undi95-meta-llama-3-70b_6209

developer_uid: Rose8860
submission_id: undi95-meta-llama-3-70b_6209_v25
model_name: undi95-meta-llama-3-hollow
model_group: Undi95/Meta-Llama-3-70B-
status: torndown
timestamp: 2024-07-23T12:22:28+00:00
num_battles: 25479
num_wins: 12165
celo_rating: 1174.35
family_friendly_score: 0.0
submission_type: basic
model_repo: Undi95/Meta-Llama-3-70B-Instruct-hf
model_architecture: LlamaForCausalLM
model_num_parameters: 70553706496.0
best_of: 2
max_input_tokens: 512
max_output_tokens: 64
reward_model: default
display_name: undi95-meta-llama-3-hollow
is_internal_developer: False
language_model: Undi95/Meta-Llama-3-70B-Instruct-hf
model_size: 71B
ranking_group: single
us_pacific_date: 2024-07-23
win_ratio: 0.47745201931002
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': ['<|im_start|>', '\n', '<|im_end|>', '\n\n'], 'max_input_tokens': 512, 'best_of': 2, 'max_output_tokens': 64}
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}
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: ChaiML/gpt2_xl_pairwise_89m_step_347634
Resubmit model
Running pipeline stage MKMLizer
Starting job with name undi95-meta-llama-3-70b-6209-v25-mkmlizer
Stopping job with name undi95-meta-llama-3-70b-6209-v25-mkmlizer
%s, retrying in %s seconds...
Starting job with name undi95-meta-llama-3-70b-6209-v25-mkmlizer
Waiting for job on undi95-meta-llama-3-70b-6209-v25-mkmlizer to finish
undi95-meta-llama-3-70b-6209-v25-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
undi95-meta-llama-3-70b-6209-v25-mkmlizer: ║     _____            __           __                                ║
undi95-meta-llama-3-70b-6209-v25-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
undi95-meta-llama-3-70b-6209-v25-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
undi95-meta-llama-3-70b-6209-v25-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
undi95-meta-llama-3-70b-6209-v25-mkmlizer: ║       /___/                                                         ║
undi95-meta-llama-3-70b-6209-v25-mkmlizer: ║                                                                     ║
undi95-meta-llama-3-70b-6209-v25-mkmlizer: ║  Version: 0.9.5.post3                                               ║
undi95-meta-llama-3-70b-6209-v25-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
undi95-meta-llama-3-70b-6209-v25-mkmlizer: ║  https://mk1.ai                                                     ║
undi95-meta-llama-3-70b-6209-v25-mkmlizer: ║                                                                     ║
undi95-meta-llama-3-70b-6209-v25-mkmlizer: ║  The license key for the current software has been verified as      ║
undi95-meta-llama-3-70b-6209-v25-mkmlizer: ║  belonging to:                                                      ║
undi95-meta-llama-3-70b-6209-v25-mkmlizer: ║                                                                     ║
undi95-meta-llama-3-70b-6209-v25-mkmlizer: ║  Chai Research Corp.                                                ║
undi95-meta-llama-3-70b-6209-v25-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
undi95-meta-llama-3-70b-6209-v25-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
undi95-meta-llama-3-70b-6209-v25-mkmlizer: ║                                                                     ║
undi95-meta-llama-3-70b-6209-v25-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission undi95-meta-llama-3-70b_6209_v18: ('http://undi95-meta-llama-3-70b-6209-v18-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"TypeError : SamplingParameters.__init__() got an unexpected keyword argument \'reward_max_tokens\'"}')
Failed to get response for submission undi95-meta-llama-3-70b_6209_v18: ('http://undi95-meta-llama-3-70b-6209-v18-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"TypeError : SamplingParameters.__init__() got an unexpected keyword argument \'reward_max_tokens\'"}')
undi95-meta-llama-3-70b-6209-v25-mkmlizer: Downloaded to shared memory in 279.168s
undi95-meta-llama-3-70b-6209-v25-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmptq6hbq6a, device:0
undi95-meta-llama-3-70b-6209-v25-mkmlizer: Saving flywheel model at /dev/shm/model_cache
undi95-meta-llama-3-70b-6209-v25-mkmlizer: 
Loading 0:   0%|          | 0/723 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/723 [00:00<00:26, 27.31it/s]
Loading 0:   1%|          | 8/723 [00:00<00:21, 33.45it/s]
Loading 0:   2%|▏         | 12/723 [00:00<00:20, 35.30it/s]
Loading 0:   2%|▏         | 16/723 [00:00<00:28, 24.63it/s]
Loading 0:   3%|▎         | 19/723 [00:00<00:30, 23.09it/s]
Loading 0:   3%|▎         | 22/723 [00:00<00:31, 22.44it/s]
Loading 0:   4%|▎         | 27/723 [00:01<00:25, 27.77it/s]
Loading 0:   4%|▍         | 31/723 [00:01<00:24, 27.75it/s]
Loading 0:   5%|▍         | 36/723 [00:01<00:21, 31.65it/s]
Loading 0:   6%|▌         | 42/723 [00:01<00:23, 29.46it/s]
Loading 0:   6%|▋         | 46/723 [00:01<00:26, 25.26it/s]
Loading 0:   7%|▋         | 49/723 [00:01<00:27, 24.31it/s]
Loading 0:   7%|▋         | 54/723 [00:01<00:23, 28.52it/s]
Loading 0:   8%|▊         | 58/723 [00:02<00:23, 28.35it/s]
Loading 0:   9%|▊         | 63/723 [00:02<00:20, 31.91it/s]
Loading 0:   9%|▉         | 68/723 [00:02<00:22, 28.82it/s]
Loading 0:  10%|▉         | 72/723 [00:02<00:25, 25.14it/s]
Loading 0:  11%|█         | 76/723 [00:02<00:25, 24.90it/s]
Loading 0:  11%|█         | 80/723 [00:02<00:23, 27.71it/s]
Loading 0:  12%|█▏        | 85/723 [00:03<00:22, 28.58it/s]
Loading 0:  12%|█▏        | 90/723 [00:03<00:19, 31.91it/s]
Loading 0:  13%|█▎        | 94/723 [00:03<00:28, 22.29it/s]
Loading 0:  14%|█▎        | 99/723 [00:03<00:23, 26.36it/s]
Loading 0:  14%|█▍        | 103/723 [00:03<00:23, 26.78it/s]
Loading 0:  15%|█▍        | 108/723 [00:03<00:20, 30.50it/s]
Loading 0:  15%|█▌        | 112/723 [00:04<00:20, 29.43it/s]
Loading 0:  16%|█▌        | 116/723 [00:04<00:23, 25.29it/s]
Loading 0:  17%|█▋        | 120/723 [00:04<00:23, 26.11it/s]
Loading 0:  17%|█▋        | 123/723 [00:04<00:24, 24.57it/s]
Loading 0:  17%|█▋        | 126/723 [00:19<12:55,  1.30s/it]
Loading 0:  18%|█▊        | 130/723 [00:19<08:48,  1.12it/s]
Loading 0:  19%|█▊        | 135/723 [00:20<05:37,  1.74it/s]
Loading 0:  19%|█▉        | 140/723 [00:20<03:44,  2.60it/s]
Loading 0:  20%|█▉        | 144/723 [00:20<02:54,  3.32it/s]
Loading 0:  20%|██        | 148/723 [00:20<02:09,  4.44it/s]
Loading 0:  21%|██        | 153/723 [00:20<01:29,  6.38it/s]
Loading 0:  22%|██▏       | 157/723 [00:20<01:09,  8.12it/s]
Loading 0:  22%|██▏       | 162/723 [00:21<00:50, 11.09it/s]
Loading 0:  23%|██▎       | 168/723 [00:21<00:39, 13.94it/s]
Loading 0:  24%|██▍       | 172/723 [00:21<00:37, 14.86it/s]
Loading 0:  24%|██▍       | 175/723 [00:21<00:34, 15.91it/s]
Loading 0:  25%|██▍       | 180/723 [00:21<00:26, 20.17it/s]
Loading 0:  25%|██▌       | 184/723 [00:21<00:24, 21.84it/s]
Loading 0:  26%|██▌       | 188/723 [00:21<00:21, 25.08it/s]
Loading 0:  27%|██▋       | 194/723 [00:22<00:20, 25.20it/s]
Loading 0:  27%|██▋       | 198/723 [00:22<00:23, 22.70it/s]
Loading 0:  28%|██▊       | 202/723 [00:22<00:22, 23.16it/s]
Loading 0:  29%|██▊       | 207/723 [00:22<00:19, 27.13it/s]
Loading 0:  29%|██▉       | 211/723 [00:22<00:18, 27.10it/s]
Loading 0:  30%|██▉       | 215/723 [00:22<00:17, 29.66it/s]
Loading 0:  30%|███       | 219/723 [00:23<00:22, 22.32it/s]
Loading 0:  31%|███       | 222/723 [00:23<00:23, 21.66it/s]
Loading 0:  32%|███▏      | 228/723 [00:23<00:17, 28.22it/s]
Loading 0:  32%|███▏      | 232/723 [00:23<00:17, 27.30it/s]
Loading 0:  33%|███▎      | 236/723 [00:23<00:16, 29.11it/s]
Loading 0:  33%|███▎      | 240/723 [00:23<00:16, 30.14it/s]
Loading 0:  34%|███▎      | 244/723 [00:24<00:20, 23.25it/s]
Loading 0:  34%|███▍      | 247/723 [00:24<00:21, 22.58it/s]
Loading 0:  35%|███▍      | 252/723 [00:24<00:17, 27.24it/s]
Loading 0:  35%|███▌      | 256/723 [00:24<00:17, 27.35it/s]
Loading 0:  36%|███▌      | 260/723 [00:24<00:15, 29.98it/s]
Loading 0:  37%|███▋      | 264/723 [00:24<00:14, 32.18it/s]
Loading 0:  37%|███▋      | 268/723 [00:25<00:17, 25.51it/s]
Loading 0:  37%|███▋      | 268/723 [00:40<00:17, 25.51it/s]
Loading 0:  37%|███▋      | 269/723 [00:40<11:25,  1.51s/it]
Loading 0:  38%|███▊      | 273/723 [00:40<07:24,  1.01it/s]
Loading 0:  38%|███▊      | 276/723 [00:40<05:25,  1.37it/s]
Loading 0:  39%|███▉      | 282/723 [00:40<03:03,  2.40it/s]
Loading 0:  40%|███▉      | 286/723 [00:40<02:13,  3.27it/s]
Loading 0:  41%|████      | 294/723 [00:41<01:18,  5.47it/s]
Loading 0:  41%|████      | 297/723 [00:41<01:08,  6.21it/s]
Loading 0:  42%|████▏     | 301/723 [00:41<00:53,  7.88it/s]
Loading 0:  42%|████▏     | 306/723 [00:41<00:38, 10.74it/s]
Loading 0:  43%|████▎     | 310/723 [00:41<00:32, 12.89it/s]
Loading 0:  44%|████▎     | 315/723 [00:41<00:24, 16.70it/s]
Loading 0:  44%|████▍     | 320/723 [00:42<00:21, 18.56it/s]
Loading 0:  45%|████▍     | 324/723 [00:42<00:21, 18.19it/s]
Loading 0:  45%|████▌     | 328/723 [00:42<00:20, 19.35it/s]
Loading 0:  46%|████▌     | 332/723 [00:42<00:17, 22.65it/s]
Loading 0:  47%|████▋     | 337/723 [00:42<00:15, 24.66it/s]
Loading 0:  47%|████▋     | 342/723 [00:42<00:13, 28.44it/s]
Loading 0:  48%|████▊     | 346/723 [00:43<00:18, 20.37it/s]
Loading 0:  49%|████▊     | 351/723 [00:43<00:15, 24.48it/s]
Loading 0:  49%|████▉     | 355/723 [00:43<00:14, 25.23it/s]
Loading 0:  50%|████▉     | 359/723 [00:43<00:12, 28.06it/s]
Loading 0:  50%|█████     | 363/723 [00:43<00:13, 26.91it/s]
Loading 0:  51%|█████     | 368/723 [00:44<00:14, 24.36it/s]
Loading 0:  51%|█████▏    | 372/723 [00:44<00:13, 25.13it/s]
Loading 0:  52%|█████▏    | 375/723 [00:44<00:14, 23.82it/s]
Loading 0:  53%|█████▎    | 381/723 [00:44<00:11, 30.38it/s]
Loading 0:  53%|█████▎    | 385/723 [00:44<00:11, 29.39it/s]
Loading 0:  54%|█████▍    | 389/723 [00:44<00:10, 30.62it/s]
Loading 0:  54%|█████▍    | 394/723 [00:44<00:12, 27.05it/s]
Loading 0:  55%|█████▍    | 397/723 [00:45<00:12, 25.32it/s]
Loading 0:  55%|█████▌    | 400/723 [00:45<00:13, 24.05it/s]
Loading 0:  56%|█████▌    | 403/723 [01:00<06:53,  1.29s/it]
Loading 0:  56%|█████▋    | 408/723 [01:00<04:15,  1.23it/s]
Loading 0:  57%|█████▋    | 412/723 [01:00<02:59,  1.73it/s]
Loading 0:  58%|█████▊    | 420/723 [01:00<01:38,  3.06it/s]
Loading 0:  59%|█████▊    | 423/723 [01:00<01:22,  3.63it/s]
Loading 0:  59%|█████▉    | 427/723 [01:00<01:02,  4.77it/s]
Loading 0:  60%|█████▉    | 432/723 [01:01<00:43,  6.76it/s]
Loading 0:  60%|██████    | 436/723 [01:01<00:33,  8.54it/s]
Loading 0:  61%|██████    | 441/723 [01:01<00:24, 11.59it/s]
Loading 0:  62%|██████▏   | 446/723 [01:01<00:19, 13.86it/s]
Loading 0:  62%|██████▏   | 450/723 [01:01<00:18, 14.92it/s]
Loading 0:  63%|██████▎   | 454/723 [01:01<00:15, 16.85it/s]
Loading 0:  63%|██████▎   | 459/723 [01:02<00:12, 21.02it/s]
Loading 0:  64%|██████▍   | 463/723 [01:02<00:11, 22.48it/s]
Loading 0:  65%|██████▍   | 468/723 [01:02<00:09, 26.65it/s]
Loading 0:  65%|██████▌   | 472/723 [01:02<00:12, 20.44it/s]
Loading 0:  66%|██████▌   | 477/723 [01:02<00:09, 24.65it/s]
Loading 0:  67%|██████▋   | 481/723 [01:02<00:09, 25.57it/s]
Loading 0:  67%|██████▋   | 486/723 [01:02<00:08, 29.43it/s]
Loading 0:  68%|██████▊   | 490/723 [01:03<00:08, 28.76it/s]
Loading 0:  68%|██████▊   | 494/723 [01:03<00:09, 25.06it/s]
Loading 0:  69%|██████▉   | 498/723 [01:03<00:08, 25.99it/s]
Loading 0:  69%|██████▉   | 501/723 [01:03<00:09, 24.58it/s]
Loading 0:  70%|███████   | 507/723 [01:03<00:06, 31.13it/s]
Loading 0:  71%|███████   | 511/723 [01:03<00:07, 30.02it/s]
Loading 0:  71%|███████   | 515/723 [01:03<00:06, 31.67it/s]
Loading 0:  72%|███████▏  | 520/723 [01:04<00:07, 28.27it/s]
Loading 0:  72%|███████▏  | 524/723 [01:04<00:07, 28.15it/s]
Loading 0:  73%|███████▎  | 527/723 [01:04<00:08, 23.07it/s]
Loading 0:  74%|███████▍  | 534/723 [01:04<00:06, 31.20it/s]
Loading 0:  74%|███████▍  | 538/723 [01:19<02:59,  1.03it/s]
Loading 0:  76%|███████▌  | 546/723 [01:19<01:41,  1.75it/s]
Loading 0:  76%|███████▌  | 550/723 [01:19<01:17,  2.22it/s]
Loading 0:  76%|███████▋  | 553/723 [01:19<01:02,  2.71it/s]
Loading 0:  77%|███████▋  | 557/723 [01:19<00:45,  3.65it/s]
Loading 0:  78%|███████▊  | 562/723 [01:20<00:31,  5.14it/s]
Loading 0:  78%|███████▊  | 566/723 [01:20<00:23,  6.76it/s]
Loading 0:  79%|███████▉  | 572/723 [01:20<00:16,  9.29it/s]
Loading 0:  80%|███████▉  | 576/723 [01:20<00:13, 10.68it/s]
Loading 0:  80%|████████  | 580/723 [01:20<00:11, 12.67it/s]
Loading 0:  81%|████████  | 585/723 [01:20<00:08, 16.47it/s]
Loading 0:  81%|████████▏ | 589/723 [01:21<00:07, 18.66it/s]
Loading 0:  82%|████████▏ | 594/723 [01:21<00:05, 22.87it/s]
Loading 0:  83%|████████▎ | 598/723 [01:21<00:06, 18.78it/s]
Loading 0:  83%|████████▎ | 603/723 [01:21<00:05, 23.01it/s]
Loading 0:  84%|████████▍ | 607/723 [01:21<00:04, 24.16it/s]
Loading 0:  85%|████████▍ | 611/723 [01:21<00:04, 27.13it/s]
Loading 0:  85%|████████▌ | 615/723 [01:21<00:04, 26.45it/s]
Loading 0:  86%|████████▌ | 620/723 [01:22<00:04, 25.16it/s]
Loading 0:  86%|████████▋ | 624/723 [01:22<00:03, 26.02it/s]
Loading 0:  87%|████████▋ | 627/723 [01:22<00:03, 24.61it/s]
Loading 0:  88%|████████▊ | 633/723 [01:22<00:02, 31.31it/s]
Loading 0:  88%|████████▊ | 637/723 [01:22<00:02, 29.11it/s]
Loading 0:  89%|████████▊ | 641/723 [01:22<00:02, 30.87it/s]
Loading 0:  89%|████████▉ | 646/723 [01:23<00:02, 27.75it/s]
Loading 0:  90%|████████▉ | 650/723 [01:23<00:02, 27.89it/s]
Loading 0:  90%|█████████ | 653/723 [01:23<00:03, 23.02it/s]
Loading 0:  91%|█████████▏| 660/723 [01:23<00:02, 31.36it/s]
Loading 0:  92%|█████████▏| 664/723 [01:23<00:01, 30.12it/s]
Loading 0:  93%|█████████▎| 672/723 [01:23<00:01, 30.53it/s]
Loading 0:  93%|█████████▎| 676/723 [01:38<00:41,  1.13it/s]
Loading 0:  94%|█████████▍| 679/723 [01:38<00:31,  1.39it/s]
Loading 0:  95%|█████████▍| 684/723 [01:38<00:19,  2.02it/s]
Loading 0:  95%|█████████▌| 688/723 [01:39<00:12,  2.70it/s]
Loading 0:  96%|█████████▌| 693/723 [01:39<00:07,  3.88it/s]
Loading 0:  97%|█████████▋| 698/723 [01:39<00:04,  5.26it/s]
Loading 0:  97%|█████████▋| 702/723 [01:39<00:03,  6.50it/s]
Loading 0:  98%|█████████▊| 706/723 [01:39<00:02,  8.17it/s]
Loading 0:  98%|█████████▊| 711/723 [01:39<00:01, 11.14it/s]
Loading 0:  99%|█████████▉| 715/723 [01:40<00:00, 13.34it/s]
Loading 0: 100%|█████████▉| 720/723 [01:40<00:00, 17.21it/s]
Loading 0: 100%|█████████▉| 722/723 [01:50<00:00, 17.21it/s]
Loading 0: 100%|██████████| 723/723 [01:50<00:00,  1.22it/s]
                                                            
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-v25-mkmlizer: quantized model in 127.443s
undi95-meta-llama-3-70b-6209-v25-mkmlizer: Processed model Undi95/Meta-Llama-3-70B-Instruct-hf in 406.611s
undi95-meta-llama-3-70b-6209-v25-mkmlizer: creating bucket guanaco-mkml-models
undi95-meta-llama-3-70b-6209-v25-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
undi95-meta-llama-3-70b-6209-v25-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v25
undi95-meta-llama-3-70b-6209-v25-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v25/config.json
undi95-meta-llama-3-70b-6209-v25-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v25/tokenizer_config.json
undi95-meta-llama-3-70b-6209-v25-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v25/special_tokens_map.json
undi95-meta-llama-3-70b-6209-v25-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v25/tokenizer.json
undi95-meta-llama-3-70b-6209-v25-mkmlizer: cp /dev/shm/model_cache/flywheel_model.5.safetensors s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v25/flywheel_model.5.safetensors
undi95-meta-llama-3-70b-6209-v25-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v25/flywheel_model.1.safetensors
undi95-meta-llama-3-70b-6209-v25-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v25/flywheel_model.0.safetensors
undi95-meta-llama-3-70b-6209-v25-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v25/flywheel_model.2.safetensors
undi95-meta-llama-3-70b-6209-v25-mkmlizer: cp /dev/shm/model_cache/flywheel_model.4.safetensors s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v25/flywheel_model.4.safetensors
undi95-meta-llama-3-70b-6209-v25-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v25/flywheel_model.3.safetensors
undi95-meta-llama-3-70b-6209-v25-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
undi95-meta-llama-3-70b-6209-v25-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:950: 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-v25-mkmlizer:   warnings.warn(
undi95-meta-llama-3-70b-6209-v25-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:778: 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-v25-mkmlizer:   warnings.warn(
undi95-meta-llama-3-70b-6209-v25-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:469: 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-v25-mkmlizer:   warnings.warn(
undi95-meta-llama-3-70b-6209-v25-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:05<00:05,  5.42s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  3.86s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  4.10s/it]
undi95-meta-llama-3-70b-6209-v25-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  2.30it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.81it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.47it/s]
undi95-meta-llama-3-70b-6209-v25-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
undi95-meta-llama-3-70b-6209-v25-mkmlizer: Saving duration: 1.327s
undi95-meta-llama-3-70b-6209-v25-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.201s
undi95-meta-llama-3-70b-6209-v25-mkmlizer: creating bucket guanaco-reward-models
undi95-meta-llama-3-70b-6209-v25-mkmlizer: Bucket 's3://guanaco-reward-models/' created
undi95-meta-llama-3-70b-6209-v25-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/undi95-meta-llama-3-70b-6209-v25_reward
undi95-meta-llama-3-70b-6209-v25-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/undi95-meta-llama-3-70b-6209-v25_reward/config.json
undi95-meta-llama-3-70b-6209-v25-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/undi95-meta-llama-3-70b-6209-v25_reward/tokenizer_config.json
undi95-meta-llama-3-70b-6209-v25-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/undi95-meta-llama-3-70b-6209-v25_reward/special_tokens_map.json
undi95-meta-llama-3-70b-6209-v25-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/undi95-meta-llama-3-70b-6209-v25_reward/reward.tensors
Job undi95-meta-llama-3-70b-6209-v25-mkmlizer completed after 479.08s with status: succeeded
Stopping job with name undi95-meta-llama-3-70b-6209-v25-mkmlizer
Pipeline stage MKMLizer completed in 480.97s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.14s
Running pipeline stage ISVCDeployer
Creating inference service undi95-meta-llama-3-70b-6209-v25
Waiting for inference service undi95-meta-llama-3-70b-6209-v25 to be ready
Inference service undi95-meta-llama-3-70b-6209-v25 ready after 90.68006372451782s
Pipeline stage ISVCDeployer completed in 92.43s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.92356276512146s
Received healthy response to inference request in 4.0825583934783936s
Received healthy response to inference request in 4.02097225189209s
Received healthy response to inference request in 3.156216621398926s
Received healthy response to inference request in 3.523151159286499s
5 requests
0 failed requests
5th percentile: 3.2296035289764404
10th percentile: 3.302990436553955
20th percentile: 3.4497642517089844
30th percentile: 3.622715377807617
40th percentile: 3.8218438148498537
50th percentile: 4.02097225189209
60th percentile: 4.045606708526611
70th percentile: 4.070241165161133
80th percentile: 4.250759267807007
90th percentile: 4.587161016464234
95th percentile: 4.755361890792846
99th percentile: 4.889922590255737
mean time: 3.941292238235474
Pipeline stage StressChecker completed in 20.63s
undi95-meta-llama-3-70b_6209_v25 status is now deployed due to DeploymentManager action
undi95-meta-llama-3-70b_6209_v25 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of undi95-meta-llama-3-70b_6209_v25
Running pipeline stage ISVCDeleter
Checking if service undi95-meta-llama-3-70b-6209-v25 is running
Tearing down inference service undi95-meta-llama-3-70b-6209-v25
Service undi95-meta-llama-3-70b-6209-v25 has been torndown
Pipeline stage ISVCDeleter completed in 5.18s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key undi95-meta-llama-3-70b-6209-v25/config.json from bucket guanaco-mkml-models
Deleting key undi95-meta-llama-3-70b-6209-v25/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key undi95-meta-llama-3-70b-6209-v25/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key undi95-meta-llama-3-70b-6209-v25/flywheel_model.2.safetensors from bucket guanaco-mkml-models
Deleting key undi95-meta-llama-3-70b-6209-v25/flywheel_model.3.safetensors from bucket guanaco-mkml-models
Deleting key undi95-meta-llama-3-70b-6209-v25/flywheel_model.4.safetensors from bucket guanaco-mkml-models
Deleting key undi95-meta-llama-3-70b-6209-v25/flywheel_model.5.safetensors from bucket guanaco-mkml-models
Deleting key undi95-meta-llama-3-70b-6209-v25/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key undi95-meta-llama-3-70b-6209-v25/tokenizer.json from bucket guanaco-mkml-models
Deleting key undi95-meta-llama-3-70b-6209-v25/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key undi95-meta-llama-3-70b-6209-v25_reward/config.json from bucket guanaco-reward-models
Deleting key undi95-meta-llama-3-70b-6209-v25_reward/merges.txt from bucket guanaco-reward-models
Deleting key undi95-meta-llama-3-70b-6209-v25_reward/reward.tensors from bucket guanaco-reward-models
Deleting key undi95-meta-llama-3-70b-6209-v25_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key undi95-meta-llama-3-70b-6209-v25_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key undi95-meta-llama-3-70b-6209-v25_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key undi95-meta-llama-3-70b-6209-v25_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 13.66s
undi95-meta-llama-3-70b_6209_v25 status is now torndown due to DeploymentManager action