developer_uid: Hastagaras
submission_id: hastagaras-l3-dt-prep-test_v4
model_name: auto
model_group: Hastagaras/l3-dt-prep-te
status: torndown
timestamp: 2024-07-26T07:00:56+00:00
num_battles: 11157
num_wins: 5045
celo_rating: 1161.64
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/l3-dt-prep-test
model_architecture: LlamaForCausalLM
reward_repo: Jellywibble/gpt2_xl_pairwise_89m_step_347634
model_num_parameters: 8030261248.0
best_of: 2
max_input_tokens: 1024
max_output_tokens: 64
display_name: auto
is_internal_developer: False
language_model: Hastagaras/l3-dt-prep-test
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-26
win_ratio: 0.4521824863314511
generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.0, 'top_k': 45, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 2, 'max_output_tokens': 64, 'reward_max_token_input': 256}
formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>system\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', 'truncate_by_message': False}
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-l3-dt-prep-test-v4-mkmlizer
Waiting for job on hastagaras-l3-dt-prep-test-v4-mkmlizer to finish
hastagaras-l3-dt-prep-test-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-l3-dt-prep-test-v4-mkmlizer: ║ _____ __ __ ║
hastagaras-l3-dt-prep-test-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-l3-dt-prep-test-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-l3-dt-prep-test-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-l3-dt-prep-test-v4-mkmlizer: ║ /___/ ║
hastagaras-l3-dt-prep-test-v4-mkmlizer: ║ ║
hastagaras-l3-dt-prep-test-v4-mkmlizer: ║ Version: 0.9.7 ║
hastagaras-l3-dt-prep-test-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-l3-dt-prep-test-v4-mkmlizer: ║ https://mk1.ai ║
hastagaras-l3-dt-prep-test-v4-mkmlizer: ║ ║
hastagaras-l3-dt-prep-test-v4-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-l3-dt-prep-test-v4-mkmlizer: ║ belonging to: ║
hastagaras-l3-dt-prep-test-v4-mkmlizer: ║ ║
hastagaras-l3-dt-prep-test-v4-mkmlizer: ║ Chai Research Corp. ║
hastagaras-l3-dt-prep-test-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-l3-dt-prep-test-v4-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
hastagaras-l3-dt-prep-test-v4-mkmlizer: ║ ║
hastagaras-l3-dt-prep-test-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-l3-dt-prep-test-v4-mkmlizer: Downloaded to shared memory in 24.817s
hastagaras-l3-dt-prep-test-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpfwfrc2z9, device:0
hastagaras-l3-dt-prep-test-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-l3-dt-prep-test-v4-mkmlizer: quantized model in 26.741s
hastagaras-l3-dt-prep-test-v4-mkmlizer: Processed model Hastagaras/l3-dt-prep-test in 51.558s
hastagaras-l3-dt-prep-test-v4-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-l3-dt-prep-test-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-l3-dt-prep-test-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-l3-dt-prep-test-v4
hastagaras-l3-dt-prep-test-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-l3-dt-prep-test-v4/special_tokens_map.json
hastagaras-l3-dt-prep-test-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-l3-dt-prep-test-v4/config.json
hastagaras-l3-dt-prep-test-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-l3-dt-prep-test-v4/tokenizer_config.json
hastagaras-l3-dt-prep-test-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-l3-dt-prep-test-v4/tokenizer.json
hastagaras-l3-dt-prep-test-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-l3-dt-prep-test-v4/flywheel_model.0.safetensors
hastagaras-l3-dt-prep-test-v4-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
hastagaras-l3-dt-prep-test-v4-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:09, 30.51it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:05, 52.00it/s] Loading 0: 7%|▋ | 19/291 [00:00<00:06, 45.24it/s] Loading 0: 8%|▊ | 24/291 [00:00<00:06, 43.93it/s] Loading 0: 11%|█ | 31/291 [00:00<00:05, 49.41it/s] Loading 0: 13%|█▎ | 37/291 [00:00<00:05, 46.65it/s] Loading 0: 14%|█▍ | 42/291 [00:00<00:05, 46.03it/s] Loading 0: 17%|█▋ | 49/291 [00:01<00:04, 50.60it/s] Loading 0: 19%|█▉ | 55/291 [00:01<00:04, 47.54it/s] Loading 0: 21%|██ | 60/291 [00:01<00:04, 46.77it/s] Loading 0: 23%|██▎ | 68/291 [00:01<00:04, 45.72it/s] Loading 0: 26%|██▌ | 76/291 [00:01<00:04, 53.25it/s] Loading 0: 28%|██▊ | 82/291 [00:01<00:04, 48.71it/s] Loading 0: 30%|███ | 88/291 [00:02<00:06, 31.59it/s] Loading 0: 32%|███▏ | 94/291 [00:02<00:05, 36.15it/s] Loading 0: 34%|███▍ | 100/291 [00:02<00:05, 36.94it/s] Loading 0: 36%|███▌ | 105/291 [00:02<00:04, 38.74it/s] Loading 0: 38%|███▊ | 111/291 [00:02<00:04, 42.37it/s] Loading 0: 40%|███▉ | 116/291 [00:02<00:04, 42.55it/s] Loading 0: 42%|████▏ | 122/291 [00:02<00:04, 40.09it/s] Loading 0: 45%|████▍ | 130/291 [00:02<00:03, 47.63it/s] Loading 0: 47%|████▋ | 136/291 [00:03<00:03, 45.84it/s] Loading 0: 48%|████▊ | 141/291 [00:03<00:03, 46.34it/s] Loading 0: 51%|█████ | 148/291 [00:03<00:02, 51.63it/s] Loading 0: 53%|█████▎ | 154/291 [00:03<00:02, 48.97it/s] Loading 0: 55%|█████▍ | 160/291 [00:03<00:02, 50.39it/s] Loading 0: 57%|█████▋ | 167/291 [00:03<00:02, 47.29it/s] Loading 0: 59%|█████▉ | 173/291 [00:03<00:02, 49.11it/s] Loading 0: 62%|██████▏ | 179/291 [00:03<00:02, 51.34it/s] Loading 0: 64%|██████▎ | 185/291 [00:04<00:02, 52.19it/s] Loading 0: 66%|██████▌ | 191/291 [00:04<00:03, 32.21it/s] Loading 0: 67%|██████▋ | 196/291 [00:04<00:02, 33.42it/s] Loading 0: 69%|██████▉ | 201/291 [00:04<00:02, 36.25it/s] Loading 0: 71%|███████ | 206/291 [00:04<00:02, 38.36it/s] Loading 0: 73%|███████▎ | 211/291 [00:04<00:01, 40.18it/s] Loading 0: 75%|███████▍ | 217/291 [00:05<00:01, 39.75it/s] Loading 0: 76%|███████▋ | 222/291 [00:05<00:01, 40.74it/s] Loading 0: 79%|███████▊ | 229/291 [00:05<00:01, 46.62it/s] Loading 0: 81%|████████ | 235/291 [00:05<00:01, 44.91it/s] Loading 0: 82%|████████▏ | 240/291 [00:05<00:01, 44.78it/s] Loading 0: 85%|████████▍ | 247/291 [00:05<00:00, 49.91it/s] Loading 0: 87%|████████▋ | 253/291 [00:05<00:00, 46.57it/s] Loading 0: 89%|████████▊ | 258/291 [00:05<00:00, 47.05it/s] Loading 0: 91%|█████████ | 265/291 [00:05<00:00, 52.24it/s] Loading 0: 93%|█████████▎| 271/291 [00:06<00:00, 48.61it/s] Loading 0: 95%|█████████▍| 276/291 [00:06<00:00, 47.36it/s] Loading 0: 97%|█████████▋| 282/291 [00:06<00:00, 44.79it/s] Loading 0: 99%|█████████▊| 287/291 [00:11<00:01, 3.22it/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-l3-dt-prep-test-v4-mkmlizer: warnings.warn(
hastagaras-l3-dt-prep-test-v4-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-l3-dt-prep-test-v4-mkmlizer: warnings.warn(
hastagaras-l3-dt-prep-test-v4-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-l3-dt-prep-test-v4-mkmlizer: warnings.warn(
hastagaras-l3-dt-prep-test-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-l3-dt-prep-test-v4-mkmlizer: Saving duration: 1.415s
hastagaras-l3-dt-prep-test-v4-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.669s
hastagaras-l3-dt-prep-test-v4-mkmlizer: creating bucket guanaco-reward-models
hastagaras-l3-dt-prep-test-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-l3-dt-prep-test-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-l3-dt-prep-test-v4_reward
hastagaras-l3-dt-prep-test-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-l3-dt-prep-test-v4_reward/config.json
hastagaras-l3-dt-prep-test-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-l3-dt-prep-test-v4_reward/special_tokens_map.json
hastagaras-l3-dt-prep-test-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-l3-dt-prep-test-v4_reward/tokenizer_config.json
hastagaras-l3-dt-prep-test-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-l3-dt-prep-test-v4_reward/merges.txt
hastagaras-l3-dt-prep-test-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-l3-dt-prep-test-v4_reward/vocab.json
hastagaras-l3-dt-prep-test-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-l3-dt-prep-test-v4_reward/tokenizer.json
hastagaras-l3-dt-prep-test-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-l3-dt-prep-test-v4_reward/reward.tensors
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Job hastagaras-l3-dt-prep-test-v4-mkmlizer completed after 95.89s with status: succeeded
Stopping job with name hastagaras-l3-dt-prep-test-v4-mkmlizer
Pipeline stage MKMLizer completed in 96.97s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-l3-dt-prep-test-v4
Waiting for inference service hastagaras-l3-dt-prep-test-v4 to be ready
Inference service hastagaras-l3-dt-prep-test-v4 ready after 80.56383609771729s
Pipeline stage ISVCDeployer completed in 82.12s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0341806411743164s
Received healthy response to inference request in 2.126763343811035s
Received healthy response to inference request in 0.8801212310791016s
Received healthy response to inference request in 1.1541030406951904s
Received healthy response to inference request in 0.9668171405792236s
5 requests
0 failed requests
5th percentile: 0.8974604129791259
10th percentile: 0.9147995948791504
20th percentile: 0.9494779586791993
30th percentile: 1.004274320602417
40th percentile: 1.0791886806488038
50th percentile: 1.1541030406951904
60th percentile: 1.5061340808868406
70th percentile: 1.858165121078491
80th percentile: 2.05269718170166
90th percentile: 2.0897302627563477
95th percentile: 2.1082468032836914
99th percentile: 2.1230600357055662
mean time: 1.4323970794677734
Pipeline stage StressChecker completed in 7.87s
hastagaras-l3-dt-prep-test_v4 status is now deployed due to DeploymentManager action
hastagaras-l3-dt-prep-test_v4 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-l3-dt-prep-test_v4
Running pipeline stage ISVCDeleter
Checking if service hastagaras-l3-dt-prep-test-v4 is running
Tearing down inference service hastagaras-l3-dt-prep-test-v4
Service hastagaras-l3-dt-prep-test-v4 has been torndown
Pipeline stage ISVCDeleter completed in 4.19s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-l3-dt-prep-test-v4/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-dt-prep-test-v4/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-l3-dt-prep-test-v4/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-dt-prep-test-v4/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-dt-prep-test-v4/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-l3-dt-prep-test-v4_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-dt-prep-test-v4_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-l3-dt-prep-test-v4_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-l3-dt-prep-test-v4_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-dt-prep-test-v4_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-dt-prep-test-v4_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-dt-prep-test-v4_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.58s
hastagaras-l3-dt-prep-test_v4 status is now torndown due to DeploymentManager action