developer_uid: Trace2333
submission_id: trace2333-duduk-llama2-v0_v3
model_name: trace2333-duduk-llama2-v0_v2
model_group: Trace2333/duduk_llama2_v
status: torndown
timestamp: 2024-07-04T08:45:30+00:00
num_battles: 16602
num_wins: 7054
celo_rating: 1133.07
family_friendly_score: 0.0
submission_type: basic
model_repo: Trace2333/duduk_llama2_v0
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 6738415616.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
display_name: trace2333-duduk-llama2-v0_v2
is_internal_developer: False
language_model: Trace2333/duduk_llama2_v0
model_size: 7B
ranking_group: single
us_pacific_date: 2024-07-04
win_ratio: 0.4248885676424527
generation_params: {'temperature': 1.15, 'top_p': 1.0, 'min_p': 0.12, 'top_k': 200, 'presence_penalty': 0.2, 'frequency_penalty': 0.3, 'stopping_words': ['</s>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona####: {memory}", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': 'You: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': True}
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 trace2333-duduk-llama2-v0-v3-mkmlizer
Waiting for job on trace2333-duduk-llama2-v0-v3-mkmlizer to finish
trace2333-duduk-llama2-v0-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-duduk-llama2-v0-v3-mkmlizer: ║     _____            __           __                                ║
trace2333-duduk-llama2-v0-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-duduk-llama2-v0-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-duduk-llama2-v0-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-duduk-llama2-v0-v3-mkmlizer: ║       /___/                                                         ║
trace2333-duduk-llama2-v0-v3-mkmlizer: ║                                                                     ║
trace2333-duduk-llama2-v0-v3-mkmlizer: ║  Version: 0.8.14                                                    ║
trace2333-duduk-llama2-v0-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-duduk-llama2-v0-v3-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-duduk-llama2-v0-v3-mkmlizer: ║                                                                     ║
trace2333-duduk-llama2-v0-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-duduk-llama2-v0-v3-mkmlizer: ║  belonging to:                                                      ║
trace2333-duduk-llama2-v0-v3-mkmlizer: ║                                                                     ║
trace2333-duduk-llama2-v0-v3-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-duduk-llama2-v0-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-duduk-llama2-v0-v3-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
trace2333-duduk-llama2-v0-v3-mkmlizer: ║                                                                     ║
trace2333-duduk-llama2-v0-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-duduk-llama2-v0-v3-mkmlizer: Downloaded to shared memory in 38.473s
trace2333-duduk-llama2-v0-v3-mkmlizer: quantizing model to /dev/shm/model_cache
trace2333-duduk-llama2-v0-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-duduk-llama2-v0-v3-mkmlizer: quantized model in 19.208s
trace2333-duduk-llama2-v0-v3-mkmlizer: Processed model Trace2333/duduk_llama2_v0 in 57.682s
trace2333-duduk-llama2-v0-v3-mkmlizer: creating bucket guanaco-mkml-models
trace2333-duduk-llama2-v0-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-duduk-llama2-v0-v3/tokenizer.json
trace2333-duduk-llama2-v0-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-duduk-llama2-v0-v3/flywheel_model.0.safetensors
trace2333-duduk-llama2-v0-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
trace2333-duduk-llama2-v0-v3-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   3%|▎         | 8/291 [00:00<00:03, 73.03it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:03, 71.17it/s]
Loading 0:   8%|▊         | 24/291 [00:00<00:03, 69.86it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:03, 67.28it/s]
Loading 0:  14%|█▍        | 41/291 [00:00<00:03, 68.59it/s]
Loading 0:  18%|█▊        | 51/291 [00:00<00:05, 43.93it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:05, 45.24it/s]
Loading 0:  23%|██▎       | 66/291 [00:01<00:04, 52.30it/s]
Loading 0:  25%|██▍       | 72/291 [00:01<00:04, 44.83it/s]
Loading 0:  28%|██▊       | 81/291 [00:01<00:04, 51.45it/s]
Loading 0:  31%|███       | 90/291 [00:01<00:03, 56.85it/s]
Loading 0:  34%|███▍      | 99/291 [00:01<00:03, 60.75it/s]
Loading 0:  36%|███▋      | 106/291 [00:02<00:04, 39.84it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:04, 42.41it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 49.08it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:02, 54.67it/s]
Loading 0:  48%|████▊     | 139/291 [00:02<00:02, 58.97it/s]
Loading 0:  51%|█████     | 147/291 [00:02<00:02, 63.56it/s]
Loading 0:  53%|█████▎    | 154/291 [00:02<00:02, 64.64it/s]
Loading 0:  55%|█████▌    | 161/291 [00:03<00:03, 41.14it/s]
Loading 0:  57%|█████▋    | 167/291 [00:03<00:02, 43.64it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:02, 50.94it/s]
Loading 0:  63%|██████▎   | 183/291 [00:03<00:01, 57.33it/s]
Loading 0:  66%|██████▌   | 192/291 [00:03<00:01, 61.12it/s]
Loading 0:  68%|██████▊   | 199/291 [00:03<00:01, 62.88it/s]
Loading 0:  71%|███████   | 206/291 [00:03<00:01, 62.78it/s]
Loading 0:  73%|███████▎  | 213/291 [00:04<00:01, 41.33it/s]
Loading 0:  75%|███████▌  | 219/291 [00:04<00:01, 37.06it/s]
Loading 0:  77%|███████▋  | 224/291 [00:04<00:02, 32.05it/s]
Loading 0:  78%|███████▊  | 228/291 [00:04<00:02, 21.35it/s]
Loading 0:  79%|███████▉  | 231/291 [00:05<00:04, 14.78it/s]
Loading 0:  80%|████████  | 234/291 [00:05<00:04, 13.87it/s]
Loading 0:  81%|████████▏ | 237/291 [00:06<00:04, 12.30it/s]
Loading 0:  82%|████████▏ | 239/291 [00:06<00:05,  9.81it/s]
Loading 0:  83%|████████▎ | 242/291 [00:06<00:04, 11.13it/s]
Loading 0:  84%|████████▍ | 244/291 [00:06<00:04, 11.19it/s]
Loading 0:  85%|████████▍ | 246/291 [00:06<00:04, 11.24it/s]
Loading 0:  85%|████████▌ | 248/291 [00:07<00:03, 10.89it/s]
Loading 0:  88%|████████▊ | 257/291 [00:07<00:01, 22.92it/s]
Loading 0:  92%|█████████▏| 267/291 [00:09<00:02,  9.38it/s]
Loading 0:  94%|█████████▍| 274/291 [00:09<00:01, 13.14it/s]
Loading 0:  97%|█████████▋| 283/291 [00:09<00:00, 19.24it/s]
                                                            
/opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
trace2333-duduk-llama2-v0-v3-mkmlizer:   warnings.warn(
trace2333-duduk-llama2-v0-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
trace2333-duduk-llama2-v0-v3-mkmlizer:   warnings.warn(
trace2333-duduk-llama2-v0-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
trace2333-duduk-llama2-v0-v3-mkmlizer:   warnings.warn(
trace2333-duduk-llama2-v0-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:468: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
trace2333-duduk-llama2-v0-v3-mkmlizer:   warnings.warn(
Job trace2333-duduk-llama2-v0-v3-mkmlizer completed after 102.36s with status: succeeded
Stopping job with name trace2333-duduk-llama2-v0-v3-mkmlizer
Pipeline stage MKMLizer completed in 103.38s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-duduk-llama2-v0-v3
Waiting for inference service trace2333-duduk-llama2-v0-v3 to be ready
Inference service trace2333-duduk-llama2-v0-v3 ready after 100.51822972297668s
Pipeline stage ISVCDeployer completed in 107.51s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9521467685699463s
Received healthy response to inference request in 1.1395745277404785s
Received healthy response to inference request in 1.1719861030578613s
Received healthy response to inference request in 1.191608190536499s
Received healthy response to inference request in 1.1909160614013672s
5 requests
0 failed requests
5th percentile: 1.146056842803955
10th percentile: 1.1525391578674316
20th percentile: 1.1655037879943848
30th percentile: 1.1757720947265624
40th percentile: 1.1833440780639648
50th percentile: 1.1909160614013672
60th percentile: 1.19119291305542
70th percentile: 1.1914697647094727
80th percentile: 1.3437159061431887
90th percentile: 1.6479313373565674
95th percentile: 1.8000390529632566
99th percentile: 1.9217252254486084
mean time: 1.3292463302612305
Pipeline stage StressChecker completed in 7.36s
trace2333-duduk-llama2-v0_v3 status is now deployed due to DeploymentManager action
trace2333-duduk-llama2-v0_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of trace2333-duduk-llama2-v0_v3
Running pipeline stage ISVCDeleter
Checking if service trace2333-duduk-llama2-v0-v3 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.01s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key trace2333-duduk-llama2-v0-v3/config.json from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama2-v0-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama2-v0-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama2-v0-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama2-v0-v3/tokenizer.model from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama2-v0-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key trace2333-duduk-llama2-v0-v3_reward/config.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama2-v0-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama2-v0-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama2-v0-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama2-v0-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama2-v0-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama2-v0-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.34s
trace2333-duduk-llama2-v0_v3 status is now torndown due to DeploymentManager action