submission_id: chaiml-elo-run-3-cp7000_v2
developer_uid: zonemercy
status: inactive
model_repo: ChaiML/elo_run_3_cp7000
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, '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: 2024-07-13T05:26:05+00:00
model_name: nitral-ai-hathor-l3-8b-v-01_v1
model_group: ChaiML/elo_run_3_cp7000
num_battles: 408901
num_wins: 236265
celo_rating: 1284.75
alignment_score: None
alignment_samples: 0
propriety_score: 0.7047366412907211
propriety_total_count: 55039.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: nitral-ai-hathor-l3-8b-v-01_v1
ineligible_reason: None
language_model: ChaiML/elo_run_3_cp7000
model_size: 8B
reward_model: ChaiML/gpt2_xl_pairwise_89m_step_347634
us_pacific_date: 2024-07-12
win_ratio: 0.5778048965397492
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-elo-run-3-cp7000-v2-mkmlizer
Waiting for job on chaiml-elo-run-3-cp7000-v2-mkmlizer to finish
chaiml-elo-run-3-cp7000-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-elo-run-3-cp7000-v2-mkmlizer: ║ _____ __ __ ║
chaiml-elo-run-3-cp7000-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-elo-run-3-cp7000-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-elo-run-3-cp7000-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-elo-run-3-cp7000-v2-mkmlizer: ║ /___/ ║
chaiml-elo-run-3-cp7000-v2-mkmlizer: ║ ║
chaiml-elo-run-3-cp7000-v2-mkmlizer: ║ Version: 0.8.14 ║
chaiml-elo-run-3-cp7000-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-elo-run-3-cp7000-v2-mkmlizer: ║ https://mk1.ai ║
chaiml-elo-run-3-cp7000-v2-mkmlizer: ║ ║
chaiml-elo-run-3-cp7000-v2-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-elo-run-3-cp7000-v2-mkmlizer: ║ belonging to: ║
chaiml-elo-run-3-cp7000-v2-mkmlizer: ║ ║
chaiml-elo-run-3-cp7000-v2-mkmlizer: ║ Chai Research Corp. ║
chaiml-elo-run-3-cp7000-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-elo-run-3-cp7000-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-elo-run-3-cp7000-v2-mkmlizer: ║ ║
chaiml-elo-run-3-cp7000-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-elo-run-3-cp7000-v2-mkmlizer: Downloaded to shared memory in 40.020s
chaiml-elo-run-3-cp7000-v2-mkmlizer: quantizing model to /dev/shm/model_cache
chaiml-elo-run-3-cp7000-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-elo-run-3-cp7000-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 3%|▎ | 8/291 [00:00<00:03, 78.89it/s] Loading 0: 6%|▌ | 17/291 [00:00<00:03, 83.01it/s] Loading 0: 9%|▉ | 26/291 [00:00<00:03, 84.06it/s] Loading 0: 12%|█▏ | 35/291 [00:00<00:05, 43.96it/s] Loading 0: 14%|█▍ | 42/291 [00:00<00:05, 48.33it/s] Loading 0: 17%|█▋ | 50/291 [00:00<00:04, 55.26it/s] Loading 0: 20%|██ | 59/291 [00:00<00:03, 63.21it/s] Loading 0: 23%|██▎ | 68/291 [00:01<00:03, 69.35it/s] Loading 0: 27%|██▋ | 80/291 [00:01<00:04, 52.18it/s] Loading 0: 30%|██▉ | 87/291 [00:01<00:03, 55.60it/s] Loading 0: 33%|███▎ | 96/291 [00:01<00:03, 62.68it/s] Loading 0: 36%|███▌ | 105/291 [00:01<00:02, 68.60it/s] Loading 0: 39%|███▉ | 114/291 [00:01<00:02, 72.67it/s] Loading 0: 43%|████▎ | 125/291 [00:01<00:02, 80.47it/s] Loading 0: 46%|████▌ | 134/291 [00:02<00:03, 51.07it/s] Loading 0: 48%|████▊ | 141/291 [00:02<00:02, 52.95it/s] Loading 0: 51%|█████ | 149/291 [00:02<00:02, 57.94it/s] Loading 0: 54%|█████▍ | 158/291 [00:02<00:02, 64.83it/s] Loading 0: 57%|█████▋ | 167/291 [00:02<00:01, 70.58it/s] Loading 0: 60%|██████ | 175/291 [00:02<00:01, 71.82it/s] Loading 0: 64%|██████▍ | 186/291 [00:03<00:01, 52.97it/s] Loading 0: 66%|██████▋ | 193/291 [00:03<00:01, 52.22it/s] Loading 0: 69%|██████▉ | 202/291 [00:03<00:01, 59.71it/s] Loading 0: 73%|███████▎ | 211/291 [00:03<00:01, 66.19it/s] Loading 0: 76%|███████▌ | 220/291 [00:03<00:00, 71.54it/s] Loading 0: 78%|███████▊ | 228/291 [00:03<00:00, 71.35it/s] Loading 0: 81%|████████ | 236/291 [00:03<00:01, 50.71it/s] Loading 0: 84%|████████▎ | 243/291 [00:04<00:00, 54.41it/s] Loading 0: 87%|████████▋ | 252/291 [00:04<00:00, 61.88it/s] Loading 0: 89%|████████▉ | 260/291 [00:04<00:00, 65.69it/s] Loading 0: 92%|█████████▏| 269/291 [00:04<00:00, 71.39it/s] Loading 0: 95%|█████████▌| 277/291 [00:04<00:00, 71.69it/s] Loading 0: 98%|█████████▊| 286/291 [00:10<00:01, 4.87it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
chaiml-elo-run-3-cp7000-v2-mkmlizer: quantized model in 24.515s
chaiml-elo-run-3-cp7000-v2-mkmlizer: Processed model ChaiML/elo_run_3_cp7000 in 64.535s
chaiml-elo-run-3-cp7000-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-elo-run-3-cp7000-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-elo-run-3-cp7000-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-elo-run-3-cp7000-v2
chaiml-elo-run-3-cp7000-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-elo-run-3-cp7000-v2/config.json
chaiml-elo-run-3-cp7000-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-elo-run-3-cp7000-v2/special_tokens_map.json
chaiml-elo-run-3-cp7000-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-elo-run-3-cp7000-v2/tokenizer_config.json
chaiml-elo-run-3-cp7000-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-elo-run-3-cp7000-v2/tokenizer.json
chaiml-elo-run-3-cp7000-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-elo-run-3-cp7000-v2/flywheel_model.0.safetensors
chaiml-elo-run-3-cp7000-v2-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
chaiml-elo-run-3-cp7000-v2-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.
chaiml-elo-run-3-cp7000-v2-mkmlizer: warnings.warn(
chaiml-elo-run-3-cp7000-v2-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`.
chaiml-elo-run-3-cp7000-v2-mkmlizer: warnings.warn(
chaiml-elo-run-3-cp7000-v2-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.
chaiml-elo-run-3-cp7000-v2-mkmlizer: warnings.warn(
chaiml-elo-run-3-cp7000-v2-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.
chaiml-elo-run-3-cp7000-v2-mkmlizer: warnings.warn(
chaiml-elo-run-3-cp7000-v2-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:05<00:05, 5.52s/it] Downloading shards: 100%|██████████| 2/2 [00:07<00:00, 3.23s/it] Downloading shards: 100%|██████████| 2/2 [00:07<00:00, 3.58s/it]
chaiml-elo-run-3-cp7000-v2-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 2.09it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.46it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.15it/s]
chaiml-elo-run-3-cp7000-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-elo-run-3-cp7000-v2-mkmlizer: Saving duration: 4.538s
chaiml-elo-run-3-cp7000-v2-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.898s
chaiml-elo-run-3-cp7000-v2-mkmlizer: creating bucket guanaco-reward-models
chaiml-elo-run-3-cp7000-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-elo-run-3-cp7000-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v2_reward
chaiml-elo-run-3-cp7000-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v2_reward/config.json
chaiml-elo-run-3-cp7000-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v2_reward/special_tokens_map.json
chaiml-elo-run-3-cp7000-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v2_reward/tokenizer_config.json
chaiml-elo-run-3-cp7000-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v2_reward/vocab.json
chaiml-elo-run-3-cp7000-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v2_reward/merges.txt
chaiml-elo-run-3-cp7000-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v2_reward/tokenizer.json
chaiml-elo-run-3-cp7000-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v2_reward/reward.tensors
Job chaiml-elo-run-3-cp7000-v2-mkmlizer completed after 808.77s with status: succeeded
Stopping job with name chaiml-elo-run-3-cp7000-v2-mkmlizer
Pipeline stage MKMLizer completed in 809.76s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-elo-run-3-cp7000-v2
Waiting for inference service chaiml-elo-run-3-cp7000-v2 to be ready
Inference service chaiml-elo-run-3-cp7000-v2 ready after 40.1731333732605s
Pipeline stage ISVCDeployer completed in 47.31s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.854588747024536s
Received healthy response to inference request in 6.989238739013672s
Received healthy response to inference request in 4.769728183746338s
Received healthy response to inference request in 1.493271827697754s
Received healthy response to inference request in 1.745356798171997s
5 requests
0 failed requests
5th percentile: 1.5436888217926026
10th percentile: 1.5941058158874513
20th percentile: 1.6949398040771484
30th percentile: 2.167203187942505
40th percentile: 3.0108959674835205
50th percentile: 3.854588747024536
60th percentile: 4.220644521713257
70th percentile: 4.586700296401977
80th percentile: 5.213630294799805
90th percentile: 6.101434516906738
95th percentile: 6.5453366279602045
99th percentile: 6.900458316802978
mean time: 3.7704368591308595
Pipeline stage StressChecker completed in 19.69s
chaiml-elo-run-3-cp7000_v2 status is now deployed due to DeploymentManager action
chaiml-elo-run-3-cp7000_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics