submission_id: frank2030-hathor-stable-_6519_v3
developer_uid: frank2030
status: inactive
model_repo: frank2030/Hathor_Stable-v0.2-L3-8B-DPO-3epoch-9k-26
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
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': 4, 'max_output_tokens': 64}
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}
reward_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}
timestamp: 2024-07-08T16:39:14+00:00
model_name: frank2030-hathor-stable-_6519_v3
model_group: frank2030/Hathor_Stable-
num_battles: 30637
num_wins: 15512
celo_rating: 1209.57
propriety_score: 0.7134447398404862
propriety_total_count: 5266.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: frank2030-hathor-stable-_6519_v3
ineligible_reason: None
language_model: frank2030/Hathor_Stable-v0.2-L3-8B-DPO-3epoch-9k-26
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-08
win_ratio: 0.506315892548226
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name frank2030-hathor-stable-6519-v3-mkmlizer
Waiting for job on frank2030-hathor-stable-6519-v3-mkmlizer to finish
frank2030-hathor-stable-6519-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
frank2030-hathor-stable-6519-v3-mkmlizer: ║ _____ __ __ ║
frank2030-hathor-stable-6519-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
frank2030-hathor-stable-6519-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
frank2030-hathor-stable-6519-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
frank2030-hathor-stable-6519-v3-mkmlizer: ║ /___/ ║
frank2030-hathor-stable-6519-v3-mkmlizer: ║ ║
frank2030-hathor-stable-6519-v3-mkmlizer: ║ Version: 0.8.14 ║
frank2030-hathor-stable-6519-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
frank2030-hathor-stable-6519-v3-mkmlizer: ║ https://mk1.ai ║
frank2030-hathor-stable-6519-v3-mkmlizer: ║ ║
frank2030-hathor-stable-6519-v3-mkmlizer: ║ The license key for the current software has been verified as ║
frank2030-hathor-stable-6519-v3-mkmlizer: ║ belonging to: ║
frank2030-hathor-stable-6519-v3-mkmlizer: ║ ║
frank2030-hathor-stable-6519-v3-mkmlizer: ║ Chai Research Corp. ║
frank2030-hathor-stable-6519-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
frank2030-hathor-stable-6519-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
frank2030-hathor-stable-6519-v3-mkmlizer: ║ ║
frank2030-hathor-stable-6519-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
frank2030-hathor-stable-6519-v3-mkmlizer: Downloaded to shared memory in 71.463s
frank2030-hathor-stable-6519-v3-mkmlizer: quantizing model to /dev/shm/model_cache
frank2030-hathor-stable-6519-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
frank2030-hathor-stable-6519-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 118.91it/s] Loading 0: 9%|▉ | 27/291 [00:00<00:02, 130.77it/s] Loading 0: 14%|█▍ | 41/291 [00:00<00:02, 123.94it/s] Loading 0: 20%|█▉ | 58/291 [00:00<00:01, 135.54it/s] Loading 0: 26%|██▌ | 75/291 [00:00<00:01, 140.82it/s] Loading 0: 31%|███ | 90/291 [00:00<00:02, 75.71it/s] Loading 0: 35%|███▌ | 103/291 [00:01<00:02, 85.05it/s] Loading 0: 40%|███▉ | 115/291 [00:01<00:01, 88.54it/s] Loading 0: 45%|████▍ | 130/291 [00:01<00:01, 98.93it/s] Loading 0: 51%|█████ | 147/291 [00:01<00:01, 111.18it/s] Loading 0: 55%|█████▍ | 160/291 [00:01<00:01, 113.70it/s] Loading 0: 60%|██████ | 175/291 [00:01<00:00, 121.62it/s] Loading 0: 65%|██████▍ | 188/291 [00:01<00:01, 77.29it/s] Loading 0: 69%|██████▉ | 201/291 [00:02<00:01, 86.51it/s] Loading 0: 73%|███████▎ | 212/291 [00:02<00:00, 90.76it/s] Loading 0: 79%|███████▊ | 229/291 [00:02<00:00, 105.00it/s] Loading 0: 84%|████████▍ | 244/291 [00:02<00:00, 115.76it/s] Loading 0: 88%|████████▊ | 257/291 [00:02<00:00, 113.09it/s] Loading 0: 94%|█████████▍| 273/291 [00:02<00:00, 125.03it/s] Loading 0: 99%|█████████▊| 287/291 [00:08<00:00, 8.24it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
frank2030-hathor-stable-6519-v3-mkmlizer: quantized model in 23.302s
frank2030-hathor-stable-6519-v3-mkmlizer: Processed model frank2030/Hathor_Stable-v0.2-L3-8B-DPO-3epoch-9k-26 in 94.766s
frank2030-hathor-stable-6519-v3-mkmlizer: creating bucket guanaco-mkml-models
frank2030-hathor-stable-6519-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
frank2030-hathor-stable-6519-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/frank2030-hathor-stable-6519-v3
frank2030-hathor-stable-6519-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/frank2030-hathor-stable-6519-v3/special_tokens_map.json
frank2030-hathor-stable-6519-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/frank2030-hathor-stable-6519-v3/config.json
frank2030-hathor-stable-6519-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/frank2030-hathor-stable-6519-v3/tokenizer_config.json
frank2030-hathor-stable-6519-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/frank2030-hathor-stable-6519-v3/tokenizer.json
frank2030-hathor-stable-6519-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/frank2030-hathor-stable-6519-v3/flywheel_model.0.safetensors
frank2030-hathor-stable-6519-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
frank2030-hathor-stable-6519-v3-mkmlizer: /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.
frank2030-hathor-stable-6519-v3-mkmlizer: warnings.warn(
frank2030-hathor-stable-6519-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`.
frank2030-hathor-stable-6519-v3-mkmlizer: warnings.warn(
frank2030-hathor-stable-6519-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.
frank2030-hathor-stable-6519-v3-mkmlizer: warnings.warn(
frank2030-hathor-stable-6519-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.
frank2030-hathor-stable-6519-v3-mkmlizer: warnings.warn(
frank2030-hathor-stable-6519-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()
frank2030-hathor-stable-6519-v3-mkmlizer: return self.fget.__get__(instance, owner)()
frank2030-hathor-stable-6519-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
frank2030-hathor-stable-6519-v3-mkmlizer: Saving duration: 0.461s
frank2030-hathor-stable-6519-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.761s
frank2030-hathor-stable-6519-v3-mkmlizer: creating bucket guanaco-reward-models
frank2030-hathor-stable-6519-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
frank2030-hathor-stable-6519-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/frank2030-hathor-stable-6519-v3_reward
frank2030-hathor-stable-6519-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/frank2030-hathor-stable-6519-v3_reward/config.json
frank2030-hathor-stable-6519-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/frank2030-hathor-stable-6519-v3_reward/special_tokens_map.json
frank2030-hathor-stable-6519-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/frank2030-hathor-stable-6519-v3_reward/tokenizer_config.json
frank2030-hathor-stable-6519-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/frank2030-hathor-stable-6519-v3_reward/vocab.json
frank2030-hathor-stable-6519-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/frank2030-hathor-stable-6519-v3_reward/merges.txt
frank2030-hathor-stable-6519-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/frank2030-hathor-stable-6519-v3_reward/tokenizer.json
frank2030-hathor-stable-6519-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/frank2030-hathor-stable-6519-v3_reward/reward.tensors
Job frank2030-hathor-stable-6519-v3-mkmlizer completed after 212.03s with status: succeeded
Stopping job with name frank2030-hathor-stable-6519-v3-mkmlizer
Pipeline stage MKMLizer completed in 213.10s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service frank2030-hathor-stable-6519-v3
Waiting for inference service frank2030-hathor-stable-6519-v3 to be ready
Failed to get response for submission invisietch-nimbus-miqu-v_1959_v2: ('http://invisietch-nimbus-miqu-v-1959-v2-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:55838->127.0.0.1:8080: read: connection reset by peer\n')
Inference service frank2030-hathor-stable-6519-v3 ready after 120.62347412109375s
Pipeline stage ISVCDeployer completed in 127.53s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9136810302734375s
Received healthy response to inference request in 1.1055200099945068s
Received healthy response to inference request in 1.1310772895812988s
Received healthy response to inference request in 1.1436669826507568s
Received healthy response to inference request in 1.1038858890533447s
5 requests
0 failed requests
5th percentile: 1.104212713241577
10th percentile: 1.1045395374298095
20th percentile: 1.1051931858062745
30th percentile: 1.1106314659118652
40th percentile: 1.120854377746582
50th percentile: 1.1310772895812988
60th percentile: 1.136113166809082
70th percentile: 1.1411490440368652
80th percentile: 1.297669792175293
90th percentile: 1.6056754112243654
95th percentile: 1.7596782207489012
99th percentile: 1.8828804683685303
mean time: 1.279566240310669
Pipeline stage StressChecker completed in 7.74s
frank2030-hathor-stable-_6519_v3 status is now deployed due to DeploymentManager action
frank2030-hathor-stable-_6519_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics