submission_id: thanhdaonguyen-once-upon-a-t_v30
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': 8, '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: 2024-02-16T00:39:08+00:00
model_name: thanhdaonguyen-once-upon-a-t_v30
model_eval_status: success
model_group: thanhdaonguyen/once-upon
num_battles: 122924
num_wins: 61008
celo_rating: 1153.52
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: None
model_num_parameters: 13015864320.0
best_of: 8
max_input_tokens: 512
max_output_tokens: 64
display_name: thanhdaonguyen-once-upon-a-t_v30
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: 2024-02-15
win_ratio: 0.4963066610263252
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name thanhdaonguyen-once-upon-a-t-v30-mkmlizer
Waiting for job on thanhdaonguyen-once-upon-a-t-v30-mkmlizer to finish
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: ║ _____ __ __ ║
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: ║ /___/ ║
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: ║ ║
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: ║ Version: 0.6.11 ║
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: ║ ║
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: ║ The license key for the current software has been verified as ║
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: ║ belonging to: ║
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: ║ ║
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: ║ Chai Research Corp. ║
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: ║ Expiration: 2024-04-15 23:59:59 ║
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: ║ ║
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 19.5MB/s]
thanhdaonguyen-once-upon-a-t-v30-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, 278kB/s]
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: config.json: 0%| | 0.00/643 [00:00<?, ?B/s] config.json: 100%|██████████| 643/643 [00:00<00:00, 10.5MB/s]
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: generation_config.json: 0%| | 0.00/154 [00:00<?, ?B/s] generation_config.json: 100%|██████████| 154/154 [00:00<00:00, 1.25MB/s]
thanhdaonguyen-once-upon-a-t-v30-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<05:59, 27.5MB/s] pytorch_model-00002-of-00003.bin: 0%| | 21.0M/9.90G [00:00<04:44, 34.8MB/s] pytorch_model-00002-of-00003.bin: 1%| | 52.4M/9.90G [00:00<01:50, 89.5MB/s] pytorch_model-00002-of-00003.bin: 1%| | 105M/9.90G [00:00<00:53, 184MB/s] pytorch_model-00002-of-00003.bin: 2%|▏ | 199M/9.90G [00:00<00:26, 361MB/s] pytorch_model-00002-of-00003.bin: 3%|▎ | 294M/9.90G [00:01<00:19, 483MB/s] pytorch_model-00002-of-00003.bin: 4%|▍ | 440M/9.90G [00:01<00:13, 709MB/s] pytorch_model-00002-of-00003.bin: 8%|▊ | 765M/9.90G [00:01<00:06, 1.36GB/s] pytorch_model-00002-of-00003.bin: 10%|▉ | 975M/9.90G [00:01<00:05, 1.51GB/s] pytorch_model-00002-of-00003.bin: 15%|█▍ | 1.46G/9.90G [00:01<00:03, 2.39GB/s] pytorch_model-00002-of-00003.bin: 17%|█▋ | 1.72G/9.90G [00:02<00:07, 1.16GB/s] pytorch_model-00002-of-00003.bin: 19%|█▉ | 1.92G/9.90G [00:02<00:07, 1.08GB/s] pytorch_model-00002-of-00003.bin: 21%|██ | 2.09G/9.90G [00:02<00:07, 1.04GB/s] pytorch_model-00002-of-00003.bin: 24%|██▍ | 2.40G/9.90G [00:02<00:05, 1.38GB/s] pytorch_model-00002-of-00003.bin: 27%|██▋ | 2.71G/9.90G [00:02<00:04, 1.69GB/s] pytorch_model-00002-of-00003.bin: 30%|███ | 2.98G/9.90G [00:02<00:03, 1.89GB/s] pytorch_model-00002-of-00003.bin: 33%|███▎ | 3.22G/9.90G [00:02<00:03, 1.75GB/s] pytorch_model-00002-of-00003.bin: 35%|███▍ | 3.43G/9.90G [00:03<00:03, 1.64GB/s] pytorch_model-00002-of-00003.bin: 37%|███▋ | 3.62G/9.90G [00:03<00:03, 1.59GB/s] pytorch_model-00002-of-00003.bin: 38%|███▊ | 3.80G/9.90G [00:03<00:04, 1.24GB/s] pytorch_model-00002-of-00003.bin: 41%|████ | 4.02G/9.90G [00:03<00:04, 1.43GB/s] pytorch_model-00002-of-00003.bin: 42%|████▏ | 4.18G/9.90G [00:03<00:04, 1.42GB/s] pytorch_model-00002-of-00003.bin: 45%|████▍ | 4.46G/9.90G [00:03<00:03, 1.71GB/s] pytorch_model-00002-of-00003.bin: 47%|████▋ | 4.66G/9.90G [00:03<00:03, 1.40GB/s] pytorch_model-00002-of-00003.bin: 49%|████▊ | 4.82G/9.90G [00:04<00:03, 1.37GB/s] pytorch_model-00002-of-00003.bin: 50%|█████ | 4.99G/9.90G [00:04<00:03, 1.40GB/s] pytorch_model-00002-of-00003.bin: 52%|█████▏ | 5.15G/9.90G [00:04<00:03, 1.43GB/s] pytorch_model-00002-of-00003.bin: 54%|█████▍ | 5.35G/9.90G [00:04<00:02, 1.56GB/s] pytorch_model-00002-of-00003.bin: 56%|█████▌ | 5.54G/9.90G [00:04<00:02, 1.63GB/s] pytorch_model-00002-of-00003.bin: 58%|█████▊ | 5.71G/9.90G [00:04<00:02, 1.58GB/s] pytorch_model-00002-of-00003.bin: 59%|█████▉ | 5.88G/9.90G [00:04<00:02, 1.46GB/s] pytorch_model-00002-of-00003.bin: 61%|██████ | 6.04G/9.90G [00:04<00:02, 1.37GB/s] pytorch_model-00002-of-00003.bin: 63%|██████▎ | 6.25G/9.90G [00:05<00:02, 1.55GB/s] pytorch_model-00002-of-00003.bin: 65%|██████▍ | 6.42G/9.90G [00:05<00:02, 1.37GB/s] pytorch_model-00002-of-00003.bin: 66%|██████▋ | 6.56G/9.90G [00:05<00:02, 1.31GB/s] pytorch_model-00002-of-00003.bin: 68%|██████▊ | 6.71G/9.90G [00:05<00:02, 1.28GB/s] pytorch_model-00002-of-00003.bin: 69%|██████▉ | 6.85G/9.90G [00:05<00:02, 1.24GB/s] pytorch_model-00002-of-00003.bin: 71%|███████ | 7.04G/9.90G [00:05<00:02, 1.39GB/s] pytorch_model-00002-of-00003.bin: 73%|███████▎ | 7.25G/9.90G [00:05<00:01, 1.50GB/s] pytorch_model-00002-of-00003.bin: 75%|███████▌ | 7.44G/9.90G [00:05<00:01, 1.63GB/s] pytorch_model-00002-of-00003.bin: 77%|███████▋ | 7.64G/9.90G [00:05<00:01, 1.73GB/s] pytorch_model-00002-of-00003.bin: 79%|███████▉ | 7.84G/9.90G [00:06<00:01, 1.76GB/s] pytorch_model-00002-of-00003.bin: 81%|████████ | 8.02G/9.90G [00:06<00:01, 1.72GB/s] pytorch_model-00002-of-00003.bin: 84%|████████▎ | 8.29G/9.90G [00:06<00:00, 2.00GB/s] pytorch_model-00002-of-00003.bin: 89%|████████▊ | 8.78G/9.90G [00:06<00:00, 2.79GB/s] pytorch_model-00002-of-00003.bin: 91%|█████████▏| 9.06G/9.90G [00:06<00:00, 1.30GB/s] pytorch_model-00002-of-00003.bin: 94%|█████████▎| 9.28G/9.90G [00:07<00:00, 1.36GB/s] pytorch_model-00002-of-00003.bin: 96%|█████████▌| 9.48G/9.90G [00:07<00:00, 1.37GB/s] pytorch_model-00002-of-00003.bin: 98%|█████████▊| 9.67G/9.90G [00:07<00:00, 1.15GB/s] pytorch_model-00002-of-00003.bin: 99%|█████████▉| 9.83G/9.90G [00:08<00:00, 521MB/s] pytorch_model-00002-of-00003.bin: 100%|█████████▉| 9.90G/9.90G [00:08<00:00, 1.13GB/s]
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: pytorch_model-00003-of-00003.bin: 0%| | 0.00/6.18G [00:00<?, ?B/s] pytorch_model-00003-of-00003.bin: 0%| | 10.5M/6.18G [00:00<03:18, 31.0MB/s] pytorch_model-00003-of-00003.bin: 0%| | 21.0M/6.18G [00:00<02:19, 44.1MB/s] pytorch_model-00003-of-00003.bin: 1%| | 62.9M/6.18G [00:00<00:43, 139MB/s] pytorch_model-00003-of-00003.bin: 3%|▎ | 178M/6.18G [00:00<00:14, 400MB/s] pytorch_model-00003-of-00003.bin: 6%|▌ | 367M/6.18G [00:00<00:07, 767MB/s] pytorch_model-00003-of-00003.bin: 8%|▊ | 514M/6.18G [00:00<00:05, 948MB/s] pytorch_model-00003-of-00003.bin: 10%|█ | 629M/6.18G [00:01<00:06, 884MB/s] pytorch_model-00003-of-00003.bin: 12%|█▏ | 734M/6.18G [00:01<00:06, 891MB/s] pytorch_model-00003-of-00003.bin: 14%|█▎ | 839M/6.18G [00:01<00:05, 903MB/s] pytorch_model-00003-of-00003.bin: 15%|█▌ | 944M/6.18G [00:01<00:06, 851MB/s] pytorch_model-00003-of-00003.bin: 18%|█▊ | 1.09G/6.18G [00:01<00:05, 999MB/s] pytorch_model-00003-of-00003.bin: 20%|█▉ | 1.21G/6.18G [00:01<00:04, 1.01GB/s] pytorch_model-00003-of-00003.bin: 23%|██▎ | 1.42G/6.18G [00:01<00:03, 1.29GB/s] pytorch_model-00003-of-00003.bin: 25%|██▌ | 1.55G/6.18G [00:01<00:03, 1.30GB/s] pytorch_model-00003-of-00003.bin: 27%|██▋ | 1.69G/6.18G [00:02<00:03, 1.25GB/s] pytorch_model-00003-of-00003.bin: 30%|███ | 1.88G/6.18G [00:02<00:03, 1.41GB/s] pytorch_model-00003-of-00003.bin: 33%|███▎ | 2.04G/6.18G [00:02<00:02, 1.48GB/s] pytorch_model-00003-of-00003.bin: 36%|███▌ | 2.22G/6.18G [00:02<00:02, 1.55GB/s] pytorch_model-00003-of-00003.bin: 41%|████ | 2.52G/6.18G [00:02<00:01, 1.94GB/s] pytorch_model-00003-of-00003.bin: 45%|████▌ | 2.80G/6.18G [00:02<00:01, 2.15GB/s] pytorch_model-00003-of-00003.bin: 50%|████▉ | 3.08G/6.18G [00:02<00:01, 2.30GB/s] pytorch_model-00003-of-00003.bin: 54%|█████▍ | 3.32G/6.18G [00:02<00:01, 1.69GB/s] pytorch_model-00003-of-00003.bin: 57%|█████▋ | 3.52G/6.18G [00:02<00:01, 1.68GB/s] pytorch_model-00003-of-00003.bin: 60%|██████ | 3.72G/6.18G [00:03<00:01, 1.63GB/s] pytorch_model-00003-of-00003.bin: 63%|██████▎ | 3.90G/6.18G [00:03<00:01, 1.55GB/s] pytorch_model-00003-of-00003.bin: 66%|██████▌ | 4.07G/6.18G [00:03<00:01, 1.37GB/s] pytorch_model-00003-of-00003.bin: 68%|██████▊ | 4.22G/6.18G [00:03<00:01, 1.29GB/s] pytorch_model-00003-of-00003.bin: 70%|███████ | 4.35G/6.18G [00:03<00:01, 1.29GB/s] pytorch_model-00003-of-00003.bin: 74%|███████▎ | 4.55G/6.18G [00:03<00:01, 1.30GB/s] pytorch_model-00003-of-00003.bin: 77%|███████▋ | 4.73G/6.18G [00:03<00:01, 1.41GB/s] pytorch_model-00003-of-00003.bin: 79%|███████▉ | 4.88G/6.18G [00:04<00:00, 1.34GB/s] pytorch_model-00003-of-00003.bin: 81%|████████▏ | 5.02G/6.18G [00:04<00:00, 1.37GB/s] pytorch_model-00003-of-00003.bin: 84%|████████▍ | 5.19G/6.18G [00:04<00:00, 1.44GB/s] pytorch_model-00003-of-00003.bin: 88%|████████▊ | 5.44G/6.18G [00:04<00:00, 1.74GB/s] pytorch_model-00003-of-00003.bin: 93%|█████████▎| 5.74G/6.18G [00:04<00:00, 2.07GB/s] pytorch_model-00003-of-00003.bin: 96%|█████████▋| 5.96G/6.18G [00:04<00:00, 1.30GB/s] pytorch_model-00003-of-00003.bin: 99%|█████████▉| 6.14G/6.18G [00:05<00:00, 690MB/s] pytorch_model-00003-of-00003.bin: 100%|█████████▉| 6.18G/6.18G [00:06<00:00, 1.01GB/s]
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: pytorch_model.bin.index.json: 0%| | 0.00/29.9k [00:00<?, ?B/s] pytorch_model.bin.index.json: 100%|██████████| 29.9k/29.9k [00:00<00:00, 11.5MB/s]
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: special_tokens_map.json: 0%| | 0.00/438 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 438/438 [00:00<00:00, 2.23MB/s]
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: tokenizer.json: 0%| | 0.00/1.84M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 1.84M/1.84M [00:00<00:00, 15.9MB/s] tokenizer.json: 100%|██████████| 1.84M/1.84M [00:00<00:00, 15.8MB/s]
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: tokenizer.model: 0%| | 0.00/500k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 500k/500k [00:00<00:00, 5.44MB/s]
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: tokenizer_config.json: 0%| | 0.00/828 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 828/828 [00:00<00:00, 6.72MB/s]
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: Downloaded to shared memory in 54.128s
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: quantizing model to /dev/shm/model_cache
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: Saving mkml model at /dev/shm/model_cache
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: Reading /tmp/tmpk3fggcmt/pytorch_model.bin.index.json
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: Profiling: 0%| | 0/363 [00:00<?, ?it/s] Profiling: 0%| | 1/363 [00:04<26:06, 4.33s/it] Profiling: 38%|███▊ | 139/363 [00:06<00:08, 26.22it/s] Profiling: 77%|███████▋ | 278/363 [00:07<00:01, 47.12it/s] Profiling: 100%|██████████| 363/363 [00:09<00:00, 48.57it/s] Profiling: 100%|██████████| 363/363 [00:09<00:00, 38.05it/s]
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: quantized model in 28.578s
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: Processed model thanhdaonguyen/once-upon-a-time in 84.482s
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: creating bucket guanaco-mkml-models
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/thanhdaonguyen-once-upon-a-t-v30
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/thanhdaonguyen-once-upon-a-t-v30/special_tokens_map.json
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/thanhdaonguyen-once-upon-a-t-v30/tokenizer_config.json
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/thanhdaonguyen-once-upon-a-t-v30/added_tokens.json
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/thanhdaonguyen-once-upon-a-t-v30/config.json
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/thanhdaonguyen-once-upon-a-t-v30/tokenizer.model
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/thanhdaonguyen-once-upon-a-t-v30/tokenizer.json
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/thanhdaonguyen-once-upon-a-t-v30/mkml_model.tensors
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: loading reward model from rirv938/gpt2_ties_merge_preference_plus_classic_e2_density_99
thanhdaonguyen-once-upon-a-t-v30-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-v30-mkmlizer: warnings.warn(
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: config.json: 0%| | 0.00/983 [00:00<?, ?B/s] config.json: 100%|██████████| 983/983 [00:00<00:00, 12.5MB/s]
thanhdaonguyen-once-upon-a-t-v30-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-v30-mkmlizer: warnings.warn(
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: tokenizer_config.json: 0%| | 0.00/445 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 445/445 [00:00<00:00, 3.28MB/s]
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: vocab.json: 0%| | 0.00/798k [00:00<?, ?B/s] vocab.json: 100%|██████████| 798k/798k [00:00<00:00, 7.86MB/s] vocab.json: 100%|██████████| 798k/798k [00:00<00:00, 7.84MB/s]
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: merges.txt: 0%| | 0.00/456k [00:00<?, ?B/s] merges.txt: 100%|██████████| 456k/456k [00:00<00:00, 37.4MB/s]
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 24.0MB/s]
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: special_tokens_map.json: 0%| | 0.00/441 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 441/441 [00:00<00:00, 4.05MB/s]
thanhdaonguyen-once-upon-a-t-v30-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-v30-mkmlizer: warnings.warn(
thanhdaonguyen-once-upon-a-t-v30-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, 49.2MB/s]
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: Downloading shards: 0%| | 0/1 [00:00<?, ?it/s]
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: model-00001-of-00001.safetensors: 0%| | 0.00/249M [00:00<?, ?B/s]
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: model-00001-of-00001.safetensors: 4%|▍ | 10.5M/249M [00:00<00:08, 29.4MB/s]
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: model-00001-of-00001.safetensors: 13%|█▎ | 31.5M/249M [00:00<00:02, 77.6MB/s] model-00001-of-00001.safetensors: 100%|█████████▉| 249M/249M [00:00<00:00, 443MB/s]
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: Downloading shards: 100%|██████████| 1/1 [00:01<00:00, 1.02s/it] Downloading shards: 100%|██████████| 1/1 [00:01<00:00, 1.02s/it]
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: Saving duration: 0.089s
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: Processed model rirv938/gpt2_ties_merge_preference_plus_classic_e2_density_99 in 3.187s
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: creating bucket guanaco-reward-models
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: Bucket 's3://guanaco-reward-models/' created
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/thanhdaonguyen-once-upon-a-t-v30_reward
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/thanhdaonguyen-once-upon-a-t-v30_reward/config.json
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/thanhdaonguyen-once-upon-a-t-v30_reward/special_tokens_map.json
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/thanhdaonguyen-once-upon-a-t-v30_reward/tokenizer_config.json
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/thanhdaonguyen-once-upon-a-t-v30_reward/merges.txt
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/thanhdaonguyen-once-upon-a-t-v30_reward/vocab.json
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/thanhdaonguyen-once-upon-a-t-v30_reward/tokenizer.json
thanhdaonguyen-once-upon-a-t-v30-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/thanhdaonguyen-once-upon-a-t-v30_reward/reward.tensors
Job thanhdaonguyen-once-upon-a-t-v30-mkmlizer completed after 107.22s with status: succeeded
Stopping job with name thanhdaonguyen-once-upon-a-t-v30-mkmlizer
Pipeline stage MKMLizer completed in 112.87s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service thanhdaonguyen-once-upon-a-t-v30
Waiting for inference service thanhdaonguyen-once-upon-a-t-v30 to be ready
Inference service thanhdaonguyen-once-upon-a-t-v30 ready after 40.270747423172s
Pipeline stage ISVCDeployer completed in 48.52s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6463351249694824s
Received healthy response to inference request in 1.7446951866149902s
Received healthy response to inference request in 1.7786741256713867s
Received healthy response to inference request in 1.5570156574249268s
Received healthy response to inference request in 1.777517557144165s
5 requests
0 failed requests
5th percentile: 1.5945515632629395
10th percentile: 1.6320874691009521
20th percentile: 1.7071592807769775
30th percentile: 1.7512596607208253
40th percentile: 1.7643886089324952
50th percentile: 1.777517557144165
60th percentile: 1.7779801845550538
70th percentile: 1.7784428119659423
80th percentile: 1.952206325531006
90th percentile: 2.2992707252502442
95th percentile: 2.472802925109863
99th percentile: 2.6116286849975587
mean time: 1.9008475303649903
Pipeline stage StressChecker completed in 10.47s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.04s
Running M-Eval for topic stay_in_character
M-Eval Dataset for topic stay_in_character is loaded
AUTO_DEACTIVATION: submission %s deactivated %s
thanhdaonguyen-once-upon-a-t_v30 status is now inactive due to auto deactivation removed underperforming models
thanhdaonguyen-once-upon-a-t_v30 status is now deployed due to admin request
thanhdaonguyen-once-upon-a-t_v30 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of thanhdaonguyen-once-upon-a-t_v30
Running pipeline stage ISVCDeleter
Checking if service thanhdaonguyen-once-upon-a-t-v30 is running
Tearing down inference service thanhdaonguyen-once-upon-a-t-v30
Toredown service thanhdaonguyen-once-upon-a-t-v30
Pipeline stage ISVCDeleter completed in 3.18s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key thanhdaonguyen-once-upon-a-t-v30/added_tokens.json from bucket guanaco-mkml-models
Deleting key thanhdaonguyen-once-upon-a-t-v30/config.json from bucket guanaco-mkml-models
Deleting key thanhdaonguyen-once-upon-a-t-v30/mkml_model.tensors from bucket guanaco-mkml-models
Deleting key thanhdaonguyen-once-upon-a-t-v30/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key thanhdaonguyen-once-upon-a-t-v30/tokenizer.json from bucket guanaco-mkml-models
Deleting key thanhdaonguyen-once-upon-a-t-v30/tokenizer.model from bucket guanaco-mkml-models
Deleting key thanhdaonguyen-once-upon-a-t-v30/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key thanhdaonguyen-once-upon-a-t-v30_reward/config.json from bucket guanaco-reward-models
Deleting key thanhdaonguyen-once-upon-a-t-v30_reward/merges.txt from bucket guanaco-reward-models
Deleting key thanhdaonguyen-once-upon-a-t-v30_reward/reward.tensors from bucket guanaco-reward-models
Deleting key thanhdaonguyen-once-upon-a-t-v30_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key thanhdaonguyen-once-upon-a-t-v30_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key thanhdaonguyen-once-upon-a-t-v30_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key thanhdaonguyen-once-upon-a-t-v30_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.65s
thanhdaonguyen-once-upon-a-t_v30 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics