jic062-instruct-v17-ori-g36

developer_uid: chace9580

submission_id: jic062-instruct-v17-ori-g36_v2

model_name: jic062-instruct-v17-ori-g36_v2

model_group: jic062/instruct_v17_ori_

status: torndown

timestamp: 2024-08-06T05:21:15+00:00

num_battles: 10589

num_wins: 5469

celo_rating: 1232.39

family_friendly_score: 0.0

submission_type: basic

model_repo: jic062/instruct_v17_ori_g36

model_architecture: LlamaForCausalLM

reward_repo: Jellywibble/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-ori-g36_v2

is_internal_developer: False

language_model: jic062/instruct_v17_ori_g36

model_size: 8B

ranking_group: single

us_pacific_date: 2024-08-05

win_ratio: 0.516479365379167

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', '<|end_of_text|>', '|eot_id|'], '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-ori-g36-v2-mkmlizer
Waiting for job on jic062-instruct-v17-ori-g36-v2-mkmlizer to finish
Stopping job with name jic062-instruct-v17-ori-g36-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name jic062-instruct-v17-ori-g36-v2-mkmlizer
Waiting for job on jic062-instruct-v17-ori-g36-v2-mkmlizer to finish
jic062-instruct-v17-ori-g36-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-instruct-v17-ori-g36-v2-mkmlizer: ║     _____            __           __                                ║
jic062-instruct-v17-ori-g36-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jic062-instruct-v17-ori-g36-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jic062-instruct-v17-ori-g36-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jic062-instruct-v17-ori-g36-v2-mkmlizer: ║       /___/                                                         ║
jic062-instruct-v17-ori-g36-v2-mkmlizer: ║                                                                     ║
jic062-instruct-v17-ori-g36-v2-mkmlizer: ║  Version: 0.9.9                                                     ║
jic062-instruct-v17-ori-g36-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jic062-instruct-v17-ori-g36-v2-mkmlizer: ║  https://mk1.ai                                                     ║
jic062-instruct-v17-ori-g36-v2-mkmlizer: ║                                                                     ║
jic062-instruct-v17-ori-g36-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
jic062-instruct-v17-ori-g36-v2-mkmlizer: ║  belonging to:                                                      ║
jic062-instruct-v17-ori-g36-v2-mkmlizer: ║                                                                     ║
jic062-instruct-v17-ori-g36-v2-mkmlizer: ║  Chai Research Corp.                                                ║
jic062-instruct-v17-ori-g36-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jic062-instruct-v17-ori-g36-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
jic062-instruct-v17-ori-g36-v2-mkmlizer: ║                                                                     ║
jic062-instruct-v17-ori-g36-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jic062-instruct-v17-ori-g36-v2-mkmlizer: Downloaded to shared memory in 22.069s
jic062-instruct-v17-ori-g36-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpnorx69j1, device:0
jic062-instruct-v17-ori-g36-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jic062-instruct-v17-ori-g36-v2-mkmlizer: quantized model in 26.182s
jic062-instruct-v17-ori-g36-v2-mkmlizer: Processed model jic062/instruct_v17_ori_g36 in 48.251s
jic062-instruct-v17-ori-g36-v2-mkmlizer: creating bucket guanaco-mkml-models
jic062-instruct-v17-ori-g36-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-instruct-v17-ori-g36-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-instruct-v17-ori-g36-v2
jic062-instruct-v17-ori-g36-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-instruct-v17-ori-g36-v2/config.json
jic062-instruct-v17-ori-g36-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-instruct-v17-ori-g36-v2/special_tokens_map.json
jic062-instruct-v17-ori-g36-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-instruct-v17-ori-g36-v2/tokenizer_config.json
jic062-instruct-v17-ori-g36-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-instruct-v17-ori-g36-v2/tokenizer.json
jic062-instruct-v17-ori-g36-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-instruct-v17-ori-g36-v2/flywheel_model.0.safetensors
jic062-instruct-v17-ori-g36-v2-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
jic062-instruct-v17-ori-g36-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:06, 47.25it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:04, 63.23it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:03, 70.46it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:03, 75.71it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:03, 79.42it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:02, 81.44it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:02, 78.95it/s]
Loading 0:  24%|██▍       | 70/291 [00:00<00:02, 78.73it/s]
Loading 0:  27%|██▋       | 79/291 [00:01<00:02, 79.24it/s]
Loading 0:  30%|██▉       | 87/291 [00:02<00:09, 20.82it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:07, 25.30it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:05, 31.83it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:04, 38.79it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 45.82it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 51.46it/s]
Loading 0:  48%|████▊     | 139/291 [00:02<00:02, 57.75it/s]
Loading 0:  51%|█████     | 148/291 [00:02<00:02, 62.64it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 66.79it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:01, 69.96it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:01, 70.84it/s]
Loading 0:  63%|██████▎   | 184/291 [00:03<00:01, 70.80it/s]
Loading 0:  66%|██████▌   | 192/291 [00:04<00:04, 21.03it/s]
Loading 0:  68%|██████▊   | 198/291 [00:04<00:03, 24.16it/s]
Loading 0:  70%|███████   | 205/291 [00:04<00:03, 28.57it/s]
Loading 0:  74%|███████▎  | 214/291 [00:04<00:02, 35.32it/s]
Loading 0:  77%|███████▋  | 223/291 [00:05<00:01, 42.97it/s]
Loading 0:  80%|███████▉  | 232/291 [00:05<00:01, 50.18it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:00, 55.32it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 59.62it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 63.32it/s]
Loading 0:  92%|█████████▏| 268/291 [00:05<00:00, 66.46it/s]
Loading 0:  95%|█████████▌| 277/291 [00:05<00:00, 69.03it/s]
Loading 0:  98%|█████████▊| 286/291 [00:05<00:00, 70.03it/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-ori-g36-v2-mkmlizer:   warnings.warn(
jic062-instruct-v17-ori-g36-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-ori-g36-v2-mkmlizer:   warnings.warn(
jic062-instruct-v17-ori-g36-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-ori-g36-v2-mkmlizer:   warnings.warn(
jic062-instruct-v17-ori-g36-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jic062-instruct-v17-ori-g36-v2-mkmlizer: Saving duration: 1.421s
jic062-instruct-v17-ori-g36-v2-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 12.092s
jic062-instruct-v17-ori-g36-v2-mkmlizer: creating bucket guanaco-reward-models
jic062-instruct-v17-ori-g36-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jic062-instruct-v17-ori-g36-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jic062-instruct-v17-ori-g36-v2_reward
jic062-instruct-v17-ori-g36-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jic062-instruct-v17-ori-g36-v2_reward/config.json
jic062-instruct-v17-ori-g36-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jic062-instruct-v17-ori-g36-v2_reward/special_tokens_map.json
jic062-instruct-v17-ori-g36-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jic062-instruct-v17-ori-g36-v2_reward/tokenizer_config.json
jic062-instruct-v17-ori-g36-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jic062-instruct-v17-ori-g36-v2_reward/merges.txt
jic062-instruct-v17-ori-g36-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jic062-instruct-v17-ori-g36-v2_reward/vocab.json
jic062-instruct-v17-ori-g36-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jic062-instruct-v17-ori-g36-v2_reward/tokenizer.json
jic062-instruct-v17-ori-g36-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/jic062-instruct-v17-ori-g36-v2_reward/reward.tensors
Job jic062-instruct-v17-ori-g36-v2-mkmlizer completed after 94.45s with status: succeeded
Stopping job with name jic062-instruct-v17-ori-g36-v2-mkmlizer
Pipeline stage MKMLizer completed in 96.19s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service jic062-instruct-v17-ori-g36-v2
Failed to get response for submission trace2333-fd-llama3-v2-f_5485_v2: ('http://trace2333-fd-llama3-v2-f-5485-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"ValueError : [TypeError(\\"\'numpy.int64\' object is not iterable\\"), TypeError(\'vars() argument must have __dict__ attribute\')]"}')
Waiting for inference service jic062-instruct-v17-ori-g36-v2 to be ready
Inference service jic062-instruct-v17-ori-g36-v2 ready after 181.2334246635437s
Pipeline stage ISVCDeployer completed in 183.22s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2661406993865967s
Received healthy response to inference request in 1.4602563381195068s
Received healthy response to inference request in 1.4450922012329102s
Received healthy response to inference request in 1.4378199577331543s
Received healthy response to inference request in 1.5060491561889648s
5 requests
0 failed requests
5th percentile: 1.4392744064331056
10th percentile: 1.4407288551330566
20th percentile: 1.443637752532959
30th percentile: 1.4481250286102294
40th percentile: 1.4541906833648681
50th percentile: 1.4602563381195068
60th percentile: 1.47857346534729
70th percentile: 1.4968905925750733
80th percentile: 1.6580674648284914
90th percentile: 1.962104082107544
95th percentile: 2.1141223907470703
99th percentile: 2.2357370376586916
mean time: 1.6230716705322266
Pipeline stage StressChecker completed in 8.75s
jic062-instruct-v17-ori-g36_v2 status is now deployed due to DeploymentManager action
jic062-instruct-v17-ori-g36_v2 status is now inactive due to auto deactivation removed underperforming models
jic062-instruct-v17-ori-g36_v2 status is now torndown due to DeploymentManager action