submission_id: turboderp-cat-llama-3-70_8684_v2
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': '<|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}
timestamp: 2024-06-25T20:47:49+00:00
model_name: turboderp-cat-llama-3-70_8684_v2
model_group: turboderp/Cat-Llama-3-70
num_battles: 29541
num_wins: 15092
celo_rating: 1186.6
propriety_score: 0.729507032248899
propriety_total_count: 14078.0
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_v2
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: 2024-06-25
win_ratio: 0.5108831793101114
Resubmit model
Running pipeline stage MKMLizer
Starting job with name turboderp-cat-llama-3-70-8684-v2-mkmlizer
Waiting for job on turboderp-cat-llama-3-70-8684-v2-mkmlizer to finish
turboderp-cat-llama-3-70-8684-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
turboderp-cat-llama-3-70-8684-v2-mkmlizer: ║ _____ __ __ ║
turboderp-cat-llama-3-70-8684-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
turboderp-cat-llama-3-70-8684-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
turboderp-cat-llama-3-70-8684-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
turboderp-cat-llama-3-70-8684-v2-mkmlizer: ║ /___/ ║
turboderp-cat-llama-3-70-8684-v2-mkmlizer: ║ ║
turboderp-cat-llama-3-70-8684-v2-mkmlizer: ║ Version: 0.8.14 ║
turboderp-cat-llama-3-70-8684-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
turboderp-cat-llama-3-70-8684-v2-mkmlizer: ║ https://mk1.ai ║
turboderp-cat-llama-3-70-8684-v2-mkmlizer: ║ ║
turboderp-cat-llama-3-70-8684-v2-mkmlizer: ║ The license key for the current software has been verified as ║
turboderp-cat-llama-3-70-8684-v2-mkmlizer: ║ belonging to: ║
turboderp-cat-llama-3-70-8684-v2-mkmlizer: ║ ║
turboderp-cat-llama-3-70-8684-v2-mkmlizer: ║ Chai Research Corp. ║
turboderp-cat-llama-3-70-8684-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
turboderp-cat-llama-3-70-8684-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
turboderp-cat-llama-3-70-8684-v2-mkmlizer: ║ ║
turboderp-cat-llama-3-70-8684-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
turboderp-cat-llama-3-70-8684-v2-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-v2-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
Job turboderp-cat-llama-3-70-8684-v2-mkmlizer completed after 331.03s with status: failed
Stopping job with name turboderp-cat-llama-3-70-8684-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name turboderp-cat-llama-3-70-8684-v2-mkmlizer
Waiting for job on turboderp-cat-llama-3-70-8684-v2-mkmlizer to finish
turboderp-cat-llama-3-70-8684-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
turboderp-cat-llama-3-70-8684-v2-mkmlizer: ║ _____ __ __ ║
turboderp-cat-llama-3-70-8684-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
turboderp-cat-llama-3-70-8684-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
turboderp-cat-llama-3-70-8684-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
turboderp-cat-llama-3-70-8684-v2-mkmlizer: ║ /___/ ║
turboderp-cat-llama-3-70-8684-v2-mkmlizer: ║ ║
turboderp-cat-llama-3-70-8684-v2-mkmlizer: ║ Version: 0.8.14 ║
turboderp-cat-llama-3-70-8684-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
turboderp-cat-llama-3-70-8684-v2-mkmlizer: ║ https://mk1.ai ║
turboderp-cat-llama-3-70-8684-v2-mkmlizer: ║ ║
turboderp-cat-llama-3-70-8684-v2-mkmlizer: ║ The license key for the current software has been verified as ║
turboderp-cat-llama-3-70-8684-v2-mkmlizer: ║ belonging to: ║
turboderp-cat-llama-3-70-8684-v2-mkmlizer: ║ ║
turboderp-cat-llama-3-70-8684-v2-mkmlizer: ║ Chai Research Corp. ║
turboderp-cat-llama-3-70-8684-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
turboderp-cat-llama-3-70-8684-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
turboderp-cat-llama-3-70-8684-v2-mkmlizer: ║ ║
turboderp-cat-llama-3-70-8684-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
turboderp-cat-llama-3-70-8684-v2-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-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
turboderp-cat-llama-3-70-8684-v2-mkmlizer: Downloaded to shared memory in 277.729s
turboderp-cat-llama-3-70-8684-v2-mkmlizer: quantizing model to /dev/shm/model_cache
turboderp-cat-llama-3-70-8684-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
turboderp-cat-llama-3-70-8684-v2-mkmlizer: Loading 0: 0%| | 0/723 [00:00<?, ?it/s] Loading 0: 1%| | 4/723 [00:00<00:24, 29.40it/s] Loading 0: 1%| | 9/723 [00:00<00:19, 36.71it/s] Loading 0: 2%|▏ | 14/723 [00:00<00:17, 40.30it/s] Loading 0: 3%|▎ | 19/723 [00:00<00:35, 19.62it/s] Loading 0: 3%|▎ | 22/723 [00:00<00:34, 20.51it/s] Loading 0: 4%|▎ | 26/723 [00:01<00:28, 24.32it/s] Loading 0: 4%|▍ | 31/723 [00:01<00:25, 26.99it/s] Loading 0: 5%|▍ | 36/723 [00:01<00:22, 31.08it/s] Loading 0: 6%|▌ | 42/723 [00:01<00:27, 24.46it/s] Loading 0: 6%|▋ | 46/723 [00:01<00:30, 22.25it/s] Loading 0: 7%|▋ | 49/723 [00:01<00:30, 22.33it/s] Loading 0: 7%|▋ | 54/723 [00:02<00:24, 27.01it/s] Loading 0: 8%|▊ | 58/723 [00:02<00:23, 28.19it/s] Loading 0: 9%|▊ | 63/723 [00:02<00:20, 32.70it/s] Loading 0: 9%|▉ | 68/723 [00:02<00:27, 24.22it/s] Loading 0: 10%|▉ | 72/723 [00:02<00:29, 21.93it/s] Loading 0: 11%|█ | 76/723 [00:03<00:28, 22.83it/s] Loading 0: 11%|█ | 81/723 [00:03<00:23, 27.38it/s] Loading 0: 12%|█▏ | 85/723 [00:03<00:23, 27.45it/s] Loading 0: 12%|█▏ | 90/723 [00:03<00:20, 31.36it/s] Loading 0: 13%|█▎ | 94/723 [00:03<00:32, 19.11it/s] Loading 0: 14%|█▎ | 99/723 [00:03<00:26, 23.38it/s] Loading 0: 14%|█▍ | 103/723 [00:04<00:25, 24.63it/s] Loading 0: 15%|█▍ | 108/723 [00:04<00:21, 28.66it/s] Loading 0: 15%|█▌ | 112/723 [00:04<00:22, 27.76it/s] Loading 0: 16%|█▌ | 116/723 [00:04<00:28, 21.00it/s] Loading 0: 17%|█▋ | 120/723 [00:04<00:26, 22.58it/s] Loading 0: 17%|█▋ | 123/723 [00:04<00:27, 21.98it/s] Loading 0: 17%|█▋ | 126/723 [00:16<09:48, 1.01it/s] Loading 0: 18%|█▊ | 130/723 [00:16<06:42, 1.47it/s] Loading 0: 19%|█▊ | 135/723 [00:16<04:17, 2.28it/s] Loading 0: 19%|█▉ | 140/723 [00:16<02:51, 3.39it/s] Loading 0: 20%|█▉ | 144/723 [00:17<02:22, 4.06it/s] Loading 0: 20%|██ | 148/723 [00:17<01:46, 5.39it/s] Loading 0: 21%|██ | 153/723 [00:17<01:14, 7.67it/s] Loading 0: 22%|██▏ | 157/723 [00:17<00:58, 9.63it/s] Loading 0: 22%|██▏ | 162/723 [00:17<00:43, 12.97it/s] Loading 0: 23%|██▎ | 168/723 [00:18<00:38, 14.52it/s] Loading 0: 24%|██▎ | 171/723 [00:18<00:37, 14.55it/s] Loading 0: 24%|██▍ | 175/723 [00:18<00:32, 16.85it/s] Loading 0: 25%|██▍ | 179/723 [00:18<00:27, 20.13it/s] Loading 0: 25%|██▌ | 184/723 [00:18<00:23, 22.78it/s] Loading 0: 26%|██▌ | 189/723 [00:18<00:19, 27.22it/s] Loading 0: 27%|██▋ | 194/723 [00:19<00:24, 22.02it/s] Loading 0: 27%|██▋ | 197/723 [00:19<00:26, 19.69it/s] Loading 0: 28%|██▊ | 202/723 [00:19<00:23, 22.03it/s] Loading 0: 28%|██▊ | 206/723 [00:19<00:20, 24.77it/s] Loading 0: 29%|██▉ | 211/723 [00:19<00:19, 26.09it/s] Loading 0: 30%|██▉ | 215/723 [00:19<00:17, 28.76it/s] Loading 0: 30%|███ | 219/723 [00:20<00:26, 19.15it/s] Loading 0: 31%|███ | 222/723 [00:20<00:26, 19.05it/s] Loading 0: 32%|███▏ | 228/723 [00:20<00:19, 25.81it/s] Loading 0: 32%|███▏ | 232/723 [00:20<00:18, 26.43it/s] Loading 0: 33%|███▎ | 236/723 [00:20<00:16, 28.86it/s] Loading 0: 33%|███▎ | 240/723 [00:20<00:16, 29.58it/s] Loading 0: 34%|███▎ | 244/723 [00:21<00:24, 19.68it/s] Loading 0: 34%|███▍ | 247/723 [00:21<00:23, 19.99it/s] Loading 0: 35%|███▍ | 252/723 [00:21<00:18, 24.83it/s] Loading 0: 35%|███▌ | 256/723 [00:21<00:18, 25.89it/s] Loading 0: 36%|███▌ | 261/723 [00:21<00:15, 29.82it/s] Loading 0: 36%|███▋ | 263/723 [00:32<00:15, 29.82it/s] Loading 0: 37%|███▋ | 264/723 [00:32<06:22, 1.20it/s] Loading 0: 37%|███▋ | 268/723 [00:32<04:36, 1.64it/s] Loading 0: 37%|███▋ | 271/723 [00:32<03:34, 2.11it/s] Loading 0: 38%|███▊ | 274/723 [00:33<02:43, 2.74it/s] Loading 0: 39%|███▊ | 279/723 [00:33<01:44, 4.26it/s] Loading 0: 39%|███▉ | 283/723 [00:33<01:17, 5.71it/s] Loading 0: 40%|███▉ | 288/723 [00:33<00:52, 8.22it/s] Loading 0: 41%|████ | 294/723 [00:33<00:41, 10.40it/s] Loading 0: 41%|████ | 297/723 [00:34<00:38, 11.12it/s] Loading 0: 42%|████▏ | 301/723 [00:34<00:31, 13.40it/s] Loading 0: 42%|████▏ | 306/723 [00:34<00:23, 17.66it/s] Loading 0: 43%|████▎ | 310/723 [00:34<00:20, 19.92it/s] Loading 0: 44%|████▎ | 315/723 [00:34<00:16, 24.28it/s] Loading 0: 44%|████▍ | 320/723 [00:34<00:19, 20.87it/s] Loading 0: 45%|████▍ | 323/723 [00:35<00:21, 18.84it/s] Loading 0: 45%|████▌ | 328/723 [00:35<00:18, 21.42it/s] Loading 0: 46%|████▌ | 332/723 [00:35<00:16, 24.42it/s] Loading 0: 47%|████▋ | 337/723 [00:35<00:14, 26.13it/s] Loading 0: 47%|████▋ | 342/723 [00:35<00:12, 29.74it/s] Loading 0: 48%|████▊ | 346/723 [00:36<00:21, 17.95it/s] Loading 0: 49%|████▊ | 351/723 [00:36<00:16, 22.27it/s] Loading 0: 49%|████▉ | 355/723 [00:36<00:15, 24.52it/s] Loading 0: 50%|█████ | 362/723 [00:36<00:11, 30.34it/s] Loading 0: 51%|█████ | 367/723 [00:36<00:10, 34.08it/s] Loading 0: 51%|█████▏ | 372/723 [00:37<00:16, 21.17it/s] Loading 0: 52%|█████▏ | 376/723 [00:37<00:15, 22.96it/s] Loading 0: 53%|█████▎ | 382/723 [00:37<00:12, 26.58it/s] Loading 0: 54%|█████▎ | 387/723 [00:37<00:10, 30.71it/s] Loading 0: 54%|█████▍ | 394/723 [00:37<00:13, 24.47it/s] Loading 0: 55%|█████▌ | 398/723 [00:37<00:12, 26.03it/s] Loading 0: 56%|█████▌ | 402/723 [00:48<03:32, 1.51it/s] Loading 0: 56%|█████▋ | 408/723 [00:48<02:17, 2.29it/s] Loading 0: 57%|█████▋ | 413/723 [00:48<01:38, 3.15it/s] Loading 0: 58%|█████▊ | 420/723 [00:48<01:07, 4.51it/s] Loading 0: 59%|█████▊ | 424/723 [00:48<00:54, 5.48it/s] Loading 0: 59%|█████▉ | 427/723 [00:49<00:45, 6.49it/s] Loading 0: 60%|█████▉ | 432/723 [00:49<00:32, 8.98it/s] Loading 0: 60%|██████ | 436/723 [00:49<00:26, 11.03it/s] Loading 0: 61%|██████ | 441/723 [00:49<00:19, 14.54it/s] Loading 0: 62%|██████▏ | 446/723 [00:49<00:18, 15.04it/s] Loading 0: 62%|██████▏ | 449/723 [00:49<00:18, 14.69it/s] Loading 0: 63%|██████▎ | 454/723 [00:50<00:15, 17.67it/s] Loading 0: 63%|██████▎ | 458/723 [00:50<00:12, 20.73it/s] Loading 0: 64%|██████▍ | 463/723 [00:50<00:11, 22.94it/s] Loading 0: 65%|██████▍ | 468/723 [00:50<00:09, 27.11it/s] Loading 0: 65%|██████▌ | 472/723 [00:51<00:15, 16.05it/s] Loading 0: 66%|██████▌ | 476/723 [00:51<00:12, 19.24it/s] Loading 0: 67%|██████▋ | 481/723 [00:51<00:11, 21.11it/s] Loading 0: 67%|██████▋ | 486/723 [00:51<00:09, 25.16it/s] Loading 0: 68%|██████▊ | 490/723 [00:51<00:09, 25.14it/s] Loading 0: 68%|██████▊ | 494/723 [00:51<00:12, 18.00it/s] Loading 0: 69%|██████▉ | 498/723 [00:52<00:11, 20.04it/s] Loading 0: 69%|██████▉ | 501/723 [00:52<00:10, 20.29it/s] Loading 0: 70%|███████ | 507/723 [00:52<00:07, 27.17it/s] Loading 0: 71%|███████ | 511/723 [00:52<00:07, 27.30it/s] Loading 0: 71%|███████ | 515/723 [00:52<00:07, 29.03it/s] Loading 0: 72%|███████▏ | 520/723 [00:53<00:10, 19.80it/s] Loading 0: 72%|███████▏ | 523/723 [00:53<00:10, 19.88it/s] Loading 0: 73%|███████▎ | 526/723 [00:53<00:09, 20.18it/s] Loading 0: 73%|███████▎ | 531/723 [00:53<00:07, 25.32it/s] Loading 0: 74%|███████▍ | 535/723 [00:53<00:07, 25.74it/s] Loading 0: 75%|███████▍ | 540/723 [00:53<00:06, 29.54it/s] Loading 0: 75%|███████▍ | 540/723 [01:03<00:06, 29.54it/s] Loading 0: 75%|███████▍ | 541/723 [01:03<02:53, 1.05it/s] Loading 0: 76%|███████▌ | 546/723 [01:04<01:48, 1.63it/s] Loading 0: 76%|███████▌ | 549/723 [01:04<01:23, 2.10it/s] Loading 0: 76%|███████▋ | 553/723 [01:04<00:56, 2.99it/s] Loading 0: 77%|███████▋ | 558/723 [01:04<00:36, 4.53it/s] Loading 0: 78%|███████▊ | 562/723 [01:05<00:27, 5.96it/s] Loading 0: 78%|███████▊ | 567/723 [01:05<00:18, 8.50it/s] Loading 0: 79%|███████▉ | 572/723 [01:05<00:15, 9.64it/s] Loading 0: 80%|███████▉ | 575/723 [01:05<00:14, 10.43it/s] Loading 0: 80%|████████ | 579/723 [01:05<00:10, 13.35it/s] Loading 0: 80%|████████ | 582/723 [01:05<00:09, 14.46it/s] Loading 0: 81%|████████▏ | 588/723 [01:06<00:06, 20.33it/s] Loading 0: 82%|████████▏ | 592/723 [01:06<00:05, 21.87it/s] Loading 0: 82%|████████▏ | 596/723 [01:06<00:07, 16.59it/s] Loading 0: 83%|████████▎ | 599/723 [01:06<00:07, 15.89it/s] Loading 0: 84%|████████▍ | 606/723 [01:06<00:04, 23.44it/s] Loading 0: 84%|████████▍ | 610/723 [01:07<00:04, 24.23it/s] Loading 0: 85%|████████▍ | 614/723 [01:07<00:04, 26.39it/s] Loading 0: 85%|████████▌ | 618/723 [01:07<00:03, 27.21it/s] Loading 0: 86%|████████▌ | 622/723 [01:07<00:05, 18.71it/s] Loading 0: 86%|████████▋ | 625/723 [01:07<00:05, 19.15it/s] Loading 0: 87%|████████▋ | 630/723 [01:08<00:03, 24.13it/s] Loading 0: 88%|████████▊ | 634/723 [01:08<00:03, 25.36it/s] Loading 0: 88%|████████▊ | 638/723 [01:08<00:03, 27.55it/s] Loading 0: 89%|████████▉ | 643/723 [01:08<00:02, 31.77it/s] Loading 0: 89%|████████▉ | 647/723 [01:08<00:03, 19.89it/s] Loading 0: 90%|█████████ | 651/723 [01:08<00:03, 21.98it/s] Loading 0: 90%|█████████ | 654/723 [01:09<00:03, 22.41it/s] Loading 0: 91%|█████████▏| 661/723 [01:09<00:02, 29.36it/s] Loading 0: 92%|█████████▏| 666/723 [01:09<00:01, 32.60it/s] Loading 0: 93%|█████████▎| 672/723 [01:09<00:01, 25.91it/s] Loading 0: 93%|█████████▎| 676/723 [01:09<00:01, 25.09it/s] Loading 0: 94%|█████████▍| 679/723 [01:19<00:32, 1.35it/s] Loading 0: 95%|█████████▍| 684/723 [01:20<00:19, 1.99it/s] Loading 0: 95%|█████████▌| 688/723 [01:20<00:12, 2.70it/s] Loading 0: 96%|█████████▌| 693/723 [01:20<00:07, 3.92it/s] Loading 0: 97%|█████████▋| 698/723 [01:20<00:04, 5.11it/s] Loading 0: 97%|█████████▋| 702/723 [01:20<00:03, 6.38it/s] Loading 0: 98%|█████████▊| 706/723 [01:20<00:02, 8.14it/s] Loading 0: 98%|█████████▊| 711/723 [01:21<00:01, 11.21it/s] Loading 0: 99%|█████████▉| 715/723 [01:21<00:00, 13.66it/s] Loading 0: 100%|█████████▉| 721/723 [01:21<00:00, 19.07it/s] Loading 0: 100%|█████████▉| 722/723 [01:33<00:00, 19.07it/s] Loading 0: 100%|██████████| 723/723 [01:33<00:00, 1.04it/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-v2-mkmlizer: quantized model in 107.026s
turboderp-cat-llama-3-70-8684-v2-mkmlizer: Processed model turboderp/Cat-Llama-3-70B-instruct in 394.650s
turboderp-cat-llama-3-70-8684-v2-mkmlizer: creating bucket guanaco-mkml-models
turboderp-cat-llama-3-70-8684-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
turboderp-cat-llama-3-70-8684-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/turboderp-cat-llama-3-70-8684-v2
turboderp-cat-llama-3-70-8684-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/turboderp-cat-llama-3-70-8684-v2/config.json
turboderp-cat-llama-3-70-8684-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/turboderp-cat-llama-3-70-8684-v2/special_tokens_map.json
turboderp-cat-llama-3-70-8684-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/turboderp-cat-llama-3-70-8684-v2/tokenizer_config.json
turboderp-cat-llama-3-70-8684-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/turboderp-cat-llama-3-70-8684-v2/tokenizer.json
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
turboderp-cat-llama-3-70-8684-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.5.safetensors s3://guanaco-mkml-models/turboderp-cat-llama-3-70-8684-v2/flywheel_model.5.safetensors
turboderp-cat-llama-3-70-8684-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.4.safetensors s3://guanaco-mkml-models/turboderp-cat-llama-3-70-8684-v2/flywheel_model.4.safetensors
turboderp-cat-llama-3-70-8684-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/turboderp-cat-llama-3-70-8684-v2/flywheel_model.3.safetensors
turboderp-cat-llama-3-70-8684-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/turboderp-cat-llama-3-70-8684-v2/flywheel_model.2.safetensors
turboderp-cat-llama-3-70-8684-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/turboderp-cat-llama-3-70-8684-v2/flywheel_model.0.safetensors
turboderp-cat-llama-3-70-8684-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/turboderp-cat-llama-3-70-8684-v2/flywheel_model.1.safetensors
turboderp-cat-llama-3-70-8684-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
turboderp-cat-llama-3-70-8684-v2-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-v2-mkmlizer: warnings.warn(
turboderp-cat-llama-3-70-8684-v2-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-v2-mkmlizer: warnings.warn(
turboderp-cat-llama-3-70-8684-v2-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-v2-mkmlizer: warnings.warn(
turboderp-cat-llama-3-70-8684-v2-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-v2-mkmlizer: return self.fget.__get__(instance, owner)()
turboderp-cat-llama-3-70-8684-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
turboderp-cat-llama-3-70-8684-v2-mkmlizer: creating bucket guanaco-reward-models
turboderp-cat-llama-3-70-8684-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
turboderp-cat-llama-3-70-8684-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/turboderp-cat-llama-3-70-8684-v2_reward
turboderp-cat-llama-3-70-8684-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/turboderp-cat-llama-3-70-8684-v2_reward/config.json
turboderp-cat-llama-3-70-8684-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/turboderp-cat-llama-3-70-8684-v2_reward/tokenizer_config.json
turboderp-cat-llama-3-70-8684-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/turboderp-cat-llama-3-70-8684-v2_reward/merges.txt
turboderp-cat-llama-3-70-8684-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/turboderp-cat-llama-3-70-8684-v2_reward/vocab.json
turboderp-cat-llama-3-70-8684-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/turboderp-cat-llama-3-70-8684-v2_reward/special_tokens_map.json
turboderp-cat-llama-3-70-8684-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/turboderp-cat-llama-3-70-8684-v2_reward/tokenizer.json
turboderp-cat-llama-3-70-8684-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/turboderp-cat-llama-3-70-8684-v2_reward/reward.tensors
Job turboderp-cat-llama-3-70-8684-v2-mkmlizer completed after 455.31s with status: succeeded
Stopping job with name turboderp-cat-llama-3-70-8684-v2-mkmlizer
Pipeline stage MKMLizer completed in 787.56s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service turboderp-cat-llama-3-70-8684-v2
Waiting for inference service turboderp-cat-llama-3-70-8684-v2 to be ready
Inference service turboderp-cat-llama-3-70-8684-v2 ready after 90.85012245178223s
Pipeline stage ISVCDeployer completed in 96.70s
Running pipeline stage StressChecker
Received healthy response to inference request in 5.252787351608276s
Received healthy response to inference request in 4.02629017829895s
Received healthy response to inference request in 4.259406805038452s
Received healthy response to inference request in 4.253160715103149s
Received healthy response to inference request in 4.21691632270813s
5 requests
0 failed requests
5th percentile: 4.064415407180786
10th percentile: 4.102540636062622
20th percentile: 4.178791093826294
30th percentile: 4.224165201187134
40th percentile: 4.238662958145142
50th percentile: 4.253160715103149
60th percentile: 4.25565915107727
70th percentile: 4.258157587051391
80th percentile: 4.458082914352417
90th percentile: 4.855435132980347
95th percentile: 5.0541112422943115
99th percentile: 5.213052129745483
mean time: 4.401712274551391
Pipeline stage StressChecker completed in 23.21s
turboderp-cat-llama-3-70_8684_v2 status is now deployed due to DeploymentManager action
turboderp-cat-llama-3-70_8684_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics