jic062-instruct-v16

developer_uid: chace9580

submission_id: jic062-instruct-v16_v1

model_name: jic062-instruct-v16_v1

model_group: jic062/instruct_v16

status: torndown

timestamp: 2024-08-01T22:47:05+00:00

num_battles: 10310

num_wins: 5597

celo_rating: 1228.63

family_friendly_score: 0.0

submission_type: basic

model_repo: jic062/instruct_v16

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-v16_v1

is_internal_developer: False

language_model: jic062/instruct_v16

model_size: 8B

ranking_group: single

us_pacific_date: 2024-08-01

win_ratio: 0.5428709990300679

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': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{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-v16-v1-mkmlizer
Waiting for job on jic062-instruct-v16-v1-mkmlizer to finish
jic062-instruct-v16-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-instruct-v16-v1-mkmlizer: ║     _____            __           __                                ║
jic062-instruct-v16-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jic062-instruct-v16-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jic062-instruct-v16-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jic062-instruct-v16-v1-mkmlizer: ║       /___/                                                         ║
jic062-instruct-v16-v1-mkmlizer: ║                                                                     ║
jic062-instruct-v16-v1-mkmlizer: ║  Version: 0.9.7                                                     ║
jic062-instruct-v16-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jic062-instruct-v16-v1-mkmlizer: ║  https://mk1.ai                                                     ║
jic062-instruct-v16-v1-mkmlizer: ║                                                                     ║
jic062-instruct-v16-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
jic062-instruct-v16-v1-mkmlizer: ║  belonging to:                                                      ║
jic062-instruct-v16-v1-mkmlizer: ║                                                                     ║
jic062-instruct-v16-v1-mkmlizer: ║  Chai Research Corp.                                                ║
jic062-instruct-v16-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jic062-instruct-v16-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
jic062-instruct-v16-v1-mkmlizer: ║                                                                     ║
jic062-instruct-v16-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jic062-instruct-v16-v1-mkmlizer: Downloaded to shared memory in 32.313s
jic062-instruct-v16-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp73tp4o7v, device:0
jic062-instruct-v16-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
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
jic062-instruct-v16-v1-mkmlizer: quantized model in 25.886s
jic062-instruct-v16-v1-mkmlizer: Processed model jic062/instruct_v16 in 58.199s
jic062-instruct-v16-v1-mkmlizer: creating bucket guanaco-mkml-models
jic062-instruct-v16-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-instruct-v16-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-instruct-v16-v1
jic062-instruct-v16-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-instruct-v16-v1/config.json
jic062-instruct-v16-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-instruct-v16-v1/special_tokens_map.json
jic062-instruct-v16-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-instruct-v16-v1/tokenizer_config.json
jic062-instruct-v16-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-instruct-v16-v1/tokenizer.json
jic062-instruct-v16-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-instruct-v16-v1/flywheel_model.0.safetensors
jic062-instruct-v16-v1-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
jic062-instruct-v16-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 52.08it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:04, 61.80it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:03, 69.43it/s]
Loading 0:  12%|█▏        | 35/291 [00:00<00:03, 79.95it/s]
Loading 0:  15%|█▌        | 44/291 [00:00<00:03, 80.99it/s]
Loading 0:  18%|█▊        | 53/291 [00:00<00:02, 81.70it/s]
Loading 0:  21%|██▏       | 62/291 [00:00<00:02, 83.72it/s]
Loading 0:  26%|██▌       | 76/291 [00:00<00:02, 86.87it/s]
Loading 0:  29%|██▉       | 85/291 [00:02<00:09, 22.51it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:07, 27.29it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:05, 33.14it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:04, 39.21it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 45.17it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 50.43it/s]
Loading 0:  48%|████▊     | 139/291 [00:02<00:02, 55.70it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:02, 60.41it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 65.96it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:01, 67.91it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:01, 68.55it/s]
Loading 0:  63%|██████▎   | 184/291 [00:03<00:01, 68.57it/s]
Loading 0:  66%|██████▌   | 192/291 [00:04<00:04, 20.77it/s]
Loading 0:  68%|██████▊   | 198/291 [00:04<00:03, 23.77it/s]
Loading 0:  70%|███████   | 205/291 [00:04<00:03, 28.15it/s]
Loading 0:  74%|███████▎  | 214/291 [00:04<00:02, 36.45it/s]
Loading 0:  77%|███████▋  | 223/291 [00:05<00:01, 44.19it/s]
Loading 0:  80%|███████▉  | 232/291 [00:05<00:01, 49.60it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:00, 54.45it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 58.55it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 58.82it/s]
Loading 0:  92%|█████████▏| 268/291 [00:05<00:00, 62.17it/s]
Loading 0:  95%|█████████▌| 277/291 [00:05<00:00, 64.73it/s]
Loading 0:  98%|█████████▊| 286/291 [00:06<00:00, 65.95it/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-v16-v1-mkmlizer:   warnings.warn(
jic062-instruct-v16-v1-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-v16-v1-mkmlizer:   warnings.warn(
jic062-instruct-v16-v1-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-v16-v1-mkmlizer:   warnings.warn(
jic062-instruct-v16-v1-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:05<00:05,  5.76s/it]
Downloading shards: 100%|██████████| 2/2 [00:09<00:00,  4.41s/it]
Downloading shards: 100%|██████████| 2/2 [00:09<00:00,  4.61s/it]
jic062-instruct-v16-v1-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  2.46it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  4.08it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.71it/s]
jic062-instruct-v16-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jic062-instruct-v16-v1-mkmlizer: Saving duration: 1.360s
jic062-instruct-v16-v1-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 14.494s
jic062-instruct-v16-v1-mkmlizer: creating bucket guanaco-reward-models
jic062-instruct-v16-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jic062-instruct-v16-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jic062-instruct-v16-v1_reward
jic062-instruct-v16-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jic062-instruct-v16-v1_reward/config.json
jic062-instruct-v16-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jic062-instruct-v16-v1_reward/tokenizer_config.json
jic062-instruct-v16-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jic062-instruct-v16-v1_reward/special_tokens_map.json
jic062-instruct-v16-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jic062-instruct-v16-v1_reward/merges.txt
jic062-instruct-v16-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jic062-instruct-v16-v1_reward/vocab.json
jic062-instruct-v16-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jic062-instruct-v16-v1_reward/tokenizer.json
jic062-instruct-v16-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/jic062-instruct-v16-v1_reward/reward.tensors
Job jic062-instruct-v16-v1-mkmlizer completed after 105.8s with status: succeeded
Stopping job with name jic062-instruct-v16-v1-mkmlizer
Pipeline stage MKMLizer completed in 106.80s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service jic062-instruct-v16-v1
Waiting for inference service jic062-instruct-v16-v1 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
Inference service jic062-instruct-v16-v1 ready after 130.95464396476746s
Pipeline stage ISVCDeployer completed in 132.53s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1864349842071533s
Received healthy response to inference request in 1.4169273376464844s
Received healthy response to inference request in 1.400320053100586s
Received healthy response to inference request in 1.4046282768249512s
Received healthy response to inference request in 1.4137952327728271s
5 requests
0 failed requests
5th percentile: 1.401181697845459
10th percentile: 1.402043342590332
20th percentile: 1.4037666320800781
30th percentile: 1.4064616680145263
40th percentile: 1.4101284503936768
50th percentile: 1.4137952327728271
60th percentile: 1.41504807472229
70th percentile: 1.4163009166717528
80th percentile: 1.5708288669586183
90th percentile: 1.8786319255828858
95th percentile: 2.0325334548950194
99th percentile: 2.1556546783447263
mean time: 1.5644211769104004
Pipeline stage StressChecker completed in 8.50s
jic062-instruct-v16_v1 status is now deployed due to DeploymentManager action
jic062-instruct-v16_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of jic062-instruct-v16_v1
Running pipeline stage ISVCDeleter
Checking if service jic062-instruct-v16-v1 is running
Tearing down inference service jic062-instruct-v16-v1
Service jic062-instruct-v16-v1 has been torndown
Pipeline stage ISVCDeleter completed in 5.09s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key jic062-instruct-v16-v1/config.json from bucket guanaco-mkml-models
Deleting key jic062-instruct-v16-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key jic062-instruct-v16-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key jic062-instruct-v16-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key jic062-instruct-v16-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key jic062-instruct-v16-v1_reward/config.json from bucket guanaco-reward-models
Deleting key jic062-instruct-v16-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key jic062-instruct-v16-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key jic062-instruct-v16-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key jic062-instruct-v16-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key jic062-instruct-v16-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key jic062-instruct-v16-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.41s
jic062-instruct-v16_v1 status is now torndown due to DeploymentManager action