submission_id: jic062-instruct-v17-reg_v2
developer_uid: chace9580
alignment_samples: 7924
alignment_score: 0.7116909992312551
best_of: 16
celo_rating: 1237.87
display_name: jic062-instruct-v17-reg_v2
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_v2
model_num_parameters: 8030261248.0
model_repo: jic062/instruct_v17_reg
model_size: 8B
num_battles: 7924
num_wins: 4281
propriety_score: 0.7235693501454898
propriety_total_count: 1031.0
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: 2024-08-13T18:56:30+00:00
us_pacific_date: 2024-08-13
win_ratio: 0.5402574457344775
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name jic062-instruct-v17-reg-v2-mkmlizer
Waiting for job on jic062-instruct-v17-reg-v2-mkmlizer to finish
jic062-instruct-v17-reg-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-instruct-v17-reg-v2-mkmlizer: ║ _____ __ __ ║
jic062-instruct-v17-reg-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
jic062-instruct-v17-reg-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
jic062-instruct-v17-reg-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
jic062-instruct-v17-reg-v2-mkmlizer: ║ /___/ ║
jic062-instruct-v17-reg-v2-mkmlizer: ║ ║
jic062-instruct-v17-reg-v2-mkmlizer: ║ Version: 0.9.9 ║
jic062-instruct-v17-reg-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
jic062-instruct-v17-reg-v2-mkmlizer: ║ https://mk1.ai ║
jic062-instruct-v17-reg-v2-mkmlizer: ║ ║
jic062-instruct-v17-reg-v2-mkmlizer: ║ The license key for the current software has been verified as ║
jic062-instruct-v17-reg-v2-mkmlizer: ║ belonging to: ║
jic062-instruct-v17-reg-v2-mkmlizer: ║ ║
jic062-instruct-v17-reg-v2-mkmlizer: ║ Chai Research Corp. ║
jic062-instruct-v17-reg-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
jic062-instruct-v17-reg-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
jic062-instruct-v17-reg-v2-mkmlizer: ║ ║
jic062-instruct-v17-reg-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jic062-instruct-v17-reg-v2-mkmlizer: Downloaded to shared memory in 21.297s
jic062-instruct-v17-reg-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpu7ymx39f, device:0
jic062-instruct-v17-reg-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jic062-instruct-v17-reg-v2-mkmlizer: quantized model in 26.011s
jic062-instruct-v17-reg-v2-mkmlizer: Processed model jic062/instruct_v17_reg in 47.308s
jic062-instruct-v17-reg-v2-mkmlizer: creating bucket guanaco-mkml-models
jic062-instruct-v17-reg-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-instruct-v17-reg-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-instruct-v17-reg-v2
jic062-instruct-v17-reg-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-instruct-v17-reg-v2/config.json
jic062-instruct-v17-reg-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-instruct-v17-reg-v2/special_tokens_map.json
jic062-instruct-v17-reg-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-instruct-v17-reg-v2/tokenizer_config.json
jic062-instruct-v17-reg-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-instruct-v17-reg-v2/tokenizer.json
jic062-instruct-v17-reg-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-instruct-v17-reg-v2/flywheel_model.0.safetensors
jic062-instruct-v17-reg-v2-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
jic062-instruct-v17-reg-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 7/291 [00:00<00:05, 51.42it/s] Loading 0: 6%|▌ | 17/291 [00:00<00:03, 76.15it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:03, 73.60it/s] Loading 0: 12%|█▏ | 34/291 [00:00<00:03, 75.05it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:02, 87.12it/s] Loading 0: 21%|██ | 61/291 [00:00<00:02, 85.47it/s] Loading 0: 24%|██▍ | 70/291 [00:00<00:02, 85.09it/s] Loading 0: 27%|██▋ | 80/291 [00:00<00:02, 89.09it/s] Loading 0: 31%|███ | 89/291 [00:02<00:09, 22.22it/s] Loading 0: 33%|███▎ | 97/291 [00:02<00:07, 27.44it/s] Loading 0: 38%|███▊ | 112/291 [00:02<00:04, 39.54it/s] Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 46.15it/s] Loading 0: 45%|████▌ | 131/291 [00:02<00:02, 54.80it/s] Loading 0: 48%|████▊ | 140/291 [00:02<00:02, 61.05it/s] Loading 0: 51%|█████ | 149/291 [00:02<00:02, 66.66it/s] Loading 0: 54%|█████▍ | 158/291 [00:02<00:01, 67.49it/s] Loading 0: 57%|█████▋ | 167/291 [00:03<00:01, 71.26it/s] Loading 0: 60%|██████ | 176/291 [00:03<00:01, 74.69it/s] Loading 0: 64%|██████▎ | 185/291 [00:03<00:01, 78.56it/s] Loading 0: 67%|██████▋ | 194/291 [00:04<00:04, 21.60it/s] Loading 0: 70%|███████ | 204/291 [00:04<00:03, 28.84it/s] Loading 0: 74%|███████▎ | 214/291 [00:04<00:02, 35.33it/s] Loading 0: 77%|███████▋ | 223/291 [00:04<00:01, 42.46it/s] Loading 0: 80%|███████▉ | 232/291 [00:04<00:01, 48.56it/s] Loading 0: 83%|████████▎ | 241/291 [00:04<00:00, 55.05it/s] Loading 0: 86%|████████▌ | 250/291 [00:05<00:00, 60.33it/s] Loading 0: 89%|████████▉ | 259/291 [00:05<00:00, 64.27it/s] Loading 0: 94%|█████████▍| 274/291 [00:05<00:00, 76.43it/s] Loading 0: 97%|█████████▋| 283/291 [00:05<00:00, 78.74it/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-v2-mkmlizer: warnings.warn(
jic062-instruct-v17-reg-v2-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-v2-mkmlizer: warnings.warn(
jic062-instruct-v17-reg-v2-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-v2-mkmlizer: warnings.warn(
jic062-instruct-v17-reg-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jic062-instruct-v17-reg-v2-mkmlizer: Saving duration: 1.357s
jic062-instruct-v17-reg-v2-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.592s
jic062-instruct-v17-reg-v2-mkmlizer: creating bucket guanaco-reward-models
jic062-instruct-v17-reg-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jic062-instruct-v17-reg-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jic062-instruct-v17-reg-v2_reward
jic062-instruct-v17-reg-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jic062-instruct-v17-reg-v2_reward/config.json
jic062-instruct-v17-reg-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jic062-instruct-v17-reg-v2_reward/special_tokens_map.json
jic062-instruct-v17-reg-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jic062-instruct-v17-reg-v2_reward/tokenizer_config.json
jic062-instruct-v17-reg-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jic062-instruct-v17-reg-v2_reward/merges.txt
jic062-instruct-v17-reg-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jic062-instruct-v17-reg-v2_reward/vocab.json
jic062-instruct-v17-reg-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jic062-instruct-v17-reg-v2_reward/tokenizer.json
jic062-instruct-v17-reg-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/jic062-instruct-v17-reg-v2_reward/reward.tensors
Job jic062-instruct-v17-reg-v2-mkmlizer completed after 94.9s with status: succeeded
Stopping job with name jic062-instruct-v17-reg-v2-mkmlizer
Pipeline stage MKMLizer completed in 95.87s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service jic062-instruct-v17-reg-v2
Waiting for inference service jic062-instruct-v17-reg-v2 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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Retrying (%r) after connection broken by '%r': %s
Inference service jic062-instruct-v17-reg-v2 ready after 221.35370683670044s
Pipeline stage ISVCDeployer completed in 223.41s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.235703229904175s
Received healthy response to inference request in 1.4636280536651611s
Received healthy response to inference request in 1.4191291332244873s
Received healthy response to inference request in 1.4312794208526611s
Received healthy response to inference request in 1.5055830478668213s
5 requests
0 failed requests
5th percentile: 1.4215591907501222
10th percentile: 1.4239892482757568
20th percentile: 1.4288493633270263
30th percentile: 1.4377491474151611
40th percentile: 1.4506886005401611
50th percentile: 1.4636280536651611
60th percentile: 1.4804100513458252
70th percentile: 1.4971920490264892
80th percentile: 1.651607084274292
90th percentile: 1.9436551570892335
95th percentile: 2.089679193496704
99th percentile: 2.2064984226226807
mean time: 1.611064577102661
Pipeline stage StressChecker completed in 9.02s
jic062-instruct-v17-reg_v2 status is now deployed due to DeploymentManager action
jic062-instruct-v17-reg_v2 status is now inactive due to auto deactivation removed underperforming models
jic062-instruct-v17-reg_v2 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics