submission_id: rinen0721-tsk2-base_v2
developer_uid: rinen0721
alignment_samples: 12920
alignment_score: -0.5786405535368252
best_of: 4
celo_rating: 1129.14
display_name: rinen0721-tsk2-base_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-base
max_input_tokens: 512
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: rinen0721/tsk2-base
model_name: rinen0721-tsk2-base_v2
model_num_parameters: 7241732096.0
model_repo: rinen0721/tsk2-base
model_size: 7B
num_battles: 12920
num_wins: 4828
propriety_score: 0.7205479452054795
propriety_total_count: 1095.0
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: 2024-08-10T11:22:58+00:00
us_pacific_date: 2024-08-10
win_ratio: 0.3736842105263158
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name rinen0721-tsk2-base-v2-mkmlizer
Waiting for job on rinen0721-tsk2-base-v2-mkmlizer to finish
rinen0721-tsk2-base-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rinen0721-tsk2-base-v2-mkmlizer: ║ _____ __ __ ║
rinen0721-tsk2-base-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rinen0721-tsk2-base-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rinen0721-tsk2-base-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rinen0721-tsk2-base-v2-mkmlizer: ║ /___/ ║
rinen0721-tsk2-base-v2-mkmlizer: ║ ║
rinen0721-tsk2-base-v2-mkmlizer: ║ Version: 0.9.9 ║
rinen0721-tsk2-base-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rinen0721-tsk2-base-v2-mkmlizer: ║ https://mk1.ai ║
rinen0721-tsk2-base-v2-mkmlizer: ║ ║
rinen0721-tsk2-base-v2-mkmlizer: ║ The license key for the current software has been verified as ║
rinen0721-tsk2-base-v2-mkmlizer: ║ belonging to: ║
rinen0721-tsk2-base-v2-mkmlizer: ║ ║
rinen0721-tsk2-base-v2-mkmlizer: ║ Chai Research Corp. ║
rinen0721-tsk2-base-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rinen0721-tsk2-base-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
rinen0721-tsk2-base-v2-mkmlizer: ║ ║
rinen0721-tsk2-base-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rinen0721-tsk2-base-v2-mkmlizer: Downloaded to shared memory in 17.882s
rinen0721-tsk2-base-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpt6v8kjn2, device:0
rinen0721-tsk2-base-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rinen0721-tsk2-base-v2-mkmlizer: quantized model in 16.656s
rinen0721-tsk2-base-v2-mkmlizer: Processed model rinen0721/tsk2-base in 34.539s
rinen0721-tsk2-base-v2-mkmlizer: creating bucket guanaco-mkml-models
rinen0721-tsk2-base-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rinen0721-tsk2-base-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rinen0721-tsk2-base-v2
rinen0721-tsk2-base-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rinen0721-tsk2-base-v2/config.json
rinen0721-tsk2-base-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rinen0721-tsk2-base-v2/special_tokens_map.json
rinen0721-tsk2-base-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rinen0721-tsk2-base-v2/tokenizer_config.json
rinen0721-tsk2-base-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/rinen0721-tsk2-base-v2/tokenizer.model
rinen0721-tsk2-base-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rinen0721-tsk2-base-v2/tokenizer.json
rinen0721-tsk2-base-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rinen0721-tsk2-base-v2/flywheel_model.0.safetensors
rinen0721-tsk2-base-v2-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
rinen0721-tsk2-base-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:07, 37.84it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:04, 56.75it/s] Loading 0: 7%|▋ | 19/291 [00:00<00:05, 47.52it/s] Loading 0: 8%|▊ | 24/291 [00:00<00:05, 47.49it/s] Loading 0: 11%|█ | 31/291 [00:00<00:04, 54.36it/s] Loading 0: 13%|█▎ | 37/291 [00:00<00:05, 50.67it/s] Loading 0: 15%|█▍ | 43/291 [00:00<00:04, 51.70it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:04, 54.01it/s] Loading 0: 19%|█▉ | 55/291 [00:01<00:04, 50.61it/s] Loading 0: 21%|██ | 61/291 [00:01<00:04, 51.77it/s] Loading 0: 23%|██▎ | 67/291 [00:01<00:04, 52.58it/s] Loading 0: 25%|██▌ | 73/291 [00:01<00:04, 49.84it/s] Loading 0: 27%|██▋ | 79/291 [00:01<00:04, 51.62it/s] Loading 0: 30%|██▉ | 86/291 [00:01<00:04, 47.64it/s] Loading 0: 32%|███▏ | 94/291 [00:01<00:03, 53.93it/s] Loading 0: 34%|███▍ | 100/291 [00:01<00:03, 49.53it/s] Loading 0: 36%|███▋ | 106/291 [00:02<00:03, 50.67it/s] Loading 0: 38%|███▊ | 112/291 [00:02<00:03, 52.35it/s] Loading 0: 41%|████ | 118/291 [00:02<00:03, 48.29it/s] Loading 0: 42%|████▏ | 123/291 [00:02<00:03, 47.68it/s] Loading 0: 45%|████▍ | 130/291 [00:02<00:03, 51.73it/s] Loading 0: 47%|████▋ | 136/291 [00:02<00:03, 48.95it/s] Loading 0: 49%|████▉ | 144/291 [00:02<00:03, 48.77it/s] Loading 0: 52%|█████▏ | 152/291 [00:02<00:02, 55.96it/s] Loading 0: 54%|█████▍ | 158/291 [00:03<00:02, 52.01it/s] Loading 0: 56%|█████▋ | 164/291 [00:03<00:02, 52.90it/s] Loading 0: 59%|█████▉ | 171/291 [00:03<00:02, 48.96it/s] Loading 0: 62%|██████▏ | 179/291 [00:03<00:02, 55.10it/s] Loading 0: 64%|██████▎ | 185/291 [00:03<00:02, 51.29it/s] Loading 0: 66%|██████▌ | 191/291 [00:03<00:01, 52.01it/s] Loading 0: 68%|██████▊ | 197/291 [00:03<00:01, 52.64it/s] Loading 0: 70%|██████▉ | 203/291 [00:03<00:01, 48.22it/s] Loading 0: 71%|███████▏ | 208/291 [00:05<00:08, 9.80it/s] Loading 0: 73%|███████▎ | 213/291 [00:05<00:06, 12.37it/s] Loading 0: 76%|███████▌ | 220/291 [00:05<00:04, 17.25it/s] Loading 0: 78%|███████▊ | 226/291 [00:06<00:02, 21.85it/s] Loading 0: 80%|███████▉ | 232/291 [00:06<00:02, 24.71it/s] Loading 0: 82%|████████▏ | 239/291 [00:06<00:01, 31.22it/s] Loading 0: 84%|████████▍ | 245/291 [00:06<00:01, 33.13it/s] Loading 0: 86%|████████▌ | 250/291 [00:06<00:01, 36.01it/s] Loading 0: 88%|████████▊ | 257/291 [00:06<00:00, 42.81it/s] Loading 0: 90%|█████████ | 263/291 [00:06<00:00, 43.23it/s] Loading 0: 92%|█████████▏| 269/291 [00:06<00:00, 46.20it/s] Loading 0: 95%|█████████▍| 275/291 [00:06<00:00, 49.41it/s] Loading 0: 97%|█████████▋| 281/291 [00:07<00:00, 47.04it/s] Loading 0: 99%|█████████▊| 287/291 [00:07<00:00, 49.24it/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-base-v2-mkmlizer: warnings.warn(
rinen0721-tsk2-base-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-base-v2-mkmlizer: warnings.warn(
rinen0721-tsk2-base-v2-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 2.48it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 4.01it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.67it/s]
rinen0721-tsk2-base-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
rinen0721-tsk2-base-v2-mkmlizer: Saving duration: 1.313s
rinen0721-tsk2-base-v2-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 14.692s
rinen0721-tsk2-base-v2-mkmlizer: creating bucket guanaco-reward-models
rinen0721-tsk2-base-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
rinen0721-tsk2-base-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/rinen0721-tsk2-base-v2_reward
rinen0721-tsk2-base-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/rinen0721-tsk2-base-v2_reward/config.json
rinen0721-tsk2-base-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/rinen0721-tsk2-base-v2_reward/tokenizer_config.json
rinen0721-tsk2-base-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/rinen0721-tsk2-base-v2_reward/special_tokens_map.json
rinen0721-tsk2-base-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/rinen0721-tsk2-base-v2_reward/merges.txt
rinen0721-tsk2-base-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/rinen0721-tsk2-base-v2_reward/vocab.json
rinen0721-tsk2-base-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/rinen0721-tsk2-base-v2_reward/tokenizer.json
rinen0721-tsk2-base-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/rinen0721-tsk2-base-v2_reward/reward.tensors
Job rinen0721-tsk2-base-v2-mkmlizer completed after 84.52s with status: succeeded
Stopping job with name rinen0721-tsk2-base-v2-mkmlizer
Pipeline stage MKMLizer completed in 85.66s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service rinen0721-tsk2-base-v2
Waiting for inference service rinen0721-tsk2-base-v2 to be ready
Inference service rinen0721-tsk2-base-v2 ready after 191.42443323135376s
Pipeline stage ISVCDeployer completed in 193.56s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.587561845779419s
Received healthy response to inference request in 0.6112287044525146s
Received healthy response to inference request in 0.9363927841186523s
Received healthy response to inference request in 1.0292942523956299s
Received healthy response to inference request in 0.59354567527771s
5 requests
0 failed requests
5th percentile: 0.5970822811126709
10th percentile: 0.6006188869476319
20th percentile: 0.6076920986175537
30th percentile: 0.6762615203857422
40th percentile: 0.8063271522521973
50th percentile: 0.9363927841186523
60th percentile: 0.9735533714294433
70th percentile: 1.0107139587402343
80th percentile: 1.1409477710723879
90th percentile: 1.3642548084259034
95th percentile: 1.475908327102661
99th percentile: 1.5652311420440674
mean time: 0.9516046524047852
Pipeline stage StressChecker completed in 5.89s
rinen0721-tsk2-base_v2 status is now deployed due to DeploymentManager action
rinen0721-tsk2-base_v2 status is now inactive due to auto deactivation removed underperforming models
Deleting key rinen0721-tsk2-test1-v2_reward/tokenizer.json from bucket guanaco-reward-models
rinen0721-tsk2-base_v2 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics