submission_id: cgato-thespis-swiftdawn-7b_v4
developer_uid: c.gato
status: inactive
model_repo: cgato/Thespis-SwiftDawn-7b
reward_repo: rirv938/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.25, 'top_p': 0.75, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.05, '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: 2024-03-10T23:14:51+00:00
model_name: Thespis-SwiftDawn
model_eval_status: success
safety_score: 0.8
entertaining: 7.0
stay_in_character: 8.54
user_preference: 7.4
double_thumbs_up: 1811
thumbs_up: 2682
thumbs_down: 1211
num_battles: 111482
num_wins: 59179
win_ratio: 0.5308390592203226
celo_rating: 1179.38
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-thespis-swiftdawn-7b-v4-mkmlizer
Waiting for job on cgato-thespis-swiftdawn-7b-v4-mkmlizer to finish
cgato-thespis-swiftdawn-7b-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-thespis-swiftdawn-7b-v4-mkmlizer: ║ _____ __ __ ║
cgato-thespis-swiftdawn-7b-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-thespis-swiftdawn-7b-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-thespis-swiftdawn-7b-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-thespis-swiftdawn-7b-v4-mkmlizer: ║ /___/ ║
cgato-thespis-swiftdawn-7b-v4-mkmlizer: ║ ║
cgato-thespis-swiftdawn-7b-v4-mkmlizer: ║ Version: 0.6.11 ║
cgato-thespis-swiftdawn-7b-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-thespis-swiftdawn-7b-v4-mkmlizer: ║ ║
cgato-thespis-swiftdawn-7b-v4-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-thespis-swiftdawn-7b-v4-mkmlizer: ║ belonging to: ║
cgato-thespis-swiftdawn-7b-v4-mkmlizer: ║ ║
cgato-thespis-swiftdawn-7b-v4-mkmlizer: ║ Chai Research Corp. ║
cgato-thespis-swiftdawn-7b-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-thespis-swiftdawn-7b-v4-mkmlizer: ║ Expiration: 2024-04-15 23:59:59 ║
cgato-thespis-swiftdawn-7b-v4-mkmlizer: ║ ║
cgato-thespis-swiftdawn-7b-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-thespis-swiftdawn-7b-v4-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<01:52, 43.9MB/s] pytorch_model-00001-of-00003.bin: 0%| | 21.0M/4.94G [00:00<01:57, 42.0MB/s] pytorch_model-00001-of-00003.bin: 2%|▏ | 83.9M/4.94G [00:00<00:26, 184MB/s] pytorch_model-00001-of-00003.bin: 4%|▍ | 210M/4.94G [00:00<00:10, 452MB/s] pytorch_model-00001-of-00003.bin: 6%|▌ | 273M/4.94G [00:00<00:10, 440MB/s] pytorch_model-00001-of-00003.bin: 10%|█ | 503M/4.94G [00:00<00:04, 907MB/s] pytorch_model-00001-of-00003.bin: 21%|██ | 1.02G/4.94G [00:01<00:01, 2.01GB/s] pytorch_model-00001-of-00003.bin: 26%|██▌ | 1.27G/4.94G [00:01<00:02, 1.83GB/s] pytorch_model-00001-of-00003.bin: 30%|███ | 1.49G/4.94G [00:01<00:02, 1.28GB/s] pytorch_model-00001-of-00003.bin: 34%|███▎ | 1.67G/4.94G [00:01<00:02, 1.31GB/s] pytorch_model-00001-of-00003.bin: 39%|███▉ | 1.95G/4.94G [00:01<00:01, 1.62GB/s] pytorch_model-00001-of-00003.bin: 48%|████▊ | 2.35G/4.94G [00:01<00:01, 2.14GB/s] pytorch_model-00001-of-00003.bin: 53%|█████▎ | 2.61G/4.94G [00:02<00:01, 2.07GB/s] pytorch_model-00001-of-00003.bin: 58%|█████▊ | 2.85G/4.94G [00:02<00:01, 1.67GB/s] pytorch_model-00001-of-00003.bin: 62%|██████▏ | 3.05G/4.94G [00:02<00:01, 1.60GB/s] pytorch_model-00001-of-00003.bin: 66%|██████▋ | 3.28G/4.94G [00:02<00:00, 1.72GB/s] pytorch_model-00001-of-00003.bin: 73%|███████▎ | 3.62G/4.94G [00:02<00:00, 2.09GB/s] pytorch_model-00001-of-00003.bin: 78%|███████▊ | 3.86G/4.94G [00:02<00:00, 2.11GB/s] pytorch_model-00001-of-00003.bin: 83%|████████▎ | 4.09G/4.94G [00:02<00:00, 1.86GB/s] pytorch_model-00001-of-00003.bin: 87%|████████▋ | 4.32G/4.94G [00:02<00:00, 1.97GB/s] pytorch_model-00001-of-00003.bin: 100%|█████████▉| 4.94G/4.94G [00:03<00:00, 1.61GB/s]
cgato-thespis-swiftdawn-7b-v4-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<05:59, 13.9MB/s] pytorch_model-00002-of-00003.bin: 1%| | 41.9M/5.00G [00:00<01:21, 60.7MB/s] pytorch_model-00002-of-00003.bin: 6%|▌ | 283M/5.00G [00:00<00:09, 472MB/s] pytorch_model-00002-of-00003.bin: 17%|█▋ | 828M/5.00G [00:01<00:02, 1.47GB/s] pytorch_model-00002-of-00003.bin: 22%|██▏ | 1.10G/5.00G [00:01<00:03, 1.28GB/s] pytorch_model-00002-of-00003.bin: 27%|██▋ | 1.33G/5.00G [00:01<00:02, 1.33GB/s] pytorch_model-00002-of-00003.bin: 30%|███ | 1.52G/5.00G [00:01<00:02, 1.29GB/s] pytorch_model-00002-of-00003.bin: 35%|███▌ | 1.75G/5.00G [00:01<00:02, 1.43GB/s] pytorch_model-00002-of-00003.bin: 40%|████ | 2.01G/5.00G [00:01<00:01, 1.69GB/s] pytorch_model-00002-of-00003.bin: 47%|████▋ | 2.34G/5.00G [00:01<00:01, 2.04GB/s] pytorch_model-00002-of-00003.bin: 52%|█████▏ | 2.58G/5.00G [00:02<00:01, 1.90GB/s] pytorch_model-00002-of-00003.bin: 58%|█████▊ | 2.88G/5.00G [00:02<00:00, 2.16GB/s] pytorch_model-00002-of-00003.bin: 62%|██████▏ | 3.12G/5.00G [00:02<00:01, 1.74GB/s] pytorch_model-00002-of-00003.bin: 67%|██████▋ | 3.33G/5.00G [00:02<00:00, 1.80GB/s] pytorch_model-00002-of-00003.bin: 71%|███████ | 3.54G/5.00G [00:02<00:00, 1.59GB/s] pytorch_model-00002-of-00003.bin: 77%|███████▋ | 3.84G/5.00G [00:02<00:00, 1.89GB/s] pytorch_model-00002-of-00003.bin: 83%|████████▎ | 4.14G/5.00G [00:02<00:00, 2.15GB/s] pytorch_model-00002-of-00003.bin: 88%|████████▊ | 4.38G/5.00G [00:03<00:00, 2.18GB/s] pytorch_model-00002-of-00003.bin: 94%|█████████▎| 4.69G/5.00G [00:03<00:00, 2.39GB/s] pytorch_model-00002-of-00003.bin: 100%|█████████▉| 5.00G/5.00G [00:03<00:00, 2.44GB/s] pytorch_model-00002-of-00003.bin: 100%|█████████▉| 5.00G/5.00G [00:03<00:00, 1.51GB/s]
cgato-thespis-swiftdawn-7b-v4-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<02:39, 28.4MB/s] pytorch_model-00003-of-00003.bin: 1%| | 31.5M/4.54G [00:00<01:06, 67.6MB/s] pytorch_model-00003-of-00003.bin: 2%|▏ | 83.9M/4.54G [00:00<00:30, 146MB/s] pytorch_model-00003-of-00003.bin: 3%|▎ | 126M/4.54G [00:00<00:21, 206MB/s] pytorch_model-00003-of-00003.bin: 20%|█▉ | 891M/4.54G [00:00<00:01, 1.91GB/s] pytorch_model-00003-of-00003.bin: 25%|██▌ | 1.14G/4.54G [00:01<00:01, 1.87GB/s] pytorch_model-00003-of-00003.bin: 30%|███ | 1.37G/4.54G [00:01<00:01, 1.66GB/s] pytorch_model-00003-of-00003.bin: 35%|███▍ | 1.57G/4.54G [00:01<00:02, 1.18GB/s] pytorch_model-00003-of-00003.bin: 43%|████▎ | 1.97G/4.54G [00:01<00:01, 1.68GB/s] pytorch_model-00003-of-00003.bin: 50%|█████ | 2.28G/4.54G [00:01<00:01, 1.93GB/s] pytorch_model-00003-of-00003.bin: 56%|█████▌ | 2.53G/4.54G [00:02<00:01, 1.63GB/s] pytorch_model-00003-of-00003.bin: 60%|██████ | 2.74G/4.54G [00:02<00:01, 1.40GB/s] pytorch_model-00003-of-00003.bin: 65%|██████▍ | 2.95G/4.54G [00:02<00:01, 1.53GB/s] pytorch_model-00003-of-00003.bin: 73%|███████▎ | 3.33G/4.54G [00:02<00:00, 2.03GB/s] pytorch_model-00003-of-00003.bin: 79%|███████▉ | 3.60G/4.54G [00:02<00:00, 2.05GB/s] pytorch_model-00003-of-00003.bin: 85%|████████▍ | 3.84G/4.54G [00:02<00:00, 2.03GB/s] pytorch_model-00003-of-00003.bin: 90%|████████▉ | 4.07G/4.54G [00:02<00:00, 1.97GB/s] pytorch_model-00003-of-00003.bin: 100%|█████████▉| 4.54G/4.54G [00:03<00:00, 1.64GB/s] pytorch_model-00003-of-00003.bin: 100%|█████████▉| 4.54G/4.54G [00:03<00:00, 1.42GB/s]
cgato-thespis-swiftdawn-7b-v4-mkmlizer: Profiling: 0%| | 0/291 [00:00<?, ?it/s] Profiling: 0%| | 1/291 [00:03<17:47, 3.68s/it] Profiling: 34%|███▎ | 98/291 [00:04<00:07, 27.07it/s] Profiling: 70%|███████ | 204/291 [00:06<00:02, 42.59it/s] Profiling: 100%|██████████| 291/291 [00:07<00:00, 49.64it/s] Profiling: 100%|██████████| 291/291 [00:07<00:00, 38.15it/s]
cgato-thespis-swiftdawn-7b-v4-mkmlizer: quantized model in 18.236s
cgato-thespis-swiftdawn-7b-v4-mkmlizer: Processed model cgato/Thespis-SwiftDawn-7b in 30.576s
cgato-thespis-swiftdawn-7b-v4-mkmlizer: creating bucket guanaco-mkml-models
cgato-thespis-swiftdawn-7b-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-thespis-swiftdawn-7b-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-thespis-swiftdawn-7b-v4
cgato-thespis-swiftdawn-7b-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-thespis-swiftdawn-7b-v4/special_tokens_map.json
cgato-thespis-swiftdawn-7b-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-thespis-swiftdawn-7b-v4/config.json
cgato-thespis-swiftdawn-7b-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-thespis-swiftdawn-7b-v4/tokenizer_config.json
cgato-thespis-swiftdawn-7b-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cgato-thespis-swiftdawn-7b-v4/tokenizer.model
cgato-thespis-swiftdawn-7b-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-thespis-swiftdawn-7b-v4/tokenizer.json
cgato-thespis-swiftdawn-7b-v4-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/cgato-thespis-swiftdawn-7b-v4/mkml_model.tensors
cgato-thespis-swiftdawn-7b-v4-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
cgato-thespis-swiftdawn-7b-v4-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-thespis-swiftdawn-7b-v4-mkmlizer: warnings.warn(
cgato-thespis-swiftdawn-7b-v4-mkmlizer: config.json: 0%| | 0.00/1.05k [00:00<?, ?B/s] config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 11.2MB/s]
cgato-thespis-swiftdawn-7b-v4-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-thespis-swiftdawn-7b-v4-mkmlizer: warnings.warn(
cgato-thespis-swiftdawn-7b-v4-mkmlizer: tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 3.10MB/s]
cgato-thespis-swiftdawn-7b-v4-mkmlizer: vocab.json: 0%| | 0.00/1.04M [00:00<?, ?B/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 33.9MB/s]
cgato-thespis-swiftdawn-7b-v4-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 28.0MB/s]
cgato-thespis-swiftdawn-7b-v4-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-thespis-swiftdawn-7b-v4-mkmlizer: warnings.warn(
cgato-thespis-swiftdawn-7b-v4-mkmlizer: pytorch_model.bin: 0%| | 0.00/1.44G [00:00<?, ?B/s] pytorch_model.bin: 1%| | 10.5M/1.44G [00:00<01:00, 23.6MB/s] pytorch_model.bin: 19%|█▉ | 273M/1.44G [00:00<00:02, 520MB/s] pytorch_model.bin: 25%|██▍ | 357M/1.44G [00:00<00:02, 424MB/s] pytorch_model.bin: 29%|██▉ | 419M/1.44G [00:01<00:02, 393MB/s] pytorch_model.bin: 46%|████▌ | 658M/1.44G [00:01<00:01, 735MB/s] pytorch_model.bin: 53%|█████▎ | 763M/1.44G [00:02<00:02, 269MB/s] pytorch_model.bin: 58%|█████▊ | 836M/1.44G [00:02<00:02, 299MB/s] pytorch_model.bin: 72%|███████▏ | 1.05G/1.44G [00:02<00:00, 494MB/s] pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:02<00:00, 544MB/s]
cgato-thespis-swiftdawn-7b-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-thespis-swiftdawn-7b-v4-mkmlizer: Saving duration: 0.234s
cgato-thespis-swiftdawn-7b-v4-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 5.992s
cgato-thespis-swiftdawn-7b-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-thespis-swiftdawn-7b-v4_reward/reward.tensors
Job cgato-thespis-swiftdawn-7b-v4-mkmlizer completed after 75.18s with status: succeeded
Stopping job with name cgato-thespis-swiftdawn-7b-v4-mkmlizer
Pipeline stage MKMLizer completed in 78.61s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cgato-thespis-swiftdawn-7b-v4
Waiting for inference service cgato-thespis-swiftdawn-7b-v4 to be ready
Inference service cgato-thespis-swiftdawn-7b-v4 ready after 40.282182931900024s
Pipeline stage ISVCDeployer completed in 47.17s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7315475940704346s
Received healthy response to inference request in 1.189197063446045s
Received healthy response to inference request in 1.1876578330993652s
Received healthy response to inference request in 1.1917839050292969s
Received healthy response to inference request in 1.1986091136932373s
5 requests
0 failed requests
5th percentile: 1.1879656791687012
10th percentile: 1.1882735252380372
20th percentile: 1.188889217376709
30th percentile: 1.1897144317626953
40th percentile: 1.190749168395996
50th percentile: 1.1917839050292969
60th percentile: 1.194513988494873
70th percentile: 1.1972440719604491
80th percentile: 1.3051968097686768
90th percentile: 1.5183722019195558
95th percentile: 1.624959897994995
99th percentile: 1.7102300548553466
mean time: 1.2997591018676757
Pipeline stage StressChecker completed in 7.23s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.05s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.04s
M-Eval Dataset for topic stay_in_character is loaded
cgato-thespis-swiftdawn-7b_v4 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics