developer_uid: chace9580
submission_id: jic062-instruct-v17-base-mix_v2
model_name: jic062-instruct-v17-base-mix_v2
model_group: jic062/instruct_v17_base
status: torndown
timestamp: 2024-08-11T07:32:38+00:00
num_battles: 13626
num_wins: 7115
celo_rating: 1239.67
family_friendly_score: 0.0
submission_type: basic
model_repo: jic062/instruct_v17_base_mix
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: jic062-instruct-v17-base-mix_v2
is_internal_developer: False
language_model: jic062/instruct_v17_base_mix
model_size: 8B
ranking_group: single
us_pacific_date: 2024-08-11
win_ratio: 0.5221635109349773
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '|eot_id|', '<|end_of_text|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64, 'reward_max_token_input': 256}
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{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'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name jic062-instruct-v17-base-mix-v2-mkmlizer
Waiting for job on jic062-instruct-v17-base-mix-v2-mkmlizer to finish
Stopping job with name jic062-instruct-v17-base-mix-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name jic062-instruct-v17-base-mix-v2-mkmlizer
Waiting for job on jic062-instruct-v17-base-mix-v2-mkmlizer to finish
jic062-instruct-v17-base-mix-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-instruct-v17-base-mix-v2-mkmlizer: ║     _____            __           __                                ║
jic062-instruct-v17-base-mix-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jic062-instruct-v17-base-mix-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jic062-instruct-v17-base-mix-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jic062-instruct-v17-base-mix-v2-mkmlizer: ║       /___/                                                         ║
jic062-instruct-v17-base-mix-v2-mkmlizer: ║                                                                     ║
jic062-instruct-v17-base-mix-v2-mkmlizer: ║  Version: 0.9.9                                                     ║
jic062-instruct-v17-base-mix-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jic062-instruct-v17-base-mix-v2-mkmlizer: ║  https://mk1.ai                                                     ║
jic062-instruct-v17-base-mix-v2-mkmlizer: ║                                                                     ║
jic062-instruct-v17-base-mix-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
jic062-instruct-v17-base-mix-v2-mkmlizer: ║  belonging to:                                                      ║
jic062-instruct-v17-base-mix-v2-mkmlizer: ║                                                                     ║
jic062-instruct-v17-base-mix-v2-mkmlizer: ║  Chai Research Corp.                                                ║
jic062-instruct-v17-base-mix-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jic062-instruct-v17-base-mix-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
jic062-instruct-v17-base-mix-v2-mkmlizer: ║                                                                     ║
jic062-instruct-v17-base-mix-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jic062-instruct-v17-base-mix-v2-mkmlizer: Downloaded to shared memory in 20.743s
jic062-instruct-v17-base-mix-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpso30qv2i, device:0
jic062-instruct-v17-base-mix-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jic062-instruct-v17-base-mix-v2-mkmlizer: quantized model in 26.817s
jic062-instruct-v17-base-mix-v2-mkmlizer: Processed model jic062/instruct_v17_base_mix in 47.560s
jic062-instruct-v17-base-mix-v2-mkmlizer: creating bucket guanaco-mkml-models
jic062-instruct-v17-base-mix-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-instruct-v17-base-mix-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-instruct-v17-base-mix-v2
jic062-instruct-v17-base-mix-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-instruct-v17-base-mix-v2/config.json
jic062-instruct-v17-base-mix-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-instruct-v17-base-mix-v2/special_tokens_map.json
jic062-instruct-v17-base-mix-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-instruct-v17-base-mix-v2/tokenizer_config.json
jic062-instruct-v17-base-mix-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-instruct-v17-base-mix-v2/tokenizer.json
jic062-instruct-v17-base-mix-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-instruct-v17-base-mix-v2/flywheel_model.0.safetensors
jic062-instruct-v17-base-mix-v2-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
jic062-instruct-v17-base-mix-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 52.44it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:03, 71.84it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:03, 76.71it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:03, 80.24it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:03, 77.69it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:03, 77.46it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:03, 74.99it/s]
Loading 0:  24%|██▍       | 70/291 [00:00<00:02, 73.76it/s]
Loading 0:  27%|██▋       | 79/291 [00:01<00:02, 74.31it/s]
Loading 0:  30%|██▉       | 87/291 [00:02<00:10, 19.07it/s]
Loading 0:  33%|███▎      | 97/291 [00:02<00:07, 25.33it/s]
Loading 0:  36%|███▋      | 106/291 [00:02<00:05, 32.19it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 45.10it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 51.90it/s]
Loading 0:  48%|████▊     | 139/291 [00:02<00:02, 58.41it/s]
Loading 0:  51%|█████     | 148/291 [00:02<00:02, 62.88it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 66.17it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:01, 68.45it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:01, 70.49it/s]
Loading 0:  63%|██████▎   | 184/291 [00:03<00:01, 72.18it/s]
Loading 0:  66%|██████▌   | 192/291 [00:04<00:05, 19.74it/s]
Loading 0:  68%|██████▊   | 198/291 [00:04<00:04, 23.14it/s]
Loading 0:  70%|███████   | 205/291 [00:04<00:03, 27.73it/s]
Loading 0:  74%|███████▎  | 214/291 [00:04<00:02, 35.34it/s]
Loading 0:  77%|███████▋  | 223/291 [00:05<00:01, 43.71it/s]
Loading 0:  80%|███████▉  | 232/291 [00:05<00:01, 50.96it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:00, 55.82it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 61.33it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 67.15it/s]
Loading 0:  92%|█████████▏| 268/291 [00:05<00:00, 64.01it/s]
Loading 0:  95%|█████████▌| 277/291 [00:05<00:00, 62.39it/s]
Loading 0:  98%|█████████▊| 286/291 [00:05<00:00, 65.58it/s]
                                                            
/opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:957: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
jic062-instruct-v17-base-mix-v2-mkmlizer:   warnings.warn(
jic062-instruct-v17-base-mix-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:785: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
jic062-instruct-v17-base-mix-v2-mkmlizer:   warnings.warn(
jic062-instruct-v17-base-mix-v2-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.
jic062-instruct-v17-base-mix-v2-mkmlizer:   warnings.warn(
jic062-instruct-v17-base-mix-v2-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:05<00:05,  5.54s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  4.05s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  4.27s/it]
jic062-instruct-v17-base-mix-v2-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  2.38it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.96it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.60it/s]
jic062-instruct-v17-base-mix-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jic062-instruct-v17-base-mix-v2-mkmlizer: Saving duration: 1.349s
jic062-instruct-v17-base-mix-v2-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.768s
jic062-instruct-v17-base-mix-v2-mkmlizer: creating bucket guanaco-reward-models
jic062-instruct-v17-base-mix-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jic062-instruct-v17-base-mix-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jic062-instruct-v17-base-mix-v2_reward
jic062-instruct-v17-base-mix-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jic062-instruct-v17-base-mix-v2_reward/special_tokens_map.json
jic062-instruct-v17-base-mix-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jic062-instruct-v17-base-mix-v2_reward/config.json
jic062-instruct-v17-base-mix-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jic062-instruct-v17-base-mix-v2_reward/tokenizer_config.json
jic062-instruct-v17-base-mix-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jic062-instruct-v17-base-mix-v2_reward/merges.txt
jic062-instruct-v17-base-mix-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jic062-instruct-v17-base-mix-v2_reward/vocab.json
jic062-instruct-v17-base-mix-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jic062-instruct-v17-base-mix-v2_reward/tokenizer.json
jic062-instruct-v17-base-mix-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/jic062-instruct-v17-base-mix-v2_reward/reward.tensors
Job jic062-instruct-v17-base-mix-v2-mkmlizer completed after 94.85s with status: succeeded
Stopping job with name jic062-instruct-v17-base-mix-v2-mkmlizer
Pipeline stage MKMLizer completed in 96.40s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service jic062-instruct-v17-base-mix-v2
Waiting for inference service jic062-instruct-v17-base-mix-v2 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service jic062-instruct-v17-base-mix-v2 ready after 201.17118453979492s
Pipeline stage ISVCDeployer completed in 203.32s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.236755609512329s
Received healthy response to inference request in 1.4959125518798828s
Received healthy response to inference request in 1.4669573307037354s
Received healthy response to inference request in 1.4584205150604248s
Received healthy response to inference request in 1.511491060256958s
5 requests
0 failed requests
5th percentile: 1.460127878189087
10th percentile: 1.4618352413177491
20th percentile: 1.4652499675750732
30th percentile: 1.472748374938965
40th percentile: 1.4843304634094239
50th percentile: 1.4959125518798828
60th percentile: 1.502143955230713
70th percentile: 1.508375358581543
80th percentile: 1.6565439701080324
90th percentile: 1.9466497898101807
95th percentile: 2.091702699661255
99th percentile: 2.2077450275421144
mean time: 1.633907413482666
Pipeline stage StressChecker completed in 8.92s
jic062-instruct-v17-base-mix_v2 status is now deployed due to DeploymentManager action
jic062-instruct-v17-base-mix_v2 status is now inactive due to auto deactivation removed underperforming models
jic062-instruct-v17-base-mix_v2 status is now torndown due to DeploymentManager action
admin requested tearing down of mistralai-mixtral-8x7b_3473_v117