chaiml-sao10k-l3-rp-v3-3

developer_uid: robert_irvine

submission_id: chaiml-sao10k-l3-rp-v3-3_v57

model_name: chaiml-sao10k-l3-rp-v3-3_v57

model_group: ChaiML/sao10k-l3-rp-v3-3

status: torndown

timestamp: 2024-07-24T15:27:36+00:00

num_battles: 22217

num_wins: 9994

celo_rating: 1150.12

family_friendly_score: 0.0

submission_type: basic

model_repo: ChaiML/sao10k-l3-rp-v3-3

model_architecture: LlamaForCausalLM

reward_repo: rirv938/gpt2_rep_weakly_disagree_512

model_num_parameters: 8030261248.0

best_of: 1

max_input_tokens: 512

max_output_tokens: 64

display_name: chaiml-sao10k-l3-rp-v3-3_v57

is_internal_developer: True

language_model: ChaiML/sao10k-l3-rp-v3-3

model_size: 8B

ranking_group: single

us_pacific_date: 2024-07-24

win_ratio: 0.44983571139217715

generation_params: {'temperature': 0.95, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>,', '<|eot_id|>,', '\n\n{user_name}'], 'max_input_tokens': 512, 'best_of': 1, 'max_output_tokens': 64, 'reward_max_token_input': 512}

formatter: {'memory_template': "<|begin_of_text|><|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\n{user_name}: {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: {message}\n', 'memory_template': '', 'prompt_template': '', 'response_template': 'Bot:', 'truncate_by_message': False, 'user_template': 'User: {message}\n'}

Resubmit model

Running pipeline stage MKMLizer
Starting job with name chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer to finish
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: ║     _____            __           __                                ║
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: ║       /___/                                                         ║
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: ║  Version: 0.9.6                                                     ║
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: ║  belonging to:                                                      ║
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: Downloaded to shared memory in 32.746s
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpi_odnxvp, device:0
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission blend_dunet_2024-07-19: ('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\'"}')
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:31,  2.39s/it]
Loading 0:   2%|▏         | 6/291 [00:04<03:03,  1.55it/s]
Loading 0:   4%|▍         | 13/291 [00:05<01:05,  4.24it/s]
Loading 0:   7%|▋         | 20/291 [00:05<00:35,  7.58it/s]
Loading 0:   9%|▉         | 27/291 [00:05<00:22, 11.87it/s]
Loading 0:  11%|█▏        | 33/291 [00:05<00:16, 15.51it/s]
Loading 0:  14%|█▍        | 41/291 [00:05<00:11, 22.20it/s]
Loading 0:  16%|█▌        | 47/291 [00:05<00:09, 26.12it/s]
Loading 0:  18%|█▊        | 53/291 [00:05<00:07, 30.54it/s]
Loading 0:  20%|██        | 59/291 [00:05<00:06, 35.11it/s]
Loading 0:  22%|██▏       | 65/291 [00:06<00:08, 27.37it/s]
Loading 0:  24%|██▍       | 70/291 [00:06<00:07, 30.73it/s]
Loading 0:  26%|██▋       | 77/291 [00:06<00:05, 37.58it/s]
Loading 0:  29%|██▊       | 83/291 [00:06<00:05, 38.01it/s]
Loading 0:  30%|███       | 88/291 [00:06<00:05, 39.15it/s]
Loading 0:  33%|███▎      | 95/291 [00:06<00:04, 44.83it/s]
Loading 0:  35%|███▍      | 101/291 [00:06<00:04, 43.00it/s]
Loading 0:  36%|███▋      | 106/291 [00:07<00:04, 43.10it/s]
Loading 0:  39%|███▉      | 113/291 [00:07<00:03, 49.39it/s]
Loading 0:  41%|████      | 119/291 [00:07<00:03, 45.21it/s]
Loading 0:  43%|████▎     | 124/291 [00:07<00:03, 44.28it/s]
Loading 0:  45%|████▌     | 131/291 [00:07<00:03, 49.94it/s]
Loading 0:  47%|████▋     | 137/291 [00:07<00:03, 44.30it/s]
Loading 0:  49%|████▉     | 142/291 [00:07<00:03, 42.40it/s]
Loading 0:  51%|█████     | 148/291 [00:07<00:03, 46.12it/s]
Loading 0:  53%|█████▎    | 153/291 [00:08<00:03, 45.87it/s]
Loading 0:  55%|█████▍    | 159/291 [00:08<00:03, 40.67it/s]
Loading 0:  57%|█████▋    | 166/291 [00:08<00:03, 34.63it/s]
Loading 0:  58%|█████▊    | 170/291 [00:08<00:03, 35.48it/s]
Loading 0:  60%|██████    | 176/291 [00:08<00:02, 39.78it/s]
Loading 0:  63%|██████▎   | 182/291 [00:08<00:02, 40.07it/s]
Loading 0:  64%|██████▍   | 187/291 [00:09<00:02, 40.68it/s]
Loading 0:  67%|██████▋   | 194/291 [00:09<00:02, 46.41it/s]
Loading 0:  69%|██████▊   | 200/291 [00:09<00:02, 44.08it/s]
Loading 0:  70%|███████   | 205/291 [00:09<00:01, 44.63it/s]
Loading 0:  73%|███████▎  | 212/291 [00:09<00:01, 49.18it/s]
Loading 0:  75%|███████▍  | 218/291 [00:09<00:01, 45.65it/s]
Loading 0:  77%|███████▋  | 223/291 [00:09<00:01, 45.41it/s]
Loading 0:  79%|███████▉  | 230/291 [00:09<00:01, 50.80it/s]
Loading 0:  81%|████████  | 236/291 [00:10<00:01, 47.62it/s]
Loading 0:  83%|████████▎ | 241/291 [00:10<00:01, 44.90it/s]
Loading 0:  85%|████████▌ | 248/291 [00:10<00:00, 49.21it/s]
Loading 0:  87%|████████▋ | 254/291 [00:10<00:00, 44.73it/s]
Loading 0:  89%|████████▉ | 259/291 [00:10<00:00, 44.69it/s]
Loading 0:  91%|█████████ | 265/291 [00:10<00:00, 48.15it/s]
Loading 0:  93%|█████████▎| 270/291 [00:10<00:00, 32.83it/s]
Loading 0:  95%|█████████▍| 276/291 [00:11<00:00, 33.56it/s]
Loading 0:  98%|█████████▊| 284/291 [00:11<00:00, 42.27it/s]
Loading 0: 100%|█████████▉| 290/291 [00:11<00:00, 41.99it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: quantized model in 26.208s
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: Processed model ChaiML/sao10k-l3-rp-v3-3 in 58.954s
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v57
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v57/config.json
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v57/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v57/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v57/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v57/flywheel_model.0.safetensors
chaiml-sao10k-l3-rp-v3-3-v57-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.
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer:   warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v57-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.
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer:   warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:08<00:08,  8.07s/it]
Downloading shards: 100%|██████████| 2/2 [00:21<00:00, 11.11s/it]
Downloading shards: 100%|██████████| 2/2 [00:21<00:00, 10.66s/it]
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  2.47it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.95it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.63it/s]
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: Saving duration: 1.363s
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: Processed model rirv938/gpt2_rep_weakly_disagree_512 in 26.332s
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: creating bucket guanaco-reward-models
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v57_reward
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v57_reward/config.json
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v57_reward/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v57_reward/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v57_reward/merges.txt
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v57_reward/vocab.json
chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v57_reward/tokenizer.json
Job chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer completed after 118.19s with status: succeeded
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v57-mkmlizer
Pipeline stage MKMLizer completed in 119.37s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.34s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-sao10k-l3-rp-v3-3-v57
Waiting for inference service chaiml-sao10k-l3-rp-v3-3-v57 to be ready
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\'"}')
Failed to get response for submission undi95-meta-llama-3-70b_6209_v18: ('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 chaiml-sao10k-l3-rp-v3-3-v57 ready after 60.61930823326111s
Pipeline stage ISVCDeployer completed in 62.23s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.525622844696045s
Received healthy response to inference request in 0.3949124813079834s
Received healthy response to inference request in 1.0579047203063965s
Received healthy response to inference request in 0.9695703983306885s
Received healthy response to inference request in 0.9441664218902588s
5 requests
0 failed requests
5th percentile: 0.5047632694244385
10th percentile: 0.6146140575408936
20th percentile: 0.8343156337738037
30th percentile: 0.9492472171783447
40th percentile: 0.9594088077545166
50th percentile: 0.9695703983306885
60th percentile: 1.0049041271209718
70th percentile: 1.0402378559112548
80th percentile: 1.1514483451843263
90th percentile: 1.3385355949401856
95th percentile: 1.4320792198181151
99th percentile: 1.506914119720459
mean time: 0.9784353733062744
Pipeline stage StressChecker completed in 5.59s
chaiml-sao10k-l3-rp-v3-3_v57 status is now deployed due to DeploymentManager action
chaiml-sao10k-l3-rp-v3-3_v57 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-sao10k-l3-rp-v3-3_v57
Running pipeline stage ISVCDeleter
Checking if service chaiml-sao10k-l3-rp-v3-3-v57 is running
Tearing down inference service chaiml-sao10k-l3-rp-v3-3-v57
Service chaiml-sao10k-l3-rp-v3-3-v57 has been torndown
Pipeline stage ISVCDeleter completed in 5.13s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v57/config.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v57/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v57/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v57/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v57/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v57_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v57_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v57_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v57_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v57_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v57_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v57_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.56s
chaiml-sao10k-l3-rp-v3-3_v57 status is now torndown due to DeploymentManager action