submission_id: cgato-thespice-7b-ft-dc1_2900_v2
developer_uid: c.gato
status: inactive
model_repo: cgato/TheSpice-7b-FT-DC1-OT-2Epoch
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': "{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}:'}
reward_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}:'}
timestamp: 2024-03-30T21:00:04+00:00
model_name: cgato-thespice-7b-ft-dc1_2900_v2
model_eval_status: success
safety_score: 0.81
entertaining: 6.9
stay_in_character: 8.54
user_preference: 7.18
double_thumbs_up: 250
thumbs_up: 332
thumbs_down: 148
num_battles: 28342
num_wins: 14735
win_ratio: 0.5198997953567144
celo_rating: 1172.02
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer
Waiting for job on cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer to finish
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: ║ _____ __ __ ║
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: ║ /___/ ║
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: ║ ║
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: ║ Version: 0.6.11 ║
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: ║ ║
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: ║ belonging to: ║
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: ║ ║
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: ║ Chai Research Corp. ║
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: ║ ║
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 20.2MB/s]
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: README.md: 0%| | 0.00/30.0 [00:00<?, ?B/s] README.md: 100%|██████████| 30.0/30.0 [00:00<00:00, 411kB/s]
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: config.json: 0%| | 0.00/653 [00:00<?, ?B/s] config.json: 100%|██████████| 653/653 [00:00<00:00, 10.7MB/s]
cgato-thespice-7b-ft-dc1-2900-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-dc1-2900-v2-mkmlizer: model-00001-of-00003.safetensors: 0%| | 0.00/4.94G [00:00<?, ?B/s] model-00001-of-00003.safetensors: 0%| | 21.0M/4.94G [00:00<00:27, 178MB/s] model-00001-of-00003.safetensors: 3%|▎ | 147M/4.94G [00:00<00:06, 689MB/s] model-00001-of-00003.safetensors: 5%|▍ | 231M/4.94G [00:00<00:06, 723MB/s] model-00001-of-00003.safetensors: 6%|▋ | 315M/4.94G [00:00<00:06, 764MB/s] model-00001-of-00003.safetensors: 8%|▊ | 398M/4.94G [00:00<00:06, 713MB/s] model-00001-of-00003.safetensors: 10%|▉ | 472M/4.94G [00:00<00:06, 663MB/s] model-00001-of-00003.safetensors: 13%|█▎ | 661M/4.94G [00:00<00:04, 1.01GB/s] model-00001-of-00003.safetensors: 16%|█▌ | 776M/4.94G [00:00<00:03, 1.04GB/s] model-00001-of-00003.safetensors: 21%|██▏ | 1.06G/4.94G [00:01<00:02, 1.56GB/s] model-00001-of-00003.safetensors: 28%|██▊ | 1.41G/4.94G [00:01<00:01, 2.10GB/s] model-00001-of-00003.safetensors: 33%|███▎ | 1.63G/4.94G [00:01<00:01, 1.76GB/s] model-00001-of-00003.safetensors: 38%|███▊ | 1.90G/4.94G [00:01<00:01, 1.99GB/s] model-00001-of-00003.safetensors: 43%|████▎ | 2.12G/4.94G [00:01<00:01, 1.85GB/s] model-00001-of-00003.safetensors: 47%|████▋ | 2.34G/4.94G [00:01<00:01, 1.92GB/s] model-00001-of-00003.safetensors: 52%|█████▏ | 2.55G/4.94G [00:01<00:01, 1.80GB/s] model-00001-of-00003.safetensors: 60%|█████▉ | 2.95G/4.94G [00:01<00:00, 2.31GB/s] model-00001-of-00003.safetensors: 64%|██████▍ | 3.19G/4.94G [00:01<00:00, 2.27GB/s] model-00001-of-00003.safetensors: 71%|███████ | 3.50G/4.94G [00:02<00:00, 2.48GB/s] model-00001-of-00003.safetensors: 76%|███████▌ | 3.76G/4.94G [00:02<00:00, 2.10GB/s] model-00001-of-00003.safetensors: 83%|████████▎ | 4.09G/4.94G [00:02<00:00, 2.38GB/s] model-00001-of-00003.safetensors: 88%|████████▊ | 4.35G/4.94G [00:02<00:00, 2.28GB/s] model-00001-of-00003.safetensors: 93%|█████████▎| 4.59G/4.94G [00:02<00:00, 1.34GB/s] model-00001-of-00003.safetensors: 97%|█████████▋| 4.78G/4.94G [00:03<00:00, 1.34GB/s] model-00001-of-00003.safetensors: 100%|█████████▉| 4.94G/4.94G [00:05<00:00, 961MB/s]
cgato-thespice-7b-ft-dc1-2900-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<01:06, 75.1MB/s] model-00002-of-00003.safetensors: 3%|▎ | 126M/5.00G [00:00<00:07, 618MB/s] model-00002-of-00003.safetensors: 4%|▍ | 199M/5.00G [00:00<00:08, 562MB/s] model-00002-of-00003.safetensors: 7%|▋ | 325M/5.00G [00:00<00:05, 790MB/s] model-00002-of-00003.safetensors: 8%|▊ | 419M/5.00G [00:00<00:06, 759MB/s] model-00002-of-00003.safetensors: 15%|█▍ | 734M/5.00G [00:00<00:02, 1.46GB/s] model-00002-of-00003.safetensors: 23%|██▎ | 1.17G/5.00G [00:00<00:01, 2.33GB/s] model-00002-of-00003.safetensors: 29%|██▉ | 1.45G/5.00G [00:00<00:01, 2.37GB/s] model-00002-of-00003.safetensors: 34%|███▍ | 1.70G/5.00G [00:01<00:01, 2.01GB/s] model-00002-of-00003.safetensors: 39%|███▉ | 1.94G/5.00G [00:01<00:01, 2.07GB/s] model-00002-of-00003.safetensors: 45%|████▍ | 2.24G/5.00G [00:01<00:01, 2.32GB/s] model-00002-of-00003.safetensors: 52%|█████▏ | 2.61G/5.00G [00:01<00:00, 2.64GB/s] model-00002-of-00003.safetensors: 58%|█████▊ | 2.89G/5.00G [00:01<00:00, 2.16GB/s] model-00002-of-00003.safetensors: 63%|██████▎ | 3.14G/5.00G [00:02<00:01, 1.27GB/s] model-00002-of-00003.safetensors: 66%|██████▋ | 3.32G/5.00G [00:02<00:01, 1.05GB/s] model-00002-of-00003.safetensors: 70%|██████▉ | 3.48G/5.00G [00:02<00:01, 1.06GB/s] model-00002-of-00003.safetensors: 72%|███████▏ | 3.62G/5.00G [00:02<00:01, 1.07GB/s] model-00002-of-00003.safetensors: 76%|███████▌ | 3.77G/5.00G [00:02<00:01, 1.16GB/s] model-00002-of-00003.safetensors: 78%|███████▊ | 3.92G/5.00G [00:02<00:00, 1.14GB/s] model-00002-of-00003.safetensors: 81%|████████ | 4.06G/5.00G [00:02<00:00, 1.18GB/s] model-00002-of-00003.safetensors: 84%|████████▍ | 4.19G/5.00G [00:03<00:01, 615MB/s] model-00002-of-00003.safetensors: 86%|████████▌ | 4.30G/5.00G [00:03<00:01, 641MB/s] model-00002-of-00003.safetensors: 88%|████████▊ | 4.40G/5.00G [00:03<00:00, 707MB/s] model-00002-of-00003.safetensors: 90%|█████████ | 4.52G/5.00G [00:03<00:00, 785MB/s] model-00002-of-00003.safetensors: 93%|█████████▎| 4.64G/5.00G [00:03<00:00, 875MB/s] model-00002-of-00003.safetensors: 100%|█████████▉| 5.00G/5.00G [00:03<00:00, 1.26GB/s]
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: model-00003-of-00003.safetensors: 0%| | 0.00/4.54G [00:00<?, ?B/s] model-00003-of-00003.safetensors: 0%| | 21.0M/4.54G [00:00<00:43, 103MB/s] model-00003-of-00003.safetensors: 3%|▎ | 136M/4.54G [00:00<00:08, 531MB/s] model-00003-of-00003.safetensors: 5%|▍ | 210M/4.54G [00:00<00:07, 598MB/s] model-00003-of-00003.safetensors: 6%|▋ | 294M/4.54G [00:00<00:06, 650MB/s] model-00003-of-00003.safetensors: 8%|▊ | 367M/4.54G [00:00<00:07, 592MB/s] model-00003-of-00003.safetensors: 12%|█▏ | 535M/4.54G [00:00<00:04, 892MB/s] model-00003-of-00003.safetensors: 19%|█▉ | 860M/4.54G [00:00<00:02, 1.57GB/s] model-00003-of-00003.safetensors: 28%|██▊ | 1.29G/4.54G [00:00<00:01, 2.35GB/s] model-00003-of-00003.safetensors: 34%|███▍ | 1.55G/4.54G [00:01<00:01, 2.30GB/s] model-00003-of-00003.safetensors: 40%|███▉ | 1.80G/4.54G [00:01<00:01, 2.26GB/s] model-00003-of-00003.safetensors: 48%|████▊ | 2.20G/4.54G [00:01<00:00, 2.74GB/s] model-00003-of-00003.safetensors: 55%|█████▍ | 2.50G/4.54G [00:01<00:00, 2.11GB/s] model-00003-of-00003.safetensors: 60%|██████ | 2.74G/4.54G [00:01<00:00, 2.16GB/s] model-00003-of-00003.safetensors: 66%|██████▌ | 2.98G/4.54G [00:01<00:00, 1.62GB/s] model-00003-of-00003.safetensors: 70%|██████▉ | 3.18G/4.54G [00:02<00:01, 1.20GB/s] model-00003-of-00003.safetensors: 73%|███████▎ | 3.33G/4.54G [00:02<00:01, 1.00GB/s] model-00003-of-00003.safetensors: 76%|███████▋ | 3.47G/4.54G [00:02<00:01, 844MB/s] model-00003-of-00003.safetensors: 79%|███████▉ | 3.59G/4.54G [00:02<00:01, 756MB/s] model-00003-of-00003.safetensors: 81%|████████ | 3.68G/4.54G [00:03<00:01, 478MB/s] model-00003-of-00003.safetensors: 84%|████████▍ | 3.82G/4.54G [00:03<00:01, 586MB/s] model-00003-of-00003.safetensors: 86%|████████▌ | 3.91G/4.54G [00:03<00:01, 554MB/s] model-00003-of-00003.safetensors: 88%|████████▊ | 4.02G/4.54G [00:03<00:00, 619MB/s] model-00003-of-00003.safetensors: 94%|█████████▍| 4.27G/4.54G [00:03<00:00, 948MB/s] model-00003-of-00003.safetensors: 98%|█████████▊| 4.46G/4.54G [00:04<00:00, 1.12GB/s] model-00003-of-00003.safetensors: 100%|█████████▉| 4.54G/4.54G [00:04<00:00, 1.10GB/s]
cgato-thespice-7b-ft-dc1-2900-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, 129MB/s]
cgato-thespice-7b-ft-dc1-2900-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, 4.80MB/s]
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: tokenizer.model: 0%| | 0.00/493k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 42.6MB/s]
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: tokenizer_config.json: 0%| | 0.00/982 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 982/982 [00:00<00:00, 11.7MB/s]
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: Downloaded to shared memory in 15.150s
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: Saving mkml model at /dev/shm/model_cache
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: Reading /tmp/tmppz_eshrl/model.safetensors.index.json
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: Profiling: 0%| | 0/291 [00:00<?, ?it/s] Profiling: 0%| | 1/291 [00:01<07:20, 1.52s/it] Profiling: 6%|▌ | 17/291 [00:01<00:19, 14.35it/s] Profiling: 12%|█▏ | 36/291 [00:01<00:07, 33.37it/s] Profiling: 19%|█▉ | 55/291 [00:01<00:04, 53.76it/s] Profiling: 25%|██▌ | 74/291 [00:01<00:02, 74.06it/s] Profiling: 33%|███▎ | 95/291 [00:02<00:01, 98.34it/s] Profiling: 39%|███▉ | 113/291 [00:02<00:02, 73.02it/s] Profiling: 46%|████▋ | 135/291 [00:02<00:01, 96.10it/s] Profiling: 54%|█████▎ | 156/291 [00:02<00:01, 116.95it/s] Profiling: 60%|██████ | 176/291 [00:02<00:00, 131.37it/s] Profiling: 68%|██████▊ | 198/291 [00:02<00:00, 150.73it/s] Profiling: 75%|███████▍ | 217/291 [00:04<00:02, 35.60it/s] Profiling: 82%|████████▏ | 238/291 [00:04<00:01, 47.80it/s] Profiling: 88%|████████▊ | 257/291 [00:04<00:00, 60.62it/s] Profiling: 95%|█████████▍| 276/291 [00:04<00:00, 75.04it/s] Profiling: 100%|██████████| 291/291 [00:04<00:00, 58.68it/s]
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: quantized model in 15.249s
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: Processed model cgato/TheSpice-7b-FT-DC1-OT-2Epoch in 31.372s
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: creating bucket guanaco-mkml-models
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-thespice-7b-ft-dc1-2900-v2
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-thespice-7b-ft-dc1-2900-v2/config.json
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-thespice-7b-ft-dc1-2900-v2/special_tokens_map.json
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-thespice-7b-ft-dc1-2900-v2/tokenizer_config.json
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cgato-thespice-7b-ft-dc1-2900-v2/tokenizer.model
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-thespice-7b-ft-dc1-2900-v2/tokenizer.json
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/cgato-thespice-7b-ft-dc1-2900-v2/mkml_model.tensors
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-thespice-7b-ft-dc1-2900-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-dc1-2900-v2-mkmlizer: warnings.warn(
cgato-thespice-7b-ft-dc1-2900-v2-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-dc1-2900-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-dc1-2900-v2-mkmlizer: warnings.warn(
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 3.38MB/s]
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: vocab.json: 0%| | 0.00/1.04M [00:00<?, ?B/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 33.2MB/s]
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 25.1MB/s]
cgato-thespice-7b-ft-dc1-2900-v2-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-dc1-2900-v2-mkmlizer: warnings.warn(
cgato-thespice-7b-ft-dc1-2900-v2-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, 174MB/s] pytorch_model.bin: 7%|▋ | 94.4M/1.44G [00:00<00:02, 466MB/s] pytorch_model.bin: 13%|█▎ | 189M/1.44G [00:00<00:01, 664MB/s] pytorch_model.bin: 19%|█▉ | 273M/1.44G [00:00<00:01, 717MB/s] pytorch_model.bin: 24%|██▍ | 346M/1.44G [00:00<00:01, 670MB/s] pytorch_model.bin: 29%|██▉ | 419M/1.44G [00:00<00:01, 649MB/s] pytorch_model.bin: 37%|███▋ | 535M/1.44G [00:00<00:01, 788MB/s] pytorch_model.bin: 50%|█████ | 724M/1.44G [00:00<00:00, 1.11GB/s] pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:01<00:00, 1.42GB/s]
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: Saving duration: 0.224s
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.200s
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: creating bucket guanaco-reward-models
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-thespice-7b-ft-dc1-2900-v2_reward
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-thespice-7b-ft-dc1-2900-v2_reward/config.json
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-thespice-7b-ft-dc1-2900-v2_reward/special_tokens_map.json
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-thespice-7b-ft-dc1-2900-v2_reward/tokenizer_config.json
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-thespice-7b-ft-dc1-2900-v2_reward/merges.txt
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-thespice-7b-ft-dc1-2900-v2_reward/vocab.json
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-thespice-7b-ft-dc1-2900-v2_reward/tokenizer.json
cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-thespice-7b-ft-dc1-2900-v2_reward/reward.tensors
Job cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer completed after 55.14s with status: succeeded
Stopping job with name cgato-thespice-7b-ft-dc1-2900-v2-mkmlizer
Pipeline stage MKMLizer completed in 59.68s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cgato-thespice-7b-ft-dc1-2900-v2
Waiting for inference service cgato-thespice-7b-ft-dc1-2900-v2 to be ready
Inference service cgato-thespice-7b-ft-dc1-2900-v2 ready after 40.322059869766235s
Pipeline stage ISVCDeployer completed in 47.70s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.5644285678863525s
Received healthy response to inference request in 1.1272082328796387s
Received healthy response to inference request in 1.197256088256836s
Received healthy response to inference request in 1.1988072395324707s
Received healthy response to inference request in 1.1827950477600098s
5 requests
0 failed requests
5th percentile: 1.1383255958557128
10th percentile: 1.1494429588317872
20th percentile: 1.1716776847839356
30th percentile: 1.185687255859375
40th percentile: 1.1914716720581056
50th percentile: 1.197256088256836
60th percentile: 1.19787654876709
70th percentile: 1.1984970092773437
80th percentile: 1.2719315052032472
90th percentile: 1.4181800365447998
95th percentile: 1.491304302215576
99th percentile: 1.5498037147521972
mean time: 1.2540990352630614
Pipeline stage StressChecker completed in 7.13s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.05s
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_2900_v2 status is now deployed due to DeploymentManager action
cgato-thespice-7b-ft-dc1_2900_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics