mistralai-mixtral-8x7b-_3473

developer_uid: robert_irvine
submission_id: mistralai-mixtral-8x7b-_3473_v68
model_name: mistralai-mixtral-8x7b-_3473_v68
model_group: mistralai/Mixtral-8x7B-I
status: torndown
timestamp: 2024-07-10T18:22:25+00:00
num_battles: 34807
num_wins: 14920
celo_rating: 1123.37
family_friendly_score: 0.0
submission_type: basic
model_repo: mistralai/Mixtral-8x7B-Instruct-v0.1
model_architecture: MixtralForCausalLM
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
model_num_parameters: 46702792704.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: mistralai-mixtral-8x7b-_3473_v68
is_internal_developer: True
language_model: mistralai/Mixtral-8x7B-Instruct-v0.1
model_size: 47B
ranking_group: single
us_pacific_date: 2024-07-10
win_ratio: 0.42864940960151693
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 50, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['\n', '</s>', '<|user|>', '###'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': '<s>[INST] This is an entertaining conversation. You are {bot_name} who has the persona: {memory}.\nEngage in a chat with {user_name} while staying in character. Try to flirt with {user_name}. Engage in *roleplay* actions. Describe the scene dramatically. \n', 'prompt_template': '{prompt}\n', 'bot_template': '{bot_name}: {message}</s>', 'user_template': '[INST] {user_name}: {message} [/INST]', 'response_template': '[INST] respond with humor [/INST]{bot_name}:', 'truncate_by_message': False}
reward_formatter: {'bot_template': 'Bot: {message}\n', 'memory_template': '""', 'prompt_template': '""', 'response_template': 'Bot:', 'truncate_by_message': False, 'user_template': 'User: {message}\n'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name mistralai-mixtral-8x7b-3473-v68-mkmlizer
Waiting for job on mistralai-mixtral-8x7b-3473-v68-mkmlizer to finish
mistralai-mixtral-8x7b-3473-v68-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mistralai-mixtral-8x7b-3473-v68-mkmlizer: ║     _____            __           __                                ║
mistralai-mixtral-8x7b-3473-v68-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
mistralai-mixtral-8x7b-3473-v68-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
mistralai-mixtral-8x7b-3473-v68-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
mistralai-mixtral-8x7b-3473-v68-mkmlizer: ║       /___/                                                         ║
mistralai-mixtral-8x7b-3473-v68-mkmlizer: ║                                                                     ║
mistralai-mixtral-8x7b-3473-v68-mkmlizer: ║  Version: 0.8.14                                                    ║
mistralai-mixtral-8x7b-3473-v68-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
mistralai-mixtral-8x7b-3473-v68-mkmlizer: ║  https://mk1.ai                                                     ║
mistralai-mixtral-8x7b-3473-v68-mkmlizer: ║                                                                     ║
mistralai-mixtral-8x7b-3473-v68-mkmlizer: ║  The license key for the current software has been verified as      ║
mistralai-mixtral-8x7b-3473-v68-mkmlizer: ║  belonging to:                                                      ║
mistralai-mixtral-8x7b-3473-v68-mkmlizer: ║                                                                     ║
mistralai-mixtral-8x7b-3473-v68-mkmlizer: ║  Chai Research Corp.                                                ║
mistralai-mixtral-8x7b-3473-v68-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
mistralai-mixtral-8x7b-3473-v68-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
mistralai-mixtral-8x7b-3473-v68-mkmlizer: ║                                                                     ║
mistralai-mixtral-8x7b-3473-v68-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
mistralai-mixtral-8x7b-3473-v68-mkmlizer: Downloaded to shared memory in 272.896s
mistralai-mixtral-8x7b-3473-v68-mkmlizer: quantizing model to /dev/shm/model_cache
mistralai-mixtral-8x7b-3473-v68-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
mistralai-mixtral-8x7b-3473-v68-mkmlizer: quantized model in 118.091s
mistralai-mixtral-8x7b-3473-v68-mkmlizer: Processed model mistralai/Mixtral-8x7B-Instruct-v0.1 in 390.988s
mistralai-mixtral-8x7b-3473-v68-mkmlizer: creating bucket guanaco-mkml-models
mistralai-mixtral-8x7b-3473-v68-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
mistralai-mixtral-8x7b-3473-v68-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mistralai-mixtral-8x7b-3473-v68
mistralai-mixtral-8x7b-3473-v68-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/mistralai-mixtral-8x7b-3473-v68/special_tokens_map.json
mistralai-mixtral-8x7b-3473-v68-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/mistralai-mixtral-8x7b-3473-v68/tokenizer_config.json
mistralai-mixtral-8x7b-3473-v68-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/mistralai-mixtral-8x7b-3473-v68/tokenizer.json
mistralai-mixtral-8x7b-3473-v68-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/mistralai-mixtral-8x7b-3473-v68/config.json
mistralai-mixtral-8x7b-3473-v68-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/mistralai-mixtral-8x7b-3473-v68/tokenizer.model
mistralai-mixtral-8x7b-3473-v68-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/mistralai-mixtral-8x7b-3473-v68/flywheel_model.3.safetensors
mistralai-mixtral-8x7b-3473-v68-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/mistralai-mixtral-8x7b-3473-v68/flywheel_model.0.safetensors
mistralai-mixtral-8x7b-3473-v68-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/mistralai-mixtral-8x7b-3473-v68/flywheel_model.1.safetensors
mistralai-mixtral-8x7b-3473-v68-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/mistralai-mixtral-8x7b-3473-v68/flywheel_model.2.safetensors
mistralai-mixtral-8x7b-3473-v68-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
mistralai-mixtral-8x7b-3473-v68-mkmlizer: 
Loading 0:   0%|          | 0/995 [00:00<?, ?it/s]
Loading 0:   1%|          | 7/995 [00:00<00:16, 60.58it/s]
Loading 0:   1%|▏         | 14/995 [00:00<00:17, 55.83it/s]
Loading 0:   2%|▏         | 20/995 [00:00<00:18, 53.22it/s]
Loading 0:   3%|▎         | 26/995 [00:00<00:17, 54.15it/s]
Loading 0:   4%|▎         | 37/995 [00:00<00:13, 70.09it/s]
Loading 0:   5%|▍         | 45/995 [00:00<00:15, 62.94it/s]
Loading 0:   5%|▌         | 52/995 [00:01<00:27, 34.53it/s]
Loading 0:   6%|▌         | 58/995 [00:01<00:24, 38.06it/s]
Loading 0:   7%|▋         | 66/995 [00:01<00:20, 44.61it/s]
Loading 0:   7%|▋         | 72/995 [00:01<00:20, 45.79it/s]
Loading 0:   8%|▊         | 78/995 [00:01<00:19, 47.64it/s]
Loading 0:   8%|▊         | 84/995 [00:01<00:18, 48.91it/s]
Loading 0:  10%|▉         | 96/995 [00:01<00:13, 64.65it/s]
Loading 0:  10%|█         | 103/995 [00:01<00:13, 64.43it/s]
Loading 0:  11%|█         | 110/995 [00:02<00:26, 32.99it/s]
Loading 0:  12%|█▏        | 116/995 [00:02<00:24, 35.76it/s]
Loading 0:  12%|█▏        | 122/995 [00:02<00:22, 38.99it/s]
Loading 0:  13%|█▎        | 129/995 [00:02<00:19, 44.00it/s]
Loading 0:  14%|█▎        | 135/995 [00:02<00:19, 44.74it/s]
Loading 0:  14%|█▍        | 141/995 [00:03<00:18, 45.62it/s]
Loading 0:  15%|█▍        | 147/995 [00:03<00:18, 47.10it/s]
Loading 0:  16%|█▋        | 162/995 [00:03<00:21, 38.86it/s]
Loading 0:  17%|█▋        | 168/995 [00:03<00:20, 41.25it/s]
Loading 0:  17%|█▋        | 174/995 [00:03<00:18, 43.45it/s]
Loading 0:  18%|█▊        | 179/995 [00:03<00:18, 44.20it/s]
Loading 0:  18%|█▊        | 184/995 [00:04<00:17, 45.10it/s]
Loading 0:  19%|█▉        | 192/995 [00:04<00:15, 51.48it/s]
Loading 0:  20%|█▉        | 198/995 [00:04<00:15, 51.61it/s]
Loading 0:  21%|██        | 204/995 [00:04<00:15, 50.59it/s]
Loading 0:  21%|██        | 210/995 [00:04<00:25, 30.21it/s]
Loading 0:  22%|██▏       | 216/995 [00:04<00:22, 34.22it/s]
Loading 0:  22%|██▏       | 223/995 [00:05<00:18, 40.74it/s]
Loading 0:  23%|██▎       | 229/995 [00:05<00:17, 43.46it/s]
Loading 0:  24%|██▎       | 235/995 [00:05<00:16, 45.68it/s]
Loading 0:  24%|██▍       | 241/995 [00:05<00:15, 47.36it/s]
Loading 0:  25%|██▌       | 253/995 [00:05<00:12, 60.83it/s]
Loading 0:  26%|██▌       | 260/995 [00:05<00:12, 59.19it/s]
Loading 0:  27%|██▋       | 267/995 [00:06<00:21, 33.13it/s]
Loading 0:  28%|██▊       | 277/995 [00:06<00:16, 43.06it/s]
Loading 0:  28%|██▊       | 281/995 [00:16<00:16, 43.06it/s]
Loading 0:  28%|██▊       | 282/995 [00:32<13:16,  1.12s/it]
Loading 0:  29%|██▉       | 290/995 [00:32<08:58,  1.31it/s]
Loading 0:  30%|██▉       | 297/995 [00:33<06:24,  1.82it/s]
Loading 0:  30%|███       | 303/995 [00:33<04:45,  2.42it/s]
Loading 0:  31%|███       | 309/995 [00:33<03:30,  3.27it/s]
Loading 0:  32%|███▏      | 320/995 [00:33<02:14,  5.02it/s]
Loading 0:  33%|███▎      | 326/995 [00:33<01:43,  6.45it/s]
Loading 0:  33%|███▎      | 332/995 [00:33<01:19,  8.34it/s]
Loading 0:  34%|███▍      | 337/995 [00:34<01:03, 10.36it/s]
Loading 0:  35%|███▍      | 344/995 [00:34<00:45, 14.19it/s]
Loading 0:  35%|███▌      | 350/995 [00:34<00:36, 17.82it/s]
Loading 0:  36%|███▌      | 356/995 [00:34<00:29, 21.92it/s]
Loading 0:  36%|███▋      | 362/995 [00:34<00:24, 26.32it/s]
Loading 0:  37%|███▋      | 368/995 [00:34<00:28, 21.63it/s]
Loading 0:  38%|███▊      | 376/995 [00:35<00:21, 28.60it/s]
Loading 0:  38%|███▊      | 381/995 [00:35<00:19, 31.67it/s]
Loading 0:  39%|███▉      | 386/995 [00:35<00:17, 34.79it/s]
Loading 0:  39%|███▉      | 392/995 [00:35<00:15, 38.70it/s]
Loading 0:  40%|████      | 402/995 [00:35<00:11, 51.69it/s]
Loading 0:  41%|████      | 409/995 [00:35<00:10, 55.00it/s]
Loading 0:  42%|████▏     | 416/995 [00:35<00:11, 52.49it/s]
Loading 0:  43%|████▎     | 423/995 [00:36<00:18, 31.71it/s]
Loading 0:  43%|████▎     | 428/995 [00:36<00:16, 34.36it/s]
Loading 0:  44%|████▍     | 436/995 [00:36<00:13, 41.56it/s]
Loading 0:  44%|████▍     | 442/995 [00:36<00:12, 43.85it/s]
Loading 0:  45%|████▌     | 448/995 [00:36<00:12, 45.13it/s]
Loading 0:  46%|████▌     | 454/995 [00:36<00:11, 45.51it/s]
Loading 0:  46%|████▋     | 461/995 [00:36<00:10, 51.28it/s]
Loading 0:  47%|████▋     | 471/995 [00:36<00:08, 61.22it/s]
Loading 0:  48%|████▊     | 478/995 [00:37<00:15, 33.89it/s]
Loading 0:  49%|████▊     | 484/995 [00:37<00:13, 36.56it/s]
Loading 0:  49%|████▉     | 489/995 [00:37<00:13, 38.46it/s]
Loading 0:  50%|████▉     | 495/995 [00:37<00:12, 41.53it/s]
Loading 0:  51%|█████     | 503/995 [00:37<00:10, 48.30it/s]
Loading 0:  51%|█████     | 509/995 [00:38<00:09, 48.83it/s]
Loading 0:  52%|█████▏    | 515/995 [00:38<00:09, 48.33it/s]
Loading 0:  52%|█████▏    | 521/995 [00:38<00:09, 51.07it/s]
Loading 0:  53%|█████▎    | 527/995 [00:38<00:15, 29.34it/s]
Loading 0:  54%|█████▎    | 534/995 [00:38<00:13, 35.13it/s]
Loading 0:  54%|█████▍    | 540/995 [00:38<00:11, 38.66it/s]
Loading 0:  55%|█████▍    | 546/995 [00:39<00:10, 41.70it/s]
Loading 0:  55%|█████▌    | 551/995 [00:39<00:10, 43.12it/s]
Loading 0:  56%|█████▋    | 560/995 [00:52<00:10, 43.12it/s]
Loading 0:  56%|█████▋    | 561/995 [01:05<08:16,  1.14s/it]
Loading 0:  57%|█████▋    | 567/995 [01:05<06:01,  1.18it/s]
Loading 0:  57%|█████▋    | 572/995 [01:06<04:33,  1.55it/s]
Loading 0:  58%|█████▊    | 581/995 [01:06<02:55,  2.36it/s]
Loading 0:  59%|█████▉    | 586/995 [01:06<02:14,  3.03it/s]
Loading 0:  60%|█████▉    | 593/995 [01:06<01:32,  4.35it/s]
Loading 0:  60%|██████    | 599/995 [01:06<01:07,  5.85it/s]
Loading 0:  61%|██████    | 604/995 [01:07<00:52,  7.50it/s]
Loading 0:  61%|██████    | 609/995 [01:07<00:40,  9.63it/s]
Loading 0:  62%|██████▏   | 614/995 [01:07<00:30, 12.31it/s]
Loading 0:  63%|██████▎   | 626/995 [01:07<00:17, 21.39it/s]
Loading 0:  64%|██████▍   | 635/995 [01:07<00:12, 28.88it/s]
Loading 0:  65%|██████▍   | 643/995 [01:08<00:15, 22.10it/s]
Loading 0:  65%|██████▌   | 649/995 [01:08<00:13, 25.50it/s]
Loading 0:  66%|██████▌   | 656/995 [01:08<00:11, 30.72it/s]
Loading 0:  67%|██████▋   | 662/995 [01:08<00:09, 33.37it/s]
Loading 0:  67%|██████▋   | 668/995 [01:08<00:09, 35.10it/s]
Loading 0:  68%|██████▊   | 673/995 [01:08<00:09, 35.59it/s]
Loading 0:  69%|██████▊   | 684/995 [01:08<00:06, 48.25it/s]
Loading 0:  69%|██████▉   | 691/995 [01:09<00:10, 29.62it/s]
Loading 0:  70%|██████▉   | 696/995 [01:09<00:09, 31.46it/s]
Loading 0:  70%|███████   | 701/995 [01:09<00:08, 33.89it/s]
Loading 0:  71%|███████   | 706/995 [01:09<00:07, 36.25it/s]
Loading 0:  71%|███████▏  | 711/995 [01:09<00:07, 39.08it/s]
Loading 0:  72%|███████▏  | 718/995 [01:09<00:06, 45.05it/s]
Loading 0:  73%|███████▎  | 724/995 [01:09<00:06, 44.29it/s]
Loading 0:  73%|███████▎  | 729/995 [01:10<00:06, 43.84it/s]
Loading 0:  74%|███████▍  | 735/995 [01:10<00:05, 47.82it/s]
Loading 0:  74%|███████▍  | 741/995 [01:10<00:09, 25.73it/s]
Loading 0:  75%|███████▌  | 748/995 [01:10<00:07, 31.44it/s]
Loading 0:  76%|███████▌  | 753/995 [01:10<00:07, 33.01it/s]
Loading 0:  76%|███████▌  | 758/995 [01:11<00:06, 34.58it/s]
Loading 0:  77%|███████▋  | 763/995 [01:11<00:06, 36.09it/s]
Loading 0:  77%|███████▋  | 768/995 [01:11<00:06, 36.77it/s]
Loading 0:  78%|███████▊  | 778/995 [01:11<00:04, 50.83it/s]
Loading 0:  79%|███████▉  | 784/995 [01:11<00:04, 46.63it/s]
Loading 0:  79%|███████▉  | 790/995 [01:11<00:04, 49.00it/s]
Loading 0:  80%|████████  | 796/995 [01:12<00:07, 25.91it/s]
Loading 0:  81%|████████  | 801/995 [01:12<00:06, 28.02it/s]
Loading 0:  81%|████████  | 805/995 [01:12<00:06, 29.07it/s]
Loading 0:  82%|████████▏ | 811/995 [01:12<00:05, 34.17it/s]
Loading 0:  82%|████████▏ | 816/995 [01:12<00:05, 34.40it/s]
Loading 0:  83%|████████▎ | 821/995 [01:12<00:05, 34.61it/s]
Loading 0:  83%|████████▎ | 825/995 [01:12<00:04, 34.62it/s]
Loading 0:  83%|████████▎ | 829/995 [01:13<00:04, 35.10it/s]
Loading 0:  84%|████████▍ | 840/995 [01:13<00:03, 51.63it/s]
Loading 0:  85%|████████▍ | 841/995 [01:25<00:02, 51.63it/s]
Loading 0:  85%|████████▍ | 842/995 [01:37<03:37,  1.42s/it]
Loading 0:  85%|████████▌ | 849/995 [01:37<02:15,  1.08it/s]
Loading 0:  86%|████████▌ | 854/995 [01:38<01:36,  1.47it/s]
Loading 0:  86%|████████▋ | 859/995 [01:38<01:07,  2.02it/s]
Loading 0:  87%|████████▋ | 864/995 [01:38<00:47,  2.78it/s]
Loading 0:  88%|████████▊ | 871/995 [01:38<00:29,  4.27it/s]
Loading 0:  88%|████████▊ | 877/995 [01:38<00:20,  5.89it/s]
Loading 0:  89%|████████▊ | 882/995 [01:38<00:14,  7.62it/s]
Loading 0:  89%|████████▉ | 887/995 [01:38<00:10,  9.86it/s]
Loading 0:  90%|████████▉ | 892/995 [01:38<00:08, 12.74it/s]
Loading 0:  90%|█████████ | 897/995 [01:39<00:07, 12.43it/s]
Loading 0:  91%|█████████ | 904/995 [01:39<00:05, 17.46it/s]
Loading 0:  91%|█████████▏| 909/995 [01:39<00:04, 20.43it/s]
Loading 0:  92%|█████████▏| 914/995 [01:39<00:03, 23.34it/s]
Loading 0:  92%|█████████▏| 919/995 [01:39<00:02, 26.56it/s]
Loading 0:  93%|█████████▎| 924/995 [01:39<00:02, 29.34it/s]
Loading 0:  94%|█████████▍| 935/995 [01:40<00:01, 42.95it/s]
Loading 0:  95%|█████████▍| 941/995 [01:40<00:01, 42.48it/s]
Loading 0:  95%|█████████▌| 947/995 [01:40<00:01, 44.37it/s]
Loading 0:  96%|█████████▌| 953/995 [01:42<00:04,  8.77it/s]
Loading 0:  96%|█████████▋| 958/995 [01:42<00:03, 10.97it/s]
Loading 0:  97%|█████████▋| 964/995 [01:42<00:02, 14.54it/s]
Loading 0:  97%|█████████▋| 969/995 [01:42<00:01, 17.52it/s]
Loading 0:  98%|█████████▊| 974/995 [01:42<00:01, 20.87it/s]
Loading 0:  98%|█████████▊| 979/995 [01:42<00:00, 24.33it/s]
Loading 0:  99%|█████████▉| 984/995 [01:43<00:00, 27.46it/s]
                                                            
/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.
mistralai-mixtral-8x7b-3473-v68-mkmlizer:   warnings.warn(
mistralai-mixtral-8x7b-3473-v68-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`.
mistralai-mixtral-8x7b-3473-v68-mkmlizer:   warnings.warn(
mistralai-mixtral-8x7b-3473-v68-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.
mistralai-mixtral-8x7b-3473-v68-mkmlizer:   warnings.warn(
mistralai-mixtral-8x7b-3473-v68-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.
mistralai-mixtral-8x7b-3473-v68-mkmlizer:   warnings.warn(
mistralai-mixtral-8x7b-3473-v68-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:07<00:07,  7.28s/it]
Downloading shards: 100%|██████████| 2/2 [00:09<00:00,  4.20s/it]
Downloading shards: 100%|██████████| 2/2 [00:09<00:00,  4.66s/it]
mistralai-mixtral-8x7b-3473-v68-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  1.58it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  2.53it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  2.32it/s]
mistralai-mixtral-8x7b-3473-v68-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
mistralai-mixtral-8x7b-3473-v68-mkmlizer: Saving duration: 2.216s
mistralai-mixtral-8x7b-3473-v68-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 14.586s
mistralai-mixtral-8x7b-3473-v68-mkmlizer: creating bucket guanaco-reward-models
mistralai-mixtral-8x7b-3473-v68-mkmlizer: Bucket 's3://guanaco-reward-models/' created
mistralai-mixtral-8x7b-3473-v68-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/mistralai-mixtral-8x7b-3473-v68_reward
mistralai-mixtral-8x7b-3473-v68-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/mistralai-mixtral-8x7b-3473-v68_reward/config.json
mistralai-mixtral-8x7b-3473-v68-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/mistralai-mixtral-8x7b-3473-v68_reward/special_tokens_map.json
mistralai-mixtral-8x7b-3473-v68-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/mistralai-mixtral-8x7b-3473-v68_reward/tokenizer_config.json
mistralai-mixtral-8x7b-3473-v68-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/mistralai-mixtral-8x7b-3473-v68_reward/vocab.json
mistralai-mixtral-8x7b-3473-v68-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/mistralai-mixtral-8x7b-3473-v68_reward/tokenizer.json
mistralai-mixtral-8x7b-3473-v68-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/mistralai-mixtral-8x7b-3473-v68_reward/merges.txt
mistralai-mixtral-8x7b-3473-v68-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/mistralai-mixtral-8x7b-3473-v68_reward/reward.tensors
Job mistralai-mixtral-8x7b-3473-v68-mkmlizer completed after 458.8s with status: succeeded
Stopping job with name mistralai-mixtral-8x7b-3473-v68-mkmlizer
Pipeline stage MKMLizer completed in 459.55s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service mistralai-mixtral-8x7b-3473-v68
Waiting for inference service mistralai-mixtral-8x7b-3473-v68 to be ready
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Inference service mistralai-mixtral-8x7b-3473-v68 ready after 80.48571109771729s
Pipeline stage ISVCDeployer completed in 87.51s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.1421103477478027s
Received healthy response to inference request in 1.7798562049865723s
Received healthy response to inference request in 1.8696303367614746s
Received healthy response to inference request in 2.045328378677368s
Received healthy response to inference request in 1.6569926738739014s
5 requests
0 failed requests
5th percentile: 1.6815653800964356
10th percentile: 1.7061380863189697
20th percentile: 1.755283498764038
30th percentile: 1.7978110313415527
40th percentile: 1.8337206840515137
50th percentile: 1.8696303367614746
60th percentile: 1.9399095535278321
70th percentile: 2.0101887702941896
80th percentile: 2.264684772491455
90th percentile: 2.703397560119629
95th percentile: 2.9227539539337157
99th percentile: 3.0982390689849852
mean time: 2.098783588409424
Pipeline stage StressChecker completed in 11.36s
mistralai-mixtral-8x7b-_3473_v68 status is now deployed due to DeploymentManager action
mistralai-mixtral-8x7b-_3473_v68 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of mistralai-mixtral-8x7b-_3473_v68
Running pipeline stage ISVCDeleter
Checking if service mistralai-mixtral-8x7b-3473-v68 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.78s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key mistralai-mixtral-8x7b-3473-v68/config.json from bucket guanaco-mkml-models
Deleting key mistralai-mixtral-8x7b-3473-v68/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key mistralai-mixtral-8x7b-3473-v68/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key mistralai-mixtral-8x7b-3473-v68/flywheel_model.2.safetensors from bucket guanaco-mkml-models
Deleting key mistralai-mixtral-8x7b-3473-v68/flywheel_model.3.safetensors from bucket guanaco-mkml-models
Deleting key mistralai-mixtral-8x7b-3473-v68/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key mistralai-mixtral-8x7b-3473-v68/tokenizer.json from bucket guanaco-mkml-models
Deleting key mistralai-mixtral-8x7b-3473-v68/tokenizer.model from bucket guanaco-mkml-models
Deleting key mistralai-mixtral-8x7b-3473-v68/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key mistralai-mixtral-8x7b-3473-v68_reward/config.json from bucket guanaco-reward-models
Deleting key mistralai-mixtral-8x7b-3473-v68_reward/merges.txt from bucket guanaco-reward-models
Deleting key mistralai-mixtral-8x7b-3473-v68_reward/reward.tensors from bucket guanaco-reward-models
Deleting key mistralai-mixtral-8x7b-3473-v68_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key mistralai-mixtral-8x7b-3473-v68_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key mistralai-mixtral-8x7b-3473-v68_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key mistralai-mixtral-8x7b-3473-v68_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 10.17s
mistralai-mixtral-8x7b-_3473_v68 status is now torndown due to DeploymentManager action