trace2333-aug-llama3-v1

submission_id: trace2333-aug-llama3-v1_v7

developer_uid: Trace2333

best_of: 16

celo_rating: 1150.8

display_name: trace2333-aug-llama3-v1_v5

family_friendly_score: 0.0

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': True}

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}

is_internal_developer: False

language_model: Trace2333/aug_llama3_v1

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: Trace2333/aug_llama3_v1

model_name: trace2333-aug-llama3-v1_v5

model_num_parameters: 8030261248.0

model_repo: Trace2333/aug_llama3_v1

model_size: 8B

num_battles: 23466

num_wins: 10310

ranking_group: single

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'}

reward_repo: Jellywibble/gpt2_xl_pairwise_89m_step_347634

status: torndown

submission_type: basic

timestamp: 2024-07-24T06:16:20+00:00

us_pacific_date: 2024-07-23

win_ratio: 0.439359072700929

Resubmit model

Running pipeline stage MKMLizer
Starting job with name trace2333-aug-llama3-v1-v7-mkmlizer
Waiting for job on trace2333-aug-llama3-v1-v7-mkmlizer to finish
trace2333-aug-llama3-v1-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-aug-llama3-v1-v7-mkmlizer: ║     _____            __           __                                ║
trace2333-aug-llama3-v1-v7-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-aug-llama3-v1-v7-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-aug-llama3-v1-v7-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-aug-llama3-v1-v7-mkmlizer: ║       /___/                                                         ║
trace2333-aug-llama3-v1-v7-mkmlizer: ║                                                                     ║
trace2333-aug-llama3-v1-v7-mkmlizer: ║  Version: 0.9.6                                                     ║
trace2333-aug-llama3-v1-v7-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-aug-llama3-v1-v7-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-aug-llama3-v1-v7-mkmlizer: ║                                                                     ║
trace2333-aug-llama3-v1-v7-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-aug-llama3-v1-v7-mkmlizer: ║  belonging to:                                                      ║
trace2333-aug-llama3-v1-v7-mkmlizer: ║                                                                     ║
trace2333-aug-llama3-v1-v7-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-aug-llama3-v1-v7-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-aug-llama3-v1-v7-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
trace2333-aug-llama3-v1-v7-mkmlizer: ║                                                                     ║
trace2333-aug-llama3-v1-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-aug-llama3-v1-v7-mkmlizer: Downloaded to shared memory in 41.938s
trace2333-aug-llama3-v1-v7-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9j1yqvii, device:0
trace2333-aug-llama3-v1-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-aug-llama3-v1-v7-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:11, 25.04it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:07, 35.33it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:08, 33.07it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:07, 36.55it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:07, 33.74it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:06, 40.61it/s]
Loading 0:  12%|█▏        | 36/291 [00:01<00:10, 24.45it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:09, 25.52it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:07, 31.92it/s]
Loading 0:  18%|█▊        | 52/291 [00:01<00:07, 31.09it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:06, 34.05it/s]
Loading 0:  21%|██        | 61/291 [00:01<00:06, 32.98it/s]
Loading 0:  23%|██▎       | 66/291 [00:02<00:06, 35.49it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:06, 32.93it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:06, 32.52it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:06, 32.74it/s]
Loading 0:  28%|██▊       | 82/291 [00:02<00:09, 23.08it/s]
Loading 0:  29%|██▉       | 85/291 [00:02<00:08, 24.22it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:07, 28.42it/s]
Loading 0:  32%|███▏      | 94/291 [00:03<00:06, 28.39it/s]
Loading 0:  34%|███▍      | 99/291 [00:03<00:05, 32.15it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:06, 29.60it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:05, 32.53it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:05, 31.36it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:05, 32.28it/s]
Loading 0:  42%|████▏     | 122/291 [00:03<00:04, 35.82it/s]
Loading 0:  44%|████▎     | 127/291 [00:04<00:04, 34.08it/s]
Loading 0:  46%|████▌     | 133/291 [00:04<00:05, 29.98it/s]
Loading 0:  47%|████▋     | 137/291 [00:04<00:05, 29.89it/s]
Loading 0:  48%|████▊     | 141/291 [00:04<00:05, 27.96it/s]
Loading 0:  51%|█████     | 147/291 [00:04<00:04, 31.74it/s]
Loading 0:  52%|█████▏    | 151/291 [00:04<00:04, 31.02it/s]
Loading 0:  54%|█████▎    | 156/291 [00:05<00:03, 33.87it/s]
Loading 0:  55%|█████▍    | 160/291 [00:05<00:04, 32.64it/s]
Loading 0:  57%|█████▋    | 165/291 [00:05<00:03, 35.11it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 33.51it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 36.21it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 33.60it/s]
Loading 0:  63%|██████▎   | 184/291 [00:05<00:02, 39.42it/s]
Loading 0:  65%|██████▍   | 189/291 [00:06<00:04, 23.67it/s]
Loading 0:  67%|██████▋   | 194/291 [00:06<00:03, 25.17it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:02, 31.77it/s]
Loading 0:  70%|███████   | 205/291 [00:06<00:02, 30.82it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 33.13it/s]
Loading 0:  74%|███████▎  | 214/291 [00:06<00:02, 32.26it/s]
Loading 0:  75%|███████▌  | 219/291 [00:06<00:02, 34.32it/s]
Loading 0:  77%|███████▋  | 223/291 [00:07<00:02, 32.88it/s]
Loading 0:  78%|███████▊  | 227/291 [00:07<00:01, 32.94it/s]
Loading 0:  79%|███████▉  | 231/291 [00:07<00:01, 33.22it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 25.15it/s]
Loading 0:  82%|████████▏ | 239/291 [00:07<00:02, 24.97it/s]
Loading 0:  85%|████████▍ | 246/291 [00:07<00:01, 32.48it/s]
Loading 0:  86%|████████▌ | 250/291 [00:08<00:01, 31.98it/s]
Loading 0:  88%|████████▊ | 255/291 [00:08<00:01, 34.84it/s]
Loading 0:  89%|████████▉ | 259/291 [00:08<00:00, 32.78it/s]
Loading 0:  91%|█████████ | 264/291 [00:08<00:00, 34.83it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 32.47it/s]
Loading 0:  94%|█████████▍| 273/291 [00:08<00:00, 33.44it/s]
Loading 0:  95%|█████████▌| 277/291 [00:08<00:00, 31.34it/s]
Loading 0:  97%|█████████▋| 281/291 [00:08<00:00, 31.02it/s]
Loading 0:  98%|█████████▊| 286/291 [00:14<00:01,  2.54it/s]
Loading 0:  99%|█████████▉| 289/291 [00:14<00:00,  3.15it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
trace2333-aug-llama3-v1-v7-mkmlizer: quantized model in 29.369s
trace2333-aug-llama3-v1-v7-mkmlizer: Processed model Trace2333/aug_llama3_v1 in 71.307s
trace2333-aug-llama3-v1-v7-mkmlizer: creating bucket guanaco-mkml-models
trace2333-aug-llama3-v1-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-aug-llama3-v1-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-aug-llama3-v1-v7
trace2333-aug-llama3-v1-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-aug-llama3-v1-v7/config.json
trace2333-aug-llama3-v1-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-aug-llama3-v1-v7/special_tokens_map.json
trace2333-aug-llama3-v1-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-aug-llama3-v1-v7/tokenizer_config.json
trace2333-aug-llama3-v1-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-aug-llama3-v1-v7/tokenizer.json
trace2333-aug-llama3-v1-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-aug-llama3-v1-v7/flywheel_model.0.safetensors
trace2333-aug-llama3-v1-v7-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
trace2333-aug-llama3-v1-v7-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-v7-mkmlizer:   warnings.warn(
trace2333-aug-llama3-v1-v7-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-v7-mkmlizer:   warnings.warn(
trace2333-aug-llama3-v1-v7-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-v7-mkmlizer:   warnings.warn(
trace2333-aug-llama3-v1-v7-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
trace2333-aug-llama3-v1-v7-mkmlizer: Saving duration: 1.444s
trace2333-aug-llama3-v1-v7-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.358s
trace2333-aug-llama3-v1-v7-mkmlizer: creating bucket guanaco-reward-models
trace2333-aug-llama3-v1-v7-mkmlizer: Bucket 's3://guanaco-reward-models/' created
trace2333-aug-llama3-v1-v7-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/trace2333-aug-llama3-v1-v7_reward
trace2333-aug-llama3-v1-v7-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/trace2333-aug-llama3-v1-v7_reward/special_tokens_map.json
trace2333-aug-llama3-v1-v7-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/trace2333-aug-llama3-v1-v7_reward/config.json
trace2333-aug-llama3-v1-v7-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/trace2333-aug-llama3-v1-v7_reward/tokenizer_config.json
trace2333-aug-llama3-v1-v7-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/trace2333-aug-llama3-v1-v7_reward/merges.txt
trace2333-aug-llama3-v1-v7-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/trace2333-aug-llama3-v1-v7_reward/vocab.json
trace2333-aug-llama3-v1-v7-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/trace2333-aug-llama3-v1-v7_reward/tokenizer.json
trace2333-aug-llama3-v1-v7-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/trace2333-aug-llama3-v1-v7_reward/reward.tensors
Job trace2333-aug-llama3-v1-v7-mkmlizer completed after 167.46s with status: succeeded
Stopping job with name trace2333-aug-llama3-v1-v7-mkmlizer
Pipeline stage MKMLizer completed in 168.68s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-aug-llama3-v1-v7
Waiting for inference service trace2333-aug-llama3-v1-v7 to be ready
Inference service trace2333-aug-llama3-v1-v7 ready after 50.48659634590149s
Pipeline stage ISVCDeployer completed in 52.18s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8176548480987549s
Received healthy response to inference request in 1.387742280960083s
Received healthy response to inference request in 1.1134872436523438s
Received healthy response to inference request in 1.3212604522705078s
Received healthy response to inference request in 1.3952808380126953s
5 requests
0 failed requests
5th percentile: 1.1550418853759765
10th percentile: 1.1965965270996093
20th percentile: 1.279705810546875
30th percentile: 1.3345568180084229
40th percentile: 1.361149549484253
50th percentile: 1.387742280960083
60th percentile: 1.3907577037811278
70th percentile: 1.393773126602173
80th percentile: 1.4797556400299072
90th percentile: 1.648705244064331
95th percentile: 1.733180046081543
99th percentile: 1.8007598876953126
mean time: 1.407085132598877
Pipeline stage StressChecker completed in 7.72s
trace2333-aug-llama3-v1_v7 status is now deployed due to DeploymentManager action
trace2333-aug-llama3-v1_v7 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of trace2333-aug-llama3-v1_v7
Running pipeline stage ISVCDeleter
Checking if service trace2333-aug-llama3-v1-v7 is running
Tearing down inference service trace2333-aug-llama3-v1-v7
Service trace2333-aug-llama3-v1-v7 has been torndown
Pipeline stage ISVCDeleter completed in 4.47s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key trace2333-aug-llama3-v1-v7/config.json from bucket guanaco-mkml-models
Deleting key trace2333-aug-llama3-v1-v7/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key trace2333-aug-llama3-v1-v7/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key trace2333-aug-llama3-v1-v7/tokenizer.json from bucket guanaco-mkml-models
Deleting key trace2333-aug-llama3-v1-v7/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key trace2333-aug-llama3-v1-v7_reward/config.json from bucket guanaco-reward-models
Deleting key trace2333-aug-llama3-v1-v7_reward/merges.txt from bucket guanaco-reward-models
Deleting key trace2333-aug-llama3-v1-v7_reward/reward.tensors from bucket guanaco-reward-models
Deleting key trace2333-aug-llama3-v1-v7_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key trace2333-aug-llama3-v1-v7_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key trace2333-aug-llama3-v1-v7_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key trace2333-aug-llama3-v1-v7_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.67s
trace2333-aug-llama3-v1_v7 status is now torndown due to DeploymentManager action