submission_id: turboderp-cat-llama-3-70_8684_v3
developer_uid: kaltcit
status: inactive
model_repo: turboderp/Cat-Llama-3-70B-instruct
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.9, 'top_p': 0.8, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', 'truncate_by_message': False}
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}:', 'truncate_by_message': False}
timestamp: 2024-06-26T18:34:33+00:00
model_name: turboderp-cat-llama-3-70_8684_v3
model_group: turboderp/Cat-Llama-3-70
num_battles: 15419
num_wins: 7710
celo_rating: 1191.49
propriety_score: 0.737045203969129
propriety_total_count: 7256.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 70553739264.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: turboderp-cat-llama-3-70_8684_v3
ineligible_reason: None
language_model: turboderp/Cat-Llama-3-70B-instruct
model_size: 71B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-26
win_ratio: 0.5000324275244827
Resubmit model
Running pipeline stage MKMLizer
Starting job with name turboderp-cat-llama-3-70-8684-v3-mkmlizer
Waiting for job on turboderp-cat-llama-3-70-8684-v3-mkmlizer to finish
turboderp-cat-llama-3-70-8684-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
turboderp-cat-llama-3-70-8684-v3-mkmlizer: ║ _____ __ __ ║
turboderp-cat-llama-3-70-8684-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
turboderp-cat-llama-3-70-8684-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
turboderp-cat-llama-3-70-8684-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
turboderp-cat-llama-3-70-8684-v3-mkmlizer: ║ /___/ ║
turboderp-cat-llama-3-70-8684-v3-mkmlizer: ║ ║
turboderp-cat-llama-3-70-8684-v3-mkmlizer: ║ Version: 0.8.14 ║
turboderp-cat-llama-3-70-8684-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
turboderp-cat-llama-3-70-8684-v3-mkmlizer: ║ https://mk1.ai ║
turboderp-cat-llama-3-70-8684-v3-mkmlizer: ║ ║
turboderp-cat-llama-3-70-8684-v3-mkmlizer: ║ The license key for the current software has been verified as ║
turboderp-cat-llama-3-70-8684-v3-mkmlizer: ║ belonging to: ║
turboderp-cat-llama-3-70-8684-v3-mkmlizer: ║ ║
turboderp-cat-llama-3-70-8684-v3-mkmlizer: ║ Chai Research Corp. ║
turboderp-cat-llama-3-70-8684-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
turboderp-cat-llama-3-70-8684-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
turboderp-cat-llama-3-70-8684-v3-mkmlizer: ║ ║
turboderp-cat-llama-3-70-8684-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
turboderp-cat-llama-3-70-8684-v3-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.
turboderp-cat-llama-3-70-8684-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
turboderp-cat-llama-3-70-8684-v3-mkmlizer: Downloaded to shared memory in 190.423s
turboderp-cat-llama-3-70-8684-v3-mkmlizer: quantizing model to /dev/shm/model_cache
turboderp-cat-llama-3-70-8684-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
turboderp-cat-llama-3-70-8684-v3-mkmlizer: Loading 0: 0%| | 0/723 [00:00<?, ?it/s] Loading 0: 0%| | 3/723 [00:00<00:31, 23.02it/s] Loading 0: 1%| | 6/723 [00:00<00:38, 18.52it/s] Loading 0: 2%|▏ | 11/723 [00:00<00:25, 28.09it/s] Loading 0: 2%|▏ | 16/723 [00:00<00:39, 18.09it/s] Loading 0: 3%|▎ | 19/723 [00:00<00:37, 18.83it/s] Loading 0: 3%|▎ | 22/723 [00:01<00:35, 19.69it/s] Loading 0: 4%|▎ | 27/723 [00:01<00:27, 25.32it/s] Loading 0: 4%|▍ | 31/723 [00:01<00:27, 25.56it/s] Loading 0: 5%|▍ | 36/723 [00:01<00:22, 29.96it/s] Loading 0: 6%|▌ | 42/723 [00:01<00:28, 23.74it/s] Loading 0: 6%|▌ | 45/723 [00:02<00:32, 21.14it/s] Loading 0: 7%|▋ | 49/723 [00:02<00:29, 23.05it/s] Loading 0: 7%|▋ | 54/723 [00:02<00:24, 27.53it/s] Loading 0: 8%|▊ | 58/723 [00:02<00:23, 28.28it/s] Loading 0: 9%|▊ | 63/723 [00:02<00:20, 32.16it/s] Loading 0: 9%|▉ | 68/723 [00:02<00:27, 23.66it/s] Loading 0: 10%|▉ | 71/723 [00:03<00:31, 20.84it/s] Loading 0: 11%|█ | 76/723 [00:03<00:28, 22.80it/s] Loading 0: 11%|█ | 81/723 [00:03<00:23, 27.01it/s] Loading 0: 12%|█▏ | 85/723 [00:03<00:23, 27.62it/s] Loading 0: 12%|█▏ | 90/723 [00:03<00:20, 31.47it/s] Loading 0: 13%|█▎ | 94/723 [00:04<00:34, 18.39it/s] Loading 0: 14%|█▎ | 99/723 [00:04<00:27, 22.81it/s] Loading 0: 14%|█▍ | 103/723 [00:04<00:25, 24.57it/s] Loading 0: 15%|█▍ | 107/723 [00:04<00:22, 27.32it/s] Loading 0: 15%|█▌ | 111/723 [00:04<00:22, 26.99it/s] Loading 0: 16%|█▌ | 116/723 [00:04<00:28, 21.40it/s] Loading 0: 17%|█▋ | 120/723 [00:05<00:26, 23.18it/s] Loading 0: 17%|█▋ | 123/723 [00:05<00:26, 22.80it/s] Loading 0: 17%|█▋ | 126/723 [00:14<08:16, 1.20it/s] Loading 0: 18%|█▊ | 130/723 [00:14<05:41, 1.73it/s] Loading 0: 19%|█▊ | 135/723 [00:15<03:40, 2.67it/s] Loading 0: 19%|█▉ | 140/723 [00:15<02:28, 3.93it/s] Loading 0: 20%|█▉ | 144/723 [00:15<02:06, 4.59it/s] Loading 0: 20%|██ | 148/723 [00:15<01:34, 6.05it/s] Loading 0: 21%|██ | 153/723 [00:15<01:06, 8.54it/s] Loading 0: 22%|██▏ | 157/723 [00:16<00:53, 10.51it/s] Loading 0: 22%|██▏ | 161/723 [00:16<00:42, 13.25it/s] Loading 0: 23%|██▎ | 168/723 [00:16<00:38, 14.50it/s] Loading 0: 24%|██▎ | 171/723 [00:16<00:39, 14.10it/s] Loading 0: 24%|██▍ | 175/723 [00:17<00:33, 16.25it/s] Loading 0: 25%|██▍ | 179/723 [00:17<00:27, 19.48it/s] Loading 0: 25%|██▌ | 184/723 [00:17<00:24, 21.79it/s] Loading 0: 26%|██▌ | 188/723 [00:17<00:21, 24.76it/s] Loading 0: 27%|██▋ | 194/723 [00:17<00:28, 18.67it/s] Loading 0: 27%|██▋ | 197/723 [00:18<00:30, 17.05it/s] Loading 0: 28%|██▊ | 202/723 [00:18<00:26, 19.81it/s] Loading 0: 28%|██▊ | 206/723 [00:18<00:22, 22.95it/s] Loading 0: 29%|██▉ | 211/723 [00:18<00:20, 24.62it/s] Loading 0: 30%|██▉ | 216/723 [00:18<00:17, 28.35it/s] Loading 0: 30%|███ | 220/723 [00:19<00:32, 15.65it/s] Loading 0: 31%|███ | 224/723 [00:19<00:26, 18.81it/s] Loading 0: 32%|███▏ | 229/723 [00:19<00:23, 21.35it/s] Loading 0: 32%|███▏ | 233/723 [00:19<00:20, 24.44it/s] Loading 0: 33%|███▎ | 237/723 [00:19<00:19, 24.46it/s] Loading 0: 33%|███▎ | 242/723 [00:20<00:25, 18.71it/s] Loading 0: 34%|███▍ | 246/723 [00:20<00:23, 20.36it/s] Loading 0: 34%|███▍ | 249/723 [00:20<00:23, 19.88it/s] Loading 0: 35%|███▌ | 255/723 [00:20<00:17, 26.35it/s] Loading 0: 36%|███▌ | 259/723 [00:20<00:17, 26.24it/s] Loading 0: 36%|███▋ | 263/723 [00:20<00:16, 28.36it/s] Loading 0: 37%|███▋ | 267/723 [00:30<05:37, 1.35it/s] Loading 0: 37%|███▋ | 270/723 [00:31<04:35, 1.64it/s] Loading 0: 38%|███▊ | 274/723 [00:31<03:14, 2.31it/s] Loading 0: 38%|███▊ | 278/723 [00:31<02:16, 3.25it/s] Loading 0: 39%|███▉ | 283/723 [00:31<01:32, 4.76it/s] Loading 0: 40%|███▉ | 288/723 [00:31<01:04, 6.78it/s] Loading 0: 41%|████ | 294/723 [00:32<00:50, 8.51it/s] Loading 0: 41%|████ | 297/723 [00:32<00:45, 9.29it/s] Loading 0: 42%|████▏ | 301/723 [00:32<00:36, 11.50it/s] Loading 0: 42%|████▏ | 306/723 [00:32<00:27, 15.23it/s] Loading 0: 43%|████▎ | 310/723 [00:32<00:23, 17.46it/s] Loading 0: 44%|████▎ | 315/723 [00:33<00:18, 21.75it/s] Loading 0: 44%|████▍ | 320/723 [00:33<00:22, 17.78it/s] Loading 0: 45%|████▍ | 323/723 [00:33<00:23, 16.79it/s] Loading 0: 45%|████▌ | 328/723 [00:33<00:19, 19.78it/s] Loading 0: 46%|████▌ | 333/723 [00:33<00:16, 24.21it/s] Loading 0: 47%|████▋ | 337/723 [00:34<00:15, 25.27it/s] Loading 0: 47%|████▋ | 342/723 [00:34<00:13, 29.11it/s] Loading 0: 48%|████▊ | 346/723 [00:34<00:22, 16.86it/s] Loading 0: 49%|████▊ | 351/723 [00:34<00:17, 20.98it/s] Loading 0: 49%|████▉ | 355/723 [00:34<00:16, 22.39it/s] Loading 0: 50%|████▉ | 360/723 [00:35<00:13, 26.48it/s] Loading 0: 50%|█████ | 364/723 [00:35<00:13, 26.49it/s] Loading 0: 51%|█████ | 368/723 [00:35<00:18, 19.10it/s] Loading 0: 51%|█████▏ | 372/723 [00:35<00:16, 21.12it/s] Loading 0: 52%|█████▏ | 375/723 [00:35<00:16, 21.18it/s] Loading 0: 53%|█████▎ | 381/723 [00:35<00:12, 28.28it/s] Loading 0: 53%|█████▎ | 385/723 [00:36<00:11, 28.24it/s] Loading 0: 54%|█████▍ | 389/723 [00:36<00:10, 30.39it/s] Loading 0: 54%|█████▍ | 394/723 [00:36<00:14, 22.02it/s] Loading 0: 55%|█████▍ | 397/723 [00:36<00:15, 21.68it/s] Loading 0: 55%|█████▌ | 400/723 [00:36<00:14, 21.74it/s] Loading 0: 56%|█████▌ | 403/723 [00:46<04:34, 1.16it/s] Loading 0: 56%|█████▋ | 408/723 [00:46<02:50, 1.85it/s] Loading 0: 57%|█████▋ | 411/723 [00:46<02:11, 2.38it/s] Loading 0: 58%|█████▊ | 420/723 [00:47<01:09, 4.38it/s] Loading 0: 59%|█████▊ | 423/723 [00:47<00:59, 5.00it/s] Loading 0: 59%|█████▉ | 427/723 [00:47<00:46, 6.42it/s] Loading 0: 60%|█████▉ | 432/723 [00:47<00:32, 8.89it/s] Loading 0: 60%|██████ | 436/723 [00:47<00:26, 10.99it/s] Loading 0: 61%|██████ | 441/723 [00:47<00:19, 14.55it/s] Loading 0: 62%|██████▏ | 446/723 [00:48<00:18, 14.61it/s] Loading 0: 62%|██████▏ | 449/723 [00:48<00:18, 14.60it/s] Loading 0: 63%|██████▎ | 454/723 [00:48<00:15, 17.78it/s] Loading 0: 63%|██████▎ | 459/723 [00:48<00:11, 22.02it/s] Loading 0: 64%|██████▍ | 463/723 [00:48<00:11, 23.63it/s] Loading 0: 65%|██████▍ | 468/723 [00:48<00:09, 27.77it/s] Loading 0: 65%|██████▌ | 472/723 [00:49<00:14, 17.78it/s] Loading 0: 66%|██████▌ | 477/723 [00:49<00:11, 22.02it/s] Loading 0: 67%|██████▋ | 481/723 [00:49<00:10, 23.56it/s] Loading 0: 67%|██████▋ | 486/723 [00:49<00:08, 27.94it/s] Loading 0: 68%|██████▊ | 490/723 [00:49<00:08, 27.91it/s] Loading 0: 68%|██████▊ | 494/723 [00:50<00:10, 20.95it/s] Loading 0: 69%|██████▉ | 498/723 [00:50<00:09, 22.74it/s] Loading 0: 69%|██████▉ | 501/723 [00:50<00:09, 22.43it/s] Loading 0: 70%|███████ | 507/723 [00:50<00:07, 29.59it/s] Loading 0: 71%|███████ | 511/723 [00:50<00:07, 29.34it/s] Loading 0: 71%|███████ | 515/723 [00:50<00:06, 31.25it/s] Loading 0: 72%|███████▏ | 520/723 [00:51<00:08, 22.79it/s] Loading 0: 72%|███████▏ | 523/723 [00:51<00:08, 22.27it/s] Loading 0: 73%|███████▎ | 526/723 [00:51<00:08, 22.10it/s] Loading 0: 73%|███████▎ | 531/723 [00:51<00:07, 26.99it/s] Loading 0: 74%|███████▍ | 535/723 [00:51<00:06, 27.53it/s] Loading 0: 75%|███████▍ | 540/723 [00:51<00:05, 31.59it/s] Loading 0: 75%|███████▌ | 544/723 [01:01<02:09, 1.38it/s] Loading 0: 76%|███████▌ | 547/723 [01:02<01:45, 1.67it/s] Loading 0: 76%|███████▌ | 549/723 [01:02<01:27, 1.99it/s] Loading 0: 76%|███████▋ | 553/723 [01:02<00:58, 2.92it/s] Loading 0: 77%|███████▋ | 558/723 [01:02<00:36, 4.52it/s] Loading 0: 78%|███████▊ | 562/723 [01:02<00:26, 6.07it/s] Loading 0: 78%|███████▊ | 566/723 [01:02<00:19, 8.14it/s] Loading 0: 79%|███████▉ | 572/723 [01:03<00:14, 10.34it/s] Loading 0: 80%|███████▉ | 575/723 [01:03<00:13, 10.99it/s] Loading 0: 80%|████████ | 580/723 [01:03<00:10, 14.20it/s] Loading 0: 81%|████████ | 585/723 [01:03<00:07, 18.14it/s] Loading 0: 81%|████████▏ | 589/723 [01:03<00:06, 20.06it/s] Loading 0: 82%|████████▏ | 593/723 [01:03<00:05, 23.24it/s] Loading 0: 83%|████████▎ | 597/723 [01:04<00:07, 16.48it/s] Loading 0: 83%|████████▎ | 600/723 [01:04<00:07, 17.20it/s] Loading 0: 84%|████████▍ | 606/723 [01:04<00:05, 23.24it/s] Loading 0: 84%|████████▍ | 610/723 [01:04<00:04, 23.94it/s] Loading 0: 85%|████████▍ | 614/723 [01:04<00:04, 26.36it/s] Loading 0: 85%|████████▌ | 618/723 [01:05<00:03, 27.89it/s] Loading 0: 86%|████████▌ | 622/723 [01:05<00:05, 17.45it/s] Loading 0: 86%|████████▋ | 625/723 [01:05<00:05, 18.22it/s] Loading 0: 87%|████████▋ | 630/723 [01:05<00:04, 21.24it/s] Loading 0: 88%|████████▊ | 633/723 [01:05<00:04, 21.42it/s] Loading 0: 88%|████████▊ | 636/723 [01:06<00:04, 21.12it/s] Loading 0: 89%|████████▊ | 641/723 [01:06<00:03, 25.77it/s] Loading 0: 89%|████████▉ | 646/723 [01:06<00:04, 17.76it/s] Loading 0: 90%|████████▉ | 649/723 [01:06<00:04, 17.89it/s] Loading 0: 90%|█████████ | 652/723 [01:06<00:03, 18.17it/s] Loading 0: 91%|█████████ | 656/723 [01:07<00:03, 21.36it/s] Loading 0: 91%|█████████▏| 660/723 [01:07<00:02, 24.68it/s] Loading 0: 92%|█████████▏| 663/723 [01:07<00:02, 22.89it/s] Loading 0: 93%|█████████▎| 672/723 [01:07<00:02, 19.48it/s] Loading 0: 93%|█████████▎| 675/723 [01:08<00:02, 17.70it/s] Loading 0: 94%|█████████▍| 679/723 [01:17<00:30, 1.42it/s] Loading 0: 95%|█████████▍| 684/723 [01:17<00:18, 2.09it/s] Loading 0: 95%|█████████▌| 688/723 [01:18<00:12, 2.79it/s] Loading 0: 96%|█████████▌| 692/723 [01:18<00:08, 3.77it/s] Loading 0: 97%|█████████▋| 698/723 [01:18<00:04, 5.04it/s] Loading 0: 97%|█████████▋| 701/723 [01:18<00:03, 5.76it/s] Loading 0: 98%|█████████▊| 706/723 [01:19<00:02, 7.85it/s] Loading 0: 98%|█████████▊| 710/723 [01:19<00:01, 10.05it/s] Loading 0: 99%|█████████▉| 715/723 [01:19<00:00, 12.79it/s] Loading 0: 99%|█████████▉| 719/723 [01:19<00:00, 15.45it/s] Loading 0: 100%|█████████▉| 722/723 [01:30<00:00, 15.45it/s] Loading 0: 100%|██████████| 723/723 [01:30<00:00, 1.18it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
turboderp-cat-llama-3-70-8684-v3-mkmlizer: quantized model in 106.250s
turboderp-cat-llama-3-70-8684-v3-mkmlizer: Processed model turboderp/Cat-Llama-3-70B-instruct in 308.150s
turboderp-cat-llama-3-70-8684-v3-mkmlizer: creating bucket guanaco-mkml-models
turboderp-cat-llama-3-70-8684-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
turboderp-cat-llama-3-70-8684-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/turboderp-cat-llama-3-70-8684-v3
turboderp-cat-llama-3-70-8684-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/turboderp-cat-llama-3-70-8684-v3/special_tokens_map.json
turboderp-cat-llama-3-70-8684-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/turboderp-cat-llama-3-70-8684-v3/config.json
turboderp-cat-llama-3-70-8684-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/turboderp-cat-llama-3-70-8684-v3/tokenizer.json
turboderp-cat-llama-3-70-8684-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/turboderp-cat-llama-3-70-8684-v3/tokenizer_config.json
turboderp-cat-llama-3-70-8684-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.5.safetensors s3://guanaco-mkml-models/turboderp-cat-llama-3-70-8684-v3/flywheel_model.5.safetensors
turboderp-cat-llama-3-70-8684-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/turboderp-cat-llama-3-70-8684-v3/flywheel_model.2.safetensors
turboderp-cat-llama-3-70-8684-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.4.safetensors s3://guanaco-mkml-models/turboderp-cat-llama-3-70-8684-v3/flywheel_model.4.safetensors
turboderp-cat-llama-3-70-8684-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/turboderp-cat-llama-3-70-8684-v3/flywheel_model.3.safetensors
turboderp-cat-llama-3-70-8684-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/turboderp-cat-llama-3-70-8684-v3/flywheel_model.0.safetensors
turboderp-cat-llama-3-70-8684-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/turboderp-cat-llama-3-70-8684-v3/flywheel_model.1.safetensors
turboderp-cat-llama-3-70-8684-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
turboderp-cat-llama-3-70-8684-v3-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.
turboderp-cat-llama-3-70-8684-v3-mkmlizer: warnings.warn(
turboderp-cat-llama-3-70-8684-v3-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.
turboderp-cat-llama-3-70-8684-v3-mkmlizer: warnings.warn(
turboderp-cat-llama-3-70-8684-v3-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.
turboderp-cat-llama-3-70-8684-v3-mkmlizer: warnings.warn(
turboderp-cat-llama-3-70-8684-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
turboderp-cat-llama-3-70-8684-v3-mkmlizer: return self.fget.__get__(instance, owner)()
turboderp-cat-llama-3-70-8684-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
turboderp-cat-llama-3-70-8684-v3-mkmlizer: Saving duration: 0.288s
turboderp-cat-llama-3-70-8684-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.433s
turboderp-cat-llama-3-70-8684-v3-mkmlizer: creating bucket guanaco-reward-models
turboderp-cat-llama-3-70-8684-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
turboderp-cat-llama-3-70-8684-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/turboderp-cat-llama-3-70-8684-v3_reward
turboderp-cat-llama-3-70-8684-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/turboderp-cat-llama-3-70-8684-v3_reward/config.json
turboderp-cat-llama-3-70-8684-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/turboderp-cat-llama-3-70-8684-v3_reward/special_tokens_map.json
turboderp-cat-llama-3-70-8684-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/turboderp-cat-llama-3-70-8684-v3_reward/tokenizer_config.json
turboderp-cat-llama-3-70-8684-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/turboderp-cat-llama-3-70-8684-v3_reward/merges.txt
turboderp-cat-llama-3-70-8684-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/turboderp-cat-llama-3-70-8684-v3_reward/vocab.json
turboderp-cat-llama-3-70-8684-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/turboderp-cat-llama-3-70-8684-v3_reward/tokenizer.json
turboderp-cat-llama-3-70-8684-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/turboderp-cat-llama-3-70-8684-v3_reward/reward.tensors
Job turboderp-cat-llama-3-70-8684-v3-mkmlizer completed after 362.9s with status: succeeded
Stopping job with name turboderp-cat-llama-3-70-8684-v3-mkmlizer
Pipeline stage MKMLizer completed in 363.83s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service turboderp-cat-llama-3-70-8684-v3
Waiting for inference service turboderp-cat-llama-3-70-8684-v3 to be ready
Inference service turboderp-cat-llama-3-70-8684-v3 ready after 90.46174383163452s
Pipeline stage ISVCDeployer completed in 97.57s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.652188539505005s
Received healthy response to inference request in 4.242738962173462s
Received healthy response to inference request in 4.236402273178101s
Received healthy response to inference request in 3.8671884536743164s
Received healthy response to inference request in 4.245387554168701s
5 requests
0 failed requests
5th percentile: 3.9410312175750732
10th percentile: 4.01487398147583
20th percentile: 4.162559509277344
30th percentile: 4.237669610977173
40th percentile: 4.240204286575318
50th percentile: 4.242738962173462
60th percentile: 4.243798398971558
70th percentile: 4.244857835769653
80th percentile: 4.326747751235962
90th percentile: 4.489468145370483
95th percentile: 4.5708283424377445
99th percentile: 4.635916500091553
mean time: 4.248781156539917
Pipeline stage StressChecker completed in 22.21s
turboderp-cat-llama-3-70_8684_v3 status is now deployed due to DeploymentManager action
turboderp-cat-llama-3-70_8684_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics