submission_id: jic062-instruct-v17-ori-g36_v1
developer_uid: chace9580
alignment_samples: 0
best_of: 16
celo_rating: 1231.71
display_name: jic062-instruct-v17-ori-g36_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', '<|end_of_text|>', '|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_v17_ori_g36
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: jic062/instruct_v17_ori_
model_name: jic062-instruct-v17-ori-g36_v1
model_num_parameters: 8030261248.0
model_repo: jic062/instruct_v17_ori_g36
model_size: 8B
num_battles: 14649
num_wins: 7559
propriety_score: 0.7096
propriety_total_count: 1250.0
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/gpt2_xl_pairwise_89m_step_347634
status: torndown
submission_type: basic
timestamp: 2024-08-06T05:20:47+00:00
us_pacific_date: 2024-08-05
win_ratio: 0.516007918629258
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name jic062-instruct-v17-ori-g36-v1-mkmlizer
Waiting for job on jic062-instruct-v17-ori-g36-v1-mkmlizer to finish
jic062-instruct-v17-ori-g36-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-instruct-v17-ori-g36-v1-mkmlizer: ║ _____ __ __ ║
jic062-instruct-v17-ori-g36-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
jic062-instruct-v17-ori-g36-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
jic062-instruct-v17-ori-g36-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
jic062-instruct-v17-ori-g36-v1-mkmlizer: ║ /___/ ║
jic062-instruct-v17-ori-g36-v1-mkmlizer: ║ ║
jic062-instruct-v17-ori-g36-v1-mkmlizer: ║ Version: 0.9.9 ║
jic062-instruct-v17-ori-g36-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
jic062-instruct-v17-ori-g36-v1-mkmlizer: ║ https://mk1.ai ║
jic062-instruct-v17-ori-g36-v1-mkmlizer: ║ ║
jic062-instruct-v17-ori-g36-v1-mkmlizer: ║ The license key for the current software has been verified as ║
jic062-instruct-v17-ori-g36-v1-mkmlizer: ║ belonging to: ║
jic062-instruct-v17-ori-g36-v1-mkmlizer: ║ ║
jic062-instruct-v17-ori-g36-v1-mkmlizer: ║ Chai Research Corp. ║
jic062-instruct-v17-ori-g36-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
jic062-instruct-v17-ori-g36-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
jic062-instruct-v17-ori-g36-v1-mkmlizer: ║ ║
jic062-instruct-v17-ori-g36-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jic062-instruct-v17-ori-g36-v1-mkmlizer: Downloaded to shared memory in 31.418s
jic062-instruct-v17-ori-g36-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpwwp6g5ru, device:0
jic062-instruct-v17-ori-g36-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jic062-instruct-v17-ori-g36-v1-mkmlizer: quantized model in 26.228s
jic062-instruct-v17-ori-g36-v1-mkmlizer: Processed model jic062/instruct_v17_ori_g36 in 57.646s
jic062-instruct-v17-ori-g36-v1-mkmlizer: creating bucket guanaco-mkml-models
jic062-instruct-v17-ori-g36-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-instruct-v17-ori-g36-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-instruct-v17-ori-g36-v1
jic062-instruct-v17-ori-g36-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-instruct-v17-ori-g36-v1/config.json
jic062-instruct-v17-ori-g36-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-instruct-v17-ori-g36-v1/special_tokens_map.json
jic062-instruct-v17-ori-g36-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-instruct-v17-ori-g36-v1/tokenizer_config.json
jic062-instruct-v17-ori-g36-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-instruct-v17-ori-g36-v1/tokenizer.json
jic062-instruct-v17-ori-g36-v1-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
jic062-instruct-v17-ori-g36-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 7/291 [00:00<00:05, 49.75it/s] Loading 0: 8%|▊ | 22/291 [00:00<00:03, 81.57it/s] Loading 0: 11%|█ | 31/291 [00:00<00:03, 82.74it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:03, 83.36it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:03, 77.92it/s] Loading 0: 20%|█▉ | 58/291 [00:00<00:02, 77.80it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:02, 76.75it/s] Loading 0: 26%|██▌ | 76/291 [00:00<00:02, 74.76it/s] Loading 0: 29%|██▉ | 84/291 [00:02<00:10, 20.61it/s] Loading 0: 31%|███ | 90/291 [00:02<00:08, 23.90it/s] Loading 0: 33%|███▎ | 97/291 [00:02<00:06, 28.78it/s] Loading 0: 36%|███▋ | 106/291 [00:02<00:04, 37.42it/s] Loading 0: 40%|███▉ | 115/291 [00:02<00:03, 45.12it/s] Loading 0: 43%|████▎ | 124/291 [00:02<00:03, 53.27it/s] Loading 0: 46%|████▌ | 133/291 [00:02<00:02, 57.82it/s] Loading 0: 49%|████▉ | 142/291 [00:02<00:02, 63.09it/s] Loading 0: 52%|█████▏ | 151/291 [00:02<00:02, 67.03it/s] Loading 0: 55%|█████▍ | 160/291 [00:03<00:01, 70.70it/s] Loading 0: 58%|█████▊ | 169/291 [00:03<00:01, 69.43it/s] Loading 0: 61%|██████ | 178/291 [00:03<00:01, 71.23it/s] Loading 0: 64%|██████▍ | 187/291 [00:04<00:04, 20.95it/s] Loading 0: 67%|██████▋ | 196/291 [00:04<00:03, 27.22it/s] Loading 0: 70%|███████ | 205/291 [00:04<00:02, 33.91it/s] Loading 0: 74%|███████▎ | 214/291 [00:04<00:01, 40.62it/s] Loading 0: 77%|███████▋ | 223/291 [00:04<00:01, 46.58it/s] Loading 0: 80%|███████▉ | 232/291 [00:05<00:01, 52.81it/s] Loading 0: 83%|████████▎ | 241/291 [00:05<00:00, 59.36it/s] Loading 0: 86%|████████▌ | 250/291 [00:05<00:00, 64.62it/s] Loading 0: 89%|████████▉ | 259/291 [00:05<00:00, 67.46it/s] Loading 0: 92%|█████████▏| 268/291 [00:05<00:00, 71.52it/s] Loading 0: 95%|█████████▌| 277/291 [00:05<00:00, 73.44it/s] Loading 0: 98%|█████████▊| 286/291 [00:05<00:00, 77.40it/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-v17-ori-g36-v1-mkmlizer: warnings.warn(
jic062-instruct-v17-ori-g36-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-v17-ori-g36-v1-mkmlizer: warnings.warn(
jic062-instruct-v17-ori-g36-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-v17-ori-g36-v1-mkmlizer: warnings.warn(
jic062-instruct-v17-ori-g36-v1-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:05<00:05, 5.29s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 3.87s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.08s/it]
jic062-instruct-v17-ori-g36-v1-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 2.39it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.95it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.60it/s]
jic062-instruct-v17-ori-g36-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jic062-instruct-v17-ori-g36-v1-mkmlizer: Saving duration: 1.330s
jic062-instruct-v17-ori-g36-v1-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.342s
jic062-instruct-v17-ori-g36-v1-mkmlizer: creating bucket guanaco-reward-models
jic062-instruct-v17-ori-g36-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jic062-instruct-v17-ori-g36-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jic062-instruct-v17-ori-g36-v1_reward
jic062-instruct-v17-ori-g36-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jic062-instruct-v17-ori-g36-v1_reward/config.json
jic062-instruct-v17-ori-g36-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jic062-instruct-v17-ori-g36-v1_reward/special_tokens_map.json
jic062-instruct-v17-ori-g36-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jic062-instruct-v17-ori-g36-v1_reward/tokenizer_config.json
jic062-instruct-v17-ori-g36-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jic062-instruct-v17-ori-g36-v1_reward/merges.txt
jic062-instruct-v17-ori-g36-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jic062-instruct-v17-ori-g36-v1_reward/vocab.json
jic062-instruct-v17-ori-g36-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jic062-instruct-v17-ori-g36-v1_reward/tokenizer.json
jic062-instruct-v17-ori-g36-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/jic062-instruct-v17-ori-g36-v1_reward/reward.tensors
Job jic062-instruct-v17-ori-g36-v1-mkmlizer completed after 105.0s with status: succeeded
Stopping job with name jic062-instruct-v17-ori-g36-v1-mkmlizer
Pipeline stage MKMLizer completed in 106.01s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service jic062-instruct-v17-ori-g36-v1
Waiting for inference service jic062-instruct-v17-ori-g36-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service jic062-instruct-v17-ori-g36-v1 ready after 191.2893922328949s
Pipeline stage ISVCDeployer completed in 193.37s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.200162410736084s
Received healthy response to inference request in 1.4987127780914307s
Received healthy response to inference request in 1.4271700382232666s
Received healthy response to inference request in 1.3827104568481445s
Received healthy response to inference request in 1.4881443977355957s
5 requests
0 failed requests
5th percentile: 1.391602373123169
10th percentile: 1.4004942893981933
20th percentile: 1.418278121948242
30th percentile: 1.4393649101257324
40th percentile: 1.463754653930664
50th percentile: 1.4881443977355957
60th percentile: 1.4923717498779296
70th percentile: 1.4965991020202636
80th percentile: 1.6390027046203615
90th percentile: 1.9195825576782228
95th percentile: 2.059872484207153
99th percentile: 2.1721044254302977
mean time: 1.5993800163269043
Pipeline stage StressChecker completed in 8.73s
jic062-instruct-v17-ori-g36_v1 status is now deployed due to DeploymentManager action
jic062-instruct-v17-ori-g36_v1 status is now inactive due to auto deactivation removed underperforming models
jic062-instruct-v17-ori-g36_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics