Upload 3 files

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+supervised.pol.mdl filter=lfs diff=lfs merge=lfs -text

config_saved.json

@@ -0,0 +1 @@
+{"args": {"seed": 0, "eval_freq": 1, "dataset_name": "sgd", "model_path": ""}, "config": {"batchsz": 64, "epoch": 1, "gamma": 0.99, "policy_lr": 5e-06, "supervised_lr": 1e-05, "entropy_weight": 0.01, "value_lr": 0.0001, "save_dir": "save", "log_dir": "log", "save_per_epoch": 5000, "hidden_size": 256, "load": "save/best", "logging_mode": "INFO", "use_cer": true, "memory_size": 5000, "behaviour_cloning_weight": 0.1, "supervised_weight": 0.0, "online_offline_ratio": 0.2, "smoothed_value_function": false, "use_reservoir_sampling": false, "seed": 0, "lambda": 1, "tau": 0.001, "policy_freq": 1, "print_per_batch": 400, "c": 1.0, "rho_bar": 1, "max_length": 10, "noisy_linear": false, "dataset_name": "sgd", "data_percentage": 1.0, "dialogue_order": 0, "multiwoz_like": false, "regularization_weight": 0.0, "enc_input_dim": 128, "enc_nhead": 2, "enc_d_hid": 128, "enc_nlayers": 4, "enc_dropout": 0.1, "dec_input_dim": 128, "dec_nhead": 2, "dec_d_hid": 128, "dec_nlayers": 2, "dec_dropout": 0.0, "action_embedding_dim": 128, "domain_embedding_dim": 64, "value_embedding_dim": 12, "node_embedding_dim": 128, "roberta_path": "", "node_attention": true, "semantic_descriptions": true, "freeze_roberta": true, "use_pooled": false, "mean": true, "roberta_actions": true, "independent_descriptions": true, "random_matrix": false, "distance_metric": false, "verbose": false, "ignore_features": [], "domains_removed": ["hospital", "police", "train", "hotel", "attraction", "taxi"], "only_active_values": false, "permuted_data": false, "need_weights": false, "cls_dim": 128, "independent": true, "old_critic": false, "pos_weight": 5, "weight_decay": 1e-05}, "policy_config": null}

supervised.pol.mdl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a52f1b3ef34f075c3932d80e6d569157a307ff19796421996e393e7f8ea7bc5f
+size 9331458

train_INFO.log

@@ -0,0 +1,29 @@
+Visible device: cuda
+Seed used: 0
+Batch size: 64
+Epochs: 1
+Learning rate: 1e-05
+Entropy weight: 0.01
+Regularization weight: 0.0
+Only use multiwoz like domains: False
+We use: 100.0% of the data
+Dialogue order used: 0
+Vectorizer: Data set used is sgd
+We filter state by active domains: True
+Vectorizer: Data set used is sgd
+Embedding semantic descriptions: True
+Embedded descriptions successfully. Size: torch.Size([1678, 768])
+Data set used for descriptions: sgd
+We use Roberta to embed actions.
+Didnt load a model
+Start training
+Epoch: 0
+Average actions: 1.684490442276001
+Average target actions: 2.024200201034546
+Precision: 0.3306945737954022
+Recall: 0.27521008403361347
+F1: 0.3004118891239007
+<<dialog policy>> epoch 0: saved network to mdl
+Best Precision: 0.3306945737954022
+Best Recall: 0.27521008403361347
+Best F1: 0.3004118891239007