Training in progress, step 500

config.json

@@ -1,15 +1,15 @@
 {
-  "_name_or_path": "facebook/bart-large-mnli",
-  "_num_labels": 3,
-  "activation_dropout": 0.0,
+  "_name_or_path": "facebook/bart-large",
+  "activation_dropout": 0.1,
   "activation_function": "gelu",
+  "add_bias_logits": false,
   "add_final_layer_norm": false,
   "architectures": [
     "BartForConditionalGeneration"
   ],
-  "attention_dropout": 0.0,
+  "attention_dropout": 0.1,
   "bos_token_id": 0,
-  "classif_dropout": 0.0,
+  "classif_dropout": 0.1,
   "classifier_dropout": 0.0,
   "d_model": 1024,
   "decoder_attention_heads": 16,
@@ -18,32 +18,55 @@
   "decoder_layers": 12,
   "decoder_start_token_id": 2,
   "dropout": 0.1,
+  "early_stopping": true,
   "encoder_attention_heads": 16,
   "encoder_ffn_dim": 4096,
   "encoder_layerdrop": 0.0,
   "encoder_layers": 12,
   "eos_token_id": 2,
+  "forced_bos_token_id": 0,
   "forced_eos_token_id": 2,
   "gradient_checkpointing": false,
   "id2label": {
-    "0": "contradiction",
-    "1": "neutral",
-    "2": "entailment"
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
   },
   "init_std": 0.02,
   "is_encoder_decoder": true,
   "label2id": {
-    "contradiction": 0,
-    "entailment": 2,
-    "neutral": 1
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
   },
   "max_position_embeddings": 1024,
   "model_type": "bart",
+  "no_repeat_ngram_size": 3,
   "normalize_before": false,
+  "num_beams": 4,
   "num_hidden_layers": 12,
-  "output_past": false,
   "pad_token_id": 1,
   "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
+    }
+  },
   "torch_dtype": "float32",
   "transformers_version": "4.39.3",
   "use_cache": true,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17af3ccb39fc52c7cc62a1687ef60962caa542d74e4e13c959b7ec268cc05774
+oid sha256:f937864fca38a564465f7710e53cac3914427153cae7eaaba92b865ba497d1a6
 size 1625426996

runs/May25_06-17-14_332d7128a412/events.out.tfevents.1716617921.332d7128a412.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54388330f8db2bb98d252757fd04e218b21d8d985f8dfaa1bc8848a15773baea
+size 6007

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fb7b7d5df2f5d5423079772df74162b2945961daccba49eaa4741254b567d88
+oid sha256:ab5ccda91aa70574e814c71a849f6934e2bdf40ac505a2726b21265d787b4c65
 size 5048