abacusai-smaug-llama-3-7_7578

submission_id: abacusai-smaug-llama-3-7_7578_v1
developer_uid: alexdaoud
best_of: 4
celo_rating: 1178.82
display_name: abacusai-smaug-llama-3-7_7578_v1
family_friendly_score: 0.0
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}:', 'truncate_by_message': False}
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 50, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
is_internal_developer: True
language_model: abacusai/Smaug-Llama-3-70B-Instruct
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: abacusai/Smaug-Llama-3-7
model_name: abacusai-smaug-llama-3-7_7578_v1
model_num_parameters: 70553706496.0
model_repo: abacusai/Smaug-Llama-3-70B-Instruct
model_size: 71B
num_battles: 116686
num_wins: 56882
ranking_group: single
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
reward_repo: rirv938/gpt2_ties_merge_preference_plus_classic_e2_density_99
status: torndown
submission_type: basic
timestamp: 2024-05-19T14:15:48+00:00
us_pacific_date: 2024-05-19
win_ratio: 0.4874792177296334
Resubmit model
Running pipeline stage MKMLizer
Starting job with name abacusai-smaug-llama-3-7-7578-v1-mkmlizer
Waiting for job on abacusai-smaug-llama-3-7-7578-v1-mkmlizer to finish
Stopping job with name abacusai-smaug-llama-3-7-7578-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name abacusai-smaug-llama-3-7-7578-v1-mkmlizer
Waiting for job on abacusai-smaug-llama-3-7-7578-v1-mkmlizer to finish
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: ║     _____            __           __                                ║
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: ║       /___/                                                         ║
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: ║                                                                     ║
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: ║  https://mk1.ai                                                     ║
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: ║                                                                     ║
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: ║  belonging to:                                                      ║
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: ║                                                                     ║
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: ║  Chai Research Corp.                                                ║
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: ║                                                                     ║
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
abacusai-smaug-llama-3-7-7578-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: Downloaded to shared memory in 199.435s
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: quantizing model to /dev/shm/model_cache
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: 
Loading 0:   0%|          | 0/723 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/723 [00:00<00:18, 38.68it/s]
Loading 0:   2%|▏         | 14/723 [00:00<00:11, 64.10it/s]
Loading 0:   3%|▎         | 21/723 [00:00<00:23, 29.73it/s]
Loading 0:   4%|▎         | 26/723 [00:00<00:20, 33.72it/s]
Loading 0:   4%|▍         | 32/723 [00:00<00:19, 36.02it/s]
Loading 0:   6%|▌         | 42/723 [00:01<00:19, 34.12it/s]
Loading 0:   7%|▋         | 47/723 [00:01<00:19, 34.44it/s]
Loading 0:   7%|▋         | 51/723 [00:01<00:20, 33.56it/s]
Loading 0:   8%|▊         | 58/723 [00:01<00:16, 39.75it/s]
Loading 0:   9%|▉         | 68/723 [00:01<00:19, 32.86it/s]
Loading 0:  10%|▉         | 72/723 [00:02<00:20, 31.68it/s]
Loading 0:  11%|█         | 76/723 [00:02<00:19, 32.90it/s]
Loading 0:  12%|█▏        | 84/723 [00:02<00:15, 40.43it/s]
Loading 0:  12%|█▏        | 89/723 [00:02<00:15, 41.48it/s]
Loading 0:  13%|█▎        | 94/723 [00:02<00:26, 24.03it/s]
Loading 0:  14%|█▍        | 102/723 [00:03<00:19, 31.40it/s]
Loading 0:  15%|█▍        | 107/723 [00:03<00:18, 33.91it/s]
Loading 0:  15%|█▌        | 112/723 [00:03<00:16, 36.53it/s]
Loading 0:  16%|█▌        | 117/723 [00:03<00:25, 24.11it/s]
Loading 0:  17%|█▋        | 122/723 [00:03<00:22, 26.59it/s]
Loading 0:  17%|█▋        | 126/723 [00:13<06:23,  1.56it/s]
Loading 0:  18%|█▊        | 131/723 [00:13<04:29,  2.20it/s]
Loading 0:  19%|█▉        | 140/723 [00:14<02:31,  3.84it/s]
Loading 0:  20%|██        | 146/723 [00:14<01:58,  4.86it/s]
Loading 0:  21%|██        | 151/723 [00:14<01:31,  6.27it/s]
Loading 0:  22%|██▏       | 157/723 [00:14<01:05,  8.62it/s]
Loading 0:  23%|██▎       | 166/723 [00:14<00:41, 13.42it/s]
Loading 0:  24%|██▍       | 172/723 [00:15<00:39, 13.95it/s]
Loading 0:  24%|██▍       | 177/723 [00:15<00:32, 16.56it/s]
Loading 0:  25%|██▌       | 184/723 [00:15<00:24, 21.87it/s]
Loading 0:  27%|██▋       | 194/723 [00:15<00:22, 23.91it/s]
Loading 0:  28%|██▊       | 199/723 [00:16<00:22, 23.71it/s]
Loading 0:  28%|██▊       | 203/723 [00:16<00:21, 24.74it/s]
Loading 0:  29%|██▉       | 211/723 [00:16<00:15, 32.23it/s]
Loading 0:  30%|███       | 218/723 [00:16<00:18, 27.58it/s]
Loading 0:  31%|███       | 222/723 [00:16<00:18, 27.78it/s]
Loading 0:  32%|███▏      | 229/723 [00:16<00:14, 34.18it/s]
Loading 0:  33%|███▎      | 236/723 [00:17<00:12, 39.50it/s]
Loading 0:  33%|███▎      | 242/723 [00:17<00:17, 28.24it/s]
Loading 0:  34%|███▍      | 247/723 [00:17<00:15, 30.08it/s]
Loading 0:  35%|███▌      | 255/723 [00:17<00:12, 36.35it/s]
Loading 0:  36%|███▌      | 260/723 [00:17<00:12, 38.20it/s]
Loading 0:  37%|███▋      | 265/723 [00:28<04:13,  1.81it/s]
Loading 0:  37%|███▋      | 268/723 [00:28<03:33,  2.13it/s]
Loading 0:  38%|███▊      | 272/723 [00:28<02:43,  2.77it/s]
Loading 0:  38%|███▊      | 275/723 [00:28<02:11,  3.42it/s]
Loading 0:  39%|███▉      | 283/723 [00:28<01:13,  6.00it/s]
Loading 0:  41%|████      | 293/723 [00:28<00:41, 10.33it/s]
Loading 0:  41%|████▏     | 299/723 [00:29<00:37, 11.37it/s]
Loading 0:  42%|████▏     | 304/723 [00:29<00:30, 13.73it/s]
Loading 0:  43%|████▎     | 310/723 [00:29<00:23, 17.50it/s]
Loading 0:  44%|████▍     | 319/723 [00:29<00:15, 25.48it/s]
Loading 0:  45%|████▍     | 325/723 [00:30<00:18, 21.19it/s]
Loading 0:  46%|████▌     | 330/723 [00:30<00:16, 23.87it/s]
Loading 0:  47%|████▋     | 337/723 [00:30<00:12, 30.03it/s]
Loading 0:  48%|████▊     | 344/723 [00:30<00:14, 26.81it/s]
Loading 0:  48%|████▊     | 349/723 [00:30<00:12, 28.85it/s]
Loading 0:  49%|████▉     | 355/723 [00:30<00:10, 33.65it/s]
Loading 0:  50%|█████     | 362/723 [00:30<00:09, 39.55it/s]
Loading 0:  51%|█████     | 368/723 [00:31<00:11, 30.16it/s]
Loading 0:  52%|█████▏    | 373/723 [00:31<00:11, 31.30it/s]
Loading 0:  53%|█████▎    | 381/723 [00:31<00:08, 39.36it/s]
Loading 0:  53%|█████▎    | 386/723 [00:31<00:08, 41.42it/s]
Loading 0:  54%|█████▍    | 394/723 [00:31<00:10, 32.78it/s]
Loading 0:  55%|█████▌    | 399/723 [00:32<00:09, 33.63it/s]
Loading 0:  55%|█████▌    | 400/723 [00:42<00:09, 33.63it/s]
Loading 0:  55%|█████▌    | 401/723 [00:42<03:25,  1.56it/s]
Loading 0:  57%|█████▋    | 409/723 [00:42<02:00,  2.61it/s]
Loading 0:  58%|█████▊    | 418/723 [00:42<01:11,  4.24it/s]
Loading 0:  59%|█████▊    | 424/723 [00:42<00:58,  5.14it/s]
Loading 0:  59%|█████▉    | 429/723 [00:42<00:45,  6.52it/s]
Loading 0:  60%|██████    | 436/723 [00:43<00:31,  9.23it/s]
Loading 0:  62%|██████▏   | 446/723 [00:43<00:22, 12.43it/s]
Loading 0:  62%|██████▏   | 451/723 [00:43<00:18, 14.44it/s]
Loading 0:  63%|██████▎   | 455/723 [00:43<00:16, 16.15it/s]
Loading 0:  64%|██████▍   | 463/723 [00:43<00:11, 22.35it/s]
Loading 0:  65%|██████▌   | 470/723 [00:44<00:11, 21.28it/s]
Loading 0:  66%|██████▌   | 474/723 [00:44<00:11, 22.23it/s]
Loading 0:  67%|██████▋   | 481/723 [00:44<00:08, 28.23it/s]
Loading 0:  67%|██████▋   | 488/723 [00:44<00:06, 33.81it/s]
Loading 0:  68%|██████▊   | 494/723 [00:45<00:08, 26.62it/s]
Loading 0:  69%|██████▉   | 499/723 [00:45<00:07, 28.59it/s]
Loading 0:  70%|███████   | 507/723 [00:45<00:05, 36.02it/s]
Loading 0:  71%|███████   | 512/723 [00:45<00:05, 37.74it/s]
Loading 0:  72%|███████▏  | 520/723 [00:45<00:06, 29.59it/s]
Loading 0:  73%|███████▎  | 525/723 [00:45<00:06, 31.18it/s]
Loading 0:  73%|███████▎  | 530/723 [00:45<00:05, 34.11it/s]
Loading 0:  74%|███████▍  | 535/723 [00:46<00:05, 36.78it/s]
Loading 0:  75%|███████▍  | 541/723 [00:56<01:38,  1.85it/s]
Loading 0:  76%|███████▌  | 546/723 [00:56<01:13,  2.41it/s]
Loading 0:  76%|███████▌  | 549/723 [00:56<01:00,  2.89it/s]
Loading 0:  77%|███████▋  | 554/723 [00:56<00:41,  4.04it/s]
Loading 0:  78%|███████▊  | 562/723 [00:56<00:24,  6.63it/s]
Loading 0:  79%|███████▉  | 572/723 [00:57<00:15,  9.70it/s]
Loading 0:  80%|███████▉  | 576/723 [00:57<00:13, 11.11it/s]
Loading 0:  80%|████████  | 580/723 [00:57<00:10, 13.14it/s]
Loading 0:  81%|████████▏ | 588/723 [00:57<00:07, 18.94it/s]
Loading 0:  82%|████████▏ | 593/723 [00:57<00:05, 22.18it/s]
Loading 0:  83%|████████▎ | 598/723 [00:58<00:07, 17.69it/s]
Loading 0:  84%|████████▍ | 606/723 [00:58<00:04, 23.99it/s]
Loading 0:  85%|████████▍ | 611/723 [00:58<00:04, 26.79it/s]
Loading 0:  85%|████████▌ | 616/723 [00:58<00:03, 29.82it/s]
Loading 0:  86%|████████▌ | 621/723 [00:59<00:05, 19.83it/s]
Loading 0:  87%|████████▋ | 626/723 [00:59<00:04, 22.76it/s]
Loading 0:  88%|████████▊ | 634/723 [00:59<00:02, 30.64it/s]
Loading 0:  89%|████████▊ | 641/723 [00:59<00:02, 35.81it/s]
Loading 0:  89%|████████▉ | 646/723 [00:59<00:02, 27.23it/s]
Loading 0:  90%|█████████ | 651/723 [00:59<00:02, 29.19it/s]
Loading 0:  91%|█████████ | 656/723 [00:59<00:02, 32.58it/s]
Loading 0:  91%|█████████▏| 661/723 [01:00<00:01, 35.44it/s]
Loading 0:  93%|█████████▎| 670/723 [01:00<00:01, 46.97it/s]
Loading 0:  93%|█████████▎| 676/723 [01:00<00:01, 27.84it/s]
Loading 0:  94%|█████████▍| 681/723 [01:10<00:22,  1.86it/s]
Loading 0:  95%|█████████▌| 688/723 [01:10<00:12,  2.76it/s]
Loading 0:  96%|█████████▋| 696/723 [01:10<00:06,  4.20it/s]
Loading 0:  97%|█████████▋| 702/723 [01:11<00:04,  5.04it/s]
Loading 0:  98%|█████████▊| 707/723 [01:11<00:02,  6.34it/s]
Loading 0:  99%|█████████▉| 715/723 [01:11<00:00,  9.38it/s]
Loading 0: 100%|██████████| 723/723 [01:21<00:00,  2.09it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: quantized model in 94.618s
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: Processed model abacusai/Smaug-Llama-3-70B-Instruct in 303.588s
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: creating bucket guanaco-mkml-models
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/abacusai-smaug-llama-3-7-7578-v1
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/abacusai-smaug-llama-3-7-7578-v1/special_tokens_map.json
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/abacusai-smaug-llama-3-7-7578-v1/tokenizer_config.json
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/abacusai-smaug-llama-3-7-7578-v1/config.json
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/abacusai-smaug-llama-3-7-7578-v1/tokenizer.json
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.5.safetensors s3://guanaco-mkml-models/abacusai-smaug-llama-3-7-7578-v1/flywheel_model.5.safetensors
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/abacusai-smaug-llama-3-7-7578-v1/flywheel_model.1.safetensors
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.4.safetensors s3://guanaco-mkml-models/abacusai-smaug-llama-3-7-7578-v1/flywheel_model.4.safetensors
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/abacusai-smaug-llama-3-7-7578-v1/flywheel_model.3.safetensors
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/abacusai-smaug-llama-3-7-7578-v1/flywheel_model.0.safetensors
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/abacusai-smaug-llama-3-7-7578-v1/flywheel_model.2.safetensors
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: loading reward model from rirv938/gpt2_ties_merge_preference_plus_classic_e2_density_99
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:913: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
abacusai-smaug-llama-3-7-7578-v1-mkmlizer:   warnings.warn(
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:757: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
abacusai-smaug-llama-3-7-7578-v1-mkmlizer:   warnings.warn(
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:468: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
abacusai-smaug-llama-3-7-7578-v1-mkmlizer:   warnings.warn(
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: 
Downloading shards:   0%|          | 0/1 [00:00<?, ?it/s]
Downloading shards: 100%|██████████| 1/1 [00:01<00:00,  1.50s/it]
Downloading shards: 100%|██████████| 1/1 [00:01<00:00,  1.50s/it]
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: Saving duration: 0.098s
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: Processed model rirv938/gpt2_ties_merge_preference_plus_classic_e2_density_99 in 3.313s
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: creating bucket guanaco-reward-models
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/abacusai-smaug-llama-3-7-7578-v1_reward
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/abacusai-smaug-llama-3-7-7578-v1_reward/config.json
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/abacusai-smaug-llama-3-7-7578-v1_reward/special_tokens_map.json
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/abacusai-smaug-llama-3-7-7578-v1_reward/tokenizer_config.json
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/abacusai-smaug-llama-3-7-7578-v1_reward/merges.txt
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/abacusai-smaug-llama-3-7-7578-v1_reward/vocab.json
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/abacusai-smaug-llama-3-7-7578-v1_reward/tokenizer.json
abacusai-smaug-llama-3-7-7578-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/abacusai-smaug-llama-3-7-7578-v1_reward/reward.tensors
Job abacusai-smaug-llama-3-7-7578-v1-mkmlizer completed after 390.83s with status: succeeded
Stopping job with name abacusai-smaug-llama-3-7-7578-v1-mkmlizer
Pipeline stage MKMLizer completed in 394.58s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service abacusai-smaug-llama-3-7-7578-v1
Waiting for inference service abacusai-smaug-llama-3-7-7578-v1 to be ready
Inference service abacusai-smaug-llama-3-7-7578-v1 ready after 130.7873513698578s
Pipeline stage ISVCDeployer completed in 137.79s
Running pipeline stage StressChecker
Received healthy response to inference request in 5.21165919303894s
Received healthy response to inference request in 4.189810752868652s
Received healthy response to inference request in 4.192179918289185s
Received healthy response to inference request in 4.195162296295166s
Received healthy response to inference request in 4.190882205963135s
5 requests
0 failed requests
5th percentile: 4.190025043487549
10th percentile: 4.190239334106446
20th percentile: 4.190667915344238
30th percentile: 4.191141748428345
40th percentile: 4.191660833358765
50th percentile: 4.192179918289185
60th percentile: 4.1933728694915775
70th percentile: 4.1945658206939695
80th percentile: 4.398461675643921
90th percentile: 4.8050604343414305
95th percentile: 5.008359813690185
99th percentile: 5.17099931716919
mean time: 4.395938873291016
Pipeline stage StressChecker completed in 22.72s
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 0.04s
M-Eval Dataset for topic stay_in_character is loaded
abacusai-smaug-llama-3-7_7578_v1 status is now deployed due to DeploymentManager action
abacusai-smaug-llama-3-7_7578_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of abacusai-smaug-llama-3-7_7578_v1
Running pipeline stage ISVCDeleter
Checking if service abacusai-smaug-llama-3-7-7578-v1 is running
Tearing down inference service abacusai-smaug-llama-3-7-7578-v1
Toredown service abacusai-smaug-llama-3-7-7578-v1
Pipeline stage ISVCDeleter completed in 5.56s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key abacusai-smaug-llama-3-7-7578-v1/config.json from bucket guanaco-mkml-models
Deleting key abacusai-smaug-llama-3-7-7578-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key abacusai-smaug-llama-3-7-7578-v1/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key abacusai-smaug-llama-3-7-7578-v1/flywheel_model.2.safetensors from bucket guanaco-mkml-models
Deleting key abacusai-smaug-llama-3-7-7578-v1/flywheel_model.3.safetensors from bucket guanaco-mkml-models
Deleting key abacusai-smaug-llama-3-7-7578-v1/flywheel_model.4.safetensors from bucket guanaco-mkml-models
Deleting key abacusai-smaug-llama-3-7-7578-v1/flywheel_model.5.safetensors from bucket guanaco-mkml-models
Deleting key abacusai-smaug-llama-3-7-7578-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key abacusai-smaug-llama-3-7-7578-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key abacusai-smaug-llama-3-7-7578-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key abacusai-smaug-llama-3-7-7578-v1_reward/config.json from bucket guanaco-reward-models
Deleting key abacusai-smaug-llama-3-7-7578-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key abacusai-smaug-llama-3-7-7578-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key abacusai-smaug-llama-3-7-7578-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key abacusai-smaug-llama-3-7-7578-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key abacusai-smaug-llama-3-7-7578-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key abacusai-smaug-llama-3-7-7578-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 8.19s
abacusai-smaug-llama-3-7_7578_v1 status is now torndown due to DeploymentManager action