submission_id: rinen0721-tsk2-test1_v2
developer_uid: rinen0721
alignment_samples: 13112
alignment_score: -0.21648304802142124
best_of: 4
celo_rating: 1150.58
display_name: rinen0721-tsk2-test1_v2
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\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'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64, 'reward_max_token_input': 512}
is_internal_developer: False
language_model: rinen0721/tsk2-test1
max_input_tokens: 512
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: rinen0721/tsk2-test1
model_name: rinen0721-tsk2-test1_v2
model_num_parameters: 7241732096.0
model_repo: rinen0721/tsk2-test1
model_size: 7B
num_battles: 13112
num_wins: 5230
propriety_score: 0.7472803347280335
propriety_total_count: 1195.0
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: 2024-08-10T13:14:36+00:00
us_pacific_date: 2024-08-10
win_ratio: 0.3988712629652227
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name rinen0721-tsk2-test1-v2-mkmlizer
Waiting for job on rinen0721-tsk2-test1-v2-mkmlizer to finish
rinen0721-tsk2-test1-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rinen0721-tsk2-test1-v2-mkmlizer: ║ _____ __ __ ║
rinen0721-tsk2-test1-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rinen0721-tsk2-test1-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rinen0721-tsk2-test1-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rinen0721-tsk2-test1-v2-mkmlizer: ║ /___/ ║
rinen0721-tsk2-test1-v2-mkmlizer: ║ ║
rinen0721-tsk2-test1-v2-mkmlizer: ║ Version: 0.9.9 ║
rinen0721-tsk2-test1-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rinen0721-tsk2-test1-v2-mkmlizer: ║ https://mk1.ai ║
rinen0721-tsk2-test1-v2-mkmlizer: ║ ║
rinen0721-tsk2-test1-v2-mkmlizer: ║ The license key for the current software has been verified as ║
rinen0721-tsk2-test1-v2-mkmlizer: ║ belonging to: ║
rinen0721-tsk2-test1-v2-mkmlizer: ║ ║
rinen0721-tsk2-test1-v2-mkmlizer: ║ Chai Research Corp. ║
rinen0721-tsk2-test1-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rinen0721-tsk2-test1-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
rinen0721-tsk2-test1-v2-mkmlizer: ║ ║
rinen0721-tsk2-test1-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rinen0721-tsk2-test1-v2-mkmlizer: Downloaded to shared memory in 20.488s
rinen0721-tsk2-test1-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpk11jyvsp, device:0
rinen0721-tsk2-test1-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rinen0721-tsk2-test1-v2-mkmlizer: quantized model in 17.397s
rinen0721-tsk2-test1-v2-mkmlizer: Processed model rinen0721/tsk2-test1 in 37.885s
rinen0721-tsk2-test1-v2-mkmlizer: creating bucket guanaco-mkml-models
rinen0721-tsk2-test1-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rinen0721-tsk2-test1-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rinen0721-tsk2-test1-v2
rinen0721-tsk2-test1-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rinen0721-tsk2-test1-v2/config.json
rinen0721-tsk2-test1-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rinen0721-tsk2-test1-v2/special_tokens_map.json
rinen0721-tsk2-test1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rinen0721-tsk2-test1-v2/tokenizer_config.json
rinen0721-tsk2-test1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/rinen0721-tsk2-test1-v2/tokenizer.model
rinen0721-tsk2-test1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rinen0721-tsk2-test1-v2/tokenizer.json
rinen0721-tsk2-test1-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rinen0721-tsk2-test1-v2/flywheel_model.0.safetensors
rinen0721-tsk2-test1-v2-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
rinen0721-tsk2-test1-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 7/291 [00:00<00:06, 42.86it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:04, 59.54it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:03, 70.55it/s] Loading 0: 12%|█▏ | 34/291 [00:00<00:03, 75.70it/s] Loading 0: 15%|█▍ | 43/291 [00:00<00:03, 79.06it/s] Loading 0: 18%|█▊ | 52/291 [00:00<00:02, 80.50it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:02, 90.61it/s] Loading 0: 27%|██▋ | 79/291 [00:00<00:02, 86.92it/s] Loading 0: 30%|███ | 88/291 [00:01<00:02, 85.86it/s] Loading 0: 33%|███▎ | 97/291 [00:01<00:02, 85.21it/s] Loading 0: 36%|███▋ | 106/291 [00:02<00:08, 22.47it/s] Loading 0: 40%|███▉ | 115/291 [00:02<00:06, 28.62it/s] Loading 0: 43%|████▎ | 124/291 [00:02<00:04, 35.24it/s] Loading 0: 46%|████▌ | 133/291 [00:02<00:03, 42.66it/s] Loading 0: 49%|████▉ | 142/291 [00:02<00:02, 50.07it/s] Loading 0: 52%|█████▏ | 151/291 [00:02<00:02, 55.66it/s] Loading 0: 55%|█████▍ | 160/291 [00:03<00:02, 61.25it/s] Loading 0: 58%|█████▊ | 170/291 [00:03<00:01, 69.88it/s] Loading 0: 62%|██████▏ | 179/291 [00:03<00:01, 73.02it/s] Loading 0: 65%|██████▍ | 188/291 [00:03<00:01, 76.35it/s] Loading 0: 68%|██████▊ | 197/291 [00:03<00:01, 76.67it/s] Loading 0: 71%|███████ | 206/291 [00:04<00:03, 22.65it/s] Loading 0: 76%|███████▌ | 220/291 [00:04<00:02, 32.57it/s] Loading 0: 79%|███████▊ | 229/291 [00:04<00:01, 38.72it/s] Loading 0: 82%|████████▏ | 238/291 [00:04<00:01, 45.19it/s] Loading 0: 85%|████████▍ | 247/291 [00:04<00:00, 51.17it/s] Loading 0: 88%|████████▊ | 256/291 [00:05<00:00, 56.00it/s] Loading 0: 91%|█████████ | 265/291 [00:05<00:00, 59.67it/s] Loading 0: 94%|█████████▍| 274/291 [00:05<00:00, 64.38it/s] Loading 0: 97%|█████████▋| 283/291 [00:05<00:00, 69.41it/s] Loading 0: 100%|██████████| 291/291 [00:06<00:00, 17.89it/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.
rinen0721-tsk2-test1-v2-mkmlizer: warnings.warn(
rinen0721-tsk2-test1-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.
rinen0721-tsk2-test1-v2-mkmlizer: warnings.warn(
rinen0721-tsk2-test1-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.
rinen0721-tsk2-test1-v2-mkmlizer: warnings.warn(
rinen0721-tsk2-test1-v2-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:05<00:05, 5.57s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.13s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.34s/it]
rinen0721-tsk2-test1-v2-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 2.10it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.40it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.11it/s]
rinen0721-tsk2-test1-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
rinen0721-tsk2-test1-v2-mkmlizer: Saving duration: 1.349s
rinen0721-tsk2-test1-v2-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.801s
rinen0721-tsk2-test1-v2-mkmlizer: creating bucket guanaco-reward-models
rinen0721-tsk2-test1-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
rinen0721-tsk2-test1-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/rinen0721-tsk2-test1-v2_reward
rinen0721-tsk2-test1-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/rinen0721-tsk2-test1-v2_reward/special_tokens_map.json
rinen0721-tsk2-test1-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/rinen0721-tsk2-test1-v2_reward/config.json
rinen0721-tsk2-test1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/rinen0721-tsk2-test1-v2_reward/tokenizer_config.json
rinen0721-tsk2-test1-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/rinen0721-tsk2-test1-v2_reward/merges.txt
rinen0721-tsk2-test1-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/rinen0721-tsk2-test1-v2_reward/vocab.json
rinen0721-tsk2-test1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/rinen0721-tsk2-test1-v2_reward/tokenizer.json
rinen0721-tsk2-test1-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/rinen0721-tsk2-test1-v2_reward/reward.tensors
Job rinen0721-tsk2-test1-v2-mkmlizer completed after 85.38s with status: succeeded
Stopping job with name rinen0721-tsk2-test1-v2-mkmlizer
Pipeline stage MKMLizer completed in 86.48s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service rinen0721-tsk2-test1-v2
Waiting for inference service rinen0721-tsk2-test1-v2 to be ready
Inference service rinen0721-tsk2-test1-v2 ready after 201.18984150886536s
Pipeline stage ISVCDeployer completed in 203.31s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7686491012573242s
Received healthy response to inference request in 0.819587230682373s
Received healthy response to inference request in 1.0206189155578613s
Received healthy response to inference request in 0.9818289279937744s
Received healthy response to inference request in 0.868004560470581s
5 requests
0 failed requests
5th percentile: 0.8292706966400146
10th percentile: 0.8389541625976562
20th percentile: 0.8583210945129395
30th percentile: 0.8907694339752197
40th percentile: 0.936299180984497
50th percentile: 0.9818289279937744
60th percentile: 0.9973449230194091
70th percentile: 1.0128609180450439
80th percentile: 1.170224952697754
90th percentile: 1.4694370269775392
95th percentile: 1.6190430641174316
99th percentile: 1.7387278938293458
mean time: 1.0917377471923828
Pipeline stage StressChecker completed in 6.33s
rinen0721-tsk2-test1_v2 status is now deployed due to DeploymentManager action
rinen0721-tsk2-test1_v2 status is now inactive due to auto deactivation removed underperforming models
rinen0721-tsk2-test1_v2 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics