Training in progress, step 7000

config.json

@@ -1,76 +1,31 @@
 {
-  "_name_or_path": "facebook/bart-base",
-  "activation_dropout": 0.1,
-  "activation_function": "gelu",
-  "add_bias_logits": false,
-  "add_final_layer_norm": false,
+  "_name_or_path": "google/electra-large-generator",
   "architectures": [
-    "BartForCausalLM"
+    "ElectraForCausalLM"
   ],
-  "attention_dropout": 0.1,
-  "bos_token_id": 0,
-  "classif_dropout": 0.1,
-  "classifier_dropout": 0.0,
-  "d_model": 768,
-  "decoder_attention_heads": 12,
-  "decoder_ffn_dim": 3072,
-  "decoder_layerdrop": 0.0,
-  "decoder_layers": 6,
-  "decoder_start_token_id": 2,
-  "dropout": 0.1,
-  "early_stopping": true,
-  "encoder_attention_heads": 12,
-  "encoder_ffn_dim": 3072,
-  "encoder_layerdrop": 0.0,
-  "encoder_layers": 6,
-  "eos_token_id": 2,
-  "forced_bos_token_id": 0,
-  "forced_eos_token_id": 2,
-  "gradient_checkpointing": false,
-  "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2"
-  },
-  "init_std": 0.02,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 1024,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
   "is_decoder": true,
-  "is_encoder_decoder": false,
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2
-  },
-  "max_position_embeddings": 1024,
-  "model_type": "bart",
-  "no_repeat_ngram_size": 3,
-  "normalize_before": false,
-  "normalize_embedding": true,
-  "num_beams": 4,
-  "num_hidden_layers": 6,
-  "pad_token_id": 1,
-  "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
-    }
-  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
   "torch_dtype": "float32",
   "transformers_version": "4.33.3",
+  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 50265
+  "vocab_size": 30522
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d35e0f78617d674afb849bc997ee7f775248d89369eb29e0864e5067ef4733f0
-size 384469069
+oid sha256:7069abb1970db1b61ba8437a477a4ae9e0733f5263c096f257f74754b4863452
+size 205317885

special_tokens_map.json

@@ -1,15 +1,7 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7bb7ca1064b9430bf0dbda9cb011b3be3449663b1f7f2abd9c089c700cd4a83
-size 2108872
+oid sha256:2fc687b11de0bc1b3d8348f92e3b49ef1089a621506c7661fbf3248fcd54947e
+size 711649

tokenizer_config.json

@@ -1,15 +1,13 @@
 {
-  "add_prefix_space": false,
-  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "errors": "replace",
-  "mask_token": "<mask>",
-  "model_max_length": 1024,
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "tokenizer_class": "BartTokenizer",
-  "trim_offsets": true,
-  "unk_token": "<unk>"
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "ElectraTokenizer",
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fed6a14f77dbaa02c7ee5e4897e67646fd134c8e793e583f4c9e2b0330790378
+oid sha256:5e20146335638a737527b74cf88ca20db045bd09d3bd01f62c804d1edc5fa00b
 size 4027