submission_id: cgato-thespice-7b-v0-1_v6
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': 'You are {bot_name}. {memory}\n\n', 'prompt_template': '***\n{prompt}\n***\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:'}
reward_formatter: {'memory_template': 'You are {bot_name}. {memory}\n\n', 'prompt_template': '***\n{prompt}\n***\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:'}
timestamp: 2024-03-18T01:50:43+00:00
model_name: TheSpice-NP2
model_eval_status: success
safety_score: 0.88
entertaining: 7.08
stay_in_character: 8.62
user_preference: 7.68
double_thumbs_up: 1450
thumbs_up: 2057
thumbs_down: 949
num_battles: 112731
num_wins: 59704
win_ratio: 0.5296147466091847
celo_rating: 1178.79
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-thespice-7b-v0-1-v6-mkmlizer
Waiting for job on cgato-thespice-7b-v0-1-v6-mkmlizer to finish
Failed to get response for submission chaiml-phase2-winner-13b2_v256: HTTPConnectionPool(host='chaiml-phase2-winner-13b2-v256-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud', port=80): Read timed out. (read timeout=5.5)
cgato-thespice-7b-v0-1-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-thespice-7b-v0-1-v6-mkmlizer: ║ _____ __ __ ║
cgato-thespice-7b-v0-1-v6-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-thespice-7b-v0-1-v6-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-thespice-7b-v0-1-v6-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-thespice-7b-v0-1-v6-mkmlizer: ║ /___/ ║
cgato-thespice-7b-v0-1-v6-mkmlizer: ║ ║
cgato-thespice-7b-v0-1-v6-mkmlizer: ║ Version: 0.6.11 ║
cgato-thespice-7b-v0-1-v6-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-thespice-7b-v0-1-v6-mkmlizer: ║ ║
cgato-thespice-7b-v0-1-v6-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-thespice-7b-v0-1-v6-mkmlizer: ║ belonging to: ║
cgato-thespice-7b-v0-1-v6-mkmlizer: ║ ║
cgato-thespice-7b-v0-1-v6-mkmlizer: ║ Chai Research Corp. ║
cgato-thespice-7b-v0-1-v6-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-thespice-7b-v0-1-v6-mkmlizer: ║ Expiration: 2024-04-15 23:59:59 ║
cgato-thespice-7b-v0-1-v6-mkmlizer: ║ ║
cgato-thespice-7b-v0-1-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-thespice-7b-v0-1-v6-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 16.5MB/s]
cgato-thespice-7b-v0-1-v6-mkmlizer: README.md: 0%| | 0.00/30.0 [00:00<?, ?B/s] README.md: 100%|██████████| 30.0/30.0 [00:00<00:00, 324kB/s]
cgato-thespice-7b-v0-1-v6-mkmlizer: config.json: 0%| | 0.00/643 [00:00<?, ?B/s] config.json: 100%|██████████| 643/643 [00:00<00:00, 6.50MB/s]
cgato-thespice-7b-v0-1-v6-mkmlizer: generation_config.json: 0%| | 0.00/132 [00:00<?, ?B/s] generation_config.json: 100%|██████████| 132/132 [00:00<00:00, 1.71MB/s]
cgato-thespice-7b-v0-1-v6-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<02:39, 30.9MB/s] pytorch_model-00001-of-00003.bin: 0%| | 21.0M/4.94G [00:00<01:33, 52.7MB/s] pytorch_model-00001-of-00003.bin: 2%|▏ | 115M/4.94G [00:00<00:15, 308MB/s] pytorch_model-00001-of-00003.bin: 3%|▎ | 168M/4.94G [00:00<00:16, 290MB/s] pytorch_model-00001-of-00003.bin: 6%|▌ | 283M/4.94G [00:00<00:09, 499MB/s] pytorch_model-00001-of-00003.bin: 7%|▋ | 357M/4.94G [00:00<00:08, 512MB/s] pytorch_model-00001-of-00003.bin: 10%|█ | 514M/4.94G [00:01<00:05, 768MB/s] pytorch_model-00001-of-00003.bin: 22%|██▏ | 1.09G/4.94G [00:01<00:01, 2.07GB/s] pytorch_model-00001-of-00003.bin: 27%|██▋ | 1.33G/4.94G [00:01<00:02, 1.66GB/s] pytorch_model-00001-of-00003.bin: 31%|███ | 1.54G/4.94G [00:01<00:02, 1.43GB/s] pytorch_model-00001-of-00003.bin: 35%|███▍ | 1.72G/4.94G [00:01<00:02, 1.36GB/s] pytorch_model-00001-of-00003.bin: 38%|███▊ | 1.88G/4.94G [00:01<00:02, 1.38GB/s] pytorch_model-00001-of-00003.bin: 48%|████▊ | 2.39G/4.94G [00:01<00:01, 2.24GB/s] pytorch_model-00001-of-00003.bin: 54%|█████▍ | 2.68G/4.94G [00:02<00:00, 2.38GB/s] pytorch_model-00001-of-00003.bin: 60%|█████▉ | 2.96G/4.94G [00:02<00:00, 2.15GB/s] pytorch_model-00001-of-00003.bin: 65%|██████▍ | 3.20G/4.94G [00:02<00:01, 1.71GB/s] pytorch_model-00001-of-00003.bin: 69%|██████▊ | 3.40G/4.94G [00:02<00:00, 1.55GB/s] pytorch_model-00001-of-00003.bin: 72%|███████▏ | 3.58G/4.94G [00:02<00:00, 1.53GB/s] pytorch_model-00001-of-00003.bin: 77%|███████▋ | 3.82G/4.94G [00:02<00:00, 1.73GB/s] pytorch_model-00001-of-00003.bin: 83%|████████▎ | 4.08G/4.94G [00:02<00:00, 1.94GB/s] pytorch_model-00001-of-00003.bin: 90%|████████▉ | 4.44G/4.94G [00:03<00:00, 2.30GB/s] pytorch_model-00001-of-00003.bin: 95%|█████████▍| 4.68G/4.94G [00:03<00:00, 2.08GB/s] pytorch_model-00001-of-00003.bin: 100%|█████████▉| 4.94G/4.94G [00:03<00:00, 1.52GB/s]
cgato-thespice-7b-v0-1-v6-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<02:45, 30.2MB/s] pytorch_model-00002-of-00003.bin: 1%|▏ | 73.4M/5.00G [00:00<00:24, 203MB/s] pytorch_model-00002-of-00003.bin: 3%|▎ | 126M/5.00G [00:00<00:21, 229MB/s] pytorch_model-00002-of-00003.bin: 3%|▎ | 168M/5.00G [00:00<00:22, 216MB/s] pytorch_model-00002-of-00003.bin: 4%|▍ | 210M/5.00G [00:00<00:18, 258MB/s] pytorch_model-00002-of-00003.bin: 7%|▋ | 357M/5.00G [00:01<00:08, 540MB/s] pytorch_model-00002-of-00003.bin: 16%|█▌ | 776M/5.00G [00:01<00:02, 1.45GB/s] pytorch_model-00002-of-00003.bin: 24%|██▎ | 1.18G/5.00G [00:01<00:01, 2.12GB/s] pytorch_model-00002-of-00003.bin: 29%|██▊ | 1.44G/5.00G [00:01<00:02, 1.53GB/s] pytorch_model-00002-of-00003.bin: 33%|███▎ | 1.65G/5.00G [00:01<00:02, 1.43GB/s] pytorch_model-00002-of-00003.bin: 36%|███▋ | 1.82G/5.00G [00:01<00:02, 1.47GB/s] pytorch_model-00002-of-00003.bin: 42%|████▏ | 2.12G/5.00G [00:01<00:01, 1.79GB/s] pytorch_model-00002-of-00003.bin: 49%|████▉ | 2.44G/5.00G [00:02<00:01, 2.13GB/s] pytorch_model-00002-of-00003.bin: 54%|█████▎ | 2.68G/5.00G [00:02<00:01, 2.18GB/s] pytorch_model-00002-of-00003.bin: 59%|█████▊ | 2.94G/5.00G [00:02<00:00, 2.19GB/s] pytorch_model-00002-of-00003.bin: 64%|██████▎ | 3.18G/5.00G [00:02<00:00, 2.21GB/s] pytorch_model-00002-of-00003.bin: 68%|██████▊ | 3.41G/5.00G [00:02<00:00, 2.14GB/s] pytorch_model-00002-of-00003.bin: 74%|███████▍ | 3.72G/5.00G [00:02<00:00, 2.36GB/s] pytorch_model-00002-of-00003.bin: 79%|███████▉ | 3.97G/5.00G [00:02<00:00, 2.19GB/s] pytorch_model-00002-of-00003.bin: 84%|████████▍ | 4.20G/5.00G [00:02<00:00, 1.93GB/s] pytorch_model-00002-of-00003.bin: 88%|████████▊ | 4.41G/5.00G [00:02<00:00, 1.88GB/s] pytorch_model-00002-of-00003.bin: 96%|█████████▌| 4.81G/5.00G [00:03<00:00, 2.31GB/s] pytorch_model-00002-of-00003.bin: 100%|█████████▉| 5.00G/5.00G [00:03<00:00, 1.53GB/s]
cgato-thespice-7b-v0-1-v6-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<02:13, 34.0MB/s] pytorch_model-00003-of-00003.bin: 1%|▏ | 62.9M/4.54G [00:00<00:26, 168MB/s] pytorch_model-00003-of-00003.bin: 3%|▎ | 136M/4.54G [00:00<00:13, 326MB/s] pytorch_model-00003-of-00003.bin: 4%|▍ | 189M/4.54G [00:00<00:17, 249MB/s] pytorch_model-00003-of-00003.bin: 9%|▉ | 430M/4.54G [00:00<00:05, 706MB/s] pytorch_model-00003-of-00003.bin: 26%|██▌ | 1.16G/4.54G [00:01<00:01, 2.21GB/s] pytorch_model-00003-of-00003.bin: 33%|███▎ | 1.48G/4.54G [00:01<00:01, 2.15GB/s] pytorch_model-00003-of-00003.bin: 39%|███▉ | 1.76G/4.54G [00:01<00:01, 2.14GB/s] pytorch_model-00003-of-00003.bin: 45%|████▍ | 2.02G/4.54G [00:01<00:01, 1.47GB/s] pytorch_model-00003-of-00003.bin: 49%|████▉ | 2.23G/4.54G [00:01<00:01, 1.52GB/s] pytorch_model-00003-of-00003.bin: 55%|█████▍ | 2.47G/4.54G [00:01<00:01, 1.70GB/s] pytorch_model-00003-of-00003.bin: 59%|█████▉ | 2.68G/4.54G [00:01<00:01, 1.76GB/s] pytorch_model-00003-of-00003.bin: 66%|██████▌ | 3.00G/4.54G [00:02<00:00, 2.08GB/s] pytorch_model-00003-of-00003.bin: 71%|███████▏ | 3.24G/4.54G [00:02<00:00, 2.15GB/s] pytorch_model-00003-of-00003.bin: 81%|████████ | 3.68G/4.54G [00:02<00:00, 2.74GB/s] pytorch_model-00003-of-00003.bin: 88%|████████▊ | 3.98G/4.54G [00:02<00:00, 2.00GB/s] pytorch_model-00003-of-00003.bin: 94%|█████████▍| 4.27G/4.54G [00:02<00:00, 2.18GB/s] pytorch_model-00003-of-00003.bin: 100%|█████████▉| 4.54G/4.54G [00:04<00:00, 488MB/s] pytorch_model-00003-of-00003.bin: 100%|█████████▉| 4.54G/4.54G [00:04<00:00, 1.04GB/s]
cgato-thespice-7b-v0-1-v6-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, 18.7MB/s]
cgato-thespice-7b-v0-1-v6-mkmlizer: special_tokens_map.json: 0%| | 0.00/437 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 437/437 [00:00<00:00, 5.47MB/s]
cgato-thespice-7b-v0-1-v6-mkmlizer: tokenizer.model: 0%| | 0.00/493k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 58.7MB/s]
cgato-thespice-7b-v0-1-v6-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, 10.6MB/s]
cgato-thespice-7b-v0-1-v6-mkmlizer: Downloaded to shared memory in 12.131s
cgato-thespice-7b-v0-1-v6-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-thespice-7b-v0-1-v6-mkmlizer: Saving mkml model at /dev/shm/model_cache
cgato-thespice-7b-v0-1-v6-mkmlizer: Reading /tmp/tmpdqj20ove/pytorch_model.bin.index.json
cgato-thespice-7b-v0-1-v6-mkmlizer: Profiling: 0%| | 0/291 [00:00<?, ?it/s] Profiling: 0%| | 1/291 [00:02<10:18, 2.13s/it] Profiling: 34%|███▎ | 98/291 [00:03<00:04, 40.22it/s] Profiling: 70%|███████ | 204/291 [00:03<00:01, 70.20it/s] Profiling: 100%|██████████| 291/291 [00:05<00:00, 68.37it/s] Profiling: 100%|██████████| 291/291 [00:05<00:00, 56.27it/s]
cgato-thespice-7b-v0-1-v6-mkmlizer: quantized model in 15.454s
cgato-thespice-7b-v0-1-v6-mkmlizer: Processed model cgato/TheSpice-7b-v0.1 in 28.591s
cgato-thespice-7b-v0-1-v6-mkmlizer: creating bucket guanaco-mkml-models
cgato-thespice-7b-v0-1-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-thespice-7b-v0-1-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-thespice-7b-v0-1-v6
cgato-thespice-7b-v0-1-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-thespice-7b-v0-1-v6/special_tokens_map.json
cgato-thespice-7b-v0-1-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cgato-thespice-7b-v0-1-v6/tokenizer.model
cgato-thespice-7b-v0-1-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-thespice-7b-v0-1-v6/config.json
cgato-thespice-7b-v0-1-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-thespice-7b-v0-1-v6/tokenizer.json
cgato-thespice-7b-v0-1-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-thespice-7b-v0-1-v6/tokenizer_config.json
cgato-thespice-7b-v0-1-v6-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/cgato-thespice-7b-v0-1-v6/mkml_model.tensors
cgato-thespice-7b-v0-1-v6-mkmlizer: vocab.json: 0%| | 0.00/1.04M [00:00<?, ?B/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 24.4MB/s]
cgato-thespice-7b-v0-1-v6-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 33.7MB/s]
cgato-thespice-7b-v0-1-v6-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-v6-mkmlizer: warnings.warn(
cgato-thespice-7b-v0-1-v6-mkmlizer: pytorch_model.bin: 0%| | 0.00/1.44G [00:00<?, ?B/s] pytorch_model.bin: 1%|▏ | 21.0M/1.44G [00:00<00:08, 160MB/s] pytorch_model.bin: 4%|▍ | 62.9M/1.44G [00:00<00:05, 260MB/s] pytorch_model.bin: 7%|▋ | 94.4M/1.44G [00:00<00:05, 250MB/s] pytorch_model.bin: 9%|▉ | 136M/1.44G [00:00<00:05, 236MB/s] pytorch_model.bin: 16%|█▌ | 231M/1.44G [00:00<00:02, 413MB/s] pytorch_model.bin: 20%|█▉ | 283M/1.44G [00:01<00:04, 250MB/s] pytorch_model.bin: 28%|██▊ | 409M/1.44G [00:01<00:02, 417MB/s] pytorch_model.bin: 73%|███████▎ | 1.06G/1.44G [00:01<00:00, 1.63GB/s] pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:01<00:00, 2.02GB/s] pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:01<00:00, 974MB/s]
cgato-thespice-7b-v0-1-v6-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-thespice-7b-v0-1-v6-mkmlizer: Saving duration: 0.251s
cgato-thespice-7b-v0-1-v6-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 5.020s
cgato-thespice-7b-v0-1-v6-mkmlizer: creating bucket guanaco-reward-models
cgato-thespice-7b-v0-1-v6-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-thespice-7b-v0-1-v6-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-thespice-7b-v0-1-v6_reward
cgato-thespice-7b-v0-1-v6-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-thespice-7b-v0-1-v6_reward/config.json
cgato-thespice-7b-v0-1-v6-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-thespice-7b-v0-1-v6_reward/special_tokens_map.json
cgato-thespice-7b-v0-1-v6-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-thespice-7b-v0-1-v6_reward/tokenizer_config.json
cgato-thespice-7b-v0-1-v6-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-thespice-7b-v0-1-v6_reward/merges.txt
cgato-thespice-7b-v0-1-v6-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-thespice-7b-v0-1-v6_reward/vocab.json
cgato-thespice-7b-v0-1-v6-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-thespice-7b-v0-1-v6_reward/tokenizer.json
cgato-thespice-7b-v0-1-v6-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-thespice-7b-v0-1-v6_reward/reward.tensors
Job cgato-thespice-7b-v0-1-v6-mkmlizer completed after 53.37s with status: succeeded
Stopping job with name cgato-thespice-7b-v0-1-v6-mkmlizer
Pipeline stage MKMLizer completed in 58.54s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.14s
Running pipeline stage ISVCDeployer
Creating inference service cgato-thespice-7b-v0-1-v6
Waiting for inference service cgato-thespice-7b-v0-1-v6 to be ready
Inference service cgato-thespice-7b-v0-1-v6 ready after 40.276968479156494s
Pipeline stage ISVCDeployer completed in 47.87s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7292296886444092s
Received healthy response to inference request in 1.1775317192077637s
Received healthy response to inference request in 1.1750919818878174s
Received healthy response to inference request in 1.1784958839416504s
Received healthy response to inference request in 1.214144229888916s
5 requests
0 failed requests
5th percentile: 1.1755799293518066
10th percentile: 1.176067876815796
20th percentile: 1.1770437717437745
30th percentile: 1.177724552154541
40th percentile: 1.1781102180480958
50th percentile: 1.1784958839416504
60th percentile: 1.1927552223205566
70th percentile: 1.207014560699463
80th percentile: 1.3171613216400146
90th percentile: 1.523195505142212
95th percentile: 1.6262125968933105
99th percentile: 1.7086262702941895
mean time: 1.2948987007141113
Pipeline stage StressChecker completed in 7.33s
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 0.05s
M-Eval Dataset for topic stay_in_character is loaded
cgato-thespice-7b-v0-1_v6 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics