Training in progress, epoch 1

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 5.0,
-    "eval_accuracy": 0.696640826873385,
-    "eval_f1": 0.7014550213199207,
-    "eval_loss": 0.8678217530250549,
-    "eval_precision": 0.7038992879292837,
-    "eval_recall": 0.7032174796843771,
-    "eval_runtime": 1.3135,
-    "eval_samples_per_second": 1473.183,
-    "eval_steps_per_second": 92.121,
+    "eval_accuracy": 0.8382428940568476,
+    "eval_f1": 0.8687256347190324,
+    "eval_loss": 0.47584524750709534,
+    "eval_precision": 0.8621741439443422,
+    "eval_recall": 0.8768423220906608,
+    "eval_runtime": 1.702,
+    "eval_samples_per_second": 1136.931,
+    "eval_steps_per_second": 71.095,
     "total_flos": 754719218037696.0,
     "train_loss": 1.1282823350694444,
     "train_runtime": 131.3823,

config.json

@@ -46,5 +46,5 @@
   "transformers_version": "4.28.1",
   "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 39255
+  "vocab_size": 250002
 }

eval_results.json

@@ -1,11 +1,11 @@
 {
     "epoch": 5.0,
-    "eval_accuracy": 0.696640826873385,
-    "eval_f1": 0.7014550213199207,
-    "eval_loss": 0.8678217530250549,
-    "eval_precision": 0.7038992879292837,
-    "eval_recall": 0.7032174796843771,
-    "eval_runtime": 1.3135,
-    "eval_samples_per_second": 1473.183,
-    "eval_steps_per_second": 92.121
+    "eval_accuracy": 0.8382428940568476,
+    "eval_f1": 0.8687256347190324,
+    "eval_loss": 0.47584524750709534,
+    "eval_precision": 0.8621741439443422,
+    "eval_recall": 0.8768423220906608,
+    "eval_runtime": 1.702,
+    "eval_samples_per_second": 1136.931,
+    "eval_steps_per_second": 71.095
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aaf08206fc5e72d884d039a9edc2b0fa7bd8c49b58eff75c53e1038bbd913d07
-size 464857781
+oid sha256:a014662a49ffdcdfa757d77972f7da05a006f1e12dde595c881c788667c70898
+size 1112272565

special_tokens_map.json

@@ -1,51 +1,15 @@
 {
-  "bos_token": {
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "cls_token": {
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
   "mask_token": {
-    "content": "[MASK]",
-    "lstrip": false,
+    "content": "<mask>",
+    "lstrip": true,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "[PAD]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "[UNK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -1,59 +1,20 @@
 {
-  "added_tokens_decoder": {
-    "0": {
-      "content": "[CLS]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "[PAD]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "[SEP]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "3": {
-      "content": "[UNK]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "4": {
-      "content": "[MASK]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "bos_token": "[CLS]",
+  "add_prefix_space": true,
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": false,
-  "eos_token": "[SEP]",
-  "mask_token": "[MASK]",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "model_max_length": 512,
-  "never_split": null,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "unk_token": "[UNK]"
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
 }