submission_id: mistralai-mistral-7b-ins_6151_v4
developer_uid: azuruce
status: inactive
model_repo: mistralai/Mistral-7B-Instruct-v0.2
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'top_k': 50, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 4, '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: 2024-03-29T05:07:21+00:00
model_name: albert-baseline-bo1
model_eval_status: success
safety_score: 0.98
entertaining: 6.94
stay_in_character: 8.27
user_preference: 7.32
double_thumbs_up: 224
thumbs_up: 311
thumbs_down: 185
num_battles: 46013
num_wins: 20453
win_ratio: 0.44450481385695345
celo_rating: 1118.61
Resubmit model
Running pipeline stage MKMLizer
Starting job with name mistralai-mistral-7b-ins-6151-v4-mkmlizer
Waiting for job on mistralai-mistral-7b-ins-6151-v4-mkmlizer to finish
mistralai-mistral-7b-ins-6151-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mistralai-mistral-7b-ins-6151-v4-mkmlizer: ║ _____ __ __ ║
mistralai-mistral-7b-ins-6151-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
mistralai-mistral-7b-ins-6151-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
mistralai-mistral-7b-ins-6151-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
mistralai-mistral-7b-ins-6151-v4-mkmlizer: ║ /___/ ║
mistralai-mistral-7b-ins-6151-v4-mkmlizer: ║ ║
mistralai-mistral-7b-ins-6151-v4-mkmlizer: ║ Version: 0.6.11 ║
mistralai-mistral-7b-ins-6151-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
mistralai-mistral-7b-ins-6151-v4-mkmlizer: ║ ║
mistralai-mistral-7b-ins-6151-v4-mkmlizer: ║ The license key for the current software has been verified as ║
mistralai-mistral-7b-ins-6151-v4-mkmlizer: ║ belonging to: ║
mistralai-mistral-7b-ins-6151-v4-mkmlizer: ║ ║
mistralai-mistral-7b-ins-6151-v4-mkmlizer: ║ Chai Research Corp. ║
mistralai-mistral-7b-ins-6151-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
mistralai-mistral-7b-ins-6151-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
mistralai-mistral-7b-ins-6151-v4-mkmlizer: ║ ║
mistralai-mistral-7b-ins-6151-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
mistralai-mistral-7b-ins-6151-v4-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 14.0MB/s]
mistralai-mistral-7b-ins-6151-v4-mkmlizer: README.md: 0%| | 0.00/3.79k [00:00<?, ?B/s] README.md: 100%|██████████| 3.79k/3.79k [00:00<00:00, 42.2MB/s]
mistralai-mistral-7b-ins-6151-v4-mkmlizer: config.json: 0%| | 0.00/596 [00:00<?, ?B/s] config.json: 100%|██████████| 596/596 [00:00<00:00, 6.01MB/s]
mistralai-mistral-7b-ins-6151-v4-mkmlizer: generation_config.json: 0%| | 0.00/111 [00:00<?, ?B/s] generation_config.json: 100%|██████████| 111/111 [00:00<00:00, 1.51MB/s]
mistralai-mistral-7b-ins-6151-v4-mkmlizer: model-00001-of-00003.safetensors: 0%| | 0.00/4.94G [00:00<?, ?B/s] model-00001-of-00003.safetensors: 0%| | 10.5M/4.94G [00:00<00:53, 91.6MB/s] model-00001-of-00003.safetensors: 1%| | 31.5M/4.94G [00:00<00:34, 143MB/s] model-00001-of-00003.safetensors: 3%|▎ | 136M/4.94G [00:00<00:10, 470MB/s] model-00001-of-00003.safetensors: 4%|▍ | 189M/4.94G [00:00<00:12, 367MB/s] model-00001-of-00003.safetensors: 7%|▋ | 346M/4.94G [00:00<00:06, 674MB/s] model-00001-of-00003.safetensors: 10%|█ | 503M/4.94G [00:00<00:04, 914MB/s] model-00001-of-00003.safetensors: 19%|█▉ | 933M/4.94G [00:00<00:02, 1.84GB/s] model-00001-of-00003.safetensors: 23%|██▎ | 1.15G/4.94G [00:00<00:01, 1.93GB/s] model-00001-of-00003.safetensors: 28%|██▊ | 1.36G/4.94G [00:01<00:02, 1.67GB/s] model-00001-of-00003.safetensors: 31%|███▏ | 1.55G/4.94G [00:01<00:02, 1.55GB/s] model-00001-of-00003.safetensors: 36%|███▌ | 1.76G/4.94G [00:01<00:01, 1.68GB/s] model-00001-of-00003.safetensors: 42%|████▏ | 2.06G/4.94G [00:01<00:01, 1.95GB/s] model-00001-of-00003.safetensors: 47%|████▋ | 2.32G/4.94G [00:01<00:01, 2.13GB/s] model-00001-of-00003.safetensors: 52%|█████▏ | 2.55G/4.94G [00:01<00:01, 2.06GB/s] model-00001-of-00003.safetensors: 56%|█████▌ | 2.77G/4.94G [00:01<00:01, 1.84GB/s] model-00001-of-00003.safetensors: 60%|██████ | 2.99G/4.94G [00:01<00:01, 1.89GB/s] model-00001-of-00003.safetensors: 64%|██████▍ | 3.19G/4.94G [00:02<00:00, 1.90GB/s] model-00001-of-00003.safetensors: 70%|██████▉ | 3.44G/4.94G [00:02<00:00, 2.02GB/s] model-00001-of-00003.safetensors: 74%|███████▍ | 3.65G/4.94G [00:02<00:00, 1.98GB/s] model-00001-of-00003.safetensors: 78%|███████▊ | 3.86G/4.94G [00:02<00:00, 1.84GB/s] model-00001-of-00003.safetensors: 84%|████████▍ | 4.17G/4.94G [00:02<00:00, 2.15GB/s] model-00001-of-00003.safetensors: 94%|█████████▍| 4.66G/4.94G [00:02<00:00, 2.85GB/s] model-00001-of-00003.safetensors: 100%|█████████▉| 4.94G/4.94G [00:02<00:00, 1.83GB/s]
mistralai-mistral-7b-ins-6151-v4-mkmlizer: model-00002-of-00003.safetensors: 0%| | 0.00/5.00G [00:00<?, ?B/s] model-00002-of-00003.safetensors: 0%| | 10.5M/5.00G [00:00<02:12, 37.6MB/s] model-00002-of-00003.safetensors: 0%| | 21.0M/5.00G [00:00<01:53, 43.9MB/s] model-00002-of-00003.safetensors: 1%|▏ | 62.9M/5.00G [00:00<00:50, 97.6MB/s] model-00002-of-00003.safetensors: 2%|▏ | 83.9M/5.00G [00:00<00:42, 116MB/s] model-00002-of-00003.safetensors: 5%|▌ | 252M/5.00G [00:00<00:10, 456MB/s] model-00002-of-00003.safetensors: 22%|██▏ | 1.12G/5.00G [00:01<00:01, 2.37GB/s] model-00002-of-00003.safetensors: 29%|██▉ | 1.45G/5.00G [00:01<00:02, 1.60GB/s] model-00002-of-00003.safetensors: 34%|███▍ | 1.70G/5.00G [00:01<00:02, 1.14GB/s] model-00002-of-00003.safetensors: 39%|███▉ | 1.95G/5.00G [00:01<00:02, 1.32GB/s] model-00002-of-00003.safetensors: 46%|████▌ | 2.30G/5.00G [00:02<00:01, 1.62GB/s] model-00002-of-00003.safetensors: 54%|█████▎ | 2.68G/5.00G [00:02<00:01, 2.03GB/s] model-00002-of-00003.safetensors: 59%|█████▉ | 2.96G/5.00G [00:02<00:01, 1.81GB/s] model-00002-of-00003.safetensors: 65%|██████▌ | 3.26G/5.00G [00:02<00:00, 2.01GB/s] model-00002-of-00003.safetensors: 70%|███████ | 3.51G/5.00G [00:02<00:00, 1.86GB/s] model-00002-of-00003.safetensors: 76%|███████▌ | 3.80G/5.00G [00:02<00:00, 2.05GB/s] model-00002-of-00003.safetensors: 81%|████████ | 4.04G/5.00G [00:02<00:00, 1.76GB/s] model-00002-of-00003.safetensors: 87%|████████▋ | 4.36G/5.00G [00:03<00:00, 2.07GB/s] model-00002-of-00003.safetensors: 96%|█████████▌| 4.79G/5.00G [00:03<00:00, 2.59GB/s] model-00002-of-00003.safetensors: 100%|█████████▉| 5.00G/5.00G [00:03<00:00, 1.56GB/s]
mistralai-mistral-7b-ins-6151-v4-mkmlizer: quantized model in 14.756s
mistralai-mistral-7b-ins-6151-v4-mkmlizer: Processed model mistralai/Mistral-7B-Instruct-v0.2 in 25.908s
mistralai-mistral-7b-ins-6151-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
mistralai-mistral-7b-ins-6151-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mistralai-mistral-7b-ins-6151-v4
mistralai-mistral-7b-ins-6151-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/mistralai-mistral-7b-ins-6151-v4/tokenizer_config.json
mistralai-mistral-7b-ins-6151-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/mistralai-mistral-7b-ins-6151-v4/tokenizer.model
mistralai-mistral-7b-ins-6151-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/mistralai-mistral-7b-ins-6151-v4/tokenizer.json
mistralai-mistral-7b-ins-6151-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/mistralai-mistral-7b-ins-6151-v4/config.json
mistralai-mistral-7b-ins-6151-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/mistralai-mistral-7b-ins-6151-v4/special_tokens_map.json
mistralai-mistral-7b-ins-6151-v4-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/mistralai-mistral-7b-ins-6151-v4/mkml_model.tensors
mistralai-mistral-7b-ins-6151-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
mistralai-mistral-7b-ins-6151-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.
mistralai-mistral-7b-ins-6151-v4-mkmlizer: warnings.warn(
mistralai-mistral-7b-ins-6151-v4-mkmlizer: config.json: 0%| | 0.00/1.05k [00:00<?, ?B/s] config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 10.2MB/s]
mistralai-mistral-7b-ins-6151-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.
mistralai-mistral-7b-ins-6151-v4-mkmlizer: warnings.warn(
mistralai-mistral-7b-ins-6151-v4-mkmlizer: tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 2.45MB/s]
mistralai-mistral-7b-ins-6151-v4-mkmlizer: vocab.json: 0%| | 0.00/1.04M [00:00<?, ?B/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 26.7MB/s]
mistralai-mistral-7b-ins-6151-v4-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 30.6MB/s]
mistralai-mistral-7b-ins-6151-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.
mistralai-mistral-7b-ins-6151-v4-mkmlizer: warnings.warn(
mistralai-mistral-7b-ins-6151-v4-mkmlizer: pytorch_model.bin: 0%| | 0.00/1.44G [00:00<?, ?B/s] pytorch_model.bin: 1%| | 10.5M/1.44G [00:00<00:19, 73.9MB/s] pytorch_model.bin: 2%|▏ | 31.5M/1.44G [00:00<00:13, 103MB/s] pytorch_model.bin: 9%|▉ | 136M/1.44G [00:00<00:03, 392MB/s] pytorch_model.bin: 13%|█▎ | 189M/1.44G [00:01<00:07, 164MB/s] pytorch_model.bin: 25%|██▍ | 357M/1.44G [00:01<00:02, 381MB/s] pytorch_model.bin: 82%|████████▏ | 1.18G/1.44G [00:01<00:00, 1.73GB/s] pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:01<00:00, 1.04GB/s]
mistralai-mistral-7b-ins-6151-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
Job mistralai-mistral-7b-ins-6151-v4-mkmlizer completed after 58.45s with status: succeeded
Stopping job with name mistralai-mistral-7b-ins-6151-v4-mkmlizer
Pipeline stage MKMLizer completed in 65.54s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service mistralai-mistral-7b-ins-6151-v4
Waiting for inference service mistralai-mistral-7b-ins-6151-v4 to be ready
Inference service mistralai-mistral-7b-ins-6151-v4 ready after 40.28029775619507s
Pipeline stage ISVCDeployer completed in 50.87s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8834240436553955s
Received healthy response to inference request in 2.020470142364502s
Received healthy response to inference request in 0.7940914630889893s
Received healthy response to inference request in 0.6468822956085205s
Received healthy response to inference request in 0.7500994205474854s
5 requests
0 failed requests
5th percentile: 0.6675257205963134
10th percentile: 0.6881691455841065
20th percentile: 0.7294559955596924
30th percentile: 0.7588978290557862
40th percentile: 0.7764946460723877
50th percentile: 0.7940914630889893
60th percentile: 1.2846429347991943
70th percentile: 1.7751944065093992
80th percentile: 2.193060922622681
90th percentile: 2.538242483139038
95th percentile: 2.7108332633972165
99th percentile: 2.8489058876037596
mean time: 1.4189934730529785
Pipeline stage StressChecker completed in 18.56s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
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
mistralai-mistral-7b-ins_6151_v4 status is now deployed due to DeploymentManager action
mistralai-mistral-7b-ins_6151_v4 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics