submission_id: cgato-thespice-7b-v0-1_v3
developer_uid: c.gato
status: inactive
model_repo: cgato/TheSpice-7b-v0.1
reward_repo: rirv938/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.8, 'top_p': 0.9, '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}:'}
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}:'}
timestamp: 2024-03-18T01:04:19+00:00
model_name: TheSpicev0_1_2
model_eval_status: success
safety_score: 0.79
entertaining: 7.16
stay_in_character: 8.77
user_preference: 7.58
double_thumbs_up: 1320
thumbs_up: 2047
thumbs_down: 948
num_battles: 112881
num_wins: 59859
win_ratio: 0.5302841044994286
celo_rating: 1179.09
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-thespice-7b-v0-1-v3-mkmlizer
Waiting for job on cgato-thespice-7b-v0-1-v3-mkmlizer to finish
cgato-thespice-7b-v0-1-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-thespice-7b-v0-1-v3-mkmlizer: ║ _____ __ __ ║
cgato-thespice-7b-v0-1-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-thespice-7b-v0-1-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-thespice-7b-v0-1-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-thespice-7b-v0-1-v3-mkmlizer: ║ /___/ ║
cgato-thespice-7b-v0-1-v3-mkmlizer: ║ ║
cgato-thespice-7b-v0-1-v3-mkmlizer: ║ Version: 0.6.11 ║
cgato-thespice-7b-v0-1-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-thespice-7b-v0-1-v3-mkmlizer: ║ ║
cgato-thespice-7b-v0-1-v3-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-thespice-7b-v0-1-v3-mkmlizer: ║ belonging to: ║
cgato-thespice-7b-v0-1-v3-mkmlizer: ║ ║
cgato-thespice-7b-v0-1-v3-mkmlizer: ║ Chai Research Corp. ║
cgato-thespice-7b-v0-1-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-thespice-7b-v0-1-v3-mkmlizer: ║ Expiration: 2024-04-15 23:59:59 ║
cgato-thespice-7b-v0-1-v3-mkmlizer: ║ ║
cgato-thespice-7b-v0-1-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-thespice-7b-v0-1-v3-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 11.9MB/s]
cgato-thespice-7b-v0-1-v3-mkmlizer: README.md: 0%| | 0.00/30.0 [00:00<?, ?B/s] README.md: 100%|██████████| 30.0/30.0 [00:00<00:00, 349kB/s]
cgato-thespice-7b-v0-1-v3-mkmlizer: config.json: 0%| | 0.00/643 [00:00<?, ?B/s] config.json: 100%|██████████| 643/643 [00:00<00:00, 7.53MB/s]
cgato-thespice-7b-v0-1-v3-mkmlizer: generation_config.json: 0%| | 0.00/132 [00:00<?, ?B/s] generation_config.json: 100%|██████████| 132/132 [00:00<00:00, 364kB/s]
cgato-thespice-7b-v0-1-v3-mkmlizer: pytorch_model-00001-of-00003.bin: 0%| | 0.00/4.94G [00:00<?, ?B/s] pytorch_model-00001-of-00003.bin: 0%| | 10.5M/4.94G [00:00<00:51, 96.4MB/s] pytorch_model-00001-of-00003.bin: 1%| | 41.9M/4.94G [00:00<00:24, 199MB/s] pytorch_model-00001-of-00003.bin: 1%|▏ | 62.9M/4.94G [00:00<00:37, 131MB/s] pytorch_model-00001-of-00003.bin: 3%|▎ | 147M/4.94G [00:00<00:14, 324MB/s] pytorch_model-00001-of-00003.bin: 4%|▍ | 189M/4.94G [00:00<00:16, 292MB/s] pytorch_model-00001-of-00003.bin: 5%|▍ | 231M/4.94G [00:00<00:16, 280MB/s] pytorch_model-00001-of-00003.bin: 6%|▌ | 273M/4.94G [00:01<00:15, 311MB/s] pytorch_model-00001-of-00003.bin: 8%|▊ | 409M/4.94G [00:01<00:07, 570MB/s] pytorch_model-00001-of-00003.bin: 14%|█▍ | 703M/4.94G [00:01<00:03, 1.19GB/s] pytorch_model-00001-of-00003.bin: 24%|██▍ | 1.17G/4.94G [00:01<00:01, 2.14GB/s] pytorch_model-00001-of-00003.bin: 29%|██▊ | 1.42G/4.94G [00:01<00:02, 1.72GB/s] pytorch_model-00001-of-00003.bin: 33%|███▎ | 1.63G/4.94G [00:01<00:01, 1.78GB/s] pytorch_model-00001-of-00003.bin: 37%|███▋ | 1.84G/4.94G [00:01<00:02, 1.39GB/s] pytorch_model-00001-of-00003.bin: 42%|████▏ | 2.08G/4.94G [00:01<00:01, 1.59GB/s] pytorch_model-00001-of-00003.bin: 48%|████▊ | 2.38G/4.94G [00:02<00:01, 1.91GB/s] pytorch_model-00001-of-00003.bin: 53%|█████▎ | 2.64G/4.94G [00:02<00:01, 2.04GB/s] pytorch_model-00001-of-00003.bin: 58%|█████▊ | 2.87G/4.94G [00:02<00:01, 1.97GB/s] pytorch_model-00001-of-00003.bin: 66%|██████▋ | 3.28G/4.94G [00:02<00:00, 2.51GB/s] pytorch_model-00001-of-00003.bin: 72%|███████▏ | 3.55G/4.94G [00:02<00:00, 2.17GB/s] pytorch_model-00001-of-00003.bin: 77%|███████▋ | 3.80G/4.94G [00:02<00:00, 2.23GB/s] pytorch_model-00001-of-00003.bin: 82%|████████▏ | 4.04G/4.94G [00:02<00:00, 1.46GB/s] pytorch_model-00001-of-00003.bin: 86%|████████▌ | 4.24G/4.94G [00:03<00:00, 1.30GB/s] pytorch_model-00001-of-00003.bin: 100%|█████████▉| 4.94G/4.94G [00:03<00:00, 1.49GB/s]
cgato-thespice-7b-v0-1-v3-mkmlizer: pytorch_model-00002-of-00003.bin: 0%| | 0.00/5.00G [00:00<?, ?B/s] pytorch_model-00002-of-00003.bin: 0%| | 10.5M/5.00G [00:00<02:32, 32.6MB/s] pytorch_model-00002-of-00003.bin: 2%|▏ | 83.9M/5.00G [00:00<00:20, 242MB/s] pytorch_model-00002-of-00003.bin: 3%|▎ | 168M/5.00G [00:00<00:12, 402MB/s] pytorch_model-00002-of-00003.bin: 5%|▍ | 231M/5.00G [00:00<00:20, 236MB/s] pytorch_model-00002-of-00003.bin: 6%|▌ | 283M/5.00G [00:01<00:16, 285MB/s] pytorch_model-00002-of-00003.bin: 9%|▉ | 440M/5.00G [00:01<00:08, 539MB/s] pytorch_model-00002-of-00003.bin: 20%|█▉ | 975M/5.00G [00:01<00:02, 1.59GB/s] pytorch_model-00002-of-00003.bin: 25%|██▍ | 1.23G/5.00G [00:01<00:02, 1.79GB/s] pytorch_model-00002-of-00003.bin: 29%|██▉ | 1.47G/5.00G [00:01<00:02, 1.75GB/s] pytorch_model-00002-of-00003.bin: 34%|███▍ | 1.69G/5.00G [00:01<00:01, 1.69GB/s] pytorch_model-00002-of-00003.bin: 38%|███▊ | 1.89G/5.00G [00:01<00:02, 1.44GB/s] pytorch_model-00002-of-00003.bin: 42%|████▏ | 2.12G/5.00G [00:01<00:01, 1.62GB/s] pytorch_model-00002-of-00003.bin: 46%|████▌ | 2.31G/5.00G [00:02<00:01, 1.52GB/s] pytorch_model-00002-of-00003.bin: 55%|█████▍ | 2.73G/5.00G [00:02<00:01, 2.10GB/s] pytorch_model-00002-of-00003.bin: 61%|██████ | 3.06G/5.00G [00:02<00:00, 2.38GB/s] pytorch_model-00002-of-00003.bin: 66%|██████▋ | 3.32G/5.00G [00:02<00:00, 2.25GB/s] pytorch_model-00002-of-00003.bin: 71%|███████▏ | 3.57G/5.00G [00:02<00:00, 1.83GB/s] pytorch_model-00002-of-00003.bin: 75%|███████▌ | 3.77G/5.00G [00:02<00:00, 1.51GB/s] pytorch_model-00002-of-00003.bin: 79%|███████▉ | 3.95G/5.00G [00:02<00:00, 1.52GB/s] pytorch_model-00002-of-00003.bin: 84%|████████▍ | 4.19G/5.00G [00:03<00:00, 1.72GB/s] pytorch_model-00002-of-00003.bin: 91%|█████████ | 4.56G/5.00G [00:03<00:00, 2.15GB/s] pytorch_model-00002-of-00003.bin: 100%|█████████▉| 5.00G/5.00G [00:03<00:00, 1.52GB/s]
cgato-thespice-7b-v0-1-v3-mkmlizer: pytorch_model-00003-of-00003.bin: 0%| | 0.00/4.54G [00:00<?, ?B/s] pytorch_model-00003-of-00003.bin: 0%| | 10.5M/4.54G [00:00<02:15, 33.5MB/s] pytorch_model-00003-of-00003.bin: 3%|▎ | 126M/4.54G [00:00<00:12, 353MB/s] pytorch_model-00003-of-00003.bin: 5%|▍ | 210M/4.54G [00:00<00:09, 455MB/s] pytorch_model-00003-of-00003.bin: 6%|▌ | 273M/4.54G [00:00<00:10, 407MB/s] pytorch_model-00003-of-00003.bin: 7%|▋ | 325M/4.54G [00:00<00:10, 389MB/s] pytorch_model-00003-of-00003.bin: 13%|█▎ | 577M/4.54G [00:01<00:04, 891MB/s] pytorch_model-00003-of-00003.bin: 29%|██▉ | 1.33G/4.54G [00:01<00:01, 2.53GB/s] pytorch_model-00003-of-00003.bin: 36%|███▋ | 1.65G/4.54G [00:01<00:01, 2.49GB/s] pytorch_model-00003-of-00003.bin: 43%|████▎ | 1.94G/4.54G [00:01<00:01, 2.16GB/s] pytorch_model-00003-of-00003.bin: 48%|████▊ | 2.19G/4.54G [00:01<00:01, 1.36GB/s] pytorch_model-00003-of-00003.bin: 55%|█████▌ | 2.52G/4.54G [00:01<00:01, 1.67GB/s] pytorch_model-00003-of-00003.bin: 63%|██████▎ | 2.85G/4.54G [00:02<00:00, 1.99GB/s] pytorch_model-00003-of-00003.bin: 72%|███████▏ | 3.25G/4.54G [00:02<00:00, 2.41GB/s] pytorch_model-00003-of-00003.bin: 78%|███████▊ | 3.55G/4.54G [00:02<00:00, 2.33GB/s] pytorch_model-00003-of-00003.bin: 85%|████████▌ | 3.87G/4.54G [00:02<00:00, 2.50GB/s] pytorch_model-00003-of-00003.bin: 92%|█████████▏| 4.16G/4.54G [00:02<00:00, 1.96GB/s] pytorch_model-00003-of-00003.bin: 100%|█████████▉| 4.54G/4.54G [00:02<00:00, 1.69GB/s]
cgato-thespice-7b-v0-1-v3-mkmlizer: pytorch_model.bin.index.json: 0%| | 0.00/23.9k [00:00<?, ?B/s] pytorch_model.bin.index.json: 100%|██████████| 23.9k/23.9k [00:00<00:00, 173MB/s]
cgato-thespice-7b-v0-1-v3-mkmlizer: special_tokens_map.json: 0%| | 0.00/437 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 437/437 [00:00<00:00, 5.52MB/s]
cgato-thespice-7b-v0-1-v3-mkmlizer: tokenizer.model: 0%| | 0.00/493k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 59.8MB/s]
cgato-thespice-7b-v0-1-v3-mkmlizer: tokenizer_config.json: 0%| | 0.00/1.02k [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 1.02k/1.02k [00:00<00:00, 13.7MB/s]
cgato-thespice-7b-v0-1-v3-mkmlizer: Downloaded to shared memory in 10.672s
cgato-thespice-7b-v0-1-v3-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-thespice-7b-v0-1-v3-mkmlizer: Saving mkml model at /dev/shm/model_cache
cgato-thespice-7b-v0-1-v3-mkmlizer: Reading /tmp/tmp0wbgdj9y/pytorch_model.bin.index.json
cgato-thespice-7b-v0-1-v3-mkmlizer: Profiling: 0%| | 0/291 [00:00<?, ?it/s] Profiling: 0%| | 1/291 [00:02<09:54, 2.05s/it] Profiling: 34%|███▎ | 98/291 [00:02<00:04, 42.81it/s] Profiling: 70%|███████ | 204/291 [00:03<00:01, 73.55it/s] Profiling: 100%|██████████| 291/291 [00:04<00:00, 71.35it/s] Profiling: 100%|██████████| 291/291 [00:04<00:00, 58.89it/s]
cgato-thespice-7b-v0-1-v3-mkmlizer: quantized model in 15.322s
cgato-thespice-7b-v0-1-v3-mkmlizer: Processed model cgato/TheSpice-7b-v0.1 in 26.967s
cgato-thespice-7b-v0-1-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-thespice-7b-v0-1-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-thespice-7b-v0-1-v3
cgato-thespice-7b-v0-1-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-thespice-7b-v0-1-v3/config.json
cgato-thespice-7b-v0-1-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-thespice-7b-v0-1-v3/tokenizer_config.json
cgato-thespice-7b-v0-1-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cgato-thespice-7b-v0-1-v3/tokenizer.model
cgato-thespice-7b-v0-1-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-thespice-7b-v0-1-v3/special_tokens_map.json
cgato-thespice-7b-v0-1-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-thespice-7b-v0-1-v3/tokenizer.json
cgato-thespice-7b-v0-1-v3-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/cgato-thespice-7b-v0-1-v3/mkml_model.tensors
cgato-thespice-7b-v0-1-v3-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
cgato-thespice-7b-v0-1-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:1067: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cgato-thespice-7b-v0-1-v3-mkmlizer: warnings.warn(
cgato-thespice-7b-v0-1-v3-mkmlizer: config.json: 0%| | 0.00/1.05k [00:00<?, ?B/s] config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 11.5MB/s]
cgato-thespice-7b-v0-1-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:690: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cgato-thespice-7b-v0-1-v3-mkmlizer: warnings.warn(
cgato-thespice-7b-v0-1-v3-mkmlizer: tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 2.54MB/s]
cgato-thespice-7b-v0-1-v3-mkmlizer: vocab.json: 0%| | 0.00/1.04M [00:00<?, ?B/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 2.87MB/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 2.87MB/s]
cgato-thespice-7b-v0-1-v3-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 34.4MB/s]
cgato-thespice-7b-v0-1-v3-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.
cgato-thespice-7b-v0-1-v3-mkmlizer: warnings.warn(
cgato-thespice-7b-v0-1-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-thespice-7b-v0-1-v3-mkmlizer: Saving duration: 0.269s
cgato-thespice-7b-v0-1-v3-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 5.651s
cgato-thespice-7b-v0-1-v3-mkmlizer: creating bucket guanaco-reward-models
cgato-thespice-7b-v0-1-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-thespice-7b-v0-1-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-thespice-7b-v0-1-v3_reward
cgato-thespice-7b-v0-1-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-thespice-7b-v0-1-v3_reward/special_tokens_map.json
cgato-thespice-7b-v0-1-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-thespice-7b-v0-1-v3_reward/tokenizer_config.json
cgato-thespice-7b-v0-1-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-thespice-7b-v0-1-v3_reward/config.json
cgato-thespice-7b-v0-1-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-thespice-7b-v0-1-v3_reward/merges.txt
cgato-thespice-7b-v0-1-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-thespice-7b-v0-1-v3_reward/vocab.json
cgato-thespice-7b-v0-1-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-thespice-7b-v0-1-v3_reward/tokenizer.json
cgato-thespice-7b-v0-1-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-thespice-7b-v0-1-v3_reward/reward.tensors
Job cgato-thespice-7b-v0-1-v3-mkmlizer completed after 55.8s with status: succeeded
Stopping job with name cgato-thespice-7b-v0-1-v3-mkmlizer
Pipeline stage MKMLizer completed in 60.92s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service cgato-thespice-7b-v0-1-v3
Waiting for inference service cgato-thespice-7b-v0-1-v3 to be ready
Inference service cgato-thespice-7b-v0-1-v3 ready after 40.28894591331482s
Pipeline stage ISVCDeployer completed in 48.31s
Running pipeline stage StressChecker
%s, retrying in %s seconds...
Received healthy response to inference request in 4.89383339881897s
Received healthy response to inference request in 1.1772243976593018s
Received healthy response to inference request in 1.2027690410614014s
Received healthy response to inference request in 1.193882703781128s
Received healthy response to inference request in 1.1836891174316406s
5 requests
0 failed requests
5th percentile: 1.1785173416137695
10th percentile: 1.1798102855682373
20th percentile: 1.1823961734771729
30th percentile: 1.185727834701538
40th percentile: 1.189805269241333
50th percentile: 1.193882703781128
60th percentile: 1.1974372386932373
70th percentile: 1.2009917736053466
80th percentile: 1.9409819126129157
90th percentile: 3.4174076557159427
95th percentile: 4.155620527267455
99th percentile: 4.746190824508667
mean time: 1.9302797317504883
Pipeline stage StressChecker completed in 30.64s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.06s
M-Eval Dataset for topic stay_in_character is loaded
cgato-thespice-7b-v0-1_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics