submission_id: chaiml-elo-alignment-run-3_v29
developer_uid: Jellywibble
alignment_samples: 0
best_of: 16
celo_rating: 1249.38
display_name: dpo-baseline
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': 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, 'reward_max_token_input': 256}
is_internal_developer: True
language_model: ChaiML/elo_alignment_run_3
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: ChaiML/elo_alignment_run
model_name: dpo-baseline
model_num_parameters: 8030261248.0
model_repo: ChaiML/elo_alignment_run_3
model_size: 8B
num_battles: 9782
num_wins: 5472
propriety_score: 0.7219003476245655
propriety_total_count: 863.0
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/gpt2_xl_pairwise_89m_step_347634
status: torndown
submission_type: basic
timestamp: 2024-08-05T23:08:00+00:00
us_pacific_date: 2024-08-05
win_ratio: 0.5593948067879779
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-elo-alignment-run-3-v29-mkmlizer
Waiting for job on chaiml-elo-alignment-run-3-v29-mkmlizer to finish
Stopping job with name chaiml-elo-alignment-run-3-v29-mkmlizer
%s, retrying in %s seconds...
Starting job with name chaiml-elo-alignment-run-3-v29-mkmlizer
Waiting for job on chaiml-elo-alignment-run-3-v29-mkmlizer to finish
chaiml-elo-alignment-run-3-v29-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-elo-alignment-run-3-v29-mkmlizer: ║ _____ __ __ ║
chaiml-elo-alignment-run-3-v29-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-elo-alignment-run-3-v29-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-elo-alignment-run-3-v29-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-elo-alignment-run-3-v29-mkmlizer: ║ /___/ ║
chaiml-elo-alignment-run-3-v29-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v29-mkmlizer: ║ Version: 0.9.9 ║
chaiml-elo-alignment-run-3-v29-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-elo-alignment-run-3-v29-mkmlizer: ║ https://mk1.ai ║
chaiml-elo-alignment-run-3-v29-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v29-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-elo-alignment-run-3-v29-mkmlizer: ║ belonging to: ║
chaiml-elo-alignment-run-3-v29-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v29-mkmlizer: ║ Chai Research Corp. ║
chaiml-elo-alignment-run-3-v29-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-elo-alignment-run-3-v29-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-elo-alignment-run-3-v29-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v29-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-elo-alignment-run-3-v29-mkmlizer: Downloaded to shared memory in 39.553s
chaiml-elo-alignment-run-3-v29-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp4dwbtir0, device:0
chaiml-elo-alignment-run-3-v29-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-elo-alignment-run-3-v29-mkmlizer: quantized model in 29.362s
chaiml-elo-alignment-run-3-v29-mkmlizer: Processed model ChaiML/elo_alignment_run_3 in 68.915s
chaiml-elo-alignment-run-3-v29-mkmlizer: creating bucket guanaco-mkml-models
chaiml-elo-alignment-run-3-v29-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-elo-alignment-run-3-v29-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v29
chaiml-elo-alignment-run-3-v29-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v29/config.json
chaiml-elo-alignment-run-3-v29-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v29/tokenizer.json
chaiml-elo-alignment-run-3-v29-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v29/flywheel_model.0.safetensors
chaiml-elo-alignment-run-3-v29-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
chaiml-elo-alignment-run-3-v29-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:10, 27.07it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:07, 36.31it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:08, 33.76it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:07, 37.17it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:07, 34.75it/s] Loading 0: 10%|█ | 30/291 [00:00<00:06, 38.45it/s] Loading 0: 12%|█▏ | 34/291 [00:01<00:09, 25.99it/s] Loading 0: 13%|█▎ | 38/291 [00:01<00:09, 26.63it/s] Loading 0: 14%|█▍ | 42/291 [00:01<00:09, 25.59it/s] Loading 0: 16%|█▋ | 48/291 [00:01<00:07, 30.91it/s] Loading 0: 18%|█▊ | 52/291 [00:01<00:07, 30.55it/s] Loading 0: 20%|█▉ | 57/291 [00:01<00:07, 32.72it/s] Loading 0: 21%|██ | 61/291 [00:01<00:07, 31.75it/s] Loading 0: 23%|██▎ | 66/291 [00:02<00:06, 33.77it/s] Loading 0: 24%|██▍ | 70/291 [00:02<00:06, 32.43it/s] Loading 0: 25%|██▌ | 74/291 [00:02<00:06, 31.52it/s] Loading 0: 27%|██▋ | 78/291 [00:02<00:06, 31.85it/s] Loading 0: 28%|██▊ | 82/291 [00:02<00:09, 21.96it/s] Loading 0: 29%|██▉ | 85/291 [00:02<00:08, 23.21it/s] Loading 0: 31%|███ | 90/291 [00:03<00:07, 27.57it/s] Loading 0: 32%|███▏ | 94/291 [00:03<00:06, 28.21it/s] Loading 0: 34%|███▍ | 99/291 [00:03<00:06, 31.12it/s] Loading 0: 35%|███▌ | 103/291 [00:03<00:06, 30.68it/s] Loading 0: 37%|███▋ | 108/291 [00:03<00:05, 33.62it/s] Loading 0: 38%|███▊ | 112/291 [00:03<00:05, 32.47it/s] Loading 0: 40%|███▉ | 116/291 [00:03<00:05, 32.35it/s] Loading 0: 42%|████▏ | 122/291 [00:03<00:04, 36.78it/s] Loading 0: 44%|████▎ | 127/291 [00:04<00:04, 34.20it/s] Loading 0: 46%|████▌ | 133/291 [00:04<00:05, 28.48it/s] Loading 0: 47%|████▋ | 137/291 [00:04<00:05, 28.97it/s] Loading 0: 48%|████▊ | 141/291 [00:04<00:05, 27.35it/s] Loading 0: 51%|█████ | 147/291 [00:04<00:04, 32.23it/s] Loading 0: 52%|█████▏ | 151/291 [00:04<00:04, 31.56it/s] Loading 0: 54%|█████▎ | 156/291 [00:05<00:03, 34.06it/s] Loading 0: 55%|█████▍ | 160/291 [00:05<00:04, 32.55it/s] Loading 0: 57%|█████▋ | 165/291 [00:05<00:03, 34.52it/s] Loading 0: 58%|█████▊ | 169/291 [00:05<00:03, 31.94it/s] Loading 0: 60%|█████▉ | 174/291 [00:05<00:03, 33.48it/s] Loading 0: 61%|██████ | 178/291 [00:05<00:03, 31.89it/s] Loading 0: 63%|██████▎ | 183/291 [00:05<00:02, 36.03it/s] Loading 0: 64%|██████▍ | 187/291 [00:06<00:04, 24.77it/s] Loading 0: 66%|██████▌ | 191/291 [00:06<00:03, 26.11it/s] Loading 0: 67%|██████▋ | 195/291 [00:06<00:03, 25.28it/s] Loading 0: 69%|██████▉ | 201/291 [00:06<00:02, 30.40it/s] Loading 0: 70%|███████ | 205/291 [00:06<00:02, 30.05it/s] Loading 0: 72%|███████▏ | 210/291 [00:06<00:02, 32.67it/s] Loading 0: 74%|███████▎ | 214/291 [00:06<00:02, 31.65it/s] Loading 0: 75%|███████▌ | 219/291 [00:07<00:02, 33.52it/s] Loading 0: 77%|███████▋ | 223/291 [00:07<00:02, 32.30it/s] Loading 0: 78%|███████▊ | 227/291 [00:07<00:02, 31.43it/s] Loading 0: 79%|███████▉ | 231/291 [00:07<00:01, 31.48it/s] Loading 0: 81%|████████ | 235/291 [00:07<00:02, 23.77it/s] Loading 0: 82%|████████▏ | 239/291 [00:07<00:02, 24.04it/s] Loading 0: 85%|████████▍ | 246/291 [00:08<00:01, 31.55it/s] Loading 0: 86%|████████▌ | 250/291 [00:08<00:01, 31.38it/s] Loading 0: 88%|████████▊ | 255/291 [00:08<00:01, 34.22it/s] Loading 0: 89%|████████▉ | 259/291 [00:08<00:00, 32.91it/s] Loading 0: 91%|█████████ | 264/291 [00:08<00:00, 35.47it/s] Loading 0: 92%|█████████▏| 268/291 [00:08<00:00, 34.18it/s] Loading 0: 94%|█████████▍| 273/291 [00:08<00:00, 35.88it/s] Loading 0: 95%|█████████▌| 277/291 [00:08<00:00, 33.64it/s] Loading 0: 97%|█████████▋| 281/291 [00:09<00:00, 32.58it/s] Loading 0: 98%|█████████▊| 286/291 [00:14<00:01, 2.56it/s] Loading 0: 99%|█████████▉| 289/291 [00:14<00:00, 3.19it/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.
chaiml-elo-alignment-run-3-v29-mkmlizer: warnings.warn(
chaiml-elo-alignment-run-3-v29-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.
chaiml-elo-alignment-run-3-v29-mkmlizer: warnings.warn(
chaiml-elo-alignment-run-3-v29-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.
chaiml-elo-alignment-run-3-v29-mkmlizer: warnings.warn(
chaiml-elo-alignment-run-3-v29-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:05<00:05, 5.24s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 3.85s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.06s/it]
chaiml-elo-alignment-run-3-v29-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 2.41it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.98it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.62it/s]
chaiml-elo-alignment-run-3-v29-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-elo-alignment-run-3-v29-mkmlizer: Saving duration: 1.406s
chaiml-elo-alignment-run-3-v29-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 12.930s
chaiml-elo-alignment-run-3-v29-mkmlizer: creating bucket guanaco-reward-models
chaiml-elo-alignment-run-3-v29-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v29_reward/merges.txt
chaiml-elo-alignment-run-3-v29-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v29_reward/vocab.json
chaiml-elo-alignment-run-3-v29-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v29_reward/tokenizer.json
chaiml-elo-alignment-run-3-v29-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v29_reward/reward.tensors
Job chaiml-elo-alignment-run-3-v29-mkmlizer completed after 115.13s with status: succeeded
Stopping job with name chaiml-elo-alignment-run-3-v29-mkmlizer
Pipeline stage MKMLizer completed in 116.63s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-elo-alignment-run-3-v29
Waiting for inference service chaiml-elo-alignment-run-3-v29 to be ready
Inference service chaiml-elo-alignment-run-3-v29 ready after 171.03773880004883s
Pipeline stage ISVCDeployer completed in 172.99s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2619433403015137s
Received healthy response to inference request in 1.4021432399749756s
Received healthy response to inference request in 1.4004554748535156s
Received healthy response to inference request in 1.4001550674438477s
Received healthy response to inference request in 1.4049668312072754s
5 requests
0 failed requests
5th percentile: 1.4002151489257812
10th percentile: 1.4002752304077148
20th percentile: 1.400395393371582
30th percentile: 1.4007930278778076
40th percentile: 1.4014681339263917
50th percentile: 1.4021432399749756
60th percentile: 1.4032726764678956
70th percentile: 1.4044021129608155
80th percentile: 1.5763621330261233
90th percentile: 1.9191527366638184
95th percentile: 2.090548038482666
99th percentile: 2.227664279937744
mean time: 1.5739327907562255
Pipeline stage StressChecker completed in 8.62s
chaiml-elo-alignment-run-3_v29 status is now deployed due to DeploymentManager action
chaiml-elo-alignment-run-3_v29 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-elo-alignment-run-3_v29
Running pipeline stage ISVCDeleter
Checking if service chaiml-elo-alignment-run-3-v29 is running
Tearing down inference service chaiml-elo-alignment-run-3-v29
Service chaiml-elo-alignment-run-3-v29 has been torndown
Pipeline stage ISVCDeleter completed in 6.33s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-elo-alignment-run-3-v29/config.json from bucket guanaco-mkml-models
Deleting key chaiml-elo-alignment-run-3-v29/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-elo-alignment-run-3-v29/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-elo-alignment-run-3-v29/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-elo-alignment-run-3-v29/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-elo-alignment-run-3-v29_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v29_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v29_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v29_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v29_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v29_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v29_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.46s
chaiml-elo-alignment-run-3_v29 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics