submission_id: jic062-share-qlora-out_v9
developer_uid: chace9580
alignment_samples: 0
best_of: 16
celo_rating: 1185.92
display_name: jic062-share-qlora-out_v9
formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\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}
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', '<|end_of_text|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64, 'reward_max_token_input': 1024}
is_internal_developer: False
language_model: jic062/share-qlora-out
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: jic062/share-qlora-out
model_name: jic062-share-qlora-out_v9
model_num_parameters: 8030261248.0
model_repo: jic062/share-qlora-out
model_size: 8B
num_battles: 12390
num_wins: 5680
propriety_score: 0.7435406698564593
propriety_total_count: 1045.0
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: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-07-26T19:04:09+00:00
us_pacific_date: 2024-07-26
win_ratio: 0.45843422114608556
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name jic062-share-qlora-out-v9-mkmlizer
Waiting for job on jic062-share-qlora-out-v9-mkmlizer to finish
jic062-share-qlora-out-v9-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-share-qlora-out-v9-mkmlizer: ║ _____ __ __ ║
jic062-share-qlora-out-v9-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
jic062-share-qlora-out-v9-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
jic062-share-qlora-out-v9-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
jic062-share-qlora-out-v9-mkmlizer: ║ /___/ ║
jic062-share-qlora-out-v9-mkmlizer: ║ ║
jic062-share-qlora-out-v9-mkmlizer: ║ Version: 0.9.7 ║
jic062-share-qlora-out-v9-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
jic062-share-qlora-out-v9-mkmlizer: ║ https://mk1.ai ║
jic062-share-qlora-out-v9-mkmlizer: ║ ║
jic062-share-qlora-out-v9-mkmlizer: ║ The license key for the current software has been verified as ║
jic062-share-qlora-out-v9-mkmlizer: ║ belonging to: ║
jic062-share-qlora-out-v9-mkmlizer: ║ ║
jic062-share-qlora-out-v9-mkmlizer: ║ Chai Research Corp. ║
jic062-share-qlora-out-v9-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
jic062-share-qlora-out-v9-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
jic062-share-qlora-out-v9-mkmlizer: ║ ║
jic062-share-qlora-out-v9-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jic062-share-qlora-out-v9-mkmlizer: Downloaded to shared memory in 47.805s
jic062-share-qlora-out-v9-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp1ltyphrj, device:0
jic062-share-qlora-out-v9-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jic062-share-qlora-out-v9-mkmlizer: quantized model in 25.815s
jic062-share-qlora-out-v9-mkmlizer: Processed model jic062/share-qlora-out in 73.621s
jic062-share-qlora-out-v9-mkmlizer: creating bucket guanaco-mkml-models
jic062-share-qlora-out-v9-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-share-qlora-out-v9-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-share-qlora-out-v9
jic062-share-qlora-out-v9-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-share-qlora-out-v9/config.json
jic062-share-qlora-out-v9-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-share-qlora-out-v9/special_tokens_map.json
jic062-share-qlora-out-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-share-qlora-out-v9/tokenizer_config.json
jic062-share-qlora-out-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-share-qlora-out-v9/tokenizer.json
jic062-share-qlora-out-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-share-qlora-out-v9/flywheel_model.0.safetensors
jic062-share-qlora-out-v9-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
jic062-share-qlora-out-v9-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 7/291 [00:00<00:05, 49.43it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:03, 69.33it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:03, 77.61it/s] Loading 0: 12%|█▏ | 34/291 [00:00<00:03, 79.12it/s] Loading 0: 15%|█▍ | 43/291 [00:00<00:03, 76.78it/s] Loading 0: 18%|█▊ | 52/291 [00:00<00:02, 79.71it/s] Loading 0: 21%|██ | 61/291 [00:00<00:02, 82.63it/s] Loading 0: 24%|██▍ | 70/291 [00:00<00:02, 82.37it/s] Loading 0: 27%|██▋ | 79/291 [00:00<00:02, 83.82it/s] Loading 0: 30%|███ | 88/291 [00:02<00:09, 21.13it/s] Loading 0: 33%|███▎ | 97/291 [00:02<00:07, 26.91it/s] Loading 0: 36%|███▋ | 106/291 [00:02<00:05, 33.84it/s] Loading 0: 40%|███▉ | 115/291 [00:02<00:04, 40.24it/s] Loading 0: 43%|████▎ | 124/291 [00:02<00:03, 47.97it/s] Loading 0: 46%|████▌ | 133/291 [00:02<00:02, 54.88it/s] Loading 0: 49%|████▉ | 142/291 [00:02<00:02, 61.13it/s] Loading 0: 52%|█████▏ | 151/291 [00:02<00:02, 67.00it/s] Loading 0: 55%|█████▍ | 160/291 [00:03<00:01, 72.07it/s] Loading 0: 58%|█████▊ | 169/291 [00:03<00:01, 73.83it/s] Loading 0: 61%|██████ | 178/291 [00:03<00:01, 76.61it/s] Loading 0: 64%|██████▍ | 187/291 [00:04<00:04, 21.42it/s] Loading 0: 67%|██████▋ | 196/291 [00:04<00:03, 27.56it/s] Loading 0: 70%|███████ | 205/291 [00:04<00:02, 34.36it/s] Loading 0: 74%|███████▎ | 214/291 [00:04<00:01, 41.92it/s] Loading 0: 77%|███████▋ | 223/291 [00:04<00:01, 49.57it/s] Loading 0: 80%|███████▉ | 232/291 [00:04<00:01, 56.05it/s] Loading 0: 83%|████████▎ | 241/291 [00:05<00:00, 62.31it/s] Loading 0: 86%|████████▌ | 250/291 [00:05<00:00, 67.85it/s] Loading 0: 89%|████████▉ | 259/291 [00:05<00:00, 71.89it/s] Loading 0: 92%|█████████▏| 268/291 [00:05<00:00, 70.84it/s] Loading 0: 95%|█████████▌| 277/291 [00:05<00:00, 74.31it/s] Loading 0: 99%|█████████▊| 287/291 [00:05<00:00, 43.30it/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-share-qlora-out-v9-mkmlizer: warnings.warn(
jic062-share-qlora-out-v9-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-share-qlora-out-v9-mkmlizer: warnings.warn(
jic062-share-qlora-out-v9-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-share-qlora-out-v9-mkmlizer: warnings.warn(
jic062-share-qlora-out-v9-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jic062-share-qlora-out-v9-mkmlizer: Saving duration: 0.342s
jic062-share-qlora-out-v9-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.190s
jic062-share-qlora-out-v9-mkmlizer: creating bucket guanaco-reward-models
jic062-share-qlora-out-v9-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jic062-share-qlora-out-v9-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jic062-share-qlora-out-v9_reward
jic062-share-qlora-out-v9-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jic062-share-qlora-out-v9_reward/config.json
jic062-share-qlora-out-v9-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jic062-share-qlora-out-v9_reward/tokenizer_config.json
jic062-share-qlora-out-v9-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jic062-share-qlora-out-v9_reward/special_tokens_map.json
jic062-share-qlora-out-v9-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jic062-share-qlora-out-v9_reward/merges.txt
jic062-share-qlora-out-v9-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jic062-share-qlora-out-v9_reward/vocab.json
jic062-share-qlora-out-v9-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jic062-share-qlora-out-v9_reward/tokenizer.json
jic062-share-qlora-out-v9-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/jic062-share-qlora-out-v9_reward/reward.tensors
Job jic062-share-qlora-out-v9-mkmlizer completed after 115.47s with status: succeeded
Stopping job with name jic062-share-qlora-out-v9-mkmlizer
Pipeline stage MKMLizer completed in 116.54s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service jic062-share-qlora-out-v9
Waiting for inference service jic062-share-qlora-out-v9 to be ready
Inference service jic062-share-qlora-out-v9 ready after 80.5474500656128s
Pipeline stage ISVCDeployer completed in 82.26s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.293750286102295s
Received healthy response to inference request in 1.4155206680297852s
Received healthy response to inference request in 1.3968095779418945s
Received healthy response to inference request in 1.3557021617889404s
Received healthy response to inference request in 1.2563023567199707s
5 requests
0 failed requests
5th percentile: 1.2761823177337646
10th percentile: 1.2960622787475586
20th percentile: 1.3358222007751466
30th percentile: 1.3639236450195313
40th percentile: 1.380366611480713
50th percentile: 1.3968095779418945
60th percentile: 1.4042940139770508
70th percentile: 1.411778450012207
80th percentile: 1.5911665916442872
90th percentile: 1.942458438873291
95th percentile: 2.118104362487793
99th percentile: 2.2586211013793944
mean time: 1.5436170101165771
Pipeline stage StressChecker completed in 8.39s
jic062-share-qlora-out_v9 status is now deployed due to DeploymentManager action
jic062-share-qlora-out_v9 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of jic062-share-qlora-out_v9
Running pipeline stage ISVCDeleter
Checking if service jic062-share-qlora-out-v9 is running
Tearing down inference service jic062-share-qlora-out-v9
Service jic062-share-qlora-out-v9 has been torndown
Pipeline stage ISVCDeleter completed in 5.31s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key jic062-share-qlora-out-v9/config.json from bucket guanaco-mkml-models
Deleting key jic062-share-qlora-out-v9/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key jic062-share-qlora-out-v9/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key jic062-share-qlora-out-v9/tokenizer.json from bucket guanaco-mkml-models
Deleting key jic062-share-qlora-out-v9/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key jic062-share-qlora-out-v9_reward/config.json from bucket guanaco-reward-models
Deleting key jic062-share-qlora-out-v9_reward/merges.txt from bucket guanaco-reward-models
Deleting key jic062-share-qlora-out-v9_reward/reward.tensors from bucket guanaco-reward-models
Deleting key jic062-share-qlora-out-v9_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key jic062-share-qlora-out-v9_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key jic062-share-qlora-out-v9_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key jic062-share-qlora-out-v9_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.29s
jic062-share-qlora-out_v9 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics