Training in progress, epoch 1

config.json

@@ -5,11 +5,10 @@
   "add_bias_logits": false,
   "add_final_layer_norm": false,
   "architectures": [
-    "BartPrefixPropForConditionalGeneration"
+    "BartForConditionalGeneration"
   ],
   "attention_dropout": 0.1,
   "bos_token_id": 0,
-  "bptt_depth": -1,
   "classif_dropout": 0.1,
   "classifier_dropout": 0.0,
   "d_model": 768,
@@ -28,22 +27,18 @@
   "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,
@@ -52,15 +47,7 @@
   "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:ff4e90f18a0c2b376886c2e32cbe7353812f800dc027ad868b33d80ec59e8006
-size 558266465
+oid sha256:04fb9a9b8f0d873325b6ba6bc20976077c121a48958b425658eb075fd97cbc92
+size 557971229

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d633429ad9b7a18638882560b49fca2fc9e26569b5e79111084ab774711b6099
+oid sha256:6942514476c07a92922d1fc3cbe260e31fa12e528a70c2c7ed75fc12140244ff
 size 4283