submission_id: megumi21-megumi-chat-7b-v0-6_v2
developer_uid: megumi_10073
status: inactive
model_repo: megumi21/Megumi-Chat-7B-v0.6
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, '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': "### Instruction:\nYou are a creative agent roleplaying as a character called {bot_name}. Stay true to the persona given, reply with short and descriptive sentences. Do not be repetitive.\n{bot_name}'s Persona: {memory}\n", 'prompt_template': '### Input:\n# Example conversation:\n{prompt}\n# Actual conversation:\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '### Response: {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: 2024-04-01T02:42:04+00:00
model_name: megumi-chat-7b-v6
model_eval_status: success
safety_score: 0.97
entertaining: 6.96
stay_in_character: 8.23
user_preference: 7.3
double_thumbs_up: 94
thumbs_up: 155
thumbs_down: 62
num_battles: 8730
num_wins: 4190
win_ratio: 0.47995418098510884
celo_rating: 1143.69
Resubmit model
Running pipeline stage MKMLizer
Starting job with name megumi21-megumi-chat-7b-v0-6-v2-mkmlizer
Waiting for job on megumi21-megumi-chat-7b-v0-6-v2-mkmlizer to finish
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: ║ _____ __ __ ║
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: ║ /___/ ║
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: ║ ║
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: ║ Version: 0.6.11 ║
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: ║ ║
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: ║ The license key for the current software has been verified as ║
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: ║ belonging to: ║
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: ║ ║
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: ║ Chai Research Corp. ║
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: ║ ║
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 18.7MB/s]
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: config.json: 0%| | 0.00/654 [00:00<?, ?B/s] config.json: 100%|██████████| 654/654 [00:00<00:00, 5.35MB/s]
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: generation_config.json: 0%| | 0.00/132 [00:00<?, ?B/s] generation_config.json: 100%|██████████| 132/132 [00:00<00:00, 1.10MB/s]
megumi21-megumi-chat-7b-v0-6-v2-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<01:21, 61.4MB/s] pytorch_model-00002-of-00003.bin: 1%|▏ | 62.9M/5.00G [00:00<00:18, 269MB/s] pytorch_model-00002-of-00003.bin: 3%|▎ | 126M/5.00G [00:00<00:12, 387MB/s] pytorch_model-00002-of-00003.bin: 4%|▍ | 189M/5.00G [00:00<00:10, 449MB/s] pytorch_model-00002-of-00003.bin: 5%|▍ | 241M/5.00G [00:00<00:10, 462MB/s] pytorch_model-00002-of-00003.bin: 7%|▋ | 336M/5.00G [00:00<00:08, 559MB/s] pytorch_model-00002-of-00003.bin: 8%|▊ | 409M/5.00G [00:00<00:08, 572MB/s] pytorch_model-00002-of-00003.bin: 10%|█ | 524M/5.00G [00:00<00:06, 706MB/s] pytorch_model-00002-of-00003.bin: 13%|█▎ | 661M/5.00G [00:01<00:04, 870MB/s] pytorch_model-00002-of-00003.bin: 16%|█▌ | 776M/5.00G [00:01<00:04, 938MB/s] pytorch_model-00002-of-00003.bin: 18%|█▊ | 881M/5.00G [00:01<00:04, 951MB/s] pytorch_model-00002-of-00003.bin: 20%|█▉ | 986M/5.00G [00:01<00:04, 874MB/s] pytorch_model-00002-of-00003.bin: 22%|██▏ | 1.11G/5.00G [00:01<00:04, 941MB/s] pytorch_model-00002-of-00003.bin: 24%|██▍ | 1.22G/5.00G [00:01<00:04, 944MB/s] pytorch_model-00002-of-00003.bin: 27%|██▋ | 1.33G/5.00G [00:01<00:03, 966MB/s] pytorch_model-00002-of-00003.bin: 29%|██▊ | 1.44G/5.00G [00:01<00:03, 960MB/s] pytorch_model-00002-of-00003.bin: 32%|███▏ | 1.60G/5.00G [00:01<00:02, 1.15GB/s] pytorch_model-00002-of-00003.bin: 38%|███▊ | 1.88G/5.00G [00:02<00:01, 1.58GB/s] pytorch_model-00002-of-00003.bin: 42%|████▏ | 2.11G/5.00G [00:02<00:01, 1.78GB/s] pytorch_model-00002-of-00003.bin: 47%|████▋ | 2.35G/5.00G [00:02<00:01, 1.92GB/s] pytorch_model-00002-of-00003.bin: 53%|█████▎ | 2.65G/5.00G [00:02<00:01, 2.17GB/s] pytorch_model-00002-of-00003.bin: 57%|█████▋ | 2.87G/5.00G [00:02<00:01, 2.10GB/s] pytorch_model-00002-of-00003.bin: 62%|██████▏ | 3.09G/5.00G [00:02<00:01, 1.78GB/s] pytorch_model-00002-of-00003.bin: 66%|██████▌ | 3.28G/5.00G [00:02<00:01, 1.71GB/s] pytorch_model-00002-of-00003.bin: 69%|██████▉ | 3.46G/5.00G [00:03<00:01, 1.41GB/s] pytorch_model-00002-of-00003.bin: 72%|███████▏ | 3.62G/5.00G [00:03<00:01, 1.36GB/s] pytorch_model-00002-of-00003.bin: 76%|███████▌ | 3.79G/5.00G [00:03<00:00, 1.38GB/s] pytorch_model-00002-of-00003.bin: 79%|███████▊ | 3.93G/5.00G [00:03<00:00, 1.24GB/s] pytorch_model-00002-of-00003.bin: 82%|████████▏ | 4.11G/5.00G [00:03<00:00, 1.27GB/s] pytorch_model-00002-of-00003.bin: 85%|████████▍ | 4.24G/5.00G [00:03<00:00, 905MB/s] pytorch_model-00002-of-00003.bin: 87%|████████▋ | 4.36G/5.00G [00:04<00:00, 757MB/s] pytorch_model-00002-of-00003.bin: 90%|████████▉ | 4.50G/5.00G [00:04<00:00, 860MB/s] pytorch_model-00002-of-00003.bin: 92%|█████████▏| 4.60G/5.00G [00:04<00:00, 891MB/s] pytorch_model-00002-of-00003.bin: 94%|█████████▍| 4.71G/5.00G [00:04<00:00, 924MB/s] pytorch_model-00002-of-00003.bin: 100%|█████████▉| 5.00G/5.00G [00:04<00:00, 1.11GB/s]
megumi21-megumi-chat-7b-v0-6-v2-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<01:19, 57.0MB/s] pytorch_model-00003-of-00003.bin: 2%|▏ | 83.9M/4.54G [00:00<00:13, 320MB/s] pytorch_model-00003-of-00003.bin: 3%|▎ | 126M/4.54G [00:00<00:14, 314MB/s] pytorch_model-00003-of-00003.bin: 4%|▍ | 199M/4.54G [00:00<00:09, 442MB/s] pytorch_model-00003-of-00003.bin: 8%|▊ | 357M/4.54G [00:00<00:05, 734MB/s] pytorch_model-00003-of-00003.bin: 13%|█▎ | 598M/4.54G [00:00<00:03, 1.22GB/s] pytorch_model-00003-of-00003.bin: 17%|█▋ | 786M/4.54G [00:00<00:02, 1.40GB/s] pytorch_model-00003-of-00003.bin: 21%|██ | 944M/4.54G [00:00<00:02, 1.36GB/s] pytorch_model-00003-of-00003.bin: 24%|██▍ | 1.09G/4.54G [00:01<00:02, 1.32GB/s] pytorch_model-00003-of-00003.bin: 27%|██▋ | 1.23G/4.54G [00:01<00:02, 1.16GB/s] pytorch_model-00003-of-00003.bin: 30%|███ | 1.36G/4.54G [00:01<00:02, 1.21GB/s] pytorch_model-00003-of-00003.bin: 35%|███▍ | 1.57G/4.54G [00:01<00:02, 1.43GB/s] pytorch_model-00003-of-00003.bin: 41%|████ | 1.87G/4.54G [00:01<00:01, 1.83GB/s] pytorch_model-00003-of-00003.bin: 47%|████▋ | 2.15G/4.54G [00:01<00:01, 2.07GB/s] pytorch_model-00003-of-00003.bin: 52%|█████▏ | 2.37G/4.54G [00:01<00:01, 2.09GB/s] pytorch_model-00003-of-00003.bin: 57%|█████▋ | 2.59G/4.54G [00:01<00:01, 1.89GB/s] pytorch_model-00003-of-00003.bin: 61%|██████▏ | 2.79G/4.54G [00:02<00:01, 1.58GB/s] pytorch_model-00003-of-00003.bin: 65%|██████▌ | 2.97G/4.54G [00:02<00:01, 1.46GB/s] pytorch_model-00003-of-00003.bin: 69%|██████▉ | 3.15G/4.54G [00:02<00:00, 1.51GB/s] pytorch_model-00003-of-00003.bin: 73%|███████▎ | 3.31G/4.54G [00:02<00:00, 1.48GB/s] pytorch_model-00003-of-00003.bin: 76%|███████▋ | 3.47G/4.54G [00:02<00:00, 1.44GB/s] pytorch_model-00003-of-00003.bin: 81%|████████ | 3.67G/4.54G [00:02<00:00, 1.57GB/s] pytorch_model-00003-of-00003.bin: 85%|████████▍ | 3.84G/4.54G [00:03<00:00, 1.02GB/s] pytorch_model-00003-of-00003.bin: 88%|████████▊ | 3.97G/4.54G [00:03<00:00, 621MB/s] pytorch_model-00003-of-00003.bin: 90%|████████▉ | 4.08G/4.54G [00:03<00:00, 595MB/s] pytorch_model-00003-of-00003.bin: 94%|█████████▎| 4.25G/4.54G [00:03<00:00, 734MB/s] pytorch_model-00003-of-00003.bin: 97%|█████████▋| 4.38G/4.54G [00:03<00:00, 839MB/s] pytorch_model-00003-of-00003.bin: 100%|█████████▉| 4.54G/4.54G [00:04<00:00, 1.13GB/s]
megumi21-megumi-chat-7b-v0-6-v2-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, 163MB/s]
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: special_tokens_map.json: 0%| | 0.00/437 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 437/437 [00:00<00:00, 4.68MB/s]
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: tokenizer.model: 0%| | 0.00/493k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 54.5MB/s]
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: tokenizer_config.json: 0%| | 0.00/1.51k [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 1.51k/1.51k [00:00<00:00, 15.9MB/s]
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: Downloaded to shared memory in 15.880s
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: quantizing model to /dev/shm/model_cache
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: Saving mkml model at /dev/shm/model_cache
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: Reading /tmp/tmpdwt993uv/pytorch_model.bin.index.json
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: Profiling: 0%| | 0/291 [00:00<?, ?it/s] Profiling: 0%| | 1/291 [00:02<12:05, 2.50s/it] Profiling: 34%|███▎ | 98/291 [00:03<00:05, 32.47it/s] Profiling: 70%|███████ | 204/291 [00:04<00:01, 54.30it/s] Profiling: 100%|██████████| 291/291 [00:06<00:00, 57.52it/s] Profiling: 100%|██████████| 291/291 [00:06<00:00, 46.54it/s]
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: quantized model in 17.356s
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: Processed model megumi21/Megumi-Chat-7B-v0.6 in 34.316s
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: creating bucket guanaco-mkml-models
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/megumi21-megumi-chat-7b-v0-6-v2
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/megumi21-megumi-chat-7b-v0-6-v2/config.json
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/megumi21-megumi-chat-7b-v0-6-v2/tokenizer_config.json
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/megumi21-megumi-chat-7b-v0-6-v2/special_tokens_map.json
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/megumi21-megumi-chat-7b-v0-6-v2/tokenizer.json
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/megumi21-megumi-chat-7b-v0-6-v2/tokenizer.model
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/megumi21-megumi-chat-7b-v0-6-v2/mkml_model.tensors
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: pytorch_model.bin: 0%| | 0.00/1.44G [00:00<?, ?B/s] pytorch_model.bin: 1%| | 10.5M/1.44G [00:00<00:14, 101MB/s] pytorch_model.bin: 2%|▏ | 31.5M/1.44G [00:00<00:09, 145MB/s] pytorch_model.bin: 4%|▎ | 52.4M/1.44G [00:00<00:14, 96.6MB/s] pytorch_model.bin: 6%|▌ | 83.9M/1.44G [00:00<00:09, 150MB/s] pytorch_model.bin: 7%|▋ | 105M/1.44G [00:00<00:10, 123MB/s] pytorch_model.bin: 9%|▊ | 126M/1.44G [00:01<00:12, 103MB/s] pytorch_model.bin: 12%|█▏ | 168M/1.44G [00:01<00:09, 131MB/s] pytorch_model.bin: 21%|██ | 304M/1.44G [00:01<00:03, 347MB/s] pytorch_model.bin: 67%|██████▋ | 965M/1.44G [00:01<00:00, 1.60GB/s] pytorch_model.bin: 86%|████████▌ | 1.25G/1.44G [00:01<00:00, 1.86GB/s] pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:01<00:00, 810MB/s]
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: Saving duration: 0.279s
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.812s
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: creating bucket guanaco-reward-models
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/megumi21-megumi-chat-7b-v0-6-v2_reward
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/megumi21-megumi-chat-7b-v0-6-v2_reward/tokenizer_config.json
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/megumi21-megumi-chat-7b-v0-6-v2_reward/config.json
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/megumi21-megumi-chat-7b-v0-6-v2_reward/special_tokens_map.json
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/megumi21-megumi-chat-7b-v0-6-v2_reward/vocab.json
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/megumi21-megumi-chat-7b-v0-6-v2_reward/merges.txt
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/megumi21-megumi-chat-7b-v0-6-v2_reward/tokenizer.json
megumi21-megumi-chat-7b-v0-6-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/megumi21-megumi-chat-7b-v0-6-v2_reward/reward.tensors
Job megumi21-megumi-chat-7b-v0-6-v2-mkmlizer completed after 66.38s with status: succeeded
Stopping job with name megumi21-megumi-chat-7b-v0-6-v2-mkmlizer
Pipeline stage MKMLizer completed in 69.91s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service megumi21-megumi-chat-7b-v0-6-v2
Waiting for inference service megumi21-megumi-chat-7b-v0-6-v2 to be ready
Inference service megumi21-megumi-chat-7b-v0-6-v2 ready after 50.26795029640198s
Pipeline stage ISVCDeployer completed in 57.32s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.792029619216919s
Received healthy response to inference request in 1.168180227279663s
Received healthy response to inference request in 1.2283809185028076s
Received healthy response to inference request in 1.1979753971099854s
Received healthy response to inference request in 1.2126941680908203s
5 requests
0 failed requests
5th percentile: 1.1741392612457275
10th percentile: 1.180098295211792
20th percentile: 1.192016363143921
30th percentile: 1.2009191513061523
40th percentile: 1.2068066596984863
50th percentile: 1.2126941680908203
60th percentile: 1.2189688682556152
70th percentile: 1.2252435684204102
80th percentile: 1.34111065864563
90th percentile: 1.5665701389312745
95th percentile: 1.6792998790740965
99th percentile: 1.7694836711883544
mean time: 1.319852066040039
Pipeline stage StressChecker completed in 7.30s
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 0.11s
M-Eval Dataset for topic stay_in_character is loaded
megumi21-megumi-chat-7b-v0-6_v2 status is now deployed due to DeploymentManager action
megumi21-megumi-chat-7b-v0-6_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics