trace2333-duduk-llama3-v4

developer_uid: Trace2333

submission_id: trace2333-duduk-llama3-v4_v1

model_name: trace2333-duduk-llama3-v4_v1

model_group: Trace2333/duduk_llama3_v

status: torndown

timestamp: 2024-07-30T16:02:54+00:00

num_battles: 11101

num_wins: 5093

celo_rating: 1175.53

family_friendly_score: 0.0

submission_type: basic

model_repo: Trace2333/duduk_llama3_v4

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-v4_v1

is_internal_developer: False

language_model: Trace2333/duduk_llama3_v4

model_size: 8B

ranking_group: single

us_pacific_date: 2024-07-30

win_ratio: 0.45878749662192597

generation_params: {'temperature': 1.05, '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-duduk-llama3-v4-v1-mkmlizer
Waiting for job on trace2333-duduk-llama3-v4-v1-mkmlizer to finish
Stopping job with name trace2333-duduk-llama3-v4-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name trace2333-duduk-llama3-v4-v1-mkmlizer
Waiting for job on trace2333-duduk-llama3-v4-v1-mkmlizer to finish
trace2333-duduk-llama3-v4-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-duduk-llama3-v4-v1-mkmlizer: ║     _____            __           __                                ║
trace2333-duduk-llama3-v4-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-duduk-llama3-v4-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-duduk-llama3-v4-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-duduk-llama3-v4-v1-mkmlizer: ║       /___/                                                         ║
trace2333-duduk-llama3-v4-v1-mkmlizer: ║                                                                     ║
trace2333-duduk-llama3-v4-v1-mkmlizer: ║  Version: 0.9.7                                                     ║
trace2333-duduk-llama3-v4-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-duduk-llama3-v4-v1-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-duduk-llama3-v4-v1-mkmlizer: ║                                                                     ║
trace2333-duduk-llama3-v4-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-duduk-llama3-v4-v1-mkmlizer: ║  belonging to:                                                      ║
trace2333-duduk-llama3-v4-v1-mkmlizer: ║                                                                     ║
trace2333-duduk-llama3-v4-v1-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-duduk-llama3-v4-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-duduk-llama3-v4-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
trace2333-duduk-llama3-v4-v1-mkmlizer: ║                                                                     ║
trace2333-duduk-llama3-v4-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-duduk-llama3-v4-v1-mkmlizer: Downloaded to shared memory in 64.569s
trace2333-duduk-llama3-v4-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpk3xlrx8u, device:0
trace2333-duduk-llama3-v4-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-duduk-llama3-v4-v1-mkmlizer: quantized model in 29.728s
trace2333-duduk-llama3-v4-v1-mkmlizer: Processed model Trace2333/duduk_llama3_v4 in 94.297s
trace2333-duduk-llama3-v4-v1-mkmlizer: creating bucket guanaco-mkml-models
trace2333-duduk-llama3-v4-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-duduk-llama3-v4-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-duduk-llama3-v4-v1
trace2333-duduk-llama3-v4-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v4-v1/config.json
trace2333-duduk-llama3-v4-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v4-v1/special_tokens_map.json
trace2333-duduk-llama3-v4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v4-v1/tokenizer_config.json
trace2333-duduk-llama3-v4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v4-v1/tokenizer.json
trace2333-duduk-llama3-v4-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-duduk-llama3-v4-v1/flywheel_model.0.safetensors
trace2333-duduk-llama3-v4-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
trace2333-duduk-llama3-v4-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:11, 24.94it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:08, 33.89it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:08, 31.27it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:07, 34.37it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:08, 31.97it/s]
Loading 0:  10%|█         | 30/291 [00:00<00:07, 36.11it/s]
Loading 0:  12%|█▏        | 34/291 [00:01<00:10, 24.96it/s]
Loading 0:  13%|█▎        | 37/291 [00:01<00:10, 24.17it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:10, 23.91it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:07, 31.81it/s]
Loading 0:  18%|█▊        | 52/291 [00:01<00:07, 30.65it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:07, 32.84it/s]
Loading 0:  21%|██        | 61/291 [00:02<00:07, 31.08it/s]
Loading 0:  23%|██▎       | 66/291 [00:02<00:06, 33.29it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:06, 31.68it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:06, 31.12it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:06, 30.81it/s]
Loading 0:  28%|██▊       | 82/291 [00:02<00:09, 22.23it/s]
Loading 0:  29%|██▉       | 85/291 [00:02<00:08, 23.22it/s]
Loading 0:  31%|███       | 90/291 [00:03<00:07, 26.82it/s]
Loading 0:  32%|███▏      | 93/291 [00:03<00:07, 25.75it/s]
Loading 0:  34%|███▍      | 99/291 [00:03<00:06, 31.69it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:06, 30.84it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:05, 33.68it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:05, 32.13it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:05, 32.81it/s]
Loading 0:  42%|████▏     | 122/291 [00:04<00:04, 36.35it/s]
Loading 0:  44%|████▎     | 127/291 [00:04<00:04, 33.57it/s]
Loading 0:  45%|████▌     | 132/291 [00:04<00:04, 36.74it/s]
Loading 0:  47%|████▋     | 136/291 [00:04<00:06, 24.69it/s]
Loading 0:  48%|████▊     | 140/291 [00:04<00:06, 23.46it/s]
Loading 0:  51%|█████     | 147/291 [00:04<00:04, 30.20it/s]
Loading 0:  52%|█████▏    | 151/291 [00:05<00:04, 29.71it/s]
Loading 0:  54%|█████▎    | 156/291 [00:05<00:04, 32.52it/s]
Loading 0:  55%|█████▍    | 160/291 [00:05<00:04, 31.45it/s]
Loading 0:  57%|█████▋    | 165/291 [00:05<00:03, 33.91it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 31.89it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 33.45it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 31.75it/s]
Loading 0:  63%|██████▎   | 183/291 [00:05<00:03, 35.84it/s]
Loading 0:  64%|██████▍   | 187/291 [00:06<00:04, 25.97it/s]
Loading 0:  66%|██████▌   | 191/291 [00:06<00:03, 26.74it/s]
Loading 0:  67%|██████▋   | 195/291 [00:06<00:03, 25.64it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:02, 30.44it/s]
Loading 0:  70%|███████   | 205/291 [00:06<00:02, 29.34it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 31.45it/s]
Loading 0:  74%|███████▎  | 214/291 [00:07<00:02, 30.31it/s]
Loading 0:  75%|███████▌  | 219/291 [00:07<00:02, 33.04it/s]
Loading 0:  77%|███████▋  | 223/291 [00:07<00:02, 31.77it/s]
Loading 0:  78%|███████▊  | 227/291 [00:07<00:01, 32.14it/s]
Loading 0:  79%|███████▉  | 231/291 [00:07<00:01, 32.32it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 25.23it/s]
Loading 0:  82%|████████▏ | 239/291 [00:08<00:02, 24.74it/s]
Loading 0:  85%|████████▍ | 246/291 [00:08<00:01, 32.70it/s]
Loading 0:  86%|████████▌ | 250/291 [00:08<00:01, 31.31it/s]
Loading 0:  88%|████████▊ | 255/291 [00:08<00:01, 33.38it/s]
Loading 0:  89%|████████▉ | 259/291 [00:08<00:01, 31.56it/s]
Loading 0:  91%|█████████ | 264/291 [00:08<00:00, 34.03it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 32.52it/s]
Loading 0:  94%|█████████▍| 273/291 [00:08<00:00, 34.93it/s]
Loading 0:  95%|█████████▌| 277/291 [00:09<00:00, 32.93it/s]
Loading 0:  97%|█████████▋| 281/291 [00:09<00:00, 32.31it/s]
Loading 0:  98%|█████████▊| 286/291 [00:14<00:01,  2.56it/s]
Loading 0:  99%|█████████▉| 289/291 [00:14<00:00,  3.17it/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-v4-v1-mkmlizer:   warnings.warn(
trace2333-duduk-llama3-v4-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-v4-v1-mkmlizer:   warnings.warn(
trace2333-duduk-llama3-v4-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-duduk-llama3-v4-v1-mkmlizer:   warnings.warn(
trace2333-duduk-llama3-v4-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
trace2333-duduk-llama3-v4-v1-mkmlizer: Saving duration: 1.423s
trace2333-duduk-llama3-v4-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.191s
trace2333-duduk-llama3-v4-v1-mkmlizer: creating bucket guanaco-reward-models
trace2333-duduk-llama3-v4-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
trace2333-duduk-llama3-v4-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/trace2333-duduk-llama3-v4-v1_reward
trace2333-duduk-llama3-v4-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/trace2333-duduk-llama3-v4-v1_reward/special_tokens_map.json
trace2333-duduk-llama3-v4-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/trace2333-duduk-llama3-v4-v1_reward/tokenizer_config.json
trace2333-duduk-llama3-v4-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/trace2333-duduk-llama3-v4-v1_reward/config.json
trace2333-duduk-llama3-v4-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/trace2333-duduk-llama3-v4-v1_reward/merges.txt
trace2333-duduk-llama3-v4-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/trace2333-duduk-llama3-v4-v1_reward/vocab.json
trace2333-duduk-llama3-v4-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/trace2333-duduk-llama3-v4-v1_reward/tokenizer.json
Job trace2333-duduk-llama3-v4-v1-mkmlizer completed after 135.9s with status: succeeded
Stopping job with name trace2333-duduk-llama3-v4-v1-mkmlizer
Pipeline stage MKMLizer completed in 137.64s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-duduk-llama3-v4-v1
Waiting for inference service trace2333-duduk-llama3-v4-v1 to be ready
Inference service trace2333-duduk-llama3-v4-v1 ready after 120.73418545722961s
Pipeline stage ISVCDeployer completed in 122.72s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3424737453460693s
Received healthy response to inference request in 1.4511299133300781s
Received healthy response to inference request in 1.4585697650909424s
Received healthy response to inference request in 1.4236361980438232s
Received healthy response to inference request in 1.3889639377593994s
5 requests
0 failed requests
5th percentile: 1.3958983898162842
10th percentile: 1.402832841873169
20th percentile: 1.4167017459869384
30th percentile: 1.4291349411010743
40th percentile: 1.4401324272155762
50th percentile: 1.4511299133300781
60th percentile: 1.4541058540344238
70th percentile: 1.4570817947387695
80th percentile: 1.6353505611419679
90th percentile: 1.9889121532440186
95th percentile: 2.165692949295044
99th percentile: 2.307117586135864
mean time: 1.6129547119140626
Pipeline stage StressChecker completed in 8.77s
trace2333-duduk-llama3-v4_v1 status is now deployed due to DeploymentManager action
trace2333-duduk-llama3-v4_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of trace2333-duduk-llama3-v4_v1
Running pipeline stage ISVCDeleter
Checking if service trace2333-duduk-llama3-v4-v1 is running
Tearing down inference service trace2333-duduk-llama3-v4-v1
Service trace2333-duduk-llama3-v4-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-duduk-llama3-v4-v1/config.json from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama3-v4-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama3-v4-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama3-v4-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama3-v4-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key trace2333-duduk-llama3-v4-v1_reward/config.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v4-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v4-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v4-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v4-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v4-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v4-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.82s
trace2333-duduk-llama3-v4_v1 status is now torndown due to DeploymentManager action