Training in progress, epoch 0

added_tokens.json

@@ -1,3 +1,3 @@
 {
-  "<|PAD|>": 250054
+  "<CLS>": 250054
 }

config.json

@@ -1,17 +1,58 @@
 {
-  "base_model_name_or_path": "facebook/mbart-large-50",
-  "bias": "none",
-  "fan_in_fan_out": false,
-  "inference_mode": true,
-  "init_lora_weights": true,
-  "lora_alpha": 32,
-  "lora_dropout": 0.5,
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "r": 32,
-  "target_modules": [
-    "q_proj",
-    "v_proj"
+  "_name_or_path": "facebook/mbart-large-50",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": true,
+  "architectures": [
+    "MBartForConditionalGeneration"
   ],
-  "task_type": "SEQ_2_SEQ_LM"
-}
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "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_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "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
+  },
+  "max_length": 200,
+  "max_position_embeddings": 1024,
+  "model_type": "mbart",
+  "normalize_before": true,
+  "normalize_embedding": true,
+  "num_beams": 5,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "static_position_embeddings": false,
+  "tokenizer_class": "MBart50Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.2",
+  "use_cache": true,
+  "vocab_size": 250055
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f5c688de31bb51b98076c8b4a12e77b496306d13b3db2d0ea574f37aca7e353
-size 2463717597
+oid sha256:1c730d0c4d0fe92b17cef718615aaba4aa7d4a83689e3b7fe366708d6a3c4722
+size 2444698141

special_tokens_map.json

@@ -53,11 +53,11 @@
     "gl_ES",
     "sl_SI"
   ],
-  "bos_token": "<s>",
+  "bos_token": "</s>",
   "cls_token": "<s>",
-  "eos_token": "</s>",
+  "eos_token": "<CLS>",
   "mask_token": "<mask>",
-  "pad_token": "<|PAD|>",
+  "pad_token": "<pad>",
   "sep_token": "</s>",
   "unk_token": "<unk>"
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:431f1ce0127f5078199c6f3fbe0cf273764f6b8ffedb45577109078994e50932
-size 17110206
+oid sha256:e1d4485f24d88d0e8f390de6f5f30f1964698389669dd3b255ca28726400d566
+size 17110207

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:199ef1c3e09954ce8d4c56357cc4260b5218b19626289b3fc790b91ca0495ef6
+oid sha256:d001015cb7de8f0f2df818148c25e1624dce63328e2ea32e10ef1483e87fc0b3
 size 4091