Training in progress, step 1000

config.json

@@ -1,15 +1,16 @@
 {
-  "_name_or_path": "facebook/bart-large",
-  "activation_dropout": 0.1,
+  "_name_or_path": "facebook/bart-large-xsum",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
   "activation_function": "gelu",
   "add_bias_logits": false,
   "add_final_layer_norm": false,
   "architectures": [
     "Model"
   ],
-  "attention_dropout": 0.1,
+  "attention_dropout": 0.0,
   "bos_token_id": 0,
-  "classif_dropout": 0.1,
+  "classif_dropout": 0.0,
   "classifier_dropout": 0.0,
   "d_model": 1024,
   "decoder_attention_heads": 16,
@@ -24,7 +25,9 @@
   "encoder_layerdrop": 0.0,
   "encoder_layers": 12,
   "eos_token_id": 2,
-  "forced_bos_token_id": 0,
+  "eos_token_ids": [
+    2
+  ],
   "forced_eos_token_id": 2,
   "gradient_checkpointing": false,
   "id2label": {
@@ -39,7 +42,9 @@
     "LABEL_1": 1,
     "LABEL_2": 2
   },
+  "max_length": 62,
   "max_position_embeddings": 1024,
+  "min_length": 11,
   "model_type": "bart",
   "n_gram_linear": true,
   "n_gram_lm": false,
@@ -48,32 +53,20 @@
   "no_base_loss": false,
   "no_repeat_ngram_size": 3,
   "normalize_before": false,
-  "num_beams": 4,
+  "normalize_embedding": true,
+  "num_beams": 6,
   "num_hidden_layers": 12,
+  "output_past": true,
   "pad_token_id": 1,
+  "prefix": " ",
+  "replacing_rate": 0,
   "scale_embedding": false,
-  "task_specific_params": {
-    "summarization": {
-      "length_penalty": 1.0,
-      "max_length": 128,
-      "min_length": 12,
-      "num_beams": 4
-    },
-    "summarization_cnn": {
-      "length_penalty": 2.0,
-      "max_length": 142,
-      "min_length": 56,
-      "num_beams": 4
-    },
-    "summarization_xsum": {
-      "length_penalty": 1.0,
-      "max_length": 62,
-      "min_length": 11,
-      "num_beams": 6
-    }
-  },
+  "static_position_embeddings": false,
+  "student_decoder_layers": null,
+  "student_encoder_layers": null,
+  "task_specific_params": {},
   "torch_dtype": "float32",
   "transformers_version": "4.34.0",
   "use_cache": true,
-  "vocab_size": 50265
+  "vocab_size": 50264
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73e662219dd0fd9e8cc7b55a67b678f4cf85da91c1a4be1bc44cdf888048f053
-size 1629740437
+oid sha256:e7e88f0d24071c928cd505799a2d35cea3b9b01153b065cda67e20d0b9788c49
+size 1629736341

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c9a9e9c75d362ad94762178e57491667c41abaa3dabe0ab81e0aabdcc4f02f9
+oid sha256:ccaf7a242d9b8c2c27a94961c130359eb966e079dc935724776aa9bc515d027b
 size 4219