Training in progress, step 500

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": [
     "BartForConditionalGeneration"
   ],
-  "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": {
@@ -39,36 +42,26 @@
     "LABEL_1": 1,
     "LABEL_2": 2
   },
+  "max_length": 62,
   "max_position_embeddings": 1024,
+  "min_length": 11,
   "model_type": "bart",
   "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": "4.36.0",
   "use_cache": true,
-  "vocab_size": 50265
+  "vocab_size": 50264
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d993e71f2e7d25d5da7564e83db6bf597eb75a3c2c1991783c252d4e670b7809
-size 1625426996
+oid sha256:e5015dbf1828e09877584d573146bb491729ae02ea368edcacad7664ff0728be
+size 1625422896

runs/Mar24_14-29-21_gde8xrctr1711261266898-zjnhj/events.out.tfevents.1711261769.gde8xrctr1711261266898-zjnhj.3147.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f1955d38122960825db3e93bceb783926194eb82f5a1465b47c2f0498bd4a69
+size 5590

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ff28fd884c4574fff0eba0315fb39b3e3c8973f7c12c8b88f79497dc1cdf62f
+oid sha256:7b0c141b32a5641a47ae75c6739233ed1d4ddb828f47bfdcda608686ea896e07
 size 4475