submission_id: pawankrd-cosmosrp_v74
developer_uid: PawanOsman
alignment_samples: 0
best_of: 16
celo_rating: 1270.02
display_name: pawankrd-cosmosrp_v74
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': 2.0, '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}
is_internal_developer: False
language_model: PawanKrd/CosmosRP
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: PawanKrd/CosmosRP
model_name: pawankrd-cosmosrp_v74
model_num_parameters: 8030261248.0
model_repo: PawanKrd/CosmosRP
model_size: 8B
num_battles: 12447
num_wins: 7599
propriety_score: 0.7205009887936717
propriety_total_count: 1517.0
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: 2024-07-18T08:39:28+00:00
us_pacific_date: 2024-07-18
win_ratio: 0.6105085562786213
Resubmit model
Running pipeline stage MKMLizer
Starting job with name pawankrd-cosmosrp-v74-mkmlizer
Waiting for job on pawankrd-cosmosrp-v74-mkmlizer to finish
pawankrd-cosmosrp-v74-mkmlizer: Downloaded to shared memory in 24.969s
pawankrd-cosmosrp-v74-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpd_91jbnk, device:0
pawankrd-cosmosrp-v74-mkmlizer: Saving flywheel model at /dev/shm/model_cache
pawankrd-cosmosrp-v74-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:05<13:23, 2.78s/it] Loading 0: 5%|▍ | 14/291 [00:05<01:22, 3.34it/s] Loading 0: 9%|▉ | 27/291 [00:05<00:34, 7.69it/s] Loading 0: 14%|█▍ | 41/291 [00:05<00:18, 13.76it/s] Loading 0: 19%|█▊ | 54/291 [00:06<00:11, 20.95it/s] Loading 0: 23%|██▎ | 66/291 [00:06<00:10, 21.95it/s] Loading 0: 26%|██▋ | 77/291 [00:06<00:07, 28.69it/s] Loading 0: 31%|███ | 90/291 [00:06<00:05, 39.05it/s] Loading 0: 35%|███▌ | 103/291 [00:06<00:03, 50.64it/s] Loading 0: 39%|███▉ | 114/291 [00:06<00:03, 58.73it/s] Loading 0: 45%|████▍ | 130/291 [00:07<00:02, 72.81it/s] Loading 0: 49%|████▉ | 142/291 [00:07<00:01, 77.76it/s] Loading 0: 54%|█████▍ | 157/291 [00:07<00:01, 91.62it/s] Loading 0: 58%|█████▊ | 169/291 [00:07<00:02, 50.83it/s] Loading 0: 63%|██████▎ | 184/291 [00:07<00:01, 63.53it/s] Loading 0: 67%|██████▋ | 195/291 [00:08<00:01, 68.08it/s] Loading 0: 73%|███████▎ | 211/291 [00:08<00:00, 83.72it/s] Loading 0: 77%|███████▋ | 223/291 [00:08<00:00, 89.72it/s] Loading 0: 82%|████████▏ | 238/291 [00:08<00:00, 102.20it/s] Loading 0: 86%|████████▋ | 251/291 [00:08<00:00, 100.49it/s] Loading 0: 91%|█████████ | 265/291 [00:08<00:00, 104.07it/s] Loading 0: 95%|█████████▌| 277/291 [00:09<00:00, 54.52it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
pawankrd-cosmosrp-v74-mkmlizer: quantized model in 29.810s
pawankrd-cosmosrp-v74-mkmlizer: Processed model PawanKrd/CosmosRP in 54.780s
pawankrd-cosmosrp-v74-mkmlizer: creating bucket guanaco-mkml-models
pawankrd-cosmosrp-v74-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
pawankrd-cosmosrp-v74-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/pawankrd-cosmosrp-v74
pawankrd-cosmosrp-v74-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v74/config.json
pawankrd-cosmosrp-v74-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v74/special_tokens_map.json
pawankrd-cosmosrp-v74-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v74/tokenizer_config.json
pawankrd-cosmosrp-v74-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v74/tokenizer.json
pawankrd-cosmosrp-v74-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/pawankrd-cosmosrp-v74/flywheel_model.0.safetensors
pawankrd-cosmosrp-v74-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
pawankrd-cosmosrp-v74-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:950: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
pawankrd-cosmosrp-v74-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v74-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:778: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
pawankrd-cosmosrp-v74-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v74-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-v74-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v74-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
pawankrd-cosmosrp-v74-mkmlizer: Saving duration: 2.370s
pawankrd-cosmosrp-v74-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 14.084s
pawankrd-cosmosrp-v74-mkmlizer: creating bucket guanaco-reward-models
pawankrd-cosmosrp-v74-mkmlizer: Bucket 's3://guanaco-reward-models/' created
pawankrd-cosmosrp-v74-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/pawankrd-cosmosrp-v74_reward
pawankrd-cosmosrp-v74-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v74_reward/config.json
pawankrd-cosmosrp-v74-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v74_reward/tokenizer_config.json
pawankrd-cosmosrp-v74-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/pawankrd-cosmosrp-v74_reward/special_tokens_map.json
pawankrd-cosmosrp-v74-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/pawankrd-cosmosrp-v74_reward/merges.txt
pawankrd-cosmosrp-v74-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/pawankrd-cosmosrp-v74_reward/vocab.json
pawankrd-cosmosrp-v74-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/pawankrd-cosmosrp-v74_reward/tokenizer.json
pawankrd-cosmosrp-v74-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/pawankrd-cosmosrp-v74_reward/reward.tensors
Job pawankrd-cosmosrp-v74-mkmlizer completed after 107.29s with status: succeeded
Stopping job with name pawankrd-cosmosrp-v74-mkmlizer
Pipeline stage MKMLizer completed in 108.77s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service pawankrd-cosmosrp-v74
Waiting for inference service pawankrd-cosmosrp-v74 to be ready
Inference service pawankrd-cosmosrp-v74 ready after 51.02248573303223s
Pipeline stage ISVCDeployer completed in 53.18s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.281308174133301s
Received healthy response to inference request in 1.5790891647338867s
Received healthy response to inference request in 1.545938491821289s
Received healthy response to inference request in 1.5114541053771973s
Received healthy response to inference request in 1.4932615756988525s
5 requests
0 failed requests
5th percentile: 1.4969000816345215
10th percentile: 1.5005385875701904
20th percentile: 1.5078155994415283
30th percentile: 1.5183509826660155
40th percentile: 1.5321447372436523
50th percentile: 1.545938491821289
60th percentile: 1.559198760986328
70th percentile: 1.5724590301513672
80th percentile: 1.7195329666137695
90th percentile: 2.000420570373535
95th percentile: 2.140864372253418
99th percentile: 2.253219413757324
mean time: 1.6822103023529054
Pipeline stage StressChecker completed in 9.38s
pawankrd-cosmosrp_v74 status is now deployed due to DeploymentManager action
pawankrd-cosmosrp_v74 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of pawankrd-cosmosrp_v74
Running pipeline stage ISVCDeleter
Checking if service pawankrd-cosmosrp-v74 is running
Tearing down inference service pawankrd-cosmosrp-v74
Service pawankrd-cosmosrp-v74 has been torndown
Pipeline stage ISVCDeleter completed in 5.36s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key pawankrd-cosmosrp-v74/config.json from bucket guanaco-mkml-models
Deleting key pawankrd-cosmosrp-v74/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key pawankrd-cosmosrp-v74/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key pawankrd-cosmosrp-v74/tokenizer.json from bucket guanaco-mkml-models
Deleting key pawankrd-cosmosrp-v74/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key pawankrd-cosmosrp-v74_reward/config.json from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-v74_reward/merges.txt from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-v74_reward/reward.tensors from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-v74_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-v74_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-v74_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-v74_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.47s
pawankrd-cosmosrp_v74 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics