Training in progress, epoch 1

.gitignore

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

config.json

@@ -1,31 +1,38 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "airesearch/wangchanberta-base-att-spm-uncased",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "CamembertForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "id2label": {
     "0": "Request",
     "1": "Neutral"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "Neutral": 1,
     "Request": 0
   },
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "pad_token_id": 0,
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
+  "model_type": "camembert",
+  "num_attention_head": 12,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
   "transformers_version": "4.29.1",
-  "vocab_size": 30522
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 25005
 }

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02fe737ac202363ad6f0ea3693b22e90b0a91fd4f5dfbf4ee52362dd0be800e3
+size 421057205

runs/May16_09-47-19_1fa9487fce68/1684230443.1628163/events.out.tfevents.1684230443.1fa9487fce68.53926.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e08fcaebd59c113badd0f7fbc9254f4d31573a145be28ff69667003aed4766b4
+size 5943

runs/May16_09-47-19_1fa9487fce68/events.out.tfevents.1684230443.1fa9487fce68.53926.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fe557276893d6d04213a7b64166893741495d5848c274e5c18e61b992e4cfcb
+size 4580

special_tokens_map.json

@@ -1,7 +1,20 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED",
+    "<_>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -1,13 +1,25 @@
 {
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED",
+    "<_>"
+  ],
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "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": "DistilBertTokenizer",
-  "unk_token": "[UNK]"
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 416,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "CamembertTokenizer",
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e9ea6da351db794c2c892ceeafffe93c07a52c0e894fcc5ef8995ccb4e7eba7
+size 3963