undi95-meta-llama-3-70b-_6209

submission_id: undi95-meta-llama-3-70b-_6209_v9
developer_uid: Jellywibble
best_of: 2
display_name: meta-llama-reward-bo2
family_friendly_score: 0.0
formatter: {'memory_template': "<|im_start|>system\n{bot_name}'s Persona: {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}
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', '<|im_end|>', '<|im_start|>', '\n\n'], 'max_input_tokens': 512, 'best_of': 2, 'max_output_tokens': 64}
ineligible_reason: num_battles<5000
is_internal_developer: True
language_model: Undi95/Meta-Llama-3-70B-Instruct-hf
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: Undi95/Meta-Llama-3-70B-
model_name: meta-llama-reward-bo2
model_num_parameters: 70553706496.0
model_repo: Undi95/Meta-Llama-3-70B-Instruct-hf
model_size: 71B
num_battles: 55
num_wins: 33
ranking_group: single
reward_formatter: {'bot_template': 'Bot: {message}\n', 'memory_template': 'Memory: {memory}\n', 'prompt_template': '{prompt}\n', 'response_template': 'Bot:', 'truncate_by_message': False, 'user_template': 'User: {message}\n'}
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
status: torndown
submission_type: basic
timestamp: 2024-07-13T20:29:03+00:00
us_pacific_date: 2024-07-13
win_ratio: 0.6
Resubmit model
Running pipeline stage MKMLizer
Starting job with name undi95-meta-llama-3-70b-6209-v9-mkmlizer
Waiting for job on undi95-meta-llama-3-70b-6209-v9-mkmlizer to finish
undi95-meta-llama-3-70b-6209-v9-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
undi95-meta-llama-3-70b-6209-v9-mkmlizer: ║     _____            __           __                                ║
undi95-meta-llama-3-70b-6209-v9-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
undi95-meta-llama-3-70b-6209-v9-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
undi95-meta-llama-3-70b-6209-v9-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
undi95-meta-llama-3-70b-6209-v9-mkmlizer: ║       /___/                                                         ║
undi95-meta-llama-3-70b-6209-v9-mkmlizer: ║                                                                     ║
undi95-meta-llama-3-70b-6209-v9-mkmlizer: ║  Version: 0.8.14                                                    ║
undi95-meta-llama-3-70b-6209-v9-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
undi95-meta-llama-3-70b-6209-v9-mkmlizer: ║  https://mk1.ai                                                     ║
undi95-meta-llama-3-70b-6209-v9-mkmlizer: ║                                                                     ║
undi95-meta-llama-3-70b-6209-v9-mkmlizer: ║  The license key for the current software has been verified as      ║
undi95-meta-llama-3-70b-6209-v9-mkmlizer: ║  belonging to:                                                      ║
undi95-meta-llama-3-70b-6209-v9-mkmlizer: ║                                                                     ║
undi95-meta-llama-3-70b-6209-v9-mkmlizer: ║  Chai Research Corp.                                                ║
undi95-meta-llama-3-70b-6209-v9-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
undi95-meta-llama-3-70b-6209-v9-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
undi95-meta-llama-3-70b-6209-v9-mkmlizer: ║                                                                     ║
undi95-meta-llama-3-70b-6209-v9-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
undi95-meta-llama-3-70b-6209-v9-mkmlizer: Downloaded to shared memory in 694.858s
undi95-meta-llama-3-70b-6209-v9-mkmlizer: quantizing model to /dev/shm/model_cache
undi95-meta-llama-3-70b-6209-v9-mkmlizer: Saving flywheel model at /dev/shm/model_cache
undi95-meta-llama-3-70b-6209-v9-mkmlizer: 
Loading 0:   0%|          | 0/723 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/723 [00:00<00:26, 26.72it/s]
Loading 0:   1%|          | 8/723 [00:00<00:21, 32.89it/s]
Loading 0:   2%|▏         | 12/723 [00:00<00:20, 35.45it/s]
Loading 0:   2%|▏         | 16/723 [00:00<00:42, 16.83it/s]
Loading 0:   3%|▎         | 19/723 [00:00<00:39, 17.63it/s]
Loading 0:   3%|▎         | 22/723 [00:01<00:37, 18.45it/s]
Loading 0:   4%|▎         | 27/723 [00:01<00:28, 24.25it/s]
Loading 0:   4%|▍         | 31/723 [00:01<00:27, 25.39it/s]
Loading 0:   5%|▍         | 35/723 [00:01<00:24, 28.65it/s]
Loading 0:   6%|▌         | 42/723 [00:01<00:31, 21.95it/s]
Loading 0:   6%|▌         | 45/723 [00:02<00:34, 19.55it/s]
Loading 0:   7%|▋         | 49/723 [00:02<00:31, 21.27it/s]
Loading 0:   7%|▋         | 54/723 [00:02<00:26, 25.64it/s]
Loading 0:   8%|▊         | 58/723 [00:02<00:25, 26.12it/s]
Loading 0:   9%|▊         | 63/723 [00:02<00:22, 29.88it/s]
Loading 0:   9%|▉         | 68/723 [00:02<00:31, 21.11it/s]
Loading 0:  10%|▉         | 71/723 [00:03<00:35, 18.41it/s]
Loading 0:  11%|█         | 76/723 [00:03<00:30, 21.49it/s]
Loading 0:  11%|█         | 81/723 [00:03<00:24, 25.69it/s]
Loading 0:  12%|█▏        | 85/723 [00:03<00:24, 26.23it/s]
Loading 0:  12%|█▏        | 90/723 [00:03<00:21, 29.95it/s]
Loading 0:  13%|█▎        | 94/723 [00:04<00:36, 17.09it/s]
Loading 0:  14%|█▎        | 99/723 [00:04<00:29, 21.31it/s]
Loading 0:  14%|█▍        | 103/723 [00:04<00:27, 22.91it/s]
Loading 0:  15%|█▍        | 108/723 [00:04<00:22, 27.09it/s]
Loading 0:  15%|█▌        | 112/723 [00:04<00:23, 25.75it/s]
Loading 0:  16%|█▌        | 116/723 [00:05<00:32, 18.62it/s]
Loading 0:  17%|█▋        | 120/723 [00:05<00:29, 20.64it/s]
Loading 0:  17%|█▋        | 123/723 [00:05<00:29, 20.62it/s]
Loading 0:  17%|█▋        | 124/723 [00:20<00:29, 20.62it/s]
Loading 0:  17%|█▋        | 125/723 [00:31<24:02,  2.41s/it]
Loading 0:  18%|█▊        | 130/723 [00:31<14:33,  1.47s/it]
Loading 0:  19%|█▊        | 135/723 [00:31<09:19,  1.05it/s]
Loading 0:  19%|█▉        | 140/723 [00:31<06:10,  1.57it/s]
Loading 0:  20%|█▉        | 144/723 [00:32<04:46,  2.02it/s]
Loading 0:  20%|██        | 148/723 [00:32<03:29,  2.74it/s]
Loading 0:  21%|██        | 153/723 [00:32<02:22,  4.01it/s]
Loading 0:  22%|██▏       | 157/723 [00:32<01:47,  5.27it/s]
Loading 0:  22%|██▏       | 162/723 [00:32<01:15,  7.44it/s]
Loading 0:  23%|██▎       | 168/723 [00:33<01:00,  9.11it/s]
Loading 0:  24%|██▎       | 171/723 [00:33<00:56,  9.75it/s]
Loading 0:  24%|██▍       | 175/723 [00:33<00:45, 11.94it/s]
Loading 0:  25%|██▍       | 180/723 [00:33<00:34, 15.70it/s]
Loading 0:  25%|██▌       | 184/723 [00:33<00:30, 17.84it/s]
Loading 0:  26%|██▌       | 189/723 [00:34<00:24, 22.01it/s]
Loading 0:  27%|██▋       | 194/723 [00:34<00:29, 18.13it/s]
Loading 0:  27%|██▋       | 197/723 [00:34<00:30, 17.07it/s]
Loading 0:  28%|██▊       | 202/723 [00:34<00:25, 20.10it/s]
Loading 0:  29%|██▊       | 207/723 [00:34<00:21, 24.21it/s]
Loading 0:  29%|██▉       | 211/723 [00:35<00:20, 25.10it/s]
Loading 0:  30%|██▉       | 216/723 [00:35<00:17, 28.92it/s]
Loading 0:  30%|███       | 220/723 [00:35<00:30, 16.75it/s]
Loading 0:  31%|███       | 225/723 [00:35<00:23, 20.88it/s]
Loading 0:  32%|███▏      | 229/723 [00:35<00:22, 22.41it/s]
Loading 0:  32%|███▏      | 234/723 [00:36<00:18, 26.45it/s]
Loading 0:  33%|███▎      | 238/723 [00:36<00:18, 25.73it/s]
Loading 0:  33%|███▎      | 242/723 [00:36<00:26, 18.38it/s]
Loading 0:  34%|███▍      | 246/723 [00:36<00:23, 20.23it/s]
Loading 0:  34%|███▍      | 249/723 [00:36<00:23, 20.31it/s]
Loading 0:  35%|███▌      | 255/723 [00:37<00:17, 26.90it/s]
Loading 0:  36%|███▌      | 259/723 [00:37<00:17, 26.86it/s]
Loading 0:  36%|███▋      | 263/723 [00:37<00:15, 28.87it/s]
Loading 0:  36%|███▋      | 263/723 [00:51<00:15, 28.87it/s]
Loading 0:  37%|███▋      | 264/723 [01:04<19:03,  2.49s/it]
Loading 0:  37%|███▋      | 268/723 [01:04<12:48,  1.69s/it]
Loading 0:  37%|███▋      | 271/723 [01:04<09:23,  1.25s/it]
Loading 0:  38%|███▊      | 274/723 [01:05<06:50,  1.09it/s]
Loading 0:  38%|███▊      | 278/723 [01:05<04:30,  1.65it/s]
Loading 0:  39%|███▉      | 283/723 [01:05<02:50,  2.58it/s]
Loading 0:  40%|███▉      | 288/723 [01:05<01:52,  3.86it/s]
Loading 0:  41%|████      | 294/723 [01:05<01:19,  5.39it/s]
Loading 0:  41%|████      | 297/723 [01:06<01:08,  6.20it/s]
Loading 0:  42%|████▏     | 301/723 [01:06<00:53,  7.93it/s]
Loading 0:  42%|████▏     | 305/723 [01:06<00:40, 10.31it/s]
Loading 0:  43%|████▎     | 310/723 [01:06<00:31, 13.21it/s]
Loading 0:  43%|████▎     | 314/723 [01:06<00:25, 16.23it/s]
Loading 0:  44%|████▍     | 320/723 [01:06<00:26, 15.32it/s]
Loading 0:  45%|████▍     | 323/723 [01:07<00:26, 14.97it/s]
Loading 0:  45%|████▌     | 327/723 [01:07<00:21, 18.06it/s]
Loading 0:  46%|████▌     | 330/723 [01:07<00:21, 18.57it/s]
Loading 0:  46%|████▋     | 336/723 [01:07<00:15, 24.82it/s]
Loading 0:  47%|████▋     | 340/723 [01:07<00:15, 25.34it/s]
Loading 0:  48%|████▊     | 344/723 [01:08<00:21, 17.68it/s]
Loading 0:  48%|████▊     | 347/723 [01:08<00:22, 16.64it/s]
Loading 0:  49%|████▉     | 354/723 [01:08<00:15, 23.67it/s]
Loading 0:  50%|████▉     | 358/723 [01:08<00:14, 24.41it/s]
Loading 0:  50%|█████     | 362/723 [01:08<00:13, 26.68it/s]
Loading 0:  51%|█████     | 366/723 [01:08<00:12, 28.30it/s]
Loading 0:  51%|█████     | 370/723 [01:09<00:19, 18.26it/s]
Loading 0:  52%|█████▏    | 373/723 [01:09<00:18, 18.81it/s]
Loading 0:  52%|█████▏    | 378/723 [01:09<00:14, 23.56it/s]
Loading 0:  53%|█████▎    | 382/723 [01:09<00:13, 24.80it/s]
Loading 0:  54%|█████▎    | 387/723 [01:09<00:11, 28.90it/s]
Loading 0:  54%|█████▍    | 392/723 [01:09<00:10, 32.34it/s]
Loading 0:  55%|█████▍    | 396/723 [01:10<00:17, 18.29it/s]
Loading 0:  55%|█████▌    | 400/723 [01:10<00:15, 20.22it/s]
Loading 0:  55%|█████▌    | 400/723 [01:24<00:15, 20.22it/s]
Loading 0:  55%|█████▌    | 401/723 [01:36<13:08,  2.45s/it]
Loading 0:  56%|█████▋    | 408/723 [01:37<06:46,  1.29s/it]
Loading 0:  57%|█████▋    | 412/723 [01:37<04:52,  1.06it/s]
Loading 0:  58%|█████▊    | 420/723 [01:37<02:45,  1.83it/s]
Loading 0:  59%|█████▊    | 423/723 [01:37<02:18,  2.17it/s]
Loading 0:  59%|█████▉    | 427/723 [01:38<01:42,  2.89it/s]
Loading 0:  60%|█████▉    | 432/723 [01:38<01:10,  4.15it/s]
Loading 0:  60%|██████    | 436/723 [01:38<00:53,  5.40it/s]
Loading 0:  61%|██████    | 441/723 [01:38<00:37,  7.54it/s]
Loading 0:  62%|██████▏   | 446/723 [01:38<00:31,  8.77it/s]
Loading 0:  62%|██████▏   | 449/723 [01:39<00:28,  9.52it/s]
Loading 0:  63%|██████▎   | 454/723 [01:39<00:21, 12.44it/s]
Loading 0:  63%|██████▎   | 459/723 [01:39<00:16, 16.17it/s]
Loading 0:  64%|██████▍   | 463/723 [01:39<00:14, 18.23it/s]
Loading 0:  65%|██████▍   | 467/723 [01:39<00:12, 20.89it/s]
Loading 0:  65%|██████▌   | 471/723 [01:40<00:16, 15.12it/s]
Loading 0:  66%|██████▌   | 474/723 [01:40<00:15, 16.09it/s]
Loading 0:  66%|██████▋   | 480/723 [01:40<00:11, 21.15it/s]
Loading 0:  67%|██████▋   | 483/723 [01:40<00:12, 19.67it/s]
Loading 0:  67%|██████▋   | 488/723 [01:40<00:10, 23.05it/s]
Loading 0:  68%|██████▊   | 491/723 [01:40<00:10, 22.76it/s]
Loading 0:  68%|██████▊   | 494/723 [01:41<00:15, 14.34it/s]
Loading 0:  69%|██████▊   | 497/723 [01:41<00:13, 16.59it/s]
Loading 0:  69%|██████▉   | 500/723 [01:41<00:15, 14.37it/s]
Loading 0:  70%|███████   | 507/723 [01:41<00:10, 20.91it/s]
Loading 0:  71%|███████   | 510/723 [01:41<00:11, 19.11it/s]
Loading 0:  71%|███████   | 515/723 [01:42<00:09, 22.13it/s]
Loading 0:  72%|███████▏  | 520/723 [01:42<00:12, 16.44it/s]
Loading 0:  72%|███████▏  | 523/723 [01:42<00:12, 16.20it/s]
Loading 0:  73%|███████▎  | 526/723 [01:42<00:12, 16.16it/s]
Loading 0:  73%|███████▎  | 530/723 [01:43<00:10, 19.19it/s]
Loading 0:  74%|███████▍  | 534/723 [01:43<00:08, 22.11it/s]
Loading 0:  74%|███████▍  | 537/723 [01:43<00:09, 20.14it/s]
Loading 0:  75%|███████▍  | 540/723 [01:56<00:09, 20.14it/s]
Loading 0:  75%|███████▍  | 541/723 [02:09<06:34,  2.17s/it]
Loading 0:  76%|███████▌  | 546/723 [02:10<04:09,  1.41s/it]
Loading 0:  76%|███████▌  | 548/723 [02:10<03:26,  1.18s/it]
Loading 0:  76%|███████▋  | 552/723 [02:10<02:18,  1.24it/s]
Loading 0:  77%|███████▋  | 554/723 [02:10<01:53,  1.49it/s]
Loading 0:  78%|███████▊  | 561/723 [02:11<00:57,  2.80it/s]
Loading 0:  78%|███████▊  | 564/723 [02:11<00:46,  3.43it/s]
Loading 0:  79%|███████▉  | 572/723 [02:11<00:27,  5.47it/s]
Loading 0:  79%|███████▉  | 574/723 [02:12<00:25,  5.92it/s]
Loading 0:  80%|███████▉  | 577/723 [02:12<00:20,  7.21it/s]
Loading 0:  80%|████████  | 580/723 [02:12<00:17,  8.36it/s]
Loading 0:  80%|████████  | 582/723 [02:12<00:14,  9.41it/s]
Loading 0:  81%|████████▏ | 588/723 [02:12<00:09, 14.29it/s]
Loading 0:  82%|████████▏ | 591/723 [02:12<00:09, 14.43it/s]
Loading 0:  82%|████████▏ | 596/723 [02:13<00:09, 13.18it/s]
Loading 0:  83%|████████▎ | 598/723 [02:13<00:09, 12.59it/s]
Loading 0:  83%|████████▎ | 601/723 [02:13<00:08, 14.89it/s]
Loading 0:  84%|████████▍ | 606/723 [02:13<00:06, 18.94it/s]
Loading 0:  84%|████████▍ | 609/723 [02:13<00:06, 17.89it/s]
Loading 0:  85%|████████▍ | 614/723 [02:14<00:05, 21.50it/s]
Loading 0:  85%|████████▌ | 617/723 [02:14<00:05, 21.03it/s]
Loading 0:  86%|████████▌ | 620/723 [02:14<00:07, 14.35it/s]
Loading 0:  86%|████████▌ | 622/723 [02:14<00:06, 15.19it/s]
Loading 0:  86%|████████▋ | 625/723 [02:14<00:06, 15.44it/s]
Loading 0:  87%|████████▋ | 629/723 [02:14<00:04, 18.99it/s]
Loading 0:  88%|████████▊ | 633/723 [02:15<00:04, 22.21it/s]
Loading 0:  88%|████████▊ | 636/723 [02:15<00:04, 20.07it/s]
Loading 0:  89%|████████▊ | 641/723 [02:15<00:03, 23.77it/s]
Loading 0:  89%|████████▉ | 646/723 [02:15<00:04, 17.47it/s]
Loading 0:  90%|████████▉ | 649/723 [02:16<00:04, 17.00it/s]
Loading 0:  90%|█████████ | 652/723 [02:16<00:04, 16.76it/s]
Loading 0:  91%|█████████ | 655/723 [02:16<00:03, 18.96it/s]
Loading 0:  91%|█████████▏| 660/723 [02:16<00:02, 22.69it/s]
Loading 0:  92%|█████████▏| 663/723 [02:16<00:02, 20.34it/s]
Loading 0:  93%|█████████▎| 670/723 [02:16<00:01, 28.94it/s]
Loading 0:  93%|█████████▎| 674/723 [02:17<00:03, 15.98it/s]
Loading 0:  94%|█████████▍| 678/723 [02:17<00:02, 17.20it/s]
Loading 0:  94%|█████████▍| 678/723 [02:29<00:02, 17.20it/s]
Loading 0:  94%|█████████▍| 679/723 [02:43<01:46,  2.42s/it]
Loading 0:  94%|█████████▍| 681/723 [02:43<01:21,  1.94s/it]
Loading 0:  95%|█████████▌| 687/723 [02:44<00:37,  1.04s/it]
Loading 0:  95%|█████████▌| 690/723 [02:44<00:26,  1.25it/s]
Loading 0:  97%|█████████▋| 698/723 [02:44<00:10,  2.28it/s]
Loading 0:  97%|█████████▋| 701/723 [02:45<00:08,  2.72it/s]
Loading 0:  98%|█████████▊| 705/723 [02:45<00:04,  3.68it/s]
Loading 0:  98%|█████████▊| 708/723 [02:45<00:03,  4.48it/s]
Loading 0:  99%|█████████▉| 714/723 [02:45<00:01,  6.93it/s]
Loading 0:  99%|█████████▉| 717/723 [02:45<00:00,  7.92it/s]
Loading 0: 100%|█████████▉| 722/723 [03:00<00:00,  7.92it/s]
Loading 0: 100%|██████████| 723/723 [03:00<00:00,  1.03s/it]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
undi95-meta-llama-3-70b-6209-v9-mkmlizer: quantized model in 203.451s
undi95-meta-llama-3-70b-6209-v9-mkmlizer: Processed model Undi95/Meta-Llama-3-70B-Instruct-hf in 898.310s
undi95-meta-llama-3-70b-6209-v9-mkmlizer: creating bucket guanaco-mkml-models
undi95-meta-llama-3-70b-6209-v9-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
undi95-meta-llama-3-70b-6209-v9-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v9
undi95-meta-llama-3-70b-6209-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v9/tokenizer_config.json
undi95-meta-llama-3-70b-6209-v9-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v9/special_tokens_map.json
undi95-meta-llama-3-70b-6209-v9-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v9/config.json
undi95-meta-llama-3-70b-6209-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v9/tokenizer.json
undi95-meta-llama-3-70b-6209-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.5.safetensors s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v9/flywheel_model.5.safetensors
undi95-meta-llama-3-70b-6209-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.4.safetensors s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v9/flywheel_model.4.safetensors
undi95-meta-llama-3-70b-6209-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v9/flywheel_model.1.safetensors
undi95-meta-llama-3-70b-6209-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v9/flywheel_model.2.safetensors
undi95-meta-llama-3-70b-6209-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v9/flywheel_model.3.safetensors
undi95-meta-llama-3-70b-6209-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v9/flywheel_model.0.safetensors
undi95-meta-llama-3-70b-6209-v9-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
undi95-meta-llama-3-70b-6209-v9-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
undi95-meta-llama-3-70b-6209-v9-mkmlizer:   warnings.warn(
undi95-meta-llama-3-70b-6209-v9-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
undi95-meta-llama-3-70b-6209-v9-mkmlizer:   warnings.warn(
undi95-meta-llama-3-70b-6209-v9-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
undi95-meta-llama-3-70b-6209-v9-mkmlizer:   warnings.warn(
undi95-meta-llama-3-70b-6209-v9-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.
undi95-meta-llama-3-70b-6209-v9-mkmlizer:   warnings.warn(
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
undi95-meta-llama-3-70b-6209-v9-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:07<00:07,  7.82s/it]
Downloading shards: 100%|██████████| 2/2 [00:13<00:00,  6.33s/it]
Downloading shards: 100%|██████████| 2/2 [00:13<00:00,  6.56s/it]
undi95-meta-llama-3-70b-6209-v9-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  1.28it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:01<00:00,  2.04it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:01<00:00,  1.87it/s]
undi95-meta-llama-3-70b-6209-v9-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
undi95-meta-llama-3-70b-6209-v9-mkmlizer: Saving duration: 2.938s
undi95-meta-llama-3-70b-6209-v9-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 19.145s
undi95-meta-llama-3-70b-6209-v9-mkmlizer: creating bucket guanaco-reward-models
undi95-meta-llama-3-70b-6209-v9-mkmlizer: Bucket 's3://guanaco-reward-models/' created
undi95-meta-llama-3-70b-6209-v9-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/undi95-meta-llama-3-70b-6209-v9_reward
undi95-meta-llama-3-70b-6209-v9-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/undi95-meta-llama-3-70b-6209-v9_reward/config.json
undi95-meta-llama-3-70b-6209-v9-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/undi95-meta-llama-3-70b-6209-v9_reward/special_tokens_map.json
undi95-meta-llama-3-70b-6209-v9-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/undi95-meta-llama-3-70b-6209-v9_reward/tokenizer_config.json
undi95-meta-llama-3-70b-6209-v9-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/undi95-meta-llama-3-70b-6209-v9_reward/merges.txt
undi95-meta-llama-3-70b-6209-v9-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/undi95-meta-llama-3-70b-6209-v9_reward/tokenizer.json
undi95-meta-llama-3-70b-6209-v9-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/undi95-meta-llama-3-70b-6209-v9_reward/vocab.json
undi95-meta-llama-3-70b-6209-v9-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/undi95-meta-llama-3-70b-6209-v9_reward/reward.tensors
Job undi95-meta-llama-3-70b-6209-v9-mkmlizer completed after 984.63s with status: succeeded
Stopping job with name undi95-meta-llama-3-70b-6209-v9-mkmlizer
Pipeline stage MKMLizer completed in 985.54s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service undi95-meta-llama-3-70b-6209-v9
Waiting for inference service undi95-meta-llama-3-70b-6209-v9 to be ready
Inference service undi95-meta-llama-3-70b-6209-v9 ready after 271.23082661628723s
Pipeline stage ISVCDeployer completed in 278.03s
Running pipeline stage StressChecker
Received healthy response to inference request in 5.050232648849487s
Received healthy response to inference request in 4.158240079879761s
Received healthy response to inference request in 4.1583662033081055s
Received healthy response to inference request in 4.1680827140808105s
Received healthy response to inference request in 4.173860549926758s
5 requests
0 failed requests
5th percentile: 4.15826530456543
10th percentile: 4.158290529251099
20th percentile: 4.158340978622436
30th percentile: 4.160309505462647
40th percentile: 4.164196109771728
50th percentile: 4.1680827140808105
60th percentile: 4.17039384841919
70th percentile: 4.172704982757568
80th percentile: 4.3491349697113035
90th percentile: 4.699683809280396
95th percentile: 4.874958229064942
99th percentile: 5.015177764892578
mean time: 4.341756439208984
Pipeline stage StressChecker completed in 22.47s
undi95-meta-llama-3-70b-_6209_v9 status is now deployed due to DeploymentManager action
admin requested tearing down of undi95-meta-llama-3-70b-_6209_v9
Running pipeline stage ISVCDeleter
Pipeline stage %s skipped, reason=%s
Pipeline stage ISVCDeleter completed in 0.48s
Running pipeline stage MKMLModelDeleter
Pipeline stage %s skipped, reason=%s
Pipeline stage MKMLModelDeleter completed in 0.34s
undi95-meta-llama-3-70b-_6209_v9 status is now torndown due to DeploymentManager action