submission_id: cgato-thespice-7b-ft-dc1-ot_v2
developer_uid: c.gato
status: torndown
model_repo: cgato/TheSpice-7b-FT-DC1-OT
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, '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': "{bot_name}'s Persona: {memory}\n {bot_name} responds in one.\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: 2024-03-30T20:59:00+00:00
model_name: cgato-thespice-7b-ft-dc1-ot_v2
model_eval_status: success
model_group: cgato/TheSpice-7b-FT-DC1
num_battles: 68624
num_wins: 36853
celo_rating: 1184.28
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-ft-dc1-ot_v2
ineligible_reason: propriety_total_count < 800
language_model: cgato/TheSpice-7b-FT-DC1-OT
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-03-30
win_ratio: 0.5370278619724878
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer
Waiting for job on cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer to finish
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: ║ _____ __ __ ║
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: ║ /___/ ║
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: ║ ║
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: ║ Version: 0.6.11 ║
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: ║ ║
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: ║ belonging to: ║
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: ║ ║
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: ║ Chai Research Corp. ║
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: ║ ║
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 20.5MB/s]
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: README.md: 0%| | 0.00/30.0 [00:00<?, ?B/s] README.md: 100%|██████████| 30.0/30.0 [00:00<00:00, 495kB/s]
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: config.json: 0%| | 0.00/653 [00:00<?, ?B/s] config.json: 100%|██████████| 653/653 [00:00<00:00, 5.35MB/s]
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: generation_config.json: 0%| | 0.00/137 [00:00<?, ?B/s] generation_config.json: 100%|██████████| 137/137 [00:00<00:00, 2.28MB/s]
cgato-thespice-7b-ft-dc1-ot-v2-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, 91.5MB/s] model-00001-of-00003.safetensors: 1%| | 31.5M/4.94G [00:00<00:32, 150MB/s] model-00001-of-00003.safetensors: 3%|▎ | 126M/4.94G [00:00<00:09, 488MB/s] model-00001-of-00003.safetensors: 5%|▌ | 262M/4.94G [00:00<00:05, 820MB/s] model-00001-of-00003.safetensors: 7%|▋ | 357M/4.94G [00:00<00:05, 815MB/s] model-00001-of-00003.safetensors: 9%|▉ | 440M/4.94G [00:00<00:05, 819MB/s] model-00001-of-00003.safetensors: 14%|█▍ | 692M/4.94G [00:00<00:03, 1.33GB/s] model-00001-of-00003.safetensors: 21%|██ | 1.05G/4.94G [00:00<00:01, 2.00GB/s] model-00001-of-00003.safetensors: 28%|██▊ | 1.39G/4.94G [00:00<00:01, 2.43GB/s] model-00001-of-00003.safetensors: 34%|███▍ | 1.68G/4.94G [00:01<00:01, 2.53GB/s] model-00001-of-00003.safetensors: 39%|███▉ | 1.94G/4.94G [00:01<00:01, 2.53GB/s] model-00001-of-00003.safetensors: 46%|████▌ | 2.25G/4.94G [00:01<00:00, 2.71GB/s] model-00001-of-00003.safetensors: 51%|█████ | 2.53G/4.94G [00:01<00:01, 2.26GB/s] model-00001-of-00003.safetensors: 57%|█████▋ | 2.84G/4.94G [00:01<00:00, 2.44GB/s] model-00001-of-00003.safetensors: 63%|██████▎ | 3.10G/4.94G [00:01<00:00, 1.99GB/s] model-00001-of-00003.safetensors: 67%|██████▋ | 3.32G/4.94G [00:01<00:00, 1.82GB/s] model-00001-of-00003.safetensors: 71%|███████▏ | 3.52G/4.94G [00:02<00:00, 1.71GB/s] model-00001-of-00003.safetensors: 75%|███████▌ | 3.71G/4.94G [00:02<00:00, 1.65GB/s] model-00001-of-00003.safetensors: 80%|████████ | 3.96G/4.94G [00:02<00:00, 1.82GB/s] model-00001-of-00003.safetensors: 85%|████████▍ | 4.19G/4.94G [00:02<00:00, 1.91GB/s] model-00001-of-00003.safetensors: 90%|████████▉ | 4.44G/4.94G [00:02<00:00, 2.02GB/s] model-00001-of-00003.safetensors: 94%|█████████▍| 4.65G/4.94G [00:02<00:00, 1.62GB/s] model-00001-of-00003.safetensors: 98%|█████████▊| 4.83G/4.94G [00:02<00:00, 1.54GB/s] model-00001-of-00003.safetensors: 100%|█████████▉| 4.94G/4.94G [00:02<00:00, 1.73GB/s]
cgato-thespice-7b-ft-dc1-ot-v2-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<01:03, 78.5MB/s] model-00002-of-00003.safetensors: 3%|▎ | 147M/5.00G [00:00<00:06, 715MB/s] model-00002-of-00003.safetensors: 6%|▌ | 294M/5.00G [00:00<00:04, 1.01GB/s] model-00002-of-00003.safetensors: 8%|▊ | 409M/5.00G [00:00<00:04, 1.06GB/s] model-00002-of-00003.safetensors: 11%|█ | 545M/5.00G [00:00<00:04, 1.10GB/s] model-00002-of-00003.safetensors: 16%|█▌ | 776M/5.00G [00:00<00:02, 1.47GB/s] model-00002-of-00003.safetensors: 21%|██ | 1.06G/5.00G [00:00<00:02, 1.80GB/s] model-00002-of-00003.safetensors: 26%|██▌ | 1.29G/5.00G [00:00<00:01, 1.93GB/s] model-00002-of-00003.safetensors: 33%|███▎ | 1.66G/5.00G [00:00<00:01, 2.43GB/s] model-00002-of-00003.safetensors: 39%|███▉ | 1.96G/5.00G [00:01<00:01, 2.56GB/s] model-00002-of-00003.safetensors: 44%|████▍ | 2.22G/5.00G [00:01<00:01, 2.00GB/s] model-00002-of-00003.safetensors: 49%|████▉ | 2.44G/5.00G [00:01<00:01, 1.90GB/s] model-00002-of-00003.safetensors: 53%|█████▎ | 2.65G/5.00G [00:01<00:01, 1.90GB/s] model-00002-of-00003.safetensors: 61%|██████▏ | 3.07G/5.00G [00:01<00:00, 2.48GB/s] model-00002-of-00003.safetensors: 67%|██████▋ | 3.34G/5.00G [00:01<00:00, 2.34GB/s] model-00002-of-00003.safetensors: 73%|███████▎ | 3.67G/5.00G [00:01<00:00, 2.54GB/s] model-00002-of-00003.safetensors: 79%|███████▉ | 3.94G/5.00G [00:01<00:00, 2.56GB/s] model-00002-of-00003.safetensors: 84%|████████▍ | 4.22G/5.00G [00:02<00:00, 2.42GB/s] model-00002-of-00003.safetensors: 89%|████████▉ | 4.47G/5.00G [00:02<00:00, 2.17GB/s] model-00002-of-00003.safetensors: 98%|█████████▊| 4.89G/5.00G [00:02<00:00, 2.70GB/s] model-00002-of-00003.safetensors: 100%|█████████▉| 5.00G/5.00G [00:02<00:00, 2.01GB/s]
cgato-thespice-7b-ft-dc1-ot-v2-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<00:54, 83.6MB/s] model-00003-of-00003.safetensors: 3%|▎ | 126M/4.54G [00:00<00:06, 646MB/s] model-00003-of-00003.safetensors: 4%|▍ | 199M/4.54G [00:00<00:06, 670MB/s] model-00003-of-00003.safetensors: 8%|▊ | 357M/4.54G [00:00<00:04, 1.01GB/s] model-00003-of-00003.safetensors: 10%|█ | 472M/4.54G [00:00<00:03, 1.06GB/s] model-00003-of-00003.safetensors: 14%|█▎ | 619M/4.54G [00:00<00:03, 1.19GB/s] model-00003-of-00003.safetensors: 20%|█▉ | 902M/4.54G [00:00<00:02, 1.70GB/s] model-00003-of-00003.safetensors: 27%|██▋ | 1.23G/4.54G [00:00<00:01, 2.14GB/s] model-00003-of-00003.safetensors: 34%|███▍ | 1.56G/4.54G [00:00<00:01, 2.50GB/s] model-00003-of-00003.safetensors: 40%|███▉ | 1.81G/4.54G [00:01<00:01, 2.12GB/s] model-00003-of-00003.safetensors: 45%|████▌ | 2.04G/4.54G [00:01<00:01, 2.03GB/s] model-00003-of-00003.safetensors: 50%|█████ | 2.29G/4.54G [00:01<00:01, 2.11GB/s] model-00003-of-00003.safetensors: 55%|█████▌ | 2.51G/4.54G [00:01<00:00, 2.04GB/s] model-00003-of-00003.safetensors: 60%|█████▉ | 2.72G/4.54G [00:01<00:00, 2.05GB/s] model-00003-of-00003.safetensors: 69%|██████▊ | 3.11G/4.54G [00:01<00:00, 2.57GB/s] model-00003-of-00003.safetensors: 74%|███████▍ | 3.38G/4.54G [00:01<00:00, 2.43GB/s] model-00003-of-00003.safetensors: 81%|████████ | 3.68G/4.54G [00:01<00:00, 2.46GB/s] model-00003-of-00003.safetensors: 87%|████████▋ | 3.93G/4.54G [00:02<00:00, 2.44GB/s] model-00003-of-00003.safetensors: 94%|█████████▍| 4.27G/4.54G [00:02<00:00, 2.05GB/s] model-00003-of-00003.safetensors: 99%|█████████▉| 4.49G/4.54G [00:02<00:00, 1.65GB/s] model-00003-of-00003.safetensors: 100%|█████████▉| 4.54G/4.54G [00:02<00:00, 1.84GB/s]
cgato-thespice-7b-ft-dc1-ot-v2-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, 117MB/s]
cgato-thespice-7b-ft-dc1-ot-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, 3.41MB/s]
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: tokenizer.model: 0%| | 0.00/493k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 18.9MB/s]
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: tokenizer_config.json: 0%| | 0.00/982 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 982/982 [00:00<00:00, 8.55MB/s]
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: Downloaded to shared memory in 9.368s
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: Saving mkml model at /dev/shm/model_cache
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: Reading /tmp/tmpuhyk5bzq/model.safetensors.index.json
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: Profiling: 0%| | 0/291 [00:00<?, ?it/s] Profiling: 0%| | 1/291 [00:01<07:04, 1.46s/it] Profiling: 7%|▋ | 20/291 [00:01<00:15, 17.41it/s] Profiling: 14%|█▍ | 41/291 [00:01<00:06, 38.87it/s] Profiling: 22%|██▏ | 64/291 [00:01<00:03, 64.19it/s] Profiling: 30%|██▉ | 86/291 [00:01<00:02, 89.15it/s] Profiling: 36%|███▌ | 105/291 [00:02<00:02, 77.93it/s] Profiling: 44%|████▍ | 129/291 [00:02<00:01, 103.59it/s] Profiling: 51%|█████ | 148/291 [00:02<00:01, 118.74it/s] Profiling: 58%|█████▊ | 168/291 [00:02<00:00, 135.72it/s] Profiling: 66%|██████▌ | 192/291 [00:02<00:00, 157.97it/s] Profiling: 73%|███████▎ | 212/291 [00:04<00:02, 37.91it/s] Profiling: 79%|███████▉ | 231/291 [00:04<00:01, 48.69it/s] Profiling: 88%|████████▊ | 256/291 [00:04<00:00, 67.19it/s] Profiling: 95%|█████████▍| 275/291 [00:04<00:00, 81.62it/s] Profiling: 100%|██████████| 291/291 [00:04<00:00, 62.28it/s]
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: quantized model in 14.701s
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: Processed model cgato/TheSpice-7b-FT-DC1-OT in 24.931s
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: creating bucket guanaco-mkml-models
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-thespice-7b-ft-dc1-ot-v2
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-thespice-7b-ft-dc1-ot-v2/tokenizer_config.json
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-thespice-7b-ft-dc1-ot-v2/config.json
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-thespice-7b-ft-dc1-ot-v2/special_tokens_map.json
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cgato-thespice-7b-ft-dc1-ot-v2/tokenizer.model
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-thespice-7b-ft-dc1-ot-v2/tokenizer.json
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/cgato-thespice-7b-ft-dc1-ot-v2/mkml_model.tensors
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-thespice-7b-ft-dc1-ot-v2-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-dc1-ot-v2-mkmlizer: warnings.warn(
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: config.json: 0%| | 0.00/1.05k [00:00<?, ?B/s] config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 9.46MB/s]
cgato-thespice-7b-ft-dc1-ot-v2-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-dc1-ot-v2-mkmlizer: warnings.warn(
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 1.53MB/s]
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: pytorch_model.bin: 0%| | 0.00/1.44G [00:00<?, ?B/s] pytorch_model.bin: 1%| | 10.5M/1.44G [00:00<00:29, 47.9MB/s] pytorch_model.bin: 2%|▏ | 31.5M/1.44G [00:00<00:15, 92.0MB/s] pytorch_model.bin: 9%|▉ | 136M/1.44G [00:00<00:03, 394MB/s] pytorch_model.bin: 17%|█▋ | 252M/1.44G [00:00<00:03, 357MB/s] pytorch_model.bin: 21%|██ | 304M/1.44G [00:00<00:03, 379MB/s] pytorch_model.bin: 25%|██▍ | 357M/1.44G [00:01<00:02, 368MB/s] pytorch_model.bin: 28%|██▊ | 398M/1.44G [00:01<00:02, 379MB/s] pytorch_model.bin: 44%|████▍ | 640M/1.44G [00:01<00:00, 838MB/s] pytorch_model.bin: 93%|█████████▎| 1.34G/1.44G [00:01<00:00, 2.32GB/s] pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:01<00:00, 1.01GB/s]
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: Saving duration: 0.221s
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.719s
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: creating bucket guanaco-reward-models
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-thespice-7b-ft-dc1-ot-v2_reward
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-thespice-7b-ft-dc1-ot-v2_reward/config.json
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-thespice-7b-ft-dc1-ot-v2_reward/special_tokens_map.json
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-thespice-7b-ft-dc1-ot-v2_reward/merges.txt
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-thespice-7b-ft-dc1-ot-v2_reward/tokenizer_config.json
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-thespice-7b-ft-dc1-ot-v2_reward/vocab.json
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-thespice-7b-ft-dc1-ot-v2_reward/tokenizer.json
cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-thespice-7b-ft-dc1-ot-v2_reward/reward.tensors
Job cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer completed after 53.64s with status: succeeded
Stopping job with name cgato-thespice-7b-ft-dc1-ot-v2-mkmlizer
Pipeline stage MKMLizer completed in 59.55s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service cgato-thespice-7b-ft-dc1-ot-v2
Waiting for inference service cgato-thespice-7b-ft-dc1-ot-v2 to be ready
Exception raised while processing tagging_function
Traceback (most recent call last): File "/code/guanaco/guanaco_services/src/guanaco_model_service/chat_api.py", line 274, in resolve_chat_api conversation_tag = self.tagging_function(conversation_state) File "/home/zongyi/gitlab/zztools/zztools/llm/guanaco/submit_routing_model.py", line 176, in last_user_message_length TypeError: 'ConversationMessage' object is not subscriptable
Inference service cgato-thespice-7b-ft-dc1-ot-v2 ready after 30.187192678451538s
Pipeline stage ISVCDeployer completed in 38.13s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.710951566696167s
Received healthy response to inference request in 1.1736969947814941s
Received healthy response to inference request in 1.4905903339385986s
Received healthy response to inference request in 1.1815319061279297s
Received healthy response to inference request in 1.1473281383514404s
5 requests
0 failed requests
5th percentile: 1.1526019096374511
10th percentile: 1.1578756809234618
20th percentile: 1.1684232234954834
30th percentile: 1.1752639770507813
40th percentile: 1.1783979415893555
50th percentile: 1.1815319061279297
60th percentile: 1.3051552772521973
70th percentile: 1.4287786483764648
80th percentile: 1.5346625804901124
90th percentile: 1.6228070735931397
95th percentile: 1.6668793201446532
99th percentile: 1.7021371173858642
mean time: 1.340819787979126
Pipeline stage StressChecker completed in 7.63s
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-dc1-ot_v2 status is now deployed due to DeploymentManager action
cgato-thespice-7b-ft-dc1-ot_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cgato-thespice-7b-ft-dc1-ot_v2
Running pipeline stage ISVCDeleter
Checking if service cgato-thespice-7b-ft-dc1-ot-v2 is running
Tearing down inference service cgato-thespice-7b-ft-dc1-ot-v2
Toredown service cgato-thespice-7b-ft-dc1-ot-v2
Pipeline stage ISVCDeleter completed in 4.35s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cgato-thespice-7b-ft-dc1-ot-v2/config.json from bucket guanaco-mkml-models
Deleting key cgato-thespice-7b-ft-dc1-ot-v2/mkml_model.tensors from bucket guanaco-mkml-models
Deleting key cgato-thespice-7b-ft-dc1-ot-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-thespice-7b-ft-dc1-ot-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-thespice-7b-ft-dc1-ot-v2/tokenizer.model from bucket guanaco-mkml-models
Deleting key cgato-thespice-7b-ft-dc1-ot-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cgato-thespice-7b-ft-dc1-ot-v2_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-ft-dc1-ot-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-ft-dc1-ot-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-ft-dc1-ot-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-ft-dc1-ot-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-ft-dc1-ot-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-ft-dc1-ot-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.41s
cgato-thespice-7b-ft-dc1-ot_v2 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics