submission_id: jic062-instruct_v15
developer_uid: chace9580
alignment_samples: 2069
alignment_score: 2.3181691536896314
best_of: 16
celo_rating: 1236.45
display_name: jic062-instruct_v15
formatter: {'memory_template': "<|begin_of_text|><|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': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '|eot_id|', '<|end_of_text|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64, 'reward_max_token_input': 256}
is_internal_developer: False
language_model: jic062/instruct
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: jic062/instruct
model_name: jic062-instruct_v15
model_num_parameters: 8030261248.0
model_repo: jic062/instruct
model_size: 8B
num_battles: 19673
num_wins: 10633
propriety_score: 0.7404129793510325
propriety_total_count: 1017.0
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: 2024-08-01T06:29:26+00:00
us_pacific_date: 2024-07-31
win_ratio: 0.5404869618258527
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name jic062-instruct-v15-mkmlizer
Waiting for job on jic062-instruct-v15-mkmlizer to finish
jic062-instruct-v15-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-instruct-v15-mkmlizer: ║ _____ __ __ ║
jic062-instruct-v15-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
jic062-instruct-v15-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
jic062-instruct-v15-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
jic062-instruct-v15-mkmlizer: ║ /___/ ║
jic062-instruct-v15-mkmlizer: ║ ║
jic062-instruct-v15-mkmlizer: ║ Version: 0.9.7 ║
jic062-instruct-v15-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
jic062-instruct-v15-mkmlizer: ║ https://mk1.ai ║
jic062-instruct-v15-mkmlizer: ║ ║
jic062-instruct-v15-mkmlizer: ║ The license key for the current software has been verified as ║
jic062-instruct-v15-mkmlizer: ║ belonging to: ║
jic062-instruct-v15-mkmlizer: ║ ║
jic062-instruct-v15-mkmlizer: ║ Chai Research Corp. ║
jic062-instruct-v15-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
jic062-instruct-v15-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
jic062-instruct-v15-mkmlizer: ║ ║
jic062-instruct-v15-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jic062-instruct-v15-mkmlizer: Downloaded to shared memory in 22.239s
jic062-instruct-v15-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp6655vs4h, device:0
jic062-instruct-v15-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jic062-instruct-v15-mkmlizer: quantized model in 26.060s
jic062-instruct-v15-mkmlizer: Processed model jic062/instruct in 48.300s
jic062-instruct-v15-mkmlizer: creating bucket guanaco-mkml-models
jic062-instruct-v15-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-instruct-v15-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-instruct-v15
jic062-instruct-v15-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-instruct-v15/special_tokens_map.json
jic062-instruct-v15-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-instruct-v15/config.json
jic062-instruct-v15-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-instruct-v15/tokenizer_config.json
jic062-instruct-v15-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-instruct-v15/tokenizer.json
jic062-instruct-v15-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-instruct-v15/flywheel_model.0.safetensors
jic062-instruct-v15-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
jic062-instruct-v15-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 7/291 [00:00<00:06, 45.05it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:04, 62.08it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:03, 70.95it/s] Loading 0: 12%|█▏ | 34/291 [00:00<00:03, 76.36it/s] Loading 0: 15%|█▍ | 43/291 [00:00<00:03, 80.33it/s] Loading 0: 18%|█▊ | 52/291 [00:00<00:02, 82.84it/s] Loading 0: 21%|██ | 61/291 [00:00<00:02, 84.21it/s] Loading 0: 24%|██▍ | 70/291 [00:00<00:02, 83.09it/s] Loading 0: 27%|██▋ | 79/291 [00:01<00:02, 81.09it/s] Loading 0: 30%|███ | 88/291 [00:02<00:09, 20.62it/s] Loading 0: 34%|███▎ | 98/291 [00:02<00:06, 27.88it/s] Loading 0: 38%|███▊ | 112/291 [00:02<00:04, 39.01it/s] Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 45.32it/s] Loading 0: 45%|████▍ | 130/291 [00:02<00:03, 51.52it/s] Loading 0: 48%|████▊ | 139/291 [00:02<00:02, 58.00it/s] Loading 0: 51%|█████ | 148/291 [00:02<00:02, 63.81it/s] Loading 0: 55%|█████▍ | 159/291 [00:02<00:01, 74.16it/s] Loading 0: 58%|█████▊ | 169/291 [00:03<00:01, 71.39it/s] Loading 0: 63%|██████▎ | 184/291 [00:03<00:01, 80.69it/s] Loading 0: 66%|██████▋ | 193/291 [00:04<00:04, 24.29it/s] Loading 0: 69%|██████▉ | 202/291 [00:04<00:02, 29.87it/s] Loading 0: 73%|███████▎ | 211/291 [00:04<00:02, 36.29it/s] Loading 0: 76%|███████▌ | 220/291 [00:04<00:01, 43.53it/s] Loading 0: 79%|███████▊ | 229/291 [00:04<00:01, 50.50it/s] Loading 0: 82%|████████▏ | 238/291 [00:04<00:00, 55.11it/s] Loading 0: 85%|████████▍ | 247/291 [00:05<00:00, 61.48it/s] Loading 0: 88%|████████▊ | 256/291 [00:05<00:00, 66.43it/s] Loading 0: 91%|█████████ | 265/291 [00:05<00:00, 69.06it/s] Loading 0: 94%|█████████▍| 274/291 [00:05<00:00, 69.47it/s] Loading 0: 97%|█████████▋| 283/291 [00:05<00:00, 73.62it/s] Loading 0: 100%|██████████| 291/291 [00:10<00:00, 5.10it/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.
jic062-instruct-v15-mkmlizer: warnings.warn(
jic062-instruct-v15-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.
jic062-instruct-v15-mkmlizer: warnings.warn(
jic062-instruct-v15-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.
jic062-instruct-v15-mkmlizer: warnings.warn(
jic062-instruct-v15-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jic062-instruct-v15_reward/config.json
jic062-instruct-v15-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jic062-instruct-v15_reward/special_tokens_map.json
jic062-instruct-v15-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jic062-instruct-v15_reward/tokenizer_config.json
jic062-instruct-v15-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jic062-instruct-v15_reward/merges.txt
jic062-instruct-v15-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jic062-instruct-v15_reward/vocab.json
jic062-instruct-v15-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jic062-instruct-v15_reward/tokenizer.json
jic062-instruct-v15-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/jic062-instruct-v15_reward/reward.tensors
Job jic062-instruct-v15-mkmlizer completed after 98.4s with status: succeeded
Stopping job with name jic062-instruct-v15-mkmlizer
Pipeline stage MKMLizer completed in 99.38s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service jic062-instruct-v15
Waiting for inference service jic062-instruct-v15 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
Inference service jic062-instruct-v15 ready after 141.25733494758606s
Pipeline stage ISVCDeployer completed in 143.52s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.192164182662964s
Received healthy response to inference request in 1.4961090087890625s
Received healthy response to inference request in 1.4377999305725098s
Received healthy response to inference request in 1.3952572345733643s
Received healthy response to inference request in 1.4433012008666992s
5 requests
0 failed requests
5th percentile: 1.4037657737731934
10th percentile: 1.4122743129730224
20th percentile: 1.4292913913726806
30th percentile: 1.4389001846313476
40th percentile: 1.4411006927490235
50th percentile: 1.4433012008666992
60th percentile: 1.4644243240356445
70th percentile: 1.4855474472045898
80th percentile: 1.6353200435638429
90th percentile: 1.9137421131134034
95th percentile: 2.0529531478881835
99th percentile: 2.164321975708008
mean time: 1.59292631149292
Pipeline stage StressChecker completed in 8.69s
jic062-instruct_v15 status is now deployed due to DeploymentManager action
jic062-instruct_v15 status is now inactive due to auto deactivation removed underperforming models
jic062-instruct_v15 status is now deployed due to admin request
jic062-instruct_v15 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of jic062-instruct_v15
Running pipeline stage ISVCDeleter
Checking if service jic062-instruct-v15 is running
Tearing down inference service jic062-instruct-v15
Service jic062-instruct-v15 has been torndown
Pipeline stage ISVCDeleter completed in 4.58s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key jic062-instruct-v15/config.json from bucket guanaco-mkml-models
Deleting key jic062-instruct-v15/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key jic062-instruct-v15/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key jic062-instruct-v15/tokenizer.json from bucket guanaco-mkml-models
Deleting key jic062-instruct-v15/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key jic062-instruct-v15_reward/config.json from bucket guanaco-reward-models
Deleting key jic062-instruct-v15_reward/merges.txt from bucket guanaco-reward-models
Deleting key jic062-instruct-v15_reward/reward.tensors from bucket guanaco-reward-models
Deleting key jic062-instruct-v15_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key jic062-instruct-v15_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key jic062-instruct-v15_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key jic062-instruct-v15_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.35s
jic062-instruct_v15 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics