hastagaras-l31-test

developer_uid: Hastagaras

submission_id: hastagaras-l31-test_v1

model_name: 31t

model_group: Hastagaras/l31-test

status: torndown

timestamp: 2024-07-26T07:41:22+00:00

num_battles: 10746

num_wins: 3866

celo_rating: 1103.46

family_friendly_score: 0.0

submission_type: basic

model_repo: Hastagaras/l31-test

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: 31t

is_internal_developer: False

language_model: Hastagaras/l31-test

model_size: 8B

ranking_group: single

us_pacific_date: 2024-07-26

win_ratio: 0.3597617718220733

generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 60, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<|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 hastagaras-l31-test-v1-mkmlizer
Waiting for job on hastagaras-l31-test-v1-mkmlizer to finish
hastagaras-l31-test-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-l31-test-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-l31-test-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-l31-test-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-l31-test-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-l31-test-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-l31-test-v1-mkmlizer: ║                                                                     ║
hastagaras-l31-test-v1-mkmlizer: ║  Version: 0.9.7                                                     ║
hastagaras-l31-test-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-l31-test-v1-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-l31-test-v1-mkmlizer: ║                                                                     ║
hastagaras-l31-test-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-l31-test-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-l31-test-v1-mkmlizer: ║                                                                     ║
hastagaras-l31-test-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-l31-test-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-l31-test-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
hastagaras-l31-test-v1-mkmlizer: ║                                                                     ║
hastagaras-l31-test-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-l31-test-v1-mkmlizer: Downloaded to shared memory in 30.184s
hastagaras-l31-test-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp43bd1z2o, device:0
hastagaras-l31-test-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-l31-test-v1-mkmlizer: quantized model in 25.696s
hastagaras-l31-test-v1-mkmlizer: Processed model Hastagaras/l31-test in 55.880s
hastagaras-l31-test-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-l31-test-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-l31-test-v1/config.json
hastagaras-l31-test-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-l31-test-v1/special_tokens_map.json
hastagaras-l31-test-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-l31-test-v1/tokenizer_config.json
hastagaras-l31-test-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-l31-test-v1/tokenizer.json
hastagaras-l31-test-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-l31-test-v1/flywheel_model.0.safetensors
hastagaras-l31-test-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
hastagaras-l31-test-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:08, 33.48it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:05, 47.19it/s]
Loading 0:   8%|▊         | 23/291 [00:00<00:05, 50.08it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:04, 58.39it/s]
Loading 0:  13%|█▎        | 38/291 [00:00<00:04, 57.57it/s]
Loading 0:  15%|█▌        | 44/291 [00:00<00:04, 57.69it/s]
Loading 0:  17%|█▋        | 50/291 [00:00<00:04, 50.27it/s]
Loading 0:  20%|██        | 59/291 [00:01<00:04, 52.55it/s]
Loading 0:  23%|██▎       | 68/291 [00:01<00:04, 53.94it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:03, 57.70it/s]
Loading 0:  28%|██▊       | 82/291 [00:01<00:03, 53.95it/s]
Loading 0:  30%|███       | 88/291 [00:01<00:05, 37.50it/s]
Loading 0:  33%|███▎      | 95/291 [00:01<00:05, 38.59it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:04, 45.38it/s]
Loading 0:  37%|███▋      | 109/291 [00:02<00:04, 43.86it/s]
Loading 0:  39%|███▉      | 114/291 [00:02<00:03, 44.85it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 50.64it/s]
Loading 0:  44%|████▎     | 127/291 [00:02<00:03, 48.91it/s]
Loading 0:  46%|████▌     | 133/291 [00:02<00:03, 50.19it/s]
Loading 0:  48%|████▊     | 140/291 [00:02<00:03, 46.82it/s]
Loading 0:  51%|█████     | 148/291 [00:02<00:02, 54.06it/s]
Loading 0:  53%|█████▎    | 154/291 [00:03<00:02, 51.26it/s]
Loading 0:  55%|█████▍    | 160/291 [00:03<00:02, 51.53it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:02, 52.55it/s]
Loading 0:  59%|█████▉    | 172/291 [00:03<00:02, 49.56it/s]
Loading 0:  62%|██████▏   | 179/291 [00:03<00:02, 53.92it/s]
Loading 0:  64%|██████▎   | 185/291 [00:03<00:01, 55.25it/s]
Loading 0:  66%|██████▌   | 191/291 [00:04<00:02, 35.75it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:02, 37.61it/s]
Loading 0:  70%|██████▉   | 203/291 [00:04<00:02, 38.95it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:01, 47.27it/s]
Loading 0:  75%|███████▍  | 217/291 [00:04<00:01, 46.46it/s]
Loading 0:  77%|███████▋  | 223/291 [00:04<00:01, 48.94it/s]
Loading 0:  79%|███████▉  | 230/291 [00:04<00:01, 46.51it/s]
Loading 0:  82%|████████▏ | 239/291 [00:04<00:01, 48.96it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:00, 55.57it/s]
Loading 0:  87%|████████▋ | 253/291 [00:05<00:00, 52.31it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 53.24it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 54.66it/s]
Loading 0:  93%|█████████▎| 271/291 [00:05<00:00, 49.05it/s]
Loading 0:  95%|█████████▌| 277/291 [00:05<00:00, 50.78it/s]
Loading 0:  97%|█████████▋| 283/291 [00:05<00:00, 46.02it/s]
Loading 0:  99%|█████████▉| 288/291 [00:11<00:00,  3.37it/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.
hastagaras-l31-test-v1-mkmlizer:   warnings.warn(
hastagaras-l31-test-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.
hastagaras-l31-test-v1-mkmlizer:   warnings.warn(
hastagaras-l31-test-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.
hastagaras-l31-test-v1-mkmlizer:   warnings.warn(
hastagaras-l31-test-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-l31-test-v1-mkmlizer: Saving duration: 1.397s
hastagaras-l31-test-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.717s
hastagaras-l31-test-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-l31-test-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-l31-test-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-l31-test-v1_reward
hastagaras-l31-test-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-l31-test-v1_reward/config.json
hastagaras-l31-test-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-l31-test-v1_reward/special_tokens_map.json
hastagaras-l31-test-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-l31-test-v1_reward/tokenizer_config.json
hastagaras-l31-test-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-l31-test-v1_reward/merges.txt
hastagaras-l31-test-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-l31-test-v1_reward/vocab.json
hastagaras-l31-test-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-l31-test-v1_reward/tokenizer.json
hastagaras-l31-test-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-l31-test-v1_reward/reward.tensors
Job hastagaras-l31-test-v1-mkmlizer completed after 95.68s with status: succeeded
Stopping job with name hastagaras-l31-test-v1-mkmlizer
Pipeline stage MKMLizer completed in 96.66s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-l31-test-v1
Waiting for inference service hastagaras-l31-test-v1 to be ready
Failed to get response for submission hastagaras-l3-dt-prep-test_v5: ('http://hastagaras-l3-dt-prep-test-v5-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:52732->127.0.0.1:8080: read: connection reset by peer\n')
Inference service hastagaras-l31-test-v1 ready after 90.88741564750671s
Pipeline stage ISVCDeployer completed in 91.59s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3460867404937744s
Received healthy response to inference request in 1.2097992897033691s
Received healthy response to inference request in 1.3095715045928955s
Received healthy response to inference request in 1.356389045715332s
Received healthy response to inference request in 1.2048373222351074s
5 requests
0 failed requests
5th percentile: 1.2058297157287599
10th percentile: 1.206822109222412
20th percentile: 1.2088068962097167
30th percentile: 1.2297537326812744
40th percentile: 1.269662618637085
50th percentile: 1.3095715045928955
60th percentile: 1.32829852104187
70th percentile: 1.3470255374908446
80th percentile: 1.5543285846710206
90th percentile: 1.9502076625823976
95th percentile: 2.1481472015380856
99th percentile: 2.3064988327026366
mean time: 1.4853367805480957
Pipeline stage StressChecker completed in 8.07s
hastagaras-l31-test_v1 status is now deployed due to DeploymentManager action
hastagaras-l31-test_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-l31-test_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-l31-test-v1 is running
Tearing down inference service hastagaras-l31-test-v1
Service hastagaras-l31-test-v1 has been torndown
Pipeline stage ISVCDeleter completed in 4.96s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-l31-test-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-l31-test-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-l31-test-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-l31-test-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-l31-test-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-l31-test-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-l31-test-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-l31-test-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-l31-test-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-l31-test-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-l31-test-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-l31-test-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.61s
hastagaras-l31-test_v1 status is now torndown due to DeploymentManager action