Training in progress, epoch 1

config.json

@@ -1,20 +1,21 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "huawei-noah/TinyBERT_General_4L_312D",
   "architectures": [
     "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
+  "cell": {},
   "classifier_dropout": null,
-  "gradient_checkpointing": false,
+  "emb_size": 312,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 312,
   "id2label": {
     "0": "negative",
     "1": "positive"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 1200,
   "label2id": {
     "negative": 0,
     "positive": 1
@@ -23,10 +24,12 @@
   "max_position_embeddings": 512,
   "model_type": "bert",
   "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_hidden_layers": 4,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
+  "pre_trained": "",
   "problem_type": "single_label_classification",
+  "structure": [],
   "torch_dtype": "float32",
   "transformers_version": "4.44.2",
   "type_vocab_size": 2,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb117a0cd21a1cf38123ed94ab64d67516db3e840485ac19d4fa43e8a8fe2824
-size 437958648
+oid sha256:a61f980ef66b3d08e91389ca4e9572e8a03beacb7c62eb7276663c0c42933934
+size 57411808

runs/Nov05_22-19-22_46b3524ef801/events.out.tfevents.1730845193.46b3524ef801.811.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:001e020c1bdbf4e85b02f33813529a4dc69035dfa5970ef5871143d7b3123a25
+size 10175

runs/Nov05_23-20-30_46b3524ef801/events.out.tfevents.1730848836.46b3524ef801.811.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:438f086382cd90eed09b837f7ed9db6e89c7f68ec3542d3fe5610c4abee677e8
+size 5115

runs/Nov05_23-21-12_46b3524ef801/events.out.tfevents.1730848881.46b3524ef801.811.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca7df368c354767d0a8bd569b494f92857a4ed3bdc6cdfa75914a93f78799abf
+size 5115

runs/Nov05_23-23-33_46b3524ef801/events.out.tfevents.1730849018.46b3524ef801.811.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:807cfa7f2c8bd31b8607ef198101bebf15ba57b6c8a01c41ed2d607a0ef6c8f5
+size 6282

tokenizer_config.json

@@ -43,9 +43,11 @@
   },
   "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,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7148495376ddc25c18323f1abf59218375cab6ebdc15e742dc437eec60cdee57
+oid sha256:9f833beed14970205e0757ba46e53564c71ed3f6b4f4f768bfb17ea42677841d
 size 5240