trace2333-duduk-llama3-v3

developer_uid: Trace2333

submission_id: trace2333-duduk-llama3-v3_v1

model_name: trace2333-duduk-llama3-v3_v1

model_group: Trace2333/duduk_llama3_v

status: torndown

timestamp: 2024-07-30T05:30:19+00:00

num_battles: 10718

num_wins: 5097

celo_rating: 1179.84

family_friendly_score: 0.0

submission_type: basic

model_repo: Trace2333/duduk_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-duduk-llama3-v3_v1

is_internal_developer: False

language_model: Trace2333/duduk_llama3_v3

model_size: 8B

ranking_group: single

us_pacific_date: 2024-07-29

win_ratio: 0.47555514088449335

generation_params: {'temperature': 1.05, 'top_p': 1.0, 'min_p': 0.12, 'top_k': 40, '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-duduk-llama3-v3-v1-mkmlizer
Waiting for job on trace2333-duduk-llama3-v3-v1-mkmlizer to finish
Stopping job with name trace2333-duduk-llama3-v3-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name trace2333-duduk-llama3-v3-v1-mkmlizer
Waiting for job on trace2333-duduk-llama3-v3-v1-mkmlizer to finish
trace2333-duduk-llama3-v3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-duduk-llama3-v3-v1-mkmlizer: ║     _____            __           __                                ║
trace2333-duduk-llama3-v3-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-duduk-llama3-v3-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-duduk-llama3-v3-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-duduk-llama3-v3-v1-mkmlizer: ║       /___/                                                         ║
trace2333-duduk-llama3-v3-v1-mkmlizer: ║                                                                     ║
trace2333-duduk-llama3-v3-v1-mkmlizer: ║  Version: 0.9.7                                                     ║
trace2333-duduk-llama3-v3-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-duduk-llama3-v3-v1-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-duduk-llama3-v3-v1-mkmlizer: ║                                                                     ║
trace2333-duduk-llama3-v3-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-duduk-llama3-v3-v1-mkmlizer: ║  belonging to:                                                      ║
trace2333-duduk-llama3-v3-v1-mkmlizer: ║                                                                     ║
trace2333-duduk-llama3-v3-v1-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-duduk-llama3-v3-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-duduk-llama3-v3-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
trace2333-duduk-llama3-v3-v1-mkmlizer: ║                                                                     ║
trace2333-duduk-llama3-v3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-duduk-llama3-v3-v1-mkmlizer: Downloaded to shared memory in 57.799s
trace2333-duduk-llama3-v3-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp6ta2on3d, device:0
trace2333-duduk-llama3-v3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-duduk-llama3-v3-v1-mkmlizer: quantized model in 28.836s
trace2333-duduk-llama3-v3-v1-mkmlizer: Processed model Trace2333/duduk_llama3_v3 in 86.636s
trace2333-duduk-llama3-v3-v1-mkmlizer: creating bucket guanaco-mkml-models
trace2333-duduk-llama3-v3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-duduk-llama3-v3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-duduk-llama3-v3-v1
trace2333-duduk-llama3-v3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v3-v1/config.json
trace2333-duduk-llama3-v3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v3-v1/special_tokens_map.json
trace2333-duduk-llama3-v3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v3-v1/tokenizer_config.json
trace2333-duduk-llama3-v3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v3-v1/tokenizer.json
trace2333-duduk-llama3-v3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-duduk-llama3-v3-v1/flywheel_model.0.safetensors
trace2333-duduk-llama3-v3-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
trace2333-duduk-llama3-v3-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:10, 26.10it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:06, 41.87it/s]
Loading 0:   6%|▌         | 17/291 [00:00<00:06, 39.33it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:07, 37.81it/s]
Loading 0:   9%|▉         | 26/291 [00:00<00:07, 37.67it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:06, 37.53it/s]
Loading 0:  12%|█▏        | 36/291 [00:01<00:11, 22.78it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:10, 24.86it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:07, 32.12it/s]
Loading 0:  18%|█▊        | 52/291 [00:01<00:07, 31.59it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:06, 34.40it/s]
Loading 0:  21%|██        | 61/291 [00:01<00:06, 33.18it/s]
Loading 0:  23%|██▎       | 66/291 [00:01<00:06, 35.75it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:06, 34.49it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:06, 34.89it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:06, 35.02it/s]
Loading 0:  28%|██▊       | 82/291 [00:02<00:08, 24.09it/s]
Loading 0:  30%|██▉       | 86/291 [00:02<00:07, 26.99it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:06, 29.52it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:06, 30.09it/s]
Loading 0:  34%|███▍      | 99/291 [00:03<00:05, 32.82it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:05, 31.90it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:05, 34.36it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:05, 32.84it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:05, 32.52it/s]
Loading 0:  42%|████▏     | 122/291 [00:03<00:04, 37.48it/s]
Loading 0:  44%|████▎     | 127/291 [00:03<00:04, 35.76it/s]
Loading 0:  46%|████▌     | 133/291 [00:04<00:05, 30.55it/s]
Loading 0:  47%|████▋     | 137/291 [00:04<00:04, 30.91it/s]
Loading 0:  48%|████▊     | 141/291 [00:04<00:05, 29.21it/s]
Loading 0:  51%|█████     | 147/291 [00:04<00:04, 33.54it/s]
Loading 0:  52%|█████▏    | 151/291 [00:04<00:04, 32.93it/s]
Loading 0:  54%|█████▎    | 156/291 [00:04<00:03, 35.49it/s]
Loading 0:  55%|█████▍    | 160/291 [00:04<00:03, 33.87it/s]
Loading 0:  57%|█████▋    | 165/291 [00:05<00:03, 36.42it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 35.10it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 37.54it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 34.72it/s]
Loading 0:  63%|██████▎   | 184/291 [00:05<00:02, 40.31it/s]
Loading 0:  65%|██████▍   | 189/291 [00:05<00:04, 24.90it/s]
Loading 0:  67%|██████▋   | 194/291 [00:06<00:03, 26.62it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:02, 33.43it/s]
Loading 0:  71%|███████   | 206/291 [00:06<00:02, 33.92it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 34.87it/s]
Loading 0:  74%|███████▎  | 214/291 [00:06<00:02, 34.17it/s]
Loading 0:  75%|███████▌  | 219/291 [00:06<00:01, 36.63it/s]
Loading 0:  77%|███████▋  | 223/291 [00:06<00:01, 34.91it/s]
Loading 0:  78%|███████▊  | 227/291 [00:06<00:01, 34.77it/s]
Loading 0:  79%|███████▉  | 231/291 [00:07<00:01, 34.46it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 24.56it/s]
Loading 0:  82%|████████▏ | 239/291 [00:07<00:02, 24.43it/s]
Loading 0:  85%|████████▍ | 246/291 [00:07<00:01, 31.86it/s]
Loading 0:  86%|████████▌ | 250/291 [00:07<00:01, 31.65it/s]
Loading 0:  88%|████████▊ | 255/291 [00:07<00:01, 34.61it/s]
Loading 0:  89%|████████▉ | 259/291 [00:08<00:00, 33.16it/s]
Loading 0:  91%|█████████ | 264/291 [00:08<00:00, 35.32it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 34.02it/s]
Loading 0:  94%|█████████▍| 273/291 [00:08<00:00, 36.25it/s]
Loading 0:  95%|█████████▌| 277/291 [00:08<00:00, 34.65it/s]
Loading 0:  97%|█████████▋| 281/291 [00:08<00:00, 34.48it/s]
Loading 0:  98%|█████████▊| 286/291 [00:14<00:01,  2.59it/s]
Loading 0:  99%|█████████▉| 289/291 [00:14<00:00,  3.23it/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-duduk-llama3-v3-v1-mkmlizer:   warnings.warn(
trace2333-duduk-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-duduk-llama3-v3-v1-mkmlizer:   warnings.warn(
trace2333-duduk-llama3-v3-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
trace2333-duduk-llama3-v3-v1-mkmlizer: Saving duration: 1.382s
trace2333-duduk-llama3-v3-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.975s
trace2333-duduk-llama3-v3-v1-mkmlizer: creating bucket guanaco-reward-models
trace2333-duduk-llama3-v3-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
trace2333-duduk-llama3-v3-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/trace2333-duduk-llama3-v3-v1_reward
trace2333-duduk-llama3-v3-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/trace2333-duduk-llama3-v3-v1_reward/config.json
trace2333-duduk-llama3-v3-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/trace2333-duduk-llama3-v3-v1_reward/special_tokens_map.json
trace2333-duduk-llama3-v3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/trace2333-duduk-llama3-v3-v1_reward/tokenizer_config.json
trace2333-duduk-llama3-v3-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/trace2333-duduk-llama3-v3-v1_reward/merges.txt
trace2333-duduk-llama3-v3-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/trace2333-duduk-llama3-v3-v1_reward/vocab.json
trace2333-duduk-llama3-v3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/trace2333-duduk-llama3-v3-v1_reward/tokenizer.json
trace2333-duduk-llama3-v3-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/trace2333-duduk-llama3-v3-v1_reward/reward.tensors
Job trace2333-duduk-llama3-v3-v1-mkmlizer completed after 135.38s with status: succeeded
Stopping job with name trace2333-duduk-llama3-v3-v1-mkmlizer
Pipeline stage MKMLizer completed in 137.14s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-duduk-llama3-v3-v1
Waiting for inference service trace2333-duduk-llama3-v3-v1 to be ready
Inference service trace2333-duduk-llama3-v3-v1 ready after 120.7471010684967s
Pipeline stage ISVCDeployer completed in 122.70s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.208233594894409s
Received healthy response to inference request in 1.502634048461914s
Received healthy response to inference request in 1.4596095085144043s
Received healthy response to inference request in 1.451366662979126s
Received healthy response to inference request in 1.3670752048492432s
5 requests
0 failed requests
5th percentile: 1.3839334964752197
10th percentile: 1.4007917881011962
20th percentile: 1.4345083713531495
30th percentile: 1.4530152320861816
40th percentile: 1.456312370300293
50th percentile: 1.4596095085144043
60th percentile: 1.4768193244934082
70th percentile: 1.4940291404724122
80th percentile: 1.6437539577484133
90th percentile: 1.9259937763214112
95th percentile: 2.06711368560791
99th percentile: 2.180009613037109
mean time: 1.5977838039398193
Pipeline stage StressChecker completed in 8.72s
trace2333-duduk-llama3-v3_v1 status is now deployed due to DeploymentManager action
trace2333-duduk-llama3-v3_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of trace2333-duduk-llama3-v3_v1
Running pipeline stage ISVCDeleter
Checking if service trace2333-duduk-llama3-v3-v1 is running
Tearing down inference service trace2333-duduk-llama3-v3-v1
Service trace2333-duduk-llama3-v3-v1 has been torndown
Pipeline stage ISVCDeleter completed in 4.63s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key trace2333-duduk-llama3-v3-v1/config.json from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama3-v3-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama3-v3-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama3-v3-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama3-v3-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key trace2333-duduk-llama3-v3-v1_reward/config.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v3-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v3-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v3-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v3-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v3-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v3-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.40s
trace2333-duduk-llama3-v3_v1 status is now torndown due to DeploymentManager action