developer_uid: robert_irvine
submission_id: chaiml-sao10k-l3-rp-v3-3_v72
model_name: chaiml-sao10k-l3-rp-v3-3_v72
model_group: ChaiML/sao10k-l3-rp-v3-3
status: torndown
timestamp: 2024-08-01T18:56:21+00:00
num_battles: 32032
num_wins: 16353
celo_rating: 1232.09
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_1560
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
display_name: chaiml-sao10k-l3-rp-v3-3_v72
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: 0.5105207292707292
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-v72-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer to finish
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: ║ _____ __ __ ║
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: ║ /___/ ║
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: ║ Version: 0.9.7 ║
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: ║ https://mk1.ai ║
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: ║ belonging to: ║
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: ║ Chai Research Corp. ║
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: Downloaded to shared memory in 22.796s
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpk_zgx6op, device:0
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission blend_sugom_2024-08-01: 'BlendChatApi' object has no attribute 'tags'
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: quantized model in 25.822s
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: Processed model ChaiML/sao10k-l3-rp-v3-3 in 48.618s
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v72
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v72/config.json
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v72/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v72/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v72/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v72/flywheel_model.0.safetensors
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: loading reward model from rirv938/retune_gpt2_xl_on_chaiml_sao10k_step_1560
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:24, 2.37s/it] Loading 0: 2%|▏ | 6/291 [00:04<03:02, 1.56it/s] Loading 0: 4%|▍ | 13/291 [00:04<01:05, 4.26it/s] Loading 0: 7%|▋ | 19/291 [00:05<00:37, 7.22it/s] Loading 0: 8%|▊ | 24/291 [00:05<00:27, 9.83it/s] Loading 0: 11%|█ | 32/291 [00:05<00:16, 16.04it/s] Loading 0: 13%|█▎ | 38/291 [00:05<00:12, 20.05it/s] Loading 0: 15%|█▌ | 44/291 [00:05<00:09, 24.87it/s] Loading 0: 17%|█▋ | 50/291 [00:05<00:07, 30.34it/s] Loading 0: 19%|█▉ | 56/291 [00:05<00:07, 32.52it/s] Loading 0: 21%|██ | 61/291 [00:06<00:08, 26.25it/s] Loading 0: 23%|██▎ | 68/291 [00:06<00:06, 32.99it/s] Loading 0: 25%|██▌ | 74/291 [00:06<00:06, 35.03it/s] Loading 0: 27%|██▋ | 79/291 [00:06<00:05, 37.11it/s] Loading 0: 30%|██▉ | 86/291 [00:06<00:04, 43.04it/s] Loading 0: 32%|███▏ | 92/291 [00:06<00:04, 41.75it/s] Loading 0: 33%|███▎ | 97/291 [00:06<00:04, 42.04it/s] Loading 0: 36%|███▌ | 104/291 [00:07<00:03, 47.94it/s] Loading 0: 38%|███▊ | 110/291 [00:07<00:03, 46.09it/s] Loading 0: 40%|███▉ | 115/291 [00:07<00:03, 46.07it/s] Loading 0: 42%|████▏ | 122/291 [00:07<00:03, 51.68it/s] Loading 0: 44%|████▍ | 128/291 [00:07<00:03, 47.35it/s] Loading 0: 46%|████▌ | 133/291 [00:07<00:03, 46.13it/s] Loading 0: 48%|████▊ | 140/291 [00:07<00:02, 51.67it/s] Loading 0: 50%|█████ | 146/291 [00:07<00:02, 48.61it/s] Loading 0: 52%|█████▏ | 152/291 [00:08<00:02, 47.93it/s] Loading 0: 54%|█████▍ | 158/291 [00:08<00:02, 50.84it/s] Loading 0: 56%|█████▋ | 164/291 [00:08<00:02, 48.07it/s] Loading 0: 58%|█████▊ | 169/291 [00:08<00:03, 33.12it/s] Loading 0: 60%|██████ | 176/291 [00:08<00:02, 39.70it/s] Loading 0: 63%|██████▎ | 182/291 [00:08<00:02, 39.69it/s] Loading 0: 64%|██████▍ | 187/291 [00:08<00:02, 40.62it/s] Loading 0: 67%|██████▋ | 194/291 [00:09<00:02, 47.10it/s] Loading 0: 69%|██████▊ | 200/291 [00:09<00:02, 45.43it/s] Loading 0: 70%|███████ | 205/291 [00:09<00:01, 44.53it/s] Loading 0: 73%|███████▎ | 211/291 [00:09<00:01, 47.95it/s] Loading 0: 75%|███████▍ | 217/291 [00:09<00:01, 49.82it/s] Loading 0: 77%|███████▋ | 223/291 [00:09<00:01, 45.52it/s] Loading 0: 79%|███████▉ | 230/291 [00:09<00:01, 51.07it/s] Loading 0: 81%|████████ | 236/291 [00:09<00:01, 49.04it/s] Loading 0: 83%|████████▎ | 242/291 [00:09<00:00, 50.27it/s] Loading 0: 85%|████████▌ | 248/291 [00:10<00:00, 52.35it/s] Loading 0: 87%|████████▋ | 254/291 [00:10<00:00, 48.39it/s] Loading 0: 89%|████████▉ | 259/291 [00:10<00:00, 46.59it/s] Loading 0: 91%|█████████▏| 266/291 [00:10<00:00, 35.60it/s] Loading 0: 93%|█████████▎| 272/291 [00:10<00:00, 37.35it/s] Loading 0: 95%|█████████▌| 277/291 [00:10<00:00, 39.64it/s] Loading 0: 98%|█████████▊| 284/291 [00:11<00:00, 45.62it/s] Loading 0: 100%|█████████▉| 290/291 [00:11<00:00, 44.48it/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-v72-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v72-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-v72-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v72-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-v72-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: Saving duration: 1.441s
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: Processed model rirv938/retune_gpt2_xl_on_chaiml_sao10k_step_1560 in 11.536s
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: creating bucket guanaco-reward-models
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v72_reward
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v72_reward/config.json
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v72_reward/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v72_reward/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v72_reward/merges.txt
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v72_reward/vocab.json
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v72_reward/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v72_reward/reward.tensors
Job chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer completed after 94.6s with status: succeeded
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v72-mkmlizer
Pipeline stage MKMLizer completed in 95.51s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-sao10k-l3-rp-v3-3-v72
Waiting for inference service chaiml-sao10k-l3-rp-v3-3-v72 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Failed to get response for submission blend_sugom_2024-08-01: 'BlendChatApi' object has no attribute 'tags'
Failed to get response for submission blend_sugom_2024-08-01: 'BlendChatApi' object has no attribute 'tags'
Failed to get response for submission blend_sugom_2024-08-01: 'BlendChatApi' object has no attribute 'tags'
Inference service chaiml-sao10k-l3-rp-v3-3-v72 ready after 131.13583326339722s
Pipeline stage ISVCDeployer completed in 132.33s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.078354597091675s
Received healthy response to inference request in 1.1998672485351562s
Received healthy response to inference request in 1.2566373348236084s
Received healthy response to inference request in 1.2837445735931396s
Failed to get response for submission blend_sugom_2024-08-01: 'BlendChatApi' object has no attribute 'tags'
Received healthy response to inference request in 1.230236530303955s
5 requests
0 failed requests
5th percentile: 1.205941104888916
10th percentile: 1.2120149612426758
20th percentile: 1.2241626739501954
30th percentile: 1.2355166912078857
40th percentile: 1.246077013015747
50th percentile: 1.2566373348236084
60th percentile: 1.267480230331421
70th percentile: 1.2783231258392334
80th percentile: 1.4426665782928467
90th percentile: 1.7605105876922609
95th percentile: 1.9194325923919677
99th percentile: 2.0465701961517335
mean time: 1.4097680568695068
Pipeline stage StressChecker completed in 7.80s
chaiml-sao10k-l3-rp-v3-3_v72 status is now deployed due to DeploymentManager action
chaiml-sao10k-l3-rp-v3-3_v72 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-sao10k-l3-rp-v3-3_v72
Running pipeline stage ISVCDeleter
Checking if service chaiml-sao10k-l3-rp-v3-3-v72 is running
Tearing down inference service chaiml-sao10k-l3-rp-v3-3-v72
Service chaiml-sao10k-l3-rp-v3-3-v72 has been torndown
Pipeline stage ISVCDeleter completed in 4.60s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v72/config.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v72/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v72/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v72/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v72/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v72_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v72_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v72_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v72_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v72_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v72_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v72_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.46s
chaiml-sao10k-l3-rp-v3-3_v72 status is now torndown due to DeploymentManager action