submission_id: pawankrd-cosmosrp-llama31_v3
developer_uid: PawanOsman
best_of: 16
celo_rating: 1258.39
display_name: cosmosrp-llama31-test
family_friendly_score: 0.0
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}
generation_params: {'temperature': 1.5, '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, 'reward_max_token_input': 128}
is_internal_developer: False
language_model: PawanKrd/cosmosrp-llama31
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: PawanKrd/cosmosrp-llama3
model_name: cosmosrp-llama31-test
model_num_parameters: 8030261248.0
model_repo: PawanKrd/cosmosrp-llama31
model_size: 8B
num_battles: 13253
num_wins: 7577
ranking_group: single
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'}
reward_repo: Jellywibble/gpt2_xl_pairwise_89m_step_347634
status: torndown
submission_type: basic
timestamp: 2024-07-26T12:57:52+00:00
us_pacific_date: 2024-07-26
win_ratio: 0.5717196106541915
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name pawankrd-cosmosrp-llama31-v3-mkmlizer
Waiting for job on pawankrd-cosmosrp-llama31-v3-mkmlizer to finish
LLM-Router throws exception AssertionError('LLM-Router predict returns error 500') for galileo
pawankrd-cosmosrp-llama31-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
pawankrd-cosmosrp-llama31-v3-mkmlizer: ║ _____ __ __ ║
pawankrd-cosmosrp-llama31-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
pawankrd-cosmosrp-llama31-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
pawankrd-cosmosrp-llama31-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
pawankrd-cosmosrp-llama31-v3-mkmlizer: ║ /___/ ║
pawankrd-cosmosrp-llama31-v3-mkmlizer: ║ ║
pawankrd-cosmosrp-llama31-v3-mkmlizer: ║ Version: 0.9.7 ║
pawankrd-cosmosrp-llama31-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
pawankrd-cosmosrp-llama31-v3-mkmlizer: ║ https://mk1.ai ║
pawankrd-cosmosrp-llama31-v3-mkmlizer: ║ ║
pawankrd-cosmosrp-llama31-v3-mkmlizer: ║ The license key for the current software has been verified as ║
pawankrd-cosmosrp-llama31-v3-mkmlizer: ║ belonging to: ║
pawankrd-cosmosrp-llama31-v3-mkmlizer: ║ ║
pawankrd-cosmosrp-llama31-v3-mkmlizer: ║ Chai Research Corp. ║
pawankrd-cosmosrp-llama31-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
pawankrd-cosmosrp-llama31-v3-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
pawankrd-cosmosrp-llama31-v3-mkmlizer: ║ ║
pawankrd-cosmosrp-llama31-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
LLM-Router throws exception AssertionError('LLM-Router predict returns error 500') for galileo
pawankrd-cosmosrp-llama31-v3-mkmlizer: Downloaded to shared memory in 22.254s
pawankrd-cosmosrp-llama31-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmplvksy4a_, device:0
pawankrd-cosmosrp-llama31-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
LLM-Router throws exception AssertionError('LLM-Router predict returns error 500') for galileo
pawankrd-cosmosrp-llama31-v3-mkmlizer: quantized model in 25.764s
pawankrd-cosmosrp-llama31-v3-mkmlizer: Processed model PawanKrd/cosmosrp-llama31 in 48.018s
pawankrd-cosmosrp-llama31-v3-mkmlizer: creating bucket guanaco-mkml-models
pawankrd-cosmosrp-llama31-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
pawankrd-cosmosrp-llama31-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/pawankrd-cosmosrp-llama31-v3
pawankrd-cosmosrp-llama31-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-llama31-v3/config.json
pawankrd-cosmosrp-llama31-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/pawankrd-cosmosrp-llama31-v3/special_tokens_map.json
pawankrd-cosmosrp-llama31-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-llama31-v3/tokenizer_config.json
pawankrd-cosmosrp-llama31-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/pawankrd-cosmosrp-llama31-v3/tokenizer.json
pawankrd-cosmosrp-llama31-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/pawankrd-cosmosrp-llama31-v3/flywheel_model.0.safetensors
pawankrd-cosmosrp-llama31-v3-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
pawankrd-cosmosrp-llama31-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:36, 2.41s/it] Loading 0: 2%|▏ | 6/291 [00:04<03:05, 1.54it/s] Loading 0: 5%|▍ | 14/291 [00:05<01:00, 4.57it/s] Loading 0: 7%|▋ | 20/291 [00:05<00:36, 7.40it/s] Loading 0: 9%|▊ | 25/291 [00:05<00:26, 10.17it/s] Loading 0: 11%|█ | 32/291 [00:05<00:16, 15.44it/s] Loading 0: 13%|█▎ | 38/291 [00:05<00:12, 19.96it/s] Loading 0: 15%|█▌ | 44/291 [00:05<00:09, 25.12it/s] Loading 0: 18%|█▊ | 51/291 [00:05<00:08, 29.65it/s] Loading 0: 21%|██ | 60/291 [00:06<00:08, 27.51it/s] Loading 0: 23%|██▎ | 68/291 [00:06<00:06, 35.14it/s] Loading 0: 25%|██▌ | 74/291 [00:06<00:05, 37.16it/s] Loading 0: 27%|██▋ | 80/291 [00:06<00:05, 39.99it/s] Loading 0: 30%|██▉ | 86/291 [00:06<00:04, 43.18it/s] Loading 0: 32%|███▏ | 92/291 [00:06<00:04, 43.68it/s] Loading 0: 33%|███▎ | 97/291 [00:06<00:04, 43.93it/s] Loading 0: 36%|███▌ | 104/291 [00:06<00:03, 49.69it/s] Loading 0: 38%|███▊ | 110/291 [00:07<00:03, 48.11it/s] Loading 0: 40%|███▉ | 116/291 [00:07<00:03, 49.61it/s] Loading 0: 42%|████▏ | 123/291 [00:07<00:03, 47.47it/s] Loading 0: 45%|████▌ | 131/291 [00:07<00:02, 54.88it/s] Loading 0: 47%|████▋ | 137/291 [00:07<00:02, 51.96it/s] Loading 0: 49%|████▉ | 143/291 [00:07<00:02, 53.42it/s] Loading 0: 51%|█████ | 149/291 [00:07<00:02, 55.07it/s] Loading 0: 53%|█████▎ | 155/291 [00:07<00:02, 48.60it/s] Loading 0: 55%|█████▌ | 161/291 [00:08<00:02, 50.72it/s] Loading 0: 57%|█████▋ | 167/291 [00:08<00:03, 36.87it/s] Loading 0: 59%|█████▉ | 173/291 [00:08<00:03, 38.49it/s] Loading 0: 61%|██████ | 178/291 [00:08<00:02, 40.38it/s] Loading 0: 64%|██████▎ | 185/291 [00:08<00:02, 46.80it/s] Loading 0: 66%|██████▌ | 191/291 [00:08<00:02, 46.35it/s] Loading 0: 67%|██████▋ | 196/291 [00:08<00:02, 46.86it/s] Loading 0: 70%|███████ | 204/291 [00:09<00:01, 47.65it/s] Loading 0: 73%|███████▎ | 212/291 [00:09<00:01, 54.84it/s] Loading 0: 75%|███████▍ | 218/291 [00:09<00:01, 50.81it/s] Loading 0: 77%|███████▋ | 224/291 [00:09<00:01, 52.14it/s] Loading 0: 79%|███████▉ | 231/291 [00:09<00:01, 49.71it/s] Loading 0: 82%|████████▏ | 239/291 [00:09<00:00, 56.34it/s] Loading 0: 84%|████████▍ | 245/291 [00:09<00:00, 52.32it/s] Loading 0: 86%|████████▋ | 251/291 [00:09<00:00, 53.57it/s] Loading 0: 89%|████████▊ | 258/291 [00:10<00:00, 48.97it/s] Loading 0: 91%|█████████▏| 266/291 [00:10<00:00, 39.62it/s] Loading 0: 93%|█████████▎| 271/291 [00:10<00:00, 41.01it/s] Loading 0: 95%|█████████▍| 276/291 [00:10<00:00, 37.76it/s] Loading 0: 98%|█████████▊| 285/291 [00:10<00:00, 42.87it/s] /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:957: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
pawankrd-cosmosrp-llama31-v3-mkmlizer: warnings.warn(
pawankrd-cosmosrp-llama31-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:785: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
pawankrd-cosmosrp-llama31-v3-mkmlizer: warnings.warn(
pawankrd-cosmosrp-llama31-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:469: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
pawankrd-cosmosrp-llama31-v3-mkmlizer: warnings.warn(
pawankrd-cosmosrp-llama31-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
pawankrd-cosmosrp-llama31-v3-mkmlizer: Saving duration: 1.454s
pawankrd-cosmosrp-llama31-v3-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.861s
pawankrd-cosmosrp-llama31-v3-mkmlizer: creating bucket guanaco-reward-models
pawankrd-cosmosrp-llama31-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
pawankrd-cosmosrp-llama31-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/pawankrd-cosmosrp-llama31-v3_reward
pawankrd-cosmosrp-llama31-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/pawankrd-cosmosrp-llama31-v3_reward/special_tokens_map.json
pawankrd-cosmosrp-llama31-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/pawankrd-cosmosrp-llama31-v3_reward/config.json
pawankrd-cosmosrp-llama31-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/pawankrd-cosmosrp-llama31-v3_reward/tokenizer_config.json
pawankrd-cosmosrp-llama31-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/pawankrd-cosmosrp-llama31-v3_reward/merges.txt
pawankrd-cosmosrp-llama31-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/pawankrd-cosmosrp-llama31-v3_reward/vocab.json
pawankrd-cosmosrp-llama31-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/pawankrd-cosmosrp-llama31-v3_reward/tokenizer.json
LLM-Router throws exception AssertionError('LLM-Router predict returns error 500') for galileo
Job pawankrd-cosmosrp-llama31-v3-mkmlizer completed after 94.83s with status: succeeded
Stopping job with name pawankrd-cosmosrp-llama31-v3-mkmlizer
Pipeline stage MKMLizer completed in 95.71s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service pawankrd-cosmosrp-llama31-v3
Waiting for inference service pawankrd-cosmosrp-llama31-v3 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
LLM-Router throws exception AssertionError('LLM-Router predict returns error 500') for galileo
LLM-Router throws exception AssertionError('LLM-Router predict returns error 500') for galileo
LLM-Router throws exception AssertionError('LLM-Router predict returns error 500') for galileo
LLM-Router throws exception AssertionError('LLM-Router predict returns error 500') for galileo
LLM-Router throws exception AssertionError('LLM-Router predict returns error 500') for galileo
Inference service pawankrd-cosmosrp-llama31-v3 ready after 80.72512793540955s
Pipeline stage ISVCDeployer completed in 81.72s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.118894577026367s
Received healthy response to inference request in 1.4046165943145752s
Received healthy response to inference request in 1.3517353534698486s
Received healthy response to inference request in 1.3391263484954834s
Received healthy response to inference request in 1.2827515602111816s
5 requests
0 failed requests
5th percentile: 1.294026517868042
10th percentile: 1.3053014755249024
20th percentile: 1.3278513908386231
30th percentile: 1.3416481494903565
40th percentile: 1.3466917514801025
50th percentile: 1.3517353534698486
60th percentile: 1.3728878498077393
70th percentile: 1.3940403461456299
80th percentile: 1.5474721908569338
90th percentile: 1.8331833839416505
95th percentile: 1.9760389804840086
99th percentile: 2.0903234577178953
mean time: 1.4994248867034912
Pipeline stage StressChecker completed in 8.29s
pawankrd-cosmosrp-llama31_v3 status is now deployed due to DeploymentManager action
pawankrd-cosmosrp-llama31_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of pawankrd-cosmosrp-llama31_v3
Running pipeline stage ISVCDeleter
Checking if service pawankrd-cosmosrp-llama31-v3 is running
Tearing down inference service pawankrd-cosmosrp-llama31-v3
Service pawankrd-cosmosrp-llama31-v3 has been torndown
Pipeline stage ISVCDeleter completed in 5.06s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key pawankrd-cosmosrp-llama31-v3/config.json from bucket guanaco-mkml-models
Deleting key pawankrd-cosmosrp-llama31-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key pawankrd-cosmosrp-llama31-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key pawankrd-cosmosrp-llama31-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key pawankrd-cosmosrp-llama31-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key pawankrd-cosmosrp-llama31-v3_reward/config.json from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-llama31-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-llama31-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-llama31-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-llama31-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-llama31-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-llama31-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.18s
pawankrd-cosmosrp-llama31_v3 status is now torndown due to DeploymentManager action