submission_id: jic062-instruct-v17-g32-lr1_v2
developer_uid: chace9580
best_of: 16
celo_rating: 1224.6
display_name: jic062-instruct-v17-g32-lr1_v2
family_friendly_score: 0.0
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}
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}
is_internal_developer: False
language_model: jic062/instruct_v17_g32_lr1
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: jic062/instruct_v17_g32_
model_name: jic062-instruct-v17-g32-lr1_v2
model_num_parameters: 8030261248.0
model_repo: jic062/instruct_v17_g32_lr1
model_size: 8B
num_battles: 13465
num_wins: 6846
ranking_group: single
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: Jellywibble/gpt2_xl_pairwise_89m_step_347634
status: torndown
submission_type: basic
timestamp: 2024-08-08T16:30:55+00:00
us_pacific_date: 2024-08-08
win_ratio: 0.5084292610471594
Resubmit model
Running pipeline stage MKMLizer
Starting job with name jic062-instruct-v17-g32-lr1-v2-mkmlizer
Waiting for job on jic062-instruct-v17-g32-lr1-v2-mkmlizer to finish
Stopping job with name jic062-instruct-v17-g32-lr1-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name jic062-instruct-v17-g32-lr1-v2-mkmlizer
Waiting for job on jic062-instruct-v17-g32-lr1-v2-mkmlizer to finish
jic062-instruct-v17-g32-lr1-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-instruct-v17-g32-lr1-v2-mkmlizer: ║ _____ __ __ ║
jic062-instruct-v17-g32-lr1-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
jic062-instruct-v17-g32-lr1-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
jic062-instruct-v17-g32-lr1-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
jic062-instruct-v17-g32-lr1-v2-mkmlizer: ║ /___/ ║
jic062-instruct-v17-g32-lr1-v2-mkmlizer: ║ ║
jic062-instruct-v17-g32-lr1-v2-mkmlizer: ║ Version: 0.9.9 ║
jic062-instruct-v17-g32-lr1-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
jic062-instruct-v17-g32-lr1-v2-mkmlizer: ║ https://mk1.ai ║
jic062-instruct-v17-g32-lr1-v2-mkmlizer: ║ ║
jic062-instruct-v17-g32-lr1-v2-mkmlizer: ║ The license key for the current software has been verified as ║
jic062-instruct-v17-g32-lr1-v2-mkmlizer: ║ belonging to: ║
jic062-instruct-v17-g32-lr1-v2-mkmlizer: ║ ║
jic062-instruct-v17-g32-lr1-v2-mkmlizer: ║ Chai Research Corp. ║
jic062-instruct-v17-g32-lr1-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
jic062-instruct-v17-g32-lr1-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
jic062-instruct-v17-g32-lr1-v2-mkmlizer: ║ ║
jic062-instruct-v17-g32-lr1-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jic062-instruct-v17-g32-lr1-v2-mkmlizer: Downloaded to shared memory in 22.843s
jic062-instruct-v17-g32-lr1-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjxtsnmq1, device:0
jic062-instruct-v17-g32-lr1-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jic062-instruct-v17-g32-lr1-v2-mkmlizer: quantized model in 26.671s
jic062-instruct-v17-g32-lr1-v2-mkmlizer: Processed model jic062/instruct_v17_g32_lr1 in 49.515s
jic062-instruct-v17-g32-lr1-v2-mkmlizer: creating bucket guanaco-mkml-models
jic062-instruct-v17-g32-lr1-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-instruct-v17-g32-lr1-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-instruct-v17-g32-lr1-v2
jic062-instruct-v17-g32-lr1-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-instruct-v17-g32-lr1-v2/config.json
jic062-instruct-v17-g32-lr1-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-instruct-v17-g32-lr1-v2/special_tokens_map.json
jic062-instruct-v17-g32-lr1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-instruct-v17-g32-lr1-v2/tokenizer_config.json
jic062-instruct-v17-g32-lr1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-instruct-v17-g32-lr1-v2/tokenizer.json
jic062-instruct-v17-g32-lr1-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-instruct-v17-g32-lr1-v2/flywheel_model.0.safetensors
jic062-instruct-v17-g32-lr1-v2-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
jic062-instruct-v17-g32-lr1-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 7/291 [00:00<00:05, 49.88it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:04, 63.00it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:04, 65.41it/s] Loading 0: 12%|█▏ | 34/291 [00:00<00:03, 70.62it/s] Loading 0: 15%|█▍ | 43/291 [00:00<00:03, 73.89it/s] Loading 0: 18%|█▊ | 52/291 [00:00<00:03, 74.32it/s] Loading 0: 21%|██ | 61/291 [00:00<00:03, 76.25it/s] Loading 0: 24%|██▍ | 70/291 [00:00<00:02, 78.41it/s] Loading 0: 27%|██▋ | 79/291 [00:01<00:02, 79.06it/s] Loading 0: 30%|██▉ | 87/291 [00:02<00:10, 20.32it/s] Loading 0: 32%|███▏ | 94/291 [00:02<00:07, 24.83it/s] Loading 0: 35%|███▌ | 103/291 [00:02<00:05, 31.65it/s] Loading 0: 38%|███▊ | 112/291 [00:02<00:04, 38.92it/s] Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 44.93it/s] Loading 0: 45%|████▍ | 130/291 [00:02<00:03, 51.27it/s] Loading 0: 48%|████▊ | 139/291 [00:02<00:02, 57.34it/s] Loading 0: 51%|█████ | 148/291 [00:03<00:02, 62.47it/s] Loading 0: 54%|█████▍ | 157/291 [00:03<00:01, 67.61it/s] Loading 0: 57%|█████▋ | 166/291 [00:03<00:01, 71.59it/s] Loading 0: 60%|██████ | 175/291 [00:03<00:01, 74.97it/s] Loading 0: 63%|██████▎ | 184/291 [00:03<00:01, 75.22it/s] Loading 0: 66%|██████▌ | 192/291 [00:04<00:04, 20.80it/s] Loading 0: 68%|██████▊ | 198/291 [00:04<00:03, 24.42it/s] Loading 0: 70%|███████ | 205/291 [00:04<00:02, 29.28it/s] Loading 0: 74%|███████▎ | 214/291 [00:04<00:02, 37.03it/s] Loading 0: 77%|███████▋ | 223/291 [00:05<00:01, 45.23it/s] Loading 0: 80%|███████▉ | 232/291 [00:05<00:01, 52.62it/s] Loading 0: 83%|████████▎ | 241/291 [00:05<00:00, 59.38it/s] Loading 0: 86%|████████▌ | 250/291 [00:05<00:00, 60.61it/s] Loading 0: 89%|████████▉ | 259/291 [00:05<00:00, 66.22it/s] Loading 0: 92%|█████████▏| 268/291 [00:05<00:00, 70.96it/s] Loading 0: 95%|█████████▌| 277/291 [00:05<00:00, 72.48it/s] Loading 0: 98%|█████████▊| 286/291 [00:05<00:00, 73.32it/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-g32-lr1-v2-mkmlizer: warnings.warn(
jic062-instruct-v17-g32-lr1-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-g32-lr1-v2-mkmlizer: warnings.warn(
jic062-instruct-v17-g32-lr1-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-g32-lr1-v2-mkmlizer: warnings.warn(
jic062-instruct-v17-g32-lr1-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jic062-instruct-v17-g32-lr1-v2-mkmlizer: Saving duration: 1.390s
jic062-instruct-v17-g32-lr1-v2-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 13.228s
jic062-instruct-v17-g32-lr1-v2-mkmlizer: creating bucket guanaco-reward-models
jic062-instruct-v17-g32-lr1-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jic062-instruct-v17-g32-lr1-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jic062-instruct-v17-g32-lr1-v2_reward
jic062-instruct-v17-g32-lr1-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jic062-instruct-v17-g32-lr1-v2_reward/config.json
jic062-instruct-v17-g32-lr1-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jic062-instruct-v17-g32-lr1-v2_reward/special_tokens_map.json
jic062-instruct-v17-g32-lr1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jic062-instruct-v17-g32-lr1-v2_reward/tokenizer_config.json
jic062-instruct-v17-g32-lr1-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jic062-instruct-v17-g32-lr1-v2_reward/merges.txt
jic062-instruct-v17-g32-lr1-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jic062-instruct-v17-g32-lr1-v2_reward/vocab.json
jic062-instruct-v17-g32-lr1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jic062-instruct-v17-g32-lr1-v2_reward/tokenizer.json
jic062-instruct-v17-g32-lr1-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/jic062-instruct-v17-g32-lr1-v2_reward/reward.tensors
Job jic062-instruct-v17-g32-lr1-v2-mkmlizer completed after 94.42s with status: succeeded
Stopping job with name jic062-instruct-v17-g32-lr1-v2-mkmlizer
Pipeline stage MKMLizer completed in 96.11s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service jic062-instruct-v17-g32-lr1-v2
Waiting for inference service jic062-instruct-v17-g32-lr1-v2 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service jic062-instruct-v17-g32-lr1-v2 ready after 201.41478419303894s
Pipeline stage ISVCDeployer completed in 202.98s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.307539701461792s
Received healthy response to inference request in 1.8850574493408203s
Received healthy response to inference request in 1.4427814483642578s
Received healthy response to inference request in 1.4870145320892334s
Failed to get response for submission jic062-instruct-v17-g32-lr1_v1: ('http://jic062-instruct-v17-g32-lr1-v1-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\')]"}')
Received healthy response to inference request in 1.507467269897461s
5 requests
0 failed requests
5th percentile: 1.451628065109253
10th percentile: 1.460474681854248
20th percentile: 1.4781679153442382
30th percentile: 1.491105079650879
40th percentile: 1.49928617477417
50th percentile: 1.507467269897461
60th percentile: 1.6585033416748047
70th percentile: 1.8095394134521483
80th percentile: 1.9695538997650148
90th percentile: 2.1385468006134034
95th percentile: 2.2230432510375975
99th percentile: 2.290640411376953
mean time: 1.7259720802307128
Failed to get response for submission jic062-instruct-v17-g32-lr1_v1: ('http://jic062-instruct-v17-g32-lr1-v1-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\')]"}')
Pipeline stage StressChecker completed in 9.40s
jic062-instruct-v17-g32-lr1_v2 status is now deployed due to DeploymentManager action
jic062-instruct-v17-g32-lr1_v2 status is now inactive due to auto deactivation removed underperforming models
jic062-instruct-v17-g32-lr1_v2 status is now torndown due to DeploymentManager action