submission_id: jic062-instruct-v14-v15_v1
developer_uid: chace9580
alignment_samples: 2073
alignment_score: 2.3392330415874953
best_of: 16
celo_rating: 1235.29
display_name: jic062-instruct-v14-v15_v1
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|'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64, 'reward_max_token_input': 256}
is_internal_developer: False
language_model: jic062/instruct_v14_v15
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: jic062/instruct_v14_v15
model_name: jic062-instruct-v14-v15_v1
model_num_parameters: 8030261248.0
model_repo: jic062/instruct_v14_v15
model_size: 8B
num_battles: 13692
num_wins: 7394
propriety_score: 0.7223567393058918
propriety_total_count: 1239.0
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: 2024-08-05T03:29:06+00:00
us_pacific_date: 2024-08-04
win_ratio: 0.5400233713117149
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name jic062-instruct-v14-v15-v1-mkmlizer
Waiting for job on jic062-instruct-v14-v15-v1-mkmlizer to finish
jic062-instruct-v14-v15-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-instruct-v14-v15-v1-mkmlizer: ║ _____ __ __ ║
jic062-instruct-v14-v15-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
jic062-instruct-v14-v15-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
jic062-instruct-v14-v15-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
jic062-instruct-v14-v15-v1-mkmlizer: ║ /___/ ║
jic062-instruct-v14-v15-v1-mkmlizer: ║ ║
jic062-instruct-v14-v15-v1-mkmlizer: ║ Version: 0.9.9 ║
jic062-instruct-v14-v15-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
jic062-instruct-v14-v15-v1-mkmlizer: ║ https://mk1.ai ║
jic062-instruct-v14-v15-v1-mkmlizer: ║ ║
jic062-instruct-v14-v15-v1-mkmlizer: ║ The license key for the current software has been verified as ║
jic062-instruct-v14-v15-v1-mkmlizer: ║ belonging to: ║
jic062-instruct-v14-v15-v1-mkmlizer: ║ ║
jic062-instruct-v14-v15-v1-mkmlizer: ║ Chai Research Corp. ║
jic062-instruct-v14-v15-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
jic062-instruct-v14-v15-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
jic062-instruct-v14-v15-v1-mkmlizer: ║ ║
jic062-instruct-v14-v15-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jic062-instruct-v14-v15-v1-mkmlizer: Downloaded to shared memory in 23.942s
jic062-instruct-v14-v15-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmphsm8hzm3, device:0
jic062-instruct-v14-v15-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jic062-instruct-v14-v15-v1-mkmlizer: quantized model in 26.931s
jic062-instruct-v14-v15-v1-mkmlizer: Processed model jic062/instruct_v14_v15 in 50.873s
jic062-instruct-v14-v15-v1-mkmlizer: creating bucket guanaco-mkml-models
jic062-instruct-v14-v15-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-instruct-v14-v15-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-instruct-v14-v15-v1
jic062-instruct-v14-v15-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-instruct-v14-v15-v1/config.json
jic062-instruct-v14-v15-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-instruct-v14-v15-v1/special_tokens_map.json
jic062-instruct-v14-v15-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-instruct-v14-v15-v1/tokenizer_config.json
jic062-instruct-v14-v15-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-instruct-v14-v15-v1/tokenizer.json
jic062-instruct-v14-v15-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-instruct-v14-v15-v1/flywheel_model.0.safetensors
jic062-instruct-v14-v15-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
jic062-instruct-v14-v15-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 7/291 [00:00<00:05, 47.65it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:04, 64.84it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:03, 71.62it/s] Loading 0: 12%|█▏ | 34/291 [00:00<00:03, 75.54it/s] Loading 0: 15%|█▍ | 43/291 [00:00<00:03, 75.72it/s] Loading 0: 18%|█▊ | 52/291 [00:00<00:03, 77.30it/s] Loading 0: 21%|██ | 61/291 [00:00<00:02, 79.14it/s] Loading 0: 24%|██▍ | 70/291 [00:00<00:02, 79.62it/s] Loading 0: 27%|██▋ | 79/291 [00:01<00:02, 76.58it/s] Loading 0: 30%|██▉ | 87/291 [00:02<00:09, 20.50it/s] Loading 0: 32%|███▏ | 94/291 [00:02<00:07, 25.03it/s] Loading 0: 35%|███▌ | 103/291 [00:02<00:05, 32.28it/s] Loading 0: 38%|███▊ | 112/291 [00:02<00:04, 39.81it/s] Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 47.92it/s] Loading 0: 45%|████▍ | 130/291 [00:02<00:02, 55.44it/s] Loading 0: 48%|████▊ | 139/291 [00:02<00:02, 58.75it/s] Loading 0: 51%|█████ | 148/291 [00:02<00:02, 64.10it/s] Loading 0: 54%|█████▍ | 157/291 [00:03<00:01, 69.54it/s] Loading 0: 57%|█████▋ | 166/291 [00:03<00:01, 71.06it/s] Loading 0: 60%|██████ | 175/291 [00:03<00:01, 69.78it/s] Loading 0: 63%|██████▎ | 184/291 [00:03<00:01, 69.39it/s] Loading 0: 66%|██████▌ | 192/291 [00:04<00:04, 20.47it/s] Loading 0: 68%|██████▊ | 198/291 [00:04<00:03, 23.67it/s] Loading 0: 70%|███████ | 205/291 [00:04<00:02, 28.88it/s] Loading 0: 74%|███████▎ | 214/291 [00:04<00:02, 37.09it/s] Loading 0: 77%|███████▋ | 223/291 [00:04<00:01, 45.37it/s] Loading 0: 80%|███████▉ | 232/291 [00:05<00:01, 51.46it/s] Loading 0: 83%|████████▎ | 241/291 [00:05<00:00, 56.45it/s] Loading 0: 86%|████████▌ | 250/291 [00:05<00:00, 62.43it/s] Loading 0: 89%|████████▉ | 259/291 [00:05<00:00, 65.32it/s] Loading 0: 92%|█████████▏| 268/291 [00:05<00:00, 67.10it/s] Loading 0: 95%|█████████▌| 277/291 [00:05<00:00, 69.94it/s] Loading 0: 98%|█████████▊| 286/291 [00:05<00:00, 72.52it/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-v14-v15-v1-mkmlizer: warnings.warn(
jic062-instruct-v14-v15-v1-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-v14-v15-v1-mkmlizer: warnings.warn(
jic062-instruct-v14-v15-v1-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-v14-v15-v1-mkmlizer: warnings.warn(
jic062-instruct-v14-v15-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jic062-instruct-v14-v15-v1-mkmlizer: Saving duration: 1.405s
jic062-instruct-v14-v15-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.157s
jic062-instruct-v14-v15-v1-mkmlizer: creating bucket guanaco-reward-models
jic062-instruct-v14-v15-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jic062-instruct-v14-v15-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jic062-instruct-v14-v15-v1_reward
jic062-instruct-v14-v15-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jic062-instruct-v14-v15-v1_reward/config.json
jic062-instruct-v14-v15-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jic062-instruct-v14-v15-v1_reward/tokenizer_config.json
jic062-instruct-v14-v15-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jic062-instruct-v14-v15-v1_reward/special_tokens_map.json
jic062-instruct-v14-v15-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jic062-instruct-v14-v15-v1_reward/merges.txt
jic062-instruct-v14-v15-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jic062-instruct-v14-v15-v1_reward/vocab.json
jic062-instruct-v14-v15-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jic062-instruct-v14-v15-v1_reward/tokenizer.json
Job jic062-instruct-v14-v15-v1-mkmlizer completed after 94.03s with status: succeeded
Stopping job with name jic062-instruct-v14-v15-v1-mkmlizer
Pipeline stage MKMLizer completed in 94.99s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service jic062-instruct-v14-v15-v1
Waiting for inference service jic062-instruct-v14-v15-v1 to be ready
Inference service jic062-instruct-v14-v15-v1 ready after 160.95168471336365s
Pipeline stage ISVCDeployer completed in 162.55s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.263803482055664s
Received healthy response to inference request in 1.460282325744629s
Received healthy response to inference request in 1.4279074668884277s
Received healthy response to inference request in 1.4416992664337158s
Received healthy response to inference request in 1.4753949642181396s
5 requests
0 failed requests
5th percentile: 1.4306658267974854
10th percentile: 1.433424186706543
20th percentile: 1.4389409065246581
30th percentile: 1.4454158782958983
40th percentile: 1.4528491020202636
50th percentile: 1.460282325744629
60th percentile: 1.4663273811340332
70th percentile: 1.4723724365234374
80th percentile: 1.6330766677856448
90th percentile: 1.9484400749206543
95th percentile: 2.106121778488159
99th percentile: 2.232267141342163
mean time: 1.6138175010681153
Pipeline stage StressChecker completed in 8.72s
jic062-instruct-v14-v15_v1 status is now deployed due to DeploymentManager action
jic062-instruct-v14-v15_v1 status is now inactive due to auto deactivation removed underperforming models
jic062-instruct-v14-v15_v1 status is now deployed due to admin request
jic062-instruct-v14-v15_v1 status is now inactive due to auto deactivation removed underperforming models
jic062-instruct-v14-v15_v1 status is now torndown due to DeploymentManager action
admin requested tearing down of mistralai-mixtral-8x7b_3473_v112

Usage Metrics

Latency Metrics