submission_id: jic062-instruct-v17-reg_v1
developer_uid: chace9580
alignment_samples: 9352
alignment_score: 0.3953824057937701
best_of: 16
celo_rating: 1230.69
display_name: jic062-instruct-v17-reg_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_reg
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: jic062/instruct_v17_reg
model_name: jic062-instruct-v17-reg_v1
model_num_parameters: 8030261248.0
model_repo: jic062/instruct_v17_reg
model_size: 8B
num_battles: 9352
num_wins: 4944
propriety_score: 0.7239819004524887
propriety_total_count: 1105.0
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: 2024-08-13T18:56:10+00:00
us_pacific_date: 2024-08-13
win_ratio: 0.5286569717707442
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name jic062-instruct-v17-reg-v1-mkmlizer
Waiting for job on jic062-instruct-v17-reg-v1-mkmlizer to finish
Stopping job with name jic062-instruct-v17-reg-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name jic062-instruct-v17-reg-v1-mkmlizer
Waiting for job on jic062-instruct-v17-reg-v1-mkmlizer to finish
jic062-instruct-v17-reg-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-instruct-v17-reg-v1-mkmlizer: ║ _____ __ __ ║
jic062-instruct-v17-reg-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
jic062-instruct-v17-reg-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
jic062-instruct-v17-reg-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
jic062-instruct-v17-reg-v1-mkmlizer: ║ /___/ ║
jic062-instruct-v17-reg-v1-mkmlizer: ║ ║
jic062-instruct-v17-reg-v1-mkmlizer: ║ Version: 0.9.9 ║
jic062-instruct-v17-reg-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
jic062-instruct-v17-reg-v1-mkmlizer: ║ https://mk1.ai ║
jic062-instruct-v17-reg-v1-mkmlizer: ║ ║
jic062-instruct-v17-reg-v1-mkmlizer: ║ The license key for the current software has been verified as ║
jic062-instruct-v17-reg-v1-mkmlizer: ║ belonging to: ║
jic062-instruct-v17-reg-v1-mkmlizer: ║ ║
jic062-instruct-v17-reg-v1-mkmlizer: ║ Chai Research Corp. ║
jic062-instruct-v17-reg-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
jic062-instruct-v17-reg-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
jic062-instruct-v17-reg-v1-mkmlizer: ║ ║
jic062-instruct-v17-reg-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jic062-instruct-v17-reg-v1-mkmlizer: Downloaded to shared memory in 31.936s
jic062-instruct-v17-reg-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpavb5owgt, device:0
jic062-instruct-v17-reg-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jic062-instruct-v17-reg-v1-mkmlizer: quantized model in 27.022s
jic062-instruct-v17-reg-v1-mkmlizer: Processed model jic062/instruct_v17_reg in 58.958s
jic062-instruct-v17-reg-v1-mkmlizer: creating bucket guanaco-mkml-models
jic062-instruct-v17-reg-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-instruct-v17-reg-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-instruct-v17-reg-v1
jic062-instruct-v17-reg-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-instruct-v17-reg-v1/config.json
jic062-instruct-v17-reg-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-instruct-v17-reg-v1/special_tokens_map.json
jic062-instruct-v17-reg-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-instruct-v17-reg-v1/tokenizer_config.json
jic062-instruct-v17-reg-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-instruct-v17-reg-v1/tokenizer.json
jic062-instruct-v17-reg-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-instruct-v17-reg-v1/flywheel_model.0.safetensors
jic062-instruct-v17-reg-v1-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
jic062-instruct-v17-reg-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 7/291 [00:00<00:05, 49.84it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:03, 69.77it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:03, 75.89it/s] Loading 0: 12%|█▏ | 34/291 [00:00<00:03, 75.99it/s] Loading 0: 15%|█▍ | 43/291 [00:00<00:03, 73.83it/s] Loading 0: 18%|█▊ | 52/291 [00:00<00:03, 74.52it/s] Loading 0: 21%|██ | 61/291 [00:00<00:03, 75.72it/s] Loading 0: 24%|██▍ | 70/291 [00:00<00:02, 73.68it/s] Loading 0: 27%|██▋ | 79/291 [00:01<00:02, 74.26it/s] Loading 0: 30%|██▉ | 87/291 [00:02<00:10, 19.77it/s] Loading 0: 32%|███▏ | 94/291 [00:02<00:08, 23.78it/s] Loading 0: 35%|███▌ | 103/291 [00:02<00:06, 30.71it/s] Loading 0: 38%|███▊ | 112/291 [00:02<00:04, 37.99it/s] Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 44.82it/s] Loading 0: 45%|████▍ | 130/291 [00:02<00:03, 50.49it/s] Loading 0: 48%|████▊ | 139/291 [00:02<00:02, 56.60it/s] Loading 0: 51%|█████ | 148/291 [00:03<00:02, 60.94it/s] Loading 0: 54%|█████▍ | 157/291 [00:03<00:02, 61.60it/s] Loading 0: 57%|█████▋ | 166/291 [00:03<00:01, 65.16it/s] Loading 0: 60%|██████ | 175/291 [00:03<00:01, 67.25it/s] Loading 0: 63%|██████▎ | 184/291 [00:03<00:01, 67.02it/s] Loading 0: 66%|██████▌ | 192/291 [00:04<00:04, 20.10it/s] Loading 0: 68%|██████▊ | 198/291 [00:04<00:04, 23.23it/s] Loading 0: 70%|███████ | 205/291 [00:04<00:03, 27.64it/s] Loading 0: 74%|███████▎ | 214/291 [00:05<00:02, 34.65it/s] Loading 0: 77%|███████▋ | 223/291 [00:05<00:01, 42.18it/s] Loading 0: 80%|███████▉ | 232/291 [00:05<00:01, 47.67it/s] Loading 0: 83%|████████▎ | 241/291 [00:05<00:00, 52.03it/s] Loading 0: 86%|████████▌ | 250/291 [00:05<00:00, 56.25it/s] Loading 0: 89%|████████▉ | 259/291 [00:05<00:00, 60.87it/s] Loading 0: 92%|█████████▏| 268/291 [00:05<00:00, 63.62it/s] Loading 0: 95%|█████████▌| 277/291 [00:05<00:00, 65.93it/s] Loading 0: 98%|█████████▊| 286/291 [00:06<00:00, 68.23it/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-reg-v1-mkmlizer: warnings.warn(
jic062-instruct-v17-reg-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-reg-v1-mkmlizer: warnings.warn(
jic062-instruct-v17-reg-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-reg-v1-mkmlizer: warnings.warn(
jic062-instruct-v17-reg-v1-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:06<00:06, 6.05s/it] Downloading shards: 100%|██████████| 2/2 [00:09<00:00, 4.35s/it] Downloading shards: 100%|██████████| 2/2 [00:09<00:00, 4.61s/it]
jic062-instruct-v17-reg-v1-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 2.37it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.90it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.56it/s]
jic062-instruct-v17-reg-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jic062-instruct-v17-reg-v1-mkmlizer: Saving duration: 1.341s
jic062-instruct-v17-reg-v1-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 14.503s
jic062-instruct-v17-reg-v1-mkmlizer: creating bucket guanaco-reward-models
jic062-instruct-v17-reg-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jic062-instruct-v17-reg-v1_reward/tokenizer_config.json
jic062-instruct-v17-reg-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jic062-instruct-v17-reg-v1_reward/config.json
jic062-instruct-v17-reg-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jic062-instruct-v17-reg-v1_reward/special_tokens_map.json
jic062-instruct-v17-reg-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jic062-instruct-v17-reg-v1_reward/merges.txt
jic062-instruct-v17-reg-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jic062-instruct-v17-reg-v1_reward/vocab.json
jic062-instruct-v17-reg-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jic062-instruct-v17-reg-v1_reward/tokenizer.json
jic062-instruct-v17-reg-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/jic062-instruct-v17-reg-v1_reward/reward.tensors
Job jic062-instruct-v17-reg-v1-mkmlizer completed after 104.92s with status: succeeded
Stopping job with name jic062-instruct-v17-reg-v1-mkmlizer
Pipeline stage MKMLizer completed in 106.65s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service jic062-instruct-v17-reg-v1
Waiting for inference service jic062-instruct-v17-reg-v1 to be ready
Inference service jic062-instruct-v17-reg-v1 ready after 211.2871332168579s
Pipeline stage ISVCDeployer completed in 213.02s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.291273593902588s
Received healthy response to inference request in 1.4630932807922363s
Received healthy response to inference request in 1.468904733657837s
Received healthy response to inference request in 1.448364019393921s
Received healthy response to inference request in 1.5249245166778564s
5 requests
0 failed requests
5th percentile: 1.451309871673584
10th percentile: 1.454255723953247
20th percentile: 1.4601474285125733
30th percentile: 1.4642555713653564
40th percentile: 1.4665801525115967
50th percentile: 1.468904733657837
60th percentile: 1.4913126468658446
70th percentile: 1.5137205600738526
80th percentile: 1.6781943321228028
90th percentile: 1.9847339630126954
95th percentile: 2.1380037784576413
99th percentile: 2.2606196308135984
mean time: 1.6393120288848877
Pipeline stage StressChecker completed in 8.95s
jic062-instruct-v17-reg_v1 status is now deployed due to DeploymentManager action
jic062-instruct-v17-reg_v1 status is now inactive due to auto deactivation removed underperforming models
jic062-instruct-v17-reg_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics