From 0c1a22545820db24ef4f9932b2e55f7b012815d4 Mon Sep 17 00:00:00 2001 From: Abhiram E Date: Tue, 11 Jun 2019 12:41:24 -0400 Subject: [PATCH] Changes to train on AMLCompute --- utils_nlp/model/gensen/aml_config.json | 46 ++++++++++++++++++++++++++ 1 file changed, 46 insertions(+) create mode 100644 utils_nlp/model/gensen/aml_config.json diff --git a/utils_nlp/model/gensen/aml_config.json b/utils_nlp/model/gensen/aml_config.json new file mode 100644 index 0000000..72d7444 --- /dev/null +++ b/utils_nlp/model/gensen/aml_config.json @@ -0,0 +1,46 @@ +{ + "training": { + "optimizer": "adam", + "clip_c": 1, + "lrate": 0.0001, + "batch_size": 48, + "n_gpus": 1, + "stop_patience": 2 + }, + "management": { + "monitor_loss": 480, + "print_samples": 12800, + "checkpoint_freq": 480000, + "eval_freq": 9600 + }, + "data": { + "paths": [ + { + "train_src": "data/processed/snli_1.0_train.txt.s1.tok", + "train_trg": "data/processed/snli_1.0_train.txt.s2.tok", + "val_src": "data/processed/snli_1.0_dev.txt.s1.tok", + "val_trg": "data/processed/snli_1.0_dev.txt.s1.tok", + "taskname": "snli" + } + ], + "max_src_length": 90, + "max_trg_length": 90, + "task": "multi-seq2seq-nli", + "save_dir": "data/models/example", + "nli_train": "data/processed/snli_1.0_train.txt.clean.noblank", + "nli_dev": "data/processed/snli_1.0_dev.txt.clean.noblank", + "nli_test": "data/processed/snli_1.0_test.txt.clean.noblank" + }, + "model": { + "dim_src": 2048, + "dim_trg": 2048, + "dim_word_src": 512, + "dim_word_trg": 512, + "n_words_src": 80000, + "n_words_trg": 30000, + "n_layers_src": 1, + "bidirectional": true, + "layernorm": false, + "dropout": 0.8 + } +}