Training in progress, epoch 1

config.json

@@ -1,38 +1,33 @@
 {
-  "_name_or_path": "airesearch/wangchanberta-base-att-spm-uncased",
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "CamembertForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "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,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "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": "camembert",
-  "num_attention_head": 12,
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 1,
-  "position_embedding_type": "absolute",
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
   "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.29.1",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 25005
+  "vocab_size": 30522
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:721852c5d35177c05942235cd1ab21c12400ecc99164304339652efe98e47747
-size 421057205
+oid sha256:b0a65c1266d828104a3a93c5bf15f3da35bec5592b9aafb658d9a2df1a071e4b
+size 267855533

runs/May16_09-57-58_1fa9487fce68/1684231081.2639241/events.out.tfevents.1684231081.1fa9487fce68.53926.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ee03c02cd6ab5e89d711d702d5e0b839cf17d461e4645c19d5dfbbf8abe2b39
+size 5943

runs/May16_09-57-58_1fa9487fce68/events.out.tfevents.1684231081.1fa9487fce68.53926.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94a3a02954cb3c00577dab62194a7a19f631335804fd7cea5bb86b3b4a1009e9
+size 4362

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e9ea6da351db794c2c892ceeafffe93c07a52c0e894fcc5ef8995ccb4e7eba7
+oid sha256:155f9c09bb54102df069a1b96f680346df858a2c6d0f81c6c0e94a2b812835f0
 size 3963