Training in progress, epoch 1

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "Alfahluzi/bert2bert-abs-final-lr-5e-05-encmaxlen-512-decmaxlen-256",
   "architectures": [
     "EncoderDecoderModel"
   ],
@@ -169,14 +170,14 @@
   },
   "eos_token_id": 4,
   "is_encoder_decoder": true,
-  "model_type": "encoder-decoder",
-  "pad_token_id": 0,
   "length_penalty": 2.0,
   "max_length": 80,
   "min_length": 10,
+  "model_type": "encoder-decoder",
   "no_repeat_ngram_size": 3,
   "num_beams": 10,
+  "pad_token_id": 0,
   "torch_dtype": "float32",
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.40.0",
   "vocab_size": 31923
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d14b2625731e10121a80f6ac3f80823b2ec5bc1eeaff746ba755b443f7f2ab5
+oid sha256:0816dc34a32b97874e5fa9d26ea412a3994710e4de3176c817ccdb0633594a66
 size 998132132

runs/Apr19_10-11-58_28c8ce36e596/events.out.tfevents.1713521519.28c8ce36e596.1117.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0f2e58e2ba20271dfde883d478ed49d65b481f505b10442dc8338884392e702
+size 10260

special_tokens_map.json

@@ -1,7 +1,37 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -46,12 +46,19 @@
   "do_basic_tokenize": true,
   "do_lower_case": true,
   "mask_token": "[MASK]",
+  "max_length": 256,
   "model_max_length": 1000000000000000019884624838656,
   "never_split": null,
+  "pad_to_multiple_of": null,
   "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "sep_token": "[SEP]",
+  "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:631aae2ce4635324c15d53d1768e2aa35de994426d0a551012fc9bb8fb0e4b35
-size 5112
+oid sha256:d690f6119f320209cf0edb738cfd51e0fc5b1678e7eeca9220caba20770d2e43
+size 5240