Training in progress, step 500

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.8308823529411765,
+    "eval_f1": 0.8765652951699464,
+    "eval_loss": 0.5847203731536865,
+    "eval_runtime": 2.253,
+    "eval_samples_per_second": 181.094,
+    "eval_steps_per_second": 22.637,
+    "total_flos": 206072701738896.0,
+    "train_loss": 0.3793434802396798,
+    "train_runtime": 166.2323,
+    "train_samples_per_second": 66.197,
+    "train_steps_per_second": 8.284
+}

config.json

@@ -1,12 +1,11 @@
 {
-  "_name_or_path": "distilroberta-base",
+  "_name_or_path": "bert-base-uncased",
   "architectures": [
-    "RobertaForSequenceClassification"
+    "BertForSequenceClassification"
   ],
   "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,
@@ -20,17 +19,17 @@
     "equivalent": "1",
     "not_equivalent": "0"
   },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "roberta",
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
   "num_attention_heads": 12,
-  "num_hidden_layers": 6,
-  "pad_token_id": 1,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.30.2",
-  "type_vocab_size": 1,
+  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 50265
+  "vocab_size": 30522
 }

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.8308823529411765,
+    "eval_f1": 0.8765652951699464,
+    "eval_loss": 0.5847203731536865,
+    "eval_runtime": 2.253,
+    "eval_samples_per_second": 181.094,
+    "eval_steps_per_second": 22.637
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:509f82ff8616a546955672e12ec2e7e4254776ca541fffb944980a151c7898f0
-size 328519925
+oid sha256:53c2e1b3eb9d521fea40f33f1fd4eae788ffda4e50b0124d19c64d49cfb9dbe0
+size 438007925

runs/Jun30_02-24-00_7e1c4afb4004/events.out.tfevents.1688093596.7e1c4afb4004.25826.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35ac3a2867d93573792c5e6f35745c5cd987193fbd31393ff55d9237884d2b90
+size 457

runs/Jun30_02-55-23_7e1c4afb4004/events.out.tfevents.1688093733.7e1c4afb4004.25826.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47d310ada5591ed4f51aae2544192f6f7eef626b3bc8d93d83aad32a4fb64346
+size 4735

special_tokens_map.json

@@ -1,15 +1,7 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -1,15 +1,13 @@
 {
-  "add_prefix_space": false,
-  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "errors": "replace",
-  "mask_token": "<mask>",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
   "model_max_length": 512,
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "tokenizer_class": "RobertaTokenizer",
-  "trim_offsets": true,
-  "unk_token": "<unk>"
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
 }

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 206072701738896.0,
+    "train_loss": 0.3793434802396798,
+    "train_runtime": 166.2323,
+    "train_samples_per_second": 66.197,
+    "train_steps_per_second": 8.284
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30ce5669f004c1bb767cddb59c89c798f0fb2a8c62d6b5791e473499268013d2
+oid sha256:58ff1be6851e9602a98fb801aafef8a1eec3b7a560499ca528c17bc8d1acec9d
 size 3963