submission_id: chaser-cz-sharegpt-qlora-out_v3
developer_uid: chace9580
best_of: 16
celo_rating: 1161.42
display_name: chaser-cz-sharegpt-qlora-out_v3
family_friendly_score: 0.0
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
is_internal_developer: False
language_model: Chaser-cz/sharegpt-qlora-out
max_input_tokens: 512
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: Chaser-cz/sharegpt-qlora
model_name: chaser-cz-sharegpt-qlora-out_v3
model_num_parameters: 7241732096.0
model_repo: Chaser-cz/sharegpt-qlora-out
model_size: 7B
num_battles: 33900
num_wins: 15489
ranking_group: single
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-07-11T17:05:44+00:00
us_pacific_date: 2024-07-11
win_ratio: 0.4569026548672566
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaser-cz-sharegpt-qlora-out-v3-mkmlizer
Waiting for job on chaser-cz-sharegpt-qlora-out-v3-mkmlizer to finish
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: ║ _____ __ __ ║
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: ║ /___/ ║
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: ║ ║
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: ║ Version: 0.8.14 ║
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: ║ https://mk1.ai ║
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: ║ ║
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: ║ The license key for the current software has been verified as ║
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: ║ belonging to: ║
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: ║ ║
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: ║ Chai Research Corp. ║
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: ║ ║
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: Downloaded to shared memory in 41.874s
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: quantizing model to /dev/shm/model_cache
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: quantized model in 19.364s
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: Processed model Chaser-cz/sharegpt-qlora-out in 61.239s
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: creating bucket guanaco-mkml-models
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaser-cz-sharegpt-qlora-out-v3
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaser-cz-sharegpt-qlora-out-v3/config.json
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaser-cz-sharegpt-qlora-out-v3/tokenizer_config.json
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/chaser-cz-sharegpt-qlora-out-v3/tokenizer.model
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaser-cz-sharegpt-qlora-out-v3/special_tokens_map.json
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaser-cz-sharegpt-qlora-out-v3/tokenizer.json
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaser-cz-sharegpt-qlora-out-v3/flywheel_model.0.safetensors
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 34%|███▎ | 98/291 [00:01<00:02, 70.43it/s] Loading 0: 70%|███████ | 204/291 [00:02<00:01, 78.76it/s] Loading 0: 100%|██████████| 291/291 [00:04<00:00, 66.15it/s] /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: warnings.warn(
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: warnings.warn(
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: warnings.warn(
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:468: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: warnings.warn(
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: return self.fget.__get__(instance, owner)()
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: Saving duration: 0.518s
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.832s
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: creating bucket guanaco-reward-models
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaser-cz-sharegpt-qlora-out-v3_reward
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaser-cz-sharegpt-qlora-out-v3_reward/config.json
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaser-cz-sharegpt-qlora-out-v3_reward/special_tokens_map.json
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaser-cz-sharegpt-qlora-out-v3_reward/tokenizer_config.json
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaser-cz-sharegpt-qlora-out-v3_reward/vocab.json
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaser-cz-sharegpt-qlora-out-v3_reward/merges.txt
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaser-cz-sharegpt-qlora-out-v3_reward/tokenizer.json
chaser-cz-sharegpt-qlora-out-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaser-cz-sharegpt-qlora-out-v3_reward/reward.tensors
Job chaser-cz-sharegpt-qlora-out-v3-mkmlizer completed after 94.06s with status: succeeded
Stopping job with name chaser-cz-sharegpt-qlora-out-v3-mkmlizer
Pipeline stage MKMLizer completed in 94.88s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service chaser-cz-sharegpt-qlora-out-v3
Waiting for inference service chaser-cz-sharegpt-qlora-out-v3 to be ready
Failed to get response for submission sao10k-l3-rp-v5-4_v2: ('http://sao10k-l3-rp-v5-4-v2-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:48268->127.0.0.1:8080: read: connection reset by peer\n')
Inference service chaser-cz-sharegpt-qlora-out-v3 ready after 40.20740723609924s
Pipeline stage ISVCDeployer completed in 47.18s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.848520278930664s
Received healthy response to inference request in 1.1345148086547852s
Received healthy response to inference request in 1.1757259368896484s
Received healthy response to inference request in 1.157109260559082s
Received healthy response to inference request in 1.1703646183013916s
5 requests
0 failed requests
5th percentile: 1.1390336990356444
10th percentile: 1.143552589416504
20th percentile: 1.1525903701782227
30th percentile: 1.159760332107544
40th percentile: 1.1650624752044678
50th percentile: 1.1703646183013916
60th percentile: 1.1725091457366943
70th percentile: 1.174653673171997
80th percentile: 1.3102848052978517
90th percentile: 1.579402542114258
95th percentile: 1.7139614105224608
99th percentile: 1.8216085052490234
mean time: 1.2972469806671143
Pipeline stage StressChecker completed in 7.11s
chaser-cz-sharegpt-qlora-out_v3 status is now deployed due to DeploymentManager action
chaser-cz-sharegpt-qlora-out_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaser-cz-sharegpt-qlora-out_v3
Running pipeline stage ISVCDeleter
Checking if service chaser-cz-sharegpt-qlora-out-v3 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 5.44s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaser-cz-sharegpt-qlora-out-v3/config.json from bucket guanaco-mkml-models
Deleting key chaser-cz-sharegpt-qlora-out-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaser-cz-sharegpt-qlora-out-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaser-cz-sharegpt-qlora-out-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaser-cz-sharegpt-qlora-out-v3/tokenizer.model from bucket guanaco-mkml-models
Deleting key chaser-cz-sharegpt-qlora-out-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaser-cz-sharegpt-qlora-out-v3_reward/config.json from bucket guanaco-reward-models
Deleting key chaser-cz-sharegpt-qlora-out-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaser-cz-sharegpt-qlora-out-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaser-cz-sharegpt-qlora-out-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaser-cz-sharegpt-qlora-out-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaser-cz-sharegpt-qlora-out-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaser-cz-sharegpt-qlora-out-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.50s
chaser-cz-sharegpt-qlora-out_v3 status is now torndown due to DeploymentManager action