Training in progress, step 500

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,58 @@
+{
+  "_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"
+  ],
+  "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": "4.22.2",
+  "use_cache": true,
+  "vocab_size": 250054
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce51a3ed1213a69d70d9cea5c5cf3c0b038ae4f32833a3f3d1055bef94cf3879
+size 2444690425

runs/Sep28_08-35-59_b2b9d645d6a8/1664354238.8399656/events.out.tfevents.1664354238.b2b9d645d6a8.87.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:427d83ccdcc1bdaac74ffe5054842453ce3391c7f01633d8ac010f3c4c7c2a80
+size 5752

runs/Sep28_08-35-59_b2b9d645d6a8/events.out.tfevents.1664354238.b2b9d645d6a8.87.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:980c43866b1b3118fa1f140f31a41a8c1124d1e56fb408204fd7ca3da43cb377
+size 4737

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 50,
+    "max_length": 128,
     "strategy": "LongestFirst",
     "stride": 0
   },

tokenizer_config.json

@@ -4,7 +4,7 @@
   "do_lower_case": true,
   "lowercase": false,
   "mask_token": "[MASK]",
-  "name_or_path": "/content/dump",
+  "name_or_path": "eun-younglee/mBART_tokenizer_custom",
   "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4895bd811d9faa6e6c264dd586f4d5ac787909e399635406f1fc990e6df837f1
+size 3503