trace2333-aug-llama3-v1

developer_uid: Trace2333

submission_id: trace2333-aug-llama3-v1_v5

model_name: trace2333-aug-llama3-v1_v5

model_group: Trace2333/aug_llama3_v1

status: torndown

timestamp: 2024-07-24T05:17:17+00:00

num_battles: 23639

num_wins: 10636

celo_rating: 1152.21

family_friendly_score: 0.0

submission_type: basic

model_repo: Trace2333/aug_llama3_v1

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: trace2333-aug-llama3-v1_v5

is_internal_developer: False

language_model: Trace2333/aug_llama3_v1

model_size: 8B

ranking_group: single

us_pacific_date: 2024-07-23

win_ratio: 0.44993443039045644

generation_params: {'temperature': 1.05, 'top_p': 1.0, 'min_p': 0.15, 'top_k': 200, 'presence_penalty': 0.1, 'frequency_penalty': 0.1, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64, 'reward_max_token_input': 256}

formatter: {'memory_template': "<|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\nYou: {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 trace2333-aug-llama3-v1-v5-mkmlizer
Waiting for job on trace2333-aug-llama3-v1-v5-mkmlizer to finish
trace2333-aug-llama3-v1-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-aug-llama3-v1-v5-mkmlizer: ║     _____            __           __                                ║
trace2333-aug-llama3-v1-v5-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-aug-llama3-v1-v5-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-aug-llama3-v1-v5-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-aug-llama3-v1-v5-mkmlizer: ║       /___/                                                         ║
trace2333-aug-llama3-v1-v5-mkmlizer: ║                                                                     ║
trace2333-aug-llama3-v1-v5-mkmlizer: ║  Version: 0.9.6                                                     ║
trace2333-aug-llama3-v1-v5-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-aug-llama3-v1-v5-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-aug-llama3-v1-v5-mkmlizer: ║                                                                     ║
trace2333-aug-llama3-v1-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-aug-llama3-v1-v5-mkmlizer: ║  belonging to:                                                      ║
trace2333-aug-llama3-v1-v5-mkmlizer: ║                                                                     ║
trace2333-aug-llama3-v1-v5-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-aug-llama3-v1-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-aug-llama3-v1-v5-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
trace2333-aug-llama3-v1-v5-mkmlizer: ║                                                                     ║
trace2333-aug-llama3-v1-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-aug-llama3-v1-v5-mkmlizer: Downloaded to shared memory in 40.395s
trace2333-aug-llama3-v1-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmps3o9i2di, device:0
trace2333-aug-llama3-v1-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-aug-llama3-v1-v5-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:11, 25.52it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:08, 34.60it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:08, 32.06it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:07, 34.54it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:08, 32.00it/s]
Loading 0:  10%|█         | 30/291 [00:00<00:07, 35.71it/s]
Loading 0:  12%|█▏        | 34/291 [00:01<00:10, 24.23it/s]
Loading 0:  13%|█▎        | 37/291 [00:01<00:10, 23.82it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:10, 23.76it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:07, 30.69it/s]
Loading 0:  18%|█▊        | 52/291 [00:01<00:07, 30.14it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:07, 32.64it/s]
Loading 0:  21%|██        | 61/291 [00:02<00:07, 31.61it/s]
Loading 0:  23%|██▎       | 66/291 [00:02<00:06, 34.06it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:06, 32.56it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:06, 32.32it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:06, 32.22it/s]
Loading 0:  28%|██▊       | 82/291 [00:02<00:09, 22.31it/s]
Loading 0:  29%|██▉       | 85/291 [00:02<00:08, 23.71it/s]
Loading 0:  31%|███       | 90/291 [00:03<00:07, 28.25it/s]
Loading 0:  32%|███▏      | 94/291 [00:03<00:06, 29.15it/s]
Loading 0:  34%|███▍      | 99/291 [00:03<00:05, 33.32it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:05, 32.38it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:05, 35.71it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:05, 34.47it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:05, 34.18it/s]
Loading 0:  42%|████▏     | 122/291 [00:03<00:04, 38.70it/s]
Loading 0:  44%|████▎     | 127/291 [00:04<00:04, 36.77it/s]
Loading 0:  46%|████▌     | 133/291 [00:04<00:04, 31.63it/s]
Loading 0:  47%|████▋     | 137/291 [00:04<00:04, 31.23it/s]
Loading 0:  48%|████▊     | 141/291 [00:04<00:05, 28.88it/s]
Loading 0:  51%|█████     | 147/291 [00:04<00:04, 33.64it/s]
Loading 0:  52%|█████▏    | 151/291 [00:04<00:04, 32.55it/s]
Loading 0:  54%|█████▎    | 156/291 [00:04<00:03, 35.62it/s]
Loading 0:  55%|█████▍    | 160/291 [00:05<00:03, 34.62it/s]
Loading 0:  57%|█████▋    | 165/291 [00:05<00:03, 37.18it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 35.51it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 38.09it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 36.42it/s]
Loading 0:  63%|██████▎   | 184/291 [00:05<00:02, 42.13it/s]
Loading 0:  65%|██████▍   | 189/291 [00:06<00:03, 25.66it/s]
Loading 0:  67%|██████▋   | 194/291 [00:06<00:03, 27.04it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:02, 33.47it/s]
Loading 0:  70%|███████   | 205/291 [00:06<00:02, 33.03it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 35.42it/s]
Loading 0:  74%|███████▎  | 214/291 [00:06<00:02, 34.31it/s]
Loading 0:  75%|███████▌  | 219/291 [00:06<00:01, 36.78it/s]
Loading 0:  77%|███████▋  | 223/291 [00:06<00:01, 35.48it/s]
Loading 0:  78%|███████▊  | 227/291 [00:07<00:01, 34.10it/s]
Loading 0:  79%|███████▉  | 231/291 [00:07<00:01, 34.53it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 26.13it/s]
Loading 0:  82%|████████▏ | 239/291 [00:07<00:01, 26.04it/s]
Loading 0:  85%|████████▍ | 246/291 [00:07<00:01, 34.16it/s]
Loading 0:  86%|████████▌ | 250/291 [00:07<00:01, 33.87it/s]
Loading 0:  88%|████████▊ | 255/291 [00:07<00:00, 36.54it/s]
Loading 0:  89%|████████▉ | 259/291 [00:08<00:00, 35.30it/s]
Loading 0:  91%|█████████ | 264/291 [00:08<00:00, 37.99it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 36.43it/s]
Loading 0:  94%|█████████▍| 273/291 [00:08<00:00, 38.45it/s]
Loading 0:  95%|█████████▌| 277/291 [00:08<00:00, 36.17it/s]
Loading 0:  97%|█████████▋| 281/291 [00:08<00:00, 35.63it/s]
Loading 0:  98%|█████████▊| 286/291 [00:14<00:01,  2.59it/s]
Loading 0:  99%|█████████▉| 289/291 [00:14<00:00,  3.22it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
trace2333-aug-llama3-v1-v5-mkmlizer: quantized model in 29.020s
trace2333-aug-llama3-v1-v5-mkmlizer: Processed model Trace2333/aug_llama3_v1 in 69.415s
trace2333-aug-llama3-v1-v5-mkmlizer: creating bucket guanaco-mkml-models
trace2333-aug-llama3-v1-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-aug-llama3-v1-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-aug-llama3-v1-v5
trace2333-aug-llama3-v1-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-aug-llama3-v1-v5/config.json
trace2333-aug-llama3-v1-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-aug-llama3-v1-v5/special_tokens_map.json
trace2333-aug-llama3-v1-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-aug-llama3-v1-v5/tokenizer_config.json
trace2333-aug-llama3-v1-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-aug-llama3-v1-v5/tokenizer.json
trace2333-aug-llama3-v1-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-aug-llama3-v1-v5/flywheel_model.0.safetensors
trace2333-aug-llama3-v1-v5-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
trace2333-aug-llama3-v1-v5-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:950: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
trace2333-aug-llama3-v1-v5-mkmlizer:   warnings.warn(
trace2333-aug-llama3-v1-v5-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:778: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
trace2333-aug-llama3-v1-v5-mkmlizer:   warnings.warn(
trace2333-aug-llama3-v1-v5-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.
trace2333-aug-llama3-v1-v5-mkmlizer:   warnings.warn(
trace2333-aug-llama3-v1-v5-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
trace2333-aug-llama3-v1-v5-mkmlizer: Saving duration: 1.396s
trace2333-aug-llama3-v1-v5-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.023s
trace2333-aug-llama3-v1-v5-mkmlizer: creating bucket guanaco-reward-models
trace2333-aug-llama3-v1-v5-mkmlizer: Bucket 's3://guanaco-reward-models/' created
trace2333-aug-llama3-v1-v5-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/trace2333-aug-llama3-v1-v5_reward
trace2333-aug-llama3-v1-v5-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/trace2333-aug-llama3-v1-v5_reward/config.json
trace2333-aug-llama3-v1-v5-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/trace2333-aug-llama3-v1-v5_reward/special_tokens_map.json
trace2333-aug-llama3-v1-v5-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/trace2333-aug-llama3-v1-v5_reward/tokenizer_config.json
trace2333-aug-llama3-v1-v5-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/trace2333-aug-llama3-v1-v5_reward/merges.txt
trace2333-aug-llama3-v1-v5-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/trace2333-aug-llama3-v1-v5_reward/vocab.json
trace2333-aug-llama3-v1-v5-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/trace2333-aug-llama3-v1-v5_reward/tokenizer.json
trace2333-aug-llama3-v1-v5-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/trace2333-aug-llama3-v1-v5_reward/reward.tensors
Job trace2333-aug-llama3-v1-v5-mkmlizer completed after 116.15s with status: succeeded
Stopping job with name trace2333-aug-llama3-v1-v5-mkmlizer
Pipeline stage MKMLizer completed in 117.02s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-aug-llama3-v1-v5
Waiting for inference service trace2333-aug-llama3-v1-v5 to be ready
Inference service trace2333-aug-llama3-v1-v5 ready after 70.5020649433136s
Pipeline stage ISVCDeployer completed in 71.92s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.267540693283081s
Received healthy response to inference request in 1.5368359088897705s
Received healthy response to inference request in 1.4894418716430664s
Received healthy response to inference request in 1.439377784729004s
Received healthy response to inference request in 1.418473243713379s
5 requests
0 failed requests
5th percentile: 1.422654151916504
10th percentile: 1.426835060119629
20th percentile: 1.435196876525879
30th percentile: 1.4493906021118164
40th percentile: 1.4694162368774415
50th percentile: 1.4894418716430664
60th percentile: 1.508399486541748
70th percentile: 1.5273571014404297
80th percentile: 1.6829768657684328
90th percentile: 1.975258779525757
95th percentile: 2.1213997364044186
99th percentile: 2.2383125019073487
mean time: 1.6303339004516602
Pipeline stage StressChecker completed in 8.79s
trace2333-aug-llama3-v1_v5 status is now deployed due to DeploymentManager action
trace2333-aug-llama3-v1_v5 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of trace2333-aug-llama3-v1_v5
Running pipeline stage ISVCDeleter
Checking if service trace2333-aug-llama3-v1-v5 is running
Tearing down inference service trace2333-aug-llama3-v1-v5
Service trace2333-aug-llama3-v1-v5 has been torndown
Pipeline stage ISVCDeleter completed in 6.28s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key trace2333-aug-llama3-v1-v5/config.json from bucket guanaco-mkml-models
Deleting key trace2333-aug-llama3-v1-v5/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key trace2333-aug-llama3-v1-v5/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key trace2333-aug-llama3-v1-v5/tokenizer.json from bucket guanaco-mkml-models
Deleting key trace2333-aug-llama3-v1-v5/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key trace2333-aug-llama3-v1-v5_reward/config.json from bucket guanaco-reward-models
Deleting key trace2333-aug-llama3-v1-v5_reward/merges.txt from bucket guanaco-reward-models
Deleting key trace2333-aug-llama3-v1-v5_reward/reward.tensors from bucket guanaco-reward-models
Deleting key trace2333-aug-llama3-v1-v5_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key trace2333-aug-llama3-v1-v5_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key trace2333-aug-llama3-v1-v5_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key trace2333-aug-llama3-v1-v5_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.31s
trace2333-aug-llama3-v1_v5 status is now torndown due to DeploymentManager action