submission_id: jic062-instruct-v17-g32-lr1_v1
developer_uid: chace9580
alignment_samples: 0
best_of: 16
celo_rating: 1224.41
display_name: jic062-instruct-v17-g32-lr1_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_g32_lr1
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: jic062/instruct_v17_g32_
model_name: jic062-instruct-v17-g32-lr1_v1
model_num_parameters: 8030261248.0
model_repo: jic062/instruct_v17_g32_lr1
model_size: 8B
num_battles: 14521
num_wins: 7375
propriety_score: 0.7170228445099485
propriety_total_count: 1357.0
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: 2024-08-08T16:29:26+00:00
us_pacific_date: 2024-08-08
win_ratio: 0.5078851318779698
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name jic062-instruct-v17-g32-lr1-v1-mkmlizer
Waiting for job on jic062-instruct-v17-g32-lr1-v1-mkmlizer to finish
jic062-instruct-v17-g32-lr1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-instruct-v17-g32-lr1-v1-mkmlizer: ║ _____ __ __ ║
jic062-instruct-v17-g32-lr1-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
jic062-instruct-v17-g32-lr1-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
jic062-instruct-v17-g32-lr1-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
jic062-instruct-v17-g32-lr1-v1-mkmlizer: ║ /___/ ║
jic062-instruct-v17-g32-lr1-v1-mkmlizer: ║ ║
jic062-instruct-v17-g32-lr1-v1-mkmlizer: ║ Version: 0.9.9 ║
jic062-instruct-v17-g32-lr1-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
jic062-instruct-v17-g32-lr1-v1-mkmlizer: ║ https://mk1.ai ║
jic062-instruct-v17-g32-lr1-v1-mkmlizer: ║ ║
jic062-instruct-v17-g32-lr1-v1-mkmlizer: ║ The license key for the current software has been verified as ║
jic062-instruct-v17-g32-lr1-v1-mkmlizer: ║ belonging to: ║
jic062-instruct-v17-g32-lr1-v1-mkmlizer: ║ ║
jic062-instruct-v17-g32-lr1-v1-mkmlizer: ║ Chai Research Corp. ║
jic062-instruct-v17-g32-lr1-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
jic062-instruct-v17-g32-lr1-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
jic062-instruct-v17-g32-lr1-v1-mkmlizer: ║ ║
jic062-instruct-v17-g32-lr1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jic062-instruct-v17-g32-lr1-v1-mkmlizer: Downloaded to shared memory in 30.717s
jic062-instruct-v17-g32-lr1-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpvkr88g0f, device:0
jic062-instruct-v17-g32-lr1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jic062-instruct-v17-g32-lr1-v1-mkmlizer: quantized model in 25.897s
jic062-instruct-v17-g32-lr1-v1-mkmlizer: Processed model jic062/instruct_v17_g32_lr1 in 56.614s
jic062-instruct-v17-g32-lr1-v1-mkmlizer: creating bucket guanaco-mkml-models
jic062-instruct-v17-g32-lr1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-instruct-v17-g32-lr1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-instruct-v17-g32-lr1-v1
jic062-instruct-v17-g32-lr1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-instruct-v17-g32-lr1-v1/config.json
jic062-instruct-v17-g32-lr1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-instruct-v17-g32-lr1-v1/special_tokens_map.json
jic062-instruct-v17-g32-lr1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-instruct-v17-g32-lr1-v1/tokenizer_config.json
jic062-instruct-v17-g32-lr1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-instruct-v17-g32-lr1-v1/tokenizer.json
jic062-instruct-v17-g32-lr1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-instruct-v17-g32-lr1-v1/flywheel_model.0.safetensors
jic062-instruct-v17-g32-lr1-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-g32-lr1-v1-mkmlizer: warnings.warn(
jic062-instruct-v17-g32-lr1-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-g32-lr1-v1-mkmlizer: warnings.warn(
jic062-instruct-v17-g32-lr1-v1-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:06<00:06, 6.46s/it] Downloading shards: 100%|██████████| 2/2 [00:13<00:00, 6.58s/it] Downloading shards: 100%|██████████| 2/2 [00:13<00:00, 6.56s/it]
jic062-instruct-v17-g32-lr1-v1-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 2.41it/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-g32-lr1-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jic062-instruct-v17-g32-lr1-v1-mkmlizer: Saving duration: 1.365s
jic062-instruct-v17-g32-lr1-v1-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 18.122s
jic062-instruct-v17-g32-lr1-v1-mkmlizer: creating bucket guanaco-reward-models
jic062-instruct-v17-g32-lr1-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jic062-instruct-v17-g32-lr1-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jic062-instruct-v17-g32-lr1-v1_reward
jic062-instruct-v17-g32-lr1-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jic062-instruct-v17-g32-lr1-v1_reward/config.json
jic062-instruct-v17-g32-lr1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jic062-instruct-v17-g32-lr1-v1_reward/tokenizer_config.json
jic062-instruct-v17-g32-lr1-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jic062-instruct-v17-g32-lr1-v1_reward/special_tokens_map.json
jic062-instruct-v17-g32-lr1-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jic062-instruct-v17-g32-lr1-v1_reward/merges.txt
jic062-instruct-v17-g32-lr1-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/jic062-instruct-v17-g32-lr1-v1_reward/reward.tensors
Job jic062-instruct-v17-g32-lr1-v1-mkmlizer completed after 104.89s with status: succeeded
Stopping job with name jic062-instruct-v17-g32-lr1-v1-mkmlizer
Pipeline stage MKMLizer completed in 106.46s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service jic062-instruct-v17-g32-lr1-v1
Waiting for inference service jic062-instruct-v17-g32-lr1-v1 to be ready
Inference service jic062-instruct-v17-g32-lr1-v1 ready after 201.39219784736633s
Pipeline stage ISVCDeployer completed in 203.12s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.270155668258667s
Received healthy response to inference request in 1.5979015827178955s
Received healthy response to inference request in 1.433049201965332s
Received healthy response to inference request in 1.4140567779541016s
Received healthy response to inference request in 1.4910516738891602s
5 requests
0 failed requests
5th percentile: 1.4178552627563477
10th percentile: 1.4216537475585938
20th percentile: 1.429250717163086
30th percentile: 1.4446496963500977
40th percentile: 1.467850685119629
50th percentile: 1.4910516738891602
60th percentile: 1.5337916374206544
70th percentile: 1.5765316009521484
80th percentile: 1.73235239982605
90th percentile: 2.0012540340423586
95th percentile: 2.1357048511505123
99th percentile: 2.2432655048370362
mean time: 1.6412429809570312
Pipeline stage StressChecker completed in 8.88s
jic062-instruct-v17-g32-lr1_v1 status is now deployed due to DeploymentManager action
jic062-instruct-v17-g32-lr1_v1 status is now inactive due to auto deactivation removed underperforming models
jic062-instruct-v17-g32-lr1_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics