chaiml-sao10k-l3-rp-v3-3

developer_uid: robert_irvine

submission_id: chaiml-sao10k-l3-rp-v3-3_v81

model_name: chaiml-sao10k-l3-rp-v3-3_v81

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

status: torndown

timestamp: 2024-08-01T21:35:21+00:00

num_battles: 15672

num_wins: 8010

celo_rating: 1230.52

family_friendly_score: 0.0

submission_type: basic

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

model_architecture: LlamaForCausalLM

reward_repo: rirv938/retune_gpt2_xl_on_chaiml_sao10k_step_195

model_num_parameters: 8030261248.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

display_name: chaiml-sao10k-l3-rp-v3-3_v81

is_internal_developer: True

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

model_size: 8B

ranking_group: single

us_pacific_date: 2024-08-01

win_ratio: 0.5111026033690659

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': 1024, 'best_of': 8, 'max_output_tokens': 64, 'reward_max_token_input': 256}

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-v81-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer to finish
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: ║     _____            __           __                                ║
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: ║       /___/                                                         ║
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: ║  Version: 0.9.7                                                     ║
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: ║  belonging to:                                                      ║
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: Downloaded to shared memory in 21.727s
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp1s0m424r, device:0
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: quantized model in 25.917s
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: Processed model ChaiML/sao10k-l3-rp-v3-3 in 47.645s
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v81
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v81/config.json
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v81/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v81/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v81/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v81/flywheel_model.0.safetensors
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: loading reward model from rirv938/retune_gpt2_xl_on_chaiml_sao10k_step_195
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:23,  2.36s/it]
Loading 0:   2%|▏         | 6/291 [00:04<03:01,  1.57it/s]
Loading 0:   5%|▍         | 14/291 [00:04<00:59,  4.66it/s]
Loading 0:   7%|▋         | 20/291 [00:05<00:36,  7.50it/s]
Loading 0:   9%|▊         | 25/291 [00:05<00:25, 10.43it/s]
Loading 0:  11%|█▏        | 33/291 [00:05<00:16, 15.74it/s]
Loading 0:  14%|█▍        | 42/291 [00:05<00:11, 22.29it/s]
Loading 0:  18%|█▊        | 51/291 [00:05<00:08, 28.27it/s]
Loading 0:  20%|██        | 59/291 [00:05<00:06, 35.27it/s]
Loading 0:  22%|██▏       | 65/291 [00:06<00:08, 28.05it/s]
Loading 0:  24%|██▍       | 70/291 [00:06<00:07, 30.50it/s]
Loading 0:  26%|██▋       | 77/291 [00:06<00:05, 37.05it/s]
Loading 0:  29%|██▊       | 83/291 [00:06<00:05, 38.04it/s]
Loading 0:  30%|███       | 88/291 [00:06<00:05, 39.68it/s]
Loading 0:  33%|███▎      | 95/291 [00:06<00:04, 45.97it/s]
Loading 0:  35%|███▍      | 101/291 [00:06<00:04, 45.63it/s]
Loading 0:  37%|███▋      | 107/291 [00:06<00:03, 47.02it/s]
Loading 0:  39%|███▉      | 113/291 [00:07<00:03, 49.41it/s]
Loading 0:  41%|████      | 119/291 [00:07<00:03, 46.58it/s]
Loading 0:  43%|████▎     | 124/291 [00:07<00:03, 45.08it/s]
Loading 0:  45%|████▌     | 132/291 [00:07<00:03, 45.62it/s]
Loading 0:  48%|████▊     | 140/291 [00:07<00:02, 52.81it/s]
Loading 0:  50%|█████     | 146/291 [00:07<00:02, 50.08it/s]
Loading 0:  52%|█████▏    | 152/291 [00:07<00:02, 51.38it/s]
Loading 0:  54%|█████▍    | 158/291 [00:08<00:02, 52.88it/s]
Loading 0:  56%|█████▋    | 164/291 [00:08<00:02, 47.94it/s]
Loading 0:  58%|█████▊    | 169/291 [00:08<00:03, 33.46it/s]
Loading 0:  60%|██████    | 176/291 [00:08<00:02, 40.42it/s]
Loading 0:  63%|██████▎   | 182/291 [00:08<00:02, 40.49it/s]
Loading 0:  64%|██████▍   | 187/291 [00:08<00:02, 40.61it/s]
Loading 0:  67%|██████▋   | 194/291 [00:08<00:02, 46.36it/s]
Loading 0:  69%|██████▊   | 200/291 [00:09<00:02, 45.49it/s]
Loading 0:  70%|███████   | 205/291 [00:09<00:01, 45.82it/s]
Loading 0:  73%|███████▎  | 212/291 [00:09<00:01, 51.78it/s]
Loading 0:  75%|███████▍  | 218/291 [00:09<00:01, 49.38it/s]
Loading 0:  77%|███████▋  | 224/291 [00:09<00:01, 50.61it/s]
Loading 0:  79%|███████▉  | 231/291 [00:09<00:01, 47.40it/s]
Loading 0:  82%|████████▏ | 238/291 [00:09<00:01, 51.82it/s]
Loading 0:  84%|████████▍ | 244/291 [00:09<00:00, 51.56it/s]
Loading 0:  86%|████████▌ | 250/291 [00:10<00:00, 44.02it/s]
Loading 0:  88%|████████▊ | 256/291 [00:10<00:00, 46.89it/s]
Loading 0:  90%|████████▉ | 261/291 [00:10<00:00, 45.65it/s]
Loading 0:  91%|█████████▏| 266/291 [00:10<00:00, 33.33it/s]
Loading 0:  93%|█████████▎| 272/291 [00:10<00:00, 35.74it/s]
Loading 0:  95%|█████████▍| 276/291 [00:10<00:00, 36.27it/s]
Loading 0:  98%|█████████▊| 284/291 [00:10<00:00, 45.97it/s]
Loading 0: 100%|█████████▉| 290/291 [00:11<00:00, 45.01it/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.
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer:   warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v81-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.
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer:   warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v81-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-v81-mkmlizer:   warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: Saving duration: 1.394s
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: Processed model rirv938/retune_gpt2_xl_on_chaiml_sao10k_step_195 in 8.036s
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: creating bucket guanaco-reward-models
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v81_reward
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v81_reward/merges.txt
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v81_reward/vocab.json
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v81_reward/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v81_reward/reward.tensors
Job chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer completed after 84.44s with status: succeeded
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v81-mkmlizer
Pipeline stage MKMLizer completed in 85.41s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-sao10k-l3-rp-v3-3-v81
Waiting for inference service chaiml-sao10k-l3-rp-v3-3-v81 to be ready
Inference service chaiml-sao10k-l3-rp-v3-3-v81 ready after 131.18319654464722s
Pipeline stage ISVCDeployer completed in 132.84s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1616101264953613s
Received healthy response to inference request in 1.1855390071868896s
Received healthy response to inference request in 1.2538120746612549s
Received healthy response to inference request in 1.2467260360717773s
Received healthy response to inference request in 1.2023096084594727s
5 requests
0 failed requests
5th percentile: 1.1888931274414063
10th percentile: 1.192247247695923
20th percentile: 1.198955488204956
30th percentile: 1.2111928939819336
40th percentile: 1.2289594650268554
50th percentile: 1.2467260360717773
60th percentile: 1.2495604515075684
70th percentile: 1.2523948669433593
80th percentile: 1.4353716850280764
90th percentile: 1.7984909057617189
95th percentile: 1.9800505161285398
99th percentile: 2.125298204421997
mean time: 1.4099993705749512
Pipeline stage StressChecker completed in 7.75s
chaiml-sao10k-l3-rp-v3-3_v81 status is now deployed due to DeploymentManager action
chaiml-sao10k-l3-rp-v3-3_v81 status is now inactive due to auto deactivation removed underperforming models
chaiml-sao10k-l3-rp-v3-3_v81 status is now deployed due to admin request
chaiml-sao10k-l3-rp-v3-3_v81 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-sao10k-l3-rp-v3-3_v81
Running pipeline stage ISVCDeleter
Checking if service chaiml-sao10k-l3-rp-v3-3-v81 is running
Tearing down inference service chaiml-sao10k-l3-rp-v3-3-v81
Service chaiml-sao10k-l3-rp-v3-3-v81 has been torndown
Pipeline stage ISVCDeleter completed in 4.81s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v81/config.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v81/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v81/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v81/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v81/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v81_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v81_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v81_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v81_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v81_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v81_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v81_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.53s
chaiml-sao10k-l3-rp-v3-3_v81 status is now torndown due to DeploymentManager action