Training in progress, step 42

config.json

@@ -1,13 +1,15 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "huawei-noah/TinyBERT_General_4L_312D",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "BertForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "cell": {},
+  "classifier_dropout": null,
+  "emb_size": 312,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 312,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -61,6 +63,7 @@
     "49": "LABEL_49"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 1200,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
@@ -113,17 +116,19 @@
     "LABEL_8": 8,
     "LABEL_9": 9
   },
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 4,
   "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "pre_trained": "",
   "problem_type": "single_label_classification",
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
+  "structure": [],
   "torch_dtype": "float32",
   "transformers_version": "4.46.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
   "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edc1bef311fcea51df2bd17d35e3b41be09787ac31461aea85df42c94ee6e644
-size 267980224
+oid sha256:b8d3d32b5679e2c458d1b2b346d314d96fffee4dbb0a796a68e9df71dcbfcb91
+size 57471904

runs/Dec16_15-03-02_c53344d78de6/events.out.tfevents.1734361421.c53344d78de6.295.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:624883e7651f321b93c7eecb7813b2bf5abe176b01b3a6dbea31625d25b3121f
+size 7382

runs/Dec16_15-11-25_c53344d78de6/events.out.tfevents.1734361900.c53344d78de6.295.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2d45a8ad16370350a189cc659e912ad56f030bc44a87a6e26dc004ca71582c1
+size 7501

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": {
     "strategy": "BatchLongest",
     "direction": "Right",

tokenizer_config.json

@@ -41,15 +41,17 @@
       "special": true
     }
   },
-  "clean_up_tokenization_spaces": false,
+  "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
   "do_lower_case": true,
   "mask_token": "[MASK]",
-  "model_max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
+  "tokenizer_class": "BertTokenizer",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4be3aded3a9d8dd6d9c5c92cebcc6334ba062055e82284a7c71bbdb7ac5ffd2
+oid sha256:f774ec1f0aaafd84737fa2ba92eac8ceb73f0a4b26b803de336210995e4cfa37
 size 5240