submission_id: cgato-thespice-7b-invert_9589_v6
developer_uid: c.gato
status: torndown
model_repo: cgato/TheSpice-7b-InvertedInstruct-v0.1.3
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.8, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 70, 'presence_penalty': 0.9, 'frequency_penalty': 0.25, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n {bot_name} responds in one line.\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
reward_formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n {bot_name} gives single line responses.\n{bot_name} gives short responses.\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
timestamp: 2024-04-18T13:16:10+00:00
model_name: cgato-thespice-7b-invert_9589_v6
model_eval_status: success
model_group: cgato/TheSpice-7b-Invert
num_battles: 5218
num_wins: 2895
celo_rating: 1184.35
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: MistralForCausalLM
model_num_parameters: 7241732096.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: cgato-thespice-7b-invert_9589_v6
ineligible_reason: propriety_total_count < 800
language_model: cgato/TheSpice-7b-InvertedInstruct-v0.1.3
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-18
win_ratio: 0.5548102721349176
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-thespice-7b-invert-9589-v6-mkmlizer
Waiting for job on cgato-thespice-7b-invert-9589-v6-mkmlizer to finish
Stopping job with name cgato-thespice-7b-invert-9589-v6-mkmlizer
%s, retrying in %s seconds...
Starting job with name cgato-thespice-7b-invert-9589-v6-mkmlizer
Waiting for job on cgato-thespice-7b-invert-9589-v6-mkmlizer to finish
Stopping job with name cgato-thespice-7b-invert-9589-v6-mkmlizer
%s, retrying in %s seconds...
Starting job with name cgato-thespice-7b-invert-9589-v6-mkmlizer
Waiting for job on cgato-thespice-7b-invert-9589-v6-mkmlizer to finish
cgato-thespice-7b-invert-9589-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-thespice-7b-invert-9589-v6-mkmlizer: ║ _____ __ __ ║
cgato-thespice-7b-invert-9589-v6-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-thespice-7b-invert-9589-v6-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-thespice-7b-invert-9589-v6-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-thespice-7b-invert-9589-v6-mkmlizer: ║ /___/ ║
cgato-thespice-7b-invert-9589-v6-mkmlizer: ║ ║
cgato-thespice-7b-invert-9589-v6-mkmlizer: ║ Version: 0.6.11 ║
cgato-thespice-7b-invert-9589-v6-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-thespice-7b-invert-9589-v6-mkmlizer: ║ ║
cgato-thespice-7b-invert-9589-v6-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-thespice-7b-invert-9589-v6-mkmlizer: ║ belonging to: ║
cgato-thespice-7b-invert-9589-v6-mkmlizer: ║ ║
cgato-thespice-7b-invert-9589-v6-mkmlizer: ║ Chai Research Corp. ║
cgato-thespice-7b-invert-9589-v6-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-thespice-7b-invert-9589-v6-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-thespice-7b-invert-9589-v6-mkmlizer: ║ ║
cgato-thespice-7b-invert-9589-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-thespice-7b-invert-9589-v6-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 5.93MB/s]
cgato-thespice-7b-invert-9589-v6-mkmlizer: README.md: 0%| | 0.00/30.0 [00:00<?, ?B/s] README.md: 100%|██████████| 30.0/30.0 [00:00<00:00, 195kB/s]
cgato-thespice-7b-invert-9589-v6-mkmlizer: config.json: 0%| | 0.00/653 [00:00<?, ?B/s] config.json: 100%|██████████| 653/653 [00:00<00:00, 4.03MB/s]
cgato-thespice-7b-invert-9589-v6-mkmlizer: generation_config.json: 0%| | 0.00/137 [00:00<?, ?B/s] generation_config.json: 100%|██████████| 137/137 [00:00<00:00, 1.05MB/s]
cgato-thespice-7b-invert-9589-v6-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 [00:02<19:42, 4.17MB/s] model-00001-of-00003.safetensors: 0%| | 21.0M/4.94G [00:02<08:37, 9.52MB/s] model-00001-of-00003.safetensors: 1%| | 31.5M/4.94G [00:02<05:12, 15.7MB/s] model-00001-of-00003.safetensors: 1%|▏ | 73.4M/4.94G [00:03<02:04, 39.0MB/s] model-00001-of-00003.safetensors: 3%|▎ | 157M/4.94G [00:03<00:44, 107MB/s] model-00001-of-00003.safetensors: 6%|▋ | 315M/4.94G [00:03<00:17, 265MB/s] model-00001-of-00003.safetensors: 21%|██ | 1.02G/4.94G [00:03<00:03, 1.17GB/s] model-00001-of-00003.safetensors: 26%|██▋ | 1.30G/4.94G [00:03<00:03, 1.19GB/s] model-00001-of-00003.safetensors: 31%|███ | 1.53G/4.94G [00:04<00:03, 1.13GB/s] model-00001-of-00003.safetensors: 35%|███▍ | 1.72G/4.94G [00:04<00:03, 1.07GB/s] model-00001-of-00003.safetensors: 39%|███▉ | 1.93G/4.94G [00:04<00:02, 1.20GB/s] model-00001-of-00003.safetensors: 42%|████▏ | 2.10G/4.94G [00:04<00:02, 1.17GB/s] model-00001-of-00003.safetensors: 46%|████▌ | 2.29G/4.94G [00:04<00:02, 1.30GB/s] model-00001-of-00003.safetensors: 50%|████▉ | 2.45G/4.94G [00:04<00:01, 1.29GB/s] model-00001-of-00003.safetensors: 53%|█████▎ | 2.61G/4.94G [00:04<00:01, 1.26GB/s] model-00001-of-00003.safetensors: 56%|█████▌ | 2.76G/4.94G [00:05<00:02, 1.06GB/s] model-00001-of-00003.safetensors: 58%|█████▊ | 2.88G/4.94G [00:05<00:02, 997MB/s] model-00001-of-00003.safetensors: 61%|██████ | 3.02G/4.94G [00:05<00:01, 1.07GB/s] model-00001-of-00003.safetensors: 64%|██████▎ | 3.15G/4.94G [00:05<00:03, 586MB/s] model-00001-of-00003.safetensors: 67%|██████▋ | 3.29G/4.94G [00:05<00:02, 707MB/s] model-00001-of-00003.safetensors: 70%|██████▉ | 3.45G/4.94G [00:06<00:01, 842MB/s] model-00001-of-00003.safetensors: 75%|███████▌ | 3.71G/4.94G [00:06<00:01, 1.18GB/s] model-00001-of-00003.safetensors: 78%|███████▊ | 3.87G/4.94G [00:06<00:00, 1.24GB/s] model-00001-of-00003.safetensors: 82%|████████▏ | 4.04G/4.94G [00:06<00:00, 1.30GB/s] model-00001-of-00003.safetensors: 85%|████████▍ | 4.19G/4.94G [00:06<00:00, 1.13GB/s] model-00001-of-00003.safetensors: 90%|█████████ | 4.47G/4.94G [00:06<00:00, 1.48GB/s] model-00001-of-00003.safetensors: 100%|█████████▉| 4.94G/4.94G [00:06<00:00, 728MB/s]
cgato-thespice-7b-invert-9589-v6-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 [00:02<21:20, 3.89MB/s] model-00002-of-00003.safetensors: 1%|▏ | 62.9M/5.00G [00:03<03:09, 26.1MB/s] model-00002-of-00003.safetensors: 5%|▍ | 241M/5.00G [00:03<00:37, 128MB/s] model-00002-of-00003.safetensors: 23%|██▎ | 1.13G/5.00G [00:03<00:04, 803MB/s] model-00002-of-00003.safetensors: 31%|███ | 1.53G/5.00G [00:04<00:05, 643MB/s] model-00002-of-00003.safetensors: 36%|███▌ | 1.80G/5.00G [00:04<00:04, 650MB/s] model-00002-of-00003.safetensors: 40%|████ | 2.00G/5.00G [00:04<00:04, 693MB/s] model-00002-of-00003.safetensors: 43%|████▎ | 2.17G/5.00G [00:04<00:03, 724MB/s] model-00002-of-00003.safetensors: 46%|████▋ | 2.32G/5.00G [00:05<00:03, 758MB/s] model-00002-of-00003.safetensors: 49%|████▉ | 2.44G/5.00G [00:05<00:04, 610MB/s] model-00002-of-00003.safetensors: 51%|█████ | 2.55G/5.00G [00:05<00:03, 636MB/s] model-00002-of-00003.safetensors: 60%|█████▉ | 2.98G/5.00G [00:05<00:01, 1.16GB/s] model-00002-of-00003.safetensors: 64%|██████▎ | 3.18G/5.00G [00:05<00:01, 1.14GB/s] model-00002-of-00003.safetensors: 67%|██████▋ | 3.36G/5.00G [00:06<00:01, 1.24GB/s] model-00002-of-00003.safetensors: 71%|███████ | 3.53G/5.00G [00:06<00:01, 1.09GB/s] model-00002-of-00003.safetensors: 74%|███████▍ | 3.70G/5.00G [00:06<00:01, 1.20GB/s] model-00002-of-00003.safetensors: 77%|███████▋ | 3.86G/5.00G [00:06<00:00, 1.17GB/s] model-00002-of-00003.safetensors: 80%|████████ | 4.01G/5.00G [00:06<00:00, 1.10GB/s] model-00002-of-00003.safetensors: 84%|████████▍ | 4.20G/5.00G [00:06<00:00, 1.27GB/s] model-00002-of-00003.safetensors: 91%|█████████ | 4.55G/5.00G [00:06<00:00, 1.77GB/s] model-00002-of-00003.safetensors: 100%|█████████▉| 5.00G/5.00G [00:06<00:00, 717MB/s]
cgato-thespice-7b-invert-9589-v6-mkmlizer: model-00003-of-00003.safetensors: 0%| | 0.00/4.54G [00:00<?, ?B/s] model-00003-of-00003.safetensors: 0%| | 10.5M/4.54G [00:02<20:52, 3.62MB/s] model-00003-of-00003.safetensors: 1%| | 52.4M/4.54G [00:03<03:32, 21.1MB/s] model-00003-of-00003.safetensors: 3%|▎ | 157M/4.54G [00:03<00:57, 75.9MB/s] model-00003-of-00003.safetensors: 9%|▉ | 430M/4.54G [00:03<00:15, 267MB/s] model-00003-of-00003.safetensors: 27%|██▋ | 1.23G/4.54G [00:04<00:04, 685MB/s] model-00003-of-00003.safetensors: 30%|███ | 1.36G/4.54G [00:04<00:05, 559MB/s] model-00003-of-00003.safetensors: 38%|███▊ | 1.71G/4.54G [00:04<00:03, 788MB/s] model-00003-of-00003.safetensors: 41%|████▏ | 1.88G/4.54G [00:05<00:04, 547MB/s] model-00003-of-00003.safetensors: 44%|████▍ | 1.99G/4.54G [00:05<00:05, 460MB/s] model-00003-of-00003.safetensors: 47%|████▋ | 2.12G/4.54G [00:05<00:04, 527MB/s] model-00003-of-00003.safetensors: 57%|█████▋ | 2.58G/4.54G [00:06<00:02, 968MB/s] model-00003-of-00003.safetensors: 65%|██████▌ | 2.96G/4.54G [00:06<00:01, 1.33GB/s] model-00003-of-00003.safetensors: 71%|███████ | 3.22G/4.54G [00:06<00:00, 1.34GB/s] model-00003-of-00003.safetensors: 76%|███████▌ | 3.44G/4.54G [00:06<00:00, 1.16GB/s] model-00003-of-00003.safetensors: 80%|███████▉ | 3.62G/4.54G [00:06<00:00, 1.04GB/s] model-00003-of-00003.safetensors: 83%|████████▎ | 3.76G/4.54G [00:06<00:00, 1.10GB/s] model-00003-of-00003.safetensors: 89%|████████▉ | 4.04G/4.54G [00:07<00:00, 1.38GB/s] model-00003-of-00003.safetensors: 100%|█████████▉| 4.52G/4.54G [00:07<00:00, 2.08GB/s] model-00003-of-00003.safetensors: 100%|█████████▉| 4.54G/4.54G [00:07<00:00, 631MB/s]
cgato-thespice-7b-invert-9589-v6-mkmlizer: model.safetensors.index.json: 0%| | 0.00/23.9k [00:00<?, ?B/s] model.safetensors.index.json: 100%|██████████| 23.9k/23.9k [00:00<00:00, 140MB/s]
cgato-thespice-7b-invert-9589-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, 2.48MB/s]
cgato-thespice-7b-invert-9589-v6-mkmlizer: tokenizer.model: 0%| | 0.00/493k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 27.3MB/s]
cgato-thespice-7b-invert-9589-v6-mkmlizer: tokenizer_config.json: 0%| | 0.00/982 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 982/982 [00:00<00:00, 13.0MB/s]
cgato-thespice-7b-invert-9589-v6-mkmlizer: Downloaded to shared memory in 24.983s
cgato-thespice-7b-invert-9589-v6-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-thespice-7b-invert-9589-v6-mkmlizer: Saving mkml model at /dev/shm/model_cache
cgato-thespice-7b-invert-9589-v6-mkmlizer: Reading /tmp/tmpvbos0evs/model.safetensors.index.json
cgato-thespice-7b-invert-9589-v6-mkmlizer: Profiling: 0%| | 0/291 [00:00<?, ?it/s] Profiling: 0%| | 1/291 [00:01<06:47, 1.40s/it] Profiling: 4%|▍ | 13/291 [00:01<00:24, 11.49it/s] Profiling: 8%|▊ | 23/291 [00:01<00:12, 21.44it/s] Profiling: 11%|█ | 31/291 [00:01<00:09, 28.86it/s] Profiling: 13%|█▎ | 39/291 [00:01<00:07, 34.23it/s] Profiling: 16%|█▌ | 46/291 [00:02<00:06, 40.53it/s] Profiling: 19%|█▊ | 54/291 [00:02<00:04, 47.57it/s] Profiling: 22%|██▏ | 63/291 [00:02<00:04, 53.41it/s] Profiling: 25%|██▍ | 72/291 [00:02<00:03, 58.73it/s] Profiling: 28%|██▊ | 81/291 [00:02<00:03, 61.34it/s] Profiling: 31%|███ | 90/291 [00:02<00:03, 65.85it/s] Profiling: 34%|███▎ | 98/291 [00:03<00:04, 39.67it/s] Profiling: 36%|███▌ | 104/291 [00:03<00:04, 39.14it/s] Profiling: 41%|████ | 120/291 [00:03<00:02, 59.51it/s] Profiling: 45%|████▌ | 131/291 [00:03<00:02, 67.86it/s] Profiling: 51%|█████ | 147/291 [00:03<00:01, 86.65it/s] Profiling: 54%|█████▍ | 158/291 [00:03<00:01, 90.54it/s] Profiling: 60%|█████▉ | 174/291 [00:03<00:01, 104.89it/s] Profiling: 64%|██████▍ | 186/291 [00:03<00:01, 104.43it/s] Profiling: 69%|██████▉ | 202/291 [00:03<00:00, 118.78it/s] Profiling: 74%|███████▍ | 215/291 [00:05<00:03, 23.48it/s] Profiling: 79%|███████▊ | 229/291 [00:05<00:01, 31.39it/s] Profiling: 82%|████████▏ | 240/291 [00:05<00:01, 37.84it/s] Profiling: 88%|████████▊ | 256/291 [00:05<00:00, 51.08it/s] Profiling: 92%|█████████▏| 268/291 [00:06<00:00, 58.54it/s] Profiling: 97%|█████████▋| 283/291 [00:06<00:00, 70.85it/s] Profiling: 100%|██████████| 291/291 [00:06<00:00, 44.71it/s]
cgato-thespice-7b-invert-9589-v6-mkmlizer: quantized model in 17.736s
cgato-thespice-7b-invert-9589-v6-mkmlizer: Processed model cgato/TheSpice-7b-InvertedInstruct-v0.1.3 in 43.655s
cgato-thespice-7b-invert-9589-v6-mkmlizer: creating bucket guanaco-mkml-models
cgato-thespice-7b-invert-9589-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-thespice-7b-invert-9589-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-thespice-7b-invert-9589-v6
cgato-thespice-7b-invert-9589-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-thespice-7b-invert-9589-v6/config.json
cgato-thespice-7b-invert-9589-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-thespice-7b-invert-9589-v6/special_tokens_map.json
cgato-thespice-7b-invert-9589-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-thespice-7b-invert-9589-v6/tokenizer_config.json
cgato-thespice-7b-invert-9589-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cgato-thespice-7b-invert-9589-v6/tokenizer.model
cgato-thespice-7b-invert-9589-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-thespice-7b-invert-9589-v6/tokenizer.json
cgato-thespice-7b-invert-9589-v6-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/cgato-thespice-7b-invert-9589-v6/mkml_model.tensors
cgato-thespice-7b-invert-9589-v6-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-thespice-7b-invert-9589-v6-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-invert-9589-v6-mkmlizer: warnings.warn(
cgato-thespice-7b-invert-9589-v6-mkmlizer: config.json: 0%| | 0.00/1.05k [00:00<?, ?B/s] config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 8.75MB/s]
cgato-thespice-7b-invert-9589-v6-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-invert-9589-v6-mkmlizer: warnings.warn(
cgato-thespice-7b-invert-9589-v6-mkmlizer: tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 1.99MB/s]
cgato-thespice-7b-invert-9589-v6-mkmlizer: vocab.json: 0%| | 0.00/1.04M [00:00<?, ?B/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 6.94MB/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 6.91MB/s]
cgato-thespice-7b-invert-9589-v6-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 18.0MB/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 17.9MB/s]
cgato-thespice-7b-invert-9589-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-invert-9589-v6-mkmlizer: warnings.warn(
cgato-thespice-7b-invert-9589-v6-mkmlizer: pytorch_model.bin: 0%| | 0.00/1.44G [00:00<?, ?B/s] pytorch_model.bin: 1%| | 10.5M/1.44G [00:02<05:01, 4.76MB/s] pytorch_model.bin: 1%|▏ | 21.0M/1.44G [00:02<02:13, 10.6MB/s] pytorch_model.bin: 2%|▏ | 31.5M/1.44G [00:03<01:54, 12.3MB/s] pytorch_model.bin: 6%|▌ | 83.9M/1.44G [00:03<00:33, 40.6MB/s] pytorch_model.bin: 7%|▋ | 94.4M/1.44G [00:03<00:33, 40.6MB/s] pytorch_model.bin: 12%|█▏ | 178M/1.44G [00:03<00:11, 109MB/s] pytorch_model.bin: 60%|█████▉ | 860M/1.44G [00:03<00:00, 855MB/s] pytorch_model.bin: 81%|████████▏ | 1.17G/1.44G [00:04<00:00, 1.16GB/s] pytorch_model.bin: 99%|█████████▉| 1.43G/1.44G [00:04<00:00, 1.09GB/s] pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:04<00:00, 329MB/s]
cgato-thespice-7b-invert-9589-v6-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-thespice-7b-invert-9589-v6-mkmlizer: Saving duration: 0.239s
cgato-thespice-7b-invert-9589-v6-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 8.511s
cgato-thespice-7b-invert-9589-v6-mkmlizer: creating bucket guanaco-reward-models
cgato-thespice-7b-invert-9589-v6-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-thespice-7b-invert-9589-v6-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-thespice-7b-invert-9589-v6_reward
cgato-thespice-7b-invert-9589-v6-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-thespice-7b-invert-9589-v6_reward/config.json
cgato-thespice-7b-invert-9589-v6-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-thespice-7b-invert-9589-v6_reward/special_tokens_map.json
cgato-thespice-7b-invert-9589-v6-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-thespice-7b-invert-9589-v6_reward/vocab.json
cgato-thespice-7b-invert-9589-v6-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-thespice-7b-invert-9589-v6_reward/tokenizer_config.json
cgato-thespice-7b-invert-9589-v6-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-thespice-7b-invert-9589-v6_reward/tokenizer.json
cgato-thespice-7b-invert-9589-v6-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-thespice-7b-invert-9589-v6_reward/merges.txt
Job cgato-thespice-7b-invert-9589-v6-mkmlizer completed after 103.48s with status: succeeded
Stopping job with name cgato-thespice-7b-invert-9589-v6-mkmlizer
Pipeline stage MKMLizer completed in 124.58s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cgato-thespice-7b-invert-9589-v6
Waiting for inference service cgato-thespice-7b-invert-9589-v6 to be ready
Inference service cgato-thespice-7b-invert-9589-v6 ready after 40.299864292144775s
Pipeline stage ISVCDeployer completed in 47.74s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.598292589187622s
Received healthy response to inference request in 1.172116756439209s
Received healthy response to inference request in 1.177553653717041s
Received healthy response to inference request in 1.0402569770812988s
Received healthy response to inference request in 1.7703266143798828s
5 requests
0 failed requests
5th percentile: 1.0666289329528809
10th percentile: 1.093000888824463
20th percentile: 1.145744800567627
30th percentile: 1.1732041358947753
40th percentile: 1.1753788948059083
50th percentile: 1.177553653717041
60th percentile: 1.3458492279052734
70th percentile: 1.5141448020935058
80th percentile: 1.6326993942260744
90th percentile: 1.7015130043029785
95th percentile: 1.7359198093414305
99th percentile: 1.7634452533721923
mean time: 1.3517093181610107
Pipeline stage StressChecker completed in 7.64s
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 0.05s
M-Eval Dataset for topic stay_in_character is loaded
cgato-thespice-7b-invert_9589_v6 status is now deployed due to DeploymentManager action
cgato-thespice-7b-invert_9589_v6 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cgato-thespice-7b-invert_9589_v6
Running pipeline stage ISVCDeleter
Checking if service cgato-thespice-7b-invert-9589-v6 is running
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Tearing down inference service cgato-thespice-7b-invert-9589-v6
Toredown service cgato-thespice-7b-invert-9589-v6
Pipeline stage ISVCDeleter completed in 4.83s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cgato-thespice-7b-invert-9589-v6/config.json from bucket guanaco-mkml-models
Deleting key cgato-thespice-7b-invert-9589-v6/mkml_model.tensors from bucket guanaco-mkml-models
Deleting key cgato-thespice-7b-invert-9589-v6/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-thespice-7b-invert-9589-v6/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-thespice-7b-invert-9589-v6/tokenizer.model from bucket guanaco-mkml-models
Deleting key cgato-thespice-7b-invert-9589-v6/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cgato-thespice-7b-invert-9589-v6_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-invert-9589-v6_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-invert-9589-v6_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-invert-9589-v6_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-invert-9589-v6_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-invert-9589-v6_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-invert-9589-v6_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.18s
cgato-thespice-7b-invert_9589_v6 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics