jic062-instruct-dp7-lr1-g32

developer_uid: chace9580

submission_id: jic062-instruct-dp7-lr1-g32_v4

model_name: jic062-instruct-dp7-lr1-g32_v4

model_group: jic062/instruct_dp7_lr1_

status: torndown

timestamp: 2024-08-12T23:12:50+00:00

num_battles: 11328

num_wins: 5760

celo_rating: 1229.3

family_friendly_score: 0.0

submission_type: basic

model_repo: jic062/instruct_dp7_lr1_g32

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-dp7-lr1-g32_v4

is_internal_developer: False

language_model: jic062/instruct_dp7_lr1_g32

model_size: 8B

ranking_group: single

us_pacific_date: 2024-08-12

win_ratio: 0.5084745762711864

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-dp7-lr1-g32-v4-mkmlizer
Waiting for job on jic062-instruct-dp7-lr1-g32-v4-mkmlizer to finish
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: ║     _____            __           __                                ║
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: ║       /___/                                                         ║
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: ║                                                                     ║
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: ║  Version: 0.9.9                                                     ║
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: ║  https://mk1.ai                                                     ║
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: ║                                                                     ║
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: ║  belonging to:                                                      ║
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: ║                                                                     ║
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: ║  Chai Research Corp.                                                ║
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: ║                                                                     ║
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: Downloaded to shared memory in 25.305s
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_zjapmq8, device:0
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: quantized model in 26.431s
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: Processed model jic062/instruct_dp7_lr1_g32 in 51.736s
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: creating bucket guanaco-mkml-models
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-instruct-dp7-lr1-g32-v4
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-instruct-dp7-lr1-g32-v4/special_tokens_map.json
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-instruct-dp7-lr1-g32-v4/config.json
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-instruct-dp7-lr1-g32-v4/tokenizer_config.json
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-instruct-dp7-lr1-g32-v4/tokenizer.json
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-instruct-dp7-lr1-g32-v4/flywheel_model.0.safetensors
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 52.77it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:03, 83.14it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:02, 89.41it/s]
Loading 0:  14%|█▍        | 42/291 [00:00<00:02, 90.75it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:03, 78.92it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:02, 80.58it/s]
Loading 0:  24%|██▍       | 70/291 [00:00<00:02, 80.75it/s]
Loading 0:  27%|██▋       | 79/291 [00:00<00:02, 82.02it/s]
Loading 0:  30%|███       | 88/291 [00:02<00:09, 20.51it/s]
Loading 0:  33%|███▎      | 97/291 [00:02<00:07, 26.30it/s]
Loading 0:  36%|███▋      | 106/291 [00:02<00:05, 33.04it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:04, 40.30it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:03, 47.87it/s]
Loading 0:  46%|████▌     | 133/291 [00:02<00:02, 53.37it/s]
Loading 0:  49%|████▉     | 142/291 [00:02<00:02, 59.27it/s]
Loading 0:  52%|█████▏    | 151/291 [00:02<00:02, 65.28it/s]
Loading 0:  55%|█████▍    | 160/291 [00:03<00:01, 70.09it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:01, 73.54it/s]
Loading 0:  61%|██████    | 178/291 [00:03<00:01, 74.93it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:04, 20.91it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:03, 27.08it/s]
Loading 0:  70%|███████   | 205/291 [00:04<00:02, 34.24it/s]
Loading 0:  74%|███████▎  | 214/291 [00:04<00:01, 41.98it/s]
Loading 0:  77%|███████▋  | 224/291 [00:04<00:01, 51.47it/s]
Loading 0:  80%|████████  | 233/291 [00:04<00:00, 58.03it/s]
Loading 0:  83%|████████▎ | 242/291 [00:05<00:00, 63.79it/s]
Loading 0:  86%|████████▋ | 251/291 [00:05<00:00, 66.43it/s]
Loading 0:  89%|████████▉ | 260/291 [00:05<00:00, 70.85it/s]
Loading 0:  92%|█████████▏| 269/291 [00:05<00:00, 74.14it/s]
Loading 0:  96%|█████████▌| 278/291 [00:05<00:00, 78.19it/s]
Loading 0:  99%|█████████▊| 287/291 [00:05<00:00, 42.72it/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-dp7-lr1-g32-v4-mkmlizer:   warnings.warn(
jic062-instruct-dp7-lr1-g32-v4-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-dp7-lr1-g32-v4-mkmlizer:   warnings.warn(
jic062-instruct-dp7-lr1-g32-v4-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-dp7-lr1-g32-v4-mkmlizer:   warnings.warn(
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: Saving duration: 1.441s
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.488s
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jic062-instruct-dp7-lr1-g32-v4_reward
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jic062-instruct-dp7-lr1-g32-v4_reward/config.json
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jic062-instruct-dp7-lr1-g32-v4_reward/special_tokens_map.json
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jic062-instruct-dp7-lr1-g32-v4_reward/tokenizer_config.json
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jic062-instruct-dp7-lr1-g32-v4_reward/merges.txt
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jic062-instruct-dp7-lr1-g32-v4_reward/vocab.json
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jic062-instruct-dp7-lr1-g32-v4_reward/tokenizer.json
jic062-instruct-dp7-lr1-g32-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/jic062-instruct-dp7-lr1-g32-v4_reward/reward.tensors
Job jic062-instruct-dp7-lr1-g32-v4-mkmlizer completed after 105.25s with status: succeeded
Stopping job with name jic062-instruct-dp7-lr1-g32-v4-mkmlizer
Pipeline stage MKMLizer completed in 106.37s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service jic062-instruct-dp7-lr1-g32-v4
Waiting for inference service jic062-instruct-dp7-lr1-g32-v4 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service jic062-instruct-dp7-lr1-g32-v4 ready after 211.47242259979248s
Pipeline stage ISVCDeployer completed in 213.13s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4742276668548584s
Received healthy response to inference request in 1.4875383377075195s
Received healthy response to inference request in 1.5007562637329102s
Received healthy response to inference request in 1.477867603302002s
Received healthy response to inference request in 1.5174388885498047s
5 requests
0 failed requests
5th percentile: 1.4798017501831056
10th percentile: 1.481735897064209
20th percentile: 1.485604190826416
30th percentile: 1.4901819229125977
40th percentile: 1.495469093322754
50th percentile: 1.5007562637329102
60th percentile: 1.507429313659668
70th percentile: 1.5141023635864257
80th percentile: 1.7087966442108156
90th percentile: 2.091512155532837
95th percentile: 2.2828699111938473
99th percentile: 2.4359561157226564
mean time: 1.691565752029419
Pipeline stage StressChecker completed in 9.23s
jic062-instruct-dp7-lr1-g32_v4 status is now deployed due to DeploymentManager action
jic062-instruct-dp7-lr1-g32_v4 status is now inactive due to auto deactivation removed underperforming models
jic062-instruct-dp7-lr1-g32_v4 status is now torndown due to DeploymentManager action