trace2333-fd-llama3-v3

developer_uid: Trace2333

submission_id: trace2333-fd-llama3-v3_v1

model_name: trace2333-fd-llama3-v3_v1

model_group: Trace2333/fd_llama3_v3

status: torndown

timestamp: 2024-08-01T03:15:42+00:00

num_battles: 18587

num_wins: 9279

celo_rating: 1200.27

family_friendly_score: 0.0

submission_type: basic

model_repo: Trace2333/fd_llama3_v3

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-fd-llama3-v3_v1

is_internal_developer: False

language_model: Trace2333/fd_llama3_v3

model_size: 8B

ranking_group: single

us_pacific_date: 2024-07-31

win_ratio: 0.4992198848657664

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.12, 'top_k': 200, 'presence_penalty': 0.0, '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-fd-llama3-v3-v1-mkmlizer
Waiting for job on trace2333-fd-llama3-v3-v1-mkmlizer to finish
trace2333-fd-llama3-v3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-fd-llama3-v3-v1-mkmlizer: ║     _____            __           __                                ║
trace2333-fd-llama3-v3-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-fd-llama3-v3-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-fd-llama3-v3-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-fd-llama3-v3-v1-mkmlizer: ║       /___/                                                         ║
trace2333-fd-llama3-v3-v1-mkmlizer: ║                                                                     ║
trace2333-fd-llama3-v3-v1-mkmlizer: ║  Version: 0.9.7                                                     ║
trace2333-fd-llama3-v3-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-fd-llama3-v3-v1-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-fd-llama3-v3-v1-mkmlizer: ║                                                                     ║
trace2333-fd-llama3-v3-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-fd-llama3-v3-v1-mkmlizer: ║  belonging to:                                                      ║
trace2333-fd-llama3-v3-v1-mkmlizer: ║                                                                     ║
trace2333-fd-llama3-v3-v1-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-fd-llama3-v3-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-fd-llama3-v3-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
trace2333-fd-llama3-v3-v1-mkmlizer: ║                                                                     ║
trace2333-fd-llama3-v3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-fd-llama3-v3-v1-mkmlizer: Downloaded to shared memory in 59.704s
trace2333-fd-llama3-v3-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpfm31b20p, device:0
trace2333-fd-llama3-v3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-fd-llama3-v3-v1-mkmlizer: quantized model in 28.522s
trace2333-fd-llama3-v3-v1-mkmlizer: Processed model Trace2333/fd_llama3_v3 in 88.226s
trace2333-fd-llama3-v3-v1-mkmlizer: creating bucket guanaco-mkml-models
trace2333-fd-llama3-v3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-fd-llama3-v3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-fd-llama3-v3-v1
trace2333-fd-llama3-v3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-fd-llama3-v3-v1/special_tokens_map.json
trace2333-fd-llama3-v3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-fd-llama3-v3-v1/tokenizer_config.json
trace2333-fd-llama3-v3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-fd-llama3-v3-v1/config.json
trace2333-fd-llama3-v3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-fd-llama3-v3-v1/tokenizer.json
trace2333-fd-llama3-v3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-fd-llama3-v3-v1/flywheel_model.0.safetensors
trace2333-fd-llama3-v3-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
trace2333-fd-llama3-v3-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:10, 27.81it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:07, 37.65it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:07, 35.34it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:07, 38.44it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:07, 36.03it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:06, 42.32it/s]
Loading 0:  12%|█▏        | 36/291 [00:01<00:10, 24.36it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:09, 26.36it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:07, 33.20it/s]
Loading 0:  18%|█▊        | 53/291 [00:01<00:06, 34.21it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:06, 35.37it/s]
Loading 0:  21%|██        | 61/291 [00:01<00:06, 34.60it/s]
Loading 0:  23%|██▎       | 66/291 [00:01<00:06, 37.00it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:06, 35.42it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:06, 35.47it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:05, 35.56it/s]
Loading 0:  28%|██▊       | 82/291 [00:02<00:08, 24.15it/s]
Loading 0:  29%|██▉       | 85/291 [00:02<00:08, 25.28it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:06, 29.30it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:06, 29.91it/s]
Loading 0:  34%|███▍      | 99/291 [00:03<00:05, 33.56it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:05, 33.02it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:05, 35.90it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:05, 34.48it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:05, 34.59it/s]
Loading 0:  41%|████      | 120/291 [00:03<00:04, 35.62it/s]
Loading 0:  43%|████▎     | 126/291 [00:03<00:03, 41.32it/s]
Loading 0:  45%|████▌     | 131/291 [00:03<00:03, 41.98it/s]
Loading 0:  47%|████▋     | 136/291 [00:04<00:05, 26.30it/s]
Loading 0:  48%|████▊     | 140/291 [00:04<00:05, 26.03it/s]
Loading 0:  51%|█████     | 147/291 [00:04<00:04, 33.09it/s]
Loading 0:  52%|█████▏    | 151/291 [00:04<00:04, 32.82it/s]
Loading 0:  54%|█████▎    | 156/291 [00:04<00:03, 35.75it/s]
Loading 0:  55%|█████▍    | 160/291 [00:04<00:03, 34.59it/s]
Loading 0:  57%|█████▋    | 165/291 [00:04<00:03, 36.51it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 34.76it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 37.20it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 35.51it/s]
Loading 0:  63%|██████▎   | 183/291 [00:05<00:02, 38.91it/s]
Loading 0:  65%|██████▍   | 188/291 [00:05<00:03, 27.86it/s]
Loading 0:  66%|██████▌   | 192/291 [00:05<00:03, 28.42it/s]
Loading 0:  67%|██████▋   | 196/291 [00:06<00:03, 29.06it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:02, 32.38it/s]
Loading 0:  70%|███████   | 205/291 [00:06<00:02, 31.80it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 34.61it/s]
Loading 0:  74%|███████▎  | 214/291 [00:06<00:02, 33.65it/s]
Loading 0:  75%|███████▌  | 219/291 [00:06<00:01, 36.52it/s]
Loading 0:  77%|███████▋  | 223/291 [00:06<00:01, 34.97it/s]
Loading 0:  78%|███████▊  | 227/291 [00:06<00:01, 35.00it/s]
Loading 0:  79%|███████▉  | 231/291 [00:06<00:01, 35.07it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 25.70it/s]
Loading 0:  82%|████████▏ | 239/291 [00:07<00:02, 25.86it/s]
Loading 0:  85%|████████▍ | 246/291 [00:07<00:01, 33.88it/s]
Loading 0:  86%|████████▌ | 250/291 [00:07<00:01, 33.27it/s]
Loading 0:  88%|████████▊ | 255/291 [00:07<00:00, 36.15it/s]
Loading 0:  89%|████████▉ | 259/291 [00:07<00:00, 35.10it/s]
Loading 0:  91%|█████████ | 264/291 [00:07<00:00, 37.68it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 35.59it/s]
Loading 0:  94%|█████████▍| 273/291 [00:08<00:00, 37.71it/s]
Loading 0:  95%|█████████▌| 277/291 [00:08<00:00, 36.11it/s]
Loading 0:  97%|█████████▋| 281/291 [00:08<00:00, 35.50it/s]
Loading 0:  98%|█████████▊| 286/291 [00:13<00:01,  2.61it/s]
Loading 0:  99%|█████████▉| 289/291 [00:14<00:00,  3.25it/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.
trace2333-fd-llama3-v3-v1-mkmlizer:   warnings.warn(
trace2333-fd-llama3-v3-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.
trace2333-fd-llama3-v3-v1-mkmlizer:   warnings.warn(
trace2333-fd-llama3-v3-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.
trace2333-fd-llama3-v3-v1-mkmlizer:   warnings.warn(
trace2333-fd-llama3-v3-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
trace2333-fd-llama3-v3-v1-mkmlizer: Saving duration: 1.397s
trace2333-fd-llama3-v3-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.604s
trace2333-fd-llama3-v3-v1-mkmlizer: creating bucket guanaco-reward-models
Failed to get response for submission chaiml-sao10k-l3-rp-v3-3_v37: ('http://chaiml-sao10k-l3-rp-v3-3-v37-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:45546->127.0.0.1:8080: read: connection reset by peer\n')
trace2333-fd-llama3-v3-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/trace2333-fd-llama3-v3-v1_reward/config.json
trace2333-fd-llama3-v3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/trace2333-fd-llama3-v3-v1_reward/tokenizer_config.json
trace2333-fd-llama3-v3-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/trace2333-fd-llama3-v3-v1_reward/merges.txt
trace2333-fd-llama3-v3-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/trace2333-fd-llama3-v3-v1_reward/vocab.json
trace2333-fd-llama3-v3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/trace2333-fd-llama3-v3-v1_reward/tokenizer.json
trace2333-fd-llama3-v3-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/trace2333-fd-llama3-v3-v1_reward/reward.tensors
Job trace2333-fd-llama3-v3-v1-mkmlizer completed after 126.25s with status: succeeded
Stopping job with name trace2333-fd-llama3-v3-v1-mkmlizer
Pipeline stage MKMLizer completed in 127.22s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-fd-llama3-v3-v1
Waiting for inference service trace2333-fd-llama3-v3-v1 to be ready
Inference service trace2333-fd-llama3-v3-v1 ready after 131.03607153892517s
Pipeline stage ISVCDeployer completed in 132.53s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2633206844329834s
Received healthy response to inference request in 1.493354320526123s
Received healthy response to inference request in 1.4551119804382324s
Received healthy response to inference request in 1.4386484622955322s
Received healthy response to inference request in 1.3909633159637451s
5 requests
0 failed requests
5th percentile: 1.4005003452301026
10th percentile: 1.41003737449646
20th percentile: 1.4291114330291748
30th percentile: 1.4419411659240722
40th percentile: 1.4485265731811523
50th percentile: 1.4551119804382324
60th percentile: 1.4704089164733887
70th percentile: 1.485705852508545
80th percentile: 1.6473475933074953
90th percentile: 1.9553341388702394
95th percentile: 2.109327411651611
99th percentile: 2.232522029876709
mean time: 1.6082797527313233
Pipeline stage StressChecker completed in 8.76s
trace2333-fd-llama3-v3_v1 status is now deployed due to DeploymentManager action
trace2333-fd-llama3-v3_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of trace2333-fd-llama3-v3_v1
Running pipeline stage ISVCDeleter
Checking if service trace2333-fd-llama3-v3-v1 is running
Tearing down inference service trace2333-fd-llama3-v3-v1
Service trace2333-fd-llama3-v3-v1 has been torndown
Pipeline stage ISVCDeleter completed in 5.36s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key trace2333-fd-llama3-v3-v1/config.json from bucket guanaco-mkml-models
Deleting key trace2333-fd-llama3-v3-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key trace2333-fd-llama3-v3-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key trace2333-fd-llama3-v3-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key trace2333-fd-llama3-v3-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key trace2333-fd-llama3-v3-v1_reward/config.json from bucket guanaco-reward-models
Deleting key trace2333-fd-llama3-v3-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key trace2333-fd-llama3-v3-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key trace2333-fd-llama3-v3-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key trace2333-fd-llama3-v3-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key trace2333-fd-llama3-v3-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key trace2333-fd-llama3-v3-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.73s
trace2333-fd-llama3-v3_v1 status is now torndown due to DeploymentManager action