Training in progress, epoch 1

config.json

@@ -5,10 +5,11 @@
   "add_bias_logits": false,
   "add_final_layer_norm": false,
   "architectures": [
-    "BartForConditionalGeneration"
+    "BartPrefixPropForConditionalGeneration"
   ],
   "attention_dropout": 0.1,
   "bos_token_id": 0,
+  "bptt_depth": -1,
   "classif_dropout": 0.1,
   "classifier_dropout": 0.0,
   "d_model": 768,
@@ -27,18 +28,22 @@
   "forced_bos_token_id": 0,
   "forced_eos_token_id": 2,
   "gradient_checkpointing": false,
+  "hidden_dropout_prob": 0.1,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
     "2": "LABEL_2"
   },
   "init_std": 0.02,
+  "input_size": 512,
   "is_encoder_decoder": true,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
     "LABEL_2": 2
   },
+  "label_max_size": 256,
+  "max_n_segments": 4,
   "max_position_embeddings": 1024,
   "model_type": "bart",
   "no_repeat_ngram_size": 3,
@@ -47,7 +52,15 @@
   "num_beams": 4,
   "num_hidden_layers": 6,
   "pad_token_id": 1,
+  "post_seq_len": 128,
+  "pre_seq_len": 16,
+  "prefix_projection": false,
+  "propagate_prefix": "only",
+  "propagate_prefix_scalar": false,
   "scale_embedding": false,
+  "segment_alignment": "left",
+  "sum_loss": true,
+  "sum_token_size": 0,
   "task_specific_params": {
     "summarization": {
       "length_penalty": 1.0,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:395f7520f673490d2d95b09febf2d363dd4910b064ecfa56ebbb5206b8262c3d
-size 557971229
+oid sha256:b02ac8497bf83830b37b64270aefd83dd3875bca8812ce9f74eecc155b06552f
+size 558266465

tokenizer.json

@@ -1,7 +1,21 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 128,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": {
+      "Fixed": 128
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 1,
+    "pad_type_id": 0,
+    "pad_token": "<pad>"
+  },
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6b929350665b6b984003aafd584c4273c8b7ac61d24b96fe60fee3a4b21842a
+oid sha256:d633429ad9b7a18638882560b49fca2fc9e26569b5e79111084ab774711b6099
 size 4283