submission_id: turboderp-cat-llama-3-7_8684_v14
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': '<|begin_of_text|><|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>system\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: 2024-06-27T23:40:27+00:00
model_name: turboderp-cat-llama-3-70
model_group: turboderp/Cat-Llama-3-70
num_battles: 32404
num_wins: 16280
celo_rating: 1184.98
propriety_score: 0.728595890410959
propriety_total_count: 15184.0
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
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: 2024-06-27
win_ratio: 0.5024071102333045
Resubmit model
Running pipeline stage MKMLizer
Starting job with name turboderp-cat-llama-3-7-8684-v14-mkmlizer
Waiting for job on turboderp-cat-llama-3-7-8684-v14-mkmlizer to finish
turboderp-cat-llama-3-7-8684-v14-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
turboderp-cat-llama-3-7-8684-v14-mkmlizer: ║ _____ __ __ ║
turboderp-cat-llama-3-7-8684-v14-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
turboderp-cat-llama-3-7-8684-v14-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
turboderp-cat-llama-3-7-8684-v14-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
turboderp-cat-llama-3-7-8684-v14-mkmlizer: ║ /___/ ║
turboderp-cat-llama-3-7-8684-v14-mkmlizer: ║ ║
turboderp-cat-llama-3-7-8684-v14-mkmlizer: ║ Version: 0.8.14 ║
turboderp-cat-llama-3-7-8684-v14-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
turboderp-cat-llama-3-7-8684-v14-mkmlizer: ║ https://mk1.ai ║
turboderp-cat-llama-3-7-8684-v14-mkmlizer: ║ ║
turboderp-cat-llama-3-7-8684-v14-mkmlizer: ║ The license key for the current software has been verified as ║
turboderp-cat-llama-3-7-8684-v14-mkmlizer: ║ belonging to: ║
turboderp-cat-llama-3-7-8684-v14-mkmlizer: ║ ║
turboderp-cat-llama-3-7-8684-v14-mkmlizer: ║ Chai Research Corp. ║
turboderp-cat-llama-3-7-8684-v14-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
turboderp-cat-llama-3-7-8684-v14-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
turboderp-cat-llama-3-7-8684-v14-mkmlizer: ║ ║
turboderp-cat-llama-3-7-8684-v14-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
turboderp-cat-llama-3-7-8684-v14-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-3-7-8684-v14-mkmlizer: warnings.warn(warning_message, FutureWarning)
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
turboderp-cat-llama-3-7-8684-v14-mkmlizer: Downloaded to shared memory in 220.301s
turboderp-cat-llama-3-7-8684-v14-mkmlizer: quantizing model to /dev/shm/model_cache
turboderp-cat-llama-3-7-8684-v14-mkmlizer: Saving flywheel model at /dev/shm/model_cache
turboderp-cat-llama-3-7-8684-v14-mkmlizer: Loading 0: 0%| | 0/723 [00:00<?, ?it/s] Loading 0: 1%| | 4/723 [00:00<00:26, 27.18it/s] Loading 0: 1%| | 9/723 [00:00<00:20, 35.23it/s] Loading 0: 2%|▏ | 14/723 [00:00<00:18, 38.69it/s] Loading 0: 2%|▏ | 18/723 [00:00<00:41, 17.11it/s] Loading 0: 3%|▎ | 22/723 [00:00<00:35, 19.74it/s] Loading 0: 4%|▎ | 27/723 [00:01<00:28, 24.74it/s] Loading 0: 4%|▍ | 31/723 [00:01<00:26, 25.78it/s] Loading 0: 5%|▍ | 36/723 [00:01<00:22, 29.97it/s] Loading 0: 6%|▌ | 42/723 [00:01<00:29, 22.79it/s] Loading 0: 6%|▌ | 45/723 [00:01<00:33, 20.34it/s] Loading 0: 7%|▋ | 49/723 [00:02<00:30, 22.13it/s] Loading 0: 7%|▋ | 54/723 [00:02<00:25, 26.51it/s] Loading 0: 8%|▊ | 58/723 [00:02<00:24, 27.11it/s] Loading 0: 9%|▊ | 63/723 [00:02<00:21, 31.03it/s] Loading 0: 9%|▉ | 68/723 [00:02<00:29, 21.86it/s] Loading 0: 10%|▉ | 71/723 [00:03<00:33, 19.67it/s] Loading 0: 11%|█ | 76/723 [00:03<00:28, 22.58it/s] Loading 0: 11%|█ | 81/723 [00:03<00:23, 26.77it/s] Loading 0: 12%|█▏ | 85/723 [00:03<00:23, 27.24it/s] Loading 0: 12%|█▏ | 90/723 [00:03<00:20, 31.01it/s] Loading 0: 13%|█▎ | 94/723 [00:04<00:34, 18.33it/s] Loading 0: 14%|█▎ | 99/723 [00:04<00:27, 22.68it/s] Loading 0: 14%|█▍ | 103/723 [00:04<00:25, 23.89it/s] Loading 0: 15%|█▍ | 108/723 [00:04<00:22, 27.89it/s] Loading 0: 15%|█▌ | 112/723 [00:04<00:21, 27.94it/s] Loading 0: 16%|█▌ | 116/723 [00:04<00:29, 20.47it/s] Loading 0: 17%|█▋ | 120/723 [00:05<00:27, 22.32it/s] Loading 0: 17%|█▋ | 123/723 [00:05<00:27, 21.94it/s] Loading 0: 17%|█▋ | 126/723 [00:15<09:07, 1.09it/s] Loading 0: 18%|█▊ | 130/723 [00:15<06:14, 1.58it/s] Loading 0: 19%|█▊ | 135/723 [00:15<04:00, 2.44it/s] Loading 0: 19%|█▉ | 140/723 [00:16<02:41, 3.62it/s] Loading 0: 20%|█▉ | 144/723 [00:16<02:14, 4.29it/s] Loading 0: 20%|██ | 148/723 [00:16<01:41, 5.68it/s] Loading 0: 21%|██ | 153/723 [00:16<01:10, 8.05it/s] Loading 0: 22%|██▏ | 157/723 [00:16<00:56, 10.06it/s] Loading 0: 22%|██▏ | 162/723 [00:17<00:41, 13.49it/s] Loading 0: 23%|██▎ | 168/723 [00:17<00:37, 14.97it/s] Loading 0: 24%|██▎ | 171/723 [00:17<00:37, 14.77it/s] Loading 0: 24%|██▍ | 175/723 [00:17<00:32, 16.92it/s] Loading 0: 25%|██▍ | 180/723 [00:17<00:25, 21.21it/s] Loading 0: 25%|██▌ | 184/723 [00:18<00:23, 22.93it/s] Loading 0: 26%|██▌ | 189/723 [00:18<00:19, 27.23it/s] Loading 0: 27%|██▋ | 194/723 [00:18<00:23, 22.25it/s] Loading 0: 27%|██▋ | 197/723 [00:18<00:26, 19.71it/s] Loading 0: 28%|██▊ | 202/723 [00:18<00:23, 22.22it/s] Loading 0: 28%|██▊ | 206/723 [00:18<00:20, 25.32it/s] Loading 0: 29%|██▉ | 211/723 [00:19<00:19, 26.66it/s] Loading 0: 30%|██▉ | 215/723 [00:19<00:17, 29.22it/s] Loading 0: 30%|███ | 219/723 [00:19<00:25, 19.57it/s] Loading 0: 31%|███ | 222/723 [00:19<00:25, 19.76it/s] Loading 0: 32%|███▏ | 228/723 [00:19<00:18, 26.55it/s] Loading 0: 32%|███▏ | 232/723 [00:19<00:18, 26.89it/s] Loading 0: 33%|███▎ | 236/723 [00:20<00:16, 29.14it/s] Loading 0: 33%|███▎ | 240/723 [00:20<00:15, 30.43it/s] Loading 0: 34%|███▎ | 244/723 [00:20<00:22, 20.90it/s] Loading 0: 34%|███▍ | 247/723 [00:20<00:22, 20.99it/s] Loading 0: 35%|███▍ | 251/723 [00:20<00:19, 24.64it/s] Loading 0: 35%|███▌ | 256/723 [00:20<00:17, 26.24it/s] Loading 0: 36%|███▌ | 261/723 [00:21<00:15, 30.02it/s] Loading 0: 36%|███▋ | 263/723 [00:32<00:15, 30.02it/s] Loading 0: 37%|███▋ | 264/723 [00:32<06:40, 1.15it/s] Loading 0: 37%|███▋ | 268/723 [00:32<04:49, 1.57it/s] Loading 0: 37%|███▋ | 271/723 [00:32<03:44, 2.01it/s] Loading 0: 38%|███▊ | 274/723 [00:33<02:51, 2.62it/s] Loading 0: 38%|███▊ | 278/723 [00:33<01:57, 3.79it/s] Loading 0: 39%|███▉ | 283/723 [00:33<01:18, 5.59it/s] Loading 0: 40%|███▉ | 288/723 [00:33<00:54, 7.99it/s] Loading 0: 41%|████ | 294/723 [00:33<00:42, 10.21it/s] Loading 0: 41%|████ | 297/723 [00:33<00:39, 10.80it/s] Loading 0: 42%|████▏ | 301/723 [00:34<00:32, 13.05it/s] Loading 0: 42%|████▏ | 306/723 [00:34<00:24, 16.99it/s] Loading 0: 43%|████▎ | 310/723 [00:34<00:21, 18.98it/s] Loading 0: 43%|████▎ | 314/723 [00:34<00:18, 22.32it/s] Loading 0: 44%|████▍ | 320/723 [00:34<00:19, 20.79it/s] Loading 0: 45%|████▍ | 323/723 [00:35<00:21, 18.77it/s] Loading 0: 45%|████▌ | 328/723 [00:35<00:18, 21.44it/s] Loading 0: 46%|████▌ | 332/723 [00:35<00:15, 24.61it/s] Loading 0: 47%|████▋ | 337/723 [00:35<00:14, 26.26it/s] Loading 0: 47%|████▋ | 342/723 [00:35<00:12, 29.90it/s] Loading 0: 48%|████▊ | 346/723 [00:35<00:19, 19.11it/s] Loading 0: 49%|████▊ | 351/723 [00:36<00:15, 23.48it/s] Loading 0: 49%|████▉ | 355/723 [00:36<00:14, 24.88it/s] Loading 0: 50%|████▉ | 360/723 [00:36<00:12, 29.10it/s] Loading 0: 50%|█████ | 364/723 [00:36<00:12, 28.90it/s] Loading 0: 51%|█████ | 368/723 [00:36<00:16, 21.09it/s] Loading 0: 51%|█████▏ | 372/723 [00:36<00:15, 23.02it/s] Loading 0: 52%|█████▏ | 375/723 [00:37<00:15, 22.76it/s] Loading 0: 53%|█████▎ | 381/723 [00:37<00:11, 29.92it/s] Loading 0: 53%|█████▎ | 385/723 [00:37<00:11, 29.45it/s] Loading 0: 54%|█████▍ | 389/723 [00:37<00:10, 31.58it/s] Loading 0: 54%|█████▍ | 394/723 [00:37<00:14, 23.21it/s] Loading 0: 55%|█████▍ | 397/723 [00:37<00:14, 22.84it/s] Loading 0: 55%|█████▌ | 400/723 [00:38<00:14, 22.81it/s] Loading 0: 56%|█████▌ | 403/723 [00:48<05:01, 1.06it/s] Loading 0: 56%|█████▋ | 408/723 [00:48<03:06, 1.68it/s] Loading 0: 57%|█████▋ | 412/723 [00:48<02:12, 2.35it/s] Loading 0: 58%|█████▊ | 420/723 [00:49<01:16, 3.97it/s] Loading 0: 59%|█████▊ | 423/723 [00:49<01:05, 4.60it/s] Loading 0: 59%|█████▉ | 427/723 [00:49<00:49, 5.98it/s] Loading 0: 60%|█████▉ | 432/723 [00:49<00:34, 8.35it/s] Loading 0: 60%|██████ | 436/723 [00:49<00:27, 10.40it/s] Loading 0: 61%|██████ | 441/723 [00:50<00:20, 13.92it/s] Loading 0: 62%|██████▏ | 446/723 [00:50<00:19, 14.31it/s] Loading 0: 62%|██████▏ | 449/723 [00:50<00:18, 14.78it/s] Loading 0: 63%|██████▎ | 454/723 [00:50<00:14, 18.70it/s] Loading 0: 64%|██████▍ | 462/723 [00:50<00:10, 26.00it/s] Loading 0: 64%|██████▍ | 466/723 [00:50<00:09, 27.40it/s] Loading 0: 65%|██████▌ | 470/723 [00:51<00:11, 21.57it/s] Loading 0: 65%|██████▌ | 473/723 [00:51<00:12, 20.67it/s] Loading 0: 67%|██████▋ | 481/723 [00:51<00:08, 28.35it/s] Loading 0: 67%|██████▋ | 488/723 [00:51<00:07, 32.75it/s] Loading 0: 68%|██████▊ | 494/723 [00:52<00:08, 25.60it/s] Loading 0: 69%|██████▉ | 498/723 [00:52<00:08, 27.22it/s] Loading 0: 69%|██████▉ | 502/723 [00:52<00:07, 28.54it/s] Loading 0: 70%|███████ | 508/723 [00:52<00:06, 32.15it/s] Loading 0: 71%|███████ | 515/723 [00:52<00:05, 36.40it/s] Loading 0: 72%|███████▏ | 520/723 [00:52<00:07, 27.41it/s] Loading 0: 72%|███████▏ | 524/723 [00:53<00:06, 28.85it/s] Loading 0: 73%|███████▎ | 528/723 [00:53<00:07, 27.24it/s] Loading 0: 74%|███████▍ | 535/723 [00:53<00:05, 32.55it/s] Loading 0: 75%|███████▍ | 540/723 [01:04<00:05, 32.55it/s] Loading 0: 75%|███████▍ | 541/723 [01:04<01:50, 1.64it/s] Loading 0: 76%|███████▌ | 546/723 [01:04<01:21, 2.18it/s] Loading 0: 76%|███████▌ | 549/723 [01:04<01:07, 2.59it/s] Loading 0: 76%|███████▋ | 553/723 [01:05<00:49, 3.44it/s] Loading 0: 77%|███████▋ | 558/723 [01:05<00:33, 4.93it/s] Loading 0: 78%|███████▊ | 562/723 [01:05<00:25, 6.42it/s] Loading 0: 79%|███████▊ | 568/723 [01:05<00:16, 9.54it/s] Loading 0: 79%|███████▉ | 573/723 [01:05<00:14, 10.68it/s] Loading 0: 80%|███████▉ | 577/723 [01:05<00:11, 12.82it/s] Loading 0: 80%|████████ | 581/723 [01:05<00:09, 14.63it/s] Loading 0: 81%|████████▏ | 589/723 [01:06<00:06, 21.34it/s] Loading 0: 82%|████████▏ | 595/723 [01:06<00:04, 26.83it/s] Loading 0: 83%|████████▎ | 600/723 [01:06<00:06, 19.67it/s] Loading 0: 84%|████████▍ | 607/723 [01:06<00:04, 24.42it/s] Loading 0: 85%|████████▍ | 613/723 [01:06<00:03, 29.69it/s] Loading 0: 85%|████████▌ | 618/723 [01:07<00:03, 30.56it/s] Loading 0: 86%|████████▌ | 623/723 [01:07<00:04, 23.42it/s] Loading 0: 87%|████████▋ | 627/723 [01:07<00:04, 23.32it/s] Loading 0: 88%|████████▊ | 634/723 [01:07<00:03, 28.38it/s] Loading 0: 89%|████████▊ | 640/723 [01:07<00:02, 33.82it/s] Loading 0: 89%|████████▉ | 646/723 [01:08<00:03, 24.67it/s] Loading 0: 90%|████████▉ | 650/723 [01:08<00:02, 26.21it/s] Loading 0: 90%|█████████ | 654/723 [01:08<00:02, 25.21it/s] Loading 0: 91%|█████████▏| 661/723 [01:08<00:02, 30.32it/s] Loading 0: 92%|█████████▏| 667/723 [01:08<00:01, 35.86it/s] Loading 0: 93%|█████████▎| 672/723 [01:09<00:01, 25.74it/s] Loading 0: 93%|█████████▎| 676/723 [01:09<00:01, 24.83it/s] Loading 0: 94%|█████████▍| 680/723 [01:20<00:31, 1.38it/s] Loading 0: 95%|█████████▌| 688/723 [01:20<00:15, 2.33it/s] Loading 0: 96%|█████████▋| 696/723 [01:20<00:07, 3.66it/s] Loading 0: 97%|█████████▋| 701/723 [01:21<00:05, 4.34it/s] Loading 0: 98%|█████████▊| 706/723 [01:21<00:03, 5.67it/s] Loading 0: 99%|█████████▉| 714/723 [01:21<00:01, 8.53it/s] Loading 0: 99%|█████████▉| 719/723 [01:21<00:00, 10.56it/s] Loading 0: 100%|█████████▉| 722/723 [01:31<00:00, 10.56it/s] Loading 0: 100%|██████████| 723/723 [01:31<00:00, 1.57it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
turboderp-cat-llama-3-7-8684-v14-mkmlizer: quantized model in 105.854s
turboderp-cat-llama-3-7-8684-v14-mkmlizer: Processed model turboderp/Cat-Llama-3-70B-instruct in 335.555s
turboderp-cat-llama-3-7-8684-v14-mkmlizer: creating bucket guanaco-mkml-models
turboderp-cat-llama-3-7-8684-v14-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
turboderp-cat-llama-3-7-8684-v14-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/turboderp-cat-llama-3-7-8684-v14
turboderp-cat-llama-3-7-8684-v14-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/turboderp-cat-llama-3-7-8684-v14/config.json
turboderp-cat-llama-3-7-8684-v14-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/turboderp-cat-llama-3-7-8684-v14/special_tokens_map.json
turboderp-cat-llama-3-7-8684-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/turboderp-cat-llama-3-7-8684-v14/tokenizer.json
turboderp-cat-llama-3-7-8684-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/turboderp-cat-llama-3-7-8684-v14/tokenizer_config.json
turboderp-cat-llama-3-7-8684-v14-mkmlizer: cp /dev/shm/model_cache/flywheel_model.5.safetensors s3://guanaco-mkml-models/turboderp-cat-llama-3-7-8684-v14/flywheel_model.5.safetensors
turboderp-cat-llama-3-7-8684-v14-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/turboderp-cat-llama-3-7-8684-v14/flywheel_model.1.safetensors
turboderp-cat-llama-3-7-8684-v14-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/turboderp-cat-llama-3-7-8684-v14/flywheel_model.0.safetensors
turboderp-cat-llama-3-7-8684-v14-mkmlizer: cp /dev/shm/model_cache/flywheel_model.4.safetensors s3://guanaco-mkml-models/turboderp-cat-llama-3-7-8684-v14/flywheel_model.4.safetensors
turboderp-cat-llama-3-7-8684-v14-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/turboderp-cat-llama-3-7-8684-v14/flywheel_model.3.safetensors
turboderp-cat-llama-3-7-8684-v14-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/turboderp-cat-llama-3-7-8684-v14/flywheel_model.2.safetensors
turboderp-cat-llama-3-7-8684-v14-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
turboderp-cat-llama-3-7-8684-v14-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-3-7-8684-v14-mkmlizer: warnings.warn(
turboderp-cat-llama-3-7-8684-v14-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-3-7-8684-v14-mkmlizer: warnings.warn(
turboderp-cat-llama-3-7-8684-v14-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-3-7-8684-v14-mkmlizer: warnings.warn(
turboderp-cat-llama-3-7-8684-v14-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-3-7-8684-v14-mkmlizer: return self.fget.__get__(instance, owner)()
turboderp-cat-llama-3-7-8684-v14-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
turboderp-cat-llama-3-7-8684-v14-mkmlizer: Saving duration: 0.256s
turboderp-cat-llama-3-7-8684-v14-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.070s
turboderp-cat-llama-3-7-8684-v14-mkmlizer: creating bucket guanaco-reward-models
turboderp-cat-llama-3-7-8684-v14-mkmlizer: Bucket 's3://guanaco-reward-models/' created
turboderp-cat-llama-3-7-8684-v14-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/turboderp-cat-llama-3-7-8684-v14_reward
turboderp-cat-llama-3-7-8684-v14-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/turboderp-cat-llama-3-7-8684-v14_reward/config.json
turboderp-cat-llama-3-7-8684-v14-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/turboderp-cat-llama-3-7-8684-v14_reward/special_tokens_map.json
turboderp-cat-llama-3-7-8684-v14-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/turboderp-cat-llama-3-7-8684-v14_reward/merges.txt
turboderp-cat-llama-3-7-8684-v14-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/turboderp-cat-llama-3-7-8684-v14_reward/vocab.json
turboderp-cat-llama-3-7-8684-v14-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/turboderp-cat-llama-3-7-8684-v14_reward/tokenizer_config.json
turboderp-cat-llama-3-7-8684-v14-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/turboderp-cat-llama-3-7-8684-v14_reward/tokenizer.json
turboderp-cat-llama-3-7-8684-v14-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/turboderp-cat-llama-3-7-8684-v14_reward/reward.tensors
Job turboderp-cat-llama-3-7-8684-v14-mkmlizer completed after 390.63s with status: succeeded
Stopping job with name turboderp-cat-llama-3-7-8684-v14-mkmlizer
Pipeline stage MKMLizer completed in 391.68s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service turboderp-cat-llama-3-7-8684-v14
Waiting for inference service turboderp-cat-llama-3-7-8684-v14 to be ready
Inference service turboderp-cat-llama-3-7-8684-v14 ready after 90.37282013893127s
Pipeline stage ISVCDeployer completed in 97.68s
Running pipeline stage StressChecker
Received healthy response to inference request in 5.127652406692505s
Received healthy response to inference request in 3.4569783210754395s
Received healthy response to inference request in 4.200714349746704s
Received healthy response to inference request in 4.425427675247192s
Received healthy response to inference request in 4.175621747970581s
5 requests
0 failed requests
5th percentile: 3.600707006454468
10th percentile: 3.744435691833496
20th percentile: 4.031893062591553
30th percentile: 4.1806402683258055
40th percentile: 4.190677309036255
50th percentile: 4.200714349746704
60th percentile: 4.290599679946899
70th percentile: 4.380485010147095
80th percentile: 4.565872621536255
90th percentile: 4.8467625141143795
95th percentile: 4.987207460403442
99th percentile: 5.099563417434692
mean time: 4.277278900146484
Pipeline stage StressChecker completed in 22.35s
turboderp-cat-llama-3-7_8684_v14 status is now deployed due to DeploymentManager action
turboderp-cat-llama-3-7_8684_v14 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics