Training in progress, epoch 1

config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "pascalrai/pretrain_nep_BART",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.0,
+  "d_model": 768,
+  "decoder_attention_heads": 6,
+  "decoder_ffn_dim": 768,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 1,
+  "do_sample": true,
+  "dropout": 0.1,
+  "encoder_attention_heads": 6,
+  "encoder_ffn_dim": 768,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 1,
+  "forced_eos_token_id": 1,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "length_penalty": 2.0,
+  "max_length": 128,
+  "max_position_embeddings": 1000,
+  "min_length": 32,
+  "model_type": "bart",
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 3,
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0",
+  "use_cache": true,
+  "vocab_size": 55000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fe775663e4cb05ecbc4eba068c10c8c67e400707385d5877e1eee6847a1718b
+size 402350000

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc19340c7d377c581358f4f37d7f3ad6d7db7e7d3bac6a1d63cc4e6d69d04790
+size 4536