submission_id: grimjim-kuno-kunoichi-v1-dpo-_v1
developer_uid: chaiwill
status: torndown
model_repo: grimjim/kuno-kunoichi-v1-DPO-v2-SLERP-7B
reward_repo: rirv938/reward_gpt2_medium_preference_24m_e2
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': 16, 'max_output_tokens': 64}
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}
reward_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}
timestamp: 2024-03-13T23:40:55+00:00
model_name: grimjim-kuno-kunoichi-v1-dpo-_v1
model_eval_status: success
model_group: grimjim/kuno-kunoichi-v1
num_battles: 101953
num_wins: 53813
celo_rating: 1176.47
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: None
model_num_parameters: 7241732096.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: grimjim-kuno-kunoichi-v1-dpo-_v1
ineligible_reason: propriety_total_count < 800
language_model: grimjim/kuno-kunoichi-v1-DPO-v2-SLERP-7B
model_size: 7B
reward_model: rirv938/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-03-13
win_ratio: 0.5278216433062294
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer
Waiting for job on grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer to finish
Stopping job with name grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer
Waiting for job on grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer to finish
grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer: 
model-00001-of-00002.safetensors:   0%|          | 0.00/9.94G [00:00<?, ?B/s]
model-00001-of-00002.safetensors:   0%|          | 10.5M/9.94G [00:06<1:42:26, 1.62MB/s]
model-00001-of-00002.safetensors:   0%|          | 21.0M/9.94G [00:07<47:54, 3.45MB/s]  
model-00001-of-00002.safetensors:   0%|          | 31.5M/9.94G [00:07<30:34, 5.40MB/s]
model-00001-of-00002.safetensors:   0%|          | 41.9M/9.94G [00:07<19:12, 8.59MB/s]
model-00001-of-00002.safetensors:   1%|          | 83.9M/9.94G [00:07<06:12, 26.4MB/s]
model-00001-of-00002.safetensors:   1%|          | 115M/9.94G [00:08<03:51, 42.4MB/s] 
model-00001-of-00002.safetensors:   2%|▏         | 220M/9.94G [00:08<01:23, 117MB/s] 
model-00001-of-00002.safetensors:   3%|▎         | 262M/9.94G [00:08<01:14, 131MB/s]
model-00001-of-00002.safetensors:   3%|▎         | 325M/9.94G [00:08<00:52, 182MB/s]
model-00001-of-00002.safetensors:   4%|▎         | 367M/9.94G [00:08<00:47, 203MB/s]
model-00001-of-00002.safetensors:   4%|▍         | 440M/9.94G [00:08<00:33, 280MB/s]
model-00001-of-00002.safetensors:   7%|▋         | 713M/9.94G [00:08<00:12, 713MB/s]
model-00001-of-00002.safetensors:  11%|█         | 1.05G/9.94G [00:09<00:07, 1.23GB/s]
model-00001-of-00002.safetensors:  14%|█▎        | 1.35G/9.94G [00:09<00:05, 1.63GB/s]
model-00001-of-00002.safetensors:  16%|█▌        | 1.57G/9.94G [00:09<00:12, 684MB/s] 
model-00001-of-00002.safetensors:  18%|█▊        | 1.74G/9.94G [00:10<00:11, 692MB/s]
model-00001-of-00002.safetensors:  19%|█▉        | 1.88G/9.94G [00:10<00:10, 734MB/s]
model-00001-of-00002.safetensors:  20%|██        | 2.00G/9.94G [00:10<00:09, 796MB/s]
model-00001-of-00002.safetensors:  21%|██▏       | 2.13G/9.94G [00:10<00:09, 792MB/s]
model-00001-of-00002.safetensors:  25%|██▍       | 2.46G/9.94G [00:10<00:06, 1.22GB/s]
model-00001-of-00002.safetensors:  26%|██▋       | 2.63G/9.94G [00:11<00:09, 812MB/s] 
model-00001-of-00002.safetensors:  28%|██▊       | 2.77G/9.94G [00:11<00:09, 719MB/s]
model-00001-of-00002.safetensors:  29%|██▉       | 2.87G/9.94G [00:11<00:09, 748MB/s]
model-00001-of-00002.safetensors:  30%|██▉       | 2.98G/9.94G [00:11<00:09, 755MB/s]
model-00001-of-00002.safetensors:  31%|███       | 3.07G/9.94G [00:11<00:08, 781MB/s]
model-00001-of-00002.safetensors:  32%|███▏      | 3.22G/9.94G [00:11<00:07, 907MB/s]
model-00001-of-00002.safetensors:  33%|███▎      | 3.32G/9.94G [00:11<00:07, 893MB/s]
model-00001-of-00002.safetensors:  36%|███▌      | 3.57G/9.94G [00:12<00:05, 1.22GB/s]
model-00001-of-00002.safetensors:  37%|███▋      | 3.70G/9.94G [00:12<00:06, 899MB/s] 
model-00001-of-00002.safetensors:  38%|███▊      | 3.82G/9.94G [00:12<00:09, 636MB/s]
model-00001-of-00002.safetensors:  39%|███▉      | 3.92G/9.94G [00:12<00:08, 693MB/s]
model-00001-of-00002.safetensors:  40%|████      | 4.02G/9.94G [00:12<00:08, 696MB/s]
model-00001-of-00002.safetensors:  41%|████▏     | 4.12G/9.94G [00:12<00:07, 754MB/s]
model-00001-of-00002.safetensors:  43%|████▎     | 4.24G/9.94G [00:13<00:06, 820MB/s]
model-00001-of-00002.safetensors:  44%|████▎     | 4.34G/9.94G [00:13<00:06, 837MB/s]
model-00001-of-00002.safetensors:  45%|████▌     | 4.48G/9.94G [00:13<00:05, 933MB/s]
model-00001-of-00002.safetensors:  47%|████▋     | 4.68G/9.94G [00:13<00:04, 1.20GB/s]
model-00001-of-00002.safetensors:  48%|████▊     | 4.81G/9.94G [00:13<00:04, 1.11GB/s]
model-00001-of-00002.safetensors:  50%|████▉     | 4.94G/9.94G [00:13<00:05, 846MB/s] 
model-00001-of-00002.safetensors:  51%|█████     | 5.04G/9.94G [00:13<00:05, 817MB/s]
model-00001-of-00002.safetensors:  52%|█████▏    | 5.15G/9.94G [00:14<00:05, 862MB/s]
model-00001-of-00002.safetensors:  53%|█████▎    | 5.25G/9.94G [00:14<00:05, 799MB/s]
model-00001-of-00002.safetensors:  54%|█████▍    | 5.35G/9.94G [00:14<00:05, 774MB/s]
model-00001-of-00002.safetensors:  55%|█████▍    | 5.43G/9.94G [00:14<00:06, 719MB/s]
model-00001-of-00002.safetensors:  56%|█████▌    | 5.56G/9.94G [00:14<00:05, 841MB/s]
model-00001-of-00002.safetensors:  57%|█████▋    | 5.66G/9.94G [00:14<00:04, 858MB/s]
model-00001-of-00002.safetensors:  59%|█████▉    | 5.90G/9.94G [00:14<00:03, 1.18GB/s]
model-00001-of-00002.safetensors:  61%|██████    | 6.03G/9.94G [00:15<00:04, 953MB/s] 
model-00001-of-00002.safetensors:  62%|██████▏   | 6.18G/9.94G [00:15<00:03, 1.04GB/s]
model-00001-of-00002.safetensors:  63%|██████▎   | 6.29G/9.94G [00:15<00:04, 883MB/s] 
model-00001-of-00002.safetensors:  64%|██████▍   | 6.40G/9.94G [00:15<00:04, 751MB/s]
model-00001-of-00002.safetensors:  65%|██████▌   | 6.48G/9.94G [00:15<00:04, 704MB/s]
model-00001-of-00002.safetensors:  66%|██████▌   | 6.57G/9.94G [00:15<00:04, 727MB/s]
model-00001-of-00002.safetensors:  67%|██████▋   | 6.68G/9.94G [00:15<00:04, 787MB/s]
model-00001-of-00002.safetensors:  69%|██████▉   | 6.84G/9.94G [00:16<00:03, 967MB/s]
model-00001-of-00002.safetensors:  70%|██████▉   | 6.94G/9.94G [00:16<00:03, 948MB/s]
model-00001-of-00002.safetensors:  71%|███████   | 7.05G/9.94G [00:16<00:03, 916MB/s]
model-00001-of-00002.safetensors:  72%|███████▏  | 7.18G/9.94G [00:16<00:02, 1.00GB/s]
model-00001-of-00002.safetensors:  74%|███████▎  | 7.31G/9.94G [00:16<00:02, 1.07GB/s]
model-00001-of-00002.safetensors:  75%|███████▍  | 7.43G/9.94G [00:16<00:02, 1.12GB/s]
model-00001-of-00002.safetensors:  76%|███████▌  | 7.55G/9.94G [00:16<00:03, 757MB/s] 
model-00001-of-00002.safetensors:  77%|███████▋  | 7.67G/9.94G [00:16<00:02, 839MB/s]
model-00001-of-00002.safetensors:  78%|███████▊  | 7.77G/9.94G [00:17<00:02, 863MB/s]
model-00001-of-00002.safetensors:  79%|███████▉  | 7.87G/9.94G [00:17<00:02, 882MB/s]
model-00001-of-00002.safetensors:  80%|████████  | 7.99G/9.94G [00:17<00:02, 949MB/s]
model-00001-of-00002.safetensors:  82%|████████▏ | 8.14G/9.94G [00:17<00:01, 1.07GB/s]
model-00001-of-00002.safetensors:  83%|████████▎ | 8.25G/9.94G [00:17<00:01, 978MB/s] 
model-00001-of-00002.safetensors:  84%|████████▍ | 8.38G/9.94G [00:17<00:01, 1.04GB/s]
model-00001-of-00002.safetensors:  87%|████████▋ | 8.65G/9.94G [00:17<00:00, 1.36GB/s]
model-00001-of-00002.safetensors:  88%|████████▊ | 8.79G/9.94G [00:17<00:01, 1.07GB/s]
model-00001-of-00002.safetensors:  90%|████████▉ | 8.90G/9.94G [00:18<00:01, 910MB/s] 
model-00001-of-00002.safetensors:  91%|█████████ | 9.01G/9.94G [00:18<00:01, 893MB/s]
model-00001-of-00002.safetensors:  92%|█████████▏| 9.11G/9.94G [00:18<00:01, 787MB/s]
model-00001-of-00002.safetensors:  92%|█████████▏| 9.20G/9.94G [00:18<00:00, 759MB/s]
model-00001-of-00002.safetensors:  93%|█████████▎| 9.28G/9.94G [00:18<00:00, 733MB/s]
model-00001-of-00002.safetensors:  94%|█████████▍| 9.38G/9.94G [00:18<00:00, 751MB/s]
model-00001-of-00002.safetensors:  95%|█████████▌| 9.46G/9.94G [00:18<00:00, 703MB/s]
model-00001-of-00002.safetensors:  97%|█████████▋| 9.62G/9.94G [00:19<00:00, 907MB/s]
model-00001-of-00002.safetensors: 100%|█████████▉| 9.94G/9.94G [00:19<00:00, 517MB/s]
grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer: 
tokenizer.json:   0%|          | 0.00/1.80M [00:00<?, ?B/s]
tokenizer.json: 100%|██████████| 1.80M/1.80M [00:00<00:00, 43.5MB/s]
grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer: 
tokenizer.model:   0%|          | 0.00/493k [00:00<?, ?B/s]
tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 39.7MB/s]
grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer: 
tokenizer_config.json:   0%|          | 0.00/967 [00:00<?, ?B/s]
tokenizer_config.json: 100%|██████████| 967/967 [00:00<00:00, 11.8MB/s]
grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer: Downloaded to shared memory in 25.893s
grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer: quantizing model to /dev/shm/model_cache
grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer: Saving mkml model at /dev/shm/model_cache
grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer: Reading /tmp/tmpvd2u9i1d/model.safetensors.index.json
grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer: 
Profiling:   0%|          | 0/291 [00:00<?, ?it/s]
Profiling:   0%|          | 1/291 [00:02<12:19,  2.55s/it]
Profiling:   4%|▍         | 12/291 [00:02<00:45,  6.15it/s]
Profiling:   8%|▊         | 22/291 [00:02<00:21, 12.63it/s]
Profiling:  11%|█         | 32/291 [00:02<00:12, 20.44it/s]
Profiling:  15%|█▌        | 45/291 [00:02<00:07, 32.85it/s]
Profiling:  20%|█▉        | 57/291 [00:03<00:05, 44.62it/s]
Profiling:  23%|██▎       | 68/291 [00:03<00:04, 52.90it/s]
Profiling:  28%|██▊       | 81/291 [00:03<00:03, 66.85it/s]
Profiling:  32%|███▏      | 93/291 [00:03<00:02, 76.13it/s]
Profiling:  36%|███▌      | 104/291 [00:03<00:02, 78.22it/s]
Profiling:  40%|████      | 117/291 [00:03<00:01, 89.91it/s]
Profiling:  44%|████▍     | 129/291 [00:03<00:01, 95.29it/s]
Profiling:  49%|████▉     | 142/291 [00:03<00:01, 103.43it/s]
Profiling:  53%|█████▎    | 154/291 [00:04<00:01, 99.59it/s] 
Profiling:  57%|█████▋    | 166/291 [00:04<00:01, 104.64it/s]
Profiling:  61%|██████    | 178/291 [00:04<00:01, 106.66it/s]
Profiling:  65%|██████▌   | 190/291 [00:04<00:00, 105.13it/s]
Profiling:  70%|██████▉   | 203/291 [00:04<00:00, 111.87it/s]
Profiling:  74%|███████▍  | 215/291 [00:07<00:05, 13.94it/s] 
Profiling:  79%|███████▉  | 230/291 [00:07<00:03, 20.18it/s]
Profiling:  85%|████████▍ | 247/291 [00:07<00:01, 29.47it/s]
Profiling:  90%|█████████ | 262/291 [00:07<00:00, 39.28it/s]
Profiling:  95%|█████████▍| 276/291 [00:07<00:00, 49.14it/s]
Profiling: 100%|██████████| 291/291 [00:07<00:00, 37.12it/s]
grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer: quantized model in 22.345s
grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer: Processed model grimjim/kuno-kunoichi-v1-DPO-v2-SLERP-7B in 49.650s
grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer: creating bucket guanaco-mkml-models
grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/grimjim-kuno-kunoichi-v1-dpo-v1
grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/grimjim-kuno-kunoichi-v1-dpo-v1/special_tokens_map.json
grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/grimjim-kuno-kunoichi-v1-dpo-v1/tokenizer_config.json
grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/grimjim-kuno-kunoichi-v1-dpo-v1/tokenizer.model
grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/grimjim-kuno-kunoichi-v1-dpo-v1/tokenizer.json
grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/grimjim-kuno-kunoichi-v1-dpo-v1/config.json
grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/grimjim-kuno-kunoichi-v1-dpo-v1/mkml_model.tensors
grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer: 
vocab.json:   0%|          | 0.00/1.04M [00:00<?, ?B/s]
vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 4.12MB/s]
vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 4.11MB/s]
grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer: 
tokenizer.json:   0%|          | 0.00/2.11M [00:00<?, ?B/s]
tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 9.44MB/s]
tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 9.41MB/s]
grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:472: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer:   warnings.warn(
grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer: 
pytorch_model.bin:   0%|          | 0.00/1.44G [00:00<?, ?B/s]
pytorch_model.bin:   1%|          | 10.5M/1.44G [00:00<00:55, 25.8MB/s]
pytorch_model.bin:   2%|▏         | 31.5M/1.44G [00:00<00:19, 71.7MB/s]
pytorch_model.bin:   7%|▋         | 94.4M/1.44G [00:00<00:08, 163MB/s] 
pytorch_model.bin:   9%|▊         | 126M/1.44G [00:00<00:06, 192MB/s] 
pytorch_model.bin:  28%|██▊       | 409M/1.44G [00:00<00:01, 810MB/s]
pytorch_model.bin:  43%|████▎     | 619M/1.44G [00:01<00:00, 1.12GB/s]
pytorch_model.bin:  54%|█████▎    | 773M/1.44G [00:02<00:01, 376MB/s] 
pytorch_model.bin:  61%|██████    | 878M/1.44G [00:02<00:01, 314MB/s]
pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:02<00:00, 543MB/s]
grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer: Saving duration: 0.379s
grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 8.310s
grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer: creating bucket guanaco-reward-models
grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/grimjim-kuno-kunoichi-v1-dpo-v1_reward
grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/grimjim-kuno-kunoichi-v1-dpo-v1_reward/special_tokens_map.json
grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/grimjim-kuno-kunoichi-v1-dpo-v1_reward/config.json
grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/grimjim-kuno-kunoichi-v1-dpo-v1_reward/vocab.json
grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/grimjim-kuno-kunoichi-v1-dpo-v1_reward/merges.txt
grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/grimjim-kuno-kunoichi-v1-dpo-v1_reward/tokenizer_config.json
grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/grimjim-kuno-kunoichi-v1-dpo-v1_reward/tokenizer.json
grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/grimjim-kuno-kunoichi-v1-dpo-v1_reward/reward.tensors
Job grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer completed after 92.56s with status: succeeded
Stopping job with name grimjim-kuno-kunoichi-v1-dpo-v1-mkmlizer
Pipeline stage MKMLizer completed in 109.23s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.18s
Running pipeline stage ISVCDeployer
Creating inference service grimjim-kuno-kunoichi-v1-dpo-v1
Waiting for inference service grimjim-kuno-kunoichi-v1-dpo-v1 to be ready
Inference service grimjim-kuno-kunoichi-v1-dpo-v1 ready after 141.03918361663818s
Pipeline stage ISVCDeployer completed in 153.58s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.5635864734649658s
Received healthy response to inference request in 1.162369728088379s
Received healthy response to inference request in 1.1608970165252686s
Received healthy response to inference request in 1.1571528911590576s
Received healthy response to inference request in 1.181896686553955s
5 requests
0 failed requests
5th percentile: 1.1579017162322998
10th percentile: 1.158650541305542
20th percentile: 1.1601481914520264
30th percentile: 1.1611915588378907
40th percentile: 1.1617806434631348
50th percentile: 1.162369728088379
60th percentile: 1.1701805114746093
70th percentile: 1.1779912948608398
80th percentile: 1.2582346439361574
90th percentile: 1.4109105587005615
95th percentile: 1.4872485160827635
99th percentile: 1.5483188819885254
mean time: 1.2451805591583252
Pipeline stage StressChecker completed in 6.97s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.04s
Running M-Eval for topic stay_in_character
M-Eval Dataset for topic stay_in_character is loaded
grimjim-kuno-kunoichi-v1-dpo-_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of grimjim-kuno-kunoichi-v1-dpo-_v1
Running pipeline stage ISVCDeleter
Checking if service grimjim-kuno-kunoichi-v1-dpo-v1 is running
Tearing down inference service grimjim-kuno-kunoichi-v1-dpo-v1
Toredown service grimjim-kuno-kunoichi-v1-dpo-v1
Pipeline stage ISVCDeleter completed in 6.04s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key grimjim-kuno-kunoichi-v1-dpo-v1/config.json from bucket guanaco-mkml-models
Deleting key grimjim-kuno-kunoichi-v1-dpo-v1/mkml_model.tensors from bucket guanaco-mkml-models
Deleting key grimjim-kuno-kunoichi-v1-dpo-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key grimjim-kuno-kunoichi-v1-dpo-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key grimjim-kuno-kunoichi-v1-dpo-v1/tokenizer.model from bucket guanaco-mkml-models
Deleting key grimjim-kuno-kunoichi-v1-dpo-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key grimjim-kuno-kunoichi-v1-dpo-v1_reward/config.json from bucket guanaco-reward-models
Deleting key grimjim-kuno-kunoichi-v1-dpo-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key grimjim-kuno-kunoichi-v1-dpo-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key grimjim-kuno-kunoichi-v1-dpo-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key grimjim-kuno-kunoichi-v1-dpo-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key grimjim-kuno-kunoichi-v1-dpo-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key grimjim-kuno-kunoichi-v1-dpo-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.44s
grimjim-kuno-kunoichi-v1-dpo-_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics