-mkmlizer: Downloaded to shared memory in 32.133s
pawankrd-cosmosrp-v12-mkmlizer: quantizing model to /dev/shm/model_cache
pawankrd-cosmosrp-v12-mkmlizer: Saving flywheel model at /dev/shm/model_cache
pawankrd-cosmosrp-v12-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:18, 2.35s/it] Loading 0: 3%|▎ | 9/291 [00:04<01:53, 2.48it/s] Loading 0: 5%|▍ | 14/291 [00:05<01:08, 4.02it/s] Loading 0: 8%|▊ | 23/291 [00:05<00:32, 8.33it/s] Loading 0: 11%|█ | 32/291 [00:05<00:18, 13.78it/s] Loading 0: 14%|█▍ | 41/291 [00:05<00:12, 20.41it/s] Loading 0: 17%|█▋ | 50/291 [00:05<00:08, 27.92it/s] Loading 0: 20%|██ | 59/291 [00:05<00:06, 36.23it/s] Loading 0: 23%|██▎ | 68/291 [00:05<00:06, 32.38it/s] Loading 0: 26%|██▋ | 77/291 [00:06<00:05, 40.47it/s] Loading 0: 30%|██▉ | 86/291 [00:06<00:04, 47.75it/s] Loading 0: 33%|███▎ | 95/291 [00:06<00:03, 55.42it/s] Loading 0: 36%|███▌ | 105/291 [00:06<00:03, 61.50it/s] Loading 0: 39%|███▉ | 113/291 [00:06<00:04, 44.43it/s] Loading 0: 42%|████▏ | 122/291 [00:06<00:03, 52.10it/s] Loading 0: 45%|████▌ | 131/291 [00:06<00:02, 55.65it/s] Loading 0: 48%|████▊ | 140/291 [00:07<00:02, 62.11it/s] Loading 0: 51%|█████ | 149/291 [00:07<00:02, 67.95it/s] Loading 0: 54%|█████▍ | 158/291 [00:07<00:01, 72.58it/s] Loading 0: 57%|█████▋ | 167/291 [00:07<00:02, 45.93it/s] Loading 0: 60%|██████ | 176/291 [00:07<00:02, 53.39it/s] Loading 0: 64%|██████▎ | 185/291 [00:07<00:01, 59.70it/s] Loading 0: 67%|██████▋ | 194/291 [00:07<00:01, 65.80it/s] Loading 0: 70%|██████▉ | 203/291 [00:08<00:01, 71.18it/s] Loading 0: 73%|███████▎ | 212/291 [00:08<00:01, 75.17it/s] Loading 0: 76%|███████▌ | 221/291 [00:08<00:01, 47.73it/s] Loading 0: 79%|███████▉ | 230/291 [00:08<00:01, 54.94it/s] Loading 0: 82%|████████▏ | 239/291 [00:08<00:00, 61.77it/s] Loading 0: 85%|████████▌ | 248/291 [00:08<00:00, 67.30it/s] Loading 0: 88%|████████▊ | 257/291 [00:08<00:00, 71.49it/s] Loading 0: 91%|█████████▏| 266/291 [00:09<00:00, 34.71it/s] Loading 0: 95%|█████████▍| 275/291 [00:09<00:00, 42.37it/s] Loading 0: 98%|█████████▊| 284/291 [00:09<00:00, 50.02it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
pawankrd-cosmosrp-v12-mkmlizer: quantized model in 26.088s
pawankrd-cosmosrp-v12-mkmlizer: Processed model PawanKrd/CosmosRP in 63.413s
pawankrd-cosmosrp-v12-mkmlizer: creating bucket guanaco-mkml-models
pawankrd-cosmosrp-v12-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
pawankrd-cosmosrp-v12-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/pawankrd-cosmosrp-v12
pawankrd-cosmosrp-v12-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v12/special_tokens_map.json
pawankrd-cosmosrp-v12-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v12/config.json
pawankrd-cosmosrp-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v12/tokenizer_config.json
pawankrd-cosmosrp-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v12/tokenizer.json
pawankrd-cosmosrp-v12-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/pawankrd-cosmosrp-v12/flywheel_model.0.safetensors
pawankrd-cosmosrp-v12-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
pawankrd-cosmosrp-v12-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:913: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
pawankrd-cosmosrp-v12-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v12-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:757: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
pawankrd-cosmosrp-v12-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v12-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-v12-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v12-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-v12-mkmlizer: return self.fget.__get__(instance, owner)()
pawankrd-cosmosrp-v12-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
pawankrd-cosmosrp-v12-mkmlizer: Saving duration: 0.410s
pawankrd-cosmosrp-v12-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.630s
pawankrd-cosmosrp-v12-mkmlizer: creating bucket guanaco-reward-models
pawankrd-cosmosrp-v12-mkmlizer: Bucket 's3://guanaco-reward-models/' created
pawankrd-cosmosrp-v12-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/pawankrd-cosmosrp-v12_reward
pawankrd-cosmosrp-v12-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/pawankrd-cosmosrp-v12_reward/special_tokens_map.json
pawankrd-cosmosrp-v12-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v12_reward/config.json
pawankrd-cosmosrp-v12-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v12_reward/tokenizer_config.json
pawankrd-cosmosrp-v12-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/pawankrd-cosmosrp-v12_reward/merges.txt
pawankrd-cosmosrp-v12-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/pawankrd-cosmosrp-v12_reward/vocab.json
pawankrd-cosmosrp-v12-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/pawankrd-cosmosrp-v12_reward/tokenizer.json
pawankrd-cosmosrp-v12-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/pawankrd-cosmosrp-v12_reward/reward.tensors
Job pawankrd-cosmosrp-v12-mkmlizer completed after 93.26s with status: succeeded
Stopping job with name pawankrd-cosmosrp-v12-mkmlizer
Pipeline stage MKMLizer completed in 96.43s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service pawankrd-cosmosrp-v12
Waiting for inference service pawankrd-cosmosrp-v12 to be ready
Tearing down inference service pawankrd-cosmosrp-v12
%s, retrying in %s seconds...
Creating inference service pawankrd-cosmosrp-v12
Waiting for inference service pawankrd-cosmosrp-v12 to be ready
Inference service pawankrd-cosmosrp-v12 ready after 171.5794608592987s
Pipeline stage ISVCDeployer completed in 788.84s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2140679359436035s
Received healthy response to inference request in 1.3842012882232666s
Received healthy response to inference request in 1.3467493057250977s
Received healthy response to inference request in 1.3170700073242188s
Received healthy response to inference request in 1.2749626636505127s
5 requests
0 failed requests
5th percentile: 1.283384132385254
10th percentile: 1.2918056011199952
20th percentile: 1.3086485385894775
30th percentile: 1.3230058670043945
40th percentile: 1.3348775863647462
50th percentile: 1.3467493057250977
60th percentile: 1.3617300987243652
70th percentile: 1.3767108917236328
80th percentile: 1.5501746177673341
90th percentile: 1.882121276855469
95th percentile: 2.0480946063995358
99th percentile: 2.18087327003479
mean time: 1.5074102401733398
Pipeline stage StressChecker completed in 8.13s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.03s
M-Eval Dataset for topic stay_in_character is loaded
pawankrd-cosmosrp_v12 status is now deployed due to DeploymentManager action
pawankrd-cosmosrp_v12 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics