trace2333-duduk-llama3-v3

developer_uid: Trace2333

submission_id: trace2333-duduk-llama3-v3_v2

model_name: trace2333-duduk-llama3-v3_v2

model_group: Trace2333/duduk_llama3_v

status: torndown

timestamp: 2024-07-30T05:55:20+00:00

num_battles: 15979

num_wins: 7542

celo_rating: 1177.56

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_v2

is_internal_developer: False

language_model: Trace2333/duduk_llama3_v3

model_size: 8B

ranking_group: single

us_pacific_date: 2024-07-29

win_ratio: 0.4719944927717629

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-v3-v2-mkmlizer
Waiting for job on trace2333-duduk-llama3-v3-v2-mkmlizer to finish
trace2333-duduk-llama3-v3-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-duduk-llama3-v3-v2-mkmlizer: ║     _____            __           __                                ║
trace2333-duduk-llama3-v3-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-duduk-llama3-v3-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-duduk-llama3-v3-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-duduk-llama3-v3-v2-mkmlizer: ║       /___/                                                         ║
trace2333-duduk-llama3-v3-v2-mkmlizer: ║                                                                     ║
trace2333-duduk-llama3-v3-v2-mkmlizer: ║  Version: 0.9.7                                                     ║
trace2333-duduk-llama3-v3-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-duduk-llama3-v3-v2-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-duduk-llama3-v3-v2-mkmlizer: ║                                                                     ║
trace2333-duduk-llama3-v3-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-duduk-llama3-v3-v2-mkmlizer: ║  belonging to:                                                      ║
trace2333-duduk-llama3-v3-v2-mkmlizer: ║                                                                     ║
trace2333-duduk-llama3-v3-v2-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-duduk-llama3-v3-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-duduk-llama3-v3-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
trace2333-duduk-llama3-v3-v2-mkmlizer: ║                                                                     ║
trace2333-duduk-llama3-v3-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
trace2333-duduk-llama3-v3-v2-mkmlizer: Downloaded to shared memory in 57.312s
trace2333-duduk-llama3-v3-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpb_zvmfuw, device:0
trace2333-duduk-llama3-v3-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-duduk-llama3-v3-v2-mkmlizer: quantized model in 28.680s
trace2333-duduk-llama3-v3-v2-mkmlizer: Processed model Trace2333/duduk_llama3_v3 in 85.992s
trace2333-duduk-llama3-v3-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-duduk-llama3-v3-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-duduk-llama3-v3-v2
trace2333-duduk-llama3-v3-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v3-v2/config.json
trace2333-duduk-llama3-v3-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v3-v2/special_tokens_map.json
trace2333-duduk-llama3-v3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v3-v2/tokenizer_config.json
trace2333-duduk-llama3-v3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v3-v2/tokenizer.json
trace2333-duduk-llama3-v3-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-duduk-llama3-v3-v2/flywheel_model.0.safetensors
trace2333-duduk-llama3-v3-v2-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
trace2333-duduk-llama3-v3-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:10, 26.34it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:07, 37.46it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:07, 34.87it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:07, 38.05it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:07, 35.59it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:06, 42.37it/s]
Loading 0:  12%|█▏        | 36/291 [00:01<00:10, 24.55it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:09, 26.58it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:07, 33.97it/s]
Loading 0:  18%|█▊        | 53/291 [00:01<00:07, 33.92it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:06, 34.74it/s]
Loading 0:  21%|██        | 61/291 [00:01<00:06, 33.96it/s]
Loading 0:  23%|██▎       | 66/291 [00:01<00:06, 36.69it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:06, 34.48it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:06, 34.84it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:06, 35.05it/s]
Loading 0:  28%|██▊       | 82/291 [00:02<00:08, 24.61it/s]
Loading 0:  30%|██▉       | 86/291 [00:02<00:07, 27.24it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:06, 29.81it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:06, 29.77it/s]
Loading 0:  34%|███▍      | 99/291 [00:03<00:05, 33.65it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:05, 32.22it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:05, 35.07it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:05, 32.77it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:05, 32.23it/s]
Loading 0:  42%|████▏     | 122/291 [00:03<00:04, 36.00it/s]
Loading 0:  44%|████▎     | 127/291 [00:03<00:04, 33.88it/s]
Loading 0:  46%|████▌     | 133/291 [00:04<00:05, 30.67it/s]
Loading 0:  47%|████▋     | 137/291 [00:04<00:05, 30.35it/s]
Loading 0:  48%|████▊     | 141/291 [00:04<00:05, 28.54it/s]
Loading 0:  51%|█████     | 147/291 [00:04<00:04, 32.79it/s]
Loading 0:  52%|█████▏    | 151/291 [00:04<00:04, 31.42it/s]
Loading 0:  54%|█████▎    | 156/291 [00:04<00:03, 33.98it/s]
Loading 0:  55%|█████▍    | 160/291 [00:04<00:03, 33.14it/s]
Loading 0:  57%|█████▋    | 165/291 [00:05<00:03, 35.80it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 33.58it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 35.76it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 33.62it/s]
Loading 0:  63%|██████▎   | 184/291 [00:05<00:02, 39.74it/s]
Loading 0:  65%|██████▍   | 189/291 [00:05<00:04, 24.44it/s]
Loading 0:  67%|██████▋   | 194/291 [00:06<00:03, 25.66it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:02, 32.54it/s]
Loading 0:  70%|███████   | 205/291 [00:06<00:02, 32.01it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 34.58it/s]
Loading 0:  74%|███████▎  | 214/291 [00:06<00:02, 33.54it/s]
Loading 0:  75%|███████▌  | 219/291 [00:06<00:01, 36.82it/s]
Loading 0:  77%|███████▋  | 223/291 [00:06<00:01, 34.97it/s]
Loading 0:  78%|███████▊  | 227/291 [00:06<00:01, 34.94it/s]
Loading 0:  79%|███████▉  | 231/291 [00:07<00:01, 34.05it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 25.23it/s]
Loading 0:  82%|████████▏ | 239/291 [00:07<00:02, 24.96it/s]
Loading 0:  85%|████████▍ | 246/291 [00:07<00:01, 33.10it/s]
Loading 0:  86%|████████▌ | 250/291 [00:07<00:01, 32.61it/s]
Loading 0:  88%|████████▊ | 255/291 [00:07<00:01, 35.69it/s]
Loading 0:  89%|████████▉ | 259/291 [00:08<00:00, 34.32it/s]
Loading 0:  91%|█████████ | 264/291 [00:08<00:00, 37.74it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 35.89it/s]
Loading 0:  94%|█████████▍| 273/291 [00:08<00:00, 38.87it/s]
Loading 0:  96%|█████████▌| 278/291 [00:08<00:00, 37.76it/s]
Loading 0:  97%|█████████▋| 282/291 [00:08<00:00, 38.06it/s]
Loading 0:  98%|█████████▊| 286/291 [00:14<00:01,  2.52it/s]
Loading 0:  99%|█████████▉| 289/291 [00:14<00:00,  3.14it/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-v2-mkmlizer:   warnings.warn(
trace2333-duduk-llama3-v3-v2-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-v2-mkmlizer:   warnings.warn(
trace2333-duduk-llama3-v3-v2-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-v3-v2-mkmlizer:   warnings.warn(
trace2333-duduk-llama3-v3-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
trace2333-duduk-llama3-v3-v2-mkmlizer: Saving duration: 1.398s
trace2333-duduk-llama3-v3-v2-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.866s
trace2333-duduk-llama3-v3-v2-mkmlizer: creating bucket guanaco-reward-models
trace2333-duduk-llama3-v3-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
trace2333-duduk-llama3-v3-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/trace2333-duduk-llama3-v3-v2_reward
trace2333-duduk-llama3-v3-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/trace2333-duduk-llama3-v3-v2_reward/config.json
trace2333-duduk-llama3-v3-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/trace2333-duduk-llama3-v3-v2_reward/tokenizer_config.json
trace2333-duduk-llama3-v3-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/trace2333-duduk-llama3-v3-v2_reward/special_tokens_map.json
trace2333-duduk-llama3-v3-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/trace2333-duduk-llama3-v3-v2_reward/merges.txt
trace2333-duduk-llama3-v3-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/trace2333-duduk-llama3-v3-v2_reward/vocab.json
trace2333-duduk-llama3-v3-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/trace2333-duduk-llama3-v3-v2_reward/tokenizer.json
trace2333-duduk-llama3-v3-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/trace2333-duduk-llama3-v3-v2_reward/reward.tensors
Job trace2333-duduk-llama3-v3-v2-mkmlizer completed after 135.51s with status: succeeded
Stopping job with name trace2333-duduk-llama3-v3-v2-mkmlizer
Pipeline stage MKMLizer completed in 136.61s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-duduk-llama3-v3-v2
Waiting for inference service trace2333-duduk-llama3-v3-v2 to be ready
Inference service trace2333-duduk-llama3-v3-v2 ready after 110.80607318878174s
Pipeline stage ISVCDeployer completed in 112.61s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.192211627960205s
Received healthy response to inference request in 1.4391522407531738s
Received healthy response to inference request in 1.3928627967834473s
Received healthy response to inference request in 1.3361313343048096s
Received healthy response to inference request in 1.3817510604858398s
5 requests
0 failed requests
5th percentile: 1.3452552795410155
10th percentile: 1.3543792247772217
20th percentile: 1.3726271152496339
30th percentile: 1.3839734077453614
40th percentile: 1.3884181022644042
50th percentile: 1.3928627967834473
60th percentile: 1.4113785743713378
70th percentile: 1.4298943519592284
80th percentile: 1.5897641181945803
90th percentile: 1.8909878730773926
95th percentile: 2.041599750518799
99th percentile: 2.1620892524719237
mean time: 1.548421812057495
Pipeline stage StressChecker completed in 8.40s
trace2333-duduk-llama3-v3_v2 status is now deployed due to DeploymentManager action
trace2333-duduk-llama3-v3_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of trace2333-duduk-llama3-v3_v2
Running pipeline stage ISVCDeleter
Checking if service trace2333-duduk-llama3-v3-v2 is running
Tearing down inference service trace2333-duduk-llama3-v3-v2
Service trace2333-duduk-llama3-v3-v2 has been torndown
Pipeline stage ISVCDeleter completed in 5.17s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key trace2333-duduk-llama3-v3-v2/config.json from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama3-v3-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama3-v3-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama3-v3-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama3-v3-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key trace2333-duduk-llama3-v3-v2_reward/config.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v3-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v3-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v3-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v3-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v3-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v3-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.50s
trace2333-duduk-llama3-v3_v2 status is now torndown due to DeploymentManager action