submission_id: hastagaras-cupang-12b-test-4_v3
developer_uid: Hastagaras
alignment_samples: 0
best_of: 4
celo_rating: 1175.23
display_name: hastagaras-cupang-12b-test-4_v3
formatter: {'memory_template': "<s>[INST] {bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt} [/INST]\n', 'bot_template': '{bot_name}: {message}</s>\n', 'user_template': '[INST] {user_name}: {message} [/INST]\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64, 'reward_max_token_input': 256}
is_internal_developer: False
language_model: Hastagaras/Cupang-12B-Test-4
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: Hastagaras/Cupang-12B-Te
model_name: hastagaras-cupang-12b-test-4_v3
model_num_parameters: 12772070400.0
model_repo: Hastagaras/Cupang-12B-Test-4
model_size: 13B
num_battles: 10544
num_wins: 4929
propriety_score: 0.7185261003070624
propriety_total_count: 977.0
ranking_group: single
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': '', 'prompt_template': '', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
status: torndown
submission_type: basic
timestamp: 2024-08-02T02:58:04+00:00
us_pacific_date: 2024-08-01
win_ratio: 0.46746965098634297
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-cupang-12b-test-4-v3-mkmlizer
Waiting for job on hastagaras-cupang-12b-test-4-v3-mkmlizer to finish
hastagaras-cupang-12b-test-4-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-cupang-12b-test-4-v3-mkmlizer: ║ _____ __ __ ║
hastagaras-cupang-12b-test-4-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-cupang-12b-test-4-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-cupang-12b-test-4-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-cupang-12b-test-4-v3-mkmlizer: ║ /___/ ║
hastagaras-cupang-12b-test-4-v3-mkmlizer: ║ ║
hastagaras-cupang-12b-test-4-v3-mkmlizer: ║ Version: 0.9.9 ║
hastagaras-cupang-12b-test-4-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-cupang-12b-test-4-v3-mkmlizer: ║ https://mk1.ai ║
hastagaras-cupang-12b-test-4-v3-mkmlizer: ║ ║
hastagaras-cupang-12b-test-4-v3-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-cupang-12b-test-4-v3-mkmlizer: ║ belonging to: ║
hastagaras-cupang-12b-test-4-v3-mkmlizer: ║ ║
hastagaras-cupang-12b-test-4-v3-mkmlizer: ║ Chai Research Corp. ║
hastagaras-cupang-12b-test-4-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-cupang-12b-test-4-v3-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
hastagaras-cupang-12b-test-4-v3-mkmlizer: ║ ║
hastagaras-cupang-12b-test-4-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-cupang-12b-test-4-v3-mkmlizer: Downloaded to shared memory in 29.307s
hastagaras-cupang-12b-test-4-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpcbgz2ywf, device:0
hastagaras-cupang-12b-test-4-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-cupang-12b-test-4-v3-mkmlizer: quantized model in 35.907s
hastagaras-cupang-12b-test-4-v3-mkmlizer: Processed model Hastagaras/Cupang-12B-Test-4 in 65.215s
hastagaras-cupang-12b-test-4-v3-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-cupang-12b-test-4-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-cupang-12b-test-4-v3/tokenizer_config.json
hastagaras-cupang-12b-test-4-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-cupang-12b-test-4-v3/tokenizer.json
hastagaras-cupang-12b-test-4-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-cupang-12b-test-4-v3/flywheel_model.0.safetensors
hastagaras-cupang-12b-test-4-v3-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
hastagaras-cupang-12b-test-4-v3-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:11, 30.28it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:06, 50.15it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 45.45it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:07, 43.60it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 48.43it/s] Loading 0: 10%|█ | 37/363 [00:00<00:07, 44.02it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 43.18it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:06, 47.43it/s] Loading 0: 15%|█▍ | 53/363 [00:01<00:06, 46.88it/s] Loading 0: 17%|█▋ | 60/363 [00:01<00:06, 46.40it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:09, 31.14it/s] Loading 0: 20%|█▉ | 71/363 [00:01<00:07, 36.68it/s] Loading 0: 21%|██ | 76/363 [00:01<00:07, 38.82it/s] Loading 0: 22%|██▏ | 81/363 [00:01<00:06, 41.01it/s] Loading 0: 24%|██▍ | 87/363 [00:02<00:06, 40.57it/s] Loading 0: 25%|██▌ | 92/363 [00:02<00:06, 39.61it/s] Loading 0: 27%|██▋ | 98/363 [00:02<00:06, 43.62it/s] Loading 0: 28%|██▊ | 103/363 [00:02<00:06, 43.13it/s] Loading 0: 30%|███ | 109/363 [00:02<00:05, 47.38it/s] Loading 0: 31%|███▏ | 114/363 [00:02<00:06, 40.77it/s] Loading 0: 33%|███▎ | 119/363 [00:02<00:06, 39.88it/s] Loading 0: 34%|███▍ | 125/363 [00:02<00:05, 44.34it/s] Loading 0: 36%|███▌ | 130/363 [00:03<00:05, 43.80it/s] Loading 0: 37%|███▋ | 135/363 [00:03<00:05, 44.69it/s] Loading 0: 39%|███▉ | 141/363 [00:03<00:05, 43.29it/s] Loading 0: 40%|████ | 146/363 [00:03<00:07, 30.62it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 30.73it/s] Loading 0: 43%|████▎ | 157/363 [00:03<00:05, 37.59it/s] Loading 0: 45%|████▍ | 163/363 [00:04<00:05, 38.16it/s] Loading 0: 46%|████▋ | 168/363 [00:04<00:04, 39.03it/s] Loading 0: 48%|████▊ | 175/363 [00:04<00:04, 44.44it/s] Loading 0: 50%|████▉ | 181/363 [00:04<00:04, 42.82it/s] Loading 0: 51%|█████ | 186/363 [00:04<00:04, 42.01it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 46.69it/s] Loading 0: 55%|█████▍ | 199/363 [00:04<00:03, 44.24it/s] Loading 0: 56%|█████▌ | 204/363 [00:04<00:03, 42.84it/s] Loading 0: 58%|█████▊ | 211/363 [00:05<00:03, 47.28it/s] Loading 0: 60%|█████▉ | 217/363 [00:05<00:03, 44.61it/s] Loading 0: 61%|██████ | 222/363 [00:05<00:03, 45.74it/s] Loading 0: 63%|██████▎ | 227/363 [00:05<00:04, 31.69it/s] Loading 0: 64%|██████▎ | 231/363 [00:05<00:04, 31.30it/s] Loading 0: 66%|██████▌ | 238/363 [00:05<00:03, 38.03it/s] Loading 0: 67%|██████▋ | 244/363 [00:05<00:03, 38.36it/s] Loading 0: 69%|██████▊ | 249/363 [00:06<00:02, 38.67it/s] Loading 0: 70%|███████ | 255/363 [00:06<00:02, 43.29it/s] Loading 0: 72%|███████▏ | 260/363 [00:06<00:02, 43.70it/s] Loading 0: 73%|███████▎ | 265/363 [00:06<00:02, 44.64it/s] Loading 0: 75%|███████▍ | 271/363 [00:06<00:02, 42.67it/s] Loading 0: 76%|███████▌ | 276/363 [00:06<00:02, 41.78it/s] Loading 0: 78%|███████▊ | 283/363 [00:06<00:01, 46.59it/s] Loading 0: 79%|███████▉ | 288/363 [00:06<00:01, 47.33it/s] Loading 0: 81%|████████ | 293/363 [00:07<00:01, 38.78it/s] Loading 0: 82%|████████▏ | 299/363 [00:07<00:01, 43.66it/s] Loading 0: 84%|████████▎ | 304/363 [00:14<00:23, 2.55it/s] Loading 0: 85%|████████▍ | 308/363 [00:14<00:16, 3.28it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:11, 4.26it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:06, 7.07it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:03, 9.51it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:02, 12.02it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 16.66it/s] Loading 0: 95%|█████████▍| 344/363 [00:14<00:00, 20.15it/s] Loading 0: 96%|█████████▌| 349/363 [00:15<00:00, 23.17it/s] Loading 0: 98%|█████████▊| 355/363 [00:15<00:00, 28.51it/s] Loading 0: 99%|█████████▉| 360/363 [00:15<00:00, 31.59it/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.
hastagaras-cupang-12b-test-4-v3-mkmlizer: warnings.warn(
hastagaras-cupang-12b-test-4-v3-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.
hastagaras-cupang-12b-test-4-v3-mkmlizer: warnings.warn(
hastagaras-cupang-12b-test-4-v3-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.
hastagaras-cupang-12b-test-4-v3-mkmlizer: warnings.warn(
hastagaras-cupang-12b-test-4-v3-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:05<00:05, 5.16s/it] Downloading shards: 100%|██████████| 2/2 [00:07<00:00, 3.77s/it] Downloading shards: 100%|██████████| 2/2 [00:07<00:00, 3.98s/it]
hastagaras-cupang-12b-test-4-v3-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 2.40it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.96it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.61it/s]
hastagaras-cupang-12b-test-4-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-cupang-12b-test-4-v3-mkmlizer: Saving duration: 1.321s
hastagaras-cupang-12b-test-4-v3-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 12.732s
hastagaras-cupang-12b-test-4-v3-mkmlizer: creating bucket guanaco-reward-models
hastagaras-cupang-12b-test-4-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-cupang-12b-test-4-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-cupang-12b-test-4-v3_reward
hastagaras-cupang-12b-test-4-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-cupang-12b-test-4-v3_reward/config.json
hastagaras-cupang-12b-test-4-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-cupang-12b-test-4-v3_reward/special_tokens_map.json
hastagaras-cupang-12b-test-4-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-cupang-12b-test-4-v3_reward/tokenizer_config.json
hastagaras-cupang-12b-test-4-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-cupang-12b-test-4-v3_reward/merges.txt
hastagaras-cupang-12b-test-4-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-cupang-12b-test-4-v3_reward/vocab.json
hastagaras-cupang-12b-test-4-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-cupang-12b-test-4-v3_reward/tokenizer.json
hastagaras-cupang-12b-test-4-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-cupang-12b-test-4-v3_reward/reward.tensors
Job hastagaras-cupang-12b-test-4-v3-mkmlizer completed after 115.58s with status: succeeded
Stopping job with name hastagaras-cupang-12b-test-4-v3-mkmlizer
Pipeline stage MKMLizer completed in 116.55s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.23s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-cupang-12b-test-4-v3
Waiting for inference service hastagaras-cupang-12b-test-4-v3 to be ready
Inference service hastagaras-cupang-12b-test-4-v3 ready after 130.9704909324646s
Pipeline stage ISVCDeployer completed in 136.36s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.298210382461548s
Received healthy response to inference request in 1.274404764175415s
Received healthy response to inference request in 1.501821517944336s
Received healthy response to inference request in 1.5470280647277832s
Received healthy response to inference request in 1.563638687133789s
5 requests
0 failed requests
5th percentile: 1.3198881149291992
10th percentile: 1.3653714656829834
20th percentile: 1.4563381671905518
30th percentile: 1.5108628273010254
40th percentile: 1.5289454460144043
50th percentile: 1.5470280647277832
60th percentile: 1.5536723136901855
70th percentile: 1.560316562652588
80th percentile: 1.710553026199341
90th percentile: 2.004381704330444
95th percentile: 2.151296043395996
99th percentile: 2.2688275146484376
mean time: 1.6370206832885743
Pipeline stage StressChecker completed in 8.85s
hastagaras-cupang-12b-test-4_v3 status is now deployed due to DeploymentManager action
hastagaras-cupang-12b-test-4_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-cupang-12b-test-4_v3
Running pipeline stage ISVCDeleter
Checking if service hastagaras-cupang-12b-test-4-v3 is running
Tearing down inference service hastagaras-cupang-12b-test-4-v3
Service hastagaras-cupang-12b-test-4-v3 has been torndown
Pipeline stage ISVCDeleter completed in 4.57s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-cupang-12b-test-4-v3/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-cupang-12b-test-4-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-cupang-12b-test-4-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-cupang-12b-test-4-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-cupang-12b-test-4-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-cupang-12b-test-4-v3_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-cupang-12b-test-4-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-cupang-12b-test-4-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-cupang-12b-test-4-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-cupang-12b-test-4-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-cupang-12b-test-4-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-cupang-12b-test-4-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.97s
hastagaras-cupang-12b-test-4_v3 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics