submission_id: cgato-thespice-7b-ft-ins_5091_v1
developer_uid: c.gato
status: inactive
model_repo: cgato/TheSpice-7b-FT-InstructExperiment-Overtrain
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####\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####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:'}
timestamp: 2024-03-29T01:32:28+00:00
model_name: cgato-thespice-7b-ft-ins_5091_v1
model_eval_status: success
safety_score: 0.87
entertaining: 6.7
stay_in_character: 8.52
user_preference: 7.28
double_thumbs_up: 742
thumbs_up: 1021
thumbs_down: 489
num_battles: 93224
num_wins: 49521
win_ratio: 0.5312044108813181
celo_rating: 1179.79
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-thespice-7b-ft-ins-5091-v1-mkmlizer
Waiting for job on cgato-thespice-7b-ft-ins-5091-v1-mkmlizer to finish
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: ║ _____ __ __ ║
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: ║ /___/ ║
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: ║ ║
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: ║ Version: 0.6.11 ║
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: ║ ║
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: ║ belonging to: ║
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: ║ ║
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: ║ Chai Research Corp. ║
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: ║ ║
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 19.4MB/s]
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: README.md: 0%| | 0.00/30.0 [00:00<?, ?B/s] README.md: 100%|██████████| 30.0/30.0 [00:00<00:00, 403kB/s]
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: config.json: 0%| | 0.00/653 [00:00<?, ?B/s] config.json: 100%|██████████| 653/653 [00:00<00:00, 7.28MB/s]
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: generation_config.json: 0%| | 0.00/137 [00:00<?, ?B/s] generation_config.json: 100%|██████████| 137/137 [00:00<00:00, 1.90MB/s]
cgato-thespice-7b-ft-ins-5091-v1-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 [00:01<11:38, 7.06MB/s] model-00001-of-00003.safetensors: 1%|▏ | 62.9M/4.94G [00:01<01:33, 52.4MB/s] model-00001-of-00003.safetensors: 4%|▍ | 189M/4.94G [00:01<00:25, 187MB/s] model-00001-of-00003.safetensors: 7%|▋ | 336M/4.94G [00:01<00:13, 331MB/s] model-00001-of-00003.safetensors: 8%|▊ | 419M/4.94G [00:02<00:13, 344MB/s] model-00001-of-00003.safetensors: 10%|▉ | 493M/4.94G [00:02<00:12, 365MB/s] model-00001-of-00003.safetensors: 12%|█▏ | 587M/4.94G [00:02<00:09, 460MB/s] model-00001-of-00003.safetensors: 14%|█▍ | 692M/4.94G [00:02<00:07, 552MB/s] model-00001-of-00003.safetensors: 16%|█▌ | 776M/4.94G [00:02<00:07, 560MB/s] model-00001-of-00003.safetensors: 17%|█▋ | 849M/4.94G [00:02<00:07, 550MB/s] model-00001-of-00003.safetensors: 19%|█▊ | 923M/4.94G [00:02<00:06, 590MB/s] model-00001-of-00003.safetensors: 31%|███ | 1.54G/4.94G [00:02<00:01, 1.92GB/s] model-00001-of-00003.safetensors: 36%|███▌ | 1.78G/4.94G [00:03<00:01, 1.90GB/s] model-00001-of-00003.safetensors: 41%|████ | 2.00G/4.94G [00:04<00:04, 609MB/s] model-00001-of-00003.safetensors: 44%|████▍ | 2.17G/4.94G [00:04<00:04, 658MB/s] model-00001-of-00003.safetensors: 47%|████▋ | 2.32G/4.94G [00:04<00:03, 674MB/s] model-00001-of-00003.safetensors: 51%|█████ | 2.51G/4.94G [00:04<00:02, 824MB/s] model-00001-of-00003.safetensors: 59%|█████▉ | 2.94G/4.94G [00:04<00:01, 1.36GB/s] model-00001-of-00003.safetensors: 64%|██████▍ | 3.17G/4.94G [00:04<00:01, 1.13GB/s] model-00001-of-00003.safetensors: 68%|██████▊ | 3.36G/4.94G [00:05<00:02, 658MB/s] model-00001-of-00003.safetensors: 71%|███████ | 3.49G/4.94G [00:05<00:02, 667MB/s] model-00001-of-00003.safetensors: 73%|███████▎ | 3.63G/4.94G [00:05<00:01, 745MB/s] model-00001-of-00003.safetensors: 76%|███████▌ | 3.75G/4.94G [00:06<00:01, 812MB/s] model-00001-of-00003.safetensors: 78%|███████▊ | 3.88G/4.94G [00:06<00:01, 867MB/s] model-00001-of-00003.safetensors: 85%|████████▍ | 4.19G/4.94G [00:06<00:00, 1.24GB/s] model-00001-of-00003.safetensors: 88%|████████▊ | 4.35G/4.94G [00:06<00:00, 859MB/s] model-00001-of-00003.safetensors: 91%|█████████ | 4.48G/4.94G [00:06<00:00, 863MB/s] model-00001-of-00003.safetensors: 93%|█████████▎| 4.61G/4.94G [00:06<00:00, 929MB/s] model-00001-of-00003.safetensors: 96%|█████████▌| 4.72G/4.94G [00:06<00:00, 954MB/s] model-00001-of-00003.safetensors: 100%|█████████▉| 4.94G/4.94G [00:07<00:00, 697MB/s]
cgato-thespice-7b-ft-ins-5091-v1-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 [00:01<09:15, 8.98MB/s] model-00002-of-00003.safetensors: 1%| | 52.4M/5.00G [00:01<01:32, 53.4MB/s] model-00002-of-00003.safetensors: 3%|▎ | 168M/5.00G [00:01<00:24, 199MB/s] model-00002-of-00003.safetensors: 6%|▌ | 294M/5.00G [00:01<00:12, 363MB/s] model-00002-of-00003.safetensors: 8%|▊ | 377M/5.00G [00:02<00:18, 250MB/s] model-00002-of-00003.safetensors: 9%|▉ | 472M/5.00G [00:02<00:13, 338MB/s] model-00002-of-00003.safetensors: 12%|█▏ | 587M/5.00G [00:02<00:09, 450MB/s] model-00002-of-00003.safetensors: 15%|█▍ | 734M/5.00G [00:02<00:06, 628MB/s] model-00002-of-00003.safetensors: 17%|█▋ | 839M/5.00G [00:02<00:07, 577MB/s] model-00002-of-00003.safetensors: 19%|█▊ | 933M/5.00G [00:02<00:06, 590MB/s] model-00002-of-00003.safetensors: 25%|██▌ | 1.27G/5.00G [00:02<00:03, 1.13GB/s] model-00002-of-00003.safetensors: 32%|███▏ | 1.59G/5.00G [00:02<00:02, 1.56GB/s] model-00002-of-00003.safetensors: 38%|███▊ | 1.88G/5.00G [00:03<00:01, 1.73GB/s] model-00002-of-00003.safetensors: 42%|████▏ | 2.09G/5.00G [00:03<00:04, 698MB/s] model-00002-of-00003.safetensors: 45%|████▍ | 2.24G/5.00G [00:04<00:03, 712MB/s] model-00002-of-00003.safetensors: 48%|████▊ | 2.38G/5.00G [00:04<00:03, 795MB/s] model-00002-of-00003.safetensors: 50%|█████ | 2.52G/5.00G [00:04<00:03, 810MB/s] model-00002-of-00003.safetensors: 53%|█████▎ | 2.65G/5.00G [00:04<00:02, 877MB/s] model-00002-of-00003.safetensors: 56%|█████▋ | 2.82G/5.00G [00:04<00:02, 1.03GB/s] model-00002-of-00003.safetensors: 64%|██████▍ | 3.21G/5.00G [00:04<00:01, 1.46GB/s] model-00002-of-00003.safetensors: 68%|██████▊ | 3.38G/5.00G [00:05<00:01, 998MB/s] model-00002-of-00003.safetensors: 70%|███████ | 3.51G/5.00G [00:05<00:01, 852MB/s] model-00002-of-00003.safetensors: 73%|███████▎ | 3.63G/5.00G [00:05<00:01, 693MB/s] model-00002-of-00003.safetensors: 74%|███████▍ | 3.72G/5.00G [00:05<00:01, 699MB/s] model-00002-of-00003.safetensors: 76%|███████▋ | 3.82G/5.00G [00:05<00:01, 717MB/s] model-00002-of-00003.safetensors: 79%|███████▊ | 3.93G/5.00G [00:05<00:01, 739MB/s] model-00002-of-00003.safetensors: 81%|████████▏ | 4.07G/5.00G [00:06<00:01, 858MB/s] model-00002-of-00003.safetensors: 88%|████████▊ | 4.41G/5.00G [00:06<00:00, 1.39GB/s] model-00002-of-00003.safetensors: 92%|█████████▏| 4.59G/5.00G [00:06<00:00, 1.47GB/s] model-00002-of-00003.safetensors: 95%|█████████▌| 4.76G/5.00G [00:06<00:00, 1.35GB/s] model-00002-of-00003.safetensors: 100%|█████████▉| 5.00G/5.00G [00:06<00:00, 1.33GB/s] model-00002-of-00003.safetensors: 100%|█████████▉| 5.00G/5.00G [00:06<00:00, 753MB/s]
cgato-thespice-7b-ft-ins-5091-v1-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<03:05, 24.4MB/s] model-00003-of-00003.safetensors: 0%| | 21.0M/4.54G [00:01<04:10, 18.0MB/s] model-00003-of-00003.safetensors: 1%|▏ | 62.9M/4.54G [00:01<01:09, 64.3MB/s] model-00003-of-00003.safetensors: 3%|▎ | 147M/4.54G [00:01<00:25, 175MB/s] model-00003-of-00003.safetensors: 4%|▍ | 199M/4.54G [00:01<00:19, 220MB/s] model-00003-of-00003.safetensors: 5%|▌ | 241M/4.54G [00:01<00:20, 208MB/s] model-00003-of-00003.safetensors: 8%|▊ | 377M/4.54G [00:01<00:10, 408MB/s] model-00003-of-00003.safetensors: 10%|▉ | 451M/4.54G [00:02<00:10, 376MB/s] model-00003-of-00003.safetensors: 11%|█▏ | 514M/4.54G [00:02<00:10, 387MB/s] model-00003-of-00003.safetensors: 13%|█▎ | 608M/4.54G [00:02<00:08, 471MB/s] model-00003-of-00003.safetensors: 15%|█▌ | 692M/4.54G [00:02<00:07, 542MB/s] model-00003-of-00003.safetensors: 17%|█▋ | 776M/4.54G [00:02<00:06, 583MB/s] model-00003-of-00003.safetensors: 20%|█▉ | 902M/4.54G [00:02<00:04, 742MB/s] model-00003-of-00003.safetensors: 22%|██▏ | 986M/4.54G [00:02<00:05, 653MB/s] model-00003-of-00003.safetensors: 25%|██▌ | 1.14G/4.54G [00:02<00:03, 865MB/s] model-00003-of-00003.safetensors: 38%|███▊ | 1.72G/4.54G [00:03<00:01, 1.88GB/s] model-00003-of-00003.safetensors: 42%|████▏ | 1.91G/4.54G [00:03<00:03, 704MB/s] model-00003-of-00003.safetensors: 46%|████▌ | 2.10G/4.54G [00:03<00:02, 831MB/s] model-00003-of-00003.safetensors: 50%|████▉ | 2.25G/4.54G [00:04<00:02, 810MB/s] model-00003-of-00003.safetensors: 53%|█████▎ | 2.39G/4.54G [00:04<00:02, 867MB/s] model-00003-of-00003.safetensors: 55%|█████▌ | 2.52G/4.54G [00:04<00:02, 814MB/s] model-00003-of-00003.safetensors: 58%|█████▊ | 2.63G/4.54G [00:04<00:02, 836MB/s] model-00003-of-00003.safetensors: 60%|██████ | 2.74G/4.54G [00:04<00:02, 859MB/s] model-00003-of-00003.safetensors: 63%|██████▎ | 2.84G/4.54G [00:04<00:01, 895MB/s] model-00003-of-00003.safetensors: 65%|██████▍ | 2.95G/4.54G [00:04<00:01, 850MB/s] model-00003-of-00003.safetensors: 69%|██████▉ | 3.14G/4.54G [00:05<00:01, 1.08GB/s] model-00003-of-00003.safetensors: 72%|███████▏ | 3.26G/4.54G [00:05<00:01, 1.09GB/s] model-00003-of-00003.safetensors: 75%|███████▍ | 3.39G/4.54G [00:05<00:01, 1.02GB/s] model-00003-of-00003.safetensors: 81%|████████▏ | 3.69G/4.54G [00:05<00:00, 1.51GB/s] model-00003-of-00003.safetensors: 88%|████████▊ | 4.00G/4.54G [00:05<00:00, 1.89GB/s] model-00003-of-00003.safetensors: 93%|█████████▎| 4.20G/4.54G [00:05<00:00, 1.70GB/s] model-00003-of-00003.safetensors: 97%|█████████▋| 4.39G/4.54G [00:05<00:00, 1.55GB/s] model-00003-of-00003.safetensors: 100%|█████████▉| 4.54G/4.54G [00:06<00:00, 694MB/s]
cgato-thespice-7b-ft-ins-5091-v1-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, 143MB/s]
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: special_tokens_map.json: 0%| | 0.00/437 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 437/437 [00:00<00:00, 4.75MB/s]
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: tokenizer.model: 0%| | 0.00/493k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 5.79MB/s]
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: tokenizer_config.json: 0%| | 0.00/982 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 982/982 [00:00<00:00, 11.9MB/s]
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: Downloaded to shared memory in 22.102s
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: Saving mkml model at /dev/shm/model_cache
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: Reading /tmp/tmpm0906jcb/model.safetensors.index.json
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: Profiling: 0%| | 0/291 [00:00<?, ?it/s] Profiling: 0%| | 1/291 [00:01<06:47, 1.41s/it] Profiling: 6%|▌ | 18/291 [00:01<00:16, 16.28it/s] Profiling: 12%|█▏ | 36/291 [00:01<00:07, 35.28it/s] Profiling: 19%|█▉ | 55/291 [00:01<00:04, 57.04it/s] Profiling: 25%|██▌ | 74/291 [00:01<00:02, 79.09it/s] Profiling: 34%|███▎ | 98/291 [00:02<00:02, 73.74it/s] Profiling: 40%|███▉ | 116/291 [00:02<00:01, 90.11it/s] Profiling: 47%|████▋ | 138/291 [00:02<00:01, 112.52it/s] Profiling: 54%|█████▍ | 158/291 [00:02<00:01, 127.77it/s] Profiling: 62%|██████▏ | 180/291 [00:02<00:00, 147.53it/s] Profiling: 69%|██████▉ | 202/291 [00:02<00:00, 164.79it/s] Profiling: 76%|███████▋ | 222/291 [00:04<00:01, 35.08it/s] Profiling: 85%|████████▍ | 247/291 [00:04<00:00, 49.48it/s] Profiling: 91%|█████████▏| 266/291 [00:04<00:00, 61.84it/s] Profiling: 98%|█████████▊| 285/291 [00:04<00:00, 75.64it/s] Profiling: 100%|██████████| 291/291 [00:04<00:00, 59.82it/s]
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: quantized model in 15.343s
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: Processed model cgato/TheSpice-7b-FT-InstructExperiment-Overtrain in 38.386s
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: creating bucket guanaco-mkml-models
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-thespice-7b-ft-ins-5091-v1
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cgato-thespice-7b-ft-ins-5091-v1/tokenizer.model
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-thespice-7b-ft-ins-5091-v1/tokenizer_config.json
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-thespice-7b-ft-ins-5091-v1/config.json
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-thespice-7b-ft-ins-5091-v1/special_tokens_map.json
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-thespice-7b-ft-ins-5091-v1/tokenizer.json
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/cgato-thespice-7b-ft-ins-5091-v1/mkml_model.tensors
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-thespice-7b-ft-ins-5091-v1-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-ins-5091-v1-mkmlizer: warnings.warn(
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: config.json: 0%| | 0.00/1.05k [00:00<?, ?B/s] config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 13.3MB/s]
cgato-thespice-7b-ft-ins-5091-v1-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-ins-5091-v1-mkmlizer: warnings.warn(
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 3.26MB/s]
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: vocab.json: 0%| | 0.00/1.04M [00:00<?, ?B/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 16.4MB/s]
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 17.9MB/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 17.8MB/s]
cgato-thespice-7b-ft-ins-5091-v1-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-ins-5091-v1-mkmlizer: warnings.warn(
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: pytorch_model.bin: 0%| | 0.00/1.44G [00:00<?, ?B/s] pytorch_model.bin: 1%| | 10.5M/1.44G [00:00<00:36, 39.8MB/s] pytorch_model.bin: 2%|▏ | 31.5M/1.44G [00:00<00:20, 68.2MB/s] pytorch_model.bin: 8%|▊ | 115M/1.44G [00:00<00:05, 257MB/s] pytorch_model.bin: 17%|█▋ | 252M/1.44G [00:00<00:02, 544MB/s] pytorch_model.bin: 23%|██▎ | 336M/1.44G [00:00<00:02, 412MB/s] pytorch_model.bin: 28%|██▊ | 398M/1.44G [00:01<00:04, 256MB/s] pytorch_model.bin: 37%|███▋ | 535M/1.44G [00:01<00:02, 411MB/s] pytorch_model.bin: 97%|█████████▋| 1.40G/1.44G [00:01<00:00, 1.78GB/s] pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:01<00:00, 821MB/s]
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: Saving duration: 0.276s
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.728s
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: creating bucket guanaco-reward-models
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-thespice-7b-ft-ins-5091-v1_reward
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-thespice-7b-ft-ins-5091-v1_reward/special_tokens_map.json
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-thespice-7b-ft-ins-5091-v1_reward/tokenizer_config.json
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-thespice-7b-ft-ins-5091-v1_reward/config.json
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-thespice-7b-ft-ins-5091-v1_reward/vocab.json
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-thespice-7b-ft-ins-5091-v1_reward/merges.txt
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-thespice-7b-ft-ins-5091-v1_reward/tokenizer.json
cgato-thespice-7b-ft-ins-5091-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-thespice-7b-ft-ins-5091-v1_reward/reward.tensors
Job cgato-thespice-7b-ft-ins-5091-v1-mkmlizer completed after 67.0s with status: succeeded
Stopping job with name cgato-thespice-7b-ft-ins-5091-v1-mkmlizer
Pipeline stage MKMLizer completed in 71.25s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cgato-thespice-7b-ft-ins-5091-v1
Waiting for inference service cgato-thespice-7b-ft-ins-5091-v1 to be ready
Inference service cgato-thespice-7b-ft-ins-5091-v1 ready after 40.41997575759888s
Pipeline stage ISVCDeployer completed in 49.07s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.752002477645874s
Received healthy response to inference request in 2.796769380569458s
Received healthy response to inference request in 1.1684608459472656s
Received healthy response to inference request in 1.1692864894866943s
Received healthy response to inference request in 1.1696546077728271s
5 requests
0 failed requests
5th percentile: 1.1686259746551513
10th percentile: 1.1687911033630372
20th percentile: 1.1691213607788087
30th percentile: 1.1693601131439209
40th percentile: 1.1695073604583741
50th percentile: 1.1696546077728271
60th percentile: 1.4025937557220458
70th percentile: 1.6355329036712645
80th percentile: 1.960955858230591
90th percentile: 2.3788626194000244
95th percentile: 2.587815999984741
99th percentile: 2.7549787044525145
mean time: 1.611234760284424
Pipeline stage StressChecker completed in 15.98s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.05s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.05s
Running M-Eval for topic stay_in_character
cgato-thespice-7b-ft-ins_5091_v1 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
cgato-thespice-7b-ft-ins_5091_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics