trace2333-duduk-llama3-v1

developer_uid: Trace2333

submission_id: trace2333-duduk-llama3-v1_v5

model_name: trace2333-duduk-llama3-v1_v4

model_group: Trace2333/duduk_llama3_v

status: torndown

timestamp: 2024-07-24T05:07:16+00:00

num_battles: 25074

num_wins: 12005

celo_rating: 1171.35

family_friendly_score: 0.0

submission_type: basic

model_repo: Trace2333/duduk_llama3_v1

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-v1_v4

is_internal_developer: False

language_model: Trace2333/duduk_llama3_v1

model_size: 8B

ranking_group: single

us_pacific_date: 2024-07-23

win_ratio: 0.4787828029034059

generation_params: {'temperature': 1.15, '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}

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-v1-v5-mkmlizer
Waiting for job on trace2333-duduk-llama3-v1-v5-mkmlizer to finish
trace2333-duduk-llama3-v1-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-duduk-llama3-v1-v5-mkmlizer: ║     _____            __           __                                ║
trace2333-duduk-llama3-v1-v5-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-duduk-llama3-v1-v5-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-duduk-llama3-v1-v5-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-duduk-llama3-v1-v5-mkmlizer: ║       /___/                                                         ║
trace2333-duduk-llama3-v1-v5-mkmlizer: ║                                                                     ║
trace2333-duduk-llama3-v1-v5-mkmlizer: ║  Version: 0.9.6                                                     ║
trace2333-duduk-llama3-v1-v5-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-duduk-llama3-v1-v5-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-duduk-llama3-v1-v5-mkmlizer: ║                                                                     ║
trace2333-duduk-llama3-v1-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-duduk-llama3-v1-v5-mkmlizer: ║  belonging to:                                                      ║
trace2333-duduk-llama3-v1-v5-mkmlizer: ║                                                                     ║
trace2333-duduk-llama3-v1-v5-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-duduk-llama3-v1-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-duduk-llama3-v1-v5-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
trace2333-duduk-llama3-v1-v5-mkmlizer: ║                                                                     ║
trace2333-duduk-llama3-v1-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-duduk-llama3-v1-v5-mkmlizer: Downloaded to shared memory in 40.966s
trace2333-duduk-llama3-v1-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpj_1tiki3, device:0
trace2333-duduk-llama3-v1-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-duduk-llama3-v1-v5-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:10, 26.40it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:07, 35.10it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:08, 32.42it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:07, 34.97it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:08, 32.95it/s]
Loading 0:  10%|█         | 30/291 [00:00<00:07, 37.12it/s]
Loading 0:  12%|█▏        | 34/291 [00:01<00:10, 24.62it/s]
Loading 0:  13%|█▎        | 38/291 [00:01<00:09, 25.83it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:10, 23.31it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:07, 30.83it/s]
Loading 0:  18%|█▊        | 52/291 [00:01<00:07, 30.08it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:07, 32.87it/s]
Loading 0:  21%|██        | 61/291 [00:01<00:07, 32.22it/s]
Loading 0:  23%|██▎       | 66/291 [00:02<00:06, 34.67it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:06, 33.49it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:06, 33.88it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:06, 33.57it/s]
Loading 0:  28%|██▊       | 82/291 [00:02<00:08, 24.29it/s]
Loading 0:  30%|██▉       | 86/291 [00:02<00:07, 26.97it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:06, 29.59it/s]
Loading 0:  32%|███▏      | 94/291 [00:03<00:06, 30.00it/s]
Loading 0:  34%|███▍      | 99/291 [00:03<00:05, 33.97it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:05, 33.33it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:05, 36.30it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:05, 34.32it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:05, 34.84it/s]
Loading 0:  42%|████▏     | 122/291 [00:03<00:04, 39.72it/s]
Loading 0:  44%|████▎     | 127/291 [00:03<00:04, 37.42it/s]
Loading 0:  46%|████▌     | 133/291 [00:04<00:04, 32.53it/s]
Loading 0:  47%|████▋     | 137/291 [00:04<00:04, 32.59it/s]
Loading 0:  48%|████▊     | 141/291 [00:04<00:05, 29.60it/s]
Loading 0:  51%|█████     | 147/291 [00:04<00:04, 34.90it/s]
Loading 0:  52%|█████▏    | 151/291 [00:04<00:04, 34.38it/s]
Loading 0:  54%|█████▎    | 156/291 [00:04<00:03, 37.05it/s]
Loading 0:  55%|█████▍    | 160/291 [00:04<00:03, 35.71it/s]
Loading 0:  57%|█████▋    | 165/291 [00:05<00:03, 38.15it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 36.37it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 38.31it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 36.19it/s]
Loading 0:  63%|██████▎   | 184/291 [00:05<00:02, 42.05it/s]
Loading 0:  65%|██████▍   | 189/291 [00:05<00:03, 25.80it/s]
Loading 0:  67%|██████▋   | 194/291 [00:06<00:03, 27.30it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:02, 34.08it/s]
Loading 0:  71%|███████   | 206/291 [00:06<00:02, 34.68it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 35.78it/s]
Loading 0:  74%|███████▎  | 214/291 [00:06<00:02, 34.91it/s]
Loading 0:  75%|███████▌  | 219/291 [00:06<00:01, 36.56it/s]
Loading 0:  77%|███████▋  | 223/291 [00:06<00:01, 34.63it/s]
Loading 0:  78%|███████▊  | 227/291 [00:06<00:01, 35.00it/s]
Loading 0:  79%|███████▉  | 231/291 [00:07<00:01, 35.44it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 26.38it/s]
Loading 0:  82%|████████▏ | 239/291 [00:07<00:01, 26.46it/s]
Loading 0:  85%|████████▍ | 246/291 [00:07<00:01, 34.52it/s]
Loading 0:  86%|████████▌ | 250/291 [00:07<00:01, 34.14it/s]
Loading 0:  88%|████████▊ | 255/291 [00:07<00:00, 37.12it/s]
Loading 0:  89%|████████▉ | 259/291 [00:07<00:00, 35.95it/s]
Loading 0:  91%|█████████ | 264/291 [00:08<00:00, 38.19it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 34.96it/s]
Loading 0:  94%|█████████▍| 273/291 [00:08<00:00, 37.74it/s]
Loading 0:  95%|█████████▌| 277/291 [00:08<00:00, 35.69it/s]
Loading 0:  97%|█████████▋| 281/291 [00:08<00:00, 35.08it/s]
Loading 0:  98%|█████████▊| 286/291 [00:14<00:01,  2.60it/s]
Loading 0:  99%|█████████▉| 289/291 [00:14<00:00,  3.24it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
trace2333-duduk-llama3-v1-v5-mkmlizer: quantized model in 28.524s
trace2333-duduk-llama3-v1-v5-mkmlizer: Processed model Trace2333/duduk_llama3_v1 in 69.490s
trace2333-duduk-llama3-v1-v5-mkmlizer: creating bucket guanaco-mkml-models
trace2333-duduk-llama3-v1-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-duduk-llama3-v1-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-duduk-llama3-v1-v5
trace2333-duduk-llama3-v1-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v1-v5/config.json
trace2333-duduk-llama3-v1-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v1-v5/special_tokens_map.json
trace2333-duduk-llama3-v1-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v1-v5/tokenizer_config.json
trace2333-duduk-llama3-v1-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v1-v5/tokenizer.json
trace2333-duduk-llama3-v1-v5-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
trace2333-duduk-llama3-v1-v5-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-duduk-llama3-v1-v5-mkmlizer:   warnings.warn(
trace2333-duduk-llama3-v1-v5-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-duduk-llama3-v1-v5-mkmlizer:   warnings.warn(
trace2333-duduk-llama3-v1-v5-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-v1-v5-mkmlizer:   warnings.warn(
trace2333-duduk-llama3-v1-v5-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
trace2333-duduk-llama3-v1-v5-mkmlizer: Saving duration: 1.362s
trace2333-duduk-llama3-v1-v5-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 12.176s
trace2333-duduk-llama3-v1-v5-mkmlizer: creating bucket guanaco-reward-models
trace2333-duduk-llama3-v1-v5-mkmlizer: Bucket 's3://guanaco-reward-models/' created
trace2333-duduk-llama3-v1-v5-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/trace2333-duduk-llama3-v1-v5_reward
trace2333-duduk-llama3-v1-v5-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/trace2333-duduk-llama3-v1-v5_reward/special_tokens_map.json
trace2333-duduk-llama3-v1-v5-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/trace2333-duduk-llama3-v1-v5_reward/config.json
trace2333-duduk-llama3-v1-v5-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/trace2333-duduk-llama3-v1-v5_reward/tokenizer_config.json
trace2333-duduk-llama3-v1-v5-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/trace2333-duduk-llama3-v1-v5_reward/merges.txt
trace2333-duduk-llama3-v1-v5-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/trace2333-duduk-llama3-v1-v5_reward/vocab.json
trace2333-duduk-llama3-v1-v5-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/trace2333-duduk-llama3-v1-v5_reward/tokenizer.json
trace2333-duduk-llama3-v1-v5-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/trace2333-duduk-llama3-v1-v5_reward/reward.tensors
Job trace2333-duduk-llama3-v1-v5-mkmlizer completed after 115.87s with status: succeeded
Stopping job with name trace2333-duduk-llama3-v1-v5-mkmlizer
Pipeline stage MKMLizer completed in 116.76s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-duduk-llama3-v1-v5
Waiting for inference service trace2333-duduk-llama3-v1-v5 to be ready
Failed to get response for submission chaiml-sao10k-l3-rp-v3-3_v56: ('http://chaiml-sao10k-l3-rp-v3-3-v56-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:59728->127.0.0.1:8080: read: connection reset by peer\n')
Failed to get response for submission blend_kobem_2024-07-23: ('http://undi95-meta-llama-3-70b-6209-v18-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"TypeError : SamplingParameters.__init__() got an unexpected keyword argument \'reward_max_tokens\'"}')
Inference service trace2333-duduk-llama3-v1-v5 ready after 80.877521276474s
Pipeline stage ISVCDeployer completed in 82.49s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3764896392822266s
Received healthy response to inference request in 1.4562616348266602s
Received healthy response to inference request in 1.4427735805511475s
Received healthy response to inference request in 1.384232759475708s
Received healthy response to inference request in 1.1800243854522705s
5 requests
0 failed requests
5th percentile: 1.220866060256958
10th percentile: 1.2617077350616455
20th percentile: 1.3433910846710204
30th percentile: 1.3959409236907958
40th percentile: 1.4193572521209716
50th percentile: 1.4427735805511475
60th percentile: 1.4481688022613526
70th percentile: 1.4535640239715577
80th percentile: 1.6403072357177737
90th percentile: 2.0083984375
95th percentile: 2.192444038391113
99th percentile: 2.3396805191040038
mean time: 1.5679563999176025
Pipeline stage StressChecker completed in 8.73s
trace2333-duduk-llama3-v1_v5 status is now deployed due to DeploymentManager action
trace2333-duduk-llama3-v1_v5 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of trace2333-duduk-llama3-v1_v5
Running pipeline stage ISVCDeleter
Checking if service trace2333-duduk-llama3-v1-v5 is running
Tearing down inference service trace2333-duduk-llama3-v1-v5
Service trace2333-duduk-llama3-v1-v5 has been torndown
Pipeline stage ISVCDeleter completed in 5.64s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key trace2333-duduk-llama3-v1-v5/config.json from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama3-v1-v5/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama3-v1-v5/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama3-v1-v5/tokenizer.json from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama3-v1-v5/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key trace2333-duduk-llama3-v1-v5_reward/config.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v1-v5_reward/merges.txt from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v1-v5_reward/reward.tensors from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v1-v5_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v1-v5_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v1-v5_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v1-v5_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.95s
trace2333-duduk-llama3-v1_v5 status is now torndown due to DeploymentManager action