Training in progress, epoch 1

config.json

@@ -1,19 +1,27 @@
 {
-  "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
+  "_name_or_path": "huawei-noah/TinyBERT_General_4L_312D",
+  "adapters": {
+    "adapters": {},
+    "config_map": {},
+    "fusion_config_map": {},
+    "fusions": {}
+  },
   "architectures": [
     "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
+  "cell": {},
   "classifier_dropout": null,
+  "emb_size": 312,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 128,
+  "hidden_size": 312,
   "id2label": {
     "0": "entailment",
     "1": "not_entailment"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 512,
+  "intermediate_size": 1200,
   "label2id": {
     "entailment": "0",
     "not_entailment": "1"
@@ -21,13 +29,15 @@
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 2,
-  "num_hidden_layers": 2,
+  "num_attention_heads": 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": "4.20.1",
+  "transformers_version": "4.17.0",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

logs/1657875633.2928188/events.out.tfevents.1657875633.3130d29d5be1.142.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e91b5e896e35b2bfbd6c57260302613406e8de6f332db6a2cf2ec82bd23d1bd1
+size 4783

logs/1657877289.747412/events.out.tfevents.1657877289.3130d29d5be1.142.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7940361a4e8b35cd8c734783fe1ecf5e8c640ee5521e0d0b778af44473365568
+size 4783

logs/events.out.tfevents.1657875633.3130d29d5be1.142.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1144fd121976ed025eb3d497d0db9f11eb292a3dd9ffc762fdbfd67ce9dd00af
+size 3571

logs/events.out.tfevents.1657877289.3130d29d5be1.142.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0f5d478d06cb5e0492993a37fe7f9c3c379c3c77801f56f0087042db977c91a
+size 4051

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea04600c88de119aa14eebdb5b004ad4c07b728d41a04381cbd55414c1f8cea
-size 17561831
+oid sha256:e963ed457af2b5f745a551a432e25a5b6a10293c5fccb3af447d495219922d33
+size 57436935

special_tokens_map.json

@@ -1,7 +1 @@
-{
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
-}
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -1,14 +1 @@
-{
-  "cls_token": "[CLS]",
-  "do_lower_case": true,
-  "mask_token": "[MASK]",
-  "model_max_length": 512,
-  "name_or_path": "bert-base-uncased",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "special_tokens_map_file": null,
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "unk_token": "[UNK]"
-}
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-uncased", "tokenizer_class": "BertTokenizer"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:992d7eebc18ef81555911bbef662e0dde5c4306806ecd28fe8f037a66bc5eacd
-size 3375
+oid sha256:4d0e38336921e437638b72b7a7ad7c7c75f823a442cc96d52d62ebf541738640
+size 3055