developer_uid: robert_irvine
submission_id: chaiml-sao10k-l3-rp-v3-3_v59
model_name: chaiml-sao10k-l3-rp-v3-3_v59
model_group: ChaiML/sao10k-l3-rp-v3-3
status: torndown
timestamp: 2024-07-24T15:29:29+00:00
num_battles: 21474
num_wins: 9978
celo_rating: 1158.81
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: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: chaiml-sao10k-l3-rp-v3-3_v59
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: 0.46465493154512433
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': 16, '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-v59-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer to finish
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: ║ _____ __ __ ║
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: ║ /___/ ║
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: ║ Version: 0.9.6 ║
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: ║ https://mk1.ai ║
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: ║ belonging to: ║
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: ║ Chai Research Corp. ║
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: Downloaded to shared memory in 29.859s
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3zj1libp, device:0
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:54, 2.47s/it] Loading 0: 2%|▏ | 6/291 [00:05<03:09, 1.50it/s] Loading 0: 4%|▍ | 13/291 [00:05<01:07, 4.09it/s] Loading 0: 7%|▋ | 19/291 [00:05<00:39, 6.95it/s] Loading 0: 8%|▊ | 24/291 [00:05<00:28, 9.46it/s] Loading 0: 11%|█ | 32/291 [00:05<00:16, 15.45it/s] Loading 0: 13%|█▎ | 38/291 [00:05<00:13, 19.33it/s] Loading 0: 15%|█▍ | 43/291 [00:05<00:10, 22.89it/s] Loading 0: 17%|█▋ | 50/291 [00:05<00:08, 29.77it/s] Loading 0: 19%|█▉ | 56/291 [00:06<00:07, 32.06it/s] Loading 0: 21%|██ | 61/291 [00:06<00:09, 24.82it/s] Loading 0: 23%|██▎ | 68/291 [00:06<00:07, 31.11it/s] Loading 0: 25%|██▌ | 74/291 [00:06<00:06, 32.78it/s] Loading 0: 27%|██▋ | 79/291 [00:06<00:06, 34.98it/s] Loading 0: 30%|██▉ | 86/291 [00:06<00:04, 41.72it/s] Loading 0: 32%|███▏ | 92/291 [00:07<00:04, 41.09it/s] Loading 0: 33%|███▎ | 97/291 [00:07<00:04, 41.00it/s] Loading 0: 35%|███▌ | 103/291 [00:07<00:04, 44.86it/s] Loading 0: 37%|███▋ | 108/291 [00:07<00:04, 45.28it/s] Loading 0: 39%|███▉ | 114/291 [00:07<00:04, 41.04it/s] Loading 0: 42%|████▏ | 122/291 [00:07<00:03, 49.74it/s] Loading 0: 44%|████▍ | 128/291 [00:07<00:03, 47.69it/s] Loading 0: 46%|████▌ | 134/291 [00:07<00:03, 49.52it/s] Loading 0: 48%|████▊ | 140/291 [00:08<00:02, 51.31it/s] Loading 0: 50%|█████ | 146/291 [00:08<00:03, 44.42it/s] Loading 0: 52%|█████▏ | 151/291 [00:08<00:03, 45.19it/s] Loading 0: 54%|█████▍ | 158/291 [00:08<00:02, 50.89it/s] Loading 0: 56%|█████▋ | 164/291 [00:08<00:02, 48.79it/s] Loading 0: 58%|█████▊ | 170/291 [00:08<00:03, 35.66it/s] Loading 0: 60%|██████ | 176/291 [00:08<00:02, 40.21it/s] Loading 0: 63%|██████▎ | 182/291 [00:09<00:02, 40.81it/s] Loading 0: 64%|██████▍ | 187/291 [00:09<00:02, 42.52it/s] Loading 0: 67%|██████▋ | 194/291 [00:09<00:01, 48.98it/s] Loading 0: 69%|██████▊ | 200/291 [00:09<00:01, 46.84it/s] Loading 0: 70%|███████ | 205/291 [00:09<00:01, 45.96it/s] Loading 0: 73%|███████▎ | 211/291 [00:09<00:01, 48.97it/s] Loading 0: 75%|███████▍ | 217/291 [00:09<00:01, 49.91it/s] Loading 0: 77%|███████▋ | 223/291 [00:09<00:01, 44.67it/s] Loading 0: 79%|███████▉ | 230/291 [00:10<00:01, 49.22it/s] Loading 0: 81%|████████ | 236/291 [00:10<00:01, 47.65it/s] Loading 0: 83%|████████▎ | 241/291 [00:10<00:01, 46.57it/s] Loading 0: 86%|████████▌ | 249/291 [00:10<00:00, 46.98it/s] Loading 0: 88%|████████▊ | 257/291 [00:10<00:00, 54.44it/s] Loading 0: 90%|█████████ | 263/291 [00:10<00:00, 49.63it/s] Loading 0: 92%|█████████▏| 269/291 [00:11<00:00, 35.85it/s] Loading 0: 95%|█████████▍| 275/291 [00:11<00:00, 40.21it/s] Loading 0: 97%|█████████▋| 281/291 [00:11<00:00, 41.16it/s] Loading 0: 98%|█████████▊| 286/291 [00:11<00:00, 42.38it/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-v59-mkmlizer: quantized model in 26.805s
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: Processed model ChaiML/sao10k-l3-rp-v3-3 in 56.664s
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v59
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v59/config.json
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v59/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v59/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v59/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v59/flywheel_model.0.safetensors
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: loading reward model from rirv938/gpt2_rep_weakly_disagree_512
chaiml-sao10k-l3-rp-v3-3-v59-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.
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v59-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-v59-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:05<00:05, 5.41s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.05s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.25s/it]
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: Saving duration: 1.374s
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: Processed model rirv938/gpt2_rep_weakly_disagree_512 in 13.480s
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: creating bucket guanaco-reward-models
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v59_reward
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v59_reward/config.json
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v59_reward/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v59_reward/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v59_reward/merges.txt
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v59_reward/vocab.json
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v59_reward/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v59_reward/reward.tensors
Job chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer completed after 111.79s with status: succeeded
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v59-mkmlizer
Pipeline stage MKMLizer completed in 113.44s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.30s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-sao10k-l3-rp-v3-3-v59
Waiting for inference service chaiml-sao10k-l3-rp-v3-3-v59 to be ready
Inference service chaiml-sao10k-l3-rp-v3-3-v59 ready after 61.11243391036987s
Pipeline stage ISVCDeployer completed in 62.48s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2917611598968506s
Received healthy response to inference request in 1.43461012840271s
Received healthy response to inference request in 1.4331872463226318s
Received healthy response to inference request in 1.4256789684295654s
Received healthy response to inference request in 1.4469823837280273s
5 requests
0 failed requests
5th percentile: 1.4271806240081788
10th percentile: 1.428682279586792
20th percentile: 1.4316855907440185
30th percentile: 1.4334718227386474
40th percentile: 1.4340409755706787
50th percentile: 1.43461012840271
60th percentile: 1.439559030532837
70th percentile: 1.444507932662964
80th percentile: 1.6159381389617922
90th percentile: 1.9538496494293214
95th percentile: 2.1228054046630858
99th percentile: 2.257970008850098
mean time: 1.6064439773559571
Pipeline stage StressChecker completed in 10.35s
chaiml-sao10k-l3-rp-v3-3_v59 status is now deployed due to DeploymentManager action
chaiml-sao10k-l3-rp-v3-3_v59 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-sao10k-l3-rp-v3-3_v59
Running pipeline stage ISVCDeleter
Checking if service chaiml-sao10k-l3-rp-v3-3-v59 is running
Tearing down inference service chaiml-sao10k-l3-rp-v3-3-v59
Service chaiml-sao10k-l3-rp-v3-3-v59 has been torndown
Pipeline stage ISVCDeleter completed in 4.87s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v59/config.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v59/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v59/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v59/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v59/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v59_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v59_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v59_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v59_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v59_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v59_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v59_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.33s
chaiml-sao10k-l3-rp-v3-3_v59 status is now torndown due to DeploymentManager action