submission_id: chaiml-phase2-winner-13b2_v232
developer_uid: robert_irvine
status: torndown
model_repo: ChaiML/phase2_winner_13b2
reward_repo: rirv938/gpt2_ties_merge_preference_plus_classic_e2_density_99
generation_params: {'temperature': 1.0733671330918084, 'top_p': 0.6971846333941389, 'min_p': 0.0, 'top_k': 50, 'presence_penalty': 0.0, 'frequency_penalty': 0.312882778758545, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 8, '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: {'memory_template': 'Memory: {memory}\n', 'prompt_template': '{prompt}\n', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', 'truncate_by_message': False}
timestamp: 2024-02-16T00:33:35+00:00
model_name: chaiml-phase2-winner-13b2_v232
model_eval_status: success
model_group: ChaiML/phase2_winner_13b
num_battles: 123129
num_wins: 59376
celo_rating: 1143.68
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: None
model_num_parameters: 13015864320.0
best_of: 8
max_input_tokens: 512
max_output_tokens: 64
display_name: chaiml-phase2-winner-13b2_v232
ineligible_reason: propriety_total_count < 800
language_model: ChaiML/phase2_winner_13b2
model_size: 13B
reward_model: rirv938/gpt2_ties_merge_preference_plus_classic_e2_density_99
us_pacific_date: 2024-02-15
win_ratio: 0.4822259581414614
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-phase2-winner-13b2-v232-mkmlizer
Waiting for job on chaiml-phase2-winner-13b2-v232-mkmlizer to finish
Stopping job with name chaiml-phase2-winner-13b2-v232-mkmlizer
%s, retrying in %s seconds...
Starting job with name chaiml-phase2-winner-13b2-v232-mkmlizer
Waiting for job on chaiml-phase2-winner-13b2-v232-mkmlizer to finish
Stopping job with name chaiml-phase2-winner-13b2-v232-mkmlizer
%s, retrying in %s seconds...
Starting job with name chaiml-phase2-winner-13b2-v232-mkmlizer
Waiting for job on chaiml-phase2-winner-13b2-v232-mkmlizer to finish
chaiml-phase2-winner-13b2-v232-mkmlizer: 
pytorch_model-00001-of-00003.bin:   0%|          | 0.00/9.95G [00:00<?, ?B/s]
pytorch_model-00001-of-00003.bin:   0%|          | 10.5M/9.95G [00:00<05:43, 28.9MB/s]
pytorch_model-00001-of-00003.bin:   0%|          | 21.0M/9.95G [00:00<04:41, 35.2MB/s]
pytorch_model-00001-of-00003.bin:   0%|          | 31.5M/9.95G [00:00<04:03, 40.7MB/s]
pytorch_model-00001-of-00003.bin:   1%|          | 83.9M/9.95G [00:00<01:17, 128MB/s] 
pytorch_model-00001-of-00003.bin:   1%|          | 105M/9.95G [00:01<01:09, 141MB/s] 
pytorch_model-00001-of-00003.bin:   2%|▏         | 210M/9.95G [00:01<00:29, 332MB/s]
pytorch_model-00001-of-00003.bin:   3%|▎         | 273M/9.95G [00:01<00:26, 365MB/s]
pytorch_model-00001-of-00003.bin:   3%|▎         | 325M/9.95G [00:01<00:24, 392MB/s]
pytorch_model-00001-of-00003.bin:   4%|▍         | 398M/9.95G [00:01<00:20, 466MB/s]
pytorch_model-00001-of-00003.bin:   5%|▌         | 503M/9.95G [00:01<00:16, 576MB/s]
pytorch_model-00001-of-00003.bin:   6%|▌         | 608M/9.95G [00:01<00:13, 686MB/s]
pytorch_model-00001-of-00003.bin:   7%|▋         | 682M/9.95G [00:01<00:13, 687MB/s]
pytorch_model-00001-of-00003.bin:   8%|▊         | 755M/9.95G [00:02<00:14, 630MB/s]
pytorch_model-00001-of-00003.bin:   8%|▊         | 828M/9.95G [00:02<00:17, 534MB/s]
pytorch_model-00001-of-00003.bin:   9%|▉         | 891M/9.95G [00:02<00:20, 449MB/s]
pytorch_model-00001-of-00003.bin:  10%|▉         | 954M/9.95G [00:02<00:18, 485MB/s]
pytorch_model-00001-of-00003.bin:  10%|█         | 1.03G/9.95G [00:02<00:16, 534MB/s]
pytorch_model-00001-of-00003.bin:  11%|█         | 1.09G/9.95G [00:02<00:16, 538MB/s]
pytorch_model-00001-of-00003.bin:  12%|█▏        | 1.17G/9.95G [00:02<00:15, 571MB/s]
pytorch_model-00001-of-00003.bin:  13%|█▎        | 1.26G/9.95G [00:03<00:14, 608MB/s]
pytorch_model-00001-of-00003.bin:  13%|█▎        | 1.34G/9.95G [00:03<00:12, 664MB/s]
pytorch_model-00001-of-00003.bin:  14%|█▍        | 1.42G/9.95G [00:03<00:14, 593MB/s]
pytorch_model-00001-of-00003.bin:  16%|█▌        | 1.56G/9.95G [00:03<00:10, 810MB/s]
pytorch_model-00001-of-00003.bin:  17%|█▋        | 1.66G/9.95G [00:03<00:13, 621MB/s]
pytorch_model-00001-of-00003.bin:  18%|█▊        | 1.77G/9.95G [00:03<00:11, 697MB/s]
pytorch_model-00001-of-00003.bin:  19%|█▊        | 1.86G/9.95G [00:03<00:11, 715MB/s]
pytorch_model-00001-of-00003.bin:  19%|█▉        | 1.94G/9.95G [00:03<00:10, 737MB/s]
pytorch_model-00001-of-00003.bin:  20%|██        | 2.02G/9.95G [00:04<00:12, 657MB/s]
pytorch_model-00001-of-00003.bin:  22%|██▏       | 2.15G/9.95G [00:04<00:09, 782MB/s]
pytorch_model-00001-of-00003.bin:  23%|██▎       | 2.26G/9.95G [00:04<00:08, 868MB/s]
pytorch_model-00001-of-00003.bin:  24%|██▎       | 2.36G/9.95G [00:04<00:12, 619MB/s]
pytorch_model-00001-of-00003.bin:  25%|██▍       | 2.44G/9.95G [00:04<00:13, 538MB/s]
pytorch_model-00001-of-00003.bin:  25%|██▌       | 2.53G/9.95G [00:04<00:12, 590MB/s]
pytorch_model-00001-of-00003.bin:  26%|██▋       | 2.63G/9.95G [00:05<00:11, 661MB/s]
pytorch_model-00001-of-00003.bin:  28%|██▊       | 2.78G/9.95G [00:05<00:08, 826MB/s]
pytorch_model-00001-of-00003.bin:  29%|██▉       | 2.89G/9.95G [00:05<00:08, 869MB/s]
pytorch_model-00001-of-00003.bin:  30%|███       | 3.03G/9.95G [00:05<00:07, 975MB/s]
pytorch_model-00001-of-00003.bin:  32%|███▏      | 3.20G/9.95G [00:05<00:05, 1.14GB/s]
pytorch_model-00001-of-00003.bin:  33%|███▎      | 3.32G/9.95G [00:05<00:08, 820MB/s] 
pytorch_model-00001-of-00003.bin:  34%|███▍      | 3.43G/9.95G [00:05<00:08, 740MB/s]
pytorch_model-00001-of-00003.bin:  35%|███▌      | 3.52G/9.95G [00:06<00:09, 690MB/s]
pytorch_model-00001-of-00003.bin:  36%|███▋      | 3.62G/9.95G [00:06<00:08, 725MB/s]
pytorch_model-00001-of-00003.bin:  37%|███▋      | 3.70G/9.95G [00:06<00:08, 749MB/s]
pytorch_model-00001-of-00003.bin:  38%|███▊      | 3.80G/9.95G [00:06<00:08, 768MB/s]
pytorch_model-00001-of-00003.bin:  39%|███▉      | 3.91G/9.95G [00:06<00:07, 852MB/s]
pytorch_model-00001-of-00003.bin:  40%|████      | 4.01G/9.95G [00:06<00:07, 808MB/s]
pytorch_model-00001-of-00003.bin:  41%|████      | 4.10G/9.95G [00:06<00:07, 739MB/s]
pytorch_model-00001-of-00003.bin:  42%|████▏     | 4.18G/9.95G [00:06<00:09, 614MB/s]
pytorch_model-00001-of-00003.bin:  43%|████▎     | 4.26G/9.95G [00:07<00:09, 597MB/s]
pytorch_model-00001-of-00003.bin:  44%|████▍     | 4.40G/9.95G [00:07<00:07, 788MB/s]
pytorch_model-00001-of-00003.bin:  46%|████▌     | 4.54G/9.95G [00:07<00:05, 914MB/s]
pytorch_model-00001-of-00003.bin:  47%|████▋     | 4.68G/9.95G [00:07<00:05, 1.02GB/s]
pytorch_model-00001-of-00003.bin:  49%|████▊     | 4.83G/9.95G [00:07<00:04, 1.16GB/s]
pytorch_model-00001-of-00003.bin:  50%|████▉     | 4.96G/9.95G [00:07<00:06, 801MB/s] 
pytorch_model-00001-of-00003.bin:  51%|█████     | 5.06G/9.95G [00:08<00:07, 672MB/s]
pytorch_model-00001-of-00003.bin:  52%|█████▏    | 5.17G/9.95G [00:08<00:06, 732MB/s]
pytorch_model-00001-of-00003.bin:  53%|█████▎    | 5.28G/9.95G [00:08<00:05, 803MB/s]
pytorch_model-00001-of-00003.bin:  54%|█████▍    | 5.38G/9.95G [00:08<00:06, 745MB/s]
pytorch_model-00001-of-00003.bin:  55%|█████▍    | 5.46G/9.95G [00:08<00:06, 670MB/s]
pytorch_model-00001-of-00003.bin:  56%|█████▌    | 5.55G/9.95G [00:08<00:06, 694MB/s]
pytorch_model-00001-of-00003.bin:  57%|█████▋    | 5.67G/9.95G [00:08<00:05, 818MB/s]
pytorch_model-00001-of-00003.bin:  58%|█████▊    | 5.77G/9.95G [00:09<00:06, 663MB/s]
pytorch_model-00001-of-00003.bin:  59%|█████▉    | 5.85G/9.95G [00:09<00:05, 694MB/s]
pytorch_model-00001-of-00003.bin:  60%|█████▉    | 5.93G/9.95G [00:09<00:05, 719MB/s]
pytorch_model-00001-of-00003.bin:  60%|██████    | 6.02G/9.95G [00:09<00:05, 709MB/s]
pytorch_model-00001-of-00003.bin:  61%|██████▏   | 6.10G/9.95G [00:09<00:05, 734MB/s]
pytorch_model-00001-of-00003.bin:  62%|██████▏   | 6.19G/9.95G [00:09<00:05, 715MB/s]
pytorch_model-00001-of-00003.bin:  63%|██████▎   | 6.27G/9.95G [00:09<00:06, 605MB/s]
pytorch_model-00001-of-00003.bin:  64%|██████▍   | 6.34G/9.95G [00:09<00:05, 623MB/s]
pytorch_model-00001-of-00003.bin:  65%|██████▌   | 6.47G/9.95G [00:09<00:04, 744MB/s]
pytorch_model-00001-of-00003.bin:  66%|██████▌   | 6.55G/9.95G [00:10<00:04, 715MB/s]
pytorch_model-00001-of-00003.bin:  68%|██████▊   | 6.72G/9.95G [00:10<00:03, 951MB/s]
pytorch_model-00001-of-00003.bin:  69%|██████▉   | 6.85G/9.95G [00:10<00:03, 1.03GB/s]
pytorch_model-00001-of-00003.bin:  70%|███████   | 6.99G/9.95G [00:10<00:02, 1.14GB/s]
pytorch_model-00001-of-00003.bin:  72%|███████▏  | 7.12G/9.95G [00:10<00:02, 1.11GB/s]
pytorch_model-00001-of-00003.bin:  73%|███████▎  | 7.27G/9.95G [00:10<00:02, 1.18GB/s]
pytorch_model-00001-of-00003.bin:  75%|███████▍  | 7.42G/9.95G [00:10<00:02, 1.25GB/s]
pytorch_model-00001-of-00003.bin:  77%|███████▋  | 7.61G/9.95G [00:10<00:01, 1.42GB/s]
pytorch_model-00001-of-00003.bin:  78%|███████▊  | 7.76G/9.95G [00:10<00:01, 1.36GB/s]
pytorch_model-00001-of-00003.bin:  81%|████████  | 8.01G/9.95G [00:11<00:01, 1.63GB/s]
pytorch_model-00001-of-00003.bin:  82%|████████▏ | 8.20G/9.95G [00:11<00:01, 1.68GB/s]
pytorch_model-00001-of-00003.bin:  85%|████████▍ | 8.42G/9.95G [00:11<00:00, 1.80GB/s]
pytorch_model-00001-of-00003.bin:  87%|████████▋ | 8.68G/9.95G [00:11<00:00, 2.01GB/s]
pytorch_model-00001-of-00003.bin:  89%|████████▉ | 8.89G/9.95G [00:11<00:00, 1.82GB/s]
pytorch_model-00001-of-00003.bin:  91%|█████████▏| 9.08G/9.95G [00:11<00:00, 1.58GB/s]
pytorch_model-00001-of-00003.bin:  93%|█████████▎| 9.25G/9.95G [00:11<00:00, 1.48GB/s]
pytorch_model-00001-of-00003.bin:  96%|█████████▌| 9.53G/9.95G [00:11<00:00, 1.81GB/s]
pytorch_model-00001-of-00003.bin:  99%|█████████▉| 9.90G/9.95G [00:12<00:00, 2.19GB/s]
pytorch_model-00001-of-00003.bin: 100%|█████████▉| 9.95G/9.95G [00:12<00:00, 804MB/s] 
chaiml-phase2-winner-13b2-v232-mkmlizer: 
pytorch_model-00002-of-00003.bin:   0%|          | 0.00/9.90G [00:00<?, ?B/s]
pytorch_model-00002-of-00003.bin:   0%|          | 10.5M/9.90G [00:00<05:59, 27.5MB/s]
pytorch_model-00002-of-00003.bin:   0%|          | 21.0M/9.90G [00:00<04:59, 33.0MB/s]
pytorch_model-00002-of-00003.bin:   1%|          | 73.4M/9.90G [00:00<01:13, 134MB/s] 
pytorch_model-00002-of-00003.bin:   1%|          | 105M/9.90G [00:01<01:50, 88.8MB/s]
pytorch_model-00002-of-00003.bin:   3%|▎         | 304M/9.90G [00:01<00:26, 358MB/s] 
pytorch_model-00002-of-00003.bin:  11%|█         | 1.11G/9.90G [00:01<00:05, 1.65GB/s]
pytorch_model-00002-of-00003.bin:  15%|█▍        | 1.45G/9.90G [00:02<00:08, 1.05GB/s]
pytorch_model-00002-of-00003.bin:  17%|█▋        | 1.69G/9.90G [00:02<00:08, 1.02GB/s]
pytorch_model-00002-of-00003.bin:  19%|█▉        | 1.93G/9.90G [00:02<00:06, 1.21GB/s]
pytorch_model-00002-of-00003.bin:  22%|██▏       | 2.22G/9.90G [00:02<00:05, 1.48GB/s]
pytorch_model-00002-of-00003.bin:  25%|██▌       | 2.50G/9.90G [00:02<00:04, 1.67GB/s]
pytorch_model-00002-of-00003.bin:  28%|██▊       | 2.74G/9.90G [00:02<00:03, 1.82GB/s]
pytorch_model-00002-of-00003.bin:  30%|███       | 3.02G/9.90G [00:02<00:03, 2.04GB/s]
pytorch_model-00002-of-00003.bin:  33%|███▎      | 3.27G/9.90G [00:03<00:03, 1.77GB/s]
pytorch_model-00002-of-00003.bin:  35%|███▌      | 3.49G/9.90G [00:03<00:03, 1.63GB/s]
pytorch_model-00002-of-00003.bin:  37%|███▋      | 3.69G/9.90G [00:03<00:03, 1.60GB/s]
pytorch_model-00002-of-00003.bin:  39%|███▉      | 3.87G/9.90G [00:03<00:04, 1.45GB/s]
pytorch_model-00002-of-00003.bin:  41%|████      | 4.04G/9.90G [00:03<00:04, 1.31GB/s]
pytorch_model-00002-of-00003.bin:  43%|████▎     | 4.27G/9.90G [00:03<00:03, 1.52GB/s]
pytorch_model-00002-of-00003.bin:  47%|████▋     | 4.63G/9.90G [00:03<00:02, 2.01GB/s]
pytorch_model-00002-of-00003.bin:  50%|████▉     | 4.92G/9.90G [00:03<00:02, 2.21GB/s]
pytorch_model-00002-of-00003.bin:  52%|█████▏    | 5.16G/9.90G [00:04<00:02, 2.09GB/s]
pytorch_model-00002-of-00003.bin:  54%|█████▍    | 5.39G/9.90G [00:04<00:03, 1.44GB/s]
pytorch_model-00002-of-00003.bin:  56%|█████▋    | 5.58G/9.90G [00:04<00:02, 1.45GB/s]
pytorch_model-00002-of-00003.bin:  59%|█████▉    | 5.82G/9.90G [00:04<00:02, 1.65GB/s]
pytorch_model-00002-of-00003.bin:  61%|██████    | 6.02G/9.90G [00:04<00:02, 1.71GB/s]
pytorch_model-00002-of-00003.bin:  63%|██████▎   | 6.22G/9.90G [00:04<00:02, 1.67GB/s]
pytorch_model-00002-of-00003.bin:  65%|██████▍   | 6.41G/9.90G [00:04<00:02, 1.60GB/s]
pytorch_model-00002-of-00003.bin:  66%|██████▋   | 6.59G/9.90G [00:05<00:02, 1.57GB/s]
pytorch_model-00002-of-00003.bin:  68%|██████▊   | 6.76G/9.90G [00:05<00:01, 1.61GB/s]
pytorch_model-00002-of-00003.bin:  71%|███████   | 6.99G/9.90G [00:05<00:01, 1.72GB/s]
pytorch_model-00002-of-00003.bin:  72%|███████▏  | 7.17G/9.90G [00:05<00:01, 1.50GB/s]
pytorch_model-00002-of-00003.bin:  74%|███████▍  | 7.34G/9.90G [00:05<00:01, 1.50GB/s]
pytorch_model-00002-of-00003.bin:  76%|███████▋  | 7.57G/9.90G [00:05<00:01, 1.70GB/s]
pytorch_model-00002-of-00003.bin:  78%|███████▊  | 7.75G/9.90G [00:05<00:01, 1.68GB/s]
pytorch_model-00002-of-00003.bin:  80%|████████  | 7.93G/9.90G [00:05<00:01, 1.52GB/s]
pytorch_model-00002-of-00003.bin:  82%|████████▏ | 8.10G/9.90G [00:06<00:01, 1.43GB/s]
pytorch_model-00002-of-00003.bin:  83%|████████▎ | 8.25G/9.90G [00:06<00:01, 1.46GB/s]
pytorch_model-00002-of-00003.bin:  85%|████████▍ | 8.41G/9.90G [00:06<00:01, 1.45GB/s]
pytorch_model-00002-of-00003.bin:  87%|████████▋ | 8.66G/9.90G [00:06<00:00, 1.72GB/s]
pytorch_model-00002-of-00003.bin:  89%|████████▉ | 8.84G/9.90G [00:06<00:00, 1.51GB/s]
pytorch_model-00002-of-00003.bin:  91%|█████████ | 9.01G/9.90G [00:06<00:00, 1.48GB/s]
pytorch_model-00002-of-00003.bin:  93%|█████████▎| 9.17G/9.90G [00:06<00:00, 1.35GB/s]
pytorch_model-00002-of-00003.bin:  95%|█████████▍| 9.38G/9.90G [00:06<00:00, 1.51GB/s]
pytorch_model-00002-of-00003.bin:  99%|█████████▉| 9.79G/9.90G [00:06<00:00, 2.15GB/s]
pytorch_model-00002-of-00003.bin: 100%|█████████▉| 9.90G/9.90G [00:07<00:00, 1.29GB/s]
chaiml-phase2-winner-13b2-v232-mkmlizer: 
pytorch_model-00003-of-00003.bin:   0%|          | 0.00/6.18G [00:00<?, ?B/s]
pytorch_model-00003-of-00003.bin:   0%|          | 10.5M/6.18G [00:00<03:29, 29.5MB/s]
pytorch_model-00003-of-00003.bin:   0%|          | 21.0M/6.18G [00:00<02:29, 41.1MB/s]
pytorch_model-00003-of-00003.bin:   2%|▏         | 105M/6.18G [00:00<00:25, 236MB/s]  
pytorch_model-00003-of-00003.bin:   5%|▍         | 283M/6.18G [00:00<00:09, 625MB/s]
pytorch_model-00003-of-00003.bin:   7%|▋         | 451M/6.18G [00:00<00:06, 892MB/s]
pytorch_model-00003-of-00003.bin:  11%|█         | 661M/6.18G [00:00<00:04, 1.20GB/s]
pytorch_model-00003-of-00003.bin:  14%|█▍        | 870M/6.18G [00:01<00:03, 1.42GB/s]
pytorch_model-00003-of-00003.bin:  17%|█▋        | 1.07G/6.18G [00:01<00:03, 1.57GB/s]
pytorch_model-00003-of-00003.bin:  20%|██        | 1.25G/6.18G [00:01<00:03, 1.51GB/s]
pytorch_model-00003-of-00003.bin:  23%|██▎       | 1.42G/6.18G [00:01<00:03, 1.51GB/s]
pytorch_model-00003-of-00003.bin:  26%|██▌       | 1.58G/6.18G [00:01<00:03, 1.46GB/s]
pytorch_model-00003-of-00003.bin:  28%|██▊       | 1.75G/6.18G [00:01<00:02, 1.51GB/s]
pytorch_model-00003-of-00003.bin:  32%|███▏      | 1.95G/6.18G [00:01<00:02, 1.64GB/s]
pytorch_model-00003-of-00003.bin:  37%|███▋      | 2.28G/6.18G [00:01<00:01, 2.07GB/s]
pytorch_model-00003-of-00003.bin:  41%|████▏     | 2.56G/6.18G [00:01<00:01, 2.28GB/s]
pytorch_model-00003-of-00003.bin:  45%|████▌     | 2.81G/6.18G [00:02<00:01, 2.34GB/s]
pytorch_model-00003-of-00003.bin:  49%|████▉     | 3.05G/6.18G [00:02<00:01, 1.84GB/s]
pytorch_model-00003-of-00003.bin:  53%|█████▎    | 3.26G/6.18G [00:02<00:01, 1.62GB/s]
pytorch_model-00003-of-00003.bin:  57%|█████▋    | 3.49G/6.18G [00:02<00:01, 1.72GB/s]
pytorch_model-00003-of-00003.bin:  60%|██████    | 3.71G/6.18G [00:02<00:01, 1.82GB/s]
pytorch_model-00003-of-00003.bin:  64%|██████▍   | 3.94G/6.18G [00:02<00:01, 1.89GB/s]
pytorch_model-00003-of-00003.bin:  67%|██████▋   | 4.14G/6.18G [00:02<00:01, 1.72GB/s]
pytorch_model-00003-of-00003.bin:  70%|███████   | 4.33G/6.18G [00:02<00:01, 1.71GB/s]
pytorch_model-00003-of-00003.bin:  73%|███████▎  | 4.51G/6.18G [00:03<00:01, 1.62GB/s]
pytorch_model-00003-of-00003.bin:  76%|███████▋  | 4.72G/6.18G [00:03<00:00, 1.74GB/s]
pytorch_model-00003-of-00003.bin:  79%|███████▉  | 4.91G/6.18G [00:03<00:00, 1.73GB/s]
pytorch_model-00003-of-00003.bin:  82%|████████▏ | 5.09G/6.18G [00:03<00:00, 1.67GB/s]
pytorch_model-00003-of-00003.bin:  86%|████████▌ | 5.30G/6.18G [00:03<00:00, 1.76GB/s]
pytorch_model-00003-of-00003.bin:  89%|████████▉ | 5.48G/6.18G [00:03<00:00, 1.44GB/s]
pytorch_model-00003-of-00003.bin:  92%|█████████▏| 5.67G/6.18G [00:03<00:00, 1.51GB/s]
pytorch_model-00003-of-00003.bin:  97%|█████████▋| 6.00G/6.18G [00:03<00:00, 1.98GB/s]
pytorch_model-00003-of-00003.bin: 100%|█████████▉| 6.18G/6.18G [00:04<00:00, 1.53GB/s]
chaiml-phase2-winner-13b2-v232-mkmlizer: 
pytorch_model.bin.index.json:   0%|          | 0.00/33.4k [00:00<?, ?B/s]
pytorch_model.bin.index.json: 100%|██████████| 33.4k/33.4k [00:00<00:00, 12.1MB/s]
chaiml-phase2-winner-13b2-v232-mkmlizer: 
special_tokens_map.json:   0%|          | 0.00/414 [00:00<?, ?B/s]
special_tokens_map.json: 100%|██████████| 414/414 [00:00<00:00, 4.45MB/s]
chaiml-phase2-winner-13b2-v232-mkmlizer: 
tokenizer.json:   0%|          | 0.00/1.84M [00:00<?, ?B/s]
tokenizer.json: 100%|██████████| 1.84M/1.84M [00:00<00:00, 19.1MB/s]
chaiml-phase2-winner-13b2-v232-mkmlizer: 
tokenizer.model:   0%|          | 0.00/500k [00:00<?, ?B/s]
tokenizer.model: 100%|██████████| 500k/500k [00:00<00:00, 5.56MB/s]
chaiml-phase2-winner-13b2-v232-mkmlizer: 
tokenizer_config.json:   0%|          | 0.00/725 [00:00<?, ?B/s]
tokenizer_config.json: 100%|██████████| 725/725 [00:00<00:00, 3.76MB/s]
chaiml-phase2-winner-13b2-v232-mkmlizer: Downloaded to shared memory in 26.825s
chaiml-phase2-winner-13b2-v232-mkmlizer: quantizing model to /dev/shm/model_cache
chaiml-phase2-winner-13b2-v232-mkmlizer: Saving mkml model at /dev/shm/model_cache
chaiml-phase2-winner-13b2-v232-mkmlizer: Reading /tmp/tmpz43eqm3e/pytorch_model.bin.index.json
chaiml-phase2-winner-13b2-v232-mkmlizer: 
Profiling:   0%|          | 0/363 [00:00<?, ?it/s]
Profiling:   0%|          | 1/363 [00:04<28:11,  4.67s/it]
Profiling:  38%|███▊      | 139/363 [00:07<00:09, 24.49it/s]
Profiling:  77%|███████▋  | 278/363 [00:08<00:01, 42.68it/s]
Profiling: 100%|██████████| 363/363 [00:10<00:00, 45.16it/s]
Profiling: 100%|██████████| 363/363 [00:10<00:00, 35.23it/s]
chaiml-phase2-winner-13b2-v232-mkmlizer: Processed model ChaiML/phase2_winner_13b2 in 58.067s
chaiml-phase2-winner-13b2-v232-mkmlizer: creating bucket guanaco-mkml-models
chaiml-phase2-winner-13b2-v232-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-phase2-winner-13b2-v232-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v232
chaiml-phase2-winner-13b2-v232-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v232/special_tokens_map.json
chaiml-phase2-winner-13b2-v232-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v232/tokenizer_config.json
chaiml-phase2-winner-13b2-v232-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v232/config.json
chaiml-phase2-winner-13b2-v232-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v232/tokenizer.json
chaiml-phase2-winner-13b2-v232-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v232/tokenizer.model
chaiml-phase2-winner-13b2-v232-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v232/mkml_model.tensors
chaiml-phase2-winner-13b2-v232-mkmlizer: loading reward model from rirv938/gpt2_ties_merge_preference_plus_classic_e2_density_99
chaiml-phase2-winner-13b2-v232-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:1067: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
chaiml-phase2-winner-13b2-v232-mkmlizer:   warnings.warn(
chaiml-phase2-winner-13b2-v232-mkmlizer: 
config.json:   0%|          | 0.00/983 [00:00<?, ?B/s]
config.json: 100%|██████████| 983/983 [00:00<00:00, 10.4MB/s]
chaiml-phase2-winner-13b2-v232-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:690: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
chaiml-phase2-winner-13b2-v232-mkmlizer:   warnings.warn(
chaiml-phase2-winner-13b2-v232-mkmlizer: 
tokenizer_config.json:   0%|          | 0.00/445 [00:00<?, ?B/s]
tokenizer_config.json: 100%|██████████| 445/445 [00:00<00:00, 4.59MB/s]
chaiml-phase2-winner-13b2-v232-mkmlizer: 
vocab.json:   0%|          | 0.00/798k [00:00<?, ?B/s]
vocab.json: 100%|██████████| 798k/798k [00:00<00:00, 8.39MB/s]
chaiml-phase2-winner-13b2-v232-mkmlizer: 
merges.txt:   0%|          | 0.00/456k [00:00<?, ?B/s]
merges.txt: 100%|██████████| 456k/456k [00:00<00:00, 24.7MB/s]
chaiml-phase2-winner-13b2-v232-mkmlizer: 
tokenizer.json:   0%|          | 0.00/2.11M [00:00<?, ?B/s]
tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 24.8MB/s]
chaiml-phase2-winner-13b2-v232-mkmlizer: 
special_tokens_map.json:   0%|          | 0.00/441 [00:00<?, ?B/s]
special_tokens_map.json: 100%|██████████| 441/441 [00:00<00:00, 6.42MB/s]
chaiml-phase2-winner-13b2-v232-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:472: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
chaiml-phase2-winner-13b2-v232-mkmlizer:   warnings.warn(
chaiml-phase2-winner-13b2-v232-mkmlizer: 
model.safetensors.index.json:   0%|          | 0.00/10.5k [00:00<?, ?B/s]
model.safetensors.index.json: 100%|██████████| 10.5k/10.5k [00:00<00:00, 80.2MB/s]
chaiml-phase2-winner-13b2-v232-mkmlizer: 
Downloading shards:   0%|          | 0/1 [00:00<?, ?it/s]
chaiml-phase2-winner-13b2-v232-mkmlizer: 
model-00001-of-00001.safetensors:   0%|          | 0.00/249M [00:00<?, ?B/s]
chaiml-phase2-winner-13b2-v232-mkmlizer: 
model-00001-of-00001.safetensors:   4%|▍         | 10.5M/249M [00:00<00:09, 25.9MB/s]
chaiml-phase2-winner-13b2-v232-mkmlizer: 
model-00001-of-00001.safetensors:  12%|█▏        | 28.7M/249M [00:00<00:03, 66.3MB/s]
chaiml-phase2-winner-13b2-v232-mkmlizer: 
model-00001-of-00001.safetensors:  62%|██████▏   | 155M/249M [00:00<00:00, 386MB/s]  
chaiml-phase2-winner-13b2-v232-mkmlizer: 
model-00001-of-00001.safetensors:  87%|████████▋ | 217M/249M [00:00<00:00, 400MB/s]
model-00001-of-00001.safetensors: 100%|█████████▉| 249M/249M [00:01<00:00, 236MB/s]
chaiml-phase2-winner-13b2-v232-mkmlizer: 
Downloading shards: 100%|██████████| 1/1 [00:01<00:00,  1.64s/it]
Downloading shards: 100%|██████████| 1/1 [00:01<00:00,  1.64s/it]
chaiml-phase2-winner-13b2-v232-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-phase2-winner-13b2-v232-mkmlizer: Saving duration: 0.092s
chaiml-phase2-winner-13b2-v232-mkmlizer: Processed model rirv938/gpt2_ties_merge_preference_plus_classic_e2_density_99 in 3.937s
chaiml-phase2-winner-13b2-v232-mkmlizer: creating bucket guanaco-reward-models
chaiml-phase2-winner-13b2-v232-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-phase2-winner-13b2-v232-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v232_reward
chaiml-phase2-winner-13b2-v232-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v232_reward/config.json
chaiml-phase2-winner-13b2-v232-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v232_reward/special_tokens_map.json
chaiml-phase2-winner-13b2-v232-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v232_reward/tokenizer_config.json
chaiml-phase2-winner-13b2-v232-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v232_reward/merges.txt
chaiml-phase2-winner-13b2-v232-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v232_reward/vocab.json
chaiml-phase2-winner-13b2-v232-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v232_reward/tokenizer.json
chaiml-phase2-winner-13b2-v232-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v232_reward/reward.tensors
Job chaiml-phase2-winner-13b2-v232-mkmlizer completed after 84.66s with status: succeeded
Stopping job with name chaiml-phase2-winner-13b2-v232-mkmlizer
Pipeline stage MKMLizer completed in 91.48s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-phase2-winner-13b2-v232
Waiting for inference service chaiml-phase2-winner-13b2-v232 to be ready
Tearing down inference service chaiml-phase2-winner-13b2-v232
%s, retrying in %s seconds...
Creating inference service chaiml-phase2-winner-13b2-v232
Waiting for inference service chaiml-phase2-winner-13b2-v232 to be ready
Inference service chaiml-phase2-winner-13b2-v232 ready after 50.28634977340698s
Pipeline stage ISVCDeployer completed in 667.19s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.667299509048462s
Received healthy response to inference request in 1.7233867645263672s
Received healthy response to inference request in 1.7704706192016602s
Received healthy response to inference request in 1.4989354610443115s
Received healthy response to inference request in 1.7341694831848145s
5 requests
0 failed requests
5th percentile: 1.5438257217407227
10th percentile: 1.5887159824371337
20th percentile: 1.678496503829956
30th percentile: 1.7255433082580567
40th percentile: 1.7298563957214355
50th percentile: 1.7341694831848145
60th percentile: 1.7486899375915528
70th percentile: 1.763210391998291
80th percentile: 1.9498363971710206
90th percentile: 2.3085679531097414
95th percentile: 2.487933731079101
99th percentile: 2.63142635345459
mean time: 1.878852367401123
Pipeline stage StressChecker completed in 10.50s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.05s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.07s
M-Eval Dataset for topic stay_in_character is loaded
AUTO_DEACTIVATION: submission %s deactivated %s
chaiml-phase2-winner-13b2_v232 status is now inactive due to auto deactivation removed underperforming models
chaiml-phase2-winner-13b2_v232 status is now deployed due to admin request
chaiml-phase2-winner-13b2_v232 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-phase2-winner-13b2_v232
Running pipeline stage ISVCDeleter
Checking if service chaiml-phase2-winner-13b2-v232 is running
Tearing down inference service chaiml-phase2-winner-13b2-v232
Toredown service chaiml-phase2-winner-13b2-v232
Pipeline stage ISVCDeleter completed in 6.62s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-phase2-winner-13b2-v232/config.json from bucket guanaco-mkml-models
Deleting key chaiml-phase2-winner-13b2-v232/mkml_model.tensors from bucket guanaco-mkml-models
Deleting key chaiml-phase2-winner-13b2-v232/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-phase2-winner-13b2-v232/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-phase2-winner-13b2-v232/tokenizer.model from bucket guanaco-mkml-models
Deleting key chaiml-phase2-winner-13b2-v232/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-phase2-winner-13b2-v232_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-phase2-winner-13b2-v232_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-phase2-winner-13b2-v232_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-phase2-winner-13b2-v232_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-phase2-winner-13b2-v232_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-phase2-winner-13b2-v232_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-phase2-winner-13b2-v232_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.91s
chaiml-phase2-winner-13b2_v232 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics