submission_id: thanhdaonguyen-once-upon-a-t_v37
developer_uid: robert_irvine
status: torndown
model_repo: thanhdaonguyen/once-upon-a-time
reward_repo: rirv938/gpt2_ties_merge_preference_plus_classic_e2_density_99
generation_params: {'temperature': 0.72, 'top_p': 0.73, 'min_p': 0.0, 'top_k': 1000, 'presence_penalty': 0.7, 'frequency_penalty': 0.3, 'stopping_words': ['</s>', '<|user|>', '###', '\n'], 'max_input_tokens': 512, 'best_of': 32, 'max_output_tokens': 64}
formatter: {'memory_template': "### Instruction:\n\n{bot_name}'s Persona: {memory}.\n\nPlay the role of {bot_name}. Engage in a chat with {user_name} while stay in character. Do not write dialogues and narration for {user_name}. {bot_name} should response with engaging messages of medium length that encourage responses.", 'prompt_template': '{prompt}\n\n', 'bot_template': '### Response:\n\n{bot_name}: {message}\n\n', 'user_template': '### Input:\n\n{user_name}: {message}\n\n', 'response_template': '### Response:\n\n{bot_name}:', 'truncate_by_message': False}
reward_formatter: {'memory_template': 'Memory: {memory}\n', 'prompt_template': '{prompt}\n', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', 'truncate_by_message': False}
timestamp: 2024-02-26T22:54:26+00:00
model_name: thanhdaonguyen-once-upon-a-t_v37
model_eval_status: pending
model_group: thanhdaonguyen/once-upon
num_battles: 361163
num_wins: 187340
celo_rating: 1170.11
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: None
model_num_parameters: 13015864320.0
best_of: 32
max_input_tokens: 512
max_output_tokens: 64
display_name: thanhdaonguyen-once-upon-a-t_v37
ineligible_reason: propriety_total_count < 800
language_model: thanhdaonguyen/once-upon-a-time
model_size: 13B
reward_model: rirv938/gpt2_ties_merge_preference_plus_classic_e2_density_99
us_pacific_date: 2024-02-26
win_ratio: 0.5187131572171014
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name thanhdaonguyen-once-upon-a-t-v37-mkmlizer
Waiting for job on thanhdaonguyen-once-upon-a-t-v37-mkmlizer to finish
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: ║ _____ __ __ ║
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: ║ /___/ ║
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: ║ ║
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: ║ Version: 0.6.11 ║
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: ║ ║
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: ║ The license key for the current software has been verified as ║
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: ║ belonging to: ║
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: ║ ║
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: ║ Chai Research Corp. ║
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: ║ Expiration: 2024-04-15 23:59:59 ║
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: ║ ║
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 16.9MB/s]
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: added_tokens.json: 0%| | 0.00/21.0 [00:00<?, ?B/s] added_tokens.json: 100%|██████████| 21.0/21.0 [00:00<00:00, 299kB/s]
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: config.json: 0%| | 0.00/643 [00:00<?, ?B/s] config.json: 100%|██████████| 643/643 [00:00<00:00, 10.1MB/s]
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: generation_config.json: 0%| | 0.00/154 [00:00<?, ?B/s] generation_config.json: 100%|██████████| 154/154 [00:00<00:00, 2.50MB/s]
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: pytorch_model-00001-of-00003.bin: 0%| | 0.00/9.95G [00:00<?, ?B/s] pytorch_model-00001-of-00003.bin: 0%| | 10.5M/9.95G [00:00<01:40, 98.5MB/s] pytorch_model-00001-of-00003.bin: 0%| | 41.9M/9.95G [00:00<00:59, 167MB/s] pytorch_model-00001-of-00003.bin: 1%|▏ | 136M/9.95G [00:00<00:21, 447MB/s] pytorch_model-00001-of-00003.bin: 2%|▏ | 220M/9.95G [00:00<00:17, 571MB/s] pytorch_model-00001-of-00003.bin: 3%|▎ | 283M/9.95G [00:00<00:19, 494MB/s] pytorch_model-00001-of-00003.bin: 4%|▎ | 357M/9.95G [00:00<00:17, 560MB/s] pytorch_model-00001-of-00003.bin: 5%|▍ | 461M/9.95G [00:00<00:14, 635MB/s] pytorch_model-00001-of-00003.bin: 6%|▌ | 577M/9.95G [00:00<00:12, 769MB/s] pytorch_model-00001-of-00003.bin: 10%|▉ | 986M/9.95G [00:01<00:05, 1.68GB/s] pytorch_model-00001-of-00003.bin: 13%|█▎ | 1.34G/9.95G [00:01<00:03, 2.20GB/s] pytorch_model-00001-of-00003.bin: 16%|█▌ | 1.58G/9.95G [00:01<00:04, 2.04GB/s] pytorch_model-00001-of-00003.bin: 18%|█▊ | 1.80G/9.95G [00:01<00:04, 1.68GB/s] pytorch_model-00001-of-00003.bin: 20%|██ | 1.99G/9.95G [00:01<00:05, 1.47GB/s] pytorch_model-00001-of-00003.bin: 22%|██▏ | 2.17G/9.95G [00:01<00:05, 1.52GB/s] pytorch_model-00001-of-00003.bin: 26%|██▌ | 2.54G/9.95G [00:01<00:03, 2.01GB/s] pytorch_model-00001-of-00003.bin: 28%|██▊ | 2.79G/9.95G [00:01<00:03, 2.12GB/s] pytorch_model-00001-of-00003.bin: 30%|███ | 3.02G/9.95G [00:02<00:03, 1.98GB/s] pytorch_model-00001-of-00003.bin: 33%|███▎ | 3.24G/9.95G [00:02<00:04, 1.54GB/s] pytorch_model-00001-of-00003.bin: 34%|███▍ | 3.42G/9.95G [00:02<00:04, 1.42GB/s] pytorch_model-00001-of-00003.bin: 36%|███▋ | 3.62G/9.95G [00:02<00:04, 1.53GB/s] pytorch_model-00001-of-00003.bin: 38%|███▊ | 3.81G/9.95G [00:02<00:03, 1.60GB/s] pytorch_model-00001-of-00003.bin: 41%|████▏ | 4.11G/9.95G [00:02<00:02, 1.95GB/s] pytorch_model-00001-of-00003.bin: 44%|████▎ | 4.33G/9.95G [00:02<00:03, 1.85GB/s] pytorch_model-00001-of-00003.bin: 46%|████▌ | 4.53G/9.95G [00:03<00:03, 1.65GB/s] pytorch_model-00001-of-00003.bin: 48%|████▊ | 4.79G/9.95G [00:03<00:02, 1.78GB/s] pytorch_model-00001-of-00003.bin: 50%|█████ | 5.01G/9.95G [00:03<00:02, 1.86GB/s] pytorch_model-00001-of-00003.bin: 52%|█████▏ | 5.21G/9.95G [00:03<00:02, 1.78GB/s] pytorch_model-00001-of-00003.bin: 54%|█████▍ | 5.41G/9.95G [00:03<00:02, 1.82GB/s] pytorch_model-00001-of-00003.bin: 56%|█████▋ | 5.60G/9.95G [00:03<00:02, 1.80GB/s] pytorch_model-00001-of-00003.bin: 58%|█████▊ | 5.79G/9.95G [00:03<00:02, 1.73GB/s] pytorch_model-00001-of-00003.bin: 61%|██████▏ | 6.11G/9.95G [00:03<00:01, 2.10GB/s] pytorch_model-00001-of-00003.bin: 64%|██████▎ | 6.33G/9.95G [00:04<00:02, 1.79GB/s] pytorch_model-00001-of-00003.bin: 66%|██████▌ | 6.54G/9.95G [00:04<00:01, 1.85GB/s] pytorch_model-00001-of-00003.bin: 68%|██████▊ | 6.74G/9.95G [00:04<00:01, 1.85GB/s] pytorch_model-00001-of-00003.bin: 70%|██████▉ | 6.94G/9.95G [00:04<00:01, 1.78GB/s] pytorch_model-00001-of-00003.bin: 72%|███████▏ | 7.18G/9.95G [00:04<00:01, 1.95GB/s] pytorch_model-00001-of-00003.bin: 74%|███████▍ | 7.39G/9.95G [00:04<00:01, 1.74GB/s] pytorch_model-00001-of-00003.bin: 76%|███████▋ | 7.60G/9.95G [00:04<00:01, 1.77GB/s] pytorch_model-00001-of-00003.bin: 79%|███████▊ | 7.82G/9.95G [00:04<00:01, 1.88GB/s] pytorch_model-00001-of-00003.bin: 81%|████████ | 8.02G/9.95G [00:04<00:01, 1.84GB/s] pytorch_model-00001-of-00003.bin: 83%|████████▎ | 8.22G/9.95G [00:05<00:00, 1.86GB/s] pytorch_model-00001-of-00003.bin: 85%|████████▍ | 8.43G/9.95G [00:05<00:00, 1.92GB/s] pytorch_model-00001-of-00003.bin: 87%|████████▋ | 8.63G/9.95G [00:05<00:00, 1.74GB/s] pytorch_model-00001-of-00003.bin: 89%|████████▊ | 8.82G/9.95G [00:05<00:00, 1.70GB/s] pytorch_model-00001-of-00003.bin: 91%|█████████ | 9.02G/9.95G [00:05<00:00, 1.76GB/s] pytorch_model-00001-of-00003.bin: 93%|█████████▎| 9.28G/9.95G [00:05<00:00, 2.00GB/s] pytorch_model-00001-of-00003.bin: 97%|█████████▋| 9.66G/9.95G [00:05<00:00, 2.48GB/s] pytorch_model-00001-of-00003.bin: 100%|█████████▉| 9.95G/9.95G [00:06<00:00, 1.23GB/s] pytorch_model-00001-of-00003.bin: 100%|█████████▉| 9.95G/9.95G [00:06<00:00, 1.58GB/s]
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: pytorch_model-00002-of-00003.bin: 0%| | 0.00/9.90G [00:00<?, ?B/s] pytorch_model-00002-of-00003.bin: 0%| | 10.5M/9.90G [00:00<02:04, 79.7MB/s] pytorch_model-00002-of-00003.bin: 1%| | 73.4M/9.90G [00:00<00:27, 359MB/s] pytorch_model-00002-of-00003.bin: 2%|▏ | 168M/9.90G [00:00<00:16, 580MB/s] pytorch_model-00002-of-00003.bin: 3%|▎ | 283M/9.90G [00:00<00:12, 750MB/s] pytorch_model-00002-of-00003.bin: 4%|▎ | 367M/9.90G [00:00<00:15, 630MB/s] pytorch_model-00002-of-00003.bin: 6%|▌ | 566M/9.90G [00:00<00:09, 988MB/s] pytorch_model-00002-of-00003.bin: 9%|▊ | 860M/9.90G [00:00<00:05, 1.53GB/s] pytorch_model-00002-of-00003.bin: 11%|█▏ | 1.12G/9.90G [00:00<00:04, 1.84GB/s] pytorch_model-00002-of-00003.bin: 14%|█▎ | 1.34G/9.90G [00:01<00:04, 1.94GB/s] pytorch_model-00002-of-00003.bin: 16%|█▌ | 1.55G/9.90G [00:01<00:05, 1.57GB/s] pytorch_model-00002-of-00003.bin: 18%|█▊ | 1.78G/9.90G [00:01<00:04, 1.74GB/s] pytorch_model-00002-of-00003.bin: 20%|██ | 2.01G/9.90G [00:01<00:04, 1.89GB/s] pytorch_model-00002-of-00003.bin: 22%|██▏ | 2.22G/9.90G [00:01<00:04, 1.80GB/s] pytorch_model-00002-of-00003.bin: 25%|██▌ | 2.50G/9.90G [00:01<00:03, 2.03GB/s] pytorch_model-00002-of-00003.bin: 27%|██▋ | 2.72G/9.90G [00:01<00:03, 1.90GB/s] pytorch_model-00002-of-00003.bin: 30%|██▉ | 2.93G/9.90G [00:01<00:03, 1.95GB/s] pytorch_model-00002-of-00003.bin: 32%|███▏ | 3.14G/9.90G [00:02<00:03, 1.95GB/s] pytorch_model-00002-of-00003.bin: 34%|███▍ | 3.34G/9.90G [00:02<00:03, 1.91GB/s] pytorch_model-00002-of-00003.bin: 36%|███▋ | 3.60G/9.90G [00:02<00:03, 2.08GB/s] pytorch_model-00002-of-00003.bin: 39%|███▊ | 3.82G/9.90G [00:02<00:02, 2.07GB/s] pytorch_model-00002-of-00003.bin: 41%|████ | 4.04G/9.90G [00:02<00:02, 2.10GB/s] pytorch_model-00002-of-00003.bin: 43%|████▎ | 4.26G/9.90G [00:02<00:02, 1.99GB/s] pytorch_model-00002-of-00003.bin: 45%|████▌ | 4.47G/9.90G [00:02<00:02, 1.99GB/s] pytorch_model-00002-of-00003.bin: 47%|████▋ | 4.68G/9.90G [00:02<00:02, 2.01GB/s] pytorch_model-00002-of-00003.bin: 50%|████▉ | 4.93G/9.90G [00:02<00:02, 2.15GB/s] pytorch_model-00002-of-00003.bin: 53%|█████▎ | 5.20G/9.90G [00:02<00:02, 2.30GB/s] pytorch_model-00002-of-00003.bin: 55%|█████▍ | 5.44G/9.90G [00:03<00:02, 1.79GB/s] pytorch_model-00002-of-00003.bin: 57%|█████▋ | 5.64G/9.90G [00:03<00:02, 1.62GB/s] pytorch_model-00002-of-00003.bin: 59%|█████▉ | 5.82G/9.90G [00:03<00:02, 1.38GB/s] pytorch_model-00002-of-00003.bin: 62%|██████▏ | 6.10G/9.90G [00:03<00:02, 1.68GB/s] pytorch_model-00002-of-00003.bin: 64%|██████▎ | 6.30G/9.90G [00:03<00:02, 1.72GB/s] pytorch_model-00002-of-00003.bin: 66%|██████▌ | 6.49G/9.90G [00:03<00:02, 1.52GB/s] pytorch_model-00002-of-00003.bin: 68%|██████▊ | 6.74G/9.90G [00:03<00:01, 1.74GB/s] pytorch_model-00002-of-00003.bin: 70%|██████▉ | 6.93G/9.90G [00:04<00:01, 1.68GB/s] pytorch_model-00002-of-00003.bin: 72%|███████▏ | 7.11G/9.90G [00:04<00:01, 1.67GB/s] pytorch_model-00002-of-00003.bin: 75%|███████▍ | 7.41G/9.90G [00:04<00:01, 2.00GB/s] pytorch_model-00002-of-00003.bin: 77%|███████▋ | 7.62G/9.90G [00:04<00:01, 1.66GB/s] pytorch_model-00002-of-00003.bin: 79%|███████▉ | 7.81G/9.90G [00:04<00:01, 1.67GB/s] pytorch_model-00002-of-00003.bin: 81%|████████ | 7.99G/9.90G [00:04<00:01, 1.65GB/s] pytorch_model-00002-of-00003.bin: 82%|████████▏ | 8.17G/9.90G [00:04<00:01, 1.64GB/s] pytorch_model-00002-of-00003.bin: 85%|████████▍ | 8.41G/9.90G [00:04<00:00, 1.81GB/s] pytorch_model-00002-of-00003.bin: 87%|████████▋ | 8.65G/9.90G [00:05<00:00, 1.96GB/s] pytorch_model-00002-of-00003.bin: 89%|████████▉ | 8.86G/9.90G [00:05<00:00, 1.75GB/s] pytorch_model-00002-of-00003.bin: 91%|█████████▏| 9.05G/9.90G [00:05<00:00, 1.66GB/s] pytorch_model-00002-of-00003.bin: 95%|█████████▌| 9.45G/9.90G [00:05<00:00, 2.25GB/s] pytorch_model-00002-of-00003.bin: 100%|█████████▉| 9.90G/9.90G [00:05<00:00, 1.79GB/s]
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: Profiling: 0%| | 0/363 [00:00<?, ?it/s] Profiling: 0%| | 1/363 [00:03<22:50, 3.79s/it] Profiling: 38%|███▊ | 139/363 [00:05<00:06, 33.63it/s] Profiling: 77%|███████▋ | 278/363 [00:06<00:01, 60.83it/s] Profiling: 100%|██████████| 363/363 [00:07<00:00, 59.51it/s] Profiling: 100%|██████████| 363/363 [00:07<00:00, 46.88it/s]
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: quantized model in 25.596s
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: Processed model thanhdaonguyen/once-upon-a-time in 45.839s
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: creating bucket guanaco-mkml-models
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/thanhdaonguyen-once-upon-a-t-v37
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/thanhdaonguyen-once-upon-a-t-v37/config.json
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/thanhdaonguyen-once-upon-a-t-v37/special_tokens_map.json
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/thanhdaonguyen-once-upon-a-t-v37/tokenizer_config.json
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/thanhdaonguyen-once-upon-a-t-v37/added_tokens.json
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/thanhdaonguyen-once-upon-a-t-v37/tokenizer.model
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/thanhdaonguyen-once-upon-a-t-v37/tokenizer.json
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/thanhdaonguyen-once-upon-a-t-v37/mkml_model.tensors
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: loading reward model from rirv938/gpt2_ties_merge_preference_plus_classic_e2_density_99
thanhdaonguyen-once-upon-a-t-v37-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.
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: warnings.warn(
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: config.json: 0%| | 0.00/983 [00:00<?, ?B/s] config.json: 100%|██████████| 983/983 [00:00<00:00, 9.98MB/s]
thanhdaonguyen-once-upon-a-t-v37-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.
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: warnings.warn(
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: tokenizer_config.json: 0%| | 0.00/445 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 445/445 [00:00<00:00, 4.28MB/s]
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: vocab.json: 0%| | 0.00/798k [00:00<?, ?B/s] vocab.json: 100%|██████████| 798k/798k [00:00<00:00, 51.6MB/s]
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: merges.txt: 0%| | 0.00/456k [00:00<?, ?B/s] merges.txt: 100%|██████████| 456k/456k [00:00<00:00, 34.5MB/s]
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 29.0MB/s]
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: special_tokens_map.json: 0%| | 0.00/441 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 441/441 [00:00<00:00, 5.03MB/s]
thanhdaonguyen-once-upon-a-t-v37-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.
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: warnings.warn(
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: model.safetensors.index.json: 0%| | 0.00/10.5k [00:00<?, ?B/s] model.safetensors.index.json: 100%|██████████| 10.5k/10.5k [00:00<00:00, 40.0MB/s]
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: Downloading shards: 0%| | 0/1 [00:00<?, ?it/s]
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: model-00001-of-00001.safetensors: 0%| | 0.00/249M [00:00<?, ?B/s]
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: model-00001-of-00001.safetensors: 4%|▍ | 10.5M/249M [00:00<00:03, 69.0MB/s]
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: model-00001-of-00001.safetensors: 55%|█████▍ | 136M/249M [00:00<00:00, 630MB/s] 
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: model-00001-of-00001.safetensors: 87%|████████▋ | 217M/249M [00:00<00:00, 679MB/s] model-00001-of-00001.safetensors: 100%|█████████▉| 249M/249M [00:00<00:00, 377MB/s]
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: Downloading shards: 100%|██████████| 1/1 [00:00<00:00, 1.15it/s] Downloading shards: 100%|██████████| 1/1 [00:00<00:00, 1.15it/s]
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: Saving duration: 0.090s
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: Processed model rirv938/gpt2_ties_merge_preference_plus_classic_e2_density_99 in 2.644s
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: creating bucket guanaco-reward-models
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: Bucket 's3://guanaco-reward-models/' created
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/thanhdaonguyen-once-upon-a-t-v37_reward
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/thanhdaonguyen-once-upon-a-t-v37_reward/config.json
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/thanhdaonguyen-once-upon-a-t-v37_reward/tokenizer_config.json
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/thanhdaonguyen-once-upon-a-t-v37_reward/merges.txt
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/thanhdaonguyen-once-upon-a-t-v37_reward/vocab.json
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/thanhdaonguyen-once-upon-a-t-v37_reward/special_tokens_map.json
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/thanhdaonguyen-once-upon-a-t-v37_reward/tokenizer.json
thanhdaonguyen-once-upon-a-t-v37-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/thanhdaonguyen-once-upon-a-t-v37_reward/reward.tensors
Job thanhdaonguyen-once-upon-a-t-v37-mkmlizer completed after 85.82s with status: succeeded
Stopping job with name thanhdaonguyen-once-upon-a-t-v37-mkmlizer
Pipeline stage MKMLizer completed in 88.15s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.39s
Running pipeline stage ISVCDeployer
Creating inference service thanhdaonguyen-once-upon-a-t-v37
Waiting for inference service thanhdaonguyen-once-upon-a-t-v37 to be ready
Inference service thanhdaonguyen-once-upon-a-t-v37 ready after 40.746522188186646s
Pipeline stage ISVCDeployer completed in 48.26s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.171170473098755s
Received healthy response to inference request in 2.551041603088379s
Received healthy response to inference request in 2.748166561126709s
Received healthy response to inference request in 2.6364800930023193s
Received healthy response to inference request in 2.546363592147827s
5 requests
0 failed requests
5th percentile: 2.5472991943359373
10th percentile: 2.548234796524048
20th percentile: 2.5501060009002687
30th percentile: 2.568129301071167
40th percentile: 2.602304697036743
50th percentile: 2.6364800930023193
60th percentile: 2.6811546802520754
70th percentile: 2.725829267501831
80th percentile: 2.8327673435211183
90th percentile: 3.0019689083099363
95th percentile: 3.0865696907043456
99th percentile: 3.154250316619873
mean time: 2.730644464492798
Pipeline stage StressChecker completed in 17.67s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.15s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.17s
%s, retrying in %s seconds...
M-Eval Dataset for topic stay_in_character is loaded
thanhdaonguyen-once-upon-a-t_v37 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of thanhdaonguyen-once-upon-a-t_v37
Running pipeline stage ISVCDeleter
Checking if service thanhdaonguyen-once-upon-a-t-v37 is running
Tearing down inference service thanhdaonguyen-once-upon-a-t-v37
Toredown service thanhdaonguyen-once-upon-a-t-v37
Pipeline stage ISVCDeleter completed in 10.09s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key thanhdaonguyen-once-upon-a-t-v37/added_tokens.json from bucket guanaco-mkml-models
Deleting key thanhdaonguyen-once-upon-a-t-v37/config.json from bucket guanaco-mkml-models
Deleting key thanhdaonguyen-once-upon-a-t-v37/mkml_model.tensors from bucket guanaco-mkml-models
Deleting key thanhdaonguyen-once-upon-a-t-v37/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key thanhdaonguyen-once-upon-a-t-v37/tokenizer.json from bucket guanaco-mkml-models
Deleting key thanhdaonguyen-once-upon-a-t-v37/tokenizer.model from bucket guanaco-mkml-models
Deleting key thanhdaonguyen-once-upon-a-t-v37/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key thanhdaonguyen-once-upon-a-t-v37_reward/config.json from bucket guanaco-reward-models
Deleting key thanhdaonguyen-once-upon-a-t-v37_reward/merges.txt from bucket guanaco-reward-models
Deleting key thanhdaonguyen-once-upon-a-t-v37_reward/reward.tensors from bucket guanaco-reward-models
Deleting key thanhdaonguyen-once-upon-a-t-v37_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key thanhdaonguyen-once-upon-a-t-v37_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key thanhdaonguyen-once-upon-a-t-v37_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key thanhdaonguyen-once-upon-a-t-v37_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.39s
thanhdaonguyen-once-upon-a-t_v37 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics