From 05d4232f63f121baefec9a87704ea7a15933f6e9 Mon Sep 17 00:00:00 2001
From: Juha Kiili <juha@juhakiili.com>
Date: Thu, 21 Nov 2019 12:38:17 +0200
Subject: [PATCH] Add valohai.yaml

---
 valohai.yaml | 94 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 94 insertions(+)
 create mode 100644 valohai.yaml

diff --git a/valohai.yaml b/valohai.yaml
new file mode 100644
index 0000000000..2573551b4e
--- /dev/null
+++ b/valohai.yaml
@@ -0,0 +1,94 @@
+---
+
+- step:
+    name: Execute python examples/run_glue.py
+    image: pytorch/pytorch:nightly-devel-cuda10.0-cudnn7
+    command:
+      - python /valohai/repository/utils/download_glue_data.py --data_dir=/glue_data
+      - pip install -e .
+      - pip install -r examples/requirements.txt
+      - python examples/run_glue.py --do_train --data_dir=/glue_data/{parameter-value:task_name} {parameters}
+    parameters:
+      - name: model_type
+        pass-as: --model_type={v}
+        type: string
+        default: bert
+      - name: model_name_or_path
+        pass-as: --model_name_or_path={v}
+        type: string
+        default: bert-base-uncased
+      - name: task_name
+        pass-as: --task_name={v}
+        type: string
+        default: MRPC
+      - name: max_seq_length
+        pass-as: --max_seq_length={v}
+        description: The maximum total input sequence length after tokenization. Sequences longer than this will be truncated, sequences shorter will be padded.
+        type: integer
+        default: 128
+      - name: per_gpu_train_batch_size
+        pass-as: --per_gpu_train_batch_size={v}
+        description: Batch size per GPU/CPU for training.
+        type: integer
+        default: 8
+      - name: per_gpu_eval_batch_size
+        pass-as: --per_gpu_eval_batch_size={v}
+        description: Batch size per GPU/CPU for evaluation.
+        type: integer
+        default: 8
+      - name: gradient_accumulation_steps
+        pass-as: --gradient_accumulation_steps={v}
+        description: Number of updates steps to accumulate before performing a backward/update pass.
+        type: integer
+        default: 1
+      - name: learning_rate
+        pass-as: --learning_rate={v}
+        description: The initial learning rate for Adam.
+        type: float
+        default: 0.00005
+      - name: adam_epsilon
+        pass-as: --adam_epsilon={v}
+        description: Epsilon for Adam optimizer.
+        type: float
+        default: 0.00000001
+      - name: max_grad_norm
+        pass-as: --max_grad_norm={v}
+        description: Max gradient norm.
+        type: float
+        default: 1.0
+      - name: num_train_epochs
+        pass-as: --num_train_epochs={v}
+        description: Total number of training epochs to perform.
+        type: integer
+        default: 3
+      - name: max_steps
+        pass-as: --max_steps={v}
+        description: If > 0, set total number of training steps to perform. Override num_train_epochs.
+        type: integer
+        default: -1
+      - name: warmup_steps
+        pass-as: --warmup_steps={v}
+        description: Linear warmup over warmup_steps.
+        type: integer
+        default: -1
+      - name: logging_steps
+        pass-as: --logging_steps={v}
+        description: Log every X updates steps.
+        type: integer
+        default: 25
+      - name: save_steps
+        pass-as: --save_steps={v}
+        description: Save checkpoint every X updates steps.
+        type: integer
+        default: -1
+      - name: output_dir
+        pass-as: --output_dir={v}
+        type: string
+        default: /valohai/outputs
+      - name: evaluate_during_training
+        description: Run evaluation during training at each logging step.
+        type: flag
+        default: true
+      - name: do_lower_case
+        description: Set this flag if you are using an uncased model.
+        type: flag