Training in progress, step 500

config.json

@@ -1,16 +1,15 @@
 {
-  "_name_or_path": "facebook/bart-large-xsum",
-  "_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,
@@ -25,9 +24,7 @@
   "encoder_layerdrop": 0.0,
   "encoder_layers": 12,
   "eos_token_id": 2,
-  "eos_token_ids": [
-    2
-  ],
+  "forced_bos_token_id": 0,
   "forced_eos_token_id": 2,
   "gradient_checkpointing": false,
   "id2label": {
@@ -42,26 +39,36 @@
     "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,
-  "normalize_embedding": true,
-  "num_beams": 6,
+  "num_beams": 4,
   "num_hidden_layers": 12,
-  "output_past": true,
   "pad_token_id": 1,
-  "prefix": " ",
-  "replacing_rate": 0,
   "scale_embedding": false,
-  "static_position_embeddings": false,
-  "student_decoder_layers": null,
-  "student_encoder_layers": null,
-  "task_specific_params": {},
+  "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": "4.36.0",
   "use_cache": true,
-  "vocab_size": 50264
+  "vocab_size": 50265
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4b2fe8c0ddbc6b74579f6f7988b9491840ced49a9232f208cc054b567eef765
-size 1625422896
+oid sha256:394affa8f628d0472049eea0a01f1f9fb68f2605bef1bed55c7e744e3ac5f3da
+size 1625426996

runs/Dec15_03-14-32_mgrqu6ctr1702517804785-49zpx/events.out.tfevents.1702581278.mgrqu6ctr1702517804785-49zpx.249647.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cbc7d73396ede1088c8f649f561522778b4930f694c9635510a8fb9cd4118ab
+size 5661

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01c663ed19879016797bb08ad8623ff08a0cc86c1262ce86a365b5c98fb515eb
+oid sha256:0436de84178a96363a861fbf0e15bf2d09092e19142cb69178288671744b8909
 size 4411