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 sha256:3c28b77d901490dd9ab4850112d15be757e93aa27631452a1d5c6a9cfd97b8bb
-size 1625426996
+oid sha256:83f7cc07c99413558ca108b5d6e6a14a737179290a5c2c553de439ac5aa12e8c
+size 1625422896

runs/Dec15_09-37-28_mgrqu6ctr1702517804785-49zpx/events.out.tfevents.1702604256.mgrqu6ctr1702517804785-49zpx.139978.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a60779985518f009914e0cec8d511acc48e49e1306c4ed0179ba8910a44d5d0f
+size 5553

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0436de84178a96363a861fbf0e15bf2d09092e19142cb69178288671744b8909
+oid sha256:9bd1c413dea93de97af9a0022fa43de72a1008e1b8a3d2b1a6e02aae435d1d06
 size 4411