submission_id: cgato-thespice-7b-ft-v0-3-1_v5
developer_uid: c.gato
status: torndown
model_repo: cgato/TheSpice-7b-FT-v0.3.1
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.7, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 100, 'presence_penalty': 0.9, 'frequency_penalty': 0.7, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\nGive short one line 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}
reward_formatter: {'memory_template': "{bot_name}'s Persona: {memory}\nGive short one line 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: 2024-04-05T18:14:41+00:00
model_name: cgato-thespice-7b-ft-v0-3-1_v5
model_eval_status: success
model_group: cgato/TheSpice-7b-FT-v0.
num_battles: 162031
num_wins: 82480
celo_rating: 1165.66
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: MistralForCausalLM
model_num_parameters: 7241732096.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
display_name: cgato-thespice-7b-ft-v0-3-1_v5
ineligible_reason: propriety_total_count < 800
language_model: cgato/TheSpice-7b-FT-v0.3.1
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-05
win_ratio: 0.5090383938875894
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer
Waiting for job on cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer to finish
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: ║ _____ __ __ ║
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: ║ /___/ ║
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: ║ ║
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: ║ Version: 0.6.11 ║
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: ║ ║
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: ║ belonging to: ║
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: ║ ║
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: ║ Chai Research Corp. ║
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: ║ ║
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 19.6MB/s]
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: README.md: 0%| | 0.00/2.46k [00:00<?, ?B/s] README.md: 100%|██████████| 2.46k/2.46k [00:00<00:00, 19.9MB/s]
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: config.json: 0%| | 0.00/653 [00:00<?, ?B/s] config.json: 100%|██████████| 653/653 [00:00<00:00, 8.78MB/s]
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: generation_config.json: 0%| | 0.00/137 [00:00<?, ?B/s] generation_config.json: 100%|██████████| 137/137 [00:00<00:00, 1.85MB/s]
cgato-thespice-7b-ft-v0-3-1-v5-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<01:29, 55.4MB/s] model-00001-of-00003.safetensors: 1%| | 41.9M/4.94G [00:00<00:29, 165MB/s] model-00001-of-00003.safetensors: 3%|▎ | 147M/4.94G [00:00<00:09, 498MB/s] model-00001-of-00003.safetensors: 4%|▍ | 210M/4.94G [00:00<00:09, 509MB/s] model-00001-of-00003.safetensors: 7%|▋ | 336M/4.94G [00:00<00:06, 722MB/s] model-00001-of-00003.safetensors: 8%|▊ | 419M/4.94G [00:00<00:06, 648MB/s] model-00001-of-00003.safetensors: 12%|█▏ | 577M/4.94G [00:00<00:04, 889MB/s] model-00001-of-00003.safetensors: 15%|█▌ | 744M/4.94G [00:00<00:03, 1.10GB/s] model-00001-of-00003.safetensors: 25%|██▍ | 1.23G/4.94G [00:01<00:01, 2.14GB/s] model-00001-of-00003.safetensors: 29%|██▉ | 1.46G/4.94G [00:01<00:01, 2.09GB/s] model-00001-of-00003.safetensors: 34%|███▍ | 1.68G/4.94G [00:01<00:01, 1.91GB/s] model-00001-of-00003.safetensors: 38%|███▊ | 1.89G/4.94G [00:01<00:01, 1.67GB/s] model-00001-of-00003.safetensors: 42%|████▏ | 2.07G/4.94G [00:01<00:01, 1.60GB/s] model-00001-of-00003.safetensors: 47%|████▋ | 2.32G/4.94G [00:01<00:01, 1.82GB/s] model-00001-of-00003.safetensors: 55%|█████▌ | 2.73G/4.94G [00:01<00:00, 2.35GB/s] model-00001-of-00003.safetensors: 60%|██████ | 2.98G/4.94G [00:01<00:00, 2.12GB/s] model-00001-of-00003.safetensors: 65%|██████▍ | 3.21G/4.94G [00:02<00:00, 1.94GB/s] model-00001-of-00003.safetensors: 69%|██████▉ | 3.42G/4.94G [00:02<00:00, 1.73GB/s] model-00001-of-00003.safetensors: 76%|███████▋ | 3.77G/4.94G [00:02<00:00, 2.15GB/s] model-00001-of-00003.safetensors: 82%|████████▏ | 4.07G/4.94G [00:02<00:00, 2.28GB/s] model-00001-of-00003.safetensors: 87%|████████▋ | 4.32G/4.94G [00:02<00:00, 2.34GB/s] model-00001-of-00003.safetensors: 92%|█████████▏| 4.57G/4.94G [00:02<00:00, 2.31GB/s] model-00001-of-00003.safetensors: 100%|█████████▉| 4.94G/4.94G [00:05<00:00, 918MB/s]
cgato-thespice-7b-ft-v0-3-1-v5-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<02:01, 41.0MB/s] model-00002-of-00003.safetensors: 2%|▏ | 83.9M/5.00G [00:00<00:17, 280MB/s] model-00002-of-00003.safetensors: 3%|▎ | 126M/5.00G [00:00<00:15, 317MB/s] model-00002-of-00003.safetensors: 3%|▎ | 168M/5.00G [00:00<00:14, 332MB/s] model-00002-of-00003.safetensors: 8%|▊ | 388M/5.00G [00:00<00:05, 875MB/s] model-00002-of-00003.safetensors: 16%|█▌ | 807M/5.00G [00:00<00:02, 1.81GB/s] model-00002-of-00003.safetensors: 24%|██▍ | 1.20G/5.00G [00:00<00:01, 2.34GB/s] model-00002-of-00003.safetensors: 29%|██▉ | 1.45G/5.00G [00:01<00:01, 2.39GB/s] model-00002-of-00003.safetensors: 34%|███▍ | 1.70G/5.00G [00:01<00:01, 2.17GB/s] model-00002-of-00003.safetensors: 39%|███▉ | 1.96G/5.00G [00:01<00:01, 2.28GB/s] model-00002-of-00003.safetensors: 45%|████▌ | 2.25G/5.00G [00:01<00:01, 2.44GB/s] model-00002-of-00003.safetensors: 50%|█████ | 2.51G/5.00G [00:01<00:01, 2.32GB/s] model-00002-of-00003.safetensors: 55%|█████▌ | 2.76G/5.00G [00:01<00:00, 2.32GB/s] model-00002-of-00003.safetensors: 60%|█████▉ | 3.00G/5.00G [00:01<00:00, 2.35GB/s] model-00002-of-00003.safetensors: 65%|██████▍ | 3.24G/5.00G [00:01<00:00, 2.35GB/s] model-00002-of-00003.safetensors: 70%|███████ | 3.51G/5.00G [00:01<00:00, 2.44GB/s] model-00002-of-00003.safetensors: 75%|███████▌ | 3.76G/5.00G [00:02<00:00, 2.19GB/s] model-00002-of-00003.safetensors: 80%|███████▉ | 4.00G/5.00G [00:02<00:00, 2.22GB/s] model-00002-of-00003.safetensors: 85%|████████▍ | 4.23G/5.00G [00:02<00:00, 1.87GB/s] model-00002-of-00003.safetensors: 94%|█████████▍| 4.70G/5.00G [00:02<00:00, 2.53GB/s] model-00002-of-00003.safetensors: 100%|█████████▉| 5.00G/5.00G [00:02<00:00, 1.98GB/s]
cgato-thespice-7b-ft-v0-3-1-v5-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 [00:00<02:24, 31.3MB/s] model-00003-of-00003.safetensors: 2%|▏ | 94.4M/4.54G [00:00<00:19, 229MB/s] model-00003-of-00003.safetensors: 5%|▍ | 220M/4.54G [00:00<00:09, 480MB/s] model-00003-of-00003.safetensors: 9%|▉ | 419M/4.54G [00:00<00:04, 877MB/s] model-00003-of-00003.safetensors: 16%|█▌ | 734M/4.54G [00:00<00:02, 1.47GB/s] model-00003-of-00003.safetensors: 22%|██▏ | 1.02G/4.54G [00:00<00:01, 1.84GB/s] model-00003-of-00003.safetensors: 27%|██▋ | 1.24G/4.54G [00:01<00:01, 1.72GB/s] model-00003-of-00003.safetensors: 32%|███▏ | 1.44G/4.54G [00:01<00:01, 1.68GB/s] model-00003-of-00003.safetensors: 37%|███▋ | 1.70G/4.54G [00:01<00:01, 1.84GB/s] model-00003-of-00003.safetensors: 44%|████▍ | 2.01G/4.54G [00:01<00:01, 2.19GB/s] model-00003-of-00003.safetensors: 51%|█████ | 2.30G/4.54G [00:01<00:00, 2.36GB/s] model-00003-of-00003.safetensors: 56%|█████▌ | 2.55G/4.54G [00:01<00:00, 2.38GB/s] model-00003-of-00003.safetensors: 62%|██████▏ | 2.80G/4.54G [00:01<00:00, 2.37GB/s] model-00003-of-00003.safetensors: 68%|██████▊ | 3.09G/4.54G [00:01<00:00, 2.50GB/s] model-00003-of-00003.safetensors: 74%|███████▍ | 3.36G/4.54G [00:01<00:00, 2.36GB/s] model-00003-of-00003.safetensors: 79%|███████▉ | 3.60G/4.54G [00:02<00:00, 2.08GB/s] model-00003-of-00003.safetensors: 85%|████████▌ | 3.88G/4.54G [00:02<00:00, 2.27GB/s] model-00003-of-00003.safetensors: 93%|█████████▎| 4.23G/4.54G [00:02<00:00, 2.46GB/s] model-00003-of-00003.safetensors: 99%|█████████▊| 4.48G/4.54G [00:02<00:00, 2.12GB/s] model-00003-of-00003.safetensors: 100%|█████████▉| 4.54G/4.54G [00:02<00:00, 1.79GB/s]
cgato-thespice-7b-ft-v0-3-1-v5-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, 139MB/s]
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: special_tokens_map.json: 0%| | 0.00/437 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 437/437 [00:00<00:00, 5.54MB/s]
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: tokenizer.model: 0%| | 0.00/493k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 47.6MB/s]
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: tokenizer_config.json: 0%| | 0.00/982 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 982/982 [00:00<00:00, 10.6MB/s]
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: Downloaded to shared memory in 12.483s
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: Saving mkml model at /dev/shm/model_cache
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: Reading /tmp/tmpgn7x3a51/model.safetensors.index.json
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: Profiling: 0%| | 0/291 [00:00<?, ?it/s] Profiling: 0%| | 1/291 [00:01<06:52, 1.42s/it] Profiling: 7%|▋ | 20/291 [00:01<00:15, 17.80it/s] Profiling: 13%|█▎ | 38/291 [00:01<00:07, 36.04it/s] Profiling: 20%|██ | 59/291 [00:01<00:03, 60.10it/s] Profiling: 27%|██▋ | 78/291 [00:01<00:02, 81.46it/s] Profiling: 33%|███▎ | 96/291 [00:02<00:02, 89.55it/s] Profiling: 38%|███▊ | 112/291 [00:02<00:02, 68.91it/s] Profiling: 45%|████▌ | 131/291 [00:02<00:01, 87.59it/s] Profiling: 54%|█████▎ | 156/291 [00:02<00:01, 115.07it/s] Profiling: 60%|█████▉ | 174/291 [00:02<00:00, 126.30it/s] Profiling: 66%|██████▌ | 192/291 [00:02<00:00, 137.02it/s] Profiling: 72%|███████▏ | 209/291 [00:04<00:02, 32.95it/s] Profiling: 79%|███████▊ | 229/291 [00:04<00:01, 44.88it/s] Profiling: 85%|████████▌ | 248/291 [00:04<00:00, 58.22it/s] Profiling: 92%|█████████▏| 268/291 [00:04<00:00, 74.81it/s] Profiling: 100%|█████████▉| 290/291 [00:04<00:00, 95.49it/s] Profiling: 100%|██████████| 291/291 [00:04<00:00, 59.07it/s]
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: quantized model in 15.079s
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: Processed model cgato/TheSpice-7b-FT-v0.3.1 in 28.514s
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: creating bucket guanaco-mkml-models
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-thespice-7b-ft-v0-3-1-v5
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-thespice-7b-ft-v0-3-1-v5/tokenizer_config.json
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-thespice-7b-ft-v0-3-1-v5/special_tokens_map.json
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-thespice-7b-ft-v0-3-1-v5/config.json
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cgato-thespice-7b-ft-v0-3-1-v5/tokenizer.model
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-thespice-7b-ft-v0-3-1-v5/tokenizer.json
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-thespice-7b-ft-v0-3-1-v5-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-ft-v0-3-1-v5-mkmlizer: warnings.warn(
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: config.json: 0%| | 0.00/1.05k [00:00<?, ?B/s] config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 12.6MB/s]
cgato-thespice-7b-ft-v0-3-1-v5-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-ft-v0-3-1-v5-mkmlizer: warnings.warn(
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 3.44MB/s]
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: vocab.json: 0%| | 0.00/1.04M [00:00<?, ?B/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 16.9MB/s]
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 2.45MB/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 2.45MB/s]
cgato-thespice-7b-ft-v0-3-1-v5-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-ft-v0-3-1-v5-mkmlizer: warnings.warn(
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: pytorch_model.bin: 0%| | 0.00/1.44G [00:00<?, ?B/s] pytorch_model.bin: 1%| | 10.5M/1.44G [00:00<00:26, 53.3MB/s] pytorch_model.bin: 7%|▋ | 94.4M/1.44G [00:00<00:03, 364MB/s] pytorch_model.bin: 16%|█▌ | 231M/1.44G [00:00<00:01, 618MB/s] pytorch_model.bin: 21%|██ | 304M/1.44G [00:00<00:02, 500MB/s] pytorch_model.bin: 25%|██▌ | 367M/1.44G [00:00<00:02, 443MB/s] pytorch_model.bin: 33%|███▎ | 472M/1.44G [00:00<00:01, 566MB/s] pytorch_model.bin: 54%|█████▎ | 776M/1.44G [00:01<00:00, 1.16GB/s] pytorch_model.bin: 96%|█████████▌| 1.38G/1.44G [00:01<00:00, 2.42GB/s] pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:15<00:00, 2.42GB/s] pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:15<00:00, 95.3MB/s]
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: Saving duration: 0.236s
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 19.392s
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: creating bucket guanaco-reward-models
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-thespice-7b-ft-v0-3-1-v5_reward
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-thespice-7b-ft-v0-3-1-v5_reward/config.json
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-thespice-7b-ft-v0-3-1-v5_reward/tokenizer_config.json
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-thespice-7b-ft-v0-3-1-v5_reward/merges.txt
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-thespice-7b-ft-v0-3-1-v5_reward/vocab.json
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-thespice-7b-ft-v0-3-1-v5_reward/special_tokens_map.json
cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-thespice-7b-ft-v0-3-1-v5_reward/tokenizer.json
Job cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer completed after 77.17s with status: succeeded
Stopping job with name cgato-thespice-7b-ft-v0-3-1-v5-mkmlizer
Pipeline stage MKMLizer completed in 82.71s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cgato-thespice-7b-ft-v0-3-1-v5
Waiting for inference service cgato-thespice-7b-ft-v0-3-1-v5 to be ready
Inference service cgato-thespice-7b-ft-v0-3-1-v5 ready after 40.275166034698486s
Pipeline stage ISVCDeployer completed in 48.14s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.3616230487823486s
Received healthy response to inference request in 1.085942268371582s
Received healthy response to inference request in 1.161088228225708s
Received healthy response to inference request in 0.8651604652404785s
Received healthy response to inference request in 0.8321266174316406s
5 requests
0 failed requests
5th percentile: 0.8387333869934082
10th percentile: 0.8453401565551758
20th percentile: 0.858553695678711
30th percentile: 0.9093168258666993
40th percentile: 0.9976295471191406
50th percentile: 1.085942268371582
60th percentile: 1.1160006523132324
70th percentile: 1.1460590362548828
80th percentile: 1.201195192337036
90th percentile: 1.2814091205596925
95th percentile: 1.3215160846710206
99th percentile: 1.353601655960083
mean time: 1.0611881256103515
Pipeline stage StressChecker completed in 6.20s
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-ft-v0-3-1_v5 status is now deployed due to DeploymentManager action
cgato-thespice-7b-ft-v0-3-1_v5 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cgato-thespice-7b-ft-v0-3-1_v5
Running pipeline stage ISVCDeleter
Checking if service cgato-thespice-7b-ft-v0-3-1-v5 is running
Tearing down inference service cgato-thespice-7b-ft-v0-3-1-v5
Toredown service cgato-thespice-7b-ft-v0-3-1-v5
Pipeline stage ISVCDeleter completed in 3.75s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cgato-thespice-7b-ft-v0-3-1-v5/config.json from bucket guanaco-mkml-models
Deleting key cgato-thespice-7b-ft-v0-3-1-v5/mkml_model.tensors from bucket guanaco-mkml-models
Deleting key cgato-thespice-7b-ft-v0-3-1-v5/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-thespice-7b-ft-v0-3-1-v5/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-thespice-7b-ft-v0-3-1-v5/tokenizer.model from bucket guanaco-mkml-models
Deleting key cgato-thespice-7b-ft-v0-3-1-v5/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cgato-thespice-7b-ft-v0-3-1-v5_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-ft-v0-3-1-v5_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-ft-v0-3-1-v5_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-ft-v0-3-1-v5_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-ft-v0-3-1-v5_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-ft-v0-3-1-v5_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-ft-v0-3-1-v5_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 16.25s
cgato-thespice-7b-ft-v0-3-1_v5 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics